机器学习算法导论---DTR共享单车需求问题的决策树回归问题

import numpy as np
import pandas as pd
from sklearn.model_selection import train_test_split
from machine_learning.lib.decision_tree_regressor import DecisionTreeRegressor
from sklearn.metrics import r2_score

def get_data():
    df=pd.read_csv("./bike.csv")
    df.datetime=df.datetime.apply(pd.to_datetime)
    df['hour']=df.datetime.apply(lambda x:x.hour)
    y=df['count'].values
    df.drop(['datetime','casual','registered','count'],1,inplace=True)
    X=df.values
    return X,y
X,y=get_data()
X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.5,random_state=0)

model=DecisionTreeRegressor(max_depth=2)
model.fit(X_train,y_train)
y_pred=model.predict(X_test)
# print('r2={}'.format(get_r2(y_test,y_pred)))