diff --git a/.idea/other.xml b/.idea/other.xml new file mode 100644 index 00000000..640fd80b --- /dev/null +++ b/.idea/other.xml @@ -0,0 +1,7 @@ + + + + + \ No newline at end of file diff --git a/02-python-essentials/02.05-indexing-and-slicing.ipynb b/02-python-essentials/02.05-indexing-and-slicing.ipynb index eaad12ad..a21ece10 100644 --- a/02-python-essentials/02.05-indexing-and-slicing.ipynb +++ b/02-python-essentials/02.05-indexing-and-slicing.ipynb @@ -23,7 +23,7 @@ }, { "cell_type": "code", - "execution_count": 1, + "execution_count": 2, "metadata": { "collapsed": false }, @@ -34,7 +34,7 @@ "'h'" ] }, - "execution_count": 1, + "execution_count": 2, "metadata": {}, "output_type": "execute_result" } @@ -119,13 +119,13 @@ { "ename": "IndexError", "evalue": "string index out of range", - "output_type": "error", "traceback": [ "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[1;31mIndexError\u001b[0m Traceback (most recent call last)", "\u001b[1;32m\u001b[0m in \u001b[0;36m\u001b[1;34m()\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0ms\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;36m11\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m", "\u001b[1;31mIndexError\u001b[0m: string index out of range" - ] + ], + "output_type": "error" } ], "source": [ @@ -285,7 +285,7 @@ }, { "cell_type": "code", - "execution_count": 10, + "execution_count": null, "metadata": { "collapsed": false }, @@ -314,7 +314,7 @@ }, { "cell_type": "code", - "execution_count": 11, + "execution_count": 3, "metadata": { "collapsed": false }, @@ -325,7 +325,7 @@ "'hlowrd'" ] }, - "execution_count": 11, + "execution_count": 3, "metadata": {}, "output_type": "execute_result" } @@ -334,6 +334,36 @@ "s[::2]" ] }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "##python的切片产生的是新的对象，对新对象的成员的操作不影响旧对象" + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "[1, 2, 3, 4, 5]" + ] + }, + "execution_count": 1, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "test=[1,2,3,4,5]\n", + "slice1 =test[1:3]\n", + "slice1[0]=4\n", + "test" + ] + }, { "cell_type": "markdown", "metadata": {}, diff --git a/02-python-essentials/02.06-lists.ipynb b/02-python-essentials/02.06-lists.ipynb index 84336636..386696af 100644 --- a/02-python-essentials/02.06-lists.ipynb +++ b/02-python-essentials/02.06-lists.ipynb @@ -327,13 +327,13 @@ { "ename": "TypeError", "evalue": "'str' object does not support item assignment", - "output_type": "error", "traceback": [ "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[1;31mTypeError\u001b[0m Traceback (most recent call last)", "\u001b[1;32m\u001b[0m in \u001b[0;36m\u001b[1;34m()\u001b[0m\n\u001b[0;32m 1\u001b[0m \u001b[0ms\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;34m\"hello world\"\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 2\u001b[0m \u001b[1;31m# 把开头的 h 改成大写\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 3\u001b[1;33m \u001b[0ms\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;36m0\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;34m'H'\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m", "\u001b[1;31mTypeError\u001b[0m: 'str' object does not support item assignment" - ] + ], + "output_type": "error" } ], "source": [ @@ -507,13 +507,13 @@ { "ename": "ValueError", "evalue": "attempt to assign sequence of size 0 to extended slice of size 3", - "output_type": "error", "traceback": [ "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[1;31mValueError\u001b[0m Traceback (most recent call last)", "\u001b[1;32m\u001b[0m in \u001b[0;36m\u001b[1;34m()\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0ma\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;36m2\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;33m[\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m", "\u001b[1;31mValueError\u001b[0m: attempt to assign sequence of size 0 to extended slice of size 3" - ] + ], + "output_type": "error" } ], "source": [ @@ -849,13 +849,13 @@ { "ename": "ValueError", "evalue": "1 is not in list", - "output_type": "error", "traceback": [ "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[1;31mValueError\u001b[0m Traceback (most recent call last)", "\u001b[1;32m\u001b[0m in \u001b[0;36m\u001b[1;34m()\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0ma\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mindex\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;36m1\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m", "\u001b[1;31mValueError\u001b[0m: 1 is not in list" - ] + ], + "output_type": "error" } ], "source": [ @@ -1184,25 +1184,24 @@ }, { "cell_type": "code", - "execution_count": 36, + "execution_count": 4, "metadata": { - "collapsed": false + "collapsed": true }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "[1, 2, 3, 4, 5, 6]\n", - "[6, 5, 4, 3, 2, 1]\n" + "[1, 2, 3, 4, 5, 6]\n[6, 5, 4, 3, 2, 1]\n" ] } ], "source": [ "a = [1, 2, 3, 4, 5, 6]\n", "b = a[::-1]\n", - "print a\n", - "print b" + "print(a)\n", + "print(b)" ] }, { @@ -1214,7 +1213,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 6, "metadata": { "collapsed": true }, @@ -1222,6 +1221,43 @@ "source": [ "a.sort?" ] + }, + { + "cell_type": "heading", + "metadata": {}, + "level": 4, + "source": [ + "列表的切片与步长:\n", + "python中提供两种索引：从左向右 0 ..... index-1 从右向左 -1 .... -index; \n", + " 若 step > 0, 则表示从左向右进行切片。此时，start必须小于end才有结果，否则为空。例如: s[0,: 5: 2]的结果是'ace'\n", + " 若 step < 0, 则表示从右向左进行切片。 此时，start必须大于end才有结果，否则为空。列如: s[5: 0: -1]的结果是'fedcb'\n" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[6, 5, 4, 3, 2, 1]\n" + ] + } + ], + "source": [ + "a = [1, 2, 3, 4, 5, 6]\n", + "b = a[::-1] \n", + "print(b)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] } ], "metadata": { diff --git a/03-numpy/numpy_normal_array.ipynb b/03-numpy/numpy_normal_array.ipynb new file mode 100644 index 00000000..160ede66 --- /dev/null +++ b/03-numpy/numpy_normal_array.ipynb @@ -0,0 +1,310 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "np.linalg.norm(求范数)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "x_norm=np.linalg.norm(x, ord=None, axis=None, keepdims=False) " + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "![image.png](attachment:image.png)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "③axis：处理类型\n", + "\n", + "axis=1表示按行向量处理，求多个行向量的范数\n", + "\n", + "axis=0表示按列向量处理，求多个列向量的范数\n", + "\n", + "axis=None表示矩阵范数。\n", + "\n", + "④keepding：是否保持矩阵的二维特性\n", + "\n", + "True表示保持矩阵的二维特性，False相反" + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "默认参数(矩阵2范数，不保留矩阵二维特性)： 8.831760866327848\n", + "矩阵2范数，保留矩阵二维特性： [[8.83176087]]\n", + "矩阵每个行向量求向量的2范数： [[5. ]\n", + " [7.28010989]]\n", + "矩阵每个列向量求向量的2范数： [[1. 6.70820393 5.65685425]]\n", + "矩阵1范数： [[9.]]\n", + "矩阵2范数： [[8.70457079]]\n", + "矩阵∞范数： [[11.]]\n", + "矩阵每个行向量求向量的1范数： [[ 7.]\n", + " [11.]]\n" + ] + } + ], + "source": [ + "import numpy as np \n", + "x = np.array([ \n", + " [0, 3, 4], \n", + " [1, 6, 4]]) \n", + "#默认参数ord=None，axis=None，keepdims=False \n", + "print (\"默认参数(矩阵2范数，不保留矩阵二维特性)：\",np.linalg.norm(x))\n", + "print(\"矩阵2范数，保留矩阵二维特性：\",np.linalg.norm(x,keepdims=True)) \n", + " \n", + "print(\"矩阵每个行向量求向量的2范数：\",np.linalg.norm(x,axis=1,keepdims=True)) \n", + "print(\"矩阵每个列向量求向量的2范数：\",np.linalg.norm(x,axis=0,keepdims=True)) \n", + " \n", + "print(\"矩阵1范数：\",np.linalg.norm(x,ord=1,keepdims=True)) \n", + "print(\"矩阵2范数：\",np.linalg.norm(x,ord=2,keepdims=True)) \n", + "print(\"矩阵∞范数：\",np.linalg.norm(x,ord=np.inf,keepdims=True)) \n", + " \n", + "print(\"矩阵每个行向量求向量的1范数：\",np.linalg.norm(x,ord=1,axis=1,keepdims=True))" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "#####numpy 数组 行列比较" + ] + }, + { + "cell_type": "code", + "execution_count": 27, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "(3,)\n", + "[0 3 4]\n" + ] + } + ], + "source": [ + "x1 = np.array([0, 3, 4]) ###秩为3的数组\n", + "print(x1.shape)\n", + "print(x1)" + ] + }, + { + "cell_type": "code", + "execution_count": 28, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "(1, 3)\n", + "[[0 3 4]]\n" + ] + } + ], + "source": [ + "x2 = np.array([[0, 3, 4]]) ###矩阵\n", + "print(x2.shape)\n", + "print(x2)" + ] + }, + { + "cell_type": "code", + "execution_count": 21, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "(2, 3)\n" + ] + } + ], + "source": [ + "x3 = np.array([[0, 3, 4],[1, 6, 4]])\n", + "print(x3.shape)" + ] + }, + { + "cell_type": "code", + "execution_count": 26, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "(1, 2, 3)\n", + "[[0 3 4 1 6 4]]\n" + ] + } + ], + "source": [ + "x4 = np.array([[[0, 3, 4],[1, 6, 4]]])\n", + "print(x4.shape)\n", + "print(x4.reshape(x4.shape[0],-1))" + ] + }, + { + "cell_type": "code", + "execution_count": 29, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[[0.]\n", + " [0.]\n", + " [0.]\n", + " [0.]]\n" + ] + } + ], + "source": [ + "### 初始化数组\n", + "w = np.zeros((4, 1))\n", + "print(w)" + ] + }, + { + "cell_type": "code", + "execution_count": 40, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "(3, 3, 2)\n", + "[[0.67826139 0.29380381 0.90714982 0.52835647 0.4215251 0.45017551]\n", + " [0.92814219 0.96677647 0.85304703 0.52351845 0.19981397 0.27417313]\n", + " [0.60659855 0.00533165 0.10820313 0.49978937 0.34144279 0.94630077]]\n", + "(3, 3, 2)\n" + ] + } + ], + "source": [ + "x4 = np.array([[[ 0.67826139, 0.29380381],\n", + " [ 0.90714982, 0.52835647],\n", + " [ 0.4215251 , 0.45017551]],\n", + "\n", + " [[ 0.92814219, 0.96677647],\n", + " [ 0.85304703, 0.52351845],\n", + " [ 0.19981397, 0.27417313]],\n", + "\n", + " [[ 0.60659855, 0.00533165],\n", + " [ 0.10820313, 0.49978937],\n", + " [ 0.34144279, 0.94630077]]])\n", + "print(x4.shape)\n", + "print(x4.reshape(x4.shape[0],-1))\n", + "print(np.squeeze(x4).shape)" + ] + }, + { + "cell_type": "code", + "execution_count": 36, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "(1, 3, 1)\n" + ] + } + ], + "source": [ + "###测试np.squeeze 的功能, ### 从数组的形状中删除单维条目，即把shape中为1的维度去掉\n", + "x5 = np.array([[[0], [1], [2]]])\n", + "print(x5.shape)" + ] + }, + { + "cell_type": "code", + "execution_count": 39, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "(3,)\n" + ] + } + ], + "source": [ + "X6 = np.squeeze(x5)\n", + "print(X6.shape)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "\n", + "print(x)\n", + "\"\"\"\n", + "x=\n", + "\n", + "[[[0]\n", + " [1]\n", + " [2]]]\n", + "\"\"\"\n", + "print(x.shape) # (1, 3, 1)\n", + "\n", + "x1 = np.squeeze(x) # 从数组的形状中删除单维条目，即把shape中为1的维度去掉\n", + "\n", + "\n", + "print(x1) # [0 1 2]\n", + "print(x1.shape) # (3,)" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.6.4" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +} diff --git a/12-pandas/12.04-pandas-for-dataanalysis-ch05.ipynb b/12-pandas/12.04-pandas-for-dataanalysis-ch05.ipynb new file mode 100644 index 00000000..ad305c4e --- /dev/null +++ b/12-pandas/12.04-pandas-for-dataanalysis-ch05.ipynb @@ -0,0 +1,571 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": { + "collapsed": true + }, + "source": [ + "###汇总和计算统计" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": {}, + "outputs": [], + "source": [ + "import numpy as np\n", + "import pandas as pd\n" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
onetwo
a1.0NaN
b2.0NaN
cNaNNaN
d2.04.0
\n", + "
" + ], + "text/plain": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
onetwo
a1.0NaN
b2.0NaN
cNaNNaN
d2.04.0
\n", + "
" + ] + }, + "execution_count": 3, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df = pd.DataFrame([[1,np.nan],[2,np.nan],[np.nan,np.nan],[2,4]], index=['a','b','c','d'], columns=['one','two'])\n", + "df" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "a 1.0\nb 2.0\nc 0.0\nd 6.0\ndtype: float64" + ] + }, + "execution_count": 8, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df.sum(axis=1)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "###执行sum, NA会被自动过滤，除非加上skipna =False" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "a NaN\nb NaN\nc NaN\nd 6.0\ndtype: float64" + ] + }, + "execution_count": 7, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df.sum(axis=1, skipna=False)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [] + }, + { + "cell_type": "code", + "execution_count": 11, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
onetwo
a1.0NaN
b3.0NaN
cNaNNaN
d5.04.0
\n", + "
" + ], + "text/plain": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
onetwo
a1.0NaN
b3.0NaN
cNaNNaN
d5.04.0
\n", + "
" + ] + }, + "execution_count": 11, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df.cumsum()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "![avatar](file:///E:/study/mechain-learning/python-node/notes-python/12-pandas/5-10-02.png)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "![avatar](file:///E:/study/mechain-learning/python-node/notes-python/12-pandas/5-10-1.png)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "###唯一值，值计算" + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "array(['a', 'c', 'd', 'e'], dtype=object)" + ] + }, + "execution_count": 18, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "obj = pd.Series(['a','c','d','e','a','c'])\n", + "uniques = obj.unique() ##\n", + "uniques" + ] + }, + { + "cell_type": "code", + "execution_count": 21, + "metadata": { + "collapsed": true + }, + "outputs": [ + { + "data": { + "text/plain": [ + "a 2\nc 2\nd 1\ne 1\ndtype: int64" + ] + }, + "execution_count": 21, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "obj.value_counts() ###计算出现的频次" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "###isin 判断是否是集合成员" + ] + }, + { + "cell_type": "code", + "execution_count": 22, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "0 True\n1 True\n2 False\n3 False\n4 True\n5 True\ndtype: bool" + ] + }, + "execution_count": 22, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "mask = obj.isin(['a','c'])\n", + "mask" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "![avatar](file:///E:/study/mechain-learning/python-node/notes-python/12-pandas/5-10-3.png)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "##处理缺失数据" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "![avatar](file:///E:/study/mechain-learning/python-node/notes-python/12-pandas/5-10-4.png)" + ] + }, + { + "cell_type": "code", + "execution_count": 27, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
onetwo
d2.04.0
\n", + "
" + ], + "text/plain": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
onetwo
d2.04.0
\n", + "
" + ] + }, + "execution_count": 27, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df.dropna() ### DataFrame 删除任何一行 ， 其中包含NA" + ] + }, + { + "cell_type": "code", + "execution_count": 25, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "d 4.0\nName: two, dtype: float64" + ] + }, + "execution_count": 25, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df['two'].dropna() ###Series 删除NA" + ] + }, + { + "cell_type": "code", + "execution_count": 30, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "d 4.0\nName: two, dtype: float64" + ] + }, + "execution_count": 30, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "###Series 的notnull 也能实现dropna 的功能\n", + "data = df['two']\n", + "data[data.notnull()]\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 2", + "language": "python", + "name": "python2" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 2 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython2", + "version": "2.7.6" + } + }, + "nbformat": 4, + "nbformat_minor": 0 +} diff --git a/12-pandas/12.05-pandas-for-dataanalysis-ch07.ipynb b/12-pandas/12.05-pandas-for-dataanalysis-ch07.ipynb new file mode 100644 index 00000000..9c83110a --- /dev/null +++ b/12-pandas/12.05-pandas-for-dataanalysis-ch07.ipynb @@ -0,0 +1,1280 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": { + "collapsed": true + }, + "source": [ + "##合并数据集" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "###数据集的merge 和join" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "![avatar](file:///E:/study/mechain-learning/python-node/notes-python/12-pandas/5-10-5.png)" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": {}, + "outputs": [], + "source": [ + "import numpy as np\n", + "import pandas as pd" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": { + "collapsed": true + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
datakey
01b
12b
23c
34c
45a
56d
\n", + "
" + ], + "text/plain": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
datakey
01b
12b
23c
34c
45a
56d
\n", + "
" + ] + }, + "execution_count": 8, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df1 = pd.DataFrame({'key':['b','b','c','c','a','d'],'data':[1,2,3,4,5,6]})\n", + "df1" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
datakey
01b
12c
23a
\n", + "
" + ], + "text/plain": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
datakey
01b
12c
23a
\n", + "
" + ] + }, + "execution_count": 9, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df2 = pd.DataFrame({'key':['b','c','a'],'data':[1,2,3]})\n", + "df2" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
data_xkeydata_y
01b1
12b1
23c2
34c2
45a3
\n", + "
" + ], + "text/plain": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
data_xkeydata_y
01b1
12b1
23c2
34c2
45a3
\n", + "
" + ] + }, + "execution_count": 11, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "pd.merge(df1,df2, on='key') ###merge默认为交集" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
data_xkeydata_y
01b1.0
12b1.0
23c2.0
34c2.0
45a3.0
56dNaN
\n", + "
" + ], + "text/plain": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
data_xkeydata_y
01b1.0
12b1.0
23c2.0
34c2.0
45a3.0
56dNaN
\n", + "
" + ] + }, + "execution_count": 13, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "pd.merge(df1,df2, how='outer', on=\"key\") ###用how 指定连接方式" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "###索引上的合并" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
keyvalue
0a0
1b1
2c2
3d3
\n", + "
" + ], + "text/plain": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
keyvalue
0a0
1b1
2c2
3d3
\n", + "
" + ] + }, + "execution_count": 15, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "left1 = pd.DataFrame({'key':['a','b','c','d'],'value':range(4)})\n", + "left1" + ] + }, + { + "cell_type": "code", + "execution_count": 19, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
group_val
a3.5
b7.0
\n", + "
" + ], + "text/plain": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
group_val
a3.5
b7.0
\n", + "
" + ] + }, + "execution_count": 19, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "right1 = pd.DataFrame({'group_val':[3.5,7]},index=['a','b'])\n", + "right1" + ] + }, + { + "cell_type": "code", + "execution_count": 20, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
keyvaluegroup_val
0a03.5
1b17.0
\n", + "
" + ], + "text/plain": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
keyvaluegroup_val
0a03.5
1b17.0
\n", + "
" + ] + }, + "execution_count": 20, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "pd.merge(left1,right1,left_on='key',right_index=True)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "##轴向连接" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "![avatar](file:///E:/study/mechain-learning/python-node/notes-python/12-pandas/5-10-6.png)" + ] + }, + { + "cell_type": "code", + "execution_count": 22, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "a 0\nb 1\nc 2\nd 3\ne 4\nf 5\ng 6\ndtype: int64" + ] + }, + "execution_count": 22, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "###concat 默认在axis =0 上进行连接，\n", + "s1=pd.Series([0,1], index=['a','b'])\n", + "s2=pd.Series([2,3,4], index=['c','d','e'])\n", + "s3=pd.Series([5,6],index=['f','g'])\n", + "pd.concat([s1,s2,s3]) " + ] + }, + { + "cell_type": "code", + "execution_count": 23, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
012
a0.0NaNNaN
b1.0NaNNaN
cNaN2.0NaN
dNaN3.0NaN
eNaN4.0NaN
fNaNNaN5.0
gNaNNaN6.0
\n", + "
" + ], + "text/plain": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
012
a0.0NaNNaN
b1.0NaNNaN
cNaN2.0NaN
dNaN3.0NaN
eNaN4.0NaN
fNaNNaN5.0
gNaNNaN6.0
\n", + "
" + ] + }, + "execution_count": 23, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "pd.concat([s1,s2,s3],axis=1) " + ] + }, + { + "cell_type": "code", + "execution_count": 24, + "metadata": {}, + "outputs": [], + "source": [ + "pd.concat([s1,s2,s3],axis=1, join='inner') " + ] + }, + { + "cell_type": "code", + "execution_count": 25, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "one a 0\n b 1\ntwo c 2\n d 3\n e 4\nthree f 5\n g 6\ndtype: int64" + ] + }, + "execution_count": 25, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "pd.concat([s1,s2,s3],keys=['one','two','three'] ) ###使用keys 创建层次化索引" + ] + }, + { + "cell_type": "code", + "execution_count": 26, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
onetwothree
a0.0NaNNaN
b1.0NaNNaN
cNaN2.0NaN
dNaN3.0NaN
eNaN4.0NaN
fNaNNaN5.0
gNaNNaN6.0
\n", + "
" + ], + "text/plain": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
onetwothree
a0.0NaNNaN
b1.0NaNNaN
cNaN2.0NaN
dNaN3.0NaN
eNaN4.0NaN
fNaNNaN5.0
gNaNNaN6.0
\n", + "
" + ] + }, + "execution_count": 26, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "pd.concat([s1,s2,s3],axis=1,keys=['one','two','three']) ###axis=1 时形成一个DataFrame" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 2", + "language": "python", + "name": "python2" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 2 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython2", + "version": "2.7.6" + } + }, + "nbformat": 4, + "nbformat_minor": 0 +} diff --git a/12-pandas/5-10-02.png b/12-pandas/5-10-02.png new file mode 100644 index 00000000..c2333773 Binary files /dev/null and b/12-pandas/5-10-02.png differ diff --git a/12-pandas/5-10-1.png b/12-pandas/5-10-1.png new file mode 100644 index 00000000..9028b091 Binary files /dev/null and b/12-pandas/5-10-1.png differ diff --git a/12-pandas/5-10-3.png b/12-pandas/5-10-3.png new file mode 100644 index 00000000..6ba384f6 Binary files /dev/null and b/12-pandas/5-10-3.png differ diff --git a/12-pandas/5-10-4.png b/12-pandas/5-10-4.png new file mode 100644 index 00000000..66e96821 Binary files /dev/null and b/12-pandas/5-10-4.png differ diff --git a/12-pandas/5-10-5.png b/12-pandas/5-10-5.png new file mode 100644 index 00000000..61be9903 Binary files /dev/null and b/12-pandas/5-10-5.png differ diff --git a/12-pandas/5-10-6.png b/12-pandas/5-10-6.png new file mode 100644 index 00000000..b6d0c891 Binary files /dev/null and b/12-pandas/5-10-6.png differ diff --git a/12-pandas/Pandas.ipynb b/12-pandas/Pandas.ipynb new file mode 100644 index 00000000..8efdedeb --- /dev/null +++ b/12-pandas/Pandas.ipynb @@ -0,0 +1,7586 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# pandas" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## 引入约定" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "import pandas as pd\n", + "import numpy as np" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "from pandas import DataFrame,Series # 数据框、一维数组" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Series 一维数组" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "arr=np.arange(20) #建立一个数组" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "series=Series(arr) #一个一维数组对象" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "0 0\n", + "1 1\n", + "2 2\n", + "3 3\n", + "4 4\n", + "5 5\n", + "6 6\n", + "7 7\n", + "8 8\n", + "9 9\n", + "10 10\n", + "11 11\n", + "12 12\n", + "13 13\n", + "14 14\n", + "15 15\n", + "16 16\n", + "17 17\n", + "18 18\n", + "19 19\n", + "dtype: int32" + ] + }, + "execution_count": 10, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "series" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 查看索引列" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "RangeIndex(start=0, stop=20, step=1)" + ] + }, + "execution_count": 11, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "series.index" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 数据index绑定" + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "series1=Series([70,89,67],index=['张三','李四','王屋']) #index实现索引的绑定" + ] + }, + { + "cell_type": "code", + "execution_count": 19, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "张三 70\n", + "李四 89\n", + "王屋 67\n", + "dtype: int64" + ] + }, + "execution_count": 19, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "series1" + ] + }, + { + "cell_type": "code", + "execution_count": 20, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "array([70, 89, 67], dtype=int64)" + ] + }, + "execution_count": 20, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "series1.values #查看数据列" + ] + }, + { + "cell_type": "code", + "execution_count": 21, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "dtype('int64')" + ] + }, + "execution_count": 21, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "series1.dtype #查看数据类型" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## 缺失值的检测" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "* isnull" + ] + }, + { + "cell_type": "code", + "execution_count": 23, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "Series2=Series([1,2,3,4,np.NaN,5,6,8,9])" + ] + }, + { + "cell_type": "code", + "execution_count": 24, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "0 1.0\n", + "1 2.0\n", + "2 3.0\n", + "3 4.0\n", + "4 NaN\n", + "5 5.0\n", + "6 6.0\n", + "7 8.0\n", + "8 9.0\n", + "dtype: float64" + ] + }, + "execution_count": 24, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "Series2" + ] + }, + { + "cell_type": "code", + "execution_count": 28, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "0 False\n", + "1 False\n", + "2 False\n", + "3 False\n", + "4 True\n", + "5 False\n", + "6 False\n", + "7 False\n", + "8 False\n", + "dtype: bool" + ] + }, + "execution_count": 28, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "Series2.isnull() # 为空的元素，返回True" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "* notnull" + ] + }, + { + "cell_type": "code", + "execution_count": 27, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "0 True\n", + "1 True\n", + "2 True\n", + "3 True\n", + "4 False\n", + "5 True\n", + "6 True\n", + "7 True\n", + "8 True\n", + "dtype: bool" + ] + }, + "execution_count": 27, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "Series2.notnull() # 不为空的元素，返回True" + ] + }, + { + "cell_type": "code", + "execution_count": 41, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "s1=Series([1,2,3,4,5],index=['a','b','c','d','e'])" + ] + }, + { + "cell_type": "code", + "execution_count": 42, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "s2=Series([1,2,3,4,5],index=['b','a','e','c','d'])" + ] + }, + { + "cell_type": "code", + "execution_count": 43, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "b 1\n", + "a 2\n", + "e 3\n", + "c 4\n", + "d 5\n", + "dtype: int64" + ] + }, + "execution_count": 43, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s2" + ] + }, + { + "cell_type": "code", + "execution_count": 44, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "a 2\n", + "b 2\n", + "c 12\n", + "d 20\n", + "e 15\n", + "dtype: int64" + ] + }, + "execution_count": 44, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s1*s2" + ] + }, + { + "cell_type": "code", + "execution_count": 45, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "a 2\n", + "b 2\n", + "c 12\n", + "d 20\n", + "e 15\n", + "dtype: int64" + ] + }, + "execution_count": 45, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s2*s1" + ] + }, + { + "cell_type": "code", + "execution_count": 46, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "a 1\n", + "b 2\n", + "c 3\n", + "d 4\n", + "e 5\n", + "dtype: int64" + ] + }, + "execution_count": 46, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s1" + ] + }, + { + "cell_type": "code", + "execution_count": 47, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "b 1\n", + "a 2\n", + "e 3\n", + "c 4\n", + "d 5\n", + "dtype: int64" + ] + }, + "execution_count": 47, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s2" + ] + }, + { + "cell_type": "code", + "execution_count": 52, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "df=DataFrame([[1,2,3],[3,4,5]])" + ] + }, + { + "cell_type": "code", + "execution_count": 53, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
012
0123
1345
\n", + "
