Python机器学习经典模型实战篇

B站账号@狼群里的小杨，记得点赞收藏加关注，一键三连哦！

朴素贝叶斯算法实例文本分类

from sklearn.datasets import  fetch_20newsgroups
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.model_selection import train_test_split
from sklearn.naive_bayes import  MultinomialNB
from sklearn.metrics import classification_report

def naviebayes():
    """
    朴素贝叶斯进行文本分类
    :return: None
    """
    # 获取新闻数据集
    news = fetch_20newsgroups(subset='all')

    # 进行数据分割
    x_train,x_test,y_train,y_test = train_test_split(news.data, news.target, test_size=0.2)

    # 对数据集进行特征抽取
    tf = TfidfVectorizer()

    # 以训练集当中的词的列表进行每篇文章重要性统计['a','b','c','d',]训练值必须是已经分好词的数据，将分词结果用空格连接起来形成每一篇文章的数据。
    x_train = tf.fit_transform(x_train)

    print(tf.get_feature_names())

    x_test = tf.transform(x_test)

    # 进行朴素贝叶斯算法的预测
    mlt = MultinomialNB(alpha=1.0)
    print(x_train)

    #设置训练集
    mlt.fit(x_train, y_train)

    y_predict = mlt.predict(x_test)
    print("预测的文章类别为: ",y_predict)

    # 得出准确率
    print("准确率：",mlt.score(x_test,y_test))

    print("每个类别的精确率和召回率：\n",classification_report(y_test, y_predict, target_names=news.target_names))

    return None

if __name__ =="__main__":
    naviebayes()

决策树实例-预测泰坦尼克号乘客生存率

import pandas as pd
from sklearn.feature_extraction import DictVectorizer #导入特征抽取的函数库
from sklearn.model_selection import train_test_split # 导入数据分割模块
from sklearn.tree import DecisionTreeClassifier # 导入决策树模型库
from sklearn.tree import export_graphviz #导入生成决策树图片的库

def decision():
    """
    决策树对泰坦尼克号进行预测生死
    :return: None
    """
    # 获取数据
    # titan = pd.read_csv('titan.csv')
    titan = pd.read_csv("http://biostat.mc.vanderbilt.edu/wiki/pub/Main/DataSets/titanic.txt")
    # 处理数据，找出特征值和目标值
    x = titan[['pclass', 'age', 'sex']]

    y= titan['survived']

    print(x)
    #  缺失值处理
    x['age'].fillna(x['age'].mean(), inplace=True)


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

    #  进行处理(特征工程) 特征-> 类别-> one_hot编码
    dict = DictVectorizer(sparse=False)

    x_train = dict.fit_transform(x_train.to_dict(orient="records")) #将每一行的数据转换成字典列表。 转换成字典才可以进行特征抽取

    print(dict.get_feature_names())

    x_test = dict.transform(x_test.to_dict(orient="records"))
    # print(x_train)
    # 用决策树进行预测
    dec = DecisionTreeClassifier(max_dept