class DostN:
def __init__(self):
self.db = DB()
self.tokenizer = RegexTokenizer()
self.model = FastTextSocialNetworkModel(tokenizer=self.tokenizer)
self.tokens = self.tokenizer.split('всё очень плохо')
def ready_msg(self, messages, nnID):
results = self.model.predict(messages, k=2)
sentiments = []
for message, sentiment in zip(messages, results):
sentiments.append(sentiment)
try:
pos = sentiments[0]['positive']
self.db.setPos(nnID, pos)
except Exception as e:
print(e, 22)
pos = 0
self.db.setPos(nnID, pos)
try:
neg = sentiments[0]['negative']
self.db.setNegative(nnID, neg)
except Exception as e:
print(e, 29)
neg = 0
self.db.setNegative(nnID, neg)
try:
ne = sentiments[0]['neutral']
self.db.setNeutral(nnID, ne)
except Exception as e:
print(e, 36)
ne = 0
self.db.setNeutral(nnID, ne)
return (sentiments)
def parse_senstiment(self, text):
tokenizer = RegexTokenizer()
tokens = tokenizer.split('всё очень плохо') # хз
model = FastTextSocialNetworkModel(tokenizer=tokenizer)
return model.predict([text], k=2)[0]
def graph():
file = filedialog.askopenfilename(filetypes=(("Text files", "*.txt"),
("all files", "*.*")))
f = open(file)
raw = f.read()
sentences = nltk.sent_tokenize(raw)
command = 'download'
arguments = ['fasttext-social-network-model']
if command == 'download':
downloader = DataDownloader()
for filename in arguments:
if filename not in AVAILABLE_FILES:
raise ValueError(f'Unknown package: {filename}')
source, destination = AVAILABLE_FILES[filename]
destination_path: str = os.path.join(DATA_BASE_PATH, destination)
if os.path.exists(destination_path):
continue
downloader.download(source=source, destination=destination)
else:
raise ValueError('Unknown command')
import dostoevsky
from dostoevsky.tokenization import RegexTokenizer
from dostoevsky.models import FastTextSocialNetworkModel
tokenizer = RegexTokenizer()
tokens = tokenizer.split(
'всё очень плохо') # [('всё', None), ('очень', None), ('плохо', None)]
model = FastTextSocialNetworkModel(tokenizer=tokenizer)
messages = sentences
results = model.predict(messages, k=2)
for message, sentiment in zip(messages, results):
positive_values_all = [
sentiment.get('positive')
for message, sentiment in zip(messages, results)
]
positive_values = [
0.0 if value == None else value for value in positive_values_all
]
negative_values_all = [
sentiment.get('negative')
for message, sentiment in zip(messages, results)
]
negative_values = [
0.0 if value == None else value for value in negative_values_all
]
summary = (len(negative_values))
n_value = np.array(negative_values)
p_value = np.array(positive_values)
counts_value = np.arange(summary)
plt.plot(counts_value, p_value, n_value)
plt.show()
def begin():
file = filedialog.askopenfilename(filetypes=(("Text files", "*.txt"),
("all files", "*.*")))
f = open(file)
raw = f.read()
sentences = nltk.sent_tokenize(raw)
command = 'download'
arguments = ['fasttext-social-network-model']
if command == 'download':
downloader = DataDownloader()
for filename in arguments:
if filename not in AVAILABLE_FILES:
raise ValueError(f'Unknown package: {filename}')
source, destination = AVAILABLE_FILES[filename]
destination_path: str = os.path.join(DATA_BASE_PATH, destination)
if os.path.exists(destination_path):
continue
downloader.download(source=source, destination=destination)
else:
raise ValueError('Unknown command')
tokenizer = RegexTokenizer()
tokens = tokenizer.split(
'всё очень плохо') # [('всё', None), ('очень', None), ('плохо', None)]
model = FastTextSocialNetworkModel(tokenizer=tokenizer)
messages = sentences
results = model.predict(messages, k=2)
for message, sentiment in zip(messages, results):
analysis_line = '\n', message, '\n', '->', '\n', sentiment, '\n'
text.insert(END, analysis_line)
from dostoevsky.tokenization import RegexTokenizer
from dostoevsky.models import FastTextSocialNetworkModel
tokenizer = RegexTokenizer()
tokens = tokenizer.split(
'всё очень плохо') # [('всё', None), ('очень', None), ('плохо', None)]
model = FastTextSocialNetworkModel(tokenizer=tokenizer)
message = ['Волосы у девушки просто огонь!!! Красота!!!']
results = model.predict(message, k=len(message))
for message, sentiment in zip(message, results):
# привет -> {'speech': 1.0000100135803223, 'skip': 0.0020607432816177607}
# люблю тебя!! -> {'positive': 0.9886782765388489, 'skip': 0.005394937004894018}
# малолетние дебилы -> {'negative': 0.9525841474533081, 'neutral': 0.13661839067935944}]
print(message, '->', sentiment)