" + ], + "text/plain": [ + " 0 1 2\n", + "0 1 2 3\n", + "1 3 4 5" + ] + }, + "execution_count": 53, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df" + ] + }, + { + "cell_type": "code", + "execution_count": 66, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "df=DataFrame([[1,2,3],[3,4,5]],index=[['a','b']])" + ] + }, + { + "cell_type": "code", + "execution_count": 67, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
012
a123
b345
\n", + "
" + ], + "text/plain": [ + " 0 1 2\n", + "a 1 2 3\n", + "b 3 4 5" + ] + }, + "execution_count": 67, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df" + ] + }, + { + "cell_type": "code", + "execution_count": 69, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "2" + ] + }, + "execution_count": 69, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df[1]['a'] #取出第2列，第'a'行的数据，从列开始取值" + ] + }, + { + "cell_type": "code", + "execution_count": 88, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
012
b345
\n", + "
" + ], + "text/plain": [ + " 0 1 2\n", + "b 3 4 5" + ] + }, + "execution_count": 88, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df[1:] # 如果使用切片，那么从行开始取值" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## 索引" + ] + }, + { + "cell_type": "code", + "execution_count": 139, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "s1=DataFrame({'python':Series([10,20,30]),'JAVA':Series([20,30,40]),'C++':Series([50,50,20])})" + ] + }, + { + "cell_type": "code", + "execution_count": 140, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
C++JAVApython
1503020
2204030
\n", + "
" + ], + "text/plain": [ + " C++ JAVA python\n", + "1 50 30 20\n", + "2 20 40 30" + ] + }, + "execution_count": 140, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s1[1:] # 缩减写法" + ] + }, + { + "cell_type": "code", + "execution_count": 141, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
C++JAVApython
1503020
2204030
\n", + "
" + ], + "text/plain": [ + " C++ JAVA python\n", + "1 50 30 20\n", + "2 20 40 30" + ] + }, + "execution_count": 141, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s1.ix[1:] #完整使用ix的写法" + ] + }, + { + "cell_type": "code", + "execution_count": 142, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "50" + ] + }, + "execution_count": 142, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s1['C++'][1] # 此时括号内的所有的内容，都代表的是索引名" + ] + }, + { + "cell_type": "code", + "execution_count": 143, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "C++ 50\n", + "JAVA 20\n", + "python 10\n", + "Name: 0, dtype: int64" + ] + }, + "execution_count": 143, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s1.ix[0]" + ] + }, + { + "cell_type": "code", + "execution_count": 144, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "s1.index=[2,3,4]" + ] + }, + { + "cell_type": "code", + "execution_count": 131, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "s1.columns=['Java', 'c', 'Vb']" + ] + }, + { + "cell_type": "code", + "execution_count": 156, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "n1=np.random.random((20,6))" + ] + }, + { + "cell_type": "code", + "execution_count": 157, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "array([[ 0.99190107, 0.83899796, 0.77560361, 0.89208866, 0.10279437,\n", + " 0.63677103],\n", + " [ 0.38946758, 0.24701241, 0.45771465, 0.14212242, 0.34648821,\n", + " 0.27123221],\n", + " [ 0.07431452, 0.18723348, 0.0369723 , 0.93616627, 0.72908362,\n", + " 0.59206907],\n", + " [ 0.79390374, 0.71684542, 0.96050877, 0.97655782, 0.92938416,\n", + " 0.36940984],\n", + " [ 0.13306575, 0.53454341, 0.56422975, 0.20828138, 0.234824 ,\n", + " 0.51994997],\n", + " [ 0.3974471 , 0.1153042 , 0.62160545, 0.74743163, 0.78913959,\n", + " 0.27984444],\n", + " [ 0.91773259, 0.73981198, 0.46308993, 0.9060514 , 0.47368118,\n", + " 0.75988065],\n", + " [ 0.23948813, 0.45337269, 0.08216876, 0.19112875, 0.27155616,\n", + " 0.20820083],\n", + " [ 0.99480795, 0.41995272, 0.87277478, 0.78213346, 0.55853741,\n", + " 0.32385912],\n", + " [ 0.38955016, 0.53699963, 0.94141653, 0.08143306, 0.90953705,\n", + " 0.27816224],\n", + " [ 0.67279955, 0.3494044 , 0.57620841, 0.92253732, 0.4317804 ,\n", + " 0.79031195],\n", + " [ 0.05277482, 0.65817173, 0.33469411, 0.15384897, 0.45439839,\n", + " 0.88991295],\n", + " [ 0.37863224, 0.32684272, 0.87614634, 0.13681068, 0.47492178,\n", + " 0.88578309],\n", + " [ 0.1320312 , 0.15179701, 0.00451204, 0.55289387, 0.00643423,\n", + " 0.04115994],\n", + " [ 0.43898922, 0.48510277, 0.69318234, 0.46558743, 0.10603275,\n", + " 0.25132022],\n", + " [ 0.68339417, 0.15860369, 0.16826826, 0.93536103, 0.4876899 ,\n", + " 0.65678234],\n", + " [ 0.10113181, 0.79764135, 0.58032216, 0.44215008, 0.73862162,\n", + " 0.9755108 ],\n", + " [ 0.18643756, 0.66543467, 0.26965587, 0.85237428, 0.86781072,\n", + " 0.17572564],\n", + " [ 0.75548088, 0.58533308, 0.87649421, 0.05180442, 0.74405802,\n", + " 0.87997703],\n", + " [ 0.75866828, 0.25024404, 0.7214714 , 0.47168856, 0.82370921,\n", + " 0.57005914]])" + ] + }, + "execution_count": 157, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "n1" + ] + }, + { + "cell_type": "code", + "execution_count": 158, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "s2=DataFrame(n1)" + ] + }, + { + "cell_type": "code", + "execution_count": 159, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
012345
00.9919010.8389980.7756040.8920890.1027940.636771
10.3894680.2470120.4577150.1421220.3464880.271232
20.0743150.1872330.0369720.9361660.7290840.592069
30.7939040.7168450.9605090.9765580.9293840.369410
40.1330660.5345430.5642300.2082810.2348240.519950
50.3974470.1153040.6216050.7474320.7891400.279844
60.9177330.7398120.4630900.9060510.4736810.759881
70.2394880.4533730.0821690.1911290.2715560.208201
80.9948080.4199530.8727750.7821330.5585370.323859
90.3895500.5370000.9414170.0814330.9095370.278162
100.6728000.3494040.5762080.9225370.4317800.790312
110.0527750.6581720.3346940.1538490.4543980.889913
120.3786320.3268430.8761460.1368110.4749220.885783
130.1320310.1517970.0045120.5528940.0064340.041160
140.4389890.4851030.6931820.4655870.1060330.251320
150.6833940.1586040.1682680.9353610.4876900.656782
160.1011320.7976410.5803220.4421500.7386220.975511
170.1864380.6654350.2696560.8523740.8678110.175726
180.7554810.5853330.8764940.0518040.7440580.879977
190.7586680.2502440.7214710.4716890.8237090.570059
\n", + "
" + ], + "text/plain": [ + " 0 1 2 3 4 5\n", + "0 0.991901 0.838998 0.775604 0.892089 0.102794 0.636771\n", + "1 0.389468 0.247012 0.457715 0.142122 0.346488 0.271232\n", + "2 0.074315 0.187233 0.036972 0.936166 0.729084 0.592069\n", + "3 0.793904 0.716845 0.960509 0.976558 0.929384 0.369410\n", + "4 0.133066 0.534543 0.564230 0.208281 0.234824 0.519950\n", + "5 0.397447 0.115304 0.621605 0.747432 0.789140 0.279844\n", + "6 0.917733 0.739812 0.463090 0.906051 0.473681 0.759881\n", + "7 0.239488 0.453373 0.082169 0.191129 0.271556 0.208201\n", + "8 0.994808 0.419953 0.872775 0.782133 0.558537 0.323859\n", + "9 0.389550 0.537000 0.941417 0.081433 0.909537 0.278162\n", + "10 0.672800 0.349404 0.576208 0.922537 0.431780 0.790312\n", + "11 0.052775 0.658172 0.334694 0.153849 0.454398 0.889913\n", + "12 0.378632 0.326843 0.876146 0.136811 0.474922 0.885783\n", + "13 0.132031 0.151797 0.004512 0.552894 0.006434 0.041160\n", + "14 0.438989 0.485103 0.693182 0.465587 0.106033 0.251320\n", + "15 0.683394 0.158604 0.168268 0.935361 0.487690 0.656782\n", + "16 0.101132 0.797641 0.580322 0.442150 0.738622 0.975511\n", + "17 0.186438 0.665435 0.269656 0.852374 0.867811 0.175726\n", + "18 0.755481 0.585333 0.876494 0.051804 0.744058 0.879977\n", + "19 0.758668 0.250244 0.721471 0.471689 0.823709 0.570059" + ] + }, + "execution_count": 159, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s2" + ] + }, + { + "cell_type": "code", + "execution_count": 164, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
012345
00.9919010.8389980.7756040.8920890.1027940.636771
10.3894680.2470120.4577150.1421220.3464880.271232
20.0743150.1872330.0369720.9361660.7290840.592069
30.7939040.7168450.9605090.9765580.9293840.369410
40.1330660.5345430.5642300.2082810.2348240.519950
\n", + "
" + ], + "text/plain": [ + " 0 1 2 3 4 5\n", + "0 0.991901 0.838998 0.775604 0.892089 0.102794 0.636771\n", + "1 0.389468 0.247012 0.457715 0.142122 0.346488 0.271232\n", + "2 0.074315 0.187233 0.036972 0.936166 0.729084 0.592069\n", + "3 0.793904 0.716845 0.960509 0.976558 0.929384 0.369410\n", + "4 0.133066 0.534543 0.564230 0.208281 0.234824 0.519950" + ] + }, + "execution_count": 164, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s2.head() # 默认为前5行数据，可以自定义显示行数" + ] + }, + { + "cell_type": "code", + "execution_count": 161, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
012345
150.6833940.1586040.1682680.9353610.4876900.656782
160.1011320.7976410.5803220.4421500.7386220.975511
170.1864380.6654350.2696560.8523740.8678110.175726
180.7554810.5853330.8764940.0518040.7440580.879977
190.7586680.2502440.7214710.4716890.8237090.570059
\n", + "
" + ], + "text/plain": [ + " 0 1 2 3 4 5\n", + "15 0.683394 0.158604 0.168268 0.935361 0.487690 0.656782\n", + "16 0.101132 0.797641 0.580322 0.442150 0.738622 0.975511\n", + "17 0.186438 0.665435 0.269656 0.852374 0.867811 0.175726\n", + "18 0.755481 0.585333 0.876494 0.051804 0.744058 0.879977\n", + "19 0.758668 0.250244 0.721471 0.471689 0.823709 0.570059" + ] + }, + "execution_count": 161, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s2.tail() # 默认为后5行数据，可以自定义显示行数" + ] + }, + { + "cell_type": "code", + "execution_count": 165, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
012345
count20.00000020.00000020.00000020.00000020.00000020.000000
mean0.4741010.4609320.5438520.5424230.5240240.517796
std0.3211710.2306970.3088360.3462240.2853900.284205
min0.0527750.1153040.0045120.0518040.0064340.041160
25%0.1730950.2494360.3184350.1818090.3277550.276430
50%0.3934990.4692380.5782650.5122910.4813060.545005
75%0.7562780.6599870.7998960.8955790.7553280.767488
max0.9948080.8389980.9605090.9765580.9293840.975511
\n", + "
" + ], + "text/plain": [ + " 0 1 2 3 4 5\n", + "count 20.000000 20.000000 20.000000 20.000000 20.000000 20.000000\n", + "mean 0.474101 0.460932 0.543852 0.542423 0.524024 0.517796\n", + "std 0.321171 0.230697 0.308836 0.346224 0.285390 0.284205\n", + "min 0.052775 0.115304 0.004512 0.051804 0.006434 0.041160\n", + "25% 0.173095 0.249436 0.318435 0.181809 0.327755 0.276430\n", + "50% 0.393499 0.469238 0.578265 0.512291 0.481306 0.545005\n", + "75% 0.756278 0.659987 0.799896 0.895579 0.755328 0.767488\n", + "max 0.994808 0.838998 0.960509 0.976558 0.929384 0.975511" + ] + }, + "execution_count": 165, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s2.describe() #快速统计汇总" + ] + }, + { + "cell_type": "code", + "execution_count": 166, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
012345678910111213141516171819
00.9919010.3894680.0743150.7939040.1330660.3974470.9177330.2394880.9948080.3895500.6728000.0527750.3786320.1320310.4389890.6833940.1011320.1864380.7554810.758668
10.8389980.2470120.1872330.7168450.5345430.1153040.7398120.4533730.4199530.5370000.3494040.6581720.3268430.1517970.4851030.1586040.7976410.6654350.5853330.250244
20.7756040.4577150.0369720.9605090.5642300.6216050.4630900.0821690.8727750.9414170.5762080.3346940.8761460.0045120.6931820.1682680.5803220.2696560.8764940.721471
30.8920890.1421220.9361660.9765580.2082810.7474320.9060510.1911290.7821330.0814330.9225370.1538490.1368110.5528940.4655870.9353610.4421500.8523740.0518040.471689
40.1027940.3464880.7290840.9293840.2348240.7891400.4736810.2715560.5585370.9095370.4317800.4543980.4749220.0064340.1060330.4876900.7386220.8678110.7440580.823709
50.6367710.2712320.5920690.3694100.5199500.2798440.7598810.2082010.3238590.2781620.7903120.8899130.8857830.0411600.2513200.6567820.9755110.1757260.8799770.570059
\n", + "
" + ], + "text/plain": [ + " 0 1 2 3 4 5 6 \\\n", + "0 0.991901 0.389468 0.074315 0.793904 0.133066 0.397447 0.917733 \n", + "1 0.838998 0.247012 0.187233 0.716845 0.534543 0.115304 0.739812 \n", + "2 0.775604 0.457715 0.036972 0.960509 0.564230 0.621605 0.463090 \n", + "3 0.892089 0.142122 0.936166 0.976558 0.208281 0.747432 0.906051 \n", + "4 0.102794 0.346488 0.729084 0.929384 0.234824 0.789140 0.473681 \n", + "5 0.636771 0.271232 0.592069 0.369410 0.519950 0.279844 0.759881 \n", + "\n", + " 7 8 9 10 11 12 13 \\\n", + "0 0.239488 0.994808 0.389550 0.672800 0.052775 0.378632 0.132031 \n", + "1 0.453373 0.419953 0.537000 0.349404 0.658172 0.326843 0.151797 \n", + "2 0.082169 0.872775 0.941417 0.576208 0.334694 0.876146 0.004512 \n", + "3 0.191129 0.782133 0.081433 0.922537 0.153849 0.136811 0.552894 \n", + "4 0.271556 0.558537 0.909537 0.431780 0.454398 0.474922 0.006434 \n", + "5 0.208201 0.323859 0.278162 0.790312 0.889913 0.885783 0.041160 \n", + "\n", + " 14 15 16 17 18 19 \n", + "0 0.438989 0.683394 0.101132 0.186438 0.755481 0.758668 \n", + "1 0.485103 0.158604 0.797641 0.665435 0.585333 0.250244 \n", + "2 0.693182 0.168268 0.580322 0.269656 0.876494 0.721471 \n", + "3 0.465587 0.935361 0.442150 0.852374 0.051804 0.471689 \n", + "4 0.106033 0.487690 0.738622 0.867811 0.744058 0.823709 \n", + "5 0.251320 0.656782 0.975511 0.175726 0.879977 0.570059 " + ] + }, + "execution_count": 166, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s2.T" + ] + }, + { + "cell_type": "code", + "execution_count": 167, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
012345678910111213141516171819
count6.0000006.0000006.0000006.0000006.0000006.0000006.0000006.0000006.0000006.0000006.0000006.0000006.0000006.0000006.0000006.0000006.0000006.0000006.0000006.000000
mean0.7063590.3090060.4259730.7911020.3658160.4917950.7100410.2409860.6586780.5228500.6238400.4239670.5131890.1481380.4067020.5150170.6058960.5029060.6488580.599307
std0.3186060.1123510.3772910.2304610.1937750.2706230.2008870.1223340.2657760.3456630.2162410.3135600.3054570.2079680.2036040.3076200.3076530.3296370.3118250.214319
min0.1027940.1421220.0369720.3694100.1330660.1153040.4630900.0821690.3238590.0814330.3494040.0527750.1368110.0045120.1060330.1586040.1011320.1757260.0518040.250244
25%0.6714790.2530670.1025440.7361100.2149170.3092450.5402140.1953970.4545990.3060090.4678870.1990600.3397900.0151160.2982370.2481240.4766930.2072420.6250140.496281
