Format: application/octet-stream
1 {
2 "cells": [
3 {
4 "cell_type": "code",
5 "execution_count": 1,
6 "id": "cce66bbb",
7 "metadata": {},
8 "outputs": [],
9 "source": [
10 "import pandas as pd\n",
11 "import numpy as np\n",
12 "import nltk\n",
13 "from nltk.corpus import stopwords\n",
14 "stopwords= stopwords.words('english')\n",
15 "stopwords.extend([',','`','?',\"'s\", \"''\", '``',\"n't\",\"(\", \")\", ';',\"'\",'re','!','--','-','*',\"'re\"])"
16 ]
17 },
18 {
19 "cell_type": "code",
20 "execution_count": null,
21 "id": "3d54aec8",
22 "metadata": {},
23 "outputs": [],
24 "source": []
25 },
26 {
27 "cell_type": "code",
28 "execution_count": 2,
29 "id": "414ede8c",
30 "metadata": {},
31 "outputs": [],
32 "source": [
33 "s1= pd.read_csv('data/unique synopsis.tsv', sep='\\t')\n"
34 ]
35 },
36 {
37 "cell_type": "code",
38 "execution_count": 3,
39 "id": "0a92550b",
40 "metadata": {
41 "scrolled": true
42 },
43 "outputs": [
44 {
45 "data": {
46 "text/html": [
47 "<div>\n",
48 "<style scoped>\n",
49 " .dataframe tbody tr th:only-of-type {\n",
50 " vertical-align: middle;\n",
51 " }\n",
52 "\n",
53 " .dataframe tbody tr th {\n",
54 " vertical-align: top;\n",
55 " }\n",
56 "\n",
57 " .dataframe thead th {\n",
58 " text-align: right;\n",
59 " }\n",
60 "</style>\n",
61 "<table border=\"1\" class=\"dataframe\">\n",
62 " <thead>\n",
63 " <tr style=\"text-align: right;\">\n",
64 " <th></th>\n",
65 " <th>0</th>\n",
66 " </tr>\n",
67 " </thead>\n",
68 " <tbody>\n",
69 " <tr>\n",
70 " <th>0</th>\n",
71 " <td>In 1947, Andy Dufresne (Tim Robbins), a banker...</td>\n",
72 " </tr>\n",
73 " <tr>\n",
74 " <th>1</th>\n",
75 " <td>The movie begins with a gang of men with clown...</td>\n",
76 " </tr>\n",
77 " <tr>\n",
78 " <th>2</th>\n",
79 " <td>A young man, exhausted and delirious, washes u...</td>\n",
80 " </tr>\n",
81 " <tr>\n",
82 " <th>3</th>\n",
83 " <td>We back out of the webbing of neurons and brai...</td>\n",
84 " </tr>\n",
85 " <tr>\n",
86 " <th>4</th>\n",
87 " <td>Late one morning in the Hawthorne Grill, a res...</td>\n",
88 " </tr>\n",
89 " </tbody>\n",
90 "</table>\n",
91 "</div>"
92 ],
93 "text/plain": [
94 " 0\n",
95 "0 In 1947, Andy Dufresne (Tim Robbins), a banker...\n",
96 "1 The movie begins with a gang of men with clown...\n",
97 "2 A young man, exhausted and delirious, washes u...\n",
98 "3 We back out of the webbing of neurons and brai...\n",
99 "4 Late one morning in the Hawthorne Grill, a res..."
100 ]
101 },
102 "execution_count": 3,
103 "metadata": {},
104 "output_type": "execute_result"
105 }
106 ],
107 "source": [
108 "s1.head()"
109 ]
110 },
111 {
112 "cell_type": "code",
113 "execution_count": 4,
114 "id": "fcd17342",
115 "metadata": {},
116 "outputs": [],
117 "source": [
118 "from nltk.tokenize import word_tokenize"
119 ]
120 },
121 {
122 "cell_type": "code",
123 "execution_count": 5,
124 "id": "c95e8fad",
125 "metadata": {},
126 "outputs": [],
127 "source": [
128 "texts= s1.dropna(axis=0).values.reshape(-1,).astype('object')"
129 ]
130 },
131 {
132 "cell_type": "code",
133 "execution_count": 6,
134 "id": "0dc29d41",
135 "metadata": {},
136 "outputs": [],
137 "source": [
138 "texts=' '.join(texts[:1000]).lower()"
139 ]
140 },
141 {
142 "cell_type": "code",
143 "execution_count": 7,
144 "id": "f234ab82",
145 "metadata": {},
146 "outputs": [],
147 "source": [
148 "texts=' '.join(texts.split('.'))"
