classifiers small fixes

api/DataProcesser.py

@@ -7,54 +7,52 @@
 from nltk.corpus import stopwords
 # mais imports
 
-
 class DataProcesser():
-
  df = pd.DataFrame()
  input_column = ''
- stopwordsenglish = nltk.corpus.stopwords.words('english')
-
+ stopwords_english = stopwords.words('english')
 
  def handle_classify(self, df, classifier):
- if classifier == 'a':
- return self.classify_emotions(df)
- elif classifier == 'b':
- return self.nb_news_application(df)
+ classifier_switcher = {
+ 0: self.classify_emotions,
+ 1: self.nb_news_application,
+ 2: self.lin_regression_model
+ }
+
+ return classifier_switcher.get(classifier, lambda: "Invalid Classifier")(df)
 
  def preprocess_text(self, texto):
  if self.input_column is not None: # Verifique se a coluna foi definida
  # tiro tudo que não for texto e espaço
  texto = re.sub('[^a-z\s]', '', texto.lower())
  # tokenizo em palavras e elimino as stopwords
  palavras = [w for w in texto.split(
- ) if w not in set(self.stopwordsenglish)]
+ ) if w not in set(self.stopwords_english)]
  palavras = [w for w in texto if nltk.corpus.wordnet.synsets(w)]
  # texto_junto = ' '.join(texto)
  # junto as palavras novamente com espaços
- return ' '.join(palavras)
+ return ''.join(palavras)
  else:
  return "Coluna não escolhida. Escolha a coluna primeiro."
 
- def nb_news_application(self, df):
- nb_model = NbNewsModel(df)
- df_result = nb_model.filter_and_classify()
- return df_result
-
  def classify_emotions(self, df):
  df['output_column'] = df['input_column'].apply(
  self.preprocess_text).apply(make_prediction)
+
  result_csv = df # converte o df pra csv
  return result_csv
 
  def lin_regression_model(self, df):
  df['output_column'] = df['input_column'].apply(
  self.preprocess_text).apply(make_prediction_nblin)
+
  result_csv = df # converte o df pra csv
  return result_csv
 
- def nb_news_application(self):
- self.df['coluna_classificada'] = self.df[self.input_column].apply(self.preprocess_text).apply(news_prediction)
- result_csv = self.df
+ def nb_news_application(self, df):
+ df['output_column'] = df['input_column'].apply(news_prediction)
+
+ result_csv = df
  return result_csv
 
  ##TODO métodos com o processamento de classificação

api/NbLinRegressionModel.py

@@ -7,7 +7,7 @@ def make_prediction_nblin(my_sentence):
  with open("./models/linear_reg.pkl", "rb") as f:
  model = pickle.load(f)
 
- new_sentence = vectorizer.transform(my_sentence)
+ new_sentence = vectorizer.transform([my_sentence])
 
  prediction = model.predict(new_sentence)
  if prediction == 0:

api/NbNewsModel.py

@@ -2,18 +2,16 @@
 import pickle
 
 def news_prediction(texts):
- model_file = "api/models/text_classification_pipeline.pkl"
+ model_file = "./models/text_classification_pipeline.pkl"
  try:
  # Carregando o pipeline do arquivo .pkl
  with open(model_file, 'rb') as model_file:
  pipeline = pickle.load(model_file)
 
  # Fazendo previsões para os textos
- predictions = pipeline.predict(texts)
+ predictions = pipeline.predict([texts])
+
+ return predictions[0]
 
- return predictions
-
  except Exception as e:
  return str(e)
-# df = pd.read_csv("api/training_df/nb_news.csv")
-# print(news_prediction(df['short_description']))

api/models/nb_news.py

@@ -6,7 +6,7 @@
 from sklearn.model_selection import train_test_split
 from sklearn.naive_bayes import MultinomialNB
 
-df = pd.read_csv("api/training_df/nb_news.csv")
+df = pd.read_csv("../training_df/nb_news.csv")
 # Dividindo os dados em um conjunto de treinamento e um conjunto de teste
 x = df['short_description']
 y = df['category']