File size: 12,308 Bytes
5ecde30 |
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 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"#!pip install pandas\n",
"import pandas as pd"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"# Load the CSV file into a pandas DataFrame\n",
"df = pd.read_csv(filepath_or_buffer=r'C:\\Users\\serban.tica\\Documents\\tobi_llm_intent_recognition\\data\\Pager_Intents.csv', \n",
" usecols=[0, 1], names=['utterance', 'intent'])\n",
"\n",
"# Remove the special character \" from the 'utterance' column\n",
"df['utterance'] = df['utterance'].str.replace('\"', '')"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>utterance</th>\n",
" <th>intent</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>utterance</td>\n",
" <td>intent</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Pot sa i scriu specialistului de cont</td>\n",
" <td>account.Specialist</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>Contact specialist de cont</td>\n",
" <td>account.Specialist</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>Ce numar de telefon are specialistul de cont</td>\n",
" <td>account.Specialist</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>Ce numar de telefon are specialistul de cont</td>\n",
" <td>account.Specialist</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" utterance intent\n",
"0 utterance intent\n",
"1 Pot sa i scriu specialistului de cont account.Specialist\n",
"2 Contact specialist de cont account.Specialist\n",
"3 Ce numar de telefon are specialistul de cont account.Specialist\n",
"4 Ce numar de telefon are specialistul de cont account.Specialist"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.head()"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"intent\n",
"offer.Request 1084\n",
"tshooting 1065\n",
"reziliere 829\n",
"activate.Service 664\n",
"info.req.MyPlan 560\n",
"switch.To.Agent 413\n",
"invoice.Explanation 318\n",
"invoice.PC 298\n",
"offer.Request.Existing 278\n",
"deactivate.Service 264\n",
"info.Dez.Roaming 244\n",
"invoice.Details 241\n",
"info.req.Service 239\n",
"info.req.Cost.Control 230\n",
"info.faq.Contact 228\n",
"info.faq.Download.DOC 186\n",
"invoice.Payment 182\n",
"info.reziliere 180\n",
"info.faq.IMEI.PUK 178\n",
"offer.Request.Tarife 167\n",
"info.faq.Roaming.Status 146\n",
"offer.Request.Port.In 145\n",
"info.faq.Order 136\n",
"info.faq.Price.Up 129\n",
"byebye 117\n",
"info.faq.Recharge 114\n",
"invoice.PA 113\n",
"info.faq.Revolut 107\n",
"info.faq.VFClub 105\n",
"info.faq.Deblocare 102\n",
"info.faq.MVA.Asociere.Servicii 88\n",
"info.faq.Schimbare.SIM 75\n",
"welcome 74\n",
"info.faq.CashBack 74\n",
"activate.Service.Electronic.Bill 73\n",
"engleza 72\n",
"info.faq.VTV.login 67\n",
"info.faq.Settings 64\n",
"info.faq.Speedtest 64\n",
"info.req.Gratie 55\n",
"info.faq.MVA.istoric.apeluri 54\n",
"UPC_pay_in_advance 53\n",
"info.faq.Own.MSISDN 53\n",
"info.faq.Telefon.furat 50\n",
"info.faq.DueDate 50\n",
"info.faq.Gamification 49\n",
"UPC_account_no 48\n",
"info.faq.Account.Creation 48\n",
"info.faq.Credit.Transfer 48\n",
"offer.Request.Port.Out 47\n",
"offer.Request.Portare 47\n",
"info.faq.MVA.Credentiale 45\n",
"info.faq.HBOMax 44\n",
"info.faq.Cont.Bancar 41\n",
"info.faq.Reclamatie 41\n",
"info.faq.Job.Vodafone 40\n",
"info.faq.ID.TV 40\n",
"info.faq.TeslaLucky 38\n",
"UPC_personal_data 38\n",
"info.faq.Lista.Canale 37\n",
"info.faq.Service.Warranty 37\n",
"info.faq.WIFI.Connect 36\n",
"info.faq.Tombola 36\n",
"info.faq.Swap 36\n",
"account.Specialist 35\n",
"info.faq.Spam 35\n",
"info.faq.PIN.TV 34\n",
"info.faq.TikTok 33\n",
