stark
/
machine_learning
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
main
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from '678d608b54'
${ noResults }
machine_learning/multivariable_linear_regres.../multivariable_linear_regres...

483 lines
10 KiB
Plaintext
Raw Normal View History Unescape Escape

sklearn
6 months ago
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "d60aff11",
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"from sklearn.linear_model import LinearRegression"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "3aafae87",
"metadata": {},
"outputs": [],
"source": [
"df = pd.read_csv(\"multivariable.csv\")"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "5ecbf4af",
"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>area</th>\n",
" <th>age</th>\n",
" <th>bashroom</th>\n",
" <th>price</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>88.54</td>\n",
" <td>5</td>\n",
" <td>1.0</td>\n",
" <td>118.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>93.36</td>\n",
" <td>8</td>\n",
" <td>1.0</td>\n",
" <td>114.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>98.90</td>\n",
" <td>13</td>\n",
" <td>2.0</td>\n",
" <td>102.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>98.58</td>\n",
" <td>5</td>\n",
" <td>2.0</td>\n",
" <td>118.4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>92.26</td>\n",
" <td>5</td>\n",
" <td>2.0</td>\n",
" <td>95.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>88.94</td>\n",
" <td>3</td>\n",
" <td>1.0</td>\n",
" <td>118.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>89.57</td>\n",
" <td>14</td>\n",
" <td>NaN</td>\n",
" <td>127.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" area age bashroom price\n",
"0 88.54 5 1.0 118.0\n",
"1 93.36 8 1.0 114.0\n",
"2 98.90 13 2.0 102.0\n",
"3 98.58 5 2.0 118.4\n",
"4 92.26 5 2.0 95.0\n",
"5 88.94 3 1.0 118.0\n",
"6 89.57 14 NaN 127.0"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df#数据存在NaN，需要处理"
]
},
{
"cell_type": "markdown",
"id": "8cab6f22",
"metadata": {},
"source": [
"$$price = ax_1 + bx_2 + cx_3 + m$$"
]
},
{
"cell_type": "markdown",
"id": "4087cc5f",
"metadata": {},
"source": [
"## 1.数据处理"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "cef313ea",
"metadata": {},
"outputs": [],
"source": [
"median = df.bashroom.median()"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "f59d79bc",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"1.5"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"median#卫生间没有小数，需要向下取整"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "f49989d8",
"metadata": {},
"outputs": [],
"source": [
"df = df.fillna(np.floor(median))"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "ee51756b",
"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>area</th>\n",
" <th>age</th>\n",
" <th>bashroom</th>\n",
" <th>price</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>88.54</td>\n",
" <td>5</td>\n",
" <td>1.0</td>\n",
" <td>118.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>93.36</td>\n",
" <td>8</td>\n",
" <td>1.0</td>\n",
" <td>114.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>98.90</td>\n",
" <td>13</td>\n",
" <td>2.0</td>\n",
" <td>102.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>98.58</td>\n",
" <td>5</td>\n",
" <td>2.0</td>\n",
" <td>118.4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>92.26</td>\n",
" <td>5</td>\n",
" <td>2.0</td>\n",
" <td>95.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>88.94</td>\n",
" <td>3</td>\n",
" <td>1.0</td>\n",
" <td>118.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>89.57</td>\n",
" <td>14</td>\n",
" <td>1.0</td>\n",
" <td>127.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" area age bashroom price\n",
"0 88.54 5 1.0 118.0\n",
"1 93.36 8 1.0 114.0\n",
"2 98.90 13 2.0 102.0\n",
"3 98.58 5 2.0 118.4\n",
"4 92.26 5 2.0 95.0\n",
"5 88.94 3 1.0 118.0\n",
"6 89.57 14 1.0 127.0"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df"
]
},
{
"cell_type": "markdown",
"id": "e41d72fc",
"metadata": {},
"source": [
"## 2.训练模型"
]
},
{
"cell_type": "code",
"execution_count": 20,
"id": "39295dee",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"LinearRegression()"
]
},
"execution_count": 20,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"model = LinearRegression()\n",
"model.fit(df[[\"area\", \"age\", \"bashroom\"]].values, df.price.values)"
]
},
{
"cell_type": "markdown",
"id": "c1b812cb",
"metadata": {},
"source": [
"## 3.模型测试"
]
},
{
"cell_type": "code",
"execution_count": 26,
"id": "636c57cb",
"metadata": {},
"outputs": [],
"source": [
"pred = model.predict(np.array([[105, 2, 1]]))"
]
},
{
"cell_type": "code",
"execution_count": 28,
"id": "4928085a",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([134.39931808])"
]
},
"execution_count": 28,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"pred"
]
},
{
"cell_type": "code",
"execution_count": 23,
"id": "d6dea269",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([ 1.03253137, 0.04233053, -20.81194367])"
]
},
"execution_count": 23,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"model.coef_"
]
},
{
"cell_type": "code",
"execution_count": 24,
"id": "7cd87a3a",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(1.032531365235341, 0.042330533476314436, -20.81194367389132)"
]
},
"execution_count": 24,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"model.coef_[0], model.coef_[1], model.coef_[2]"
]
},
{
"cell_type": "code",
"execution_count": 25,
"id": "a64c1cc5",
"metadata": {},
"outputs": [],
"source": [
"price = model.coef_[0] * 105 + model.coef_[1] * 2 + model.coef_[2]* 1 + model.intercept_"
]
},
{
"cell_type": "code",
"execution_count": 29,
"id": "c02a4f36",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"134.3993180794738"
]
},
"execution_count": 29,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"price"
]
},
{
"cell_type": "code",
"execution_count": 27,
"id": "862d7fab",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([ True])"
]
},
"execution_count": 27,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"price == pred"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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": "3.7.9"
}
},
"nbformat": 4,
"nbformat_minor": 5
}