def pre_process(self):
name = self.name
file_list = self.file_list
try:
# Split text into a list of words
list_ = []
x = 0
while x < len(file_list):
num_tweets = Functions.num_of_tweets(file_list[x])
time_stamp = Functions.time_stamp(file_list[x])
target_doc = open(file_list[x], 'r')
print("FILE: ",target_doc.name)
res = []
for lines in target_doc:
word_list = []
line = lines.lower()
word = Functions.preprocess(line)
for i in word:
if i not in punctuation:
word_list.append(i)
# For testing purposes
list_.append(i)
#print("done")
emo = EAC(name, word_list, file_list[x], time_stamp, num_tweets,res)
emo.emotion_analysis()
x += 1
return list_
except BaseException as e:
print("Pre_process error: ", e)
def pre_process(self, file_list):
try:
# Split text into a list of words
list_ = []
x=0
while x < len(file_list):
num_tweets = Functions.num_of_tweets(file_list[x])
target_doc = open(file_list[x], 'r')
time_stamp = Functions.time_stamp(file_list[x])
target_doc = open(file_list[x], 'r')
for lines in target_doc:
word_list =[]
line = lines.lower()
word = Functions.preprocess(line)
for i in word:
if i not in punctuation:
word_list.append(i)
# For testing purposes
list_.append(i)
Company.emotion_analysis(self,word_list,file_list[x],time_stamp,num_tweets)
x += 1
print(list_)
return list_
except BaseException as e:
print("Pre_process error: ", e)
def emotion_measure(name):
# read in any json file that comes in/ using glob for filename pattern matching
source = 'Tracker\\'+name
json_dir = source
json_pattern = os.path.join(json_dir, '*.json')
file_list = glob.glob(json_pattern)
for file in file_list:
print(file)
target_doc = open(file, 'r')
res = []
time_stamp = Functions.time_stamp(file)
num_tweets = Functions.num_of_tweets(file)
Functions.num_of_tweets(file)
for lines in target_doc:
# print(lines)
line = lines.lower()
word = twitterstreamV2.preprocess(line)
source = 'Emotion\\'
json_dir = source
json_pattern = os.path.join(json_dir, '*.json')
file_list = glob.glob(json_pattern)
for file_emo in file_list:
emo_doc = open(file_emo, 'r')
load_file = json.load(emo_doc)
for wd in word:
# checks if the word exists in the dictionary and prints it out
dict_words = load_file["words"][0]
if wd in dict_words:
id_ = load_file["id"]
wrd = dict_words[wd]
di_ct = {id_: wrd}
res.append(di_ct)
#print(wd)
#print(di_ct)
else:
id_ = load_file["id"]
wrd = 0
di_ct = {id_: wrd}
res.append(di_ct)
target_doc.close()
#print(res)
Functions.counting(res, file, time_stamp, num_tweets, name)