def read_csv(filename = './train.csv'):
phrase = []
emoji = []
with open (filename) as csvDataFile:
csvReader = csv.reader(csvDataFile)
print(csvReader)
for row in csvReader:
phrase.append(row[0])
emoji.append(row[1])
def read_csv(filename='data/emojify_data.csv'):
with open(filename) as f:
csvfile=csv.reader(f)
phrases=[]
emoji=[]
for row in csvfile:
phrases.append(row[0])
emoji.append(row[1])
X=np.asarray(phrases)
Y=np.asarray(emoji,dtype=int)
return X,Y
def read_csv(filename):
tweet, emoji = [], []
with open(filename) as csvDataFile:
csvReader = csv.reader(csvDataFile)
for row in csvReader:
tweet.append(row[0])
emoji.append(row[1])
return np.asarray(tweet), np.asarray(emoji, dtype=int)
def read_csv(filename): #read dataset files
phrase = []
emoji = []
with open (filename) as csvDataFile:
csvReader = csv.reader(csvDataFile)
for row in csvReader:
phrase.append(row[0])
emoji.append(row[1])
X = np.asarray(phrase)
Y = np.asarray(emoji, dtype=int)
return X, Y
def read_csv(filename = 'data/emojify_data.csv'):
phrase = []
emoji = []
with open (filename, encoding='utf-8') as csvDataFile:
csvReader = csv.reader(csvDataFile)
for row in csvReader:
phrase.append(row[0])
emoji.append(row[1])
X = np.asarray(phrase)
Y = np.asarray(emoji, dtype=int)
return X, Y
def read_csv(filename='F:\\deeplearning-data\\word2vec-data\\train_emoji.csv'):
phrase = []
emoji = []
with open(filename) as csvDataFile:
csvReader = csv.reader(csvDataFile)
for row in csvReader:
phrase.append(row[0])
emoji.append(row[1])
X = np.asarray(phrase)
Y = np.asarray(emoji, dtype=int)
return X, Y
def read_csv(filename = 'data/emojify_data.csv'):
phrase = []
emoji = []
with open (filename) as csvDataFile:
csvReader = csv.reader(csvDataFile)
for row in csvReader:
phrase.append(row[0])
emoji.append(row[1])
X = np.asarray(phrase)
Y = np.asarray(emoji, dtype=int)
return X, Y
def load_csv(filename):
sentence = []
emoji = []
# open the csv and separate the text sentences and emoji
with open(filename) as csv_file:
csv_data = csv.reader(csv_file)
for row in csv_data:
sentence.append(row[0])
emoji.append(row[1])
X = np.asarray(sentence)
Y = np.asarray(emoji, dtype=int)
return X, Y
def read_csv(filename='data/emojify_data.csv'):
phrase = []
emoji = []
with open(settings.BASE_DIR + settings.STATIC_URL +
filename) as csvDataFile:
csvReader = csv.reader(csvDataFile)
for row in csvReader:
phrase.append(row[0])
emoji.append(row[1])
X = np.asarray(phrase)
Y = np.asarray(emoji, dtype=int)
return X, Y
def read_csv(filename='data/emojify_data.csv'):
phrase = []
emoji = []
sdvgwuygv
sdbxuwydcy
csidcgwuyg
cbwu
with open(filename) as csvDataFile:
csvReader = csv.reader(csvDataFile)
for row in csvReader:
phrase.append(row[0])
emoji.append(row[1])
X = np.asarray(phrase)
Y = np.asarray(emoji, dtype=int)
return X, Y
def read_csv_ht(filename = 'data/emojify_data.csv', rte = False):
phrase_h = []
phrase_t = []
emoji = []
with open (filename, encoding='utf8') as csvDataFile:
csvReader = csv.reader(csvDataFile)
for row in csvReader:
# print(". ".join(row[0:1]))
# print(row[2])
phrase_h.append(row[0])
phrase_t.append(row[1])
emoji.append(row[2])
# print(phrase)
# print(emoji)
X_h = np.asarray(phrase_h)
X_t = np.asarray(phrase_t)
Y = np.asarray(emoji, dtype=int)
return X_h, X_t, Y
def read_csv(filename='data/SD_dataset_FINAL.csv'):
phrase = []
emoji = []
with open(filename) as csvDataFile:
csvReader = csv.reader(csvDataFile)
special_char_pattern = re.compile(r'([{.(-)!}])')
for row in csvReader:
num_col = len(row)
s = ""
for c_n in range(num_col - 1):
s += row[c_n]
s = re.sub(',', ':', s)
s = contractions.fix(s)
s = special_char_pattern.sub(" \\1 ", s)
s = remove_special_characters(s, remove_digits=True)
phrase.append(s)
emoji.append(row[num_col - 1])
X = np.asarray(phrase)
Y = np.asarray(emoji, dtype=int)
return X, Y
def read_csv(filename = 'data/emojify_data.csv', rte = False):
phrase = []
emoji = []
with open (filename, encoding='utf8') as csvDataFile:
csvReader = csv.reader(csvDataFile)
for row in csvReader:
if rte:
# print(". ".join(row[0:1]))
# print(row[2])
phrase.append(" ".join(row[0:2]))
emoji.append(row[2])
else:
phrase.append(row[0])
emoji.append(row[1])
# print(phrase)
# print(emoji)
X = np.asarray(phrase)
Y = np.asarray(emoji, dtype=int)
return X, Y
#use dictionary to store the emoji
#content include(text,city)pair
content = collection.find({},{"text":1,"place.full_name":1, "_id":0})
#for extra
stateEmojiCount = {}
for words in content:
# emoji list
emoji = []
for t in words["text"]:
if t in UNICODE_EMOJI:
emoji.append(t);
if len(words) == 2:
address = words['place']['full_name'].split(", ")
if len(address)== 2:
city = address[0]
state = address[1]
else:
state = ''
if len(state) == 2:
# for extra point
if state in stateEmojiCount:
stateEmojiCount[state] += emoji
else:
stateTweets = {}
#count the tweet used in city in California
cityCount = {}
# #for extra
# stateEmojiCount = {}
for words in content:
# print(words)
# emoji list
emoji = []
for t in words["text"]:
if t in UNICODE_EMOJI:
emoji.append(t)
for symbol in emoji:
if symbol in emojiCount:
emojiCount[symbol] += 1
else:
emojiCount[symbol] = 1
if len(words) == 2:
address = words['place']['full_name'].split(", ")
if len(address) == 2:
city = address[0]
# print(address[0])
state = address[1]
# print(address[1])
else:
