Upload 9 files

README.md

@@ -1,14 +1,13 @@
 ---
-title: Review Analyzer
-emoji: 🚀
-colorFrom: yellow
-colorTo: green
+title: Chatbot Review
+emoji: 🔥
+colorFrom: indigo
+colorTo: blue
 sdk: streamlit
-sdk_version: 1.42.1
+sdk_version: 1.42.0
 app_file: app.py
 pinned: false
-license: mit
-short_description: A streamlit application for taking review and analysis.
+short_description: A chatbot for taking review
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

abc.md

@@ -0,0 +1,87 @@
+# 🤖 **Chatbot Review**
+
+## 📖 **Overview**
+
+Chatbot Review is a **Streamlit**-based application designed to provide product reviews and inquiries. Utilizing **Natural Language Processing (NLP)**, this app allows users to ask questions about products, submit reviews, and analyze customer sentiments. Built with **Python**, it integrates various libraries for efficient data handling and interactive visualizations.
+
+## 🚀 **Features**
+
+- 📝 **Product Review**: Collect and display customer reviews for each product.
+- 💲 **Price Inquiry**: Find pricing details for different products.
+- ✍️ **Submit Review**: Share your own reviews and ratings.
+- 💬 **Review Analysis**: Analyze customer feedback to determine the overall product performance with graphical representation.
+
+## 🗂️ **Project Structure**
+
+```plaintext
+Chatbot-Review/
+│
+├── app.py             # Main app file to run the Streamlit application
+├── chat.py            # File handling the chatbot interactions and user queries
+├── chat_model.pth     # Pre-trained model for chatbot's response generation
+├── requirements.txt   # Lists dependencies required to run the app
+├── product_intents.json  # Contains predefined intents and responses for handling queries
+├── reviews_data.json  # Stores customer-submitted reviews and ratings
+│
+├── utils/
+│   └── analytics.py   # Contains functions for product data handling and analytics
+│
+├── images/            # Folder containing product images for display
+│   ├── camera.jpg     # Product image of camera
+│   ├── console.jpg    # Product image of gaming console
+│   ├── earbuds.jpg    # Product image of earbuds
+│   ├── laptop.jpg     # Product image of laptop
+│   ├── smartphone.jpg # Product image of smartphone
+│   ├── smartwatch.jpg # Product image of smartwatch
+│   └── tablet.jpg     # Product image of tablet
+│
+├── pages/             # Contains individual Streamlit pages for different app views
+│   ├── admin_dashboard.py  # Page for admin dashboard to view reviews and data
+│   ├── chatbot_page.py     # Page with the chatbot interface for product queries
+│   ├── product_catalog.py  # Page displaying the list of available products
+│   └── submit_review.py    # Page for submitting new reviews
+│
+├── train.py           # Script to train model on a custom dataset for review analysis
+└── README.md          # Project documentation
+```
+
+## ⚙️ **Setup Instructions**
+
+1. **Clone the Repository**:
+   ```bash
+   git clone <repository-url>
+   cd chatbot-review
+   ```
+2. **Install Dependencies**:  
+   Ensure **Python** is installed and run:
+   ```bash
+   pip install -r requirements.txt
+   ```
+3. **Run the Application**:  
+   Start the Streamlit app by executing:
+   ```bash
+   streamlit run app.py
+   ```
+
+## 🖥️ **Usage**
+
+Launch the app and interact with the chatbot to inquire about products, submit reviews, and more. The app will guide you through various options based on your queries.
+
+## 🔧 **Configuration**
+
+The app's configuration can be adjusted through the `README.md` file, which includes the Streamlit SDK version and other settings.
+
+## 📊 **Data Handling**
+
+- Reviews are stored in **reviews_data.json** and processed using **Pandas** for analytics.
+- Product details are managed within the **ReviewAnalytics** class in **utils/analytics.py**.
+
+## 💡 **Future Enhancements**
+
+- Integrate more advanced NLP models for more accurate responses.
+- Expand the product catalog and review database.
+- Improve UI/UX for a more intuitive user experience.
+
+## 📝 **License**
+
+This project is licensed under the **MIT License**.

