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
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import OneHotEncoder
from sklearn.neural_network import MLPClassifier
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, IterableDataset
import multiprocessing as mp
from joblib import Parallel, delayed
import gc

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 (memory-efficient)
encoder = OneHotEncoder(handle_unknown='ignore', sparse=True)
contexts_encoded = encoder.fit_transform(df[['context']])

# Encoding emotions
emotions_target = pd.Categorical(df['emotion']).codes
emotion_classes = pd.Categorical(df['emotion']).categories

# Memory-efficient Neural Network with PyTorch
class MemoryEfficientNN(nn.Module):
    def __init__(self, input_size, hidden_size, num_classes):
        super(MemoryEfficientNN, self).__init__()
        self.layers = nn.Sequential(
            nn.Linear(input_size, hidden_size),
            nn.ReLU(),
            nn.Dropout(0.2),
            nn.Linear(hidden_size, hidden_size),
            nn.ReLU(),
            nn.Dropout(0.2),
            nn.Linear(hidden_size, num_classes)
        )
        
    def forward(self, x):
        return self.layers(x)

# Memory-efficient dataset
class MemoryEfficientDataset(IterableDataset):
    def __init__(self, X, y, batch_size):
        self.X = X
        self.y = y
        self.batch_size = batch_size

    def __iter__(self):
        for i in range(0, len(self.y), self.batch_size):
            X_batch = self.X[i:i+self.batch_size].toarray()
            y_batch = self.y[i:i+self.batch_size]
            yield torch.FloatTensor(X_batch), torch.LongTensor(y_batch)

# Train Memory-Efficient Neural Network
X_train, X_test, y_train, y_test = train_test_split(contexts_encoded, emotions_target, test_size=0.2, random_state=42)
input_size = X_train.shape[1]
hidden_size = 64
num_classes = len(emotion_classes)

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = MemoryEfficientNN(input_size, hidden_size, num_classes).to(device)
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.001)

train_dataset = MemoryEfficientDataset(X_train, y_train, batch_size=32)
train_loader = DataLoader(train_dataset, batch_size=None)

num_epochs = 100
for epoch in range(num_epochs):
    for batch_X, batch_y in train_loader:
        batch_X, batch_y = batch_X.to(device), batch_y.to(device)
        outputs = model(batch_X)
        loss = criterion(outputs, batch_y)
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
    gc.collect()  # Garbage collection after each epoch

# Ensemble with Random Forest (memory-efficient)
rf_model = RandomForestClassifier(n_estimators=50, random_state=42, n_jobs=-1)
rf_model.fit(X_train, y_train)

# Isolation Forest Anomaly Detection Model (memory-efficient)
isolation_forest = IsolationForest(contamination=0.1, random_state=42, n_jobs=-1, max_samples='auto')
isolation_forest.fit(X_train)  # Fit the model before using it

# 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()

# Memory-efficient 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=50)
    
    for gen in range(25):
        offspring = algorithms.varAnd(population, toolbox, cxpb=0.7, mutpb=0.3)
        fits = toolbox.map(toolbox.evaluate, offspring)
        for fit, ind in zip(fits, offspring):
            ind.fitness.values = fit
        population = toolbox.select(offspring + population, k=len(population))
        
    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]

# Lazy loading for the language model
def get_language_model():
    model_name = 'bigscience/bloom-1b7'
    tokenizer = AutoTokenizer.from_pretrained(model_name)
    lm_model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", low_cpu_mem_usage=True)
    return tokenizer, lm_model

def generate_text(prompt, max_length=100):
    tokenizer, lm_model = get_language_model()
    input_ids = tokenizer.encode(prompt, return_tensors='pt').to(lm_model.device)
    with torch.no_grad():
        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='distilbert-base-uncased-finetuned-sst-2-english', device_map="auto")

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]])
    
    # Neural network prediction
    with torch.no_grad():
        nn_output = model(torch.FloatTensor(context_encoded.toarray()).to(device))
        nn_prediction = nn_output.argmax(1).item()
    
    # Random Forest prediction
    rf_prediction = rf_model.predict(context_encoded)[0]
    
    # Weighted ensemble
    ensemble_prediction = (0.6 * nn_prediction + 0.4 * rf_prediction)
    predicted_emotion = emotion_classes[int(ensemble_prediction)]
    
    # Isolation Forest anomaly detection
    anomaly_score = isolation_forest.decision_function(context_encoded.toarray())
    is_anomaly = isolation_forest.predict(context_encoded.toarray())[0] == -1
    
    if is_anomaly:
        return "Anomaly detected in the emotional response."
    
    return f"Predicted Emotion: {predicted_emotion}"

# Gradio interface
def process_input(input_text):
    emotional_response = get_emotional_response(input_text)
    sentiment_response = get_sentiment(input_text)
    generated_text = generate_text(input_text)
    return {
        "Emotional Response": emotional_response,
        "Sentiment Response": sentiment_response,
        "Generated Text": generated_text
    }

iface = gr.Interface(
    fn=process_input,
    inputs="text",
    outputs=[
        gr.outputs.Textbox(label="Emotional Response"),
        gr.outputs.Textbox(label="Sentiment Response"),
        gr.outputs.Textbox(label="Generated Text")
    ],
    title="Emotion and Sentiment Analysis",
    description="Analyze emotions and sentiments from text input."
)

iface.launch()