集成学习之随机森林分类器

# -*- coding:utf-8 -*-
import numpy as np
from sklearn import datasets, ensemble
from sklearn.model_selection import train_test_split
from sklearn.model_selection import cross_val_score
import matplotlib.pyplot as plt
import pandas as pd

from sklearn.metrics import accuracy_score

#此处是如何导入本地数据作为训练数据
#data = pd.read_csv(‘iris.data‘)
#print(data.head(5))

#attributes=data[[‘sl‘,‘sw‘,‘pl‘,‘pw‘]]  #前四列属性简化为sl，sw，pl，pw
#types=data[‘type‘] #第5列属性为鸢尾花的类别

iris = datasets.load_iris()
iris_X = iris.data
iris_y = iris.target
feature_names = iris.feature_names
target_names = iris.feature_names

#print(iris_X[:4,:])

X_train,X_test,y_train,y_test = train_test_split(iris_X,iris_y,test_size = 0.3)

print("\n训练集样本大小：", X_train.shape)
print("训练集标签大小：", y_train.shape)
print("测试集样本大小：", X_test.shape)
print("测试集标签大小：", y_test.shape)

#交叉验证，看看分类器选择几个的时候模型泛化的结果最佳，根据图来选择最佳的分类器个数
‘‘‘
cv_scores = []
k_range = range(1,20)

for n in k_range:
    clf = ensemble.RandomForestClassifier(max_depth=n, n_estimators=1, max_features=1)
    scores = cross_val_score(clf,X_train,y_train,cv=10,scoring=‘accuracy‘)
    cv_scores.append(scores.mean())
plt.plot(k_range,cv_scores)
plt.xlabel(‘K‘)
plt.ylabel(‘Accuracy‘)
plt.show()
‘‘‘
#clf = ensemble.RandomForestClassifier(max_depth=5, n_estimators=1, max_features=1)
#clf.fit(X_train,y_train)

#print(knn.predict(X_test))
#print(clf.score(X_test,y_test))


#X=np.array(X_train)
#Y=np.array(y_train)
clf = ensemble.RandomForestClassifier(max_depth=9, n_estimators=1, max_features=1)
clf.fit(iris_X,iris_y)
#print(clf.score(X_train,y_train))
#print(clf.score(X_test,y_test))
print(clf.predict(
[[5.1,3.5,1.4,0.2],
[4.9,3.0,1.4,0.2],
[5.7,3.0,4.2,1.2],
[5.7,2.9,4.2,1.3],
[5.7,2.8,4.1,1.3],
[6.3,3.3,6.0,2.5],
[5.8,2.7,5.1,1.9],
[6.2,2.9,4.3,1.3],
[5.1,2.5,3.0,1.1],
[7.1,3.0,5.9,2.1],
[6.3,2.9,5.6,1.8],
[6.5,3.0,5.8,2.2],
[4.7,3.2,1.3,0.2],
[4.6,3.1,1.5,0.2]]
))