app.py

import warnings
import numpy as np
import pandas as pd
import os
import json
import random
import gradio as gr
from sklearn.ensemble import IsolationForest, RandomForestClassifier, GradientBoostingClassifier
from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.preprocessing import OneHotEncoder
from sklearn.neural_network import MLPClassifier
from sklearn.metrics import accuracy_score
from deap import base, creator, tools, algorithms
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
import torch
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import DataLoader, TensorDataset

warnings.filterwarnings('ignore', category=FutureWarning, module='huggingface_hub.file_download')

# Initialize Example Emotions Dataset
data = {
    'context': [
        'I am happy', 'I am sad', 'I am angry', 'I am excited', 'I am calm',
        'I am feeling joyful', 'I am grieving', 'I am feeling peaceful', 'I am frustrated',
        'I am determined', 'I feel resentment', 'I am feeling glorious', 'I am motivated',
        'I am surprised', 'I am fearful', 'I am trusting', 'I feel disgust', 'I am optimistic',
        'I am pessimistic', 'I feel bored', 'I am envious'
    ],
    'emotion': [
        'joy', 'sadness', 'anger', 'joy', 'calmness', 'joy', 'grief', 'calmness', 'anger',
        'determination', 'resentment', 'glory', 'motivation', 'surprise', 'fear', 'trust',
        'disgust', 'optimism', 'pessimism', 'boredom', 'envy'
    ]
}
df = pd.DataFrame(data)

# Encoding the contexts using One-Hot Encoding
encoder = OneHotEncoder(handle_unknown='ignore')
contexts_encoded = encoder.fit_transform(df[['context']]).toarray()

# Encoding emotions
emotions_target = df['emotion'].astype('category').cat.codes
emotion_classes = df['emotion'].astype('category').cat.categories

# Advanced Neural Network with PyTorch
class AdvancedNN(nn.Module):
    def __init__(self, input_size, hidden_size, num_classes):
        super(AdvancedNN, self).__init__()
        self.layer1 = nn.Linear(input_size, hidden_size)
        self.layer2 = nn.Linear(hidden_size, hidden_size)
        self.layer3 = nn.Linear(hidden_size, num_classes)
        self.relu = nn.ReLU()
        self.dropout = nn.Dropout(0.2)
        
    def forward(self, x):
        x = self.relu(self.layer1(x))
        x = self.dropout(x)
        x = self.relu(self.layer2(x))
        x = self.dropout(x)
        x = self.layer3(x)
        return x

# Train Advanced Neural Network
X_train, X_test, y_train, y_test = train_test_split(contexts_encoded, emotions_target, test_size=0.2, random_state=42)

# Convert to dense array if it's a sparse matrix, otherwise leave as is
X_train = X_train.toarray() if hasattr(X_train, 'toarray') else X_train
X_test = X_test.toarray() if hasattr(X_test, 'toarray') else X_test

# Ensure y_train and y_test are numpy arrays
y_train = y_train.to_numpy() if hasattr(y_train, 'to_numpy') else np.array(y_train)
y_test = y_test.to_numpy() if hasattr(y_test, 'to_numpy') else np.array(y_test)

input_size = X_train.shape[1]
hidden_size = 64
num_classes = len(emotion_classes)

model = AdvancedNN(input_size, hidden_size, num_classes)
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.001)

train_dataset = TensorDataset(torch.FloatTensor(X_train), torch.LongTensor(y_train))
train_loader = DataLoader(train_dataset, batch_size=32, shuffle=True)

model = AdvancedNN(input_size, hidden_size, num_classes)
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.001)

train_dataset = TensorDataset(torch.FloatTensor(X_train), torch.LongTensor(y_train))
train_loader = DataLoader(train_dataset, batch_size=32, shuffle=True)

# Ensemble with Random Forest and Gradient Boosting
rf_model = RandomForestClassifier(n_estimators=100, random_state=42)
gb_model = GradientBoostingClassifier(n_estimators=100, random_state=42)

rf_model.fit(X_train, y_train)
gb_model.fit(X_train, y_train)

# Isolation Forest Anomaly Detection Model
historical_data = np.array([model(torch.FloatTensor(contexts_encoded)).argmax(1).numpy()]).T
isolation_forest = IsolationForest(contamination=0.1, random_state=42)
isolation_forest.fit(historical_data)