50%0.8073010.3088600.3896510.8616440.3773870.5095260.7498460.2238440.6703350.4632750.6245040.3945460.4267770.0865960.4522880.5722360.6594720.4675450.7497690.645765
75%0.8788160.3787230.6948300.9527280.5308950.7159750.8695090.2635390.8501140.8164030.7609340.6072280.7758400.1468560.4802240.6767410.7828860.8056390.8462410.749369
max0.9919010.4577150.9361660.9765580.5642300.7891400.9177330.4533730.9948080.9414170.9225370.8899130.8857830.5528940.6931820.9353610.9755110.8678110.8799770.823709
\n", + "
" + ], + "text/plain": [ + " 0 1 2 3 4 5 6 \\\n", + "count 6.000000 6.000000 6.000000 6.000000 6.000000 6.000000 6.000000 \n", + "mean 0.706359 0.309006 0.425973 0.791102 0.365816 0.491795 0.710041 \n", + "std 0.318606 0.112351 0.377291 0.230461 0.193775 0.270623 0.200887 \n", + "min 0.102794 0.142122 0.036972 0.369410 0.133066 0.115304 0.463090 \n", + "25% 0.671479 0.253067 0.102544 0.736110 0.214917 0.309245 0.540214 \n", + "50% 0.807301 0.308860 0.389651 0.861644 0.377387 0.509526 0.749846 \n", + "75% 0.878816 0.378723 0.694830 0.952728 0.530895 0.715975 0.869509 \n", + "max 0.991901 0.457715 0.936166 0.976558 0.564230 0.789140 0.917733 \n", + "\n", + " 7 8 9 10 11 12 13 \\\n", + "count 6.000000 6.000000 6.000000 6.000000 6.000000 6.000000 6.000000 \n", + "mean 0.240986 0.658678 0.522850 0.623840 0.423967 0.513189 0.148138 \n", + "std 0.122334 0.265776 0.345663 0.216241 0.313560 0.305457 0.207968 \n", + "min 0.082169 0.323859 0.081433 0.349404 0.052775 0.136811 0.004512 \n", + "25% 0.195397 0.454599 0.306009 0.467887 0.199060 0.339790 0.015116 \n", + "50% 0.223844 0.670335 0.463275 0.624504 0.394546 0.426777 0.086596 \n", + "75% 0.263539 0.850114 0.816403 0.760934 0.607228 0.775840 0.146856 \n", + "max 0.453373 0.994808 0.941417 0.922537 0.889913 0.885783 0.552894 \n", + "\n", + " 14 15 16 17 18 19 \n", + "count 6.000000 6.000000 6.000000 6.000000 6.000000 6.000000 \n", + "mean 0.406702 0.515017 0.605896 0.502906 0.648858 0.599307 \n", + "std 0.203604 0.307620 0.307653 0.329637 0.311825 0.214319 \n", + "min 0.106033 0.158604 0.101132 0.175726 0.051804 0.250244 \n", + "25% 0.298237 0.248124 0.476693 0.207242 0.625014 0.496281 \n", + "50% 0.452288 0.572236 0.659472 0.467545 0.749769 0.645765 \n", + "75% 0.480224 0.676741 0.782886 0.805639 0.846241 0.749369 \n", + "max 0.693182 0.935361 0.975511 0.867811 0.879977 0.823709 " + ] + }, + "execution_count": 167, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s2.T.describe()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 按轴排序" + ] + }, + { + "cell_type": "code", + "execution_count": 171, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "s2.columns=['a','c','d','b','e','y']" + ] + }, + { + "cell_type": "code", + "execution_count": 172, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
acdbey
00.9919010.8389980.7756040.8920890.1027940.636771
10.3894680.2470120.4577150.1421220.3464880.271232
20.0743150.1872330.0369720.9361660.7290840.592069
30.7939040.7168450.9605090.9765580.9293840.369410
40.1330660.5345430.5642300.2082810.2348240.519950
50.3974470.1153040.6216050.7474320.7891400.279844
60.9177330.7398120.4630900.9060510.4736810.759881
70.2394880.4533730.0821690.1911290.2715560.208201
80.9948080.4199530.8727750.7821330.5585370.323859
90.3895500.5370000.9414170.0814330.9095370.278162
100.6728000.3494040.5762080.9225370.4317800.790312
110.0527750.6581720.3346940.1538490.4543980.889913
120.3786320.3268430.8761460.1368110.4749220.885783
130.1320310.1517970.0045120.5528940.0064340.041160
140.4389890.4851030.6931820.4655870.1060330.251320
150.6833940.1586040.1682680.9353610.4876900.656782
160.1011320.7976410.5803220.4421500.7386220.975511
170.1864380.6654350.2696560.8523740.8678110.175726
180.7554810.5853330.8764940.0518040.7440580.879977
190.7586680.2502440.7214710.4716890.8237090.570059
\n", + "
" + ], + "text/plain": [ + " a c d b e y\n", + "0 0.991901 0.838998 0.775604 0.892089 0.102794 0.636771\n", + "1 0.389468 0.247012 0.457715 0.142122 0.346488 0.271232\n", + "2 0.074315 0.187233 0.036972 0.936166 0.729084 0.592069\n", + "3 0.793904 0.716845 0.960509 0.976558 0.929384 0.369410\n", + "4 0.133066 0.534543 0.564230 0.208281 0.234824 0.519950\n", + "5 0.397447 0.115304 0.621605 0.747432 0.789140 0.279844\n", + "6 0.917733 0.739812 0.463090 0.906051 0.473681 0.759881\n", + "7 0.239488 0.453373 0.082169 0.191129 0.271556 0.208201\n", + "8 0.994808 0.419953 0.872775 0.782133 0.558537 0.323859\n", + "9 0.389550 0.537000 0.941417 0.081433 0.909537 0.278162\n", + "10 0.672800 0.349404 0.576208 0.922537 0.431780 0.790312\n", + "11 0.052775 0.658172 0.334694 0.153849 0.454398 0.889913\n", + "12 0.378632 0.326843 0.876146 0.136811 0.474922 0.885783\n", + "13 0.132031 0.151797 0.004512 0.552894 0.006434 0.041160\n", + "14 0.438989 0.485103 0.693182 0.465587 0.106033 0.251320\n", + "15 0.683394 0.158604 0.168268 0.935361 0.487690 0.656782\n", + "16 0.101132 0.797641 0.580322 0.442150 0.738622 0.975511\n", + "17 0.186438 0.665435 0.269656 0.852374 0.867811 0.175726\n", + "18 0.755481 0.585333 0.876494 0.051804 0.744058 0.879977\n", + "19 0.758668 0.250244 0.721471 0.471689 0.823709 0.570059" + ] + }, + "execution_count": 172, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s2" + ] + }, + { + "cell_type": "code", + "execution_count": 175, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
yedcba
00.6367710.1027940.7756040.8389980.8920890.991901
10.2712320.3464880.4577150.2470120.1421220.389468
20.5920690.7290840.0369720.1872330.9361660.074315
30.3694100.9293840.9605090.7168450.9765580.793904
40.5199500.2348240.5642300.5345430.2082810.133066
50.2798440.7891400.6216050.1153040.7474320.397447
60.7598810.4736810.4630900.7398120.9060510.917733
70.2082010.2715560.0821690.4533730.1911290.239488
80.3238590.5585370.8727750.4199530.7821330.994808
90.2781620.9095370.9414170.5370000.0814330.389550
100.7903120.4317800.5762080.3494040.9225370.672800
110.8899130.4543980.3346940.6581720.1538490.052775
120.8857830.4749220.8761460.3268430.1368110.378632
130.0411600.0064340.0045120.1517970.5528940.132031
140.2513200.1060330.6931820.4851030.4655870.438989
150.6567820.4876900.1682680.1586040.9353610.683394
160.9755110.7386220.5803220.7976410.4421500.101132
170.1757260.8678110.2696560.6654350.8523740.186438
180.8799770.7440580.8764940.5853330.0518040.755481
190.5700590.8237090.7214710.2502440.4716890.758668
\n", + "
" + ], + "text/plain": [ + " y e d c b a\n", + "0 0.636771 0.102794 0.775604 0.838998 0.892089 0.991901\n", + "1 0.271232 0.346488 0.457715 0.247012 0.142122 0.389468\n", + "2 0.592069 0.729084 0.036972 0.187233 0.936166 0.074315\n", + "3 0.369410 0.929384 0.960509 0.716845 0.976558 0.793904\n", + "4 0.519950 0.234824 0.564230 0.534543 0.208281 0.133066\n", + "5 0.279844 0.789140 0.621605 0.115304 0.747432 0.397447\n", + "6 0.759881 0.473681 0.463090 0.739812 0.906051 0.917733\n", + "7 0.208201 0.271556 0.082169 0.453373 0.191129 0.239488\n", + "8 0.323859 0.558537 0.872775 0.419953 0.782133 0.994808\n", + "9 0.278162 0.909537 0.941417 0.537000 0.081433 0.389550\n", + "10 0.790312 0.431780 0.576208 0.349404 0.922537 0.672800\n", + "11 0.889913 0.454398 0.334694 0.658172 0.153849 0.052775\n", + "12 0.885783 0.474922 0.876146 0.326843 0.136811 0.378632\n", + "13 0.041160 0.006434 0.004512 0.151797 0.552894 0.132031\n", + "14 0.251320 0.106033 0.693182 0.485103 0.465587 0.438989\n", + "15 0.656782 0.487690 0.168268 0.158604 0.935361 0.683394\n", + "16 0.975511 0.738622 0.580322 0.797641 0.442150 0.101132\n", + "17 0.175726 0.867811 0.269656 0.665435 0.852374 0.186438\n", + "18 0.879977 0.744058 0.876494 0.585333 0.051804 0.755481\n", + "19 0.570059 0.823709 0.721471 0.250244 0.471689 0.758668" + ] + }, + "execution_count": 175, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s2.sort_index(axis=1,ascending=False) \n", + "#axis代表轴，0为行轴，1为列轴\n", + "#ascending 排序的方式，默认True，表示升序，False则为降序" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## 按值排序" + ] + }, + { + "cell_type": "code", + "execution_count": 188, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "C:\\ProgramData\\Anaconda2\\lib\\site-packages\\ipykernel\\__main__.py:1: FutureWarning: sort(columns=....) is deprecated, use sort_values(by=.....)\n", + " if __name__ == '__main__':\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
acdbey
180.7554810.5853330.8764940.0518040.7440580.879977
90.3895500.5370000.9414170.0814330.9095370.278162
120.3786320.3268430.8761460.1368110.4749220.885783
10.3894680.2470120.4577150.1421220.3464880.271232
110.0527750.6581720.3346940.1538490.4543980.889913
70.2394880.4533730.0821690.1911290.2715560.208201
40.1330660.5345430.5642300.2082810.2348240.519950
160.1011320.7976410.5803220.4421500.7386220.975511
140.4389890.4851030.6931820.4655870.1060330.251320
190.7586680.2502440.7214710.4716890.8237090.570059
130.1320310.1517970.0045120.5528940.0064340.041160
50.3974470.1153040.6216050.7474320.7891400.279844
80.9948080.4199530.8727750.7821330.5585370.323859
170.1864380.6654350.2696560.8523740.8678110.175726
00.9919010.8389980.7756040.8920890.1027940.636771
60.9177330.7398120.4630900.9060510.4736810.759881
100.6728000.3494040.5762080.9225370.4317800.790312
150.6833940.1586040.1682680.9353610.4876900.656782
20.0743150.1872330.0369720.9361660.7290840.592069
30.7939040.7168450.9605090.9765580.9293840.369410
\n", + "
" + ], + "text/plain": [ + " a c d b e y\n", + "18 0.755481 0.585333 0.876494 0.051804 0.744058 0.879977\n", + "9 0.389550 0.537000 0.941417 0.081433 0.909537 0.278162\n", + "12 0.378632 0.326843 0.876146 0.136811 0.474922 0.885783\n", + "1 0.389468 0.247012 0.457715 0.142122 0.346488 0.271232\n", + "11 0.052775 0.658172 0.334694 0.153849 0.454398 0.889913\n", + "7 0.239488 0.453373 0.082169 0.191129 0.271556 0.208201\n", + "4 0.133066 0.534543 0.564230 0.208281 0.234824 0.519950\n", + "16 0.101132 0.797641 0.580322 0.442150 0.738622 0.975511\n", + "14 0.438989 0.485103 0.693182 0.465587 0.106033 0.251320\n", + "19 0.758668 0.250244 0.721471 0.471689 0.823709 0.570059\n", + "13 0.132031 0.151797 0.004512 0.552894 0.006434 0.041160\n", + "5 0.397447 0.115304 0.621605 0.747432 0.789140 0.279844\n", + "8 0.994808 0.419953 0.872775 0.782133 0.558537 0.323859\n", + "17 0.186438 0.665435 0.269656 0.852374 0.867811 0.175726\n", + "0 0.991901 0.838998 0.775604 0.892089 0.102794 0.636771\n", + "6 0.917733 0.739812 0.463090 0.906051 0.473681 0.759881\n", + "10 0.672800 0.349404 0.576208 0.922537 0.431780 0.790312\n", + "15 0.683394 0.158604 0.168268 0.935361 0.487690 0.656782\n", + "2 0.074315 0.187233 0.036972 0.936166 0.729084 0.592069\n", + "3 0.793904 0.716845 0.960509 0.976558 0.929384 0.369410" + ] + }, + "execution_count": 188, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s2.sort(columns='b')" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## 按照标签来获取一个交叉的区域" + ] + }, + { + "cell_type": "code", + "execution_count": 199, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "datas=[0,20,30]" + ] + }, + { + "cell_type": "code", + "execution_count": 207, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "a 0.991901\n", + "Name: 0, dtype: float64" + ] + }, + "execution_count": 207, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s2.loc[0:5,['a']] #提取0~5行的数据，再提取a列的数据\n", + "# 标签的切片" + ] + }, + { + "cell_type": "code", + "execution_count": 208, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "a 0.991901\n", + "Name: 0, dtype: float64" + ] + }, + "execution_count": 208, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s2.loc[0,['a']] # 对于返回的对象进行维度缩减" + ] + }, + { + "cell_type": "code", + "execution_count": 209, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "0.99190107406189176" + ] + }, + "execution_count": 209, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s2.loc[0,'a'] # 等同于如下的效果" + ] + }, + { + "cell_type": "code", + "execution_count": 210, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "0.99190107406189176" + ] + }, + "execution_count": 210, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s2['a'][0]" + ] + }, + { + "cell_type": "code", + "execution_count": 211, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "a 0.758668\n", + "c 0.250244\n", + "d 0.721471\n", + "b 0.471689\n", + "e 0.823709\n", + "y 0.570059\n", + "Name: 19, dtype: float64" + ] + }, + "execution_count": 211, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s2.ix[19]" + ] + }, + { + "cell_type": "code", + "execution_count": 213, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "s2.ix[20]=[1,2,3,4,5,6]" + ] + }, + { + "cell_type": "code", + "execution_count": 214, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "a 1.0\n", + "c 2.0\n", + "d 3.0\n", + "b 4.0\n", + "e 5.0\n", + "y 6.0\n", + "Name: 20, dtype: float64" + ] + }, + "execution_count": 214, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s2.ix[20]" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## 通过位置选择" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 通过传递数值进行位置选择（选择的是行）" + ] + }, + { + "cell_type": "code", + "execution_count": 217, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "a 0.991901\n", + "c 0.838998\n", + "d 0.775604\n", + "b 0.892089\n", + "e 0.102794\n", + "y 0.636771\n", + "Name: 0, dtype: float64" + ] + }, + "execution_count": 217, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s2.iloc[0]" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 通过数值进行切片" + ] + }, + { + "cell_type": "code", + "execution_count": 225, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
acdbey
10.3894680.2470120.4577150.1421220.3464880.271232
20.0743150.1872330.0369720.9361660.7290840.592069
\n", + "
" + ], + "text/plain": [ + " a c d b e y\n", + "1 0.389468 0.247012 0.457715 0.142122 0.346488 0.271232\n", + "2 0.074315 0.187233 0.036972 0.936166 0.729084 0.592069" + ] + }, + "execution_count": 225, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s2.iloc[1:3] #切片 行，1-3行，[1,3)" + ] + }, + { + "cell_type": "code", + "execution_count": 228, + "metadata": { + "collapsed": false, + "scrolled": true + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
db
10.4577150.142122
20.0369720.936166
\n", + "
