决策树的运用

决策树

特征值提取

字典特征提取

from sklearn.feature_extraction import DictVectorizer

def dict_demo():
    # 获取数据
    data = [{'city': '北京', 'temperature': 100},
            {'city': '上海', 'temperature': 60},
            {'city': '深圳', 'temperature': 30}]
    # 字典特征提取
    # 实例化
    transfer = DictVectorizer(sparse=True)
    # 转换
    new_data = transfer.fit_transform(data)
    print(new_data)

    # 获取具体属性名
    names = transfer.get_feature_names_out()
    print("属性名字是:\n", names)

if __name__ == '__main__':
    dict_demo()

文本特征提取

from sklearn.feature_extraction.text import CountVectorizer

def text_count_demo():
    data = ["life is short,i like like python","life is too long,i dislike python"]
    #实例化一个转换器
    #CountVectorizer(stop_words=["写在这里的不统计"])
    transfer = CountVectorizer()
    data = transfer.fit_transform(data)
    print("文本特征抽取结果:\n",data.toarray())
    print("返回特征名称:\n",transfer.get_feature_names_out())
    
if __name__=='__main__':
    text_count_demo() 

中文分词

import jieba

def cut_word(text):
    result = " ".join(list(jieba.cut(text)))
    return result

TF-IDF

from sklearn.feature_extraction.text import TfidfVectorizer

def tfidf_demo():
    data = ["life is short,i like like python","life is too long,i dislike python"]
    #实例化一个转换器
    transfer = TfidfVectorizer()
    data = transfer.fit_transform(data)
    print("文本特征抽取结果:\n",data.toarray())
    print("返回特征名称:\n",transfer.get_feature_names_out())
    
if __name__=='__main__':
    tfidf_demo() 

决策树算法API

import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction import DictVectorizer
from sklearn.tree import DecisionTreeClassifier,export_graphviz

#获取数据
data = pd.read_csv("http://biostat.mc.vanderbilt.edu/wiki/pub/Main/DataSets/titanic.txt")
#基本数据处理
#确定特征值,目标值
x = data[["pclass","age","sex"]]
y = data['survived']
#缺失值处理
x['age'].fillna(value=data["age"].mean(),inplace=True)
#分割数据
x_train,x_test,y_train,y_test = train_test_split(x,y,random_state=22,test_size=0.2)
#特征工程(字典特征提取)
x_train = x_train.to_dict(orient="records")
x_test = x_test.to_dict(orient="records")
transfer = DictVectorizer()
x_train = transfer.fit_transform(x_train)
x_test = transfer.transform(x_test)
#机器学习(决策树)
estimator = DecisionTreeClassifier(max_depth=5)
estimator.fit(x_train,y_train)
#评估模型
y_pre = estimator.predict(x_test)
print("预测值是:\n",y_pre)
ret = estimator.score(x_test,y_test)
print("准确率为:\n",ret)

#决策树可视化
export_graphviz(estimator,out_file="保存路径.dot",feature_names=['要输出的字段名'])

显示结构网站：http://webgraphviz.com

回归决策树

import numpy as np
import matplotlib.pyplot as plt
from sklearn.tree import DecisionTreeRegressor
from sklearn import linear_model

#生成数据
x = np.array(list(range(1,11))).reshape(-1,1)
y = np.array([5.56,5.70,5.91,6.40,6.80,7.05,8.90,8.70,9.00,9.05])

#训练模型
model1 = DecisionTreeRegressor(max_depth=1)
model2 = DecisionTreeRegressor(max_depth=3)
model3 = linear_model.LinearRegression()
model1.fit(x,y)
model2.fit(x,y)
model3.fit(x,y)

#模型预测
x_test = np.arange(0.0,10.0,0.01).reshape(-1,1)
y_1 = model1.predict(x_test)
y_2 = model2.predict(x_test)
y_3= model3.predict(x_test)

#结果可视化
plt.figure(figsize=(10,6),dpi=100)
plt.scatter(x,y,label="data")
plt.plot(x_test,y_1,label="max_depth=1")
plt.plot(x_test,y_2,label="max_depth=3")
plt.plot(x_test,y_3,label="liner regression")

plt.xlabel("data")
plt.ylabel("target")
plt.title("Decision Tree Regression")
plt.legend()

plt.show()