python进行机器学习（五）之模型打分

一、画出模型的残差值分布情况

#!/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)

#调用LassoCV函数，并进行交叉验证，默认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)

#将模型预测的值与真实值作为两列放在DataFrame里面
preds = pd.DataFrame({"preds":model_lasso.predict(X_train), "true":y})

#真实值与预测值之间的差值作为一个新列
preds["residuals"] = preds["true"] - preds["preds"]

print(preds)

#预测值作为X轴，残差值作为y轴，画出图形
preds.plot(x = "preds", y = "residuals",kind = "scatter")
plt.show()

注：本样例只是为了说明问题，只用了几行数据来预测画图。

正常来讲，一个好的模型，残差值应该分布比较集中，而且基本都在0上下稍微浮动，表明残差值都比较小。