["life is short,i like python",
"life is too long,i dislike python"]

def count_demo():
    """
       文本特征抽取：CountVectorizer
       :return: None
    """
    data = ["life is short,i like like python", "life is too long,i dislike python"]
    #实例化转换器
    transfer=CountVectorizer(stop_words=["is","too"])
    #调用fit_transform
    data_new=transfer.fit_transform(data)
    print("data_new:\n",data_new.toarray())
    print("返回特征名字：\n", transfer.get_feature_names())
    return None

def count_chinese_demo():
    """
       中文文本特征抽取：CountVectorizer
       :return: None
    """
    data = ["我 爱 北京 天安门", "天安门 上 太阳 升"]
    #实例化转换器
    transfer=CountVectorizer()
    #调用fit_transform
    data_new=transfer.fit_transform(data)
    print("data_new:\n",data_new.toarray())
    print("返回特征名字：\n", transfer.get_feature_names())
    return None

def cut_word(text):
    text=" ".join(list(jieba.cut(text)))
    return text
def count_chinese_demo2():
    """
       中文文本特征抽取,自动分词
       :return: None
    """
    data = ["一种还是一种今天很残酷，明天更残酷，后天很美好，但绝对大部分是死在明天晚上，所以每个人不要放弃今天。",
            "我们看到的从很远星系来的光是在几百万年之前发出的，这样当我们看到宇宙时，我们是在看它的过去。",
            "如果只用一种方式了解某样事物，你就不会真正了解它。了解事物真正含义的秘密取决于如何将其与我们所了解的事物相联系。"]
    text_new=[]
    for item in data:
        text_new.append(cut_word(item))
    #实例化转换器
    transfer=CountVectorizer(stop_words=["一种","所以"])
    #调用fit_transform
    data_new=transfer.fit_transform(text_new)
    print("data_new:\n",data_new.toarray())
    print("返回特征名字：\n", transfer.get_feature_names())
    return None

def tfidf():
    """
    用TF-IDF的方法进行文本特征抽取
    """
    data = ["一种还是一种今天很残酷，明天更残酷，后天很美好，但绝对大部分是死在明天晚上，所以每个人不要放弃今天。",
            "我们看到的从很远星系来的光是在几百万年之前发出的，这样当我们看到宇宙时，我们是在看它的过去。",
            "如果只用一种方式了解某样事物，你就不会真正了解它。了解事物真正含义的秘密取决于如何将其与我们所了解的事物相联系。"]
    text_new = []
    for item in data:
        text_new.append(cut_word(item))
    # 实例化转换器
    transfer = TfidfVectorizer(stop_words=["一种", "所以"])
    # 调用fit_transform
    data_new = transfer.fit_transform(text_new)
    print("data_new:\n", data_new.toarray())
    print("返回特征名字：\n", transfer.get_feature_names())
    return None

from sklearn.preprocessing import MinMaxScaler,StandardScaler

def minmax_demo():
    """
    归一化
    """
    #1.获取数据
    data=pd.read_csv("datingTestSet2.txt", sep=',')
    data=data.iloc[:,:3]
    #2.实例化一个转换器,范围在0-1
    transfer = MinMaxScaler(feature_range=[0,1])
    #3.调用fit_transform
    data_new=transfer.fit_transform(data)
    print("data_new:\n",data_new)
    print("特征：\n",data.columns)
    return None

def stand_demo():
    """
    归一化
    """
    #1.获取数据
    data=pd.read_csv("datingTestSet2.txt", sep=',')
    data=data.iloc[:,:3]
    #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:\n",data_new)
    print("每一列特征的平均值：\n", transfer.mean_)
    print("每一列特征的方差：\n", transfer.var_)
    return None

from sklearn.feature_selection import VarianceThreshold

#低方差过滤
def variance_demo():
    """
        删除低方差特征——特征选择
        :return: None
        """
    data = pd.read_csv("factor_returns.csv")
    data=data.iloc[:,1:-2]
    print("data:\n",data)
    # 1、实例化一个转换器类
    transfer = VarianceThreshold(threshold=10)
    # 2、调用fit_transform
    data_new = transfer.fit_transform(data)
    print("date_new：\n", data_new)
    print("形状：\n", data_new.shape)
    #计算两个变量之间的相关系数
    r=pearsonr(data["pe_ratio"],data["pb_ratio"])
    print("相关系数：\n",r)
    r2=pearsonr(data["revenue"],data["total_expense"])
    print("revenue与total_expense之间的相关性：\n",r2)
    plt.figure(figsize=(20,8),dpi=100)
    plt.scatter(data["revenue"],data["total_expense"])
    plt.show()
    return None

def pca_demo():
    """
    pca降维
    """
    data=[[2,8,4,5],[6,3,0,8],[5,4,9,1]]
    #实例化一个转换器
    transfer=PCA(n_components=0.95)
    #调用fit_transform
    data_new=transfer.fit_transform(data)
    print("保留95%的信息，降维结果为:\n",data_new)
    # 1、实例化PCA, 整数——指定降维到的维数
    transfer2 = PCA(n_components=3)
    # 2、调用fit_transform
    data2 = transfer2.fit_transform(data)
    print("降维到3维的结果：\n", data2)
    return None