" + ], + "text/plain": [ + " d b\n", + "1 0.457715 0.142122\n", + "2 0.036972 0.936166" + ] + }, + "execution_count": 228, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s2.iloc[1:3,2:4] # 切片 行和列,1-3行，2-4列" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 通知指定一个位置的列表" + ] + }, + { + "cell_type": "code", + "execution_count": 229, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
de
10.4577150.346488
20.0369720.729084
30.9605090.929384
\n", + "
" + ], + "text/plain": [ + " d e\n", + "1 0.457715 0.346488\n", + "2 0.036972 0.729084\n", + "3 0.960509 0.929384" + ] + }, + "execution_count": 229, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s2.iloc[[1,2,3],[2,4]] #1，2，3行，2，4列" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 行切片" + ] + }, + { + "cell_type": "code", + "execution_count": 230, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
acdbey
10.3894680.2470120.4577150.1421220.3464880.271232
20.0743150.1872330.0369720.9361660.7290840.592069
\n", + "
" + ], + "text/plain": [ + " a c d b e y\n", + "1 0.389468 0.247012 0.457715 0.142122 0.346488 0.271232\n", + "2 0.074315 0.187233 0.036972 0.936166 0.729084 0.592069" + ] + }, + "execution_count": 230, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s2.iloc[1:3,:]" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 列切片" + ] + }, + { + "cell_type": "code", + "execution_count": 231, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
cd
00.8389980.775604
10.2470120.457715
20.1872330.036972
30.7168450.960509
40.5345430.564230
50.1153040.621605
60.7398120.463090
70.4533730.082169
80.4199530.872775
90.5370000.941417
100.3494040.576208
110.6581720.334694
120.3268430.876146
130.1517970.004512
140.4851030.693182
150.1586040.168268
160.7976410.580322
170.6654350.269656
180.5853330.876494
190.2502440.721471
202.0000003.000000
\n", + "
" + ], + "text/plain": [ + " c d\n", + "0 0.838998 0.775604\n", + "1 0.247012 0.457715\n", + "2 0.187233 0.036972\n", + "3 0.716845 0.960509\n", + "4 0.534543 0.564230\n", + "5 0.115304 0.621605\n", + "6 0.739812 0.463090\n", + "7 0.453373 0.082169\n", + "8 0.419953 0.872775\n", + "9 0.537000 0.941417\n", + "10 0.349404 0.576208\n", + "11 0.658172 0.334694\n", + "12 0.326843 0.876146\n", + "13 0.151797 0.004512\n", + "14 0.485103 0.693182\n", + "15 0.158604 0.168268\n", + "16 0.797641 0.580322\n", + "17 0.665435 0.269656\n", + "18 0.585333 0.876494\n", + "19 0.250244 0.721471\n", + "20 2.000000 3.000000" + ] + }, + "execution_count": 231, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s2.iloc[:,1:3]" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 获取指定位置的值" + ] + }, + { + "cell_type": "code", + "execution_count": 232, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "0.036972299117306262" + ] + }, + "execution_count": 232, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s2.iloc[2,2] # 获取3行3列的数据" + ] + }, + { + "cell_type": "code", + "execution_count": 234, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "0.036972299117306262" + ] + }, + "execution_count": 234, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s2.iat[2,2] #快速获取指定位置的数据" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## 布尔索引" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 使用一个单独列的值来选择数据" + ] + }, + { + "cell_type": "code", + "execution_count": 236, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
acdbey
00.9919010.8389980.7756040.8920890.1027940.636771
30.7939040.7168450.9605090.9765580.9293840.369410
60.9177330.7398120.4630900.9060510.4736810.759881
80.9948080.4199530.8727750.7821330.5585370.323859
100.6728000.3494040.5762080.9225370.4317800.790312
150.6833940.1586040.1682680.9353610.4876900.656782
180.7554810.5853330.8764940.0518040.7440580.879977
190.7586680.2502440.7214710.4716890.8237090.570059
201.0000002.0000003.0000004.0000005.0000006.000000
\n", + "
" + ], + "text/plain": [ + " a c d b e y\n", + "0 0.991901 0.838998 0.775604 0.892089 0.102794 0.636771\n", + "3 0.793904 0.716845 0.960509 0.976558 0.929384 0.369410\n", + "6 0.917733 0.739812 0.463090 0.906051 0.473681 0.759881\n", + "8 0.994808 0.419953 0.872775 0.782133 0.558537 0.323859\n", + "10 0.672800 0.349404 0.576208 0.922537 0.431780 0.790312\n", + "15 0.683394 0.158604 0.168268 0.935361 0.487690 0.656782\n", + "18 0.755481 0.585333 0.876494 0.051804 0.744058 0.879977\n", + "19 0.758668 0.250244 0.721471 0.471689 0.823709 0.570059\n", + "20 1.000000 2.000000 3.000000 4.000000 5.000000 6.000000" + ] + }, + "execution_count": 236, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s2[s2.a>0.5]" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 整体过滤" + ] + }, + { + "cell_type": "code", + "execution_count": 238, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
acdbey
00.9919010.8389980.7756040.892089NaN0.636771
1NaNNaNNaNNaNNaNNaN
2NaNNaNNaN0.9361660.7290840.592069
30.7939040.7168450.9605090.9765580.929384NaN
4NaN0.5345430.564230NaNNaN0.519950
5NaNNaN0.6216050.7474320.789140NaN
60.9177330.739812NaN0.906051NaN0.759881
7NaNNaNNaNNaNNaNNaN
80.994808NaN0.8727750.7821330.558537NaN
9NaN0.5370000.941417NaN0.909537NaN
100.672800NaN0.5762080.922537NaN0.790312
11NaN0.658172NaNNaNNaN0.889913
12NaNNaN0.876146NaNNaN0.885783
13NaNNaNNaN0.552894NaNNaN
14NaNNaN0.693182NaNNaNNaN
150.683394NaNNaN0.935361NaN0.656782
16NaN0.7976410.580322NaN0.7386220.975511
17NaN0.665435NaN0.8523740.867811NaN
180.7554810.5853330.876494NaN0.7440580.879977
190.758668NaN0.721471NaN0.8237090.570059
201.0000002.0000003.0000004.0000005.0000006.000000
\n", + "
" + ], + "text/plain": [ + " a c d b e y\n", + "0 0.991901 0.838998 0.775604 0.892089 NaN 0.636771\n", + "1 NaN NaN NaN NaN NaN NaN\n", + "2 NaN NaN NaN 0.936166 0.729084 0.592069\n", + "3 0.793904 0.716845 0.960509 0.976558 0.929384 NaN\n", + "4 NaN 0.534543 0.564230 NaN NaN 0.519950\n", + "5 NaN NaN 0.621605 0.747432 0.789140 NaN\n", + "6 0.917733 0.739812 NaN 0.906051 NaN 0.759881\n", + "7 NaN NaN NaN NaN NaN NaN\n", + "8 0.994808 NaN 0.872775 0.782133 0.558537 NaN\n", + "9 NaN 0.537000 0.941417 NaN 0.909537 NaN\n", + "10 0.672800 NaN 0.576208 0.922537 NaN 0.790312\n", + "11 NaN 0.658172 NaN NaN NaN 0.889913\n", + "12 NaN NaN 0.876146 NaN NaN 0.885783\n", + "13 NaN NaN NaN 0.552894 NaN NaN\n", + "14 NaN NaN 0.693182 NaN NaN NaN\n", + "15 0.683394 NaN NaN 0.935361 NaN 0.656782\n", + "16 NaN 0.797641 0.580322 NaN 0.738622 0.975511\n", + "17 NaN 0.665435 NaN 0.852374 0.867811 NaN\n", + "18 0.755481 0.585333 0.876494 NaN 0.744058 0.879977\n", + "19 0.758668 NaN 0.721471 NaN 0.823709 0.570059\n", + "20 1.000000 2.000000 3.000000 4.000000 5.000000 6.000000" + ] + }, + "execution_count": 238, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s2[s2>0.5] #把所有不满足条件的全部置空(where)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### isin() 过滤数据" + ] + }, + { + "cell_type": "code", + "execution_count": 239, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
acdbey
00.9919010.8389980.7756040.8920890.1027940.636771
10.3894680.2470120.4577150.1421220.3464880.271232
20.0743150.1872330.0369720.9361660.7290840.592069
30.7939040.7168450.9605090.9765580.9293840.369410
40.1330660.5345430.5642300.2082810.2348240.519950
50.3974470.1153040.6216050.7474320.7891400.279844
60.9177330.7398120.4630900.9060510.4736810.759881
70.2394880.4533730.0821690.1911290.2715560.208201
80.9948080.4199530.8727750.7821330.5585370.323859
90.3895500.5370000.9414170.0814330.9095370.278162
100.6728000.3494040.5762080.9225370.4317800.790312
110.0527750.6581720.3346940.1538490.4543980.889913
120.3786320.3268430.8761460.1368110.4749220.885783
130.1320310.1517970.0045120.5528940.0064340.041160
140.4389890.4851030.6931820.4655870.1060330.251320
150.6833940.1586040.1682680.9353610.4876900.656782
160.1011320.7976410.5803220.4421500.7386220.975511
170.1864380.6654350.2696560.8523740.8678110.175726
180.7554810.5853330.8764940.0518040.7440580.879977
190.7586680.2502440.7214710.4716890.8237090.570059
201.0000002.0000003.0000004.0000005.0000006.000000
\n", + "
" + ], + "text/plain": [ + " a c d b e y\n", + "0 0.991901 0.838998 0.775604 0.892089 0.102794 0.636771\n", + "1 0.389468 0.247012 0.457715 0.142122 0.346488 0.271232\n", + "2 0.074315 0.187233 0.036972 0.936166 0.729084 0.592069\n", + "3 0.793904 0.716845 0.960509 0.976558 0.929384 0.369410\n", + "4 0.133066 0.534543 0.564230 0.208281 0.234824 0.519950\n", + "5 0.397447 0.115304 0.621605 0.747432 0.789140 0.279844\n", + "6 0.917733 0.739812 0.463090 0.906051 0.473681 0.759881\n", + "7 0.239488 0.453373 0.082169 0.191129 0.271556 0.208201\n", + "8 0.994808 0.419953 0.872775 0.782133 0.558537 0.323859\n", + "9 0.389550 0.537000 0.941417 0.081433 0.909537 0.278162\n", + "10 0.672800 0.349404 0.576208 0.922537 0.431780 0.790312\n", + "11 0.052775 0.658172 0.334694 0.153849 0.454398 0.889913\n", + "12 0.378632 0.326843 0.876146 0.136811 0.474922 0.885783\n", + "13 0.132031 0.151797 0.004512 0.552894 0.006434 0.041160\n", + "14 0.438989 0.485103 0.693182 0.465587 0.106033 0.251320\n", + "15 0.683394 0.158604 0.168268 0.935361 0.487690 0.656782\n", + "16 0.101132 0.797641 0.580322 0.442150 0.738622 0.975511\n", + "17 0.186438 0.665435 0.269656 0.852374 0.867811 0.175726\n", + "18 0.755481 0.585333 0.876494 0.051804 0.744058 0.879977\n", + "19 0.758668 0.250244 0.721471 0.471689 0.823709 0.570059\n", + "20 1.000000 2.000000 3.000000 4.000000 5.000000 6.000000" + ] + }, + "execution_count": 239, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s3=s2.copy()\n", + "s3" + ] + }, + { + "cell_type": "code", + "execution_count": 244, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "s3['a'][0]=1.23" + ] + }, + { + "cell_type": "code", + "execution_count": 245, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
acdbey
01.2300000.8389980.7756040.8920890.1027940.636771
10.3894680.2470120.4577150.1421220.3464880.271232
20.0743150.1872330.0369720.9361660.7290840.592069
30.7939040.7168450.9605090.9765580.9293840.369410
40.1330660.5345430.5642300.2082810.2348240.519950
50.3974470.1153040.6216050.7474320.7891400.279844
60.9177330.7398120.4630900.9060510.4736810.759881
70.2394880.4533730.0821690.1911290.2715560.208201
80.9948080.4199530.8727750.7821330.5585370.323859
90.3895500.5370000.9414170.0814330.9095370.278162
100.6728000.3494040.5762080.9225370.4317800.790312
110.0527750.6581720.3346940.1538490.4543980.889913
120.3786320.3268430.8761460.1368110.4749220.885783
130.1320310.1517970.0045120.5528940.0064340.041160
140.4389890.4851030.6931820.4655870.1060330.251320
150.6833940.1586040.1682680.9353610.4876900.656782
160.1011320.7976410.5803220.4421500.7386220.975511
170.1864380.6654350.2696560.8523740.8678110.175726
180.7554810.5853330.8764940.0518040.7440580.879977
190.7586680.2502440.7214710.4716890.8237090.570059
201.0000002.0000003.0000004.0000005.0000006.000000
\n", + "
" + ], + "text/plain": [ + " a c d b e y\n", + "0 1.230000 0.838998 0.775604 0.892089 0.102794 0.636771\n", + "1 0.389468 0.247012 0.457715 0.142122 0.346488 0.271232\n", + "2 0.074315 0.187233 0.036972 0.936166 0.729084 0.592069\n", + "3 0.793904 0.716845 0.960509 0.976558 0.929384 0.369410\n", + "4 0.133066 0.534543 0.564230 0.208281 0.234824 0.519950\n", + "5 0.397447 0.115304 0.621605 0.747432 0.789140 0.279844\n", + "6 0.917733 0.739812 0.463090 0.906051 0.473681 0.759881\n", + "7 0.239488 0.453373 0.082169 0.191129 0.271556 0.208201\n", + "8 0.994808 0.419953 0.872775 0.782133 0.558537 0.323859\n", + "9 0.389550 0.537000 0.941417 0.081433 0.909537 0.278162\n", + "10 0.672800 0.349404 0.576208 0.922537 0.431780 0.790312\n", + "11 0.052775 0.658172 0.334694 0.153849 0.454398 0.889913\n", + "12 0.378632 0.326843 0.876146 0.136811 0.474922 0.885783\n", + "13 0.132031 0.151797 0.004512 0.552894 0.006434 0.041160\n", + "14 0.438989 0.485103 0.693182 0.465587 0.106033 0.251320\n", + "15 0.683394 0.158604 0.168268 0.935361 0.487690 0.656782\n", + "16 0.101132 0.797641 0.580322 0.442150 0.738622 0.975511\n", + "17 0.186438 0.665435 0.269656 0.852374 0.867811 0.175726\n", + "18 0.755481 0.585333 0.876494 0.051804 0.744058 0.879977\n", + "19 0.758668 0.250244 0.721471 0.471689 0.823709 0.570059\n", + "20 1.000000 2.000000 3.000000 4.000000 5.000000 6.000000" + ] + }, + "execution_count": 245, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s3" + ] + }, + { + "cell_type": "code", + "execution_count": 246, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
acdbey
00.9919010.8389980.7756040.8920890.1027940.636771
10.3894680.2470120.4577150.1421220.3464880.271232
20.0743150.1872330.0369720.9361660.7290840.592069
30.7939040.7168450.9605090.9765580.9293840.369410
40.1330660.5345430.5642300.2082810.2348240.519950
50.3974470.1153040.6216050.7474320.7891400.279844
60.9177330.7398120.4630900.9060510.4736810.759881
70.2394880.4533730.0821690.1911290.2715560.208201
80.9948080.4199530.8727750.7821330.5585370.323859
90.3895500.5370000.9414170.0814330.9095370.278162
100.6728000.3494040.5762080.9225370.4317800.790312
110.0527750.6581720.3346940.1538490.4543980.889913
120.3786320.3268430.8761460.1368110.4749220.885783
130.1320310.1517970.0045120.5528940.0064340.041160
140.4389890.4851030.6931820.4655870.1060330.251320
150.6833940.1586040.1682680.9353610.4876900.656782
160.1011320.7976410.5803220.4421500.7386220.975511
170.1864380.6654350.2696560.8523740.8678110.175726
180.7554810.5853330.8764940.0518040.7440580.879977
190.7586680.2502440.7214710.4716890.8237090.570059
201.0000002.0000003.0000004.0000005.0000006.000000
\n", + "