"UPC_no_bill 33\n",
"info.faq.PreOrder 33\n",
"info.faq.Port.Forwarding 33\n",
"UPC_suspend 33\n",
"info.faq.WIFI.Booster 32\n",
"info.faq.5G 32\n",
"info.faq.Reincarcare.Gresita 32\n",
"invoice.DueDate.Update 32\n",
"info.faq.Sincronizare.Telecomanda 32\n",
"info.faq.Acte.Necesare 32\n",
"info.faq.Service.Insurance 32\n",
"info.faq.Campanii 32\n",
"info.faq.Configurare.Modem 32\n",
"info.faq.Acoperire.roaming 31\n",
"info.faq.Adresa.Magazine 31\n",
"info.faq.Port.Cancel 31\n",
"info.faq.FUP 31\n",
"info.faq.EECCT 31\n",
"info.faq.Curs.Valutar 31\n",
"UPC_modify_services 30\n",
"Welcome2Tobi 30\n",
"info.faq.WIFI.Password 30\n",
"info.faq.Netflix 30\n",
"info.faq.WIFI.Disable 30\n",
"info.faq.Software.Update 30\n",
"info.faq.Service.Not.Warranty 30\n",
"info.faq.Port.Usage 30\n",
"info.faq.Port.Duration 30\n",
"info.faq.Cable.Connection 30\n",
"info.faq.CAW 30\n",
"info.faq.Evalueaza.Experienta 29\n",
"info.faq.MVA.Dwld 29\n",
"info.faq.Ordine.Consum.Beneficii 29\n",
"info.faq.Nr.WhatsApp 28\n",
"info.faq.Aviz.Tehnic 28\n",
"info.faq.Auto.Reincarcare 26\n",
"rejection 25\n",
"info.faq.WIFI.Discover 24\n",
"confirmation 23\n",
"chitchat.CeFaci 22\n",
"chitchat.Weather 21\n",
"TestJourney 2\n",
"intent 1\n",
"Name: count, dtype: int64\n"
]
}
],
"source": [
"# Set max rows to None to display all rows\n",
"pd.set_option('display.max_rows', None)\n",
"\n",
"# Print the count of unique 'intent', and the count of each 'intent'\n",
"print(df['intent'].value_counts()) # show all the unique values and their counts\n",
"\n",
"# Set the default max rows to 10\n",
"pd.set_option('display.max_rows', 20)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"ename": "ModuleNotFoundError",
"evalue": "No module named 'matplotlib'",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mModuleNotFoundError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[1;32mIn[5], line 1\u001b[0m\n\u001b[1;32m----> 1\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mmatplotlib\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpyplot\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m \u001b[38;5;21;01mplt\u001b[39;00m\n\u001b[0;32m 3\u001b[0m \u001b[38;5;66;03m# Get the count of each unique 'intent'\u001b[39;00m\n\u001b[0;32m 4\u001b[0m intent_counts \u001b[38;5;241m=\u001b[39m df[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mintent\u001b[39m\u001b[38;5;124m'\u001b[39m]\u001b[38;5;241m.\u001b[39mvalue_counts()\n",
"\u001b[1;31mModuleNotFoundError\u001b[0m: No module named 'matplotlib'"
]
}
],
"source": [
"import matplotlib.pyplot as plt\n",
"\n",
"# Get the count of each unique 'intent'\n",
"intent_counts = df['intent'].value_counts()\n",
"\n",
"def plot_intent_counts(intent_counts):\n",
" # Calculate the average and median count\n",
" average_count = intent_counts.mean()\n",
" median_count = intent_counts.median()\n",
"\n",
" # Create a bar plot\n",
" plt.figure(figsize=(10, 6))\n",
" intent_counts.plot(kind='bar')\n",
" plt.title('Count of each Intent')\n",
" plt.xlabel('Intent')\n",
" plt.ylabel('Count')\n",
"\n",
" # Add a horizontal line for the average count\n",
" plt.axhline(y=average_count, color='r', linestyle='--', label=f'Average count: {average_count:.2f}')\n",
" # Add a horizontal line for the median count\n",
" plt.axhline(y=median_count, color='g', linestyle='--', label=f'Median count: {median_count:.2f}')\n",
" plt.legend()\n",
"\n",
" plt.show()\n",
"\n",
"plot_intent_counts(intent_counts)"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "env",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.8"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|