Devika Nair M
commited on
Delete Briefly.ipynb
Browse files- Briefly.ipynb +0 -556
Briefly.ipynb
DELETED
|
@@ -1,556 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"cells": [
|
| 3 |
-
{
|
| 4 |
-
"cell_type": "markdown",
|
| 5 |
-
"metadata": {},
|
| 6 |
-
"source": [
|
| 7 |
-
"## Briefly\n",
|
| 8 |
-
"\n",
|
| 9 |
-
"\n",
|
| 10 |
-
"### __ Problem Statement __\n",
|
| 11 |
-
"- Obtain news from google news articles\n",
|
| 12 |
-
"- Sammarize the articles within 60 words\n",
|
| 13 |
-
"- Obtain keywords from the articles\n",
|
| 14 |
-
"\n",
|
| 15 |
-
"\n",
|
| 16 |
-
"\n",
|
| 17 |
-
"\n",
|
| 18 |
-
"\n",
|
| 19 |
-
"\n",
|
| 20 |
-
"\n",
|
| 21 |
-
"\n",
|
| 22 |
-
"\n",
|
| 23 |
-
"\n",
|
| 24 |
-
"##### Importing all the necessary libraries required to run the following code "
|
| 25 |
-
]
|
| 26 |
-
},
|
| 27 |
-
{
|
| 28 |
-
"cell_type": "code",
|
| 29 |
-
"execution_count": 1,
|
| 30 |
-
"metadata": {},
|
| 31 |
-
"outputs": [],
|
| 32 |
-
"source": [
|
| 33 |
-
"from gnewsclient import gnewsclient # for fetching google news\n",
|
| 34 |
-
"from newspaper import Article # to obtain text from news articles\n",
|
| 35 |
-
"from transformers import pipeline # to summarize text\n",
|
| 36 |
-
"import spacy # for named entity recognition\n",
|
| 37 |
-
"import spacy.displacy as displacy # display keywords"
|
| 38 |
-
]
|
| 39 |
-
},
|
| 40 |
-
{
|
| 41 |
-
"cell_type": "markdown",
|
| 42 |
-
"metadata": {},
|
| 43 |
-
"source": [
|
| 44 |
-
"##### Load sshleifer/distilbart-cnn-12-6 model"
|
| 45 |
-
]
|
| 46 |
-
},
|
| 47 |
-
{
|
| 48 |
-
"cell_type": "code",
|
| 49 |
-
"execution_count": 2,
|
| 50 |
-
"metadata": {},
|
| 51 |
-
"outputs": [],
|
| 52 |
-
"source": [
|
| 53 |
-
"def load_model(): \n",
|
| 54 |
-
" model = pipeline('summarization')\n",
|
| 55 |
-
" return model\n",
|
| 56 |
-
"data = gnewsclient.NewsClient(max_results=0)\n",
|
| 57 |
-
"nlp = spacy.load(\"en_core_web_lg\") "
|
| 58 |
-
]
|
| 59 |
-
},
|
| 60 |
-
{
|
| 61 |
-
"cell_type": "markdown",
|
| 62 |
-
"metadata": {},
|
| 63 |
-
"source": [
|
| 64 |
-
"##### Obtain urls and it's content"
|
| 65 |
-
]
|
| 66 |
-
},
|
| 67 |
-
{
|
| 68 |
-
"cell_type": "code",
|
| 69 |
-
"execution_count": 3,
|
| 70 |
-
"metadata": {},
|
| 71 |
-
"outputs": [],
|
| 72 |
-
"source": [
|
| 73 |
-
"def getNews(topic,location): \n",
|
| 74 |
-
" count=0\n",
|
| 75 |
-
" contents=[]\n",
|
| 76 |
-
" titles=[]\n",
|
| 77 |
-
" authors=[]\n",
|
| 78 |
-
" urls=[]\n",
|
| 79 |
-
" data = gnewsclient.NewsClient(language='english',location=location,topic=topic,max_results=10) \n",
|
| 80 |
-
" news = data.get_news() \n",
|
| 81 |
-
" for item in news:\n",
|
| 82 |
-
" url=item['link']\n",
|
| 83 |
-
" article = Article(url)\n",
|
| 84 |
-
" try:\n",
|
| 85 |
-
" article.download()\n",
|
| 86 |
-
" article.parse()\n",
|
| 87 |
-
" temp=item['title'][::-1]\n",
|
| 88 |
-
" index=temp.find(\"-\")\n",
|
| 89 |
-
" temp=temp[:index-1][::-1]\n",
|
| 90 |
-
" urls.append(url)\n",
|
| 91 |
-
" contents.append(article.text)\n",
|
| 92 |
-
" titles.append(item['title'][:-index-1]) \n",
|
| 93 |
-
" authors.append(temp)\n",