149 ]
150 },
151 {
152 "cell_type": "code",
153 "execution_count": null,
154 "id": "443151ad",
155 "metadata": {},
156 "outputs": [],
157 "source": []
158 },
159 {
160 "cell_type": "code",
161 "execution_count": 8,
162 "id": "65a6250a",
163 "metadata": {},
164 "outputs": [],
165 "source": [
166 "words= np.array(word_tokenize(texts)) ### chewck"
167 ]
168 },
169 {
170 "cell_type": "code",
171 "execution_count": 9,
172 "id": "1c97bb4e",
173 "metadata": {},
174 "outputs": [],
175 "source": [
176 "words=np.array([w for w in words if not w in stopwords])"
177 ]
178 },
179 {
180 "cell_type": "code",
181 "execution_count": 10,
182 "id": "7f385213",
183 "metadata": {},
184 "outputs": [
185 {
186 "data": {
187 "text/plain": [
188 "1053997"
189 ]
190 },
191 "execution_count": 10,
192 "metadata": {},
193 "output_type": "execute_result"
194 }
195 ],
196 "source": [
197 "len(words)"
198 ]
199 },
200 {
201 "cell_type": "code",
202 "execution_count": 11,
203 "id": "57de2a1f",
204 "metadata": {},
205 "outputs": [],
206 "source": [
207 "features=np.array(list(set(words)))"
208 ]
209 },
210 {
211 "cell_type": "code",
212 "execution_count": 12,
213 "id": "db456073",
214 "metadata": {},
215 "outputs": [
216 {
217 "data": {
218 "text/plain": [
219 "48792"
220 ]
221 },
222 "execution_count": 12,
223 "metadata": {},
224 "output_type": "execute_result"
225 }
226 ],
227 "source": [
228 "len(features)"
229 ]
230 },
231 {
232 "cell_type": "code",
233 "execution_count": null,
234 "id": "35f11b06",
235 "metadata": {},
236 "outputs": [],
237 "source": []
238 },
239 {
240 "cell_type": "code",
241 "execution_count": 13,
242 "id": "8e72dc01",
243 "metadata": {},
244 "outputs": [
245 {
246 "data": {
247 "text/plain": [
248 "array([], dtype=int64)"
249 ]
250 },
251 "execution_count": 13,
252 "metadata": {},
253 "output_type": "execute_result"
254 }
255 ],
256 "source": [
257 "np.where(words== 'in')[0]"
258 ]
259 },
260 {
261 "cell_type": "code",
262 "execution_count": 14,
263 "id": "02dff38f",
264 "metadata": {},
265 "outputs": [],
266 "source": [
267 "def count_f(array):\n",
268 " unique, counts = np.unique(array, return_counts=True)\n",
269 " if len(counts)>1:\n",
270 " counts= counts/len(counts)\n",
271 " else:\n",
272 " counts= counts/counts\n",
273 " array=dict(zip(unique, counts))\n",
274 " array={k: v for k, v in sorted(array.items(), key=lambda item: item[1], reverse=True)} #set to true\n",
275 " #print(array)\n",
276 " return array"
277 ]
278 },
279 {
280 "cell_type": "code",
281 "execution_count": 75,
282 "id": "50fc9bb7",
283 "metadata": {},
284 "outputs": [],
285 "source": [
286 "def next_previous(feature):\n",
287 " indexs= np.where(words== feature)[0]\n",
288 " \n",
289 " next_word= count_f(words[indexs+1])\n",
290 " previous_word= count_f(words[indexs-1])\n",
291 "\n",
292 " return np.vstack((previous_word, next_word)).astype('object').T"
293 ]
294 },
295 {
296 "cell_type": "code",
297 "execution_count": null,
298 "id": "c2778b94",
299 "metadata": {},
300 "outputs": [],
301 "source": []
302 },
303 {
304 "cell_type": "code",
305 "execution_count": null,
306 "id": "edf17f6d",
307 "metadata": {},
308 "outputs": [],
309 "source": []
310 },
311 {
312 "cell_type": "code",
313 "execution_count": null,
314 "id": "6366262a",
315 "metadata": {},
316 "outputs": [],
317 "source": []
318 },
319 {
320 "cell_type": "code",
321 "execution_count": 16,
322 "id": "72bf90f5",
323 "metadata": {},
324 "outputs": [],
325 "source": [
326 "def word_cha(features):\n",
327 " final={}\n",
328 " for feature in features:\n",
329 " final[feature]= next_previous(feature)\n",
330 " return final"
331 ]
332 },
333 {
334 "cell_type": "code",
335 "execution_count": 87,
336 "id": "f94d6cca",
337 "metadata": {},
338 "outputs": [],
339 "source": [
340 "def find_most_probable(word):\n",
341 " try:\n",
342 " words=next_previous(word)\n",
343 " previous_words= np.array(list(words[0][0].keys())).astype('object')\n",
344 " next_words= np.array(list(words[0][1].keys())).astype('object')\n",
