机器学习连载001

字典预处理

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




def dict_vec():

    # 实例化dict
    # dict = DictVectorizer()
    dict = DictVectorizer(sparse=False)
    # diaoyong fit_transform
    data = dict.fit_transform([{'city': '北京','temperature':100},{'city': '上海','temperature':60},{'city': '深圳','temperature':30}])

    # 打印每一个列的名称
    print(dict.get_feature_names())
    print(data)

    return None

if __name__ == '__main__':
    dict_vec()

 文本的预处理

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


def dict_vec():

    # 实例化dict
    # dict = DictVectorizer()
    dict = DictVectorizer(sparse=False)
    # diaoyong fit_transform
    data = dict.fit_transform([{'city': '北京','temperature':100},{'city': '上海','temperature':60},{'city': '深圳','temperature':30}])

    # 打印每一个列的名称
    print(dict.get_feature_names())
    print(data)

    return None


def countvec():
    # 实例化conunt
    count = CountVectorizer()
    # 对两篇文章进行特征抽取
    data = count.fit_transform(["人生 人生 苦短，我 喜 欢Python", "生 活太 长 久，我不 喜欢P ython"])
    # 内容
    print(count.get_feature_names())
    print(data.toarray())
    # print(data)

    return None

if __name__ == '__main__':
    countvec()