Spaces:
Sleeping
Sleeping
Delete BBC_NEWS_PREDICTION.ipynb
Browse files- BBC_NEWS_PREDICTION.ipynb +0 -845
BBC_NEWS_PREDICTION.ipynb
DELETED
|
@@ -1,845 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"cells": [
|
| 3 |
-
{
|
| 4 |
-
"cell_type": "code",
|
| 5 |
-
"execution_count": 60,
|
| 6 |
-
"metadata": {},
|
| 7 |
-
"outputs": [],
|
| 8 |
-
"source": [
|
| 9 |
-
"import pandas as pd\n",
|
| 10 |
-
"import numpy as np"
|
| 11 |
-
]
|
| 12 |
-
},
|
| 13 |
-
{
|
| 14 |
-
"cell_type": "code",
|
| 15 |
-
"execution_count": 61,
|
| 16 |
-
"metadata": {},
|
| 17 |
-
"outputs": [],
|
| 18 |
-
"source": [
|
| 19 |
-
"df=pd.read_csv(\"C:\\\\Users\\\\saipr\\\\Downloads\\\\bbc_data.csv\\\\bbc_data.csv\")"
|
| 20 |
-
]
|
| 21 |
-
},
|
| 22 |
-
{
|
| 23 |
-
"cell_type": "code",
|
| 24 |
-
"execution_count": 62,
|
| 25 |
-
"metadata": {},
|
| 26 |
-
"outputs": [
|
| 27 |
-
{
|
| 28 |
-
"data": {
|
| 29 |
-
"text/html": [
|
| 30 |
-
"<div>\n",
|
| 31 |
-
"<style scoped>\n",
|
| 32 |
-
" .dataframe tbody tr th:only-of-type {\n",
|
| 33 |
-
" vertical-align: middle;\n",
|
| 34 |
-
" }\n",
|
| 35 |
-
"\n",
|
| 36 |
-
" .dataframe tbody tr th {\n",
|
| 37 |
-
" vertical-align: top;\n",
|
| 38 |
-
" }\n",
|
| 39 |
-
"\n",
|
| 40 |
-
" .dataframe thead th {\n",
|
| 41 |
-
" text-align: right;\n",
|
| 42 |
-
" }\n",
|
| 43 |
-
"</style>\n",
|
| 44 |
-
"<table border=\"1\" class=\"dataframe\">\n",
|
| 45 |
-
" <thead>\n",
|
| 46 |
-
" <tr style=\"text-align: right;\">\n",
|
| 47 |
-
" <th></th>\n",
|
| 48 |
-
" <th>data</th>\n",
|
| 49 |
-
" <th>labels</th>\n",
|
| 50 |
-
" </tr>\n",
|
| 51 |
-
" </thead>\n",
|
| 52 |
-
" <tbody>\n",
|
| 53 |
-
" <tr>\n",
|
| 54 |
-
" <th>0</th>\n",
|
| 55 |
-
" <td>Musicians to tackle US red tape Musicians gro...</td>\n",
|
| 56 |
-
" <td>entertainment</td>\n",
|
| 57 |
-
" </tr>\n",
|
| 58 |
-
" <tr>\n",
|
| 59 |
-
" <th>1</th>\n",
|
| 60 |
-
" <td>U2s desire to be number one U2, who have won ...</td>\n",
|
| 61 |
-
" <td>entertainment</td>\n",
|
| 62 |
-
" </tr>\n",
|
| 63 |
-
" <tr>\n",
|
| 64 |
-
" <th>2</th>\n",
|
| 65 |
-
" <td>Rocker Doherty in on-stage fight Rock singer ...</td>\n",
|
| 66 |
-
" <td>entertainment</td>\n",
|
| 67 |
-
" </tr>\n",
|
| 68 |
-
" <tr>\n",
|
| 69 |
-
" <th>3</th>\n",
|
| 70 |
-
" <td>Snicket tops US box office chart The film ada...</td>\n",
|
| 71 |
-
" <td>entertainment</td>\n",
|
| 72 |
-
" </tr>\n",
|
| 73 |
-
" <tr>\n",
|
| 74 |
-
" <th>4</th>\n",
|
| 75 |
-
" <td>Oceans Twelve raids box office Oceans Twelve,...</td>\n",
|
| 76 |
-
" <td>entertainment</td>\n",
|
| 77 |
-
" </tr>\n",
|
| 78 |
-
" <tr>\n",
|
| 79 |
-
" <th>...</th>\n",
|
| 80 |
-
" <td>...</td>\n",
|
| 81 |
-
" <td>...</td>\n",
|
| 82 |
-
" </tr>\n",
|
| 83 |
-
" <tr>\n",
|
| 84 |
-
" <th>2220</th>\n",
|
| 85 |
-
" <td>Warning over Windows Word files Writing a Mic...</td>\n",
|
| 86 |
-
" <td>tech</td>\n",
|
| 87 |
-
" </tr>\n",
|
| 88 |
-
" <tr>\n",
|
| 89 |
-
" <th>2221</th>\n",
|
| 90 |
-
" <td>Fast lifts rise into record books Two high-sp...</td>\n",
|
| 91 |
-
" <td>tech</td>\n",
|
| 92 |
-
" </tr>\n",
|
| 93 |
-
" <tr>\n",
|
| 94 |
-
" <th>2222</th>\n",
|
| 95 |
-
" <td>Nintendo adds media playing to DS Nintendo is...</td>\n",
|
| 96 |
-
" <td>tech</td>\n",
|
| 97 |
-
" </tr>\n",
|
| 98 |
-
" <tr>\n",
|
| 99 |
-
" <th>2223</th>\n",
|
| 100 |
-
" <td>Fast moving phone viruses appear Security fir...</td>\n",
|
| 101 |
-
" <td>tech</td>\n",
|
| 102 |
-
" </tr>\n",
|
| 103 |
-
" <tr>\n",
|
| 104 |
-
" <th>2224</th>\n",
|
| 105 |
-
" <td>Hacker threat to Apples iTunes Users of Apple...</td>\n",
|
| 106 |
-
" <td>tech</td>\n",
|
| 107 |
-
" </tr>\n",
|
| 108 |
-
" </tbody>\n",
|
| 109 |
-
"</table>\n",
|
| 110 |
-
"<p>2225 rows × 2 columns</p>\n",
|
| 111 |
-
"</div>"
|
| 112 |
-
],
|
| 113 |
-
"text/plain": [
|
| 114 |
-
" data labels\n",
|
| 115 |
-
"0 Musicians to tackle US red tape Musicians gro... entertainment\n",
|
| 116 |
-
"1 U2s desire to be number one U2, who have won ... entertainment\n",
|
| 117 |
-
