Merge branch 'develop' into about-page

api/DataProcesser.py

@@ -1,7 +1,6 @@
 
 from NbNewsModel import news_prediction
 from NbEmotionsModel import make_prediction
-from NbLinRegressionModel import make_prediction_nblin
 from available_classifiers import get_available_classifiers
 
 import Neural_Network2

api/HateSpeechModel.py

@@ -0,0 +1,16 @@
+import pickle
+
+def make_prediction(my_sentence):
+ model_file = "./models/hate_speech.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([my_sentence])
+
+ return predictions[0]
+
+ except Exception as e:
+ return str(e)

api/NbEmotionsModel.py

@@ -1,11 +1,5 @@
-import pandas as pd
 import pickle
 
-# bag of words
-from sklearn.feature_extraction.text import TfidfVectorizer
-
-#tfidf_vectorizer = TfidfVectorizer(use_idf=True)
-
 def make_prediction(my_sentence):
  model_file = "./models/emotions_pipeline.pkl"
  try:

api/NbNewsModel.py

@@ -1,4 +1,3 @@
-import pandas as pd
 import pickle
 
 def news_prediction(texts):

api/models_code/nb_emotions.py

@@ -1,8 +1,6 @@
 import pandas as pd
 import pickle
 from sklearn.pipeline import make_pipeline
-from sklearn.feature_extraction.text import CountVectorizer
-from sklearn.feature_extraction.text import TfidfVectorizer
 
 # bag of words
 from sklearn.feature_extraction.text import TfidfVectorizer
@@ -11,7 +9,12 @@
 from sklearn.naive_bayes import MultinomialNB
 
 df = pd.read_csv('../training_df/tweet_emotions.csv')
-train_data, test_data, train_target, test_target = train_test_split(df["content"], df["sentiment"], test_size=0.2, shuffle=True)
+
+# Dividindo os dados em um conjunto de treinamento e um conjunto de teste
+x = df['content']
+y = df['sentiment']
+
+train_data, test_data, train_target, test_target = train_test_split(x, y, test_size=0.2, shuffle=True)
 
 # Criando um pipeline com o vetorizador TF-IDF e o classificador Multinomial Naive Bayes
 pipeline = make_pipeline(TfidfVectorizer(), MultinomialNB())

api/models_code/nb_hatespeech.py

@@ -0,0 +1,27 @@
+import pandas as pd
+import pickle
+from sklearn.pipeline import make_pipeline
+
+# bag of words
+from sklearn.feature_extraction.text import TfidfVectorizer
+
+from sklearn.model_selection import train_test_split
+from sklearn.naive_bayes import MultinomialNB
+
+df = pd.read_csv("../training_df/nb_hatespeech.csv", sep=';')
+
+# Dividindo os dados em um conjunto de treinamento e um conjunto de teste
+x = df["comment"]
+y = df["isHate"]
+
+X_train, X_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=42)
+
+# Criando um pipeline com o vetorizador TF-IDF e o classificador Multinomial Naive Bayes
+pipeline = make_pipeline(TfidfVectorizer(), MultinomialNB())
+
+# Ajustando o modelo ao conjunto de treinamento
+pipeline.fit(X_train, y_train)
+
+# Salvando o pipeline em um arquivo .pkl
+with open("hate_speech.pkl", "wb") as model_file:
+ pickle.dump(pipeline, model_file)

api/models_code/nb_news.py

@@ -1,18 +1,20 @@
 import pandas as pd
 import pickle
 from sklearn.pipeline import make_pipeline
-from sklearn.feature_extraction.text import CountVectorizer
+
+# bag of words
 from sklearn.feature_extraction.text import TfidfVectorizer
+
 from sklearn.model_selection import train_test_split
 from sklearn.naive_bayes import MultinomialNB
 
 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']
 
 X_train, X_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=42)
-# Criando um pipeline que inclui o vetorizador TF-IDF e o modelo Naive Bayes
 
 # Criando um pipeline com o vetorizador TF-IDF e o classificador Multinomial Naive Bayes
 pipeline = make_pipeline(TfidfVectorizer(), MultinomialNB())

api/requirements.txt.orig

@@ -0,0 +1,24 @@
+<<<<<<< Updated upstream:api/requirements.txt
+Flask==2.3.2
+Flask-Cors==4.0.0
+pandas==2.0.3
+nltk==3.8.1
+scikit-learn==1.3.0
+numpy==1.25.2
+matplotlib==3.7.1
+seaborn==0.13.0
+tensorflow==2.16.1
+keras==3.0.0
+=======
+Flask==2.3.2
+Flask-Cors==4.0.0
+pandas==2.0.3
+nltk==3.8.1
+scikit-learn==1.3.0
+numpy==1.25.2
+matplotlib==3.7.1
+seaborn==0.13.0
+tensorflow==2.16.1
+keras==3.0.0
+torchtext==0.17.2
+>>>>>>> Stashed changes:requirements.txt