def wordCounter(dictData, tweet_clean, tweet_geo):
city = getCity.getCity(tweet_geo[0][1],tweet_geo[0][0])
for word in tweet_clean:
if city not in dictData:
dictData[city] = {}
if word not in dictData[city].keys():
dictData[city][word] = 0
# if 'USA' not in dictData:
# dictData['USA'] = 0
# if word not in dictData['USA'].keys():
# dictData['USA'][word] = 0
dictData[city][word] += 1
# if city != 'USA':
# dictData['USA'][word] += 1
doc = db.WordCount.find_one({'city': city})
if doc == None:
return
wordnums = len(doc['data'])
wordnum = str(wordnums+1)
# if db.WordCount.find_one({"city":"USA","data.word":word}):
# db.WordCount.update({"city":"USA","data.word":word},{'$set':{'data.$.word':word, 'data.$.count':dictData['USA'][word]}},True)
# else:
# db.WordCount.update({"city":"USA","data.word":{'$exists':True}},{'$set':{'data.' + wordnum + '.word':word, 'data.' + wordnum + '.count':dictData['USA'][word]}})
if db.WordCount.find_one({"city":city,"data.word":word}):
db.WordCount.update({"city":city,"data.word":word},{'$set':{'data.$.word':word, 'data.$.count':dictData[city][word]}},True)
else:
db.WordCount.update({"city":city,"data.word":{'$exists':True}},{'$set':{'data.' + wordnum + '.word':word, 'data.' + wordnum + '.count':1}})
def processWordCount(jsonFile,tweet_text,tweet_geo): wordList = tweetTokenizer(tweet_text) city = getCity.getCity(tweet_geo[1],tweet_geo[0]) json1_data = json.loads(jsonFile) for word in wordList: if word not in json1_data[city].keys(): json1_data[city][word] = 0 else: json1_data[city][word] += 1 print json1_data[city]
def processWordCount(tweet_text,tweet_geo):
wordList = tweetTokenizer(tweet_text)
city = getCity.getCity(tweet_geo[0],tweet_geo[1])
print city, tweet_geo[1], tweet_geo[0]
json1_data = MongoToJson()
for word in wordList:
if city not in json1_data:
json1_data[city] = {}
if word not in json1_data[city].keys():
json1_data[city][word] = 0
json1_data[city][word] += 1
#db.WordCount.remove()
db.WordCount2.update({},json1_data)