"2 Rocker Doherty in on-stage fight Rock singer ... entertainment\n",
|
| 118 |
-
"3 Snicket tops US box office chart The film ada... entertainment\n",
|
| 119 |
-
"4 Oceans Twelve raids box office Oceans Twelve,... entertainment\n",
|
| 120 |
-
"... ... ...\n",
|
| 121 |
-
"2220 Warning over Windows Word files Writing a Mic... tech\n",
|
| 122 |
-
"2221 Fast lifts rise into record books Two high-sp... tech\n",
|
| 123 |
-
"2222 Nintendo adds media playing to DS Nintendo is... tech\n",
|
| 124 |
-
"2223 Fast moving phone viruses appear Security fir... tech\n",
|
| 125 |
-
"2224 Hacker threat to Apples iTunes Users of Apple... tech\n",
|
| 126 |
-
"\n",
|
| 127 |
-
"[2225 rows x 2 columns]"
|
| 128 |
-
]
|
| 129 |
-
},
|
| 130 |
-
"execution_count": 62,
|
| 131 |
-
"metadata": {},
|
| 132 |
-
"output_type": "execute_result"
|
| 133 |
-
}
|
| 134 |
-
],
|
| 135 |
-
"source": [
|
| 136 |
-
"df"
|
| 137 |
-
]
|
| 138 |
-
},
|
| 139 |
-
{
|
| 140 |
-
"cell_type": "code",
|
| 141 |
-
"execution_count": 63,
|
| 142 |
-
"metadata": {},
|
| 143 |
-
"outputs": [
|
| 144 |
-
{
|
| 145 |
-
"data": {
|
| 146 |
-
"text/plain": [
|
| 147 |
-
"labels\n",
|
| 148 |
-
"sport 511\n",
|
| 149 |
-
"business 510\n",
|
| 150 |
-
"politics 417\n",
|
| 151 |
-
"tech 401\n",
|
| 152 |
-
"entertainment 386\n",
|
| 153 |
-
"Name: count, dtype: int64"
|
| 154 |
-
]
|
| 155 |
-
},
|
| 156 |
-
"execution_count": 63,
|
| 157 |
-
"metadata": {},
|
| 158 |
-
"output_type": "execute_result"
|
| 159 |
-
}
|
| 160 |
-
],
|
| 161 |
-
"source": [
|
| 162 |
-
"df['labels'].value_counts()"
|
| 163 |
-
]
|
| 164 |
-
},
|
| 165 |
-
{
|
| 166 |
-
"cell_type": "code",
|
| 167 |
-
"execution_count": 64,
|
| 168 |
-
"metadata": {},
|
| 169 |
-
"outputs": [
|
| 170 |
-
{
|
| 171 |
-
"data": {
|
| 172 |
-
"text/plain": [
|
| 173 |
-
"data 0\n",
|
| 174 |
-
"labels 0\n",
|
| 175 |
-
"dtype: int64"
|
| 176 |
-
]
|
| 177 |
-
},
|
| 178 |
-
"execution_count": 64,
|
| 179 |
-
"metadata": {},
|
| 180 |
-
"output_type": "execute_result"
|
| 181 |
-
}
|
| 182 |
-
],
|
| 183 |
-
"source": [
|
| 184 |
-
"df.isnull().sum()"
|
| 185 |
-
]
|
| 186 |
-
},
|
| 187 |
-
{
|
| 188 |
-
"cell_type": "code",
|
| 189 |
-
"execution_count": 65,
|
| 190 |
-
"metadata": {},
|
| 191 |
-
"outputs": [],
|
| 192 |
-
"source": [
|
| 193 |
-
"# Split the data into features and target\n",
|
| 194 |
-
"X = df['data']\n",
|
| 195 |
-
"y = df['labels']\n"
|
| 196 |
-
]
|
| 197 |
-
},
|
| 198 |
-
{
|
| 199 |
-
"cell_type": "code",
|
| 200 |
-
"execution_count": 66,
|
| 201 |
-
"metadata": {},
|
| 202 |
-
"outputs": [
|
| 203 |
-
{
|
| 204 |
-
"name": "stderr",
|
| 205 |
-
"output_type": "stream",
|
| 206 |
-
"text": [
|
| 207 |
-
"[nltk_data] Downloading package stopwords to\n",
|
| 208 |
-
"[nltk_data] C:\\Users\\saipr\\AppData\\Roaming\\nltk_data...\n",
|
| 209 |
-
"[nltk_data] Package stopwords is already up-to-date!\n",
|
| 210 |
-
"[nltk_data] Downloading package punkt to\n",
|
| 211 |
-
"[nltk_data] C:\\Users\\saipr\\AppData\\Roaming\\nltk_data...\n",
|
| 212 |
-
"[nltk_data] Package punkt is already up-to-date!\n"
|
| 213 |
-
]
|
| 214 |
-
}
|
| 215 |
-
],
|
| 216 |
-
"source": [
|
| 217 |
-
"import re\n",
|
| 218 |
-
"from nltk.tokenize import word_tokenize\n",
|
| 219 |
-
"from nltk.corpus import stopwords\n",
|
| 220 |
-
"\n",
|
| 221 |
-
"# Ensure required NLTK data is available\n",
|
| 222 |
-
"import nltk\n",
|
| 223 |
-
"nltk.download('stopwords')\n",
|
| 224 |
-
"nltk.download('punkt')\n",
|
| 225 |
-
"\n",
|
| 226 |
-
"# Load stopwords only once\n",
|
| 227 |
-
"stop_words = set(stopwords.words('english'))\n"
|
| 228 |
-
]
|
| 229 |
-
},
|
| 230 |
-
{
|
| 231 |
-
"cell_type": "code",
|
| 232 |
-
"execution_count": 67,
|
| 233 |
-
"metadata": {},
|
| 234 |
-
"outputs": [],
|
| 235 |
-
"source": [
|
| 236 |
-
"\n",
|
| 237 |
-
"def preprocess_text(text):\n",
|
| 238 |
-
" # Remove punctuation and convert to lower case\n",
|
| 239 |
-
" text = re.sub(r'[^\\w\\s]', '', text.lower())\n",
|
| 240 |
-
" # Tokenize\n",
|
| 241 |
-
" tokens = word_tokenize(text)\n",
|
| 242 |
-
" # Remove stopwords\n",
|
| 243 |
-
" tokens = [word for word in tokens if word not in stop_words]\n",
|
| 244 |
-
" return ' '.join(tokens)\n",
|
| 245 |
-
"\n",
|
| 246 |
-
"# Apply preprocessing to the dataframe\n",
|
| 247 |
-
"df['processed_data'] = df['data'].apply(preprocess_text)\n"
|
| 248 |
-
]
|
| 249 |
-
},
|
| 250 |
-
{
|
| 251 |
-
"cell_type": "code",
|
| 252 |
-
"execution_count": 68,
|
| 253 |
-
"metadata": {},
|
| 254 |
-
"outputs": [],
|
| 255 |
-
"source": [
|
| 256 |
-
"from sklearn.model_selection import train_test_split # Import the function\n",
|
| 257 |
-
"\n",
|
| 258 |
-
"# Split the data into training and testing sets\n",
|
| 259 |
-
"X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n"
|
| 260 |
-
]
|
| 261 |
-
},
|
| 262 |
-
{
|
| 263 |
-
"cell_type": "code",
|
| 264 |
-
"execution_count": 69,
|
| 265 |
-
"metadata": {},
|
| 266 |
-
"outputs": [],
|
| 267 |
-
"source": [
|
| 268 |
-
"from sklearn.feature_extraction.text import TfidfVectorizer # Import TfidfVectorizer\n",
|
| 269 |
-
"\n",
|
| 270 |
-
"# Convert text data to numerical data using TF-IDF\n",
|
| 271 |
-
"vectorizer = TfidfVectorizer(stop_words='english')\n",
|
| 272 |
-
"X_train_tfidf = vectorizer.fit_transform(X_train)\n",
|
| 273 |
-
"X_test_tfidf = vectorizer.transform(X_test)\n"
|
| 274 |
-
]
|
| 275 |
-
},
|
| 276 |
-
{
|
| 277 |
-
"cell_type": "code",
|
| 278 |
-
"execution_count": 70,
|
| 279 |
-
"metadata": {},
|
| 280 |
-
"outputs": [
|
| 281 |
-
{
|
| 282 |
-
"data": {
|
| 283 |
-
"text/html": [
|
| 284 |
-
"<style>#sk-container-id-2 {\n",
|
| 285 |
-
" /* Definition of color scheme common for light and dark mode */\n",
|
| 286 |
-
" --sklearn-color-text: black;\n",
|
| 287 |
-
" --sklearn-color-line: gray;\n",
|
| 288 |
-
" /* Definition of color scheme for unfitted estimators */\n",
|
| 289 |
-
" --sklearn-color-unfitted-level-0: #fff5e6;\n",
|
| 290 |
-
" --sklearn-color-unfitted-level-1: #f6e4d2;\n",
|
| 291 |
-
" --sklearn-color-unfitted-level-2: #ffe0b3;\n",
|
| 292 |
-
" --sklearn-color-unfitted-level-3: chocolate;\n",
|
| 293 |
-
" /* Definition of color scheme for fitted estimators */\n",
|
| 294 |
-
" --sklearn-color-fitted-level-0: #f0f8ff;\n",
|
| 295 |
-
" --sklearn-color-fitted-level-1: #d4ebff;\n",
|
| 296 |
-
" --sklearn-color-fitted-level-2: #b3dbfd;\n",
|
| 297 |
-
" --sklearn-color-fitted-level-3: cornflowerblue;\n",
|
| 298 |
-
"\n",
|
| 299 |
-
" /* Specific color for light theme */\n",
|
| 300 |
-
" --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
|
| 301 |
-
" --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
|
| 302 |
-
" --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
|
| 303 |
-
" --sklearn-color-icon: #696969;\n",
|
| 304 |
-
"\n",
|
| 305 |
-
" @media (prefers-color-scheme: dark) {\n",
|
| 306 |
-
" /* Redefinition of color scheme for dark theme */\n",
|
| 307 |
-
" --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
|
| 308 |
-
" --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
|
| 309 |
-
" --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
|
| 310 |
-
" --sklearn-color-icon: #878787;\n",
|
| 311 |
-
" }\n",
|
| 312 |
-
"}\n",
|
| 313 |
-
"\n",
|
| 314 |
-
"#sk-container-id-2 {\n",
|
| 315 |
-
" color: var(--sklearn-color-text);\n",
|
| 316 |
-
"}\n",
|
| 317 |
-
"\n",
|
| 318 |
-
"#sk-container-id-2 pre {\n",
|
| 319 |
-
" padding: 0;\n",
|
| 320 |
-
"}\n",
|
| 321 |
-
"\n",
|
| 322 |
-
"#sk-container-id-2 input.sk-hidden--visually {\n",
|
| 323 |
-
" border: 0;\n",
|
| 324 |
-
" clip: rect(1px 1px 1px 1px);\n",
|
| 325 |
-
" clip: rect(1px, 1px, 1px, 1px);\n",
|
| 326 |
-
" height: 1px;\n",
|
| 327 |
-
" margin: -1px;\n",
|
| 328 |
-
" overflow: hidden;\n",
|
| 329 |
-
" padding: 0;\n",
|
| 330 |
-
" position: absolute;\n",
|
| 331 |
-
" width: 1px;\n",
|
| 332 |
-
"}\n",
|
| 333 |
-
"\n",
|
| 334 |
-
"#sk-container-id-2 div.sk-dashed-wrapped {\n",
|
| 335 |
-
" border: 1px dashed var(--sklearn-color-line);\n",
|
| 336 |
-
" margin: 0 0.4em 0.5em 0.4em;\n",
|
| 337 |
-