345 " previous_words_prob= np.array(list(words[0][0].values()))\n",
346 " prob_words=np.array([])\n",
347 " for i,previous_word in enumerate(previous_words):\n",
348 " #print('p',previous_word)\n",
349 " #c=previous_words_prob[i]\n",
350 " #print(f'c= {c}')\n",
351 " n=next_previous(previous_word)\n",
352 " #print(n)\n",
353 "\n",
354 " next_words_child= np.array(list(n[0][1].keys())).astype('object')\n",
355 " prob_words= np.append(prob_words, next_words_child)\n",
356 "\n",
357 " if i<len(next_words):\n",
358 " n=next_previous(next_words[i])\n",
359 " previous_words_child= np.array(list(n[0][0].keys())).astype('object')\n",
360 " prob_words= np.append(prob_words, previous_words_child)\n",
361 " #print(next_words_child)\n",
362 " #next_words_child_prob= np.array(list(next_previous(word)[0][1].values()))\n",
363 "\n",
364 " \n",
365 " #del prob_words[word]\n",
366 " #a=count_f(words)\n",
367 " #for key, value in prob_words.items():\n",
368 " # prob_words[key]= value/a[key]\n",
369 " # prob_words={k: v for k, v in sorted(prob_words.items(), key=lambda item: item[1], reverse=True)}\n",
370 " except:\n",
371 " pass\n",
372 " prob_words=count_f(prob_words)\n",
373 " for key, value in prob_words.items():\n",
374 " prob_words[key]= value/a[key]\n",
375 " prob_words={k: v for k, v in sorted(prob_words.items(), key=lambda item: item[1], reverse=True)}\n",
376 " \n",
377 " return a"
378 ]
379 },
380 {
381 "cell_type": "code",
382 "execution_count": null,
383 "id": "0e71db1d",
384 "metadata": {},
385 "outputs": [],
386 "source": []
387 },
388 {
389 "cell_type": "code",
390 "execution_count": 88,
391 "id": "e2e9d755",
392 "metadata": {},
393 "outputs": [
394 {
395 "data": {
396 "text/plain": [
397 "{'tells': 0.11868748975241843,\n",
398 " 'back': 0.10393097229053944,\n",
399 " 'one': 0.10165600918183308,\n",
400 " 'says': 0.06720363994097393,\n",
401 " 'get': 0.06378094769634367,\n",
402 " 'asks': 0.05939498278406296,\n",
403 " 'two': 0.05929250696835547,\n",
404 " 'man': 0.05779636005902607,\n",
405 " 'go': 0.0558493195605837,\n",
406 " 'time': 0.05306197737333989,\n",
407 " 'goes': 0.052447122479094936,\n",
408 " 'see': 0.05086899491719954,\n",
409 " 'find': 0.04965978029185112,\n",
410 " 'room': 0.048061157566814235,\n",
411 " 'away': 0.04742580750942778,\n",
412 " 'takes': 0.047261846204295785,\n",
413 " 'car': 0.04636005902606985,\n",
414 " 'also': 0.044003115264797506,\n",
415 " 'home': 0.04365469749139203,\n",
416 " 'take': 0.04355222167568454,\n",
417 " 'finds': 0.04299885227086408,\n",
418 " 'new': 0.04203557960321364,\n",
419 " 'house': 0.04012952943105427,\n",
420 " 'later': 0.03916625676340384,\n",
421 " 'gets': 0.038469421216592886,\n",
422 " ':': 0.0381619937694704,\n",
423 " 'father': 0.03805951795376291,\n",
424 " 'tries': 0.03703475979668798,\n",
425 " 'men': 0.03689129365469749,\n",
426 " 'next': 0.03689129365469749,\n",
427 " 'sees': 0.03685030332841449,\n",
428 " 'way': 0.03498524348253812,\n",
429 " 'another': 0.03486227250368913,\n",
430 " 'first': 0.034636825709132645,\n",
431 " 'day': 0.03406296114117068,\n",
432 " 'night': 0.03355058206263322,\n",
433 " 'like': 0.0324233480898508,\n",
434 " 'however': 0.03166502705361535,\n",
435 " 'make': 0.03164453189047385,\n",
436 " 'still': 0.03146007542220036,\n",
437 " 'help': 0.03115264797507788,\n",
438 " 'would': 0.03029185112313494,\n",
439 " 'head': 0.029943433349729463,\n",
440 " 'life': 0.02969749139203148,\n",
441 " 'police': 0.02926709296606001,\n",
442 " 'around': 0.029164617150352515,\n",
443 " 'kill': 0.029062141334645023,\n",
444 " 'leaves': 0.02893917035579603,\n",
445 " 'people': 0.02883669454008854,\n",
446 " 'leave': 0.02865223807181505,\n",
447 " 'going': 0.02807837350385309,\n",
448 " 'door': 0.027688965404164618,\n",
449 " 'comes': 0.02760698475159862,\n",
450 " 'john': 0.02748401377274963,\n",
451 " 'family': 0.027443023446466635,\n",
452 " 'peter': 0.027320052467617643,\n",
