場景：計算訓練特徵和目標之間的相關係數，用於判斷是否加入訓練。

參考程式碼：

# -*- coding: utf-8 -*-

import pandas as pd
import time
from sklearn import tree
import numpy as np
from sklearn import metrics  
from sklearn.linear_model import LinearRegression
from scipy.stats import pearsonr
from sklearn.feature_selection import SelectKBest
from sklearn.feature_selection import f_regression

def main():
    #載入標記資料
    label_ds=pd.read_csv(r"link_train_0726.txt",sep='\t',encoding='utf8',\
                         names=['link_id','length','width','link_class','start_date','week','time_interval','time_slot','travel_time',\
                                'avg_travel_time','sd_travel_time','inlinks_num','outlinks_num']) 
    label_ds["link_id"] = label_ds["link_id"].astype("string")
    label_ds["length"] = label_ds["length"].astype("int")
    label_ds["width"] = label_ds["width"].astype("int")
    label_ds["link_class"] = label_ds["link_class"].astype("int")
    label_ds["start_date"] = label_ds["start_date"].astype("string")
    label_ds["week"] = label_ds["week"].astype("int")
    label_ds["time_interval"] = label_ds["time_interval"].astype("string")
    label_ds["time_slot"] = label_ds["time_slot"].astype("int")
    label_ds["travel_time"] = label_ds["travel_time"].astype("float")
    label_ds["avg_travel_time"] = label_ds["avg_travel_time"].astype("float")
    label_ds["sd_travel_time"] = label_ds["sd_travel_time"].astype("float")
    label_ds["inlinks_num"] = label_ds["inlinks_num"].astype("int")
    label_ds["outlinks_num"] = label_ds["outlinks_num"].astype("int")
    #載入預測資料   
    unlabel_ds=pd.read_csv(r"link_test_0726.txt",sep='\t',encoding='utf8',\
                         names=['link_id','length','width','link_class','start_date','week','time_interval','time_slot',\
                                'avg_travel_time','sd_travel_time','inlinks_num','outlinks_num']) 
    unlabel_ds["link_id"] = unlabel_ds["link_id"].astype("string")
    unlabel_ds["length"] = unlabel_ds["length"].astype("int")
    unlabel_ds["width"] = unlabel_ds["width"].astype("int")
    unlabel_ds["link_class"] = unlabel_ds["link_class"].astype("int")
    unlabel_ds["start_date"] = unlabel_ds["start_date"].astype("string")
    unlabel_ds["week"] = unlabel_ds["week"].astype("int")
    unlabel_ds["time_interval"] = unlabel_ds["time_interval"].astype("string")
    unlabel_ds["time_slot"] = unlabel_ds["time_slot"].astype("int")
    unlabel_ds["avg_travel_time"] = unlabel_ds["avg_travel_time"].astype("float")
    unlabel_ds["sd_travel_time"] = unlabel_ds["sd_travel_time"].astype("float")
    unlabel_ds["inlinks_num"] = unlabel_ds["inlinks_num"].astype("int")
    unlabel_ds["outlinks_num"] = unlabel_ds["outlinks_num"].astype("int")
    
    #提取訓練集、驗證集、測試集
    train_df=label_ds.loc[(pd.to_datetime(label_ds["start_date"])<'2016-06-01')]#訓練集
    print "訓練集，有", train_df.shape[0], "行", train_df.shape[1], "列"
    valid_df=label_ds.loc[(pd.to_datetime(label_ds["start_date"])>='2016-06-01')]#驗證集train_df.sample(frac=0.2)
    print "驗證集，有", valid_df.shape[0], "行", valid_df.shape[1], "列"
    test_df=unlabel_ds#測試集
    print "測試集，有", test_df.shape[0], "行", test_df.shape[1], "列"
    #特徵選擇
    p_X=train_df['outlinks_num']#訓練屬性
    p_Y=train_df['travel_time']#目標屬性
    p_value=pearsonr(p_X,p_Y)
    print p_value
    #選擇相關性最強的k個特徵參與訓練
    #k_feature = f_regression(p_X,p_Y)
    #k_fearture=SelectKBest(lambda X, Y: np.array(map(lambda x:pearsonr(x, Y), X.T)).T, k=9).fit_transform(p_X, p_Y)
    #print k_fearture
    #模型訓練
    train_X=train_df[['length','width','link_class','week','time_slot','avg_travel_time']]
    train_y = train_df['travel_time']#標記
    model_lr=LinearRegression()#tree.DecisionTreeRegressor()
    model_lr.fit(train_X, train_y)   
    #模型驗證
    valid_X=valid_df[['length','width','link_class','week','time_slot','avg_travel_time']]
    valid_y=valid_df['travel_time']
    pre_valid_y=model_lr.predict(valid_X)
    abs_y=abs(pre_valid_y-valid_y)
    abs_error=abs_y.sum()#求和
    #abs_error=sum(list(abs_y))#求和
    print "mape:",abs_error/valid_df.shape[0]
    print "RMSE:",np.sqrt(metrics.mean_squared_error(valid_y, pre_valid_y))#均方差，模型評估
    #模型預測
    test_X = test_df[['length','width','link_class','week','time_slot','avg_travel_time']]  
    test_info = test_df[['link_id','start_date','time_interval']] 
    test_X=test_X.fillna(0)#空值替換為0
    test_y=model_lr.predict(test_X) 
    pre_test_y=pd.DataFrame(test_y,columns=['travel_time']) 
    outset=test_info.join(pre_test_y,how='left')#輸出結果 
    #outset["travel_time"]=outset["travel_time"].apply(lambda x: '{0:.3f}'.format(x))
    outset.to_csv('outit.txt',sep='#',index=False,header=None)#輸出預測資料 
    
#執行
if __name__ == '__main__':  
    start = time.clock()  
    main()
    end = time.clock()  
    print('finish all in %s' % str(end - start)) 
 

scikit-learn庫中：f_regression和SelectKBest用於選擇最佳特徵訓練，可以批量給出前k個特徵。