" box-sizing: border-box;\n",
|
| 338 |
-
" padding-bottom: 0.4em;\n",
|
| 339 |
-
" background-color: var(--sklearn-color-background);\n",
|
| 340 |
-
"}\n",
|
| 341 |
-
"\n",
|
| 342 |
-
"#sk-container-id-2 div.sk-container {\n",
|
| 343 |
-
" /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
|
| 344 |
-
" but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
|
| 345 |
-
" so we also need the `!important` here to be able to override the\n",
|
| 346 |
-
" default hidden behavior on the sphinx rendered scikit-learn.org.\n",
|
| 347 |
-
" See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
|
| 348 |
-
" display: inline-block !important;\n",
|
| 349 |
-
" position: relative;\n",
|
| 350 |
-
"}\n",
|
| 351 |
-
"\n",
|
| 352 |
-
"#sk-container-id-2 div.sk-text-repr-fallback {\n",
|
| 353 |
-
" display: none;\n",
|
| 354 |
-
"}\n",
|
| 355 |
-
"\n",
|
| 356 |
-
"div.sk-parallel-item,\n",
|
| 357 |
-
"div.sk-serial,\n",
|
| 358 |
-
"div.sk-item {\n",
|
| 359 |
-
" /* draw centered vertical line to link estimators */\n",
|
| 360 |
-
" background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
|
| 361 |
-
" background-size: 2px 100%;\n",
|
| 362 |
-
" background-repeat: no-repeat;\n",
|
| 363 |
-
" background-position: center center;\n",
|
| 364 |
-
"}\n",
|
| 365 |
-
"\n",
|
| 366 |
-
"/* Parallel-specific style estimator block */\n",
|
| 367 |
-
"\n",
|
| 368 |
-
"#sk-container-id-2 div.sk-parallel-item::after {\n",
|
| 369 |
-
" content: \"\";\n",
|
| 370 |
-
" width: 100%;\n",
|
| 371 |
-
" border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
|
| 372 |
-
" flex-grow: 1;\n",
|
| 373 |
-
"}\n",
|
| 374 |
-
"\n",
|
| 375 |
-
"#sk-container-id-2 div.sk-parallel {\n",
|
| 376 |
-
" display: flex;\n",
|
| 377 |
-
" align-items: stretch;\n",
|
| 378 |
-
" justify-content: center;\n",
|
| 379 |
-
" background-color: var(--sklearn-color-background);\n",
|
| 380 |
-
" position: relative;\n",
|
| 381 |
-
"}\n",
|
| 382 |
-
"\n",
|
| 383 |
-
"#sk-container-id-2 div.sk-parallel-item {\n",
|
| 384 |
-
" display: flex;\n",
|
| 385 |
-
" flex-direction: column;\n",
|
| 386 |
-
"}\n",
|
| 387 |
-
"\n",
|
| 388 |
-
"#sk-container-id-2 div.sk-parallel-item:first-child::after {\n",
|
| 389 |
-
" align-self: flex-end;\n",
|
| 390 |
-
" width: 50%;\n",
|
| 391 |
-
"}\n",
|
| 392 |
-
"\n",
|
| 393 |
-
"#sk-container-id-2 div.sk-parallel-item:last-child::after {\n",
|
| 394 |
-
" align-self: flex-start;\n",
|
| 395 |
-
" width: 50%;\n",
|
| 396 |
-
"}\n",
|
| 397 |
-
"\n",
|
| 398 |
-
"#sk-container-id-2 div.sk-parallel-item:only-child::after {\n",
|
| 399 |
-
" width: 0;\n",
|
| 400 |
-
"}\n",
|
| 401 |
-
"\n",
|
| 402 |
-
"/* Serial-specific style estimator block */\n",
|
| 403 |
-
"\n",
|
| 404 |
-
"#sk-container-id-2 div.sk-serial {\n",
|
| 405 |
-
" display: flex;\n",
|
| 406 |
-
" flex-direction: column;\n",
|
| 407 |
-
" align-items: center;\n",
|
| 408 |
-
" background-color: var(--sklearn-color-background);\n",
|
| 409 |
-
" padding-right: 1em;\n",
|
| 410 |
-
" padding-left: 1em;\n",
|
| 411 |
-
"}\n",
|
| 412 |
-
"\n",
|
| 413 |
-
"\n",
|
| 414 |
-
"/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
|
| 415 |
-
"clickable and can be expanded/collapsed.\n",
|
| 416 |
-
"- Pipeline and ColumnTransformer use this feature and define the default style\n",
|
| 417 |
-
"- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
|
| 418 |
-
"*/\n",
|
| 419 |
-
"\n",
|
| 420 |
-
"/* Pipeline and ColumnTransformer style (default) */\n",
|
| 421 |
-
"\n",
|
| 422 |
-
"#sk-container-id-2 div.sk-toggleable {\n",
|
| 423 |
-
" /* Default theme specific background. It is overwritten whether we have a\n",
|
| 424 |
-
" specific estimator or a Pipeline/ColumnTransformer */\n",
|
| 425 |
-
" background-color: var(--sklearn-color-background);\n",
|
| 426 |
-
"}\n",
|
| 427 |
-
"\n",
|
| 428 |
-
"/* Toggleable label */\n",
|
| 429 |
-
"#sk-container-id-2 label.sk-toggleable__label {\n",
|
| 430 |
-
" cursor: pointer;\n",
|
| 431 |
-
" display: block;\n",
|
| 432 |
-