453 " 'mother': 0.027156091162485654,\n",
454 " 'begins': 0.026500245941957698,\n",
455 " 'wants': 0.025639449090014758,\n",
456 " 'killed': 0.025393507132316775,\n",
457 " 'harry': 0.025373011969175276,\n",
458 " 'gives': 0.025024594195769797,\n",
459 " 'come': 0.024184292506968356,\n",
460 " 'three': 0.024143302180685357,\n",
461 " 'inside': 0.023938350549270373,\n",
462 " 'even': 0.02371290375471389,\n",
463 " 'fight': 0.023610427939006393,\n",
464 " 'outside': 0.02338498114444991,\n",
465 " 'makes': 0.02324151500245942,\n",
466 " 'explains': 0.022913592392195443,\n",
467 " 'death': 0.022852106902770945,\n",
468 " 'behind': 0.022749631087063453,\n",
469 " 'finally': 0.022606164945072962,\n",
470 " 'years': 0.02248319396622397,\n",
471 " 'old': 0.02221675684538449,\n",
472 " 'group': 0.02217576651910149,\n",
473 " 'dead': 0.022073290703393998,\n",
474 " 'work': 0.021991310050828005,\n",
475 " 'runs': 0.021950319724545007,\n",
476 " 'calls': 0.021929824561403508,\n",
477 " 'jack': 0.021929824561403508,\n",
478 " 'starts': 0.021929824561403508,\n",
479 " 'gun': 0.021581406787998032,\n",
480 " 'looks': 0.021212493851451058,\n",
481 " 'know': 0.02115100836202656,\n",
482 " 'wife': 0.021048532546319068,\n",
483 " 'woman': 0.02100754222003607,\n",
484 " 'ship': 0.020823085751762584,\n",
485 " 'money': 0.020802590588621085,\n",
486 " 'meanwhile': 0.020761600262338087,\n",
487 " 'escape': 0.020700114772913593,\n",
488 " 'arrives': 0.02043367765207411,\n",
489 " 'suddenly': 0.020249221183800622,\n",
490 " 'city': 0.020228726020659126,\n",
491 " 'named': 0.020228726020659126,\n",
492 " 'body': 0.02012625020495163,\n",
493 " 'shows': 0.02012625020495163,\n",
494 " 'team': 0.02012625020495163,\n",
495 " 'face': 0.02010575504181013,\n",
496 " 'son': 0.02000327922610264,\n",
497 " 'frank': 0.01985981308411215,\n",
498 " 'turns': 0.019798327594687654,\n",
499 " 'left': 0.019736842105263157,\n",
500 " 'since': 0.019613871126414165,\n",
501 " 'last': 0.01955238563698967,\n",
502 " 'young': 0.019367929168716182,\n",
503 " 'never': 0.0191424823741597,\n",
504 " 'several': 0.019019511395310707,\n",
505 " 'knows': 0.01893753074274471,\n",
506 " 'realizes': 0.018835054927037218,\n",
507 " 'reveals': 0.018650598458763733,\n",
508 " 'though': 0.018609608132480734,\n",
509 " 'well': 0.018425151664207245,\n",
510 " 'saying': 0.01836366617478275,\n",
511 " 'could': 0.018158714543367767,\n",
512 " 'returns': 0.018158714543367767,\n",
513 " 'soon': 0.018035743564518772,\n",
514 " 'appears': 0.017994753238235777,\n",
515 " 'tell': 0.017974258075094278,\n",
516 " 'sam': 0.017892277422528285,\n",
517 " 'walks': 0.017892277422528285,\n",
518 " 'meet': 0.017810296769962288,\n",
519 " 'hand': 0.017769306443679293,\n",
520 " 'stop': 0.017666830627971798,\n",
521 " 'orders': 0.0176463354648303,\n",
522 " 'run': 0.017605345138547304,\n",
523 " 'world': 0.017523364485981307,\n",
524 " 'everyone': 0.017441383833415314,\n",
525 " 'phone': 0.017441383833415314,\n",
526 " 'return': 0.01737989834399082,\n",
527 " 'something': 0.01735940318084932,\n",
528 " 'fire': 0.017154451549434332,\n",
529 " 'give': 0.01705197573372684,\n",
530 " 'together': 0.01705197573372684,\n",
531 " 'call': 0.01692900475487785,\n",
532 " 'place': 0.01692900475487785,\n",
533 " 'name': 0.01688801442859485,\n",
534 " 'much': 0.016847024102311856,\n",
535 " 'film': 0.01662157730775537,\n",
536 " 'mike': 0.01662157730775537,\n",
537 " 'able': 0.016601082144613873,\n",
538 " 'small': 0.016601082144613873,\n",
539 " 'meets': 0.016580586981472373,\n",
540 " 'school': 0.016498606328906377,\n",
541 " 'decides': 0.016457616002623382,\n",
542 " 'shoots': 0.016457616002623382,\n",
543 " 'friend': 0.016416625676340384,\n",
544 " 'friends': 0.016375635350057385,\n",
545 " 'love': 0.01633464502377439,\n",
546 " 'along': 0.016293654697491392,\n",
547 " 'leaving': 0.016252664371208394,\n",
548 " 'tony': 0.016252664371208394,\n",
549 " 'must': 0.0162116740449254,\n",