" + ], + "text/plain": [ + " a c d b e y\n", + "0 0.991901 0.838998 0.775604 0.892089 0.102794 0.636771\n", + "1 0.389468 0.247012 0.457715 0.142122 0.346488 0.271232\n", + "2 0.074315 0.187233 0.036972 0.936166 0.729084 0.592069\n", + "3 0.793904 0.716845 0.960509 0.976558 0.929384 0.369410\n", + "4 0.133066 0.534543 0.564230 0.208281 0.234824 0.519950\n", + "5 0.397447 0.115304 0.621605 0.747432 0.789140 0.279844\n", + "6 0.917733 0.739812 0.463090 0.906051 0.473681 0.759881\n", + "7 0.239488 0.453373 0.082169 0.191129 0.271556 0.208201\n", + "8 0.994808 0.419953 0.872775 0.782133 0.558537 0.323859\n", + "9 0.389550 0.537000 0.941417 0.081433 0.909537 0.278162\n", + "10 0.672800 0.349404 0.576208 0.922537 0.431780 0.790312\n", + "11 0.052775 0.658172 0.334694 0.153849 0.454398 0.889913\n", + "12 0.378632 0.326843 0.876146 0.136811 0.474922 0.885783\n", + "13 0.132031 0.151797 0.004512 0.552894 0.006434 0.041160\n", + "14 0.438989 0.485103 0.693182 0.465587 0.106033 0.251320\n", + "15 0.683394 0.158604 0.168268 0.935361 0.487690 0.656782\n", + "16 0.101132 0.797641 0.580322 0.442150 0.738622 0.975511\n", + "17 0.186438 0.665435 0.269656 0.852374 0.867811 0.175726\n", + "18 0.755481 0.585333 0.876494 0.051804 0.744058 0.879977\n", + "19 0.758668 0.250244 0.721471 0.471689 0.823709 0.570059\n", + "20 1.000000 2.000000 3.000000 4.000000 5.000000 6.000000" + ] + }, + "execution_count": 246, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s2" + ] + }, + { + "cell_type": "code", + "execution_count": 248, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
acdbey
01.230.8389980.7756040.8920890.1027940.636771
201.002.0000003.0000004.0000005.0000006.000000
\n", + "
" + ], + "text/plain": [ + " a c d b e y\n", + "0 1.23 0.838998 0.775604 0.892089 0.102794 0.636771\n", + "20 1.00 2.000000 3.000000 4.000000 5.000000 6.000000" + ] + }, + "execution_count": 248, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s3[s3['a'].isin([1.0,1.23])] \n", + "#检索a列中的数据，将满足的行返回出来" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## 设置" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 新增一个列" + ] + }, + { + "cell_type": "code", + "execution_count": 252, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "s1=Series([i for i in range(20)])" + ] + }, + { + "cell_type": "code", + "execution_count": 256, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "s2['f'][20]=11" + ] + }, + { + "cell_type": "code", + "execution_count": 257, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
acdbeyf
00.9919010.8389980.7756040.8920890.1027940.6367710.0
10.3894680.2470120.4577150.1421220.3464880.2712321.0
20.0743150.1872330.0369720.9361660.7290840.5920692.0
30.7939040.7168450.9605090.9765580.9293840.3694103.0
40.1330660.5345430.5642300.2082810.2348240.5199504.0
50.3974470.1153040.6216050.7474320.7891400.2798445.0
60.9177330.7398120.4630900.9060510.4736810.7598816.0
70.2394880.4533730.0821690.1911290.2715560.2082017.0
80.9948080.4199530.8727750.7821330.5585370.3238598.0
90.3895500.5370000.9414170.0814330.9095370.2781629.0
100.6728000.3494040.5762080.9225370.4317800.79031210.0
110.0527750.6581720.3346940.1538490.4543980.88991311.0
120.3786320.3268430.8761460.1368110.4749220.88578312.0
130.1320310.1517970.0045120.5528940.0064340.04116013.0
140.4389890.4851030.6931820.4655870.1060330.25132014.0
150.6833940.1586040.1682680.9353610.4876900.65678215.0
160.1011320.7976410.5803220.4421500.7386220.97551116.0
170.1864380.6654350.2696560.8523740.8678110.17572617.0
180.7554810.5853330.8764940.0518040.7440580.87997718.0
190.7586680.2502440.7214710.4716890.8237090.57005919.0
201.0000002.0000003.0000004.0000005.0000006.00000011.0
\n", + "
" + ], + "text/plain": [ + " a c d b e y f\n", + "0 0.991901 0.838998 0.775604 0.892089 0.102794 0.636771 0.0\n", + "1 0.389468 0.247012 0.457715 0.142122 0.346488 0.271232 1.0\n", + "2 0.074315 0.187233 0.036972 0.936166 0.729084 0.592069 2.0\n", + "3 0.793904 0.716845 0.960509 0.976558 0.929384 0.369410 3.0\n", + "4 0.133066 0.534543 0.564230 0.208281 0.234824 0.519950 4.0\n", + "5 0.397447 0.115304 0.621605 0.747432 0.789140 0.279844 5.0\n", + "6 0.917733 0.739812 0.463090 0.906051 0.473681 0.759881 6.0\n", + "7 0.239488 0.453373 0.082169 0.191129 0.271556 0.208201 7.0\n", + "8 0.994808 0.419953 0.872775 0.782133 0.558537 0.323859 8.0\n", + "9 0.389550 0.537000 0.941417 0.081433 0.909537 0.278162 9.0\n", + "10 0.672800 0.349404 0.576208 0.922537 0.431780 0.790312 10.0\n", + "11 0.052775 0.658172 0.334694 0.153849 0.454398 0.889913 11.0\n", + "12 0.378632 0.326843 0.876146 0.136811 0.474922 0.885783 12.0\n", + "13 0.132031 0.151797 0.004512 0.552894 0.006434 0.041160 13.0\n", + "14 0.438989 0.485103 0.693182 0.465587 0.106033 0.251320 14.0\n", + "15 0.683394 0.158604 0.168268 0.935361 0.487690 0.656782 15.0\n", + "16 0.101132 0.797641 0.580322 0.442150 0.738622 0.975511 16.0\n", + "17 0.186438 0.665435 0.269656 0.852374 0.867811 0.175726 17.0\n", + "18 0.755481 0.585333 0.876494 0.051804 0.744058 0.879977 18.0\n", + "19 0.758668 0.250244 0.721471 0.471689 0.823709 0.570059 19.0\n", + "20 1.000000 2.000000 3.000000 4.000000 5.000000 6.000000 11.0" + ] + }, + "execution_count": 257, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s2" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 通过便签设置值" + ] + }, + { + "cell_type": "code", + "execution_count": 259, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "s2.loc[20,'f']=13" + ] + }, + { + "cell_type": "code", + "execution_count": 260, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
acdbeyf
00.9919010.8389980.7756040.8920890.1027940.6367710.0
10.3894680.2470120.4577150.1421220.3464880.2712321.0
20.0743150.1872330.0369720.9361660.7290840.5920692.0
30.7939040.7168450.9605090.9765580.9293840.3694103.0
40.1330660.5345430.5642300.2082810.2348240.5199504.0
50.3974470.1153040.6216050.7474320.7891400.2798445.0
60.9177330.7398120.4630900.9060510.4736810.7598816.0
70.2394880.4533730.0821690.1911290.2715560.2082017.0
80.9948080.4199530.8727750.7821330.5585370.3238598.0
90.3895500.5370000.9414170.0814330.9095370.2781629.0
100.6728000.3494040.5762080.9225370.4317800.79031210.0
110.0527750.6581720.3346940.1538490.4543980.88991311.0
120.3786320.3268430.8761460.1368110.4749220.88578312.0
130.1320310.1517970.0045120.5528940.0064340.04116013.0
140.4389890.4851030.6931820.4655870.1060330.25132014.0
150.6833940.1586040.1682680.9353610.4876900.65678215.0
160.1011320.7976410.5803220.4421500.7386220.97551116.0
170.1864380.6654350.2696560.8523740.8678110.17572617.0
180.7554810.5853330.8764940.0518040.7440580.87997718.0
190.7586680.2502440.7214710.4716890.8237090.57005919.0
201.0000002.0000003.0000004.0000005.0000006.00000013.0
\n", + "
" + ], + "text/plain": [ + " a c d b e y f\n", + "0 0.991901 0.838998 0.775604 0.892089 0.102794 0.636771 0.0\n", + "1 0.389468 0.247012 0.457715 0.142122 0.346488 0.271232 1.0\n", + "2 0.074315 0.187233 0.036972 0.936166 0.729084 0.592069 2.0\n", + "3 0.793904 0.716845 0.960509 0.976558 0.929384 0.369410 3.0\n", + "4 0.133066 0.534543 0.564230 0.208281 0.234824 0.519950 4.0\n", + "5 0.397447 0.115304 0.621605 0.747432 0.789140 0.279844 5.0\n", + "6 0.917733 0.739812 0.463090 0.906051 0.473681 0.759881 6.0\n", + "7 0.239488 0.453373 0.082169 0.191129 0.271556 0.208201 7.0\n", + "8 0.994808 0.419953 0.872775 0.782133 0.558537 0.323859 8.0\n", + "9 0.389550 0.537000 0.941417 0.081433 0.909537 0.278162 9.0\n", + "10 0.672800 0.349404 0.576208 0.922537 0.431780 0.790312 10.0\n", + "11 0.052775 0.658172 0.334694 0.153849 0.454398 0.889913 11.0\n", + "12 0.378632 0.326843 0.876146 0.136811 0.474922 0.885783 12.0\n", + "13 0.132031 0.151797 0.004512 0.552894 0.006434 0.041160 13.0\n", + "14 0.438989 0.485103 0.693182 0.465587 0.106033 0.251320 14.0\n", + "15 0.683394 0.158604 0.168268 0.935361 0.487690 0.656782 15.0\n", + "16 0.101132 0.797641 0.580322 0.442150 0.738622 0.975511 16.0\n", + "17 0.186438 0.665435 0.269656 0.852374 0.867811 0.175726 17.0\n", + "18 0.755481 0.585333 0.876494 0.051804 0.744058 0.879977 18.0\n", + "19 0.758668 0.250244 0.721471 0.471689 0.823709 0.570059 19.0\n", + "20 1.000000 2.000000 3.000000 4.000000 5.000000 6.000000 13.0" + ] + }, + "execution_count": 260, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s2" + ] + }, + { + "cell_type": "code", + "execution_count": 262, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "s2[s2>0.5]=0" + ] + }, + { + "cell_type": "code", + "execution_count": 263, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
acdbeyf
00.0000000.0000000.0000000.0000000.1027940.0000000.0
10.3894680.2470120.4577150.1421220.3464880.2712320.0
20.0743150.1872330.0369720.0000000.0000000.0000000.0
30.0000000.0000000.0000000.0000000.0000000.3694100.0
40.1330660.0000000.0000000.2082810.2348240.0000000.0
50.3974470.1153040.0000000.0000000.0000000.2798440.0
60.0000000.0000000.4630900.0000000.4736810.0000000.0
70.2394880.4533730.0821690.1911290.2715560.2082010.0
80.0000000.4199530.0000000.0000000.0000000.3238590.0
90.3895500.0000000.0000000.0814330.0000000.2781620.0
100.0000000.3494040.0000000.0000000.4317800.0000000.0
110.0527750.0000000.3346940.1538490.4543980.0000000.0
120.3786320.3268430.0000000.1368110.4749220.0000000.0
130.1320310.1517970.0045120.0000000.0064340.0411600.0
140.4389890.4851030.0000000.4655870.1060330.2513200.0
150.0000000.1586040.1682680.0000000.4876900.0000000.0
160.1011320.0000000.0000000.4421500.0000000.0000000.0
170.1864380.0000000.2696560.0000000.0000000.1757260.0
180.0000000.0000000.0000000.0518040.0000000.0000000.0
190.0000000.2502440.0000000.4716890.0000000.0000000.0
200.0000000.0000000.0000000.0000000.0000000.0000000.0
\n", + "
" + ], + "text/plain": [ + " a c d b e y f\n", + "0 0.000000 0.000000 0.000000 0.000000 0.102794 0.000000 0.0\n", + "1 0.389468 0.247012 0.457715 0.142122 0.346488 0.271232 0.0\n", + "2 0.074315 0.187233 0.036972 0.000000 0.000000 0.000000 0.0\n", + "3 0.000000 0.000000 0.000000 0.000000 0.000000 0.369410 0.0\n", + "4 0.133066 0.000000 0.000000 0.208281 0.234824 0.000000 0.0\n", + "5 0.397447 0.115304 0.000000 0.000000 0.000000 0.279844 0.0\n", + "6 0.000000 0.000000 0.463090 0.000000 0.473681 0.000000 0.0\n", + "7 0.239488 0.453373 0.082169 0.191129 0.271556 0.208201 0.0\n", + "8 0.000000 0.419953 0.000000 0.000000 0.000000 0.323859 0.0\n", + "9 0.389550 0.000000 0.000000 0.081433 0.000000 0.278162 0.0\n", + "10 0.000000 0.349404 0.000000 0.000000 0.431780 0.000000 0.0\n", + "11 0.052775 0.000000 0.334694 0.153849 0.454398 0.000000 0.0\n", + "12 0.378632 0.326843 0.000000 0.136811 0.474922 0.000000 0.0\n", + "13 0.132031 0.151797 0.004512 0.000000 0.006434 0.041160 0.0\n", + "14 0.438989 0.485103 0.000000 0.465587 0.106033 0.251320 0.0\n", + "15 0.000000 0.158604 0.168268 0.000000 0.487690 0.000000 0.0\n", + "16 0.101132 0.000000 0.000000 0.442150 0.000000 0.000000 0.0\n", + "17 0.186438 0.000000 0.269656 0.000000 0.000000 0.175726 0.0\n", + "18 0.000000 0.000000 0.000000 0.051804 0.000000 0.000000 0.0\n", + "19 0.000000 0.250244 0.000000 0.471689 0.000000 0.000000 0.0\n", + "20 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.0" + ] + }, + "execution_count": 263, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s2" + ] + }, + { + "cell_type": "code", + "execution_count": 275, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "s4=s3[s3.a<0.06]" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## 缺失值的处理" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### reindex() 方法可以对指定的轴上的索引进行修改（增加/删除）" + ] + }, + { + "cell_type": "code", + "execution_count": 294, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "s4=s3.reindex(index=[i for i in range(11)],columns=list(s3.columns)+['a'])" + ] + }, + { + "cell_type": "code", + "execution_count": 309, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "0.83899796247517222" + ] + }, + "execution_count": 309, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s3.iat[0,1]" + ] + }, + { + "cell_type": "code", + "execution_count": 312, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "s4=DataFrame(np.array(\n", + " [\n", + " [1,np.nan,2,3],\n", + " [2,3,4,np.nan]\n", + " ]\n", + "))" + ] + }, + { + "cell_type": "code", + "execution_count": 317, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
0123
01.0NaN2.03.0
12.03.04.0NaN
21.02.03.04.0
\n", + "
" + ], + "text/plain": [ + " 0 1 2 3\n", + "0 1.0 NaN 2.0 3.0\n", + "1 2.0 3.0 4.0 NaN\n", + "2 1.0 2.0 3.0 4.0" + ] + }, + "execution_count": 317, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s4.ix[2]=[1,2,3,4]\n", + "s4" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### 去除包含缺失值的行" + ] + }, + { + "cell_type": "code", + "execution_count": 318, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
0123
21.02.03.04.0
\n", + "
" + ], + "text/plain": [ + " 0 1 2 3\n", + "2 1.0 2.0 3.0 4.0" + ] + }, + "execution_count": 318, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s4.dropna(how='any')" + ] + }, + { + "cell_type": "code", + "execution_count": 319, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Help on method dropna in module pandas.core.frame:\n", + "\n", + "dropna(self, axis=0, how='any', thresh=None, subset=None, inplace=False) method of pandas.core.frame.DataFrame instance\n", + " Return object with labels on given axis omitted where alternately any\n", + " or all of the data are missing\n", + " \n", + " Parameters\n", + " ----------\n", + " axis : {0 or 'index', 1 or 'columns'}, or tuple/list thereof\n", + " Pass tuple or list to drop on multiple axes\n", + " how : {'any', 'all'}\n", + " * any : if any NA values are present, drop that label\n", + " * all : if all values are NA, drop that label\n", + " thresh : int, default None\n", + " int value : require that many non-NA values\n", + " subset : array-like\n", + " Labels along other axis to consider, e.g. if you are dropping rows\n", + " these would be a list of columns to include\n", + " inplace : boolean, default False\n", + " If True, do operation inplace and return None.\n", + " \n", + " Returns\n", + " -------\n", + " dropped : DataFrame\n", + "\n" + ] + } + ], + "source": [ + "help(s4.dropna)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 对缺失值的替换" + ] + }, + { + "cell_type": "code", + "execution_count": 320, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "s4=DataFrame(np.array(\n", + " [\n", + " [1,np.nan,2,3],\n", + " [2,3,4,np.nan],\n", + " [1,3,4,5]\n", + " ]\n", + "))" + ] + }, + { + "cell_type": "code", + "execution_count": 321, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
0123
01.0NaN2.03.0
12.03.04.0NaN
21.03.04.05.0
\n", + "
" + ], + "text/plain": [ + " 0 1 2 3\n", + "0 1.0 NaN 2.0 3.0\n", + "1 2.0 3.0 4.0 NaN\n", + "2 1.0 3.0 4.0 5.0" + ] + }, + "execution_count": 321, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s4" + ] + }, + { + "cell_type": "code", + "execution_count": 323, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