" width: 100%;\n",
|
| 433 |
-
" margin-bottom: 0;\n",
|
| 434 |
-
" padding: 0.5em;\n",
|
| 435 |
-
" box-sizing: border-box;\n",
|
| 436 |
-
" text-align: center;\n",
|
| 437 |
-
"}\n",
|
| 438 |
-
"\n",
|
| 439 |
-
"#sk-container-id-2 label.sk-toggleable__label-arrow:before {\n",
|
| 440 |
-
" /* Arrow on the left of the label */\n",
|
| 441 |
-
" content: \"▸\";\n",
|
| 442 |
-
" float: left;\n",
|
| 443 |
-
" margin-right: 0.25em;\n",
|
| 444 |
-
" color: var(--sklearn-color-icon);\n",
|
| 445 |
-
"}\n",
|
| 446 |
-
"\n",
|
| 447 |
-
"#sk-container-id-2 label.sk-toggleable__label-arrow:hover:before {\n",
|
| 448 |
-
" color: var(--sklearn-color-text);\n",
|
| 449 |
-
"}\n",
|
| 450 |
-
"\n",
|
| 451 |
-
"/* Toggleable content - dropdown */\n",
|
| 452 |
-
"\n",
|
| 453 |
-
"#sk-container-id-2 div.sk-toggleable__content {\n",
|
| 454 |
-
" max-height: 0;\n",
|
| 455 |
-
" max-width: 0;\n",
|
| 456 |
-
" overflow: hidden;\n",
|
| 457 |
-
" text-align: left;\n",
|
| 458 |
-
" /* unfitted */\n",
|
| 459 |
-
" background-color: var(--sklearn-color-unfitted-level-0);\n",
|
| 460 |
-
"}\n",
|
| 461 |
-
"\n",
|
| 462 |
-
"#sk-container-id-2 div.sk-toggleable__content.fitted {\n",
|
| 463 |
-
" /* fitted */\n",
|
| 464 |
-
" background-color: var(--sklearn-color-fitted-level-0);\n",
|
| 465 |
-
"}\n",
|
| 466 |
-
"\n",
|
| 467 |
-
"#sk-container-id-2 div.sk-toggleable__content pre {\n",
|
| 468 |
-
" margin: 0.2em;\n",
|
| 469 |
-
" border-radius: 0.25em;\n",
|
| 470 |
-
" color: var(--sklearn-color-text);\n",
|
| 471 |
-
" /* unfitted */\n",
|
| 472 |
-
" background-color: var(--sklearn-color-unfitted-level-0);\n",
|
| 473 |
-
"}\n",
|
| 474 |
-
"\n",
|
| 475 |
-
"#sk-container-id-2 div.sk-toggleable__content.fitted pre {\n",
|
| 476 |
-
" /* unfitted */\n",
|
| 477 |
-
" background-color: var(--sklearn-color-fitted-level-0);\n",
|
| 478 |
-
"}\n",
|
| 479 |
-
"\n",
|
| 480 |
-
"#sk-container-id-2 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
|
| 481 |
-
" /* Expand drop-down */\n",
|
| 482 |
-
" max-height: 200px;\n",
|
| 483 |
-
" max-width: 100%;\n",
|
| 484 |
-
" overflow: auto;\n",
|
| 485 |
-
"}\n",
|
| 486 |
-
"\n",
|
| 487 |
-
"#sk-container-id-2 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
|
| 488 |
-
" content: \"▾\";\n",
|
| 489 |
-
"}\n",
|
| 490 |
-
"\n",
|
| 491 |
-
"/* Pipeline/ColumnTransformer-specific style */\n",
|
| 492 |
-
"\n",
|
| 493 |
-
"#sk-container-id-2 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
|
| 494 |
-
" color: var(--sklearn-color-text);\n",
|
| 495 |
-
" background-color: var(--sklearn-color-unfitted-level-2);\n",
|
| 496 |
-
"}\n",
|
| 497 |
-
"\n",
|
| 498 |
-
"#sk-container-id-2 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
|
| 499 |
-
" background-color: var(--sklearn-color-fitted-level-2);\n",
|
| 500 |
-
"}\n",
|
| 501 |
-
"\n",
|
| 502 |
-
"/* Estimator-specific style */\n",
|
| 503 |
-
"\n",
|
| 504 |
-
"/* Colorize estimator box */\n",
|
| 505 |
-
"#sk-container-id-2 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
|
| 506 |
-
" /* unfitted */\n",
|
| 507 |
-
" background-color: var(--sklearn-color-unfitted-level-2);\n",
|
| 508 |
-
"}\n",
|
| 509 |
-
"\n",
|
| 510 |
-
"#sk-container-id-2 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
|
| 511 |
-
" /* fitted */\n",
|
| 512 |
-
" background-color: var(--sklearn-color-fitted-level-2);\n",
|
| 513 |
-
"}\n",
|
| 514 |
-
"\n",
|
| 515 |
-
"#sk-container-id-2 div.sk-label label.sk-toggleable__label,\n",
|
| 516 |
-
"#sk-container-id-2 div.sk-label label {\n",
|
| 517 |
-
" /* The background is the default theme color */\n",
|
| 518 |
-
" color: var(--sklearn-color-text-on-default-background);\n",
|
| 519 |
-
"}\n",
|
| 520 |
-
"\n",
|
| 521 |
-
"/* On hover, darken the color of the background */\n",
|
| 522 |
-
"#sk-container-id-2 div.sk-label:hover label.sk-toggleable__label {\n",
|
| 523 |
-
" color: var(--sklearn-color-text);\n",
|
| 524 |
-
" background-color: var(--sklearn-color-unfitted-level-2);\n",
|
| 525 |
-
"}\n",
|
| 526 |
-
