app.py

import streamlit as st
import nltk
import pickle
import numpy as np
from tensorflow.keras.models import load_model
from nltk.stem import WordNetLemmatizer

# Load the pre-trained model and other data
model = load_model("chatbot_model.h5")
words = pickle.load(open('words.pkl', 'rb'))
classes = pickle.load(open('classes.pkl', 'rb'))
lemmatizer = WordNetLemmatizer()

# Function to preprocess user input
def clean_up_sentence(sentence):
    sentence_words = nltk.word_tokenize(sentence)
    sentence_words = [lemmatizer.lemmatize(word.lower()) for word in sentence_words]
    return sentence_words

# Function to convert input to bag-of-words format
def bow(sentence, words, show_details=True):
    sentence_words = clean_up_sentence(sentence)
    bag = [0]*len(words)
    for s in sentence_words:
        for i, w in enumerate(words):
            if w == s:
                bag[i] = 1
                if show_details:
                    print(f"found in bag: {w}")
    return np.array(bag)

# Streamlit app
def main():
    st.title("Healthcare Chatbot")
    st.write("Welcome to the Healthcare Chatbot! Enter your symptoms below.")

    user_input = st.text_input("You:")
    if st.button("Predict"):
        if user_input.strip() == "":
            st.write("Bot: Please enter your symptoms.")
        else:
            p = bow(user_input, words)
            res = model.predict(np.array([p]))[0]
            ERROR_THRESHOLD = 0.25
            results = [[i, r] for i, r in enumerate(res) if r > ERROR_THRESHOLD]
            results.sort(key=lambda x: x[1], reverse=True)
            for r in results:
                return_class = classes[r[0]]
                break

            st.write("Bot: Based on your symptoms, you might have:", return_class)

if __name__ == "__main__":
    main()