|
| 94 |
-
" count+=1\n",
|
| 95 |
-
" if(count==5):\n",
|
| 96 |
-
" break\n",
|
| 97 |
-
" except:\n",
|
| 98 |
-
" continue \n",
|
| 99 |
-
" return contents,titles,authors,urls "
|
| 100 |
-
]
|
| 101 |
-
},
|
| 102 |
-
{
|
| 103 |
-
"cell_type": "markdown",
|
| 104 |
-
"metadata": {},
|
| 105 |
-
"source": [
|
| 106 |
-
"##### Summarizes the content- minimum word limit 30 and maximum 60"
|
| 107 |
-
]
|
| 108 |
-
},
|
| 109 |
-
{
|
| 110 |
-
"cell_type": "code",
|
| 111 |
-
"execution_count": 4,
|
| 112 |
-
"metadata": {},
|
| 113 |
-
"outputs": [],
|
| 114 |
-
"source": [
|
| 115 |
-
"def getNewsSummary(contents,summarizer): \n",
|
| 116 |
-
" summaries=[] \n",
|
| 117 |
-
" for content in contents:\n",
|
| 118 |
-
" minimum=len(content.split())\n",
|
| 119 |
-
" summaries.append(summarizer(content,max_length=60,min_length=min(30,minimum),do_sample=False,truncation=True)[0]['summary_text']) \n",
|
| 120 |
-
" return summaries"
|
| 121 |
-
]
|
| 122 |
-
},
|
| 123 |
-
{
|
| 124 |
-
"cell_type": "markdown",
|
| 125 |
-
"metadata": {},
|
| 126 |
-
"source": [
|
| 127 |
-
"##### Named Entity Recognition"
|
| 128 |
-
]
|
| 129 |
-
},
|
| 130 |
-
{
|
| 131 |
-
"cell_type": "code",
|
| 132 |
-
"execution_count": 5,
|
| 133 |
-
"metadata": {},
|
| 134 |
-
"outputs": [],
|
| 135 |
-
"source": [
|
| 136 |
-
"# Obtain 4 keywords from content (person,organisation or geopolitical entity) \n",
|
| 137 |
-
"def generateKeyword(contents): \n",
|
| 138 |
-
" keywords=[]\n",
|
| 139 |
-
" words=[] \n",
|
| 140 |
-
" labels=[\"PERSON\",\"ORG\",\"GPE\"]\n",
|
| 141 |
-
" for content in contents:\n",
|
| 142 |
-
" doc=nlp(content)\n",
|
| 143 |
-
" keys=[]\n",
|
| 144 |
-
" limit=0\n",
|
| 145 |
-
" for ent in doc.ents:\n",
|
| 146 |
-
" key=ent.text.upper()\n",
|
| 147 |
-
" label=ent.label_\n",
|
| 148 |
-
" if(key not in words and key not in keywords and label in labels): \n",
|
| 149 |
-
" keys.append(key)\n",
|
| 150 |
-
" limit+=1\n",
|
| 151 |
-
" for element in key.split():\n",
|
| 152 |
-
" words.append(element)\n",
|
| 153 |
-
" if(limit==4):\n",
|
| 154 |
-
" keywords.append(keys)\n",
|
| 155 |
-
" break \n",
|
| 156 |
-
" return keywords\n",
|
| 157 |
-
" "
|
| 158 |
-
]
|
| 159 |
-
},
|
| 160 |
-
{
|
| 161 |
-
"cell_type": "markdown",
|
| 162 |
-
"metadata": {},
|
| 163 |
-
"source": [
|
| 164 |
-
"##### Displaying keywords "
|
| 165 |
-
]
|
| 166 |
-
},
|
| 167 |
-
{
|
| 168 |
-
"cell_type": "code",
|
| 169 |
-
"execution_count": 6,
|
| 170 |
-
"metadata": {},
|
| 171 |
-
"outputs": [],
|
| 172 |
-
"source": [
|
| 173 |
-
"def printKeywords(keywords):\n",
|
| 174 |
-
" for keyword in keywords:\n",
|
| 175 |
-
" print(keyword)"
|
| 176 |
-
]
|
| 177 |
-
},
|
| 178 |
-
{
|
| 179 |
-
"cell_type": "markdown",
|
| 180 |
-
"metadata": {},
|
| 181 |
-
"source": [
|
| 182 |
-
"##### Displaying the Summary with keywords in it highlighted"
|
| 183 |
-
]
|
| 184 |
-
},
|
| 185 |
-
{
|
| 186 |
-
"cell_type": "code",
|
| 187 |
-
"execution_count": 7,
|
| 188 |
-
"metadata": {},
|
| 189 |
-
"outputs": [],
|
| 190 |
-
"source": [
|
| 191 |
-
"def printSummary(summaries,titles):\n",
|