"\n",
|
| 527 |
-
"/* Label box, darken color on hover, fitted */\n",
|
| 528 |
-
"#sk-container-id-2 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
|
| 529 |
-
" color: var(--sklearn-color-text);\n",
|
| 530 |
-
" background-color: var(--sklearn-color-fitted-level-2);\n",
|
| 531 |
-
"}\n",
|
| 532 |
-
"\n",
|
| 533 |
-
"/* Estimator label */\n",
|
| 534 |
-
"\n",
|
| 535 |
-
"#sk-container-id-2 div.sk-label label {\n",
|
| 536 |
-
" font-family: monospace;\n",
|
| 537 |
-
" font-weight: bold;\n",
|
| 538 |
-
" display: inline-block;\n",
|
| 539 |
-
" line-height: 1.2em;\n",
|
| 540 |
-
"}\n",
|
| 541 |
-
"\n",
|
| 542 |
-
"#sk-container-id-2 div.sk-label-container {\n",
|
| 543 |
-
" text-align: center;\n",
|
| 544 |
-
"}\n",
|
| 545 |
-
"\n",
|
| 546 |
-
"/* Estimator-specific */\n",
|
| 547 |
-
"#sk-container-id-2 div.sk-estimator {\n",
|
| 548 |
-
" font-family: monospace;\n",
|
| 549 |
-
" border: 1px dotted var(--sklearn-color-border-box);\n",
|
| 550 |
-
" border-radius: 0.25em;\n",
|
| 551 |
-
" box-sizing: border-box;\n",
|
| 552 |
-
" margin-bottom: 0.5em;\n",
|
| 553 |
-
" /* unfitted */\n",
|
| 554 |
-
" background-color: var(--sklearn-color-unfitted-level-0);\n",
|
| 555 |
-
"}\n",
|
| 556 |
-
"\n",
|
| 557 |
-
"#sk-container-id-2 div.sk-estimator.fitted {\n",
|
| 558 |
-
" /* fitted */\n",
|
| 559 |
-
" background-color: var(--sklearn-color-fitted-level-0);\n",
|
| 560 |
-
"}\n",
|
| 561 |
-
"\n",
|
| 562 |
-
"/* on hover */\n",
|
| 563 |
-
"#sk-container-id-2 div.sk-estimator:hover {\n",
|
| 564 |
-
" /* unfitted */\n",
|
| 565 |
-
" background-color: var(--sklearn-color-unfitted-level-2);\n",
|
| 566 |
-
"}\n",
|
| 567 |
-
"\n",
|
| 568 |
-
"#sk-container-id-2 div.sk-estimator.fitted:hover {\n",
|
| 569 |
-
" /* fitted */\n",
|
| 570 |
-
" background-color: var(--sklearn-color-fitted-level-2);\n",
|
| 571 |
-
"}\n",
|
| 572 |
-
"\n",
|
| 573 |
-
"/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
|
| 574 |
-
"\n",
|
| 575 |
-
"/* Common style for \"i\" and \"?\" */\n",
|
| 576 |
-
"\n",
|
| 577 |
-
".sk-estimator-doc-link,\n",
|
| 578 |
-
"a:link.sk-estimator-doc-link,\n",
|
| 579 |
-
"a:visited.sk-estimator-doc-link {\n",
|
| 580 |
-
" float: right;\n",
|
| 581 |
-
" font-size: smaller;\n",
|
| 582 |
-
" line-height: 1em;\n",
|
| 583 |
-
" font-family: monospace;\n",
|
| 584 |
-
" background-color: var(--sklearn-color-background);\n",
|
| 585 |
-
" border-radius: 1em;\n",
|
| 586 |
-
" height: 1em;\n",
|
| 587 |
-
" width: 1em;\n",
|
| 588 |
-
" text-decoration: none !important;\n",
|
| 589 |
-
" margin-left: 1ex;\n",
|
| 590 |
-
" /* unfitted */\n",
|
| 591 |
-
" border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
|
| 592 |
-
" color: var(--sklearn-color-unfitted-level-1);\n",
|
| 593 |
-
"}\n",
|
| 594 |
-
"\n",
|
| 595 |
-
".sk-estimator-doc-link.fitted,\n",
|
| 596 |
-
"a:link.sk-estimator-doc-link.fitted,\n",
|
| 597 |
-
"a:visited.sk-estimator-doc-link.fitted {\n",
|
| 598 |
-
" /* fitted */\n",
|
| 599 |
-
" border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
|
| 600 |
-
" color: var(--sklearn-color-fitted-level-1);\n",
|
| 601 |
-
"}\n",
|
| 602 |
-
"\n",
|
| 603 |
-
"/* On hover */\n",
|
| 604 |
-
"div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
|
| 605 |
-
".sk-estimator-doc-link:hover,\n",
|
| 606 |
-
"div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
|
| 607 |
-
".sk-estimator-doc-link:hover {\n",
|
| 608 |
-
" /* unfitted */\n",
|
| 609 |
-
" background-color: var(--sklearn-color-unfitted-level-3);\n",
|
| 610 |
-
" color: var(--sklearn-color-background);\n",
|
| 611 |
-
" text-decoration: none;\n",
|
| 612 |
-
"}\n",
|
| 613 |
-
"\n",
|
| 614 |
-
"div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
|
| 615 |
-
".sk-estimator-doc-link.fitted:hover,\n",
|
| 616 |
-
"div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
|
| 617 |
-
".sk-estimator-doc-link.fitted:hover {\n",
|
| 618 |
-
" /* fitted */\n",
|
| 619 |
-
" background-color: var(--sklearn-color-fitted-level-3);\n",
|
| 620 |
