重拾机器学习3 随机森林及网格搜索

import pandas as pd
from collections import defaultdict
from sklearn.model_selection import cross_val_score, train_test_split
from sklearn.tree import DecisionTreeClassifier
import numpy as np
from sklearn.preprocessing import LabelEncoder
from sklearn.preprocessing import OneHotEncoder
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import GridSearchCV

data_filename = 'D:\\study\\python\\pythondatamining_study\\chapter3\\leagues_NBA_2014_games_games.csv'
# dataset = pd.read_csv(data_filename)

# 如果单切几行的数据，不切片属性值时，pandas可以直接切片dataset[:5]，也可以用loc和iloc切片data.iloc[:5]
# 切片属性是且属性名称有字符串时用loc切片  print(dataset.loc[:5, 'Date':'PTS'])
#  如上，也可以用数字代替字符串  print(dataset.iloc[:5, :2])
# 切片属性时直接切片是不行的 如print(dataset[:5, :2])  会报错'(slice(None, 5, None), slice(None, 2, None))' is an invalid key

dataset = pd.read_csv(data_filename, parse_dates=['Date'])  # 这里无需设置跳过行数skiprows=[1, ]这里需要从第1行开始
dataset.columns = ['Date', 'Score type', 'Visitor Team', 'VisitorPts', 'Home Team', 'HomePts', 'OT?', 'Notes']
dataset['HomeWin'] = dataset['VisitorPts'] < dataset['HomePts']
y_true = dataset['Home