550 " 'end': 0.01590424659780292,\n",
551 " 'trying': 0.015678799803246435,\n",
552 " 'michael': 0.015637809476963437,\n",
553 " 'building': 0.01559681915068044,\n",
554 " 'front': 0.01559681915068044,\n",
555 " 'shot': 0.01559681915068044,\n",
556 " 'large': 0.015555828824397442,\n",
557 " 'apartment': 0.015535333661255944,\n",
558 " 'using': 0.015535333661255944,\n",
559 " 'killing': 0.015514838498114445,\n",
560 " 'dr': 0.01545335300868995,\n",
561 " 'refuses': 0.015412362682406953,\n",
562 " 'telling': 0.015330382029840958,\n",
563 " 'plan': 0.01528939170355796,\n",
564 " \"'ll\": 0.015207411050991966,\n",
565 " 'open': 0.015186915887850467,\n",
566 " 'black': 0.015125430398425972,\n",
567 " 'quickly': 0.015084440072142975,\n",
568 " 'look': 0.014961469093293983,\n",
569 " 'show': 0.014920478767010985,\n",
570 " 'ca': 0.014899983603869486,\n",
571 " 'agrees': 0.014879488440727989,\n",
572 " 'water': 0.014879488440727989,\n",
573 " 'use': 0.01483849811444499,\n",
574 " 'found': 0.014797507788161994,\n",
575 " 'looking': 0.014736022298737498,\n",
576 " 'taken': 0.014715527135595999,\n",
577 " 'set': 0.014695031972454501,\n",
578 " 'falls': 0.014633546483030006,\n",
579 " 'attempts': 0.01457206099360551,\n",
580 " 'marty': 0.01457206099360551,\n",
581 " 'called': 0.014531070667322512,\n",
582 " 'manages': 0.014510575504181012,\n",
583 " 'party': 0.01442859485161502,\n",
584 " 'right': 0.01442859485161502,\n",
585 " 'story': 0.01442859485161502,\n",
586 " 'across': 0.014326119035907525,\n",
587 " 'eventually': 0.014285128709624529,\n",
588 " 'attack': 0.014244138383341532,\n",
589 " 'scene': 0.014244138383341532,\n",
590 " 'town': 0.014203148057058534,\n",
591 " 'white': 0.014080177078209542,\n",
592 " 'david': 0.013936710936219052,\n",
593 " 'made': 0.013772749631087064,\n",
594 " 'daughter': 0.013731759304804067,\n",
595 " 'talk': 0.013731759304804067,\n",
596 " 'becomes': 0.013711264141662568,\n",
597 " 'side': 0.013711264141662568,\n",
598 " 'good': 0.013629283489096573,\n",
599 " 'others': 0.013629283489096573,\n",
600 " 'try': 0.013629283489096573,\n",
601 " 'crew': 0.013608788325955074,\n",
602 " 'little': 0.013608788325955074,\n",
603 " 'pulls': 0.013608788325955074,\n",
604 " 'getting': 0.013588293162813576,\n",
605 " 'opens': 0.013465322183964585,\n",
606 " 'job': 0.013424331857681587,\n",
607 " 'train': 0.013424331857681587,\n",
608 " 'max': 0.01338334153139859,\n",
609 " 'girl': 0.013342351205115593,\n",
610 " 'long': 0.013342351205115593,\n",
611 " 'taking': 0.013321856041974094,\n",
612 " 'bruce': 0.013280865715691098,\n",
613 " 'uses': 0.0132398753894081,\n",
614 " 'boy': 0.013198885063125103,\n",
615 " 'office': 0.013157894736842105,\n",
616 " 'arrive': 0.013116904410559108,\n",
617 " 'told': 0.013075914084276111,\n",
618 " 'keep': 0.013014428594851616,\n",
619 " 'joe': 0.01295294310542712,\n",
620 " 'kills': 0.012891457616002624,\n",
621 " 'without': 0.012891457616002624,\n",
622 " 'want': 0.012850467289719626,\n",
623 " 'window': 0.012850467289719626,\n",
624 " 'morning': 0.01278898180029513,\n",
625 " 'put': 0.01278898180029513,\n",
626 " 'grabs': 0.012727496310870634,\n",
627 " 'hotel': 0.012625020495163142,\n",
628 " 'children': 0.012604525332021643,\n",
629 " 'hands': 0.012584030168880144,\n",
630 " 'ray': 0.012584030168880144,\n",
631 " 'start': 0.012584030168880144,\n",
632 " 'become': 0.012563535005738646,\n",
633 " 'real': 0.01250204951631415,\n",
634 " 'order': 0.012461059190031152,\n",
635 " 'sarah': 0.012379078537465157,\n",
636 " 'bella': 0.012276602721757665,\n",
637 " 'war': 0.012256107558616166,\n",
638 " 'charlie': 0.01221511723233317,\n",
639 " 'instead': 0.01221511723233317,\n",
640 " 'making': 0.01219462206919167,\n",
641 " 'mr': 0.01219462206919167,\n",
642 " 'nick': 0.012174126906050173,\n",
643 " 'street': 0.012174126906050173,\n",
644 " 'edward': 0.012153631742908674,\n",
645 " 'let': 0.012153631742908674,\n",
646 " 'jay': 0.012092146253484178,\n",
647 " 'many': 0.012010165600918183,\n",