-
" color: var(--sklearn-color-background);\n",
|
| 621 |
-
" text-decoration: none;\n",
|
| 622 |
-
"}\n",
|
| 623 |
-
"\n",
|
| 624 |
-
"/* Span, style for the box shown on hovering the info icon */\n",
|
| 625 |
-
".sk-estimator-doc-link span {\n",
|
| 626 |
-
" display: none;\n",
|
| 627 |
-
" z-index: 9999;\n",
|
| 628 |
-
" position: relative;\n",
|
| 629 |
-
" font-weight: normal;\n",
|
| 630 |
-
" right: .2ex;\n",
|
| 631 |
-
" padding: .5ex;\n",
|
| 632 |
-
" margin: .5ex;\n",
|
| 633 |
-
" width: min-content;\n",
|
| 634 |
-
" min-width: 20ex;\n",
|
| 635 |
-
" max-width: 50ex;\n",
|
| 636 |
-
" color: var(--sklearn-color-text);\n",
|
| 637 |
-
" box-shadow: 2pt 2pt 4pt #999;\n",
|
| 638 |
-
" /* unfitted */\n",
|
| 639 |
-
" background: var(--sklearn-color-unfitted-level-0);\n",
|
| 640 |
-
" border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
|
| 641 |
-
"}\n",
|
| 642 |
-
"\n",
|
| 643 |
-
".sk-estimator-doc-link.fitted span {\n",
|
| 644 |
-
" /* fitted */\n",
|
| 645 |
-
" background: var(--sklearn-color-fitted-level-0);\n",
|
| 646 |
-
" border: var(--sklearn-color-fitted-level-3);\n",
|
| 647 |
-
"}\n",
|
| 648 |
-
"\n",
|
| 649 |
-
".sk-estimator-doc-link:hover span {\n",
|
| 650 |
-
" display: block;\n",
|
| 651 |
-
"}\n",
|
| 652 |
-
"\n",
|
| 653 |
-
"/* \"?\"-specific style due to the `<a>` HTML tag */\n",
|
| 654 |
-
"\n",
|
| 655 |
-
"#sk-container-id-2 a.estimator_doc_link {\n",
|
| 656 |
-
" float: right;\n",
|
| 657 |
-
" font-size: 1rem;\n",
|
| 658 |
-
" line-height: 1em;\n",
|
| 659 |
-
" font-family: monospace;\n",
|
| 660 |
-
" background-color: var(--sklearn-color-background);\n",
|
| 661 |
-
" border-radius: 1rem;\n",
|
| 662 |
-
" height: 1rem;\n",
|
| 663 |
-
" width: 1rem;\n",
|
| 664 |
-
" text-decoration: none;\n",
|
| 665 |
-
" /* unfitted */\n",
|
| 666 |
-
" color: var(--sklearn-color-unfitted-level-1);\n",
|
| 667 |
-
" border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
|
| 668 |
-
"}\n",
|
| 669 |
-
"\n",
|
| 670 |
-
"#sk-container-id-2 a.estimator_doc_link.fitted {\n",
|
| 671 |
-
" /* fitted */\n",
|
| 672 |
-
" border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
|
| 673 |
-
" color: var(--sklearn-color-fitted-level-1);\n",
|
| 674 |
-
"}\n",
|
| 675 |
-
"\n",
|
| 676 |
-
"/* On hover */\n",
|
| 677 |
-
"#sk-container-id-2 a.estimator_doc_link:hover {\n",
|
| 678 |
-
" /* unfitted */\n",
|
| 679 |
-
" background-color: var(--sklearn-color-unfitted-level-3);\n",
|
| 680 |
-
" color: var(--sklearn-color-background);\n",
|
| 681 |
-
" text-decoration: none;\n",
|
| 682 |
-
"}\n",
|
| 683 |
-
"\n",
|
| 684 |
-
"#sk-container-id-2 a.estimator_doc_link.fitted:hover {\n",
|
| 685 |
-
" /* fitted */\n",
|
| 686 |
-
" background-color: var(--sklearn-color-fitted-level-3);\n",
|
| 687 |
-
"}\n",
|
| 688 |
-
"</style><div id=\"sk-container-id-2\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>LogisticRegression()</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 fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" checked><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\"> LogisticRegression<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.5/modules/generated/sklearn.linear_model.LogisticRegression.html\">?<span>Documentation for LogisticRegression</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>LogisticRegression()</pre></div> </div></div></div></div>"
|
| 689 |
-
],
|
| 690 |
-
"text/plain": [
|
| 691 |
-
"LogisticRegression()"
|
| 692 |
-
]
|
| 693 |
-
},
|
| 694 |
-
"execution_count": 70,
|
| 695 |
-
"metadata": {},
|
| 696 |
-
"output_type": "execute_result"
|
| 697 |
-
}
|
| 698 |
-
],
|
| 699 |
-
"source": [
|
| 700 |
-
"from sklearn.linear_model import LogisticRegression # Import LogisticRegression\n",
|
| 701 |
-
"\n",
|
| 702 |
-
"# Train a logistic regression model\n",
|
| 703 |
-
"model = LogisticRegression()\n",
|
| 704 |
-
"model.fit(X_train_tfidf, y_train)"
|
| 705 |
-
]
|
| 706 |
-
},
|
| 707 |
-
{
|
| 708 |
-
"cell_type": "code",
|
| 709 |
-
"execution_count": 71,
