#?-*-?coding:?utf-8?-*-
“““
Created?on?Mon?Aug?27?16:46:26?2018

@author:?caomao
“““

from?numpy?import?*
import?numpy?as?np
from?math?import?*

def?loadDataSet（）:
????postingList=[[‘my‘?‘dog‘?‘has‘?‘flea‘?‘problems‘?‘help‘?‘please‘]
?????????????????[‘maybe‘?‘not‘?‘take‘?‘him‘?‘to‘?‘dog‘?‘park‘?‘stupid‘]
?????????????????[‘my‘?‘dalmation‘?‘is‘?‘so‘?‘cute‘?‘I‘?‘love‘?‘him‘]
?????????????????[‘stop‘?‘posting‘?‘stupid‘?‘worthless‘?‘garbage‘]
?????????????????[‘mr‘?‘licks‘?‘ate‘?‘my‘?‘steak‘?‘how‘?‘to‘?‘stop‘?‘him‘]
?????????????????[‘quit‘?‘buying‘?‘worthless‘?‘dog‘?‘food‘?‘stupid‘]]
????classVec?=?[010101]????#1?is?abusive?0?not
????return?postingListclassVec
???
#?remove?repeat?words
def?createVocabList（dataSet）:
????vocabSet?=?set（[]）
????for?document?in?dataSet:
????????vocabSet?=?vocabSet?|?set（document）
????return?list（vocabSet）
def?setOfWord2Vec（vocabListinputSet）:
????returnVec?=?[0]*len（vocabList）
????for?word?in?inputSet:
????????if?word?in?vocabList:
????????????returnVec[vocabList.index（word）]=1
????????else:
????????????print?“the?word:?%s?is?not?in?my?vocab“?%?word?
????return?returnVec
????
def?bagOfWords2VecMN（vocabListinputSet）:
????returnVec?=?[0]*len（vocabList）
????for?word?in?inputSet:
????????if?word?in?vocabList:
????????????returnVec[vocabList.index（word）]?+=?1
????return?re