随机森林的使用

from sklearn.feature_extraction import DictVectorizer
from sklearn.feature_extraction.text import CountVectorizer,TfidfVectorizer
from sklearn.preprocessing import MinMaxScaler,StandardScaler
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier,export_graphviz
import jieba

import  pandas as pd

def decision():
    #获取数据
    taitan=pd.read_csv(‘http://biostat.mc.vanderbilt.edu/wiki/pub/Main/DataSets/titanic.txt‘)
    #获取特征值
    x=taitan[[‘pclass‘,‘age‘,‘sex‘]]
    #获取目标值
    y=taitan[[‘survived‘]]

    #缺失值的处理    用年龄的平均值填补
    x[‘age‘].fillna(x[‘age‘].mean(),inplace=True)

    #分割数据集到训练集和测试集
    x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.25)

    #对数据进行one_hot编码
    dict=DictVectorizer(sparse=False)

    x_train = dict.fit_transform(x_train.to_dict(orient=‘records‘))
    print(dict.get_feature_names())

    x_test = dict.fit_transform(x_test.to_dict(orient=‘records‘))

    #实例化一个决策树
    dec=DecisionTreeClassifier()
    dec.fit(x_train,y_train)
    print("预测准确率：",dec.score(x_test,y_test))

    export_graphviz(dec,out_file=‘./tree.dot‘,feature_names=[‘年龄‘,‘pclass=1st‘, ‘pclass=2nd‘, ‘pclass=3rd‘, ‘女人‘, ‘男人‘])
    # print(x_train)

if __name__ == ‘__main__‘:
    decision()

dot  -Tpng tree.dot -o tree.png    #将dot文件转为png格式的图片  必须进入到指定目录下去操作