def fit_model(df, method):
"""
Fitting chosen model
params:
df: DataFrame used,
method: model chosen
returns:
generated model,
transformed datas
"""
if method == "TF-IDF":
model = TfidfVectorizer(analyzer='word',
ngram_range=(1, 2),
min_df=0,
stop_words=STOPS)
X = model.fit_transform(df['content'])
elif method == "CountVectorizer":
model = CountVectorizer(analyzer='word',
ngram_range=(1, 2),
min_df=0,
stop_words=STOPS)
X = model.fit_transform(df['content'])
elif method == "BERT":
word_embedding_model = models.Transformer('camembert-base')
pooling_model = models.Pooling(
word_embedding_model.get_word_embedding_dimension(),
pooling_mode_mean_tokens=True,
pooling_mode_max_tokens=False)
model = SentenceTransformer(
modules=[word_embedding_model, pooling_model])
X = model.encode(df['content'], show_progress_bar=True)
return model, X
