#python script to clean incoming Sanders data-- gets rid of first three words and quotation marks, only includes if not irrelevant
import svc_emotions
tweets = svc_emotions.file_to_array("newercorpus.txt")
#create outfile to put new stuff into
outfile_name = "quoteless.txt"
outfile = open(outfile_name, 'w')
for tweet in tweets:
#part that first gets rid of the tabs and then parses based on spaces and removes irrelevant tweets
# newList = tweet.split(" ")
# newString = ""
# for smallString in newList[4:]:
# newString = newString + " " + smallString
# if newList[2] != "irrelevant":
# outfile.write("\n" + newString)
#part that takes the quotes away
newTweet = tweet[4:]
newTweet = newTweet[:-3]
outfile.write("\n" + newTweet)
outfile.close()
# coding=utf-8
import svc_emotions
import scipy
import numpy
from sklearn.pipeline import FeatureUnion
# list of emotions to get feature lists for
emotion_list = ['anger', 'disgust', 'fear', 'joy', 'love', 'sadness', 'surprise']
# load lists of tweets and corresponding labels into arrays
tweets = svc_emotions.file_to_array("tweets_full.txt")
labels = svc_emotions.file_to_array("labels_full.txt")
import tweet_processing
import svc_emotions
from nltk.tokenize import word_tokenize
def output_list_from_csv(emotion):
filename = emotion + '.csv'
with open(filename, 'rb') as f:
reader = csv.reader(f)
synonym_list = list(reader)[0]
return synonym_list
tweets_legacy = tweet_processing.clean("tweets_full.txt")
labels_legacy = svc_emotions.file_to_array("labels_full.txt")
emotion_list = [
'anger',
'disgust',
'fear',
'joy',
'love',
'sadness',
'surprise',
]
all_processed_tweets = []
count_TP = {
'anger': 0,