app.py

Add the app.py file with the AI code

app.py

@@ -0,0 +1,172 @@
+import pandas as pd
+import numpy as np
+from sklearn.feature_extraction.text import CountVectorizer
+from sklearn.tree import DecisionTreeClassifier
+from sklearn.model_selection import train_test_split
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.neural_network import MLPClassifier
+from sklearn.ensemble import VotingClassifier
+from tensorflow.keras.models import Sequential
+from tensorflow.keras.layers import Embedding, LSTM, Dense
+from tensorflow.keras.preprocessing.text import Tokenizer
+from tensorflow.keras.preprocessing.sequence import pad_sequences
+import tensorflow as tf
+from joblib import dump
+from joblib import load
+from google.colab import drive
+import gdown
+from pydrive.auth import GoogleAuth
+from pydrive.drive import GoogleDrive
+import pickle
+import gradio as gr
+
+
+def train_creative_model(text_data):
+    if not text_data or len(text_data) == 0:
+        print("No hay suficientes datos para entrenar el modelo creativo.")
+        return None, None, None
+
+    tokenizer = Tokenizer()
+    tokenizer.fit_on_texts(text_data)
+    total_words = len(tokenizer.word_index) + 1
+
+    input_sequences = []
+    for line in text_data:
+        tokens = line.split('\t')  # Separar por tabuladores
+        for token in tokens:
+            token_list = tokenizer.texts_to_sequences([token])[0]
+            for i in range(len(token_list)):
+                n_gram_sequence = token_list[i]
+                input_sequences.append(n_gram_sequence)
+
+    if not input_sequences or len(input_sequences) == 0:
+        print("No hay suficientes secuencias para entrenar el modelo creativo.")
+        return None, None, None
+
+    X = np.array(input_sequences)
+    y = tf.keras.utils.to_categorical(X, num_classes=total_words)
+
+    model = Sequential()
+    model.add(Embedding(total_words, 50, input_length=1))
+    model.add(LSTM(100))
+    model.add(Dense(total_words, activation='softmax'))
+
+    model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
+    model.fit(X, y, epochs=50, verbose=0)
+
+    return model, tokenizer, None  # Devolver None para creative_max_sequence_length
+
+file_path = 'dialogs.csv'
+df = pd.read_csv(file_path)
+
+# Crear un vectorizador TF-IDF
+vectorizer = TfidfVectorizer()
+
+# Aplicar el vectorizador a las frases de Prompt y Answer
+X = vectorizer.fit_transform(df['Prompt']).toarray()
+y = df['Answer']  # Utilizar las respuestas como etiquetas
+
+# Dividir los datos en conjuntos de entrenamiento y prueba
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+
+# Inicializar modelos
+tree_model = DecisionTreeClassifier()
+nn_model = MLPClassifier(batch_size=32)
+
+# Crear un clasificador de votación
+voting_clf = VotingClassifier(estimators=[('tree', tree_model), ('nn', nn_model)], voting='hard')
+
+with open('Voting_model.pkl', 'rb') as file:
+    voting_model = pickle.load(file)
+with open('Creative_model.pkl', 'rb') as file:
+    voting_model = pickle.load(file)
+
+def get_combined_response(prompt, voting_model, creative_model, tokenizer, creative_max_sequence_length):
+    prompt_vector = vectorizer.transform([prompt]).toarray()
+    response_index = voting_model.predict(prompt_vector)[0]
+
+
+    # Utilizar el modelo de votación
+    #return df.loc[df['Answer'] == response_index, 'Answer'].values[0]
+
+    seed_text = df.loc[df['Answer'] == response_index, 'Prompt'].values[0]
+    creative_response = generate_creative_text(seed_text, CREATIVE_NEXT_WORDS, creative_model, tokenizer, creative_max_sequence_length)
+    #return creative_response
+    return "Awnser 1: " + df.loc[df['Answer'] == response_index, 'Answer'].values[0] + " // Awnser 2: " + creative_response
+
+
+def generate_creative_text(seed_text, next_words, model, tokenizer, max_sequence_length):
+    generated_text = seed_text
+    for _ in range(next_words):
+        token_list = tokenizer.texts_to_sequences([seed_text])[0]
+        if max_sequence_length is not None:
+            token_list = pad_sequences([token_list], maxlen=max_sequence_length-1, padding='pre')
+        else:
+            token_list = [token_list]
+
+        predicted_probabilities = model.predict(token_list, verbose=0)
+        predicted = np.argmax(predicted_probabilities)
+
+
+        output_word = ""
+        for word, index in tokenizer.word_index.items():
+            if index == predicted:
+                output_word = word
+                break
+
+        seed_text += " " + output_word
+        generated_text += " " + output_word
+
+    return generated_text
+
+
+
+
+# Load your models and other necessary components here
+
+creative_max_sequence_length = 10  # Replace with the correct value used during training
+VOTING_RESPONSE_INDEX = 0  # Replace with the correct index for voting model responses
+CREATIVE_NEXT_WORDS = 10  # Replace with the desired number of creative next words
+
+def chat_interface(user_input):
+    response = get_combined_response(user_input, voting_clf, creative_model, creative_tokenizer, creative_max_sequence_length)
+
+    # Display the response to the user
+    print(f"Model Response: {response}")
+
+    # Ask the user for a score
+    score = int(input(f"Puntuación para la respuesta '{response}': "))
+
+    # Efficient retraining process
+    if score <= 2:
+        # Ask the user for the correct response
+        correct_response = input(f"La respuesta actual es '{response}'. ¿Cuál es la respuesta correcta?: ")
+
+        # Update the model only if the correct response is different from the current response
+        if correct_response.lower() != response.lower():
+            new_data = {'Prompt': user_input, 'Answer': correct_response}
+            df = df.append(new_data, ignore_index=True)
+
+            with open('dialogs.txt', 'a') as dialogs_file:
+                dialogs_file.write(f"{user_input}\t{correct_response}\n")
+
+            new_X = vectorizer.transform([user_input]).toarray()
+            new_y = [correct_response]
+            X = np.concatenate((X, new_X))
+            y = np.concatenate((y, new_y))
+
+            # Re-train the voting classifier with the new data
+            #voting_clf.fit(X, y)
+
+            print("¡Gracias por tu corrección! El modelo ha sido actualizado para mejorar. La próxima vez el modelo tendrá en cuenta tus respuestas correctas.")
+        else:
+            print("Entendido. No se necesita corrección.")
+    else:
+        print("¡Gracias por tu retroalimentación!")
+
+    # Save the updated DataFrame to a new file
+    df.to_csv('dialogs.csv', index=False)
+
+# Create a Gradio interface
+iface = gr.Interface(fn=chat_interface, inputs="text", outputs="text")
+iface.launch()