0123
01.00.02.03.0
12.03.04.00.0
21.03.04.05.0
\n", + "
" + ], + "text/plain": [ + " 0 1 2 3\n", + "0 1.0 0.0 2.0 3.0\n", + "1 2.0 3.0 4.0 0.0\n", + "2 1.0 3.0 4.0 5.0" + ] + }, + "execution_count": 323, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s4.fillna(value=0)" + ] + }, + { + "cell_type": "code", + "execution_count": 324, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "s5=DataFrame(np.array(\n", + " [\n", + " [1,np.nan,2,3],\n", + " [2,3,4,np.nan],\n", + " [1,3,4,5]\n", + " ]\n", + "))" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 对数据进行布尔填充，空值的判断" + ] + }, + { + "cell_type": "code", + "execution_count": 326, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
0123
0FalseTrueFalseFalse
1FalseFalseFalseTrue
2FalseFalseFalseFalse
\n", + "
" + ], + "text/plain": [ + " 0 1 2 3\n", + "0 False True False False\n", + "1 False False False True\n", + "2 False False False False" + ] + }, + "execution_count": 326, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "pd.isnull(s5)" + ] + }, + { + "cell_type": "code", + "execution_count": 327, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
0123
01.0NaN2.03.0
12.03.04.0NaN
21.03.04.05.0
\n", + "
" + ], + "text/plain": [ + " 0 1 2 3\n", + "0 1.0 NaN 2.0 3.0\n", + "1 2.0 3.0 4.0 NaN\n", + "2 1.0 3.0 4.0 5.0" + ] + }, + "execution_count": 327, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s5" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## 其他操作" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 数据描述性统计" + ] + }, + { + "cell_type": "code", + "execution_count": 330, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "a 0.510482\n", + "c 0.534221\n", + "d 0.660811\n", + "b 0.707069\n", + "e 0.737166\n", + "y 0.778853\n", + "dtype: float64" + ] + }, + "execution_count": 330, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s3.mean()" + ] + }, + { + "cell_type": "code", + "execution_count": 338, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "0 0.746043\n", + "1 0.309006\n", + "2 0.425973\n", + "3 0.791102\n", + "4 0.365816\n", + "5 0.491795\n", + "6 0.710041\n", + "7 0.240986\n", + "8 0.658678\n", + "9 0.522850\n", + "10 0.623840\n", + "11 0.423967\n", + "12 0.513189\n", + "13 0.148138\n", + "14 0.406702\n", + "15 0.515017\n", + "16 0.605896\n", + "17 0.502906\n", + "18 0.648858\n", + "19 0.599307\n", + "20 3.500000\n", + "dtype: float64" + ] + }, + "execution_count": 338, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s3.mean(1) #对固定的轴进行统计操作" + ] + }, + { + "cell_type": "code", + "execution_count": 336, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Help on method mean in module pandas.core.generic:\n", + "\n", + "mean(self, axis=None, skipna=None, level=None, numeric_only=None, **kwargs) method of pandas.core.frame.DataFrame instance\n", + " Return the mean of the values for the requested axis\n", + " \n", + " Parameters\n", + " ----------\n", + " axis : {index (0), columns (1)}\n", + " skipna : boolean, default True\n", + " Exclude NA/null values. If an entire row/column is NA, the result\n", + " will be NA\n", + " level : int or level name, default None\n", + " If the axis is a MultiIndex (hierarchical), count along a\n", + " particular level, collapsing into a Series\n", + " numeric_only : boolean, default None\n", + " Include only float, int, boolean columns. If None, will attempt to use\n", + " everything, then use only numeric data. Not implemented for Series.\n", + " \n", + " Returns\n", + " -------\n", + " mean : Series or DataFrame (if level specified)\n", + "\n" + ] + } + ], + "source": [ + "help(s3.mean)" + ] + }, + { + "cell_type": "code", + "execution_count": 340, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
0123
01.0NaN2.03.0
13.03.06.0NaN
24.06.010.08.0
\n", + "
" + ], + "text/plain": [ + " 0 1 2 3\n", + "0 1.0 NaN 2.0 3.0\n", + "1 3.0 3.0 6.0 NaN\n", + "2 4.0 6.0 10.0 8.0" + ] + }, + "execution_count": 340, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s4.apply(np.cumsum) #对数据应用函数" + ] + }, + { + "cell_type": "code", + "execution_count": 341, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
0123
01.0NaN2.03.0
12.03.04.0NaN
21.03.04.05.0
\n", + "
" + ], + "text/plain": [ + " 0 1 2 3\n", + "0 1.0 NaN 2.0 3.0\n", + "1 2.0 3.0 4.0 NaN\n", + "2 1.0 3.0 4.0 5.0" + ] + }, + "execution_count": 341, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s4" + ] + }, + { + "cell_type": "code", + "execution_count": 342, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Help on function cumsum in module numpy.core.fromnumeric:\n", + "\n", + "cumsum(a, axis=None, dtype=None, out=None)\n", + " Return the cumulative sum of the elements along a given axis.\n", + " \n", + " Parameters\n", + " ----------\n", + " a : array_like\n", + " Input array.\n", + " axis : int, optional\n", + " Axis along which the cumulative sum is computed. The default\n", + " (None) is to compute the cumsum over the flattened array.\n", + " dtype : dtype, optional\n", + " Type of the returned array and of the accumulator in which the\n", + " elements are summed. If `dtype` is not specified, it defaults\n", + " to the dtype of `a`, unless `a` has an integer dtype with a\n", + " precision less than that of the default platform integer. In\n", + " that case, the default platform integer is used.\n", + " out : ndarray, optional\n", + " Alternative output array in which to place the result. It must\n", + " have the same shape and buffer length as the expected output\n", + " but the type will be cast if necessary. See `doc.ufuncs`\n", + " (Section \"Output arguments\") for more details.\n", + " \n", + " Returns\n", + " -------\n", + " cumsum_along_axis : ndarray.\n", + " A new array holding the result is returned unless `out` is\n", + " specified, in which case a reference to `out` is returned. The\n", + " result has the same size as `a`, and the same shape as `a` if\n", + " `axis` is not None or `a` is a 1-d array.\n", + " \n", + " \n", + " See Also\n", + " --------\n", + " sum : Sum array elements.\n", + " \n", + " trapz : Integration of array values using the composite trapezoidal rule.\n", + " \n", + " diff : Calculate the n-th discrete difference along given axis.\n", + " \n", + " Notes\n", + " -----\n", + " Arithmetic is modular when using integer types, and no error is\n", + " raised on overflow.\n", + " \n", + " Examples\n", + " --------\n", + " >>> a = np.array([[1,2,3], [4,5,6]])\n", + " >>> a\n", + " array([[1, 2, 3],\n", + " [4, 5, 6]])\n", + " >>> np.cumsum(a)\n", + " array([ 1, 3, 6, 10, 15, 21])\n", + " >>> np.cumsum(a, dtype=float) # specifies type of output value(s)\n", + " array([ 1., 3., 6., 10., 15., 21.])\n", + " \n", + " >>> np.cumsum(a,axis=0) # sum over rows for each of the 3 columns\n", + " array([[1, 2, 3],\n", + " [5, 7, 9]])\n", + " >>> np.cumsum(a,axis=1) # sum over columns for each of the 2 rows\n", + " array([[ 1, 3, 6],\n", + " [ 4, 9, 15]])\n", + "\n" + ] + } + ], + "source": [ + "help(np.cumsum)" + ] + }, + { + "cell_type": "code", + "execution_count": 344, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "0 1.0\n", + "1 0.0\n", + "2 2.0\n", + "3 2.0\n", + "dtype: float64" + ] + }, + "execution_count": 344, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s4.apply(lambda x:x.max()-x.min())" + ] + }, + { + "cell_type": "code", + "execution_count": 345, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
0123
01.0NaN2.03.0
12.03.04.0NaN
21.03.04.05.0
\n", + "
" + ], + "text/plain": [ + " 0 1 2 3\n", + "0 1.0 NaN 2.0 3.0\n", + "1 2.0 3.0 4.0 NaN\n", + "2 1.0 3.0 4.0 5.0" + ] + }, + "execution_count": 345, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s4" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 直方图" + ] + }, + { + "cell_type": "code", + "execution_count": 348, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "n1=np.random.randint(0,7,size=10)" + ] + }, + { + "cell_type": "code", + "execution_count": 349, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "array([2, 0, 5, 3, 2, 6, 6, 1, 5, 5])" + ] + }, + "execution_count": 349, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "n1" + ] + }, + { + "cell_type": "code", + "execution_count": 355, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "s1=pd.Series(n1)" + ] + }, + { + "cell_type": "code", + "execution_count": 356, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "5 3\n", + "6 2\n", + "2 2\n", + "3 1\n", + "1 1\n", + "0 1\n", + "dtype: int64" + ] + }, + "execution_count": 356, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s1.value_counts() # 数据元素的统计" + ] + }, + { + "cell_type": "code", + "execution_count": 357, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "n1=np.random.randint(0,10,size=100)" + ] + }, + { + "cell_type": "code", + "execution_count": 364, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "df=Series(n1)" + ] + }, + { + "cell_type": "code", + "execution_count": 365, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "0 6\n", + "1 9\n", + "2 1\n", + "3 1\n", + "4 3\n", + "5 6\n", + "6 5\n", + "7 7\n", + "8 3\n", + "9 2\n", + "10 8\n", + "11 5\n", + "12 5\n", + "13 5\n", + "14 9\n", + "15 9\n", + "16 3\n", + "17 7\n", + "18 3\n", + "19 0\n", + "20 0\n", + "21 7\n", + "22 6\n", + "23 3\n", + "24 5\n", + "25 3\n", + "26 6\n", + "27 5\n", + "28 0\n", + "29 9\n", + " ..\n", + "70 3\n", + "71 2\n", + "72 1\n", + "73 6\n", + "74 4\n", + "75 4\n", + "76 1\n", + "77 4\n", + "78 2\n", + "79 3\n", + "80 2\n", + "81 8\n", + "82 5\n", + "83 5\n", + "84 9\n", + "85 2\n", + "86 4\n", + "87 3\n", + "88 3\n", + "89 8\n", + "90 6\n", + "91 6\n", + "92 1\n", + "93 7\n", + "94 9\n", + "95 1\n", + "96 2\n", + "97 5\n", + "98 5\n", + "99 5\n", + "dtype: int32" + ] + }, + "execution_count": 365, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df" + ] + }, + { + "cell_type": "code", + "execution_count": 366, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "5 16\n", + "3 15\n", + "6 13\n", + "9 10\n", + "2 10\n", + "7 8\n", + "4 8\n", + "1 7\n", + "0 7\n", + "8 6\n", + "dtype: int64" + ] + }, + "execution_count": 366, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df.value_counts()" + ] + }, + { + "cell_type": "code", + "execution_count": 368, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 368, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df.hist(color='k',alpha=0.5)" + ] + }, + { + "cell_type": "code", + "execution_count": 369, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "%matplotlib inline # 载入matplotlib 库" + ] + }, + { + "cell_type": "code", + "execution_count": 370, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 370, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXQAAAD8CAYAAABn919SAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nINABIAkCHQCSINABIAkCHQCS+D/1TICIOilCMgAAAABJRU5ErkJggg==\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "df.hist(color='k',alpha=0.5)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## 箱形图" + ] + }, + { + "cell_type": "code", + "execution_count": 382, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "n1=np.random.random((100))" + ] + }, + { + "cell_type": "code", + "execution_count": 383, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "array([ 0.67254109, 0.07475273, 0.61216037, 0.78803151, 0.54442616,\n", + " 0.12828188, 0.09975556, 0.66768324, 0.02938222, 0.40425076,\n", + " 0.15158759, 0.64804318, 0.57922253, 0.91760395, 0.40499934,\n", + " 0.04357978, 0.83193892, 0.36505744, 0.39076181, 0.44652398,\n", + " 0.42933184, 0.86588408, 0.33759624, 0.17787462, 0.72616453,\n", + " 0.3527814 , 0.5909218 , 0.82182731, 0.08299143, 0.06425946,\n", + " 0.66343628, 0.85295415, 0.58842008, 0.58876192, 0.2784494 ,\n", + " 0.45011296, 0.68564045, 0.9900975 , 0.13767155, 0.88952819,\n", + " 0.45989228, 0.64718312, 0.09370613, 0.41873627, 0.10014441,\n", + " 0.21287223, 0.20472669, 0.23058839, 0.49783398, 0.43217078,\n", + " 0.00303433, 0.91029586, 0.75229811, 0.14563701, 0.21197828,\n", + " 0.86595768, 0.73982431, 0.24801344, 0.34957526, 0.51523993,\n", + " 0.19484767, 0.34647642, 0.04870149, 0.63819138, 0.2131713 ,\n", + " 0.59834702, 0.16691724, 0.29064127, 0.73536458, 0.76465711,\n", + " 0.16700334, 0.22485507, 0.99144678, 0.43417707, 0.47777792,\n", + " 0.70906769, 0.23285697, 0.83100303, 0.77326663, 0.37270557,\n", + " 0.340129 , 0.31460653, 0.84016206, 0.34645851, 0.60804238,\n", + " 0.2439853 , 0.42445526, 0.46174861, 0.15918603, 0.75185235,\n", + " 0.78760709, 0.52138146, 0.54177471, 0.99374239, 0.77986874,\n", + " 0.04367546, 0.28790282, 0.63738054, 0.0658994 , 0.10573352])" + ] + }, + "execution_count": 383, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "n1" + ] + }, + { + "cell_type": "code", + "execution_count": 390, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "df2=DataFrame(n1.reshape(10,-1))" + ] + }, + { + "cell_type": "code", + "execution_count": 391, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 391, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXcAAAD8CAYAAACMwORRAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n3CWpQP8PzlX9XXixYbIAAAAASUVORK5CYII=\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "df2.boxplot() #箱形图" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 抖动图" + ] + }, + { + "cell_type": "code", + "execution_count": 397, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "def jitter(series,factor):\n", + " z=float(series.max())-float(series.min()) #最大值和最小值差值\n", + " a=float(factor)*z/50 # 抖动距离使用factor 阈值\n", + " return series.apply(lambda x: x+np.random.uniform(-a,a))\n", + " " + ] + }, + { + "cell_type": "code", + "execution_count": 443, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "n1=np.random.randint(50,60,size=100)" + ] + }, + { + "cell_type": "code", + "execution_count": 446, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "s1=DataFrame(n1.reshape((50,2)))" + ] + }, + { + "cell_type": "code", + "execution_count": 447, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "s2=jitter(s1[0],1)" + ] + }, + { + "cell_type": "code", + "execution_count": 448, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "0 52.123510\n", + "1 58.012349\n", + "2 52.824822\n", + "3 