机器学习-百度云视频资料

有numpy

下面安装pandas;有点慢啊！；

使用import pandas 来检查是否安装成功。

下面安装Scikit-learn      pip3 install Scikit-learn；也挺慢的。

import sklearn；用来检查是否安装成功。

跑的第一个程序；比较慢啊；能运行就好啦；

将sparse = False;关闭sparse矩阵；见上图和下图进行区分，上图为0的就不显示了，下图是不是0都会通过矩阵显示；

下载分词器pip install jieba

首先这个AttributeError: ‘module’ object has no attribute ‘cut’ 报错的原因是因为有jieba.py这个文件存在，或者jieba这样命名的文件存在，很多新人使用结巴 来分词的时候命名直接为jieba.py，但是其实官方给的教程代码里有import jieba，这样就会引用到你自己这个教程文件jieba.py，而没有引用官方的库，这样自然cut这个方法就没有，所以报错。 
 

from sklearn.feature_extraction import DictVectorizer
from sklearn.feature_extraction.text import CountVectorizer
import jieba

def dictvec():
	dict = DictVectorizer(sparse = False)
	data = dict.fit_transform(
		[
			{"city":'北京','temperature':100},
			{"city":'上海','temperature':60},
			{"city":'深圳','temperature':30}
		]
		)
	print(dict.get_feature_names())
	print(dict.inverse_transform(data))
	print(data)
	return None

def countvec():
	'''
	对于文本进行特征值化
	'''
	cv = CountVectorizer()
	data = cv.fit_transform(
		["life is short,i like python","life is too long,i dislike python"]
		)
	print(cv.get_feature_names())
	print(data.toarray())
	return None

def cutword():
	con1 = jieba.cut("今天很残酷，明天更残酷，后天很美好")
	con2 = jieba.cut("我们看到的从很远星系")
	con3 = jieba.cut("如果只是用一种方式了解某个事物")
	content1 = list(con1)
	content2 = list(con2)
	content3 = list(con3)
	c1 = ' '.join(content1)
	c2 = ' '.join(content2)
	c3 = ' '.join(content3)
	return c1,c2,c3

def hanzivec():
	c1,c2,c3 = cutword()
	print(c1,c2,c3)
	cv = CountVectorizer()
	data = cv.fit_transform(
		[c1,c2,c3]
		)
	print(cv.get_feature_names())
	print(data.toarray())
	return None


if __name__=='__main__' :
	# dictvec()
	# countvec()
	hanzivec()

07.tf-idf分析问题 

from sklearn.feature_extraction import DictVectorizer
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.feature_extraction.text import TfidfVectorizer
import jieba

def dictvec():
	dict = DictVectorizer(sparse = False)
	data = dict.fit_transform(
		[
			{"city":'北京','temperature':100},
			{"city":'上海','temperature':60},
			{"city":'深圳','temperature':30}
		]
		)
	print(dict.get_feature_names())
	print(dict.inverse_transform(data))
	print(data)
	return None

def countvec():
	'''
	对于文本进行特征值化
	'''
	cv = CountVectorizer()
	data = cv.fit_transform(
		["life is short,i like python","life is too long,i dislike python"]
		)
	print(cv.get_feature_names())
	print(data.toarray())
	return None

def cutword():
	con1 = jieba.cut("今天很残酷，明天更残酷，后天很美好")
	con2 = jieba.cut("我们看到的从很远星系")
	con3 = jieba.cut("如果只是用一种方式了解某个事物")
	content1 = list(con1)
	content2 = list(con2)
	content3 = list(con3)
	c1 = ' '.join(content1)
	c2 = ' '.join(content2)
	c3 = ' '.join(content3)
	return c1,c2,c3

def hanzivec():
	c1,c2,c3 = cutword()
	print(c1,c2,c3)
	cv = CountVectorizer()
	data = cv.fit_transform(
		[c1,c2,c3]
		)
	print(cv.get_feature_names())
	print(data.toarray())
	return None

def tfidfvec():
	c1,c2,c3 = cutword()
	print(c1,c2,c3)
	tf = TfidfVectorizer()
	data = tf.fit_transform(
		[c1,c2,c3]
		)
	print(tf.get_feature_names())
	print(data.toarray())
	return None


if __name__=='__main__' :
	# dictvec()
	# countvec()
	# hanzivec()
	tfidfvec()

09.归一化以及标准化对比