【机器学习】 应用简例 随机森林 交叉验证 网格化搜索

%matplotlib inline
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
from sklearn.model_selection import GridSearchCV
from sklearn.model_selection import cross_val_score
from sklearn.model_selection import GridSearchCV

导入数据

# 从excel表导入数据
df_t = pd.read_excel(r'D:\EdgeDownloadPlace\3dd40612152202ee8440f82a3d277008\train.xlsx')

# 删除uid列
df_t = df_t.drop(columns='uid')

# 把数据中的'?'换成每一列的众数
for col in df_t.columns:
    idx = df_t[col].value_counts().index
    df_t[col][df_t[col] == '?'] = idx[0] if idx[0] != '?' else idx[1]

# 把pandas.DataFrame数据转化为numpy.darray数据 元素类型为np.float32
arr_t = df_t.values.astype(np.float32)

交叉验证找分数最高的n_estimators

score_tt = []
for i in range(0,300,15):
    rfc = RandomForestClassifier(n_estimators = i+1