# Enhanced Emotional States
emotions = {
    'joy': {'percentage': 10, 'motivation': 'positive', 'intensity': 0},
    'pleasure': {'percentage': 10, 'motivation': 'selfish', 'intensity': 0},
    'sadness': {'percentage': 10, 'motivation': 'negative', 'intensity': 0},
    'grief': {'percentage': 10, 'motivation': 'negative', 'intensity': 0},
    'anger': {'percentage': 10, 'motivation': 'traumatic or strong', 'intensity': 0},
    'calmness': {'percentage': 10, 'motivation': 'neutral', 'intensity': 0},
    'determination': {'percentage': 10, 'motivation': 'positive', 'intensity': 0},
    'resentment': {'percentage': 10, 'motivation': 'negative', 'intensity': 0},
    'glory': {'percentage': 10, 'motivation': 'positive', 'intensity': 0},
    'motivation': {'percentage': 10, 'motivation': 'positive', 'intensity': 0},
    'ideal_state': {'percentage': 100, 'motivation': 'balanced', 'intensity': 0},
    'fear': {'percentage': 10, 'motivation': 'defensive', 'intensity': 0},
    'surprise': {'percentage': 10, 'motivation': 'unexpected', 'intensity': 0},
    'anticipation': {'percentage': 10, 'motivation': 'predictive', 'intensity': 0},
    'trust': {'percentage': 10, 'motivation': 'reliable', 'intensity': 0},
    'disgust': {'percentage': 10, 'motivation': 'repulsive', 'intensity': 0},
    'optimism': {'percentage': 10, 'motivation': 'hopeful', 'intensity': 0},
    'pessimism': {'percentage': 10, 'motivation': 'doubtful', 'intensity': 0},
    'boredom': {'percentage': 10, 'motivation': 'indifferent', 'intensity': 0},
    'envy': {'percentage': 10, 'motivation': 'jealous', 'intensity': 0}
}

total_percentage = 200
default_percentage = total_percentage / len(emotions)
for emotion in emotions:
    emotions[emotion]['percentage'] = default_percentage

emotion_history_file = 'emotion_history.json'

def load_historical_data(file_path=emotion_history_file):
    if os.path.exists(file_path):
        with open(file_path, 'r') as file:
            return json.load(file)
    return []

def save_historical_data(historical_data, file_path=emotion_history_file):
    with open(file_path, 'w') as file:
        json.dump(historical_data, file)

emotion_history = load_historical_data
def update_emotion(emotion, percentage, intensity):
    emotions['ideal_state']['percentage'] -= percentage
    emotions[emotion]['percentage'] += percentage
    emotions[emotion]['intensity'] = intensity

    total_current = sum(e['percentage'] for e in emotions.values())
    adjustment = total_percentage - total_current
    emotions['ideal_state']['percentage'] += adjustment

def normalize_context(context):
    return context.lower().strip()

# Advanced Genetic Algorithm for Emotion Evolution
def evolve_emotions():
    def evaluate(individual):
        ideal_state = individual[-1]
        other_emotions = individual[:-1]
        intensities = individual[-21:-1]
        return (abs(ideal_state - 100), 
                sum(other_emotions), 
                max(intensities) - min(intensities))

    creator.create("FitnessMulti", base.Fitness, weights=(-1.0, -1.0, -1.0))
    creator.create("Individual", list, fitness=creator.FitnessMulti)

    toolbox = base.Toolbox()
    toolbox.register("attr_float", random.uniform, 0, 20)
    toolbox.register("attr_intensity", random.uniform, 0, 10)
    toolbox.register("individual", tools.initCycle, creator.Individual,
                     (toolbox.attr_float,) * (len(emotions) - 1) + 
                     (toolbox.attr_intensity,) * len(emotions) +
                     (lambda: random.uniform(80, 120),),
                     n=1)
    toolbox.register("population", tools.initRepeat, list, toolbox.individual)