|
| 710 |
-
"metadata": {},
|
| 711 |
-
"outputs": [],
|
| 712 |
-
"source": [
|
| 713 |
-
"# Make predictions on the test set\n",
|
| 714 |
-
"y_pred = model.predict(X_test_tfidf)"
|
| 715 |
-
]
|
| 716 |
-
},
|
| 717 |
-
{
|
| 718 |
-
"cell_type": "code",
|
| 719 |
-
"execution_count": 72,
|
| 720 |
-
"metadata": {},
|
| 721 |
-
"outputs": [
|
| 722 |
-
{
|
| 723 |
-
"name": "stdout",
|
| 724 |
-
"output_type": "stream",
|
| 725 |
-
"text": [
|
| 726 |
-
"Accuracy: 0.9887640449438202\n",
|
| 727 |
-
"Classification Report:\n",
|
| 728 |
-
" precision recall f1-score support\n",
|
| 729 |
-
"\n",
|
| 730 |
-
" business 0.97 1.00 0.99 103\n",
|
| 731 |
-
"entertainment 1.00 0.98 0.99 84\n",
|
| 732 |
-
" politics 0.98 0.99 0.98 80\n",
|
| 733 |
-
" sport 1.00 0.99 0.99 98\n",
|
| 734 |
-
" tech 1.00 0.99 0.99 80\n",
|
| 735 |
-
"\n",
|
| 736 |
-
" accuracy 0.99 445\n",
|
| 737 |
-
" macro avg 0.99 0.99 0.99 445\n",
|
| 738 |
-
" weighted avg 0.99 0.99 0.99 445\n",
|
| 739 |
-
"\n"
|
| 740 |
-
]
|
| 741 |
-
}
|
| 742 |
-
],
|
| 743 |
-
"source": [
|
| 744 |
-
"from sklearn.metrics import accuracy_score, classification_report # Import evaluation metrics\n",
|
| 745 |
-
"\n",
|
| 746 |
-
"# Evaluate the model\n",
|
| 747 |
-
"print(\"Accuracy:\", accuracy_score(y_test, y_pred))\n",
|
| 748 |
-
"print(\"Classification Report:\\n\", classification_report(y_test, y_pred))\n"
|
| 749 |
-
]
|
| 750 |
-
},
|
| 751 |
-
{
|
| 752 |
-
"cell_type": "code",
|
| 753 |
-
"execution_count": 73,
|
| 754 |
-
"metadata": {},
|
| 755 |
-
"outputs": [
|
| 756 |
-
{
|
| 757 |
-
"name": "stdout",
|
| 758 |
-
"output_type": "stream",
|
| 759 |
-
"text": [
|
| 760 |
-
"confusion_matrix:\n",
|
| 761 |
-
" [[103 0 0 0 0]\n",
|
| 762 |
-
" [ 0 82 2 0 0]\n",
|
| 763 |
-
" [ 1 0 79 0 0]\n",
|
| 764 |
-
" [ 1 0 0 97 0]\n",
|
| 765 |
-
" [ 1 0 0 0 79]]\n"
|
| 766 |
-
]
|
| 767 |
-
}
|
| 768 |
-
],
|
| 769 |
-
"source": [
|
| 770 |
-
"from sklearn.metrics import confusion_matrix\n",
|
| 771 |
-
"print(\"confusion_matrix:\\n\", confusion_matrix(y_test, y_pred))\n"
|
| 772 |
-
]
|
| 773 |
-
},
|
| 774 |
-
{
|
| 775 |
-
"cell_type": "code",
|
| 776 |
-
"execution_count": 74,
|
| 777 |
-
"metadata": {},
|
| 778 |
-
"outputs": [
|
| 779 |
-
{
|
| 780 |
-
"data": {
|
| 781 |
-
"text/plain": [
|
| 782 |
-
"['model.pkl']"
|
| 783 |
-
]
|
| 784 |
-
},
|
| 785 |
-
"execution_count": 74,
|
| 786 |
-
"metadata": {},
|
| 787 |
-
"output_type": "execute_result"
|
| 788 |
-
}
|
| 789 |
-
],
|
| 790 |
-
"source": [
|
| 791 |
-
"import joblib\n",
|
| 792 |
-
"joblib.dump(model,'model.pkl')"
|
| 793 |
-
]
|
| 794 |
-
},
|
| 795 |
-
{
|
| 796 |
-
"cell_type": "code",
|
| 797 |
-
"execution_count": 75,
|
| 798 |
-
"metadata": {},
|
| 799 |
-
"outputs": [
|
| 800 |
-
{
|
| 801 |
-
"data": {
|
| 802 |
-
"text/plain": [
|
| 803 |
-
"['vectorizer.pkl']"
|
| 804 |
-
]
|
| 805 |
-
},
|
| 806 |
-
"execution_count": 75,
|
| 807 |
-
"metadata": {},
|
| 808 |
-
"output_type": "execute_result"
|
| 809 |
-
}
|
| 810 |
-
],
|
| 811 |
-
"source": [
|
| 812 |
-
"import joblib\n",
|
| 813 |
-
"joblib.dump(vectorizer,'vectorizer.pkl')"
|
| 814 |
-
]
|
| 815 |
-
},
|
| 816 |
-
{
|
| 817 |
-
"cell_type": "code",
|
| 818 |
-
"execution_count": null,
|
| 819 |
-
"metadata": {},
|
| 820 |
-
"outputs": [],
|
| 821 |
-
"source": []
|
| 822 |
-
}
|
| 823 |
-
],
|
| 824 |
-
"metadata": {
|
| 825 |
-
"kernelspec": {
|
| 826 |
-
"display_name": "base",
|
| 827 |
-
"language": "python",
|
| 828 |
-
"name": "python3"
|
| 829 |
-
},
|
| 830 |
-
"language_info": {
|
| 831 |
-
"codemirror_mode": {
|
| 832 |
-
"name": "ipython",
|
| 833 |
-
"version": 3
|
| 834 |
-
},
|
| 835 |
-
"file_extension": ".py",
|
| 836 |
-
"mimetype": "text/x-python",
|
| 837 |
-
"name": "python",
|
| 838 |
-
"nbconvert_exporter": "python",
|
| 839 |
-
"pygments_lexer": "ipython3",
|
| 840 |
-
"version": "3.10.9"
|
| 841 |
-
}
|
| 842 |
-
},
|
| 843 |
-
"nbformat": 4,
|
| 844 |
-
"nbformat_minor": 2
|
| 845 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|