| 192 |
-
" colors = {\"ORG\": \"linear-gradient(90deg, #aa9cfc, #fc9ce7)\"}\n",
|
| 193 |
-
" options = {\"ents\": [\"PERSON\",\"ORG\",\"GPE\",\"NORP\",\"PERCENT\"],\"colors\": colors} \n",
|
| 194 |
-
" for summary,title in zip(summaries,titles):\n",
|
| 195 |
-
" doc=nlp(summary) \n",
|
| 196 |
-
" print('\\033[1m' + title.upper() + '\\033[0m\\n')\n",
|
| 197 |
-
" displacy.render(doc, style=\"ent\", options=options,jupyter=True)\n",
|
| 198 |
-
" print(\"\\n\\n\")"
|
| 199 |
-
]
|
| 200 |
-
},
|
| 201 |
-
{
|
| 202 |
-
"cell_type": "code",
|
| 203 |
-
"execution_count": 8,
|
| 204 |
-
"metadata": {},
|
| 205 |
-
"outputs": [
|
| 206 |
-
{
|
| 207 |
-
"name": "stderr",
|
| 208 |
-
"output_type": "stream",
|
| 209 |
-
"text": [
|
| 210 |
-
"No model was supplied, defaulted to sshleifer/distilbart-cnn-12-6 (https://huggingface.co/sshleifer/distilbart-cnn-12-6)\n"
|
| 211 |
-
]
|
| 212 |
-
}
|
| 213 |
-
],
|
| 214 |
-
"source": [
|
| 215 |
-
"summarizer=load_model() "
|
| 216 |
-
]
|
| 217 |
-
},
|
| 218 |
-
{
|
| 219 |
-
"cell_type": "code",
|
| 220 |
-
"execution_count": 9,
|
| 221 |
-
"metadata": {},
|
| 222 |
-
"outputs": [],
|
| 223 |
-
"source": [
|
| 224 |
-
"contents,titles,authors,urls=getNews(\"Sports\",\"India\")"
|
| 225 |
-
]
|
| 226 |
-
},
|
| 227 |
-
{
|
| 228 |
-
"cell_type": "code",
|
| 229 |
-
"execution_count": 10,
|
| 230 |
-
"metadata": {},
|
| 231 |
-
"outputs": [],
|
| 232 |
-
"source": [
|
| 233 |
-
"summaries=getNewsSummary(contents,summarizer)"
|
| 234 |
-
]
|
| 235 |
-
},
|
| 236 |
-
{
|
| 237 |
-
"cell_type": "code",
|
| 238 |
-
"execution_count": 11,
|
| 239 |
-
"metadata": {},
|
| 240 |
-
"outputs": [],
|
| 241 |
-
"source": [
|
| 242 |
-
"keywords=generateKeyword(contents)"
|
| 243 |
-
]
|
| 244 |
-
},
|
| 245 |
-
{
|
| 246 |
-
"cell_type": "code",
|
| 247 |
-
"execution_count": 12,
|
| 248 |
-
"metadata": {},
|
| 249 |
-
"outputs": [
|
| 250 |
-
{
|
| 251 |
-
"name": "stdout",
|
| 252 |
-
"output_type": "stream",
|
| 253 |
-
"text": [
|
| 254 |
-
"['DWAYNE BRAVO', 'SRI LANKA', 'ICC', 'THE WEST INDIES']\n",
|
| 255 |
-
"['VIRAT KOHLI', 'INDIA', 'SCOTLAND', 'SUPER 12']\n",
|
| 256 |
-
"['AUSTRALIA', 'AFGHANISTAN', 'CRICKET AUSTRALIA', 'CRICBUZZ STAFF •']\n",
|
| 257 |
-
"['GARY STEAD', 'TRENT BOULT', 'COLIN DE GRANDHOMME', 'BLACKCAPS']\n",
|
| 258 |
-
"[\"VIRAT KOHLI'S\", 'TEAM INDIA', 'DHONI', 'UAE']\n"
|
| 259 |
-
]
|
| 260 |
-
}
|
| 261 |
-
],
|
| 262 |
-
"source": [
|
| 263 |
-
"printKeywords(keywords)"
|
| 264 |
-
]
|
| 265 |
-
},
|
| 266 |
-
{
|
| 267 |
-
"cell_type": "code",
|
| 268 |
-
"execution_count": 13,
|
| 269 |
-
"metadata": {},
|
| 270 |
-
"outputs": [
|
| 271 |
-
{
|
| 272 |
-
"name": "stdout",
|
| 273 |
-
"output_type": "stream",
|
| 274 |
-
"text": [
|
| 275 |
-
"\u001b[1mT20 WORLD CUP 2021: WEST INDIES AND CHENNAI SUPER KINGS ALL-ROUNDER DWAYNE BRAVO TO RETIRE AFTER SHOWPIECE... \u001b[0m\n",
|
| 276 |
-
"\n"
|
| 277 |
-
]
|
| 278 |
-
},
|
| 279 |
-
{
|
| 280 |
-
"data": {
|
| 281 |
-
"text/html": [
|
| 282 |
-
"<span class=\"tex2jax_ignore\"><div class=\"entities\" style=\"line-height: 2.5; direction: ltr\"> \n",
|
| 283 |
