def process(self, text, doc_id):
'''
calls on the TextProcessor class for text processing and tokenization of documents.
each url is designated with unique id number.
id is increased at the end for new url.
returns updated index.
'''
processor = TextProcessor(text, self.index, doc_id)
processor.process_text()
return processor.get_index()
def run(self):
logger.info('Creating text processor')
text_processor = TextProcessor()
for file in self.input().keys():
logger.info('Reading %s file: "%s"', file, self.input()[file].path)
df = pd.read_csv(self.input()[file].path)
logger.info('Its %s lines', df.shape[0])
logger.info('Start processing %s...', file)
df.name = df.name.map(lambda x: text_processor.process_text(x, lang='ru'))
df.name = df.name.map(lambda x: ' '.join(x))
logger.info('Processing of %s succeed, writing it to "%s"', file, self.output()[file].path)
df.to_csv(self.output()[file].path)
if __name__ == "__main__":
pp = pprint.PrettyPrinter(indent=4, depth=2)
# Initialize classifier
classifier = NaiveBayes()
# Train
for f in find("data/1/training"):
f = f.strip()
if not f.endswith(".txt"):
continue
with open(f) as doc:
text = doc.read()
sentences = nlp.process_text(text)
label = "movie" if "movie" in f else "play"
classifier.train(sentences, label=label)
# Test
for f in find("data/1/testing"):
f = f.strip()
if not f.endswith(".txt"):
continue
with open(f) as doc:
text = doc.read()
sentences = nlp.process_text(text)