53.969722\n", + "4 49.829461\n", + "5 51.029690\n", + "6 55.994653\n", + "7 54.131986\n", + "8 57.976732\n", + "9 57.971420\n", + "10 53.997460\n", + "11 59.145047\n", + "12 55.138424\n", + "13 50.090925\n", + "14 55.146193\n", + "15 56.111534\n", + "16 57.117616\n", + "17 51.170223\n", + "18 50.997385\n", + "19 53.033406\n", + "20 56.960199\n", + "21 50.834710\n", + "22 57.013655\n", + "23 49.928006\n", + "24 58.046489\n", + "25 54.033354\n", + "26 59.105066\n", + "27 50.848948\n", + "28 50.155497\n", + "29 54.850209\n", + "30 51.867595\n", + "31 53.163533\n", + "32 49.917846\n", + "33 59.097243\n", + "34 51.133678\n", + "35 53.931907\n", + "36 53.044376\n", + "37 53.964997\n", + "38 52.045519\n", + "39 52.834286\n", + "40 59.138420\n", + "41 57.074624\n", + "42 57.972544\n", + "43 50.149032\n", + "44 59.179960\n", + "45 56.947917\n", + "46 56.078795\n", + "47 58.033293\n", + "48 51.158460\n", + "49 52.075584\n", + "Name: 0, dtype: float64" + ] + }, + "execution_count": 448, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s2" + ] + }, + { + "cell_type": "code", + "execution_count": 449, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "s3=jitter(s1[1],1)" + ] + }, + { + "cell_type": "code", + "execution_count": 450, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "0 55.067653\n", + "1 49.905900\n", + "2 58.020886\n", + "3 55.895488\n", + "4 52.837326\n", + "5 58.911006\n", + "6 58.820179\n", + "7 50.105592\n", + "8 54.167879\n", + "9 54.135004\n", + "10 50.847848\n", + "11 49.858170\n", + "12 54.864867\n", + "13 55.070589\n", + "14 56.917822\n", + "15 51.091862\n", + "16 50.907922\n", + "17 56.978524\n", + "18 49.988693\n", + "19 50.121551\n", + "20 57.155825\n", + "21 58.912528\n", + "22 56.016979\n", + "23 53.083853\n", + "24 56.027485\n", + "25 53.945993\n", + "26 53.127822\n", + "27 55.952568\n", + "28 59.175573\n", + "29 53.873568\n", + "30 53.128513\n", + "31 58.047874\n", + "32 51.884349\n", + "33 57.165780\n", + "34 52.179848\n", + "35 57.945012\n", + "36 53.837373\n", + "37 49.904352\n", + "38 56.927702\n", + "39 58.857475\n", + "40 59.047213\n", + "41 58.902717\n", + "42 53.888954\n", + "43 52.831127\n", + "44 58.159211\n", + "45 50.884329\n", + "46 59.010744\n", + "47 57.959840\n", + "48 58.061866\n", + "49 52.138035\n", + "Name: 1, dtype: float64" + ] + }, + "execution_count": 450, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s3" + ] + }, + { + "cell_type": "code", + "execution_count": 451, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "# 散点图" + ] + }, + { + "cell_type": "code", + "execution_count": 452, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "df2=s1" + ] + }, + { + "cell_type": "code", + "execution_count": 453, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "df2[0]=s2\n", + "df2[1]=s3" + ] + }, + { + "cell_type": "code", + "execution_count": 454, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
01
052.12351055.067653
158.01234949.905900
252.82482258.020886
353.96972255.895488
449.82946152.837326
551.02969058.911006
655.99465358.820179
754.13198650.105592
857.97673254.167879
957.97142054.135004
1053.99746050.847848
1159.14504749.858170
1255.13842454.864867
1350.09092555.070589
1455.14619356.917822
1556.11153451.091862
1657.11761650.907922
1751.17022356.978524
1850.99738549.988693
1953.03340650.121551
2056.96019957.155825
2150.83471058.912528
2257.01365556.016979
2349.92800653.083853
2458.04648956.027485
2554.03335453.945993
2659.10506653.127822
2750.84894855.952568
2850.15549759.175573
2954.85020953.873568
3051.86759553.128513
3153.16353358.047874
3249.91784651.884349
3359.09724357.165780
3451.13367852.179848
3553.93190757.945012
3653.04437653.837373
3753.96499749.904352
3852.04551956.927702
3952.83428658.857475
4059.13842059.047213
4157.07462458.902717
4257.97254453.888954
4350.14903252.831127
4459.17996058.159211
4556.94791750.884329
4656.07879559.010744
4758.03329357.959840
4851.15846058.061866
4952.07558452.138035
\n", + "
" + ], + "text/plain": [ + " 0 1\n", + "0 52.123510 55.067653\n", + "1 58.012349 49.905900\n", + "2 52.824822 58.020886\n", + "3 53.969722 55.895488\n", + "4 49.829461 52.837326\n", + "5 51.029690 58.911006\n", + "6 55.994653 58.820179\n", + "7 54.131986 50.105592\n", + "8 57.976732 54.167879\n", + "9 57.971420 54.135004\n", + "10 53.997460 50.847848\n", + "11 59.145047 49.858170\n", + "12 55.138424 54.864867\n", + "13 50.090925 55.070589\n", + "14 55.146193 56.917822\n", + "15 56.111534 51.091862\n", + "16 57.117616 50.907922\n", + "17 51.170223 56.978524\n", + "18 50.997385 49.988693\n", + "19 53.033406 50.121551\n", + "20 56.960199 57.155825\n", + "21 50.834710 58.912528\n", + "22 57.013655 56.016979\n", + "23 49.928006 53.083853\n", + "24 58.046489 56.027485\n", + "25 54.033354 53.945993\n", + "26 59.105066 53.127822\n", + "27 50.848948 55.952568\n", + "28 50.155497 59.175573\n", + "29 54.850209 53.873568\n", + "30 51.867595 53.128513\n", + "31 53.163533 58.047874\n", + "32 49.917846 51.884349\n", + "33 59.097243 57.165780\n", + "34 51.133678 52.179848\n", + "35 53.931907 57.945012\n", + "36 53.044376 53.837373\n", + "37 53.964997 49.904352\n", + "38 52.045519 56.927702\n", + "39 52.834286 58.857475\n", + "40 59.138420 59.047213\n", + "41 57.074624 58.902717\n", + "42 57.972544 53.888954\n", + "43 50.149032 52.831127\n", + "44 59.179960 58.159211\n", + "45 56.947917 50.884329\n", + "46 56.078795 59.010744\n", + "47 58.033293 57.959840\n", + "48 51.158460 58.061866\n", + "49 52.075584 52.138035" + ] + }, + "execution_count": 454, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df2" + ] + }, + { + "cell_type": "code", + "execution_count": 460, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYIAAAEKCAYAAAAfGVI8AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAAAAAElFTkSuQmCC\n", + "text/plain": [ + "" + ] + }, + "execution_count": 460, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYIAAAEKCAYAAAAfGVI8AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAAAAAElFTkSuQmCC\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "df2.plot(kind='scatter',x=1,y=0,alpha=0.5).get_figure()" + ] + }, + { + "cell_type": "code", + "execution_count": 461, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYIAAAEKCAYAAAAfGVI8AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAAAAAElFTkSuQmCC\n", + "text/plain": [ + "" + ] + }, + "execution_count": 461, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYIAAAEKCAYAAAAfGVI8AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAAAAAElFTkSuQmCC\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "s1.plot(kind='scatter',x=1,y=0,alpha=0.5).get_figure()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 2", + "language": "python", + "name": "python2" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 2 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython2", + "version": "2.7.13" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +} diff --git a/13-python-math/math-analysis.ipynb b/13-python-math/math-analysis.ipynb new file mode 100644 index 00000000..8620ae24 --- /dev/null +++ b/13-python-math/math-analysis.ipynb @@ -0,0 +1,141 @@ +{ + "cells": [ + { + "cell_type": "heading", + "metadata": { + "collapsed": true + }, + "level": 1, + "source": [ + "指数函数和对数函数的曲线图" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "metadata": {}, + "outputs": [], + "source": [ + "import numpy as np\n", + "import matplotlib as mpl\n", + "import matplotlib.pyplot as plt\n", + "import math\n", + "from mpl_toolkits.mplot3d import Axes3D" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[0.05 0.1 0.15 0.2 0.25 0.3 0.35 0.4 0.45 0.5 0.55 0.6 0.65 0.7\n 0.75 0.8 0.85 0.9 0.95 1. 1.05 1.1 1.15 1.2 1.25 1.3 1.35 1.4\n 1.45 1.5 1.55 1.6 1.65 1.7 1.75 1.8 1.85 1.9 1.95 2. 2.05 2.1\n 2.15 2.2 2.25 2.3 2.35 2.4 2.45 2.5 2.55 2.6 2.65 2.7 2.75 2.8\n 2.85 2.9 2.95]\n" + ] + } + ], + "source": [ + "x = np.arange(0.05,3,0.05)\n", + "y1 = [math.pow(2, i) for i in x]\n", + "y2 = [math.log(i, 2) for i in x]\n", + "plt.plot(x, y1, linewidth=2,color=\"g\", label='2^x')\n", + "plt.plot(x, y2, linewidth=2,color=\"r\", label='log2(x)')\n", + "plt.legend(loc='lower right') ###在右下角画出label\n", + "plt.xlim(1,3) ###限制x轴坐标\n", + "plt.grid(True)\n", + "plt.show()" + ] + }, + { + "cell_type": "heading", + "metadata": {}, + "level": 1, + "source": [ + "y=x^2 曲线图" + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "metadata": {}, + "outputs": [], + "source": [ + "x = np.arange(-10, 11, 0.5)\n", + "y2 = [math.pow(i, 2) for i in x]\n", + "plt.plot(x, y2, linewidth=2, color='g', label='$y=x^2$')\n", + "plt.plot([1], [0], 'ro')\n", + "plt.legend(loc='lower right')\n", + "plt.xlim(-10, 10)\n", + "plt.grid(True)\n", + "plt.show()\n" + ] + }, + { + "cell_type": "heading", + "metadata": {}, + "level": 1, + "source": [ + "sin 函数和cos 函数" + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "metadata": {}, + "outputs": [], + "source": [ + "def f(x):\n", + " return math.sin(x)\n", + "\n", + "def h(x):\n", + " return math.cos(x)\n", + "\n", + "def g(x):\n", + " a = math.sin(x)\n", + " return a * -1\n", + "\n", + "x = np.arange(-5, 5, 0.05)\n", + "y = [f(i) for i in x]\n", + "y2 = [h(i) for i in x]\n", + "y3 = [g(i) for i in x]\n", + "plt.plot(x, y, linewidth=2, color='r', label=u'函数y=sin(x)')\n", + "plt.plot(x, y2, linewidth=2, color='g', label=u'一阶导数y=cos(x)')\n", + "plt.plot(x, y3, linewidth=2, color='b', label=u'二阶导数y=-sin(x)')\n", + "plt.plot([-5, 5], [0, 0], '--', color='#666666')\n", + "plt.legend(loc='lower right')\n", + "plt.grid(True)\n", + "plt.show()\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 2", + "language": "python", + "name": "python2" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 2 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython2", + "version": "2.7.6" + } + }, + "nbformat": 4, + "nbformat_minor": 0 +} diff --git a/sklearn-study.ipynb b/sklearn-study.ipynb new file mode 100644 index 00000000..9217074a --- /dev/null +++ b/sklearn-study.ipynb @@ -0,0 +1,264 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# 数据预处理" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": {}, + "outputs": [], + "source": [ + "from sklearn.preprocessing import StandardScaler,Normalizer,MinMaxScaler,OneHotEncoder\n", + "import numpy as np" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "metadata": { + "collapsed": true + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[[-1.22474487 -1.22474487]\n", + " [ 0. 0. ]\n", + " [ 1.22474487 1.22474487]]\n" + ] + } + ], + "source": [ + "###标准化，是特征值 服从正态分布，高斯分布\n", + "data =[[0,1],[1,2],[2,3]]\n", + "scaler = StandardScaler()\n", + "scaler.fit(data) ##求得期望和方差\n", + "print(scaler.transform(data)) ##使用期望和方差对数据进行处理" + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Normalizer(copy=True, norm='l2')\n" + ] + }, + { + "data": { + "text/plain": [ + "array([[ 0.40824829, -0.40824829, 0.81649658],\n", + " [ 1. , 0. , 0. ],\n", + " [ 0. , 0.70710678, -0.70710678]])" + ] + }, + "execution_count": 17, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "##Normalization 使用范数，将入参正则化到 [0,1] 之间\n", + "X = [[ 1., -1., 2.], [2., 0., 0.], [ 0., 1., -1.]]\n", + "normalizer = Normalizer().fit(X)\n", + "print(normalizer)\n", + "normalizer.fit_transform(X)" + ] + }, + { + "cell_type": "code", + "execution_count": 22, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[[0.5 0. 1. ]\n", + " [1. 0.5 0.33333333]\n", + " [0. 1. 0. ]]\n", + "[2. 1. 2.]\n", + "[ 0. -1. -1.]\n" + ] + } + ], + "source": [ + "##MinMaxScaler 将特征值数据压缩在0 到1 之间\n", + "yData = [[ 1., -1., 2.],[ 2., 0., 0.], [ 0., 1., -1.]]\n", + "maxMinScaler = MinMaxScaler()\n", + "maxMinScaler.fit(yData)\n", + "print(maxMinScaler.fit_transform(yData))\n", + "print(maxMinScaler.data_max_)\n", + "print(maxMinScaler.data_min_)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# 文档型转换成向量" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": {}, + "outputs": [], + "source": [ + "from sklearn.feature_extraction.text import TfidfVectorizer\n" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": {}, + "outputs": [], + "source": [ + " corpus = [\n", + "... 'This is the first document.',\n", + "... 'This is the second second document.',\n", + "... 'And the third one.',\n", + "... 'Is this the first document?',\n", + "... ]" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "metadata": {}, + "outputs": [], + "source": [ + "vectorizer = TfidfVectorizer()\n", + "X = vectorizer.fit_transform(corpus)" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "array([[0. , 0.43877674, 0.54197657, 0.43877674, 0. ,\n", + " 0. , 0.35872874, 0. , 0.43877674],\n", + " [0. , 0.27230147, 0. , 0.27230147, 0. ,\n", + " 0.85322574, 0.22262429, 0. , 0.27230147],\n", + " [0.55280532, 0. , 0. , 0. , 0.55280532,\n", + " 0. , 0.28847675, 0.55280532, 0. ],\n", + " [0. , 0.43877674, 0.54197657, 0.43877674, 0. ,\n", + " 0. , 0.35872874, 0. , 0.43877674]])" + ] + }, + "execution_count": 7, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "X.toarray()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# 离散数据转换成向量（独热编码-OneHotEncode ：1 of k(哑变量)）" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "array([[1., 0., 1., 0., 0., 0., 0., 0., 1.],\n", + " [0., 1., 0., 1., 0., 1., 0., 0., 0.],\n", + " [1., 0., 0., 0., 1., 0., 1., 0., 0.],\n", + " [0., 1., 1., 0., 0., 0., 0., 1., 0.]])" + ] + }, + "execution_count": 9, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "#sex:{male, female, other}\n", + "\n", + "enc = OneHotEncoder()\n", + "enc.fit([[0, 0, 3], [1, 1, 0], [0, 2, 1], [1, 0, 2]])\n", + "enc.transform([[0, 0, 3], [1, 1, 0], [0, 2, 1], [1, 0, 2]]).toarray()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "解释独热编码原理：每一列代表一个类别, 第一列 为 0 1 0 1， 分类为 0 1，第二列分类为： 0 1 2； 第三列分类为： 0 1 2 3\n", + "所以对[0,0,3] 编码 为 1 0 1 0 0 0 0 0 1（第一列 0 出现为 1 0 ， 1 出现为0 1）" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# 多项式 PolynomialFeatures()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "模型评价：\n", + "分类模型：\n", + " ROC曲线\n", + " AUC 值\n", + " 混淆矩阵\n", + " 准确率\n", + " 召回率\n", + " " + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.6.4" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +}