def load_queries(queries_filename):
file = open(queries_filename, 'r')
queries = {}
vocab = Vocab()
tokenizer = Tokenizer()
lemmatizer = Lemmatizer()
for l in file.readlines():
l = l.replace('\n', '')
l_arr = l.split('\t')
q = Query()
q.id = int(l_arr[0])
q_text = l_arr[1]
q_syn_text = ''
if len(l_arr) > 2:
q_syn_text = l_arr[2]
q.text = q_text + ' ' + q_syn_text
q.tokens = lemmatizer.fit_transform(tokenizer.fit_transform(q_text))
q.synonim_tokens = lemmatizer.fit_transform(tokenizer.fit_transform(q_syn_text))
queries[q.id] = q
file.close()
# create vocab
for q_id in queries.keys():
q = queries[q_id]
tokens = q.tokens + q.synonim_tokens
vocab.add_phrase(tuple(q.tokens))
for tkn in tokens:
vocab.add1(tkn)
grams, inv_grams, gap_grams = get_ngrams(tokens, 2, inverted=True, with_gap=True)
for g in grams + inv_grams + gap_grams:
vocab.add2(g)
return queries, vocab
def lemmatize(self, stop_words=None):
tokenizer = Tokenizer(stop_words=stop_words)
lemmatizer = Lemmatizer(stop_words=stop_words)
self.lemmatized_queries = dict()
for q_id in self.queries.dict.keys():
q = self.queries.get(q_id)
tok_q = tokenizer.fit_transform(q)
lem_q = lemmatizer.fit_transform(tok_q)
self.lemmatized_queries[int(q_id)] = lem_q
removeStopWords=args["removeStopWords"],
doSpellingCorrection=args["doSpellingCorrection"],
removeNewLine=args["removeNewLine"],
removePunctuation=args["removePunctuation"],
removeHtmlTags=args["removeHtmlTags"],
minTextLength=args["minTextLength"])
predict_df["processed"] = preprocessor.fit_transform(
predict_df["text_german"])
predict_df = predict_df.dropna(subset=["processed"], axis=0)
print("Tokenize")
tokenizer = Tokenizer(tokenizeStr=preperation_technique,
ngram=preperation_ngram,
fasttextFile=args["fasttext_file"],
doLower=args["doLower"])
predict_df["processed"] = tokenizer.fit_transform(predict_df["processed"])
## for testing purposes
#train_df = train_df.sample(100)
#val_df = val_df.sample(20)
#test_df = test_df.sample(20)
## apply the model
labels = [
"price_pos", "price_neg", "quality_pos", "quality_neg",
"restaurant_pos", "restaurant_neg", "food_pos", "food_neg",
"drinks_pos", "drinks_neg", "ambience_pos", "ambience_neg",
"service_pos", "service_neg"
]
sentimentDict = {
"pos": "positiv",
val_df.to_pickle(val_pre_path)
test_df.to_pickle(test_pre_path)
else:
train_df = pd.read_pickle(train_pre_path)
val_df = pd.read_pickle(val_pre_path)
test_df = pd.read_pickle(test_pre_path)
## get data and train columns
data_column = list(set(train_df.columns) - set(args["targets"]))[0]
if run_tokenization:
## do tokenization
print("Tokenize")
tokenizer = Tokenizer(tokenizeStr=tokenizer_model[0],
fasttextFile=args["fasttext_file"],
doLower=args["doLower"])
train_df[data_column] = tokenizer.fit_transform(train_df[data_column])
val_df[data_column] = tokenizer.transform(val_df[data_column])
test_df[data_column] = tokenizer.transform(test_df[data_column])
## save the preprocessed data
if not os.path.exists(os.path.join(args["data_path"], "temp")):
os.makedirs(os.path.join(args["data_path"], "temp"))
train_df.to_pickle(train_tok_path)
val_df.to_pickle(val_tok_path)
test_df.to_pickle(test_tok_path)
else:
train_df = pd.read_pickle(train_tok_path)
val_df = pd.read_pickle(val_tok_path)
test_df = pd.read_pickle(test_tok_path)
np.save(train_pre_path.format("data"), train_data, allow_pickle=True)
np.save(val_pre_path.format("data"), val_data, allow_pickle=True)
np.save(test_pre_path.format("data"), test_data, allow_pickle=True)
np.save(train_pre_path.format("target"),
train_target,
allow_pickle=True)
np.save(val_pre_path.format("target"), val_target, allow_pickle=True)
np.save(test_pre_path.format("target"), test_target, allow_pickle=True)
if run_tokenization:
## do tokenization
print("Tokenize")
tokenizer = Tokenizer(args=tokenizer_model,
fasttextFile=args["fasttext_file"],
doLower=args["doLower"])
train_data = tokenizer.fit_transform(train_data)
val_data = tokenizer.transform(val_data)
test_data = tokenizer.transform(test_data)
## save the preprocessed data
if not os.path.exists(os.path.join(args["data_path"], "temp")):
os.makedirs(os.path.join(args["data_path"], "temp"))
if sparse.issparse(train_data):
sparse.save_npz(train_tok_path.format("data"), train_data)
else:
np.save(train_tok_path.format("data"), train_data)
np.save(train_tok_path.format("target"), train_target)
if sparse.issparse(val_data):
sparse.save_npz(val_tok_path.format("data"), val_data)
else:
np.save(val_tok_path.format("data"), val_data)