648 " 'upon': 0.011989670437776684,\n",
649 " 'seen': 0.011948680111493687,\n",
650 " 'blood': 0.01190768978521069,\n",
651 " 'baby': 0.011887194622069192,\n",
652 " 'including': 0.011825709132644696,\n",
653 " 'onto': 0.011825709132644696,\n",
654 " 'floor': 0.011743728480078701,\n",
655 " 'rest': 0.011661747827512708,\n",
656 " 'bond': 0.011641252664371209,\n",
657 " 'notices': 0.01162075750122971,\n",
658 " 'parents': 0.011600262338088212,\n",
659 " 'power': 0.011497786522380718,\n",
660 " 'seems': 0.011497786522380718,\n",
661 " 'watch': 0.011497786522380718,\n",
662 " 'someone': 0.011456796196097721,\n",
663 " 'bill': 0.011436301032956222,\n",
664 " 'stay': 0.011436301032956222,\n",
665 " 'despite': 0.011415805869814723,\n",
666 " 'begin': 0.011374815543531726,\n",
667 " 'four': 0.011354320380390227,\n",
668 " 'hospital': 0.011354320380390227,\n",
669 " 'needs': 0.011354320380390227,\n",
670 " 'offers': 0.011292834890965732,\n",
671 " 'truck': 0.011292834890965732,\n",
672 " 'breaks': 0.011272339727824234,\n",
673 " 'control': 0.011272339727824234,\n",
674 " 'ground': 0.011272339727824234,\n",
675 " 'ends': 0.011210854238399738,\n",
676 " 'part': 0.01116986391211674,\n",
677 " 'earth': 0.011149368748975241,\n",
678 " 'agent': 0.011128873585833744,\n",
679 " 'battle': 0.010964912280701754,\n",
680 " 'kay': 0.010944417117560256,\n",
681 " 'things': 0.010923921954418757,\n",
682 " 'thinks': 0.010923921954418757,\n",
683 " 'drives': 0.010903426791277258,\n",
684 " 'station': 0.01088293162813576,\n",
685 " 'continues': 0.010862436464994261,\n",
686 " 'brother': 0.010841941301852762,\n",
687 " 'prison': 0.010841941301852762,\n",
688 " 'voice': 0.010800950975569766,\n",
689 " 'alex': 0.010780455812428267,\n",
690 " 'immediately': 0.01075996064928677,\n",
691 " 'red': 0.01075996064928677,\n",
692 " 'plane': 0.01073946548614527,\n",
693 " 'soldiers': 0.010657484833579275,\n",
694 " 'shoot': 0.010555009017871783,\n",
695 " 'may': 0.010514018691588784,\n",
696 " 'officer': 0.010493523528447287,\n",
697 " 'drive': 0.010473028365305788,\n",
698 " 'meeting': 0.010452533202164289,\n",
699 " 'bed': 0.010411542875881292,\n",
700 " 'nearby': 0.010411542875881292,\n",
701 " 'working': 0.010411542875881292,\n",
702 " 'enough': 0.010391047712739793,\n",
703 " 'alone': 0.010329562223315297,\n",
704 " 'puts': 0.010329562223315297,\n",
705 " 'danny': 0.01016560091818331,\n",
706 " 'watches': 0.01016560091818331,\n",
707 " 'break': 0.010124610591900311,\n",
708 " 'turn': 0.010124610591900311,\n",
709 " 'days': 0.010104115428758813,\n",
710 " 'ben': 0.010083620265617314,\n",
711 " 'enters': 0.010042629939334318,\n",
712 " 'king': 0.010042629939334318,\n",
713 " 'point': 0.010042629939334318,\n",
714 " 'human': 0.01000163961305132,\n",
715 " 'need': 0.009940154123626824,\n",
716 " 'given': 0.009919658960485326,\n",
717 " 'captain': 0.009858173471060829,\n",
718 " 'everything': 0.009837678307919331,\n",
719 " 'past': 0.009837678307919331,\n",
720 " 'case': 0.009796687981636333,\n",
721 " 'used': 0.009776192818494836,\n",
722 " 'top': 0.009755697655353337,\n",
723 " 'alive': 0.009673717002787342,\n",
724 " 'movie': 0.009673717002787342,\n",
725 " 'walk': 0.009653221839645844,\n",
726 " 'army': 0.009632726676504345,\n",
727 " 'news': 0.009591736350221348,\n",
728 " 'discovers': 0.00957124118707985,\n",
729 " 'wall': 0.00957124118707985,\n",
730 " 'steve': 0.00955074602393835,\n",
731 " 'nothing': 0.009530250860796853,\n",
732 " 'arthur': 0.009509755697655354,\n",
733 " 'tom': 0.009489260534513854,\n",
734 " 'move': 0.009468765371372355,\n",
735 " 'really': 0.009427775045089359,\n",
736 " 'force': 0.00940727988194786,\n",
737 " 'learns': 0.00940727988194786,\n",
738 " 'second': 0.00940727988194786,\n",
739 " 'attempt': 0.009366289555664863,\n",
740 " 'guards': 0.009345794392523364,\n",
741 " 'towards': 0.009345794392523364,\n",
742 " 'game': 0.009284308903098868,\n",
743 " 'save': 0.009284308903098868,\n",
