machine_learn/integr/random_forest.py

# -*- encoding:utf-8 -*-
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import RandomForestRegressor
from sklearn.datasets import load_wine
from sklearn.model_selection import train_test_split
import numpy as np
from sklearn.tree import DecisionTreeRegressor
from sklearn import metrics

'''
参数	含义
criterion	不纯度的衡量指标，有基尼系数和信息熵两种选择
max_depth	树的最大深度，超过最大深度的树枝都会被剪掉
min_samples_leaf	一个节点在分枝后的每个子节点都必须包含至少min_samples_leaf个训练样本，否则分枝就不会发生
min_samples_split	一个节点必须要包含至少min_samples_split个训练样本，这个节点才允许被分枝，否则分枝就不会发生
max_features	max_features限制分枝时考虑的特征个数，超过限制个数的特征都会被舍弃，默认值为总特征个数开平方取整
min_impurity_decrease	限制信息增益的大小，信息增益小于设定数值的分枝不会发生
'''
def demo_wine():
    wine = load_wine()
    #print wine.data
    #print wine.target
    Xtrain, Xtest, Ytrain, Ytest = train_test_split(wine.data,wine.target,test_size=0.3)
    rfc = RandomForestClassifier(random_state=0,n_estimators=10)
    rfc = rfc.fit(Xtrain,Ytrain)
    print(rfc.score(Xtest,Ytest))


def read_data(path):
    with open(path) as f :
        lines=f.readlines()
    lines=[eval(line.strip()) for line in lines]
    X,y=zip(*lines)
    X=np.array(X)
    y=np.array(y)
    return X,y


def demo():
    X_train, y_train = read_data("../bbztx/train_data")
    X_test, y_test = read_data("../bbztx/test_data")
    Xtrain, Xtest, Ytrain, Ytest = train_test_split(X_train, y_train, test_size=0.3)
    rfc = RandomForestRegressor(random_state=0, n_estimators=10, max_depth=10)
    rfc = rfc.fit(Xtrain, Ytrain)
    print(rfc.score(Xtest, Ytest))

    print(rfc.predict(X_test))
    # print(rfc.score(Xtest, y_test))

    y_pred_test = rfc.predict(X_test)
    test_mse = metrics.mean_squared_error(y_test, y_pred_test)
    print("测试集MSE:", test_mse)


if __name__ == '__main__':
	demo()