04-11 随机森林代码(葡萄酒质量检测)

随机森林代码(葡萄酒质量检测)

导入模块

import pandas as pd
from sklearn import datasets
from sklearn.preprocessing import LabelEncoder
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score

导入数据

X, y = datasets.load_wine(return_X_y=True)

数据预处理

le = LabelEncoder()
# 把label转换为0和1
y = le.fit_transform(y)

# 训练集和测试集比例为7:3
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.30,  random_state=1)

训练模型

rf = RandomForestClassifier(n_estimators=1000, criterion='gini',
                            max_features='sqrt', min_samples_split=2, bootstrap=True)
rf = rf.fit(X_train, y_train)

度量模型

y_train_pred = rf.predict(X_train)
y_test_pred = rf.predict(X_test)

# 度量随机森林的准确性
tree_train = accuracy_score(y_train, y_train_pred)
tree_test = accuracy_score(y_test, y_test_pred)

print('随机森林训练集和测试集准确度分别为:{:.2f}/{:.2f}'.format(tree_train, tree_test))

随机森林训练集和测试集准确度分别为:1.00/0.98