氪金预测basline（单特征）

在评论区看到的大佬评论： 

一脸懵逼，仅用单特征72。膜拜。。

import pandas as pd
from sklearn.linear_model import LinearRegression
# 文件名
train_file='tap_fun_train.csv'
test_file='tap_fun_test.csv'
train_data=pd.read_csv(train_file)
test_data=pd.read_csv(test_file)
y = train_data.pop('prediction_pay_price')
drop = ['user_id', 'register_time']
train_idx=train_data[drop]
test_idx=test_data[drop]
train_data=train_data.drop(drop, axis=1)
test_data=test_data.drop(drop, axis=1)
cols = ['pay_price']
lr = LinearRegression()
lr.fit(train_data[cols], y)
y_prob = lr.predict(test_data[cols])
test_idx['prediction_pay_price'] = y_prob
print(test_idx.prediction_pay_price.value_counts())
test_idx[['user_id','prediction_pay_price']].to_csv("subbasline.csv", index=False)