744 " 'causing': 0.009181833087391376,\n",
745 " '$': 0.00912034759796688,\n",
746 " 'bar': 0.00912034759796688,\n",
747 " 'james': 0.00912034759796688,\n",
748 " 'earlier': 0.00909985243482538,\n",
749 " 'following': 0.00909985243482538,\n",
750 " 'near': 0.009058862108542384,\n",
751 " 'high': 0.009017871782259386,\n",
752 " 'live': 0.009017871782259386,\n",
753 " 'sent': 0.009017871782259386,\n",
754 " 'close': 0.008997376619117889,\n",
755 " 'claims': 0.00895638629283489,\n",
756 " 'paul': 0.008935891129693393,\n",
757 " 'carl': 0.008915395966551894,\n",
758 " 'gone': 0.008894900803410394,\n",
759 " 'suggests': 0.008894900803410394,\n",
760 " 'van': 0.008894900803410394,\n",
761 " 'alien': 0.008812920150844401,\n",
762 " 'throws': 0.008792424987702902,\n",
763 " 'anna': 0.008771929824561403,\n",
764 " 'coming': 0.008771929824561403,\n",
765 " 'bring': 0.008751434661419906,\n",
766 " 'information': 0.008751434661419906,\n",
767 " 'company': 0.008710444335136907,\n",
768 " 'cut': 0.00868994917199541,\n",
769 " 'guy': 0.00868994917199541,\n",
770 " 'patrick': 0.00868994917199541,\n",
771 " 'stops': 0.00868994917199541,\n",
772 " 'lives': 0.00866945400885391,\n",
773 " 'already': 0.008648958845712412,\n",
774 " 'best': 0.008648958845712412,\n",
775 " 'waiting': 0.008648958845712412,\n",
776 " 'anything': 0.008628463682570914,\n",
777 " 'every': 0.008628463682570914,\n",
778 " 'mission': 0.008587473356287916,\n",
779 " 'seeing': 0.008587473356287916,\n",
780 " 'demands': 0.008566978193146417,\n",
781 " 'final': 0.008566978193146417,\n",
782 " 'leads': 0.008566978193146417,\n",
783 " 'local': 0.008566978193146417,\n",
784 " 'book': 0.00854648303000492,\n",
785 " \"'d\": 0.00852598786686342,\n",
786 " 'got': 0.00852598786686342,\n",
787 " 'hit': 0.008484997540580424,\n",
788 " 'actually': 0.008464502377438924,\n",
789 " 'kevin': 0.008444007214297425,\n",
790 " 'members': 0.008444007214297425,\n",
791 " 'wakes': 0.008423512051155928,\n",
792 " 'brings': 0.008403016888014429,\n",
793 " 'die': 0.00838252172487293,\n",
794 " 'moment': 0.00838252172487293,\n",
795 " 'number': 0.00838252172487293,\n",
796 " 'free': 0.008362026561731432,\n",
797 " 'happy': 0.008362026561731432,\n",
798 " 'security': 0.008362026561731432,\n",
799 " 'sends': 0.008362026561731432,\n",
800 " 'hears': 0.008341531398589933,\n",
801 " 'sex': 0.008321036235448434,\n",
802 " 'child': 0.008300541072306936,\n",
803 " 'forces': 0.008300541072306936,\n",
804 " 'running': 0.008300541072306936,\n",
805 " 'gang': 0.008259550746023938,\n",
806 " 'johnny': 0.008259550746023938,\n",
807 " 'bank': 0.008198065256599442,\n",
808 " 'due': 0.008198065256599442,\n",
809 " 'dog': 0.008177570093457943,\n",
810 " 'living': 0.008177570093457943,\n",
811 " 'york': 0.008177570093457943,\n",
812 " 'follows': 0.008136579767174947,\n",
813 " 'play': 0.008136579767174947,\n",
814 " 'secret': 0.008136579767174947,\n",
815 " 'lost': 0.00809558944089195,\n",
816 " 'sister': 0.00809558944089195,\n",
817 " 'island': 0.00807509427775045,\n",
818 " 'wo': 0.00807509427775045,\n",
819 " 'plans': 0.008054599114608952,\n",
820 " 'believe': 0.008034103951467454,\n",
821 " 'say': 0.008034103951467454,\n",
822 " 'join': 0.008013608788325955,\n",
823 " 'believes': 0.007993113625184456,\n",
824 " 'machine': 0.007972618462042958,\n",
825 " 'ever': 0.00795212329890146,\n",
826 " 'george': 0.00793162813575996,\n",
827 " 'almost': 0.007911132972618463,\n",
828 " 'happened': 0.007911132972618463,\n",
829 " 'talking': 0.007911132972618463,\n",
830 " 'although': 0.007890637809476964,\n",
831 " 'arm': 0.007890637809476964,\n",
832 " 'continue': 0.007890637809476964,\n",
833 " 'doc': 0.007890637809476964,\n",
834 " 'full': 0.007890637809476964,\n",
835 " 'jake': 0.007890637809476964,\n",
836 " 'eyes': 0.007870142646335464,\n",
837 " 'heads': 0.007870142646335464,\n",
838 " 'store': 0.007870142646335464,\n",
839 " 'points': 0.007849647483193967,\n",
840 " 'cell': 0.007808657156910969,\n",