-
"<mark class=\"entity\" style=\"background: #c887fb; padding: 0.45em 0.6em; margin: 0 0.25em; line-height: 1; border-radius: 0.35em;\">\n",
|
| 284 |
-
" West Indies\n",
|
| 285 |
-
" <span style=\"font-size: 0.8em; font-weight: bold; line-height: 1; border-radius: 0.35em; vertical-align: middle; margin-left: 0.5rem\">NORP</span>\n",
|
| 286 |
-
"</mark>\n",
|
| 287 |
-
" all-rounder \n",
|
| 288 |
-
"<mark class=\"entity\" style=\"background: #aa9cfc; padding: 0.45em 0.6em; margin: 0 0.25em; line-height: 1; border-radius: 0.35em;\">\n",
|
| 289 |
-
" Dwayne Bravo\n",
|
| 290 |
-
" <span style=\"font-size: 0.8em; font-weight: bold; line-height: 1; border-radius: 0.35em; vertical-align: middle; margin-left: 0.5rem\">PERSON</span>\n",
|
| 291 |
-
"</mark>\n",
|
| 292 |
-
" will hang his boots at the end of the ICC T20 World Cup 2021 . \n",
|
| 293 |
-
"<mark class=\"entity\" style=\"background: #aa9cfc; padding: 0.45em 0.6em; margin: 0 0.25em; line-height: 1; border-radius: 0.35em;\">\n",
|
| 294 |
-
" Bravo\n",
|
| 295 |
-
" <span style=\"font-size: 0.8em; font-weight: bold; line-height: 1; border-radius: 0.35em; vertical-align: middle; margin-left: 0.5rem\">PERSON</span>\n",
|
| 296 |
-
"</mark>\n",
|
| 297 |
-
" told \n",
|
| 298 |
-
"<mark class=\"entity\" style=\"background: linear-gradient(90deg, #aa9cfc, #fc9ce7); padding: 0.45em 0.6em; margin: 0 0.25em; line-height: 1; border-radius: 0.35em;\">\n",
|
| 299 |
-
" ICC\n",
|
| 300 |
-
" <span style=\"font-size: 0.8em; font-weight: bold; line-height: 1; border-radius: 0.35em; vertical-align: middle; margin-left: 0.5rem\">ORG</span>\n",
|
| 301 |
-
"</mark>\n",
|
| 302 |
-
" on the post-match Facebook Live show that he will be drawing the curtains on his international career . \n",
|
| 303 |
-
"<mark class=\"entity\" style=\"background: #c887fb; padding: 0.45em 0.6em; margin: 0 0.25em; line-height: 1; border-radius: 0.35em;\">\n",
|
| 304 |
-
" West Indies\n",
|
| 305 |
-
" <span style=\"font-size: 0.8em; font-weight: bold; line-height: 1; border-radius: 0.35em; vertical-align: middle; margin-left: 0.5rem\">NORP</span>\n",
|
| 306 |
-
"</mark>\n",
|
| 307 |
-
" lost to \n",
|
| 308 |
-
"<mark class=\"entity\" style=\"background: #feca74; padding: 0.45em 0.6em; margin: 0 0.25em; line-height: 1; border-radius: 0.35em;\">\n",
|
| 309 |
-
" Sri Lanka\n",
|
| 310 |
-
" <span style=\"font-size: 0.8em; font-weight: bold; line-height: 1; border-radius: 0.35em; vertical-align: middle; margin-left: 0.5rem\">GPE</span>\n",
|
| 311 |
-
"</mark>\n",
|
| 312 |
-
" by 20 runs in</div></span>"
|
| 313 |
-
],
|
| 314 |
-
"text/plain": [
|
| 315 |
-
"<IPython.core.display.HTML object>"
|
| 316 |
-
]
|
| 317 |
-
},
|
| 318 |
-
"metadata": {},
|
| 319 |
-
"output_type": "display_data"
|
| 320 |
-
},
|
| 321 |
-
{
|
| 322 |
-
"name": "stdout",
|
| 323 |
-
"output_type": "stream",
|
| 324 |
-
"text": [
|
| 325 |
-
"\n",
|
| 326 |
-
"\n",
|
| 327 |
-
"\n",
|
| 328 |
-
"\u001b[1mHAPPY BIRTHDAY VIRAT KOHLI: INDIAN CRICKET TEAM CAPTAIN TURNS 33 \u001b[0m\n",
|
| 329 |
-
"\n"
|
| 330 |
-
]
|
| 331 |
-
},
|
| 332 |
-
{
|
| 333 |
-
"data": {
|
