{
"cells": [
{
"cell_type": "markdown",
"id": "f0ce57f4-5984-43e6-b3bb-60f2d9251d75",
"metadata": {},
"source": [
"# Implementation of Chatbot using Natural Language Processing(NLP)"
]
},
{
"cell_type": "markdown",
"id": "3c062c6e-0773-4af8-bcb9-aa33f7afeb25",
"metadata": {},
"source": [
"### Importing necessary libraries"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "23417a10-2691-4887-b02e-2448f6200cd1",
"metadata": {},
"outputs": [],
"source": [
"import nltk\n",
"import random\n",
"import os\n",
"import ssl\n",
"import streamlit as st\n",
"from sklearn.svm import SVC\n",
"from sklearn.feature_extraction.text import TfidfVectorizer\n",
"from sklearn.linear_model import LogisticRegression"
]
},
{
"cell_type": "markdown",
"id": "1dc3d789-6567-4266-bd33-005aed1d4e93",
"metadata": {},
"source": [
"### Bypass SSL verification for NLTK downloads"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "298e3201-b127-4c68-b041-2a22ace29340",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"[nltk_data] Downloading package punkt to\n",
"[nltk_data] C:\\Users\\LENOVO\\AppData\\Roaming\\nltk_data...\n",
"[nltk_data] Package punkt is already up-to-date!\n"
]
},
{
"data": {
"text/plain": [
"True"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"ssl._create_default_https_context = ssl._create_unverified_context\n",
"nltk.data.path.append(os.path.abspath('nltk_data'))\n",
"nltk.download('punkt')"
]
},
{
"cell_type": "markdown",
"id": "62d1be3d-37b1-4ab3-a527-9185e183ac98",
"metadata": {},
"source": [
"### Intent dataset"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "a4c238c5-fe25-4802-9328-70ec7b064044",
"metadata": {},
"outputs": [],
"source": [
"intents = [\n",
" {\n",
" \"atag\": \"greeting\", \"patterns\": [\"Hi\", \"Hello\", \"Hey\", \"What's up\", \"How are you\"],\n",
" \"responses\": [\"Hi there!\", \"Hello!\", \"Hey!\", \"Nothing much.\", \"I'm fine, thank you.\"]\n",
" },\n",
" {\n",
" \"tag\": \"goodbye\", \"patterns\": [\"Bye\", \"See you later\", \"Goodbye\", \"Take care\"],\n",
" \"responses\": [\"Goodbye!\", \"See you later!\", \"Take care!\"]\n",
" },\n",
" {\n",
" \"tag\": \"thanks\", \"patterns\": [\"Thank you\", \"Thanks\", \"Thanks a lot\", \"I appreciate it\"],\n",
" \"responses\": [\"You're welcome!\", \"No problem!\", \"Glad I could help!\"]\n",
" },\n",
" {\n",
" \"tag\": \"about\", \"patterns\": [\"What can you do\", \"Who are you\", \"What are you\", \"What is your purpose\"],\n",
" \"responses\": [\"I am a chatbot.\", \"My purpose is to assist you.\", \"I can answer questions and provide assistance.\"]\n",
" },\n",
" {\n",
" \"tag\": \"help\", \"patterns\": [\"Help\", \"I need help\", \"Can you help me\", \"What should I do\"],\n",
" \"responses\": [\"Sure, what do you need help with?\", \"I'm here to help. What's the problem?\", \"How can I assist you?\"]\n",
" },\n",
" {\n",
" \"tag\": \"age\", \"patterns\": [\"How old are you\", \"What's your age\"],\n",
" \"responses\": [\"I don't have an age. I'm a chatbot.\", \"I was just born in the digital world.\", \"Age is just a number for me.\"]\n",
" },\n",
" {\n",
" \"tag\": \"weather\", \"patterns\": [\"What's the weather like\", \"How's the weather today\"],\n",
" \"responses\": [\"I'm sorry, I cannot provide real-time weather information.\", \"You can check the weather on a weather app or website.\"]\n",
" },\n",
" {\n",
" \"tag\": \"budget\", \"patterns\": [\"How can I make a budget\", \"What's a good budgeting strategy\", \"How do I create a budget\"],\n",
" \"responses\": [\"Start by tracking your income and expenses. Allocate money for essentials, savings, and discretionary spending.\",\n",
" \"A good strategy is the 50/30/20 rule: 50% for needs, 30% for wants, and 20% for savings and debt.\",\n",
" \"Set financial goals, monitor expenses, and adjust your budget as needed.\"]\n",
" },\n",
" {\n",
" \"tag\": \"credit_score\", \"patterns\": [\"What is a credit score\", \"How do I check my credit score\", \"How can I improve my credit score\"],\n",
" \"responses\": [\"A credit score reflects your creditworthiness and is used by lenders to assess loans.\",\n",
" \"Check your credit score on platforms like Credit Karma or Credit Sesame.\",\n",
" \"Improve your credit score by paying bills on time, reducing debt, and maintaining good credit utilization.\"]\n",
" },\n",
" {\n",
" \"tag\": \"food\", \"patterns\": [\"What should I eat\", \"Suggest me some food\", \"I am hungry\"],\n",
" \"responses\": [\"You could try a healthy salad, a sandwich, or some pasta!\", \"How about some homemade pizza?\", \"A nice bowl of soup and bread would be great!\"]\n",
" },\n",
" {\n",
" \"tag\": \"exercise\", \"patterns\": [\"What exercises should I do\", \"How to stay fit\", \"Suggest a workout\"],\n",
" \"responses\": [\"Try a mix of cardio and strength training!\", \"A daily walk and some stretching would help.\", \"Yoga is great for both mind and body!\"]\n",
" },\n",
" {\n",
" \"tag\": \"movies\", \"patterns\": [\"Suggest me a movie\", \"What are some good movies\", \"I want to watch a film\"],\n",
" \"responses\": [\"How about an action thriller?\", \"A comedy might lift your mood!\", \"Sci-fi movies are always exciting!\"]\n",
" },\n",
" {\n",
" \"tag\": \"music\", \"patterns\": [\"Suggest me some music\", \"What should I listen to\", \"Recommend a song\"],\n",
" \"responses\": [\"Try some relaxing jazz or lo-fi music!\", \"Pop songs are always fun!\", \"How about some classic rock?\"]\n",
" }\n",
"]"
]
},
{
"cell_type": "markdown",
"id": "3ece2689-d741-48ea-9659-be9cf20e3033",
"metadata": {},
"source": [
"### Create the vectorizer and classifier"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "18d6ccb9-639c-4053-981a-69e2fa7cccca",
"metadata": {},
"outputs": [],
"source": [
"vectorizer = TfidfVectorizer()\n",
"clf = SVC(kernel='linear', random_state=0)\n",
"#clf = LogisticRegression(random_state=0, max_iter=10000)"
]
},
{
"cell_type": "markdown",
"id": "09e70e89-e826-432a-9c22-b4097b5ac07f",
"metadata": {},
"source": [
"### Preprocess the data"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "aca02fbf-201b-47a6-b46c-ca9e0d4e9334",
"metadata": {},
"outputs": [],
"source": [
"tags = []\n",
"patterns = []\n",
"for intent in intents:\n",
" for pattern in intent['patterns']:\n",
" tags.append(intent['tag'])\n",
" patterns.append(pattern)"
]
},
{
"cell_type": "markdown",
"id": "e33f4599-2a6b-4b9b-805a-7875b1840eb4",
"metadata": {},
"source": [
"### Training the model"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "6d11f50c-7062-46e3-89d2-f6e252e5cf12",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"
SVC(kernel='linear', random_state=0)
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.