sklearn学习笔记

from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction import DictVectorizer
from sklearn.feature_extraction.text import CountVectorizer
#sklearn 数据调用

def datasets_demo():

iris = load_iris()

print(“鸢尾花数据集:\n”,iris)

print(“查看数据集描述：\n”,iris[“DESCR”])

print(“查看描述：\n”, iris.feature_names)

print(“查看描述：\n”, iris.data)

return None

#数据集划分

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.shape)

if name == ‘main’:

datasets_demo()

def dict_demo():
#字典特征提取
data = [{‘city’:‘北京’,‘temperature’:‘100’},{ ‘city’:‘上海’,‘temperature’:‘60’ },{‘city’:‘西安’,‘temperature’:‘80’}]
#1,实例化一个转换器
transfer = DictVectorizer(sparse=False)
data_new=transfer.fit_transform(data)
print(“data_new: \n”,data_new)
print(“data_new: \n”, transfer.get_feature_names())

def dictvec():
dict=DictVectorizer(sparse=False)
S = [{‘city’:‘北京’,‘temperature’:100},{‘city’:‘上海’,‘temperature’:80},{‘city’:‘广州’,‘temperature’:70}]
data=dict.fit_transform(S)
S = [{}]
name=dict.get_feature_names()
print(name)
print(data)

def count_demo():
#文本特征提取

#实例化一个转换器类
data = ["life is short ,i like python","life is too long ,i dislike python "]
#调用fit_transform
transfer = CountVectorizer()
datanew = transfer.fit_transform(data)
print("datanew:\n",datanew.toarray())

def count_0demo():
# 汉字文本特征提取

    # 实例化一个转换器类
    data = ["我 爱 北 京 天 安 门", "我 爱 我 家 "]
    # 调用fit_transform
    transfer = CountVectorizer()
    datanew = transfer.fit_transform(data)
    print("datanew:\n", datanew)
    return None

if name == ‘main’:
count_demo()