app.py

import streamlit as st
import numpy as np
from tensorflow.keras.models import load_model
from huggingface_hub import hf_hub_download
from nltk.corpus import stopwords
from nltk.stem import WordNetLemmatizer
import gensim
import nltk
import os

# Download necessary NLTK resources
nltk.download('stopwords')
nltk.download('wordnet')

# Load stop words and lemmatizer
stop_words = set(stopwords.words('english'))
lemmatizer = WordNetLemmatizer()

# Function to preprocess input text
def preprocess_text(input_text, word2vec_model):
    input_text = input_text.lower()
    tokens = input_text.split()
    tokens = [token for token in tokens if token not in stop_words]
    tokens = [lemmatizer.lemmatize(token, pos='v') for token in tokens]
    embeddings = []

    for token in tokens:
        if token in word2vec_model.wv:
            embeddings.append(word2vec_model.wv[token])
        else:
            embeddings.append(np.zeros(word2vec_model.vector_size))

    max_timesteps = 100
    if len(embeddings) > max_timesteps:
        embeddings = embeddings[:max_timesteps]
    else:
        padding = [np.zeros(word2vec_model.vector_size)] * (max_timesteps - len(embeddings))
        embeddings.extend(padding)

    input_features = np.array(embeddings).reshape((1, max_timesteps, word2vec_model.vector_size))
    return input_features

# Load Word2Vec model
def load_word2vec_model():
    repo_id = 'Preethamreddy799/NLP_MODEL'
    filename = 'word2vec_model.bin'
    word2vec_path = hf_hub_download(repo_id=repo_id, filename=filename)
    return gensim.models.Word2Vec.load(word2vec_path)

# Load LSTM model
def load_model_test_steps():
    repo_id = 'Preethamreddy799/NLP_MODEL'
    filename = 'model_test_steps.h5'
    cached_model_path = hf_hub_download(repo_id=repo_id, filename=filename)
    model = load_model(cached_model_path, compile=False)
    print(f"Model loaded successfully from {cached_model_path}")
    return model

# Initialize models
word2vec_model = load_word2vec_model()
lstm_model = load_model_test_steps()

# Streamlit App
st.title("Test Case Steps Generator")
st.write("This app generates test steps based on Test Case Acceptance Criteria.")

acceptance_criteria = st.text_area("Enter Test Case Acceptance Criteria")

if st.button("Generate Test Steps"):
    if acceptance_criteria:
        input_features = preprocess_text(acceptance_criteria, word2vec_model)
        print("Original Shape:", input_features.shape)  # Debugging

         # Adjust input for the model's requirements
        input_features = input_features[:, :1, :]  # Retain only the first timestep
        print("Adjusted Shape:", input_features.shape)  # Debugging

        try:
            predicted_steps = lstm_model.predict(input_features)
            st.subheader("Generated Test Steps")
            st.write(predicted_steps)
        except Exception as e:
            st.error(f"Error generating predictions: {e}")