Spaces:
Sleeping
Sleeping
File size: 14,923 Bytes
6bc5fb7 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 |
{
"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": [
"<style>#sk-container-id-1 {color: black;}#sk-container-id-1 pre{padding: 0;}#sk-container-id-1 div.sk-toggleable {background-color: white;}#sk-container-id-1 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-1 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-1 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-1 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-1 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-1 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-1 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-1 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-1 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-1 div.sk-item {position: relative;z-index: 1;}#sk-container-id-1 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-1 div.sk-item::before, #sk-container-id-1 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-1 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-1 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-1 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-1 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-1 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-1 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-1 div.sk-label-container {text-align: center;}#sk-container-id-1 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-1 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>SVC(kernel='linear', random_state=0)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SVC</label><div class=\"sk-toggleable__content\"><pre>SVC(kernel='linear', random_state=0)</pre></div></div></div></div></div>"
],
"text/plain": [
"SVC(kernel='linear', random_state=0)"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"x = vectorizer.fit_transform(patterns)\n",
"y = tags\n",
"clf.fit(x, y)"
]
},
{
"cell_type": "markdown",
"id": "a75b5c8f-cc42-4afc-b261-bfdbe6c79913",
"metadata": {},
"source": [
"### Python function to chat with the chatbot"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "12ac8a47-eac5-440f-ab0e-93686944b34b",
"metadata": {},
"outputs": [],
"source": [
"def chatbot(input_text):\n",
" input_text = vectorizer.transform([input_text])\n",
" tag = clf.predict(input_text)[0]\n",
" for intent in intents:\n",
" if intent['tag'] == tag:\n",
" response = random.choice(intent['responses'])\n",
" return response"
]
},
{
"cell_type": "markdown",
"id": "cf1ff963-ebbe-4fac-af82-26d3e3336c33",
"metadata": {},
"source": [
"### Checking our chatbot"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "8f469e8a-c8a0-4683-9be0-0aefa67c8cea",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Hey!\n"
]
}
],
"source": [
"user_input = \"Hello\"\n",
"response = chatbot(user_input)\n",
"print(response)"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "f49306db-d7da-4e79-860e-cd6e2985ca58",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Try a mix of cardio and strength training!\n"
]
}
],
"source": [
"user_input = \"What exercises should I do\"\n",
"response = chatbot(user_input)\n",
"print(response)"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "GPU(sam)",
"language": "python",
"name": "sam"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.8.20"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|