机器学习基础

决策树

决策树简介

决策树思想的来源非常朴素，程序设计中的条件分支结构就是if-then结构，最早的决策树就是利用这类结构分割数据的一种分类学习方法


你如何去划分是否能得到贷款？





ID3
信息增益 最大的准则
C4.5
信息增益比 最大的准则
CART
回归树: 平方误差 最小
分类树: 基尼系数 最小的准则 在sklearn中可以选择划分的原则

决策树API
class sklearn.tree.DecisionTreeClassifier(criterion=’gini’, max_depth=None,random_state=None)
决策树分类器
criterion:默认是’gini’系数，也可以选择信息增益的熵’entropy’
max_depth:树的深度大小
random_state:随机数种子
method:
decision_path:返回决策树的路径

代码分析

import pandas as pd
from sklearn.ensemble import RandomForestClassifier
from sklearn.feature_extraction import DictVectorizer
from sklearn.model_selection import train_test_split,GridSearchCV
from sklearn.tree import DecisionTreeClassifier, export_graphviz


def decision():
    """
    决策树对泰坦尼克号进行预测生死
    :return:
    """
    # 获取数据
    data = pd.read_csv("titanic_data.csv")
    # print(data.head())

    # 处理数据，找出特征值和目标值
    x = data[["Pclass","Age","Sex"]]
    y = data["Survived"]
    # print(x)
    print(y)

    # 缺失值处理
    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)
    # 进行特征处理
    dict = DictVectorizer(sparse=False)
    x_train=dict.fit_transform(x_train.to_dict(orient="records"))
    x_test =dict.transform(x_test.to_dict(orient="records"))
    print(dict.get_feature_names())
    print(x_train)


    # 用决策树进行预测
    dec = DecisionTreeClassifier(max_depth=4)
    dec.fit(x_train,y_train)
    print(dec.score(x_test,y_test))

    # 导出决策树的结构
    export_graphviz(dec,out_file="tree.dot",feature_names=['Age', 'Pclass', 'Sex=female', 'Sex=male'])

    return None

随机森林

定义：在机器学习中，随机森林是一个包含多个决策树的分类器，并且其输出的类别是由个别树输出的类别的众数而定。

import pandas as pd
from sklearn.ensemble import RandomForestClassifier
from sklearn.feature_extraction import DictVectorizer
from sklearn.model_selection import train_test_split,GridSearchCV
from sklearn.tree import DecisionTreeClassifier, export_graphviz


def decision():
    """
    决策树对泰坦尼克号进行预测生死
    :return:
    """
    # 获取数据
    data = pd.read_csv("titanic_data.csv")
    # print(data.head())

    # 处理数据，找出特征值和目标值
    x = data[["Pclass","Age","Sex"]]
    y = data["Survived"]
    # print(x)
    print(y)

    # 缺失值处理
    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)
    # 进行特征处理
    dict = DictVectorizer(sparse=False)
    x_train=dict.fit_transform(x_train.to_dict(orient="records"))
    x_test =dict.transform(x_test.to_dict(orient="records"))
    print(dict.get_feature_names())
    print(x_train)


    # 用决策树进行预测
    dec = DecisionTreeClassifier(max_depth=4)
    dec.fit(x_train,y_train)
    print(dec.score(x_test,y_test))

    # 导出决策树的结构
    export_graphviz(dec,out_file="tree.dot",feature_names=['Age', 'Pclass', 'Sex=female', 'Sex=male'])

    return None

def randonf():
    """
        决策树对泰坦尼克号进行预测生死
        :return:
        """
    # 获取数据
    data = pd.read_csv("titanic_data.csv")
    # print(data.head())

    # 处理数据，找出特征值和目标值
    x = data[["Pclass", "Age", "Sex"]]
    y = data["Survived"]
    # print(x)
    print(y)

    # 缺失值处理
    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)
    # 进行特征处理
    dict = DictVectorizer(sparse=False)
    x_train = dict.fit_transform(x_train.to_dict(orient="records"))
    x_test = dict.transform(x_test.to_dict(orient="records"))

    # 随机森林进行预测(超参数调优)
    rf = RandomForestClassifier()

    param = {"n_estimators":[120,200,300,500,800,1200],"max_depth":[5,8,15,25,30]}
    # 网格搜索与交叉验证
    gc = GridSearchCV(rf,param_grid=param,cv=2)
    gc.fit(x_train,y_train)
    print("准确率",gc.score(x_test,y_test))
    print("查看选择的参数模型",gc.best_params_)


# decision()
randonf()