app.py

@@ -0,0 +1,108 @@
+
+#                             ███████╗     ██████╗     ██╗  ██╗     █████╗     ██╗    ██╗
+#                             ██╔════╝    ██╔═══██╗    ██║  ██║    ██╔══██╗    ██║    ██║
+#   █████╗█████╗█████╗█████╗    ███████╗    ██║   ██║    ███████║    ███████║    ██║    ██║         █████╗█████╗█████╗█████╗
+#   ╚════╝╚════╝╚════╝╚════╝    ╚════██║    ██║   ██║    ██╔══██║    ██╔══██║    ██║    ██║         ╚════╝╚════╝╚════╝╚════╝
+#                             ███████║    ╚██████╔╝    ██║  ██║    ██║  ██║    ██║    ███████╗
+#                             ╚══════╝     ╚═════╝     ╚═╝  ╚═╝    ╚═╝  ╚═╝    ╚═╝    ╚══════╝
+
+# *******************************************************
+#   Created with 💓 by - 𝐒𝐨𝐡𝐚𝐢𝐥 𝐒𝐡𝐚𝐢𝐤𝐡 | 😁 
+# *******************************************************
+
+# -------------------------------------------------------
+# ✨ Support the Code 💻:
+#   ☕ Buy Me A Coffee: https://buymeacoffee.com/sohails07
+# -------------------------------------------------------
+
+# 📱 LET'S CONNECT 🌐:
+#   🚀 **Best way to contact**: 
+#     📲 Telegram: https://t.me/sohails_07
+
+#   🌍 **Other Platforms**:
+#     📸 Instagram: 
+#       - Personal: https://www.instagram.com/sohails_07/
+# -------------------------------------------------------
+
+# 🔥 **For Any Questions or Concerns**:
+# Feel free to reach out to us! Whether it's about coding or life, we're here to help you grow. Let's chat!
+
+# -------------------------------------------------------
+# 🔔 **Stay Tuned**:
+# Don't miss out on more exciting content! Hit the Follow button on our Github page:
+#     👉 Github: https://github.com/Sohail-Shaikh-07/
+# -------------------------------------------------------
+
+# ⚡ **Pro Tip**:
+# For the best experience, stick with the default library versions shown. 
+# We’ve got you covered for the smoothest coding ride! 🚀
+# -------------------------------------------------------
+
+
+
+# *************************************************************   『I』『M』『P』『O』『R』『T』『S』  *************************************************************
+
+import streamlit as st
+from utils.analytics import ReviewAnalytics
+from pages.product_catalog import show_product_catalog
+from pages.submit_review import show_submit_review
+from pages.chatbot_page import show_chatbot
+from pages.admin_dashboard import show_admin_dashboard
+
+
+# *************************************************************  『M』『A』『I』『N』  *************************************************************
+
+def main():
+    st.set_page_config(
+        page_title="Product Review ChatBot",
+        layout="wide",
+        initial_sidebar_state="expanded",
+    )
+
+    # Initialize systems
+    analytics = ReviewAnalytics()
+
+    # Initialize session state for page if not exists
+    if "current_page" not in st.session_state:
+        st.session_state.current_page = "Products Catalog"
+
+    # Hide all default elements and the text navigation --- because it is visible on app and looks unpleasant
+    st.markdown(
+        """
+        <style>
+        #MainMenu {visibility: hidden;}
+        footer {visibility: hidden;}
+        header {visibility: hidden;}
+        div[data-testid="stSidebarNav"] {display: none;}
+        </style>
+    """,
+        unsafe_allow_html=True,
+    )
+
+    # Only show the selectbox for navigation on app
+    page = st.sidebar.selectbox(
+        "Choose a page",
+        ["Products Catalog", "Submit Review", "ChatBot", "Admin Dashboard"],
+        index=["Products Catalog", "Submit Review", "ChatBot", "Admin Dashboard"].index(
+            st.session_state.current_page
+        ),
+    )
+
+    # Update current page in session state when changed
+    if page != st.session_state.current_page:
+        st.session_state.current_page = page
+        st.rerun()
+
+    # Route to appropriate page
+    if st.session_state.current_page == "Products Catalog":
+        show_product_catalog(analytics)
+    elif st.session_state.current_page == "Submit Review":
+        show_submit_review(analytics)
+    elif st.session_state.current_page == "ChatBot":
+        show_chatbot()
+    else:  # Admin Dashboard
+        show_admin_dashboard(analytics)
+
+
+if __name__ == "__main__":
+    main()

chat.py

@@ -0,0 +1,223 @@
+
+#                             ███████╗     ██████╗     ██╗  ██╗     █████╗     ██╗    ██╗
+#                             ██╔════╝    ██╔═══██╗    ██║  ██║    ██╔══██╗    ██║    ██║
+#   █████╗█████╗█████╗█████╗    ███████╗    ██║   ██║    ███████║    ███████║    ██║    ██║         █████╗█████╗█████╗█████╗
+#   ╚════╝╚════╝╚════╝╚════╝    ╚════██║    ██║   ██║    ██╔══██║    ██╔══██║    ██║    ██║         ╚════╝╚════╝╚════╝╚════╝
+#                             ███████║    ╚██████╔╝    ██║  ██║    ██║  ██║    ██║    ███████╗
+#                             ╚══════╝     ╚═════╝     ╚═╝  ╚═╝    ╚═╝  ╚═╝    ╚═╝    ╚══════╝
+
+# *******************************************************
+#   Created with 💓 by - 𝐒𝐨𝐡𝐚𝐢𝐥 𝐒𝐡𝐚𝐢𝐤𝐡 | 😁 
+# *******************************************************
+
+# -------------------------------------------------------
+# ✨ Support the Code 💻:
+#   ☕ Buy Me A Coffee: https://buymeacoffee.com/sohails07
+# -------------------------------------------------------
+
+# 📱 LET'S CONNECT 🌐:
+#   🚀 **Best way to contact**: 
+#     📲 Telegram: https://t.me/sohails_07
+
+#   🌍 **Other Platforms**:
+#     📸 Instagram: 
+#       - Personal: https://www.instagram.com/sohails_07/
+# -------------------------------------------------------
+
+# 🔥 **For Any Questions or Concerns**:
+# Feel free to reach out to us! Whether it's about coding or life, we're here to help you grow. Let's chat!
+
+# -------------------------------------------------------
+# 🔔 **Stay Tuned**:
+# Don't miss out on more exciting content! Hit the Follow button on our Github page:
+#     👉 Github: https://github.com/Sohail-Shaikh-07/
+# -------------------------------------------------------
+
+# ⚡ **Pro Tip**:
+# For the best experience, stick with the default library versions shown. 
+# We’ve got you covered for the smoothest coding ride! 🚀
+# -------------------------------------------------------
+
+
+
+# *************************************************************   『I』『M』『P』『O』『R』『T』『S』  *************************************************************
+
+import random
+import json
+import torch
+import numpy as np
+import string
+
+# *************************************************************   『C』『L』『A』『S』『S』  *************************************************************
+
+class ChatBot:
+    def __init__(
+        self,
+        model_path="chatbot_model.pth",
+        intents_path="product_intents.json",
+        confidence_threshold=0.75,
+    ):
+        self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+        self.confidence_threshold = confidence_threshold
+
+        try:
+            # loading the intents file where the chatbot data is stored in json format
+            with open(intents_path, "r", encoding="utf-8") as f:
+                self.intents = json.load(f)
+
+            # Load trained model
+            data = torch.load(model_path, map_location=self.device)
+            self.input_size = data["input_size"]
+            self.hidden_size = data["hidden_size"]
+            self.output_size = data["output_size"]
+            self.all_words = data["all_words"]
+            self.tags = data["tags"]
+
+            # Initialize model
+            self.model = NeuralNet(
+                self.input_size, self.hidden_size, self.output_size
+            ).to(self.device)
+            self.model.load_state_dict(data["model_state"])
+            self.model.eval()
+
+            print("ChatBot initialized successfully!")
+
+        except FileNotFoundError as e:
+            print(f"Error: Could not find {e.filename}")
+            raise
+        except json.JSONDecodeError:
+            print("Error: Invalid JSON format in intents file")
+            raise
+        except Exception as e:
+            print(f"Error initializing chatbot: {str(e)}")
+            raise
+
+    def clean_text(self, text):
+        """Clean and tokenize text"""
+        return text.lower().split()
+
+    def stem(self, word):
+        """Simple stemming function"""
+
+        suffixes = ["ing", "ly", "ed", "es", "s", "er", "est", "y"]
+        for suffix in suffixes:
+            if word.endswith(suffix):
+                return word[: -len(suffix)]
+        return word
+
+    def bag_of_words(self, tokenized_sentence):
+        """Convert sentence into bag of words"""
+
+        sentence_words = [self.stem(word) for word in tokenized_sentence]
+
+        bag = np.zeros(len(self.all_words), dtype=np.float32)
+
+        for idx, w in enumerate(self.all_words):
+            if w in sentence_words:
+                bag[idx] = 1
+        return bag
+
+    def get_response(self, sentence):
+        try:
+
+            sentence_tokens = self.clean_text(sentence)
+
+            if not sentence_tokens:
+                return "Please say something!", 0.0
+
+            X = self.bag_of_words(sentence_tokens)
+            X = X.reshape(1, X.shape[0])
+            X = torch.from_numpy(X).to(self.device)
+
+            output = self.model(X)
+            _, predicted = torch.max(output, dim=1)
+
+            probs = torch.softmax(output, dim=1)
+            prob = probs[0][predicted.item()]
+
+            if prob.item() > self.confidence_threshold:
+                tag = self.tags[predicted.item()]
+
+                for intent in self.intents["intents"]:
+                    if intent["tag"] == tag:
+                        responses = intent["responses"]
+                        return random.choice(responses), prob.item()
+
+            return (
+                "I'm not quite sure about that. Could you rephrase or ask something else?",    # Bot will display message if something is unrelevant
+                prob.item(),
+            )
+
+        except Exception as e:
+            print(f"Error generating response: {str(e)}")
+            return "I'm having trouble processing that right now.", 0.0
+
+
+class NeuralNet(torch.nn.Module):
+    def __init__(self, input_size, hidden_size, num_classes):
+        super(NeuralNet, self).__init__()
+        self.l1 = torch.nn.Linear(input_size, hidden_size)
+        self.l2 = torch.nn.Linear(hidden_size, hidden_size)
+        self.l3 = torch.nn.Linear(hidden_size, num_classes)
+        self.relu = torch.nn.ReLU()
+
+    def forward(self, x):
+        out = self.l1(x)
+        out = self.relu(out)
+        out = self.l2(out)
+        out = self.relu(out)
+        out = self.l3(out)
+        return out
+
+
+# *************************************************************   『M』『A』『I』『N』  *************************************************************
+
+def main():
+    print("\n=== ChatBot System ===")
+    print("Commands:")
+    print("- 'quit' or 'exit': Close the program")
+    print("- 'restart': Start a new conversation")
+    print("=" * 50)
+
+    while True:
+        # Initialize chatbot
+        print("\nInitializing ChatBot...")
+        try:
+            chatbot = ChatBot()
+            print("\nChatBot is ready! (Type 'restart' to reset, 'quit' to exit)")
+            print("-" * 50)
+
+            # Inner loop for conversation
+            while True:
+                user_input = input("You: ").strip()
+
+                if user_input.lower() in ["quit", "exit"]:
+                    print("ChatBot: Goodbye! Have a great day!")
+                    return  # Exit the program
+
+                if user_input.lower() == "restart":
+                    print("\nRestarting conversation...")
+                    break
+
+                if not user_input:
+                    print("ChatBot: Please say something!")
+                    continue
+
+                response, confidence = chatbot.get_response(user_input)
+                print(f"ChatBot: {response}")
+                if confidence > 0:
+                    print(f"Confidence: {confidence:.2%}")
+                print("-" * 50)
+
+        except KeyboardInterrupt:
+            print("\nChatBot: Goodbye! Have a great day!")
+            return
+        except Exception as e:
+            print(f"An error occurred: {str(e)}")
+            user_input = input("Would you like to restart? (yes/no): ").strip().lower()
+            if user_input != "yes":
+                return
+
+
+if __name__ == "__main__":
+    main()

chatbot_model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbb81f062654abfd983eeb3d24000aec714f3370b94211304c8fc12e495791e4
+size 5508

product_intents.json

@@ -0,0 +1,109 @@
+{
+  "intents": [
+    {
+      "tag": "product_inquiry",
+      "patterns": [
+        "Tell me about your products",
+        "What products do you offer",
+        "What can I buy here",
+        "Show me your products",
+        "What do you sell"
+      ],
+      "responses": [
+        "We offer a wide range of products. What specific category are you interested in?",
+        "Our product catalog includes various items. Is there something specific you're looking for?",
+        "I'd be happy to tell you about our products. What type of product interests you?"
+      ]
+    },
+    {
+      "tag": "product_review",
+      "patterns": [
+        "How good is this product",
+        "What do people say about this",
+        "Is this product worth buying",
+        "Reviews for this product",
+        "Customer feedback"
+      ],
+      "responses": [
+        "Based on customer reviews, this product has received positive feedback for its quality and value.",
+        "Our customers have generally been satisfied with this product. Would you like to see specific reviews?",
+        "This product has been well-received by our customers. Let me share some highlights from recent reviews."
+      ]
+    },
+    {
+      "tag": "price_inquiry",
+      "patterns": [
+        "How much does it cost",
+        "What's the price",
+        "Is it expensive",
+        "Price range",
+        "Cost of product"
+      ],
+      "responses": [
+        "I can help you with pricing information. Could you specify which product you're interested in?",
+        "Prices vary depending on the specific product and model. Which item would you like to know about?",
+        "Let me check the current price for you. Which product are you looking at?"
+      ]
+    },
+    {
+      "tag": "comparison",
+      "patterns": [
+        "Compare products",
+        "Which is better",
+        "Difference between products",
+        "Compare features",
+        "Product comparison"
+      ],
+      "responses": [
+        "I can help you compare products. Which items would you like to compare?",
+        "Let me help you understand the differences between our products. Which ones are you considering?",
+        "I'll be happy to compare features for you. Which products would you like to know more about?"
+      ]
+    },
+    {
+      "tag": "availability",
+      "patterns": [
+        "Is it in stock",
+        "When will it be available",
+        "Do you have this product",
+        "Check stock",
+        "Available now"
+      ],
+      "responses": [
+        "I can check the current availability for you. Which product are you interested in?",
+        "Let me verify the stock status. Could you specify the product?",
+        "I'll help you check if the item is in stock. Which product would you like to know about?"
+      ]
+    },
+    {
+      "tag": "submit_review",
+      "patterns": [
+        "I want to write a review",
+        "How do I submit a review",
+        "Can I review this product",
+        "Leave feedback",
+        "Rate this product"
+      ],
+      "responses": [
+        "I'll help you submit a review. Please rate the product from 1-5 stars and share your experience.",
+        "You can submit a review by rating the product and describing your experience. Would you like to proceed?",
+        "To submit a review, please tell me which product you'd like to review and share your experience."
+      ]
+    },
+    {
+      "tag": "sentiment_analysis",
+      "patterns": [
+        "What do people think about this product",
+        "Is this product good or bad",
+        "Overall sentiment",
+        "Product satisfaction",
+        "Customer satisfaction"
+      ],
+      "responses": [
+        "Based on our sentiment analysis, this product has received mostly positive feedback.",
+        "Let me analyze the reviews for you. The overall sentiment for this product is positive.",
+        "I can tell you that customers generally rate this product favorably."
+      ]
+    }
+  ]
+}

requirements.txt

@@ -0,0 +1,6 @@
+streamlit==1.31.1
+pandas==2.2.0
+plotly==5.18.0
+torch==2.2.0
+numpy==1.26.3
+

reviews_data.json

@@ -0,0 +1,44 @@
+[
+    {
+        "product": "Smart Watch",
+        "rating": 4,
+        "review": "nice",
+        "timestamp": "2025-02-17T14:15:39.313956"
+    },
+    {
+        "product": "Wireless Earbuds",
+        "rating": 5,
+        "review": "Nice build quality",
+        "timestamp": "2025-02-17T14:18:47.944078"
+    },
+    {
+        "product": "Gaming Console",
+        "rating": 5,
+        "review": "Processing power is superb",
+        "timestamp": "2025-02-17T14:19:00.395747"
+    },
+    {
+        "product": "Gaming Console",
+        "rating": 5,
+        "review": "Processing power is superb",
+        "timestamp": "2025-02-17T14:19:07.256996"
+    },
+    {
+        "product": "Gaming Console",
+        "rating": 1,
+        "review": "too bad.. lagging",
+        "timestamp": "2025-02-17T14:34:51.456843"
+    },
+    {
+        "product": "Tablet Ultra",
+        "rating": 4,
+        "review": "nice",
+        "timestamp": "2025-02-17T14:50:55.533737"
+    },
+    {
+        "product": "Gaming Console",
+        "rating": 5,
+        "review": "Superb Amazing Console",
+        "timestamp": "2025-02-18T18:01:56.433664"
+    }
+]

train.py

@@ -0,0 +1,242 @@
+
+#                             ███████╗     ██████╗     ██╗  ██╗     █████╗     ██╗    ██╗
+#                             ██╔════╝    ██╔═══██╗    ██║  ██║    ██╔══██╗    ██║    ██║
+#   █████╗█████╗█████╗█████╗    ███████╗    ██║   ██║    ███████║    ███████║    ██║    ██║         █████╗█████╗█████╗█████╗
+#   ╚════╝╚════╝╚════╝╚════╝    ╚════██║    ██║   ██║    ██╔══██║    ██╔══██║    ██║    ██║         ╚════╝╚════╝╚════╝╚════╝
+#                             ███████║    ╚██████╔╝    ██║  ██║    ██║  ██║    ██║    ███████╗
+#                             ╚══════╝     ╚═════╝     ╚═╝  ╚═╝    ╚═╝  ╚═╝    ╚═╝    ╚══════╝
+
+# *******************************************************
+#   Created with 💓 by - 𝐒𝐨𝐡𝐚𝐢𝐥 𝐒𝐡𝐚𝐢𝐤𝐡 | 😁 
+# *******************************************************
+
+# -------------------------------------------------------
+# ✨ Support the Code 💻:
+#   ☕ Buy Me A Coffee: https://buymeacoffee.com/sohails07
+# -------------------------------------------------------
+
+# 📱 LET'S CONNECT 🌐:
+#   🚀 **Best way to contact**: 
+#     📲 Telegram: https://t.me/sohails_07
+
+#   🌍 **Other Platforms**:
+#     📸 Instagram: 
+#       - Personal: https://www.instagram.com/sohails_07/
+# -------------------------------------------------------
+
+# 🔥 **For Any Questions or Concerns**:
+# Feel free to reach out to us! Whether it's about coding or life, we're here to help you grow. Let's chat!
+
+# -------------------------------------------------------
+# 🔔 **Stay Tuned**:
+# Don't miss out on more exciting content! Hit the Follow button on our Github page:
+#     👉 Github: https://github.com/Sohail-Shaikh-07/
+# -------------------------------------------------------
+
+# ⚡ **Pro Tip**:
+# For the best experience, stick with the default library versions shown. 
+# We’ve got you covered for the smoothest coding ride! 🚀
+# -------------------------------------------------------
+
+
+
+# *************************************************************   『I』『M』『P』『O』『R』『T』『S』  *************************************************************
+
+import torch
+import torch.nn as nn
+import numpy as np
+import json
+import nltk
+from nltk.stem.porter import PorterStemmer
+from torch.utils.data import Dataset, DataLoader
+
+# *************************************************************   『C』『L』『A』『S』『S』  *************************************************************
+
+class NeuralNet(nn.Module):
+    def __init__(self, input_size, hidden_size, num_classes):
+        super(NeuralNet, self).__init__()
+        self.l1 = nn.Linear(input_size, hidden_size)
+        self.l2 = nn.Linear(hidden_size, hidden_size)
+        self.l3 = nn.Linear(hidden_size, num_classes)
+        self.relu = nn.ReLU()
+
+    def forward(self, x):
+        out = self.l1(x)
+        out = self.relu(out)
+        out = self.l2(out)
+        out = self.relu(out)
+        out = self.l3(out)
+        return out
+
+
+class ChatDataset(Dataset):
+    def __init__(self, X_train, y_train):
+        self.n_samples = len(X_train)
+        self.x_data = torch.FloatTensor(X_train)
+        self.y_data = torch.LongTensor(y_train)
+
+    def __getitem__(self, index):
+        return self.x_data[index], self.y_data[index]
+
+    def __len__(self):
+        return self.n_samples
+
+
+def tokenize(sentence):
+    """
+    Split sentence into array of words/tokens
+    a token can be a word or punctuation character, or number
+    """
+    return sentence.lower().split()
+
+
+def stem(word):
+    stemmer = PorterStemmer()
+    return stemmer.stem(word.lower())
+
+
+def bag_of_words(tokenized_sentence, words):
+    sentence_words = [stem(word) for word in tokenized_sentence]
+    bag = np.zeros(len(words), dtype=np.float32)
+    for idx, w in enumerate(words):
+        if w in sentence_words:
+            bag[idx] = 1
+    return bag
+
+
+def train_model():
+    try:
+        # Download required NLTK data for model training
+        print("Downloading required NLTK data...")
+        nltk.download('punkt')
+        nltk.download('averaged_perceptron_tagger')
+        nltk.download('wordnet')
+        
+        # Load the intents file
+        print("Loading product_intents.json...")
+        with open("product_intents.json", "r", encoding="utf-8") as f:
+            intents = json.load(f)
+
+        print("Processing training data...")
+        all_words = []
+        tags = []
+        xy = []
+
+        # Validate intents structure
+        if not isinstance(intents, dict) or "intents" not in intents:
+            raise ValueError(
+                "Invalid intents.json format. Root should be a dictionary with 'intents' key."
+            )
+
+        # Process each intent
+        for intent in intents["intents"]:
+            # Skip if intent is missing required fields
+            if not isinstance(intent, dict):
+                continue
+            if "tag" not in intent or "patterns" not in intent:
+                continue
+
+            tag = intent["tag"]
+            tags.append(tag)
+
+            for pattern in intent["patterns"]:
+                w = tokenize(pattern)
+                all_words.extend(w)
+                xy.append((w, tag))
+
+        # Stem and lower each word
+        print("Processing words...")
+        ignore_words = ["?", ".", "!", ","]
+        all_words = [stem(w) for w in all_words if w not in ignore_words]
+        all_words = sorted(set(all_words))
+        tags = sorted(set(tags))
+
+        print(f"Number of patterns: {len(xy)}")
+        print(f"Number of tags: {len(tags)}")
+        print(f"Number of unique stemmed words: {len(all_words)}")
+
+        # Create training data
+        X_train = []
+        y_train = []
+
+        for pattern_sentence, tag in xy:
+            bag = bag_of_words(pattern_sentence, all_words)
+            X_train.append(bag)
+            label = tags.index(tag)
+            y_train.append(label)
+
+        # Convert to numpy arrays
+        X_train = np.array(X_train)
+        y_train = np.array(y_train)
+
+        # Hyperparameters
+        num_epochs = 100      # You can increase epochs --  An epoch refers to one complete pass through the training data, where the model adjusts its parameters to minimize loss.
+        batch_size = 8
+        learning_rate = 0.001
+        input_size = len(X_train[0])
+        hidden_size = 8
+        output_size = len(tags)
+
+        print(
+            f"Training with: input_size={input_size}, hidden_size={hidden_size}, output_size={output_size}"
+        )
+
+        # Create dataset
+        dataset = ChatDataset(X_train, y_train)
+        train_loader = DataLoader(dataset=dataset, batch_size=batch_size, shuffle=True)
+
+        device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+        model = NeuralNet(input_size, hidden_size, output_size).to(device)
+
+        # Loss and optimizer
+        criterion = nn.CrossEntropyLoss()
+        optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
+
+        # Training loop
+        print("Starting training...")
+        for epoch in range(num_epochs):
+            for words, labels in train_loader:
+                words = words.to(device)
+                labels = labels.to(device)
+
+                # Forward pass
+                outputs = model(words)
+                loss = criterion(outputs, labels)
+
+                # Backward and optimize
+                optimizer.zero_grad()
+                loss.backward()
+                optimizer.step()
+
+            if (epoch + 1) % 100 == 0:
+                print(f"Epoch [{epoch+1}/{num_epochs}], Loss: {loss.item():.4f}")
+
+        print(f"Final loss: {loss.item():.4f}")
+
+        # Save the model and data
+        data = {
+            "model_state": model.state_dict(),
+            "input_size": input_size,
+            "hidden_size": hidden_size,
+            "output_size": output_size,
+            "all_words": all_words,
+            "tags": tags,
+        }
+
+        torch.save(data, "chatbot_model.pth")
+        print(f"Training complete. Model saved to chatbot_model.pth")
+
+        return model, all_words, tags
+
+    except Exception as e:
+        print(f"An error occurred during training: {str(e)}")
+        import traceback
+
+        traceback.print_exc()
+        return None, None, None
+
+
+# *************************************************************   『M』『A』『I』『N』  *************************************************************
+
+if __name__ == "__main__":
+    train_model()