{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "import numpy as np\n", "\n", "import pandas as pd" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "from pandas import Series,DataFrame" ] }, { "cell_type": "code", "execution_count": 5, "metadata": { "scrolled": false }, "outputs": [ { "data": { "text/plain": [ "Math 120\n", "Python 136\n", "En 128\n", "Chinese 99\n", "dtype: int64" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# 创建\n", "# Series是一维的数据\n", "s = Series(data=[120,136,128,99], index=['Math','Python','En','Chinese'])\n", "s" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "(4,)" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "s.shape" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([120, 136, 128, 99])" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "v = s.values\n", "v" ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "numpy.ndarray" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "type(v)" ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "120.75" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "s.mean()" ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "136" ] }, "execution_count": 10, "metadata": {}, "output_type": "execute_result" } ], "source": [ "s.max()" ] }, { "cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "15.903353943953666" ] }, "execution_count": 11, "metadata": {}, "output_type": "execute_result" } ], "source": [ "s.std()" ] }, { "cell_type": "code", "execution_count": 20, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Math 122\n", "Python 138\n", "En 130\n", "Chinese 101\n", "dtype: int64" ] }, "execution_count": 20, "metadata": {}, "output_type": "execute_result" } ], "source": [ "s.add(1)\n", "s" ] }, { "cell_type": "code", "execution_count": 21, "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", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
PythonEnMath
a10912023
b543954
c9722106
d21963
e23145147
f806283
h7031134
i13251115
j95143111
k66947
\n", "
" ], "text/plain": [ " Python En Math\n", "a 109 120 23\n", "b 54 39 54\n", "c 97 22 106\n", "d 21 96 3\n", "e 23 145 147\n", "f 80 62 83\n", "h 70 31 134\n", "i 132 51 115\n", "j 95 143 111\n", "k 66 94 7" ] }, "execution_count": 21, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# DataFrame是二维的数据\n", "# excel就非常相似\n", "# 所有进行数据分析，数据挖掘的工具最基础的结果：行和列，行表示样本，列表示的是属性\n", "df = DataFrame(data=np.random.randint(0, 150, size=(10, 3)), index=list('abcdefhijk'), columns=['Python', 'En', 'Math'])\n", "df" ] }, { "cell_type": "code", "execution_count": 13, "metadata": { "scrolled": true }, "outputs": [ { "data": { "text/plain": [ "(10, 3)" ] }, "execution_count": 13, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.shape" ] }, { "cell_type": "code", "execution_count": 15, "metadata": { "collapsed": true }, "outputs": [ { "data": { "text/plain": [ "array([[113, 116, 75],\n", " [ 19, 145, 23],\n", " [ 57, 107, 113],\n", " [ 95, 3, 66],\n", " [ 28, 121, 120],\n", " [141, 85, 132],\n", " [124, 39, 10],\n", " [ 80, 35, 17],\n", " [ 68, 99, 31],\n", " [ 74, 12, 11]])" ] }, "execution_count": 15, "metadata": {}, "output_type": "execute_result" } ], "source": [ "v = df.values\n", "v" ] }, { "cell_type": "code", "execution_count": 16, "metadata": { "scrolled": true }, "outputs": [ { "data": { "text/plain": [ "Python 79.9\n", "En 76.2\n", "Math 59.8\n", "dtype: float64" ] }, "execution_count": 16, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.mean()" ] }, { "cell_type": "code", "execution_count": 17, "metadata": { "scrolled": true }, "outputs": [ { "data": { "text/plain": [ "Python 141\n", "En 145\n", "Math 132\n", "dtype: int32" ] }, "execution_count": 17, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.max()" ] }, { "cell_type": "code", "execution_count": 18, "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", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
PythonEnMath
a11311675
b1914523
c57107113
d95366
e28121120
f14185132
h1243910
i803517
j689931
k741211
\n", "
" ], "text/plain": [ " Python En Math\n", "a 113 116 75\n", "b 19 145 23\n", "c 57 107 113\n", "d 95 3 66\n", "e 28 121 120\n", "f 141 85 132\n", "h 124 39 10\n", "i 80 35 17\n", "j 68 99 31\n", "k 74 12 11" ] }, "execution_count": 18, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df" ] }, { "cell_type": "code", "execution_count": 22, "metadata": { "scrolled": true }, "outputs": [ { "data": { "text/plain": [ "Python 74.7\n", "En 80.3\n", "Math 78.3\n", "dtype: float64" ] }, "execution_count": 22, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.mean(axis=0)" ] }, { "cell_type": "code", "execution_count": 23, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "a 84.000000\n", "b 49.000000\n", "c 75.000000\n", "d 40.000000\n", "e 105.000000\n", "f 75.000000\n", "h 78.333333\n", "i 99.333333\n", "j 116.333333\n", "k 55.666667\n", "dtype: float64" ] }, "execution_count": 23, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.mean(axis=1)" ] }, { "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": "3.7.7" } }, "nbformat": 4, "nbformat_minor": 2 }