632 lines
13 KiB
Plaintext
632 lines
13 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import numpy as np\n",
|
|
"\n",
|
|
"import pandas as pd"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from pandas import Series,DataFrame"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": []
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"metadata": {
|
|
"scrolled": false
|
|
},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"Math 120\n",
|
|
"Python 136\n",
|
|
"En 128\n",
|
|
"Chinese 99\n",
|
|
"dtype: int64"
|
|
]
|
|
},
|
|
"execution_count": 4,
|
|
"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": 5,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"(4,)"
|
|
]
|
|
},
|
|
"execution_count": 5,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"s.shape"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 6,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"array([120, 136, 128, 99], dtype=int64)"
|
|
]
|
|
},
|
|
"execution_count": 6,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"v = s.values\n",
|
|
"v"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 7,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"numpy.ndarray"
|
|
]
|
|
},
|
|
"execution_count": 7,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"type(v)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 8,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"120.75"
|
|
]
|
|
},
|
|
"execution_count": 8,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"s.mean()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 9,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"136"
|
|
]
|
|
},
|
|
"execution_count": 9,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"s.max()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 10,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"15.903353943953666"
|
|
]
|
|
},
|
|
"execution_count": 10,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"s.std()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 11,
|
|
"metadata": {
|
|
"collapsed": true
|
|
},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"Math 14400\n",
|
|
"Python 18496\n",
|
|
"En 16384\n",
|
|
"Chinese 9801\n",
|
|
"dtype: int64"
|
|
]
|
|
},
|
|
"execution_count": 11,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"s.pow(2)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 12,
|
|
"metadata": {
|
|
"collapsed": true
|
|
},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/html": [
|
|
"<div>\n",
|
|
"<style scoped>\n",
|
|
" .dataframe tbody tr th:only-of-type {\n",
|
|
" vertical-align: middle;\n",
|
|
" }\n",
|
|
"\n",
|
|
" .dataframe tbody tr th {\n",
|
|
" vertical-align: top;\n",
|
|
" }\n",
|
|
"\n",
|
|
" .dataframe thead th {\n",
|
|
" text-align: right;\n",
|
|
" }\n",
|
|
"</style>\n",
|
|
"<table border=\"1\" class=\"dataframe\">\n",
|
|
" <thead>\n",
|
|
" <tr style=\"text-align: right;\">\n",
|
|
" <th></th>\n",
|
|
" <th>Python</th>\n",
|
|
" <th>En</th>\n",
|
|
" <th>Math</th>\n",
|
|
" </tr>\n",
|
|
" </thead>\n",
|
|
" <tbody>\n",
|
|
" <tr>\n",
|
|
" <th>a</th>\n",
|
|
" <td>113</td>\n",
|
|
" <td>116</td>\n",
|
|
" <td>75</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>b</th>\n",
|
|
" <td>19</td>\n",
|
|
" <td>145</td>\n",
|
|
" <td>23</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>c</th>\n",
|
|
" <td>57</td>\n",
|
|
" <td>107</td>\n",
|
|
" <td>113</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>d</th>\n",
|
|
" <td>95</td>\n",
|
|
" <td>3</td>\n",
|
|
" <td>66</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>e</th>\n",
|
|
" <td>28</td>\n",
|
|
" <td>121</td>\n",
|
|
" <td>120</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>f</th>\n",
|
|
" <td>141</td>\n",
|
|
" <td>85</td>\n",
|
|
" <td>132</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>h</th>\n",
|
|
" <td>124</td>\n",
|
|
" <td>39</td>\n",
|
|
" <td>10</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>i</th>\n",
|
|
" <td>80</td>\n",
|
|
" <td>35</td>\n",
|
|
" <td>17</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>j</th>\n",
|
|
" <td>68</td>\n",
|
|
" <td>99</td>\n",
|
|
" <td>31</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>k</th>\n",
|
|
" <td>74</td>\n",
|
|
" <td>12</td>\n",
|
|
" <td>11</td>\n",
|
|
" </tr>\n",
|
|
" </tbody>\n",
|
|
"</table>\n",
|
|
"</div>"
|
|
],
|
|
"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": 12,
|
|
"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": [
|
|
"<div>\n",
|
|
"<style scoped>\n",
|
|
" .dataframe tbody tr th:only-of-type {\n",
|
|
" vertical-align: middle;\n",
|
|
" }\n",
|
|
"\n",
|
|
" .dataframe tbody tr th {\n",
|
|
" vertical-align: top;\n",
|
|
" }\n",
|
|
"\n",
|
|
" .dataframe thead th {\n",
|
|
" text-align: right;\n",
|
|
" }\n",
|
|
"</style>\n",
|
|
"<table border=\"1\" class=\"dataframe\">\n",
|
|
" <thead>\n",
|
|
" <tr style=\"text-align: right;\">\n",
|
|
" <th></th>\n",
|
|
" <th>Python</th>\n",
|
|
" <th>En</th>\n",
|
|
" <th>Math</th>\n",
|
|
" </tr>\n",
|
|
" </thead>\n",
|
|
" <tbody>\n",
|
|
" <tr>\n",
|
|
" <th>a</th>\n",
|
|
" <td>113</td>\n",
|
|
" <td>116</td>\n",
|
|
" <td>75</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>b</th>\n",
|
|
" <td>19</td>\n",
|
|
" <td>145</td>\n",
|
|
" <td>23</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>c</th>\n",
|
|
" <td>57</td>\n",
|
|
" <td>107</td>\n",
|
|
" <td>113</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>d</th>\n",
|
|
" <td>95</td>\n",
|
|
" <td>3</td>\n",
|
|
" <td>66</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>e</th>\n",
|
|
" <td>28</td>\n",
|
|
" <td>121</td>\n",
|
|
" <td>120</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>f</th>\n",
|
|
" <td>141</td>\n",
|
|
" <td>85</td>\n",
|
|
" <td>132</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>h</th>\n",
|
|
" <td>124</td>\n",
|
|
" <td>39</td>\n",
|
|
" <td>10</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>i</th>\n",
|
|
" <td>80</td>\n",
|
|
" <td>35</td>\n",
|
|
" <td>17</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>j</th>\n",
|
|
" <td>68</td>\n",
|
|
" <td>99</td>\n",
|
|
" <td>31</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>k</th>\n",
|
|
" <td>74</td>\n",
|
|
" <td>12</td>\n",
|
|
" <td>11</td>\n",
|
|
" </tr>\n",
|
|
" </tbody>\n",
|
|
"</table>\n",
|
|
"</div>"
|
|
],
|
|
"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": 19,
|
|
"metadata": {
|
|
"scrolled": true
|
|
},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"Python 79.9\n",
|
|
"En 76.2\n",
|
|
"Math 59.8\n",
|
|
"dtype: float64"
|
|
]
|
|
},
|
|
"execution_count": 19,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"df.mean(axis = 0)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 20,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"a 101.333333\n",
|
|
"b 62.333333\n",
|
|
"c 92.333333\n",
|
|
"d 54.666667\n",
|
|
"e 89.666667\n",
|
|
"f 119.333333\n",
|
|
"h 57.666667\n",
|
|
"i 44.000000\n",
|
|
"j 66.000000\n",
|
|
"k 32.333333\n",
|
|
"dtype: float64"
|
|
]
|
|
},
|
|
"execution_count": 20,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"df.mean(axis = 1)"
|
|
]
|
|
}
|
|
],
|
|
"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": "3.7.3"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 2
|
|
}
|