def makeDoc2vecFile(pos_tweets,outfile,merge) :
stopwords=util.txtTolist("lists/stopwords.txt")
y=[]
for tweet in pos_tweets :
x=[tok[0].strip("@#") for tok in tweet if tok[1]=="A" or tok[1]=="N" or tok[1]=="^" or tok[1]=="V" or tok[1]=="@" or tok[1]=="#" ]
x=[tok for tok in x if tok not in stopwords ]
y.append(x)
with open(outfile,"a+") as f :
for xi in x :
f.write(str(xi)+" ")
f.write("\n")
if merge :
y=[item for sublist in y for item in sublist if item not in y ]
return y
def makeDoc2vecFile(pos_tweets, outfile, merge):
stopwords = util.txtTolist("lists/stopwords.txt")
y = []
for tweet in pos_tweets:
x = [
tok[0].strip("@#") for tok in tweet
if tok[1] == "A" or tok[1] == "N" or tok[1] == "^" or tok[1] == "V"
or tok[1] == "@" or tok[1] == "#"
]
x = [tok for tok in x if tok not in stopwords]
y.append(x)
with open(outfile, "a+") as f:
for xi in x:
f.write(str(xi) + " ")
f.write("\n")
if merge:
y = [item for sublist in y for item in sublist if item not in y]
return y
print "\n EXTRACTING TWITTER DATA \n"
util.createFilePath(PATH_TO_RAW_DATA)
extract.getTweets(topics,PATH_TO_RAW_DATA,5000)
"""
print("\n PROCESSING DATA - CLEANING AND POS TAGGING \n")
util.createFilePath(PATH_TO_CLEAN_DATA)
clean.process(PATH_TO_RAW_DATA,PATH_TO_CLEAN_DATA,topics)
print("\n EXTRACTING TOP-K TWEETS FROM DATA \n")
for topic in topics :
print topic
dataFile=PATH_TO_CLEAN_DATA+"/data_"+topic+".txt"
tweets=util.txtTolist(dataFile)
k=[5,10,25,50,100]
for ki in k :
topk="TOP_"+str(ki)
CosineSimilarityVSM=[]
method="ALL_TWEETS"
outPath=PATH_TO_RESULTS+"/"+topic+"/"+topk+"/"+method
util.createFilePath(outPath)
val=measures.entropy(tweets)
print(topic+topk+method+" Entropy : "+str(val))
method="RANDOM_TWEETS"
outPath=PATH_TO_RESULTS+"/"+topic+"/"+topk+"/"+method
"""
print "\n EXTRACTING TWITTER DATA \n"
util.createFilePath(PATH_TO_RAW_DATA)
extract.getTweets(topics,PATH_TO_RAW_DATA,5000)
"""
print("\n PROCESSING DATA - CLEANING AND POS TAGGING \n")
util.createFilePath(PATH_TO_CLEAN_DATA)
clean.process(PATH_TO_RAW_DATA, PATH_TO_CLEAN_DATA, topics)
print("\n EXTRACTING TOP-K TWEETS FROM DATA \n")
for topic in topics:
print topic
dataFile = PATH_TO_CLEAN_DATA + "/data_" + topic + ".txt"
tweets = util.txtTolist(dataFile)
k = [5, 10, 25, 50, 100]
for ki in k:
topk = "TOP_" + str(ki)
CosineSimilarityVSM = []
method = "ALL_TWEETS"
outPath = PATH_TO_RESULTS + "/" + topic + "/" + topk + "/" + method
util.createFilePath(outPath)
val = measures.entropy(tweets)
print(topic + topk + method + " Entropy : " + str(val))
method = "RANDOM_TWEETS"
outPath = PATH_TO_RESULTS + "/" + topic + "/" + topk + "/" + method
def readInData(filename):
data = util.txtTolist(filename)
return data