    toolbox.register("evaluate", evaluate)
    toolbox.register("mate", tools.cxSimulatedBinaryBounded, low=0, up=120, eta=20.0)
    toolbox.register("mutate", tools.mutPolynomialBounded, low=0, up=120, eta=20.0, indpb=0.1)
    toolbox.register("select", tools.selNSGA2)

    population = toolbox.population(n=100)
    
    algorithms.eaMuPlusLambda(population, toolbox, mu=100, lambda_=100, 
                              cxpb=0.7, mutpb=0.3, ngen=50, verbose=False)

    best_individual = tools.selBest(population, k=1)[0]
    
    for idx, emotion in enumerate(emotions.keys()):
        if idx < len(emotions) - 1:
            emotions[emotion]['percentage'] = best_individual[idx]
            emotions[emotion]['intensity'] = best_individual[idx + len(emotions) - 1]
        else:
            emotions[emotion]['percentage'] = best_individual[-1]

# Initialize the pre-trained language model (BLOOM-1b7)
model_name = 'bigscience/bloom-1b7'
tokenizer = AutoTokenizer.from_pretrained(model_name)
lm_model = AutoModelForCausalLM.from_pretrained(model_name)

def generate_text(prompt, max_length=150):
    input_ids = tokenizer.encode(prompt, return_tensors='pt')
    output = lm_model.generate(
        input_ids, 
        max_length=max_length, 
        num_return_sequences=1, 
        no_repeat_ngram_size=2,
        do_sample=True,
        top_k=50,
        top_p=0.95,
        temperature=0.7
    )
    generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
    return generated_text

sentiment_pipeline = pipeline("sentiment-analysis", model=model_name, tokenizer=tokenizer)

def get_sentiment(text):
    result = sentiment_pipeline(text)[0]
    return f"Sentiment: {result['label']}, Score: {result['score']:.4f}"

def get_emotional_response(context):
    context = normalize_context(context)
    context_encoded = encoder.transform([[context]]).toarray()
    
    # Advanced NN prediction
    nn_output = model(torch.FloatTensor(context_encoded))
    nn_prediction = nn_output.argmax(1).item()
    
    # Ensemble predictions
    rf_prediction = rf_model.predict(context_encoded)[0]
    gb_prediction = gb_model.predict(context_encoded)[0]
    
    # Weighted ensemble
    ensemble_prediction = (0.4 * nn_prediction + 0.3 * rf_prediction + 0.3 * gb_prediction)
    predicted_emotion = emotion_classes[int(round(ensemble_prediction))]

    # Anomaly detection
    anomaly_score = isolation_forest.decision_function(np.array([[nn_prediction]]))
    is_anomaly = anomaly_score < 0

    # Calculate emotion intensity based on model confidence
    nn_proba = torch.softmax(nn_output, dim=1).max().item()
    rf_proba = rf_model.predict_proba(context_encoded).max()
    gb_proba = gb_model.predict_proba(context_encoded).max()
    intensity = (nn_proba + rf_proba + gb_proba) / 3 * 10  # Scale to 0-10

    update_emotion(predicted_emotion, 20, intensity)
    evolve_emotions()

    emotion_history.append(emotions.copy())
    save_historical_data(emotion_history)

    response = f"Predicted Emotion: {predicted_emotion}\n"
    response += f"Emotion Details: {emotions[predicted_emotion]}\n"
    response += f"Anomaly Detected: {'Yes' if is_anomaly else 'No'}\n"
    response += f"Emotion Intensity: {intensity:.2f}/10\n"
    response += f"Current Emotional State: {json.dumps(emotions, indent=2)}"

    return response

def process_input(input_text):
    emotional_response = get_emotional_response(input_text)
    sentiment = get_sentiment(input_text)
    generated_text = generate_text(f"Based on the emotion analysis: {emotional_response}\nGenerate a response: {input_text}")
    
    return f"{emotional_response}\n\nSentiment Analysis: {sentiment}\n\nGenerated Response: {generated_text}"

# Gradio Interface
iface = gr.Interface(
    fn=process_input,
    inputs="text",
    outputs="text",
    title="Advanced Emotion Analysis and Text Generation with BLOOM-1b7",
    description="Enter a sentence for comprehensive emotion analysis, sentiment analysis, and context-aware text generation using advanced AI models."
)

if __name__ == "__main__":
    iface.launch()