| 334 |
-
"text/html": [
|
| 335 |
-
"<span class=\"tex2jax_ignore\"><div class=\"entities\" style=\"line-height: 2.5; direction: ltr\"> \n",
|
| 336 |
-
"<mark class=\"entity\" style=\"background: #feca74; padding: 0.45em 0.6em; margin: 0 0.25em; line-height: 1; border-radius: 0.35em;\">\n",
|
| 337 |
-
" India\n",
|
| 338 |
-
" <span style=\"font-size: 0.8em; font-weight: bold; line-height: 1; border-radius: 0.35em; vertical-align: middle; margin-left: 0.5rem\">GPE</span>\n",
|
| 339 |
-
"</mark>\n",
|
| 340 |
-
" captain \n",
|
| 341 |
-
"<mark class=\"entity\" style=\"background: #aa9cfc; padding: 0.45em 0.6em; margin: 0 0.25em; line-height: 1; border-radius: 0.35em;\">\n",
|
| 342 |
-
" Virat Kohli\n",
|
| 343 |
-
" <span style=\"font-size: 0.8em; font-weight: bold; line-height: 1; border-radius: 0.35em; vertical-align: middle; margin-left: 0.5rem\">PERSON</span>\n",
|
| 344 |
-
"</mark>\n",
|
| 345 |
-
" turns 33 on Friday . The 33-year-old is currently leading the national side in the ongoing T20 World Cup . \n",
|
| 346 |
-
"<mark class=\"entity\" style=\"background: #feca74; padding: 0.45em 0.6em; margin: 0 0.25em; line-height: 1; border-radius: 0.35em;\">\n",
|
| 347 |
-
" India\n",
|
| 348 |
-
" <span style=\"font-size: 0.8em; font-weight: bold; line-height: 1; border-radius: 0.35em; vertical-align: middle; margin-left: 0.5rem\">GPE</span>\n",
|
| 349 |
-
"</mark>\n",
|
| 350 |
-
" lost their first two games in the tournament before winning the third . \n",
|
| 351 |
-
"<mark class=\"entity\" style=\"background: #feca74; padding: 0.45em 0.6em; margin: 0 0.25em; line-height: 1; border-radius: 0.35em;\">\n",
|
| 352 |
-
" India\n",
|
| 353 |
-
" <span style=\"font-size: 0.8em; font-weight: bold; line-height: 1; border-radius: 0.35em; vertical-align: middle; margin-left: 0.5rem\">GPE</span>\n",
|
| 354 |
-
"</mark>\n",
|
| 355 |
-
" sit in fourth spot in the Group 2 points table .</div></span>"
|
| 356 |
-
],
|
| 357 |
-
"text/plain": [
|
| 358 |
-
"<IPython.core.display.HTML object>"
|
| 359 |
-
]
|
| 360 |
-
},
|
| 361 |
-
"metadata": {},
|
| 362 |
-
"output_type": "display_data"
|
| 363 |
-
},
|
| 364 |
-
{
|
| 365 |
-
"name": "stdout",
|
| 366 |
-
"output_type": "stream",
|
| 367 |
-
"text": [
|
| 368 |
-
"\n",
|
| 369 |
-
"\n",
|
| 370 |
-
"\n",
|
| 371 |
-
"\u001b[1mONE-OFF TEST VS AFGHANISTAN POSTPONED, CONFIRMS CRICKET AUSTRALIA | CRICBUZZ.COM - CRICBUZZ \u001b[0m\n",
|
| 372 |
-
"\n"
|
| 373 |
-
]
|
| 374 |
-
},
|
| 375 |
-
{
|
| 376 |
-
"data": {
|
| 377 |
-
"text/html": [
|
| 378 |
-
"<span class=\"tex2jax_ignore\"><div class=\"entities\" style=\"line-height: 2.5; direction: ltr\"> \n",
|
| 379 |
-
"<mark class=\"entity\" style=\"background: linear-gradient(90deg, #aa9cfc, #fc9ce7); padding: 0.45em 0.6em; margin: 0 0.25em; line-height: 1; border-radius: 0.35em;\">\n",
|
| 380 |
-
" Cricket Australia's\n",
|
| 381 |
-
" <span style=\"font-size: 0.8em; font-weight: bold; line-height: 1; border-radius: 0.35em; vertical-align: middle; margin-left: 0.5rem\">ORG</span>\n",
|
| 382 |
-
"</mark>\n",
|
| 383 |
-
" one-off Test against \n",
|
| 384 |
-
