for j in range(0,len(tmp_df.Time)-1): flag=0 if tmp_df.Event_Type[j]=='KeyDown': for k in range(j+1,len(tmp_df.Time)): if tmp_df.Event_Type[k]=='KeyDown': flag=1 chars=[tmp_df.Key_Code[j],tmp_df.Shift[j],tmp_df.Key_Code[k],tmp_df.Shift[k]] latency=tmp_df.Time[k]-tmp_df.Time[j] break if flag==1 and latency<1.5: feature=categorize(chars) feature_list[0][feature]=feature_list[0][feature]+latency feature_list[1][feature]=feature_list[1][feature]+1 mean_latencies=feature_list[0]/feature_list[1] ############################################################################ #Calculating hold times and number of backspaces and cpm feature_list_holdtime=np.zeros((2,7)) backspaces=0 characters=0 cpm=float('NaN') backspace_per_character=float('NaN') for j in range(0,len(tmp_df.Time)-1):
conn = mongo.Connection() db = conn.CompProb tweets = db.tweets trainer = db.trainer words = db.words priors = count_sentiment(trainer) #SELF_DESTRUCT(tweets, trainer, words) cursor = tweets.find() i = 0 # # while i < 4: for tweet in cursor: i += 1 cat = categorize(tweet['text'].lower()) tweet['category'] = cat # tweet['max_sentiment'] = determine_sentiment(tweet['sentiment_stats']) tweets.save(tweet) if i % 1000 == 0: print i # tweet = tweets.find_one() # print tweet['text'] # text = split_tweet(tweet['text']) # print text # result = classify(text, priors, words) # print result # sentiment = determine_sentiment(result) # print sentiment # #i += 1
flag = 0 if tmp_df.Event_Type[j] == 'KeyDown': for k in range(j + 1, len(tmp_df.Time)): if tmp_df.Event_Type[k] == 'KeyDown': flag = 1 chars = [ tmp_df.Key_Code[j], tmp_df.Shift[j], tmp_df.Key_Code[k], tmp_df.Shift[k] ] latency = tmp_df.Time[k] - tmp_df.Time[j] break if flag == 1 and latency < 1.5: feature = categorize(chars) feature_list[0][feature] = feature_list[0][feature] + latency feature_list[1][feature] = feature_list[1][feature] + 1 mean_latencies = feature_list[0] / feature_list[1] ############################################################################ #Calculating hold times and number of backspaces and cpm feature_list_holdtime = np.zeros((2, 7)) backspaces = 0 characters = 0 cpm = float('NaN') backspace_per_character = float('NaN') for j in range(0, len(tmp_df.Time) - 1):
db = conn.CompProb tweets = db.tweets trainer = db.trainer words = db.words priors = count_sentiment(trainer) #SELF_DESTRUCT(tweets, trainer, words) cursor = tweets.find() i = 0 # # while i < 4: for tweet in cursor: i += 1 cat = categorize(tweet['text'].lower()) tweet['category'] = cat # tweet['max_sentiment'] = determine_sentiment(tweet['sentiment_stats']) tweets.save(tweet) if i % 1000 == 0: print i # tweet = tweets.find_one() # print tweet['text'] # text = split_tweet(tweet['text']) # print text # result = classify(text, priors, words) # print result # sentiment = determine_sentiment(result) # print sentiment # #i += 1