def alpha_words(name):
# open dictionary
source = 'Emotion\\'
json_pattern = os.path.join(source, '*.json')
file_list = glob.glob(json_pattern)
# for each dictionary
for file_emo in file_list:
load_file = json.load(open(file_emo, 'r'))
# print(load_file)
# read in any json file that comes in/ using glob for filename pattern matching
source = 'Tracker\\'+name
json_pattern = os.path.join(source, '*.json')
file_list = glob.glob(json_pattern)
for file in file_list:
# open each file in file list
target_doc = open(file, 'r')
Functions.num_of_tweets(file)
res = []
# for each line in document
for lines in target_doc:
word_list = []
line = lines.lower()
word = Functions.preprocess(line)
for i in word:
# append to word list to be sorted
word_list.append(i)
# sort each line in alphabetic order
word_list.sort()
#print(word_list)
# check if the dictionary word is in the list
dict_words = load_file["words"][0]
if len(dict_words) == 0:
id_ = load_file["id"]
wrd = 0
di_ct = {id_: wrd}
res.append(di_ct)
else:
for X in dict_words:
# print(X)
if Functions.binary_search(word_list, X) is True:
id_ = load_file["id"]
wrd = dict_words[X]
di_ct = {id_: wrd}
# print(di_ct)
res.append(di_ct)
else:
id_ = load_file["id"]
wrd = 0
di_ct = {id_: wrd}
res.append(di_ct)
Functions.counting(res, file,"19-02-2016",200,name)
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)
def emotion_analysis(self,word_list,file,time_stamp,num_tweets):
try:
name = self.name
# open dictionary and order words alphabetically
dict_file = self.dictionary
dictionary = open(dict_file, "r")
di_ct = json.load(dictionary)
ordered = Functions.word_order(di_ct)
# obtain bigrams for detecting negation
grams = list(bigrams(word_list))
negative_flag = False
intensifier_flag = False
Word_found = False
print(grams)
intensi = []
negate = []
for i in grams:
for n in negation_list:
if n in i:
negate.append(i)
for n in intensifier_list:
if n in i:
intensi.append(i)
print("this is x :", intensi)
print(negate)
print("________________________")
# print(word_list)
for x in word_list:
# Check for any negative words or intensifiers
# print(x, stemmer.stem(x))
for i in grams:
if x in i:
# check for negation
for n in negation_list:
if n not in i:
pass
else:
negative_flag = True
# check for intensifier
for n in intensifier_list:
if n not in i:
pass
else:
intensifier_flag = True
# check if word or stem of word is in dictionary
if Functions.binary_search(self, ordered, x) is True:
if negative_flag is True:
count = 1
negation_counter.append(count)
pass
else:
if di_ct[x]:
i_d = di_ct[x][1]
if intensifier_flag is True:
wrd = di_ct[x][0] + 1
intensifier_flag = False
else:
wrd = di_ct[x][0]
new_d = {i_d: abs(wrd)}
res.append(new_d)
# print(new_d)
elif Functions.binary_search(self,ordered,stemmer.stem(x))is True:
x_stem = stemmer.stem(x)
# handles negation and intensifier occurrence
if negative_flag is True:
# negation_counter += 1
pass
else:
if di_ct[x_stem]:
# print(x)
i_d = di_ct[x_stem][1]
if intensifier_flag is True:
wrd = di_ct[x_stem][0] + 1
intensifier_flag = False
else:
wrd = di_ct[x_stem][0]
new_d = {i_d: abs(wrd)}
res.append(new_d)
# print(new_d)
# print("number of tweets :" , num_tweets)
# Company.create_graph(self,name)
# Company.create_csv(self, name)
# dictionary.close()
Functions.counting(self, res, file, time_stamp, num_tweets,name)
return res
except BaseException as e:
print ("emotion analysis error: ", e)