"<mark class=\"entity\" style=\"background: #feca74; padding: 0.45em 0.6em; margin: 0 0.25em; line-height: 1; border-radius: 0.35em;\">\n",
|
| 385 |
-
" Afghanistan\n",
|
| 386 |
-
" <span style=\"font-size: 0.8em; font-weight: bold; line-height: 1; border-radius: 0.35em; vertical-align: middle; margin-left: 0.5rem\">GPE</span>\n",
|
| 387 |
-
"</mark>\n",
|
| 388 |
-
" has officially been postponed . The historic Test has been hanging in the balance since the CA revealed that they wouldn't support the \n",
|
| 389 |
-
"<mark class=\"entity\" style=\"background: linear-gradient(90deg, #aa9cfc, #fc9ce7); padding: 0.45em 0.6em; margin: 0 0.25em; line-height: 1; border-radius: 0.35em;\">\n",
|
| 390 |
-
" Taliban\n",
|
| 391 |
-
" <span style=\"font-size: 0.8em; font-weight: bold; line-height: 1; border-radius: 0.35em; vertical-align: middle; margin-left: 0.5rem\">ORG</span>\n",
|
| 392 |
-
"</mark>\n",
|
| 393 |
-
" government's stance against the inclusion of women in sports . Instead of cancelling the Test match, CA has vowed to</div></span>"
|
| 394 |
-
],
|
| 395 |
-
"text/plain": [
|
| 396 |
-
"<IPython.core.display.HTML object>"
|
| 397 |
-
]
|
| 398 |
-
},
|
| 399 |
-
"metadata": {},
|
| 400 |
-
"output_type": "display_data"
|
| 401 |
-
},
|
| 402 |
-
{
|
| 403 |
-
"name": "stdout",
|
| 404 |
-
"output_type": "stream",
|
| 405 |
-
"text": [
|
| 406 |
-
"\n",
|
| 407 |
-
"\n",
|
| 408 |
-
"\n",
|
| 409 |
-
"\u001b[1mNEW ZEALAND INCLUDE FIVE SPINNERS FOR INDIA TOUR, TRENT BOULT OPTS OUT CITING BUBBLE FATIGUE \u001b[0m\n",
|
| 410 |
-
"\n"
|
| 411 |
-
]
|
| 412 |
-
},
|
| 413 |
-
{
|
| 414 |
-
"data": {
|
| 415 |
-
"text/html": [
|
| 416 |
-
"<span class=\"tex2jax_ignore\"><div class=\"entities\" style=\"line-height: 2.5; direction: ltr\"> \n",
|
| 417 |
-
"<mark class=\"entity\" style=\"background: #feca74; padding: 0.45em 0.6em; margin: 0 0.25em; line-height: 1; border-radius: 0.35em;\">\n",
|
| 418 |
-
" New Zealand\n",
|
| 419 |
-
" <span style=\"font-size: 0.8em; font-weight: bold; line-height: 1; border-radius: 0.35em; vertical-align: middle; margin-left: 0.5rem\">GPE</span>\n",
|
| 420 |
-
"</mark>\n",
|
| 421 |
-
" name five spinners in 15-man squad for two-Test series against \n",
|
| 422 |
-
"<mark class=\"entity\" style=\"background: #feca74; padding: 0.45em 0.6em; margin: 0 0.25em; line-height: 1; border-radius: 0.35em;\">\n",
|
| 423 |
-
" India\n",
|
| 424 |
-
" <span style=\"font-size: 0.8em; font-weight: bold; line-height: 1; border-radius: 0.35em; vertical-align: middle; margin-left: 0.5rem\">GPE</span>\n",
|
| 425 |
-
"</mark>\n",
|
| 426 |
-
" . Senior pacer \n",
|
| 427 |
-
"<mark class=\"entity\" style=\"background: #aa9cfc; padding: 0.45em 0.6em; margin: 0 0.25em; line-height: 1; border-radius: 0.35em;\">\n",
|
| 428 |
-
" Trent Boult\n",
|
| 429 |
-
" <span style=\"font-size: 0.8em; font-weight: bold; line-height: 1; border-radius: 0.35em; vertical-align: middle; margin-left: 0.5rem\">PERSON</span>\n",
|
| 430 |
-
"</mark>\n",
|
| 431 |
-
" and fast-bowling all-rounder \n",
|
| 432 |
-
"<mark class=\"entity\" style=\"background: #aa9cfc; padding: 0.45em 0.6em; margin: 0 0.25em; line-height: 1; border-radius: 0.35em;\">\n",
