Python_sklearn機器學習庫學習筆記（一）_一元回歸

一、引入相關庫

%matplotlib inline
import matplotlib.pyplot as plt
from matplotlib.font_manager import FontProperties
font=FontProperties(fname=r'c:/windows/fonts/msyh.ttf',size=10)

二、一元回歸范例

def runplt():
    plt.figure()
    plt.title(u'披薩價格與直徑數據',fontproperties=font)
    plt.xlabel(u'直徑(英寸)',fontproperties=font)
    plt.ylabel(u'價格(美元)',fontproperties=font)
    plt.axis([0,25,0,25])
    plt.grid(True)#是否顯示網格
    return plt

plt=runplt()
x=[[6],[8],[10],[14],[18]]
y=[[7],[9],[13],[17.5],[18]]
plt.plot(x,y,'k.')
plt.show()

 

 

三、利用sklearn建立一元回歸

from sklearn.linear_model import LinearRegression
#創建並擬合模型
model=LinearRegression()
model.fit(x,y)
print('預測一張12英寸的披薩價格：')

## 波士頓房屋價格，SGDRegressor

import numpy as np
from sklearn.datasets import load_boston
from sklearn.linear_model import SGDRegressor#隨機梯度
from sklearn.cross_validation import cross_val_score
from sklearn.preprocessing import StandardScaler#列歸一化,標准正態分布形式
from sklearn.cross_validation import train_test_split#分割訓練集和測試集，默認值是25%

data=load_boston()
X_train,X_test,y_train,y_test=train_test_split(data.data,data.target)

#歸一化
X_scaler=StandardScaler()
y_scaler=StandardScaler()
X_train=X_scaler.fit_transform(X_train)#訓練並轉換
y_train=y_scaler.fit_transform(y_train)
#對測試樣本歸一轉換
X_test=X_scaler.transform(X_test)
y_test=y_scaler.transform(y_test)

#訓練並測試樣本
regression=SGDRegressor(loss='squared_loss')
scores=cross_val_score(regression,X_train,y_train,cv=5)#cv=5訓練五次
print scores
print 'Cross validation r-squared score:',np.mean(scores)
regression.fit_transform(X_train,y_train)
print 'Test set r-squared score:',regression.score(X_test,y_test)

輸出結果：

[ 0.65592082  0.71571537  0.79468123  0.69650452  0.67266115]
Cross validation r-squared score: 0.707096620395
Test set r-squared score: 0.677424272546