python進行機器學習（五）之模型打分

一、畫出模型的殘差值分布情況

 

#!/usr/bin/python

import pandas as pd
import numpy as np
import csv as csv
import matplotlib
import matplotlib.pyplot as plt
from sklearn.linear_model import Ridge, RidgeCV, ElasticNet, LassoCV, LassoLarsCV
from sklearn.model_selection import cross_val_score



train = pd.read_csv('train.csv', header=0)        # Load the train file into a dataframe
df = pd.get_dummies(train.iloc[:,1:-1])
df = df.fillna(df.mean())

X_train = df
y = train.price



def rmse_cv(model):
    rmse= np.sqrt(-cross_val_score(model, X_train, y, scoring="neg_mean_squared_error", cv = 3))
    return(rmse)

#調用LassoCV函數，並進行交叉驗證，默認cv=3
model_lasso = LassoCV(alphas = [0.1,1,0.001, 0.0005]).fit(X_train, y)



matplotlib.rcParams['figure.figsize'] = (6.0, 6.0)

#將模型預測的值與真實值作為兩列放在DataFrame里面
preds = pd.DataFrame({"preds":model_lasso.predict(X_train), "true":y})


#真實值與預測值之間的差值作為一個新列
preds["residuals"] = preds["true"] - preds["preds"]

print(preds)

#預測值作為X軸，殘差值作為y軸，畫出圖形
preds.plot(x = "preds", y = "residuals",kind = "scatter")
plt.show()

    

注：本樣例只是為了說明問題，只用了幾行數據來預測畫圖。

正常來講，一個好的模型，殘差值應該分布比較集中，而且基本都在0上下稍微浮動，表明殘差值都比較小。