|
| 433 |
-
" Colin de Grandhomme\n",
|
| 434 |
-
" <span style=\"font-size: 0.8em; font-weight: bold; line-height: 1; border-radius: 0.35em; vertical-align: middle; margin-left: 0.5rem\">PERSON</span>\n",
|
| 435 |
-
"</mark>\n",
|
| 436 |
-
" will miss tour due to bio-bubble fatigue . \n",
|
| 437 |
-
"<mark class=\"entity\" style=\"background: #aa9cfc; padding: 0.45em 0.6em; margin: 0 0.25em; line-height: 1; border-radius: 0.35em;\">\n",
|
| 438 |
-
" Ajaz Patel\n",
|
| 439 |
-
" <span style=\"font-size: 0.8em; font-weight: bold; line-height: 1; border-radius: 0.35em; vertical-align: middle; margin-left: 0.5rem\">PERSON</span>\n",
|
| 440 |
-
"</mark>\n",
|
| 441 |
-
", \n",
|
| 442 |
-
"<mark class=\"entity\" style=\"background: #aa9cfc; padding: 0.45em 0.6em; margin: 0 0.25em; line-height: 1; border-radius: 0.35em;\">\n",
|
| 443 |
-
" Will Somerville\n",
|
| 444 |
-
" <span style=\"font-size: 0.8em; font-weight: bold; line-height: 1; border-radius: 0.35em; vertical-align: middle; margin-left: 0.5rem\">PERSON</span>\n",
|
| 445 |
-
"</mark>\n",
|
| 446 |
-
" and</div></span>"
|
| 447 |
-
],
|
| 448 |
-
"text/plain": [
|
| 449 |
-
"<IPython.core.display.HTML object>"
|
| 450 |
-
]
|
| 451 |
-
},
|
| 452 |
-
"metadata": {},
|
| 453 |
-
"output_type": "display_data"
|
| 454 |
-
},
|
| 455 |
-
{
|
| 456 |
-
"name": "stdout",
|
| 457 |
-
"output_type": "stream",
|
| 458 |
-
"text": [
|
| 459 |
-
"\n",
|
| 460 |
-
"\n",
|
| 461 |
-
"\n",
|
| 462 |
-
"\u001b[1m‘THERE ARE MANY CANDIDATES BUT HE’S THE BEST': SEHWAG PICKS NEXT INDIA CAPTAIN AFTER KOHLI STEPS DOWN AT END OF T20 WC \u001b[0m\n",
|
| 463 |
-
"\n"
|
| 464 |
-
]
|
| 465 |
-
},
|
| 466 |
-
{
|
| 467 |
-
"data": {
|
| 468 |
-
"text/html": [
|
| 469 |
-
"<span class=\"tex2jax_ignore\"><div class=\"entities\" style=\"line-height: 2.5; direction: ltr\"> \n",
|
| 470 |
-
"<mark class=\"entity\" style=\"background: #aa9cfc; padding: 0.45em 0.6em; margin: 0 0.25em; line-height: 1; border-radius: 0.35em;\">\n",
|
| 471 |
-
" Virat Kohli\n",
|
| 472 |
-
" <span style=\"font-size: 0.8em; font-weight: bold; line-height: 1; border-radius: 0.35em; vertical-align: middle; margin-left: 0.5rem\">PERSON</span>\n",
|
| 473 |
-
"</mark>\n",
|
| 474 |
-
" set to step down as T20I captain after this World Cup in \n",
|
| 475 |
-
"<mark class=\"entity\" style=\"background: #feca74; padding: 0.45em 0.6em; margin: 0 0.25em; line-height: 1; border-radius: 0.35em;\">\n",
|
| 476 |
-
" UAE\n",
|
| 477 |
-
" <span style=\"font-size: 0.8em; font-weight: bold; line-height: 1; border-radius: 0.35em; vertical-align: middle; margin-left: 0.5rem\">GPE</span>\n",
|
| 478 |
-
"</mark>\n",
|
| 479 |
-
" and \n",
|
| 480 |
-
"<mark class=\"entity\" style=\"background: #feca74; padding: 0.45em 0.6em; margin: 0 0.25em; line-height: 1; border-radius: 0.35em;\">\n",
|
| 481 |
-
" Oman\n",
|
| 482 |
-
" <span style=\"font-size: 0.8em; font-weight: bold; line-height: 1; border-radius: 0.35em; vertical-align: middle; margin-left: 0.5rem\">GPE</span>\n",
|
| 483 |
-
"</mark>\n",
|
| 484 |
-
