三、机器学习概述总结

导图：

代码：

from scipy.stats import pearsonr
from sklearn.datasets import load_iris
from sklearn.decomposition import PCA
from sklearn.feature_extraction import DictVectorizer
from sklearn.feature_extraction.text import CountVectorizer,TfidfVectorizer
from sklearn.feature_selection import VarianceThreshold
from sklearn.model_selection import train_test_split
import jieba
import pandas as pd
from sklearn.preprocessing import MinMaxScaler, StandardScaler


def datasets_demo():
    # 获取数据集
    iris = load_iris()
    print("鸢尾花数据集：\n",iris)
    print("查看数据集描述：\n",iris["DESCR"])
    print("查看特征值的名字：\n",iris.feature_names)
    print("查看特征值：\n",iris.data,iris.data.shape)

    # 数据集划分
    # random_state=22 随机种子，因为随机种子是固定的，所以每次运行程序时都会得到相同的训练集和测试集
    # 这对于代码的可重复性和调试非常有用
    x_train,x_test,y_train,y_test=train_test_split(iris.data,iris.target,test_size=0.2,random_state=22)
    print("训练集的特征值：\n",x_train,x_train.shape)
    return None

def dict_demo():
#     字典特征抽取  DictVectorizer
     data=[{'city':'背景','temperature':100},{'city':'shan','temperature':200}]
     # 1、实例化一个转换器
     transfer = DictVectorizer(sparse=False)
     # 2、调用fit_transform()
     data_new = transfer.fit_transform(data)
     print("data_new：\n",data_new)
     return None

def count_demo():
#     文本特征提取
      data = ["life is short,i like python","life is too long,i dislike python"]
      # 1、实例化一个转换器类
      transfer = CountVectorizer()
      # 2、调用fit_transform
      data_new = transfer.fit_transform(data)
      print("data_new：\n", data_new.toarray())
      print("特征名字：\n",transfer.get_feature_names_out())
      return None


def count_chinese_demo():
#     中文文本特征提取
      data = ["呜呜 呜呜 等等 是 否 分析","等等 实时 还"]
      # 1、实例化一个转换器类
      transfer = CountVectorizer()
      # 2、调用fit_transform
      data_new = transfer.fit_transform(data)
      print("data_new：\n", data_new.toarray())
      print("特征名字：\n",transfer.get_feature_names_out())
      return None


def cut_word(text):
    # 进行中文分词
    return " ".join(list(jieba.cut(text)))

def count_chinese_demo2():
#     中文文本特征抽取   自动分词
      data =["少时诵诗书所所所所丰富创新型",
             "伺服电机寻或错过过过过过过过过过",
             "爱何辜大V阿深V次氯酸钠计算出吧看啥迟迟不你"]
      # 将中文文本进行分离
      data_new=[]
      for sent in data:
          data_new.append(cut_word(sent) )
      # 1、实例化一个转换器类
      transfer = CountVectorizer()
      # 2、调用fit_transform
      data_final= transfer.fit_transform(data_new)
      print("data_new：\n", data_final.toarray())
      print("特征名字：\n", transfer.get_feature_names_out())
      return None

def tfidf_demo2():
#     中文文本特征抽取   自动分词  TfidfVectorizer
      data =["少时诵诗书所所所所丰富创新型",
             "伺服电机寻或错过过过过过过过过过",
             "爱何辜大V阿深V次氯酸钠计算出吧看啥迟迟不你"]
      # 将中文文本进行分离
      data_new=[]
      for sent in data:
          data_new.append(cut_word(sent) )
      # 1、实例化一个转换器类
      transfer = TfidfVectorizer()
      # 2、调用fit_transform
      data_final= transfer.fit_transform(data_new)
      print("data_new：\n", data_final.toarray())
      print("特征名字：\n", transfer.get_feature_names_out())
      return None

def minmax_demo():
#     归一化
#     1、获取数据
      data = pd.read_csv("dating.txt")
      # 前三列数据
      data = data.iloc[:,:3]
      print(data)
      # 2、实例化一个转换器
      transfer = MinMaxScaler()
      # 3、调用fit_transform
      data_new = transfer.fit_transform(data)
      print(data_new)
      return None


def stand_demo():
#     标准化
#     1、获取数据
      data = pd.read_csv("dating.txt")
      # 前三列数据
      data = data.iloc[:,:3]
      print(data)
      # 2、实例化一个转换器
      transfer = StandardScaler()
      # 3、调用fit_transform
      data_new = transfer.fit_transform(data)
      print(data_new)
      return None

def variance_demo():
#     过滤低方差特征
#     1、获取数据
      data = pd.read_csv("ffff.csv")
      data = data.iloc[:,1:-2]
      # 2、实例化一个转换器
      transfer = VarianceThreshold(threshold=5)
      # 3、调用fit_transform
      data_new = transfer.fit_transform(data)
      # 计算某两个变量之间的相关系数
      r1 = pearsonr(data["pre1"],data["prt2"])
      print("相关系数：",r1)
      print(data_new,data_new.shape)
      return None


def pca_demo():
    # PCA 降维
    data = [[2,8,4,5],[6,3,0,8],[5,4,9,1]]
    # 1、实例化一个转换器类
    transfer = PCA(n_components=2)
    # 2、调用 fit_transform
    data_new = transfer.fit_transform(data)
    print(data_new)
    return None



if __name__ == '__main__':
    # 1、sklearn数据集使用
    # datasets_demo()
    # 2、字典特征抽取
    # dict_demo()
    # 3、文本特征抽取
    # count_demo()
    # 4、中文文本特征抽取
    # count_chinese_demo()
    # 5、中文文本特征抽取、自动分词
    # count_chinese_demo2()
    # 6、中文分词
    # cut_word("我爱北京天安门")
    # 7、用TF-IDF方法进行文本特征抽取
    # tfidf_demo2()
    # 8、归一化
    # minmax_demo()
    # 9、标准化
    # stand_demo()
    # 10、过滤低方差特征
    # variance_demo()
    # 11、pca 降维
    pca_demo()