" . Many experts are anticipating his deputy \n",
|
| 485 |
-
"<mark class=\"entity\" style=\"background: #aa9cfc; padding: 0.45em 0.6em; margin: 0 0.25em; line-height: 1; border-radius: 0.35em;\">\n",
|
| 486 |
-
" Rohit Sharma\n",
|
| 487 |
-
" <span style=\"font-size: 0.8em; font-weight: bold; line-height: 1; border-radius: 0.35em; vertical-align: middle; margin-left: 0.5rem\">PERSON</span>\n",
|
| 488 |
-
"</mark>\n",
|
| 489 |
-
" to fill up the position . Former \n",
|
| 490 |
-
"<mark class=\"entity\" style=\"background: #feca74; padding: 0.45em 0.6em; margin: 0 0.25em; line-height: 1; border-radius: 0.35em;\">\n",
|
| 491 |
-
" India\n",
|
| 492 |
-
" <span style=\"font-size: 0.8em; font-weight: bold; line-height: 1; border-radius: 0.35em; vertical-align: middle; margin-left: 0.5rem\">GPE</span>\n",
|
| 493 |
-
"</mark>\n",
|
| 494 |
-
" opener \n",
|
| 495 |
-
"<mark class=\"entity\" style=\"background: linear-gradient(90deg, #aa9cfc, #fc9ce7); padding: 0.45em 0.6em; margin: 0 0.25em; line-height: 1; border-radius: 0.35em;\">\n",
|
| 496 |
-
" Virender Sehwag\n",
|
| 497 |
-
" <span style=\"font-size: 0.8em; font-weight: bold; line-height: 1; border-radius: 0.35em; vertical-align: middle; margin-left: 0.5rem\">ORG</span>\n",
|
| 498 |
-
"</mark>\n",
|
| 499 |
-
" backed \n",
|
| 500 |
-
"<mark class=\"entity\" style=\"background: linear-gradient(90deg, #aa9cfc, #fc9ce7); padding: 0.45em 0.6em; margin: 0 0.25em; line-height: 1; border-radius: 0.35em;\">\n",
|
| 501 |
-
" Rohit\n",
|
| 502 |
-
" <span style=\"font-size: 0.8em; font-weight: bold; line-height: 1; border-radius: 0.35em; vertical-align: middle; margin-left: 0.5rem\">ORG</span>\n",
|
| 503 |
-
"</mark>\n",
|
| 504 |
-
" as the ideal candidate .</div></span>"
|
| 505 |
-
],
|
| 506 |
-
"text/plain": [
|
| 507 |
-
"<IPython.core.display.HTML object>"
|
| 508 |
-
]
|
| 509 |
-
},
|
| 510 |
-
"metadata": {},
|
| 511 |
-
"output_type": "display_data"
|
| 512 |
-
},
|
| 513 |
-
{
|
| 514 |
-
"name": "stdout",
|
| 515 |
-
"output_type": "stream",
|
| 516 |
-
"text": [
|
| 517 |
-
"\n",
|
| 518 |
-
"\n",
|
| 519 |
-
"\n"
|
| 520 |
-
]
|
| 521 |
-
}
|
| 522 |
-
],
|
| 523 |
-
"source": [
|
| 524 |
-
"printSummary(summaries,titles)"
|
| 525 |
-
]
|
| 526 |
-
},
|
| 527 |
-
{
|
| 528 |
-
"cell_type": "code",
|
| 529 |
-
"execution_count": null,
|
| 530 |
-
"metadata": {},
|
| 531 |
-
"outputs": [],
|
| 532 |
-
"source": []
|
| 533 |
-
}
|
| 534 |
-
],
|
| 535 |
-
"metadata": {
|
| 536 |
-
"kernelspec": {
|
| 537 |
-
"display_name": "Python 3",
|
| 538 |
-
"language": "python",
|
| 539 |
-
"name": "python3"
|
| 540 |
-
},
|
| 541 |
-
"language_info": {
|
| 542 |
-
"codemirror_mode": {
|
| 543 |
-
"name": "ipython",
|
| 544 |
-
"version": 3
|
| 545 |
-
},
|
| 546 |
-
"file_extension": ".py",
|
| 547 |
-
"mimetype": "text/x-python",
|
| 548 |
-
"name": "python",
|
| 549 |
-
"nbconvert_exporter": "python",
|
| 550 |
-
"pygments_lexer": "ipython3",
|
| 551 |
-
"version": "3.8.5"
|
| 552 |
-
}
|
| 553 |
-
},
|
| 554 |
-
"nbformat": 4,
|
| 555 |
-
"nbformat_minor": 4
|
| 556 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|