841 " 'admits': 0.00778816199376947,\n",
842 " 'area': 0.007767666830627972,\n",
843 " 'alan': 0.007747171667486473,\n",
844 " 'watching': 0.007747171667486473,\n",
845 " 'chris': 0.007706181341203476,\n",
846 " 'toward': 0.007685686178061977,\n",
847 " 'walking': 0.007685686178061977,\n",
848 " 'hear': 0.007665191014920479,\n",
849 " 'rocky': 0.007665191014920479,\n",
850 " 'asking': 0.00764469585177898,\n",
851 " 'attacks': 0.0076242006886374815,\n",
852 " 'business': 0.007603705525495983,\n",
853 " 'suit': 0.007583210362354484,\n",
854 " 'chase': 0.007562715199212986,\n",
855 " 'dinner': 0.0075422200360714875,\n",
856 " 'jimmy': 0.0075422200360714875,\n",
857 " 'ready': 0.0075422200360714875,\n",
858 " 'big': 0.00750122970978849,\n",
859 " 'holding': 0.007480734546646992,\n",
860 " 'jacob': 0.007480734546646992,\n",
861 " 'bridge': 0.007460239383505493,\n",
862 " 'light': 0.007460239383505493,\n",
863 " 'missing': 0.007460239383505493,\n",
864 " 'bomb': 0.007439744220363994,\n",
865 " 'jumps': 0.007439744220363994,\n",
866 " 'escapes': 0.007419249057222495,\n",
867 " 'died': 0.007398753894080997,\n",
868 " 'brought': 0.0073782587309394985,\n",
869 " 'air': 0.007357763567797999,\n",
870 " 'driver': 0.007357763567797999,\n",
871 " 'jim': 0.007357763567797999,\n",
872 " 'women': 0.007357763567797999,\n",
873 " 'heart': 0.007337268404656501,\n",
874 " 'informs': 0.007337268404656501,\n",
875 " 'safe': 0.007337268404656501,\n",
876 " 'unable': 0.007337268404656501,\n",
877 " 'fall': 0.007316773241515003,\n",
878 " 'guard': 0.007316773241515003,\n",
879 " 'creature': 0.007275782915232005,\n",
880 " 'giving': 0.007275782915232005,\n",
881 " 'replies': 0.007275782915232005,\n",
882 " 'bad': 0.007255287752090506,\n",
883 " 'person': 0.007234792588949008,\n",
884 " 'better': 0.00721429742580751,\n",
885 " 'board': 0.00721429742580751,\n",
886 " 'talks': 0.00721429742580751,\n",
887 " 'done': 0.0071938022626660105,\n",
888 " 'former': 0.0071938022626660105,\n",
889 " 'andy': 0.007173307099524512,\n",
890 " 'eddie': 0.007173307099524512,\n",
891 " 'neo': 0.007173307099524512,\n",
892 " 'relationship': 0.007173307099524512,\n",
893 " 'hits': 0.007152811936383014,\n",
894 " 'kids': 0.007152811936383014,\n",
895 " 'forced': 0.007132316773241515,\n",
896 " 'robert': 0.007132316773241515,\n",
897 " 'line': 0.0071118216101000165,\n",
898 " 'sits': 0.0071118216101000165,\n",
899 " 'confronts': 0.007091326446958518,\n",
900 " 'planet': 0.007091326446958518,\n",
901 " 'idea': 0.007070831283817019,\n",
902 " 'six': 0.007070831283817019,\n",
903 " 'else': 0.007050336120675521,\n",
904 " 'entire': 0.007050336120675521,\n",
905 " 'holds': 0.007050336120675521,\n",
906 " 'humans': 0.007050336120675521,\n",
907 " 'luke': 0.007050336120675521,\n",
908 " 'officers': 0.007050336120675521,\n",
909 " 'helen': 0.0070298409575340216,\n",
910 " 'daniel': 0.007009345794392523,\n",
911 " 'learn': 0.007009345794392523,\n",
912 " 'true': 0.007009345794392523,\n",
913 " 'year': 0.007009345794392523,\n",
914 " 'base': 0.006968355468109526,\n",
915 " 'rose': 0.006968355468109526,\n",
916 " 'states': 0.006968355468109526,\n",
917 " 'deal': 0.0069478603049680275,\n",
918 " 'enter': 0.0069478603049680275,\n",
919 " 'five': 0.0069478603049680275,\n",
920 " 'message': 0.006927365141826529,\n",
921 " 'playing': 0.006927365141826529,\n",
922 " 'table': 0.006927365141826529,\n",
923 " 'approaches': 0.00690686997868503,\n",
924 " 'knowing': 0.00690686997868503,\n",
925 " 'fires': 0.006886374815543532,\n",
926 " 'think': 0.006886374815543532,\n",
927 " 'brian': 0.006845384489260534,\n",
928 " 'food': 0.006845384489260534,\n",
929 " 'boat': 0.006824889326119036,\n",
930 " 'dies': 0.006824889326119036,\n",
931 " 'anyone': 0.006804394162977537,\n",
932 " 'walter': 0.006804394162977537,\n",
933 " 'ask': 0.006783898999836039,\n",
934 " 'box': 0.006783898999836039,\n",
935 " 'finding': 0.006783898999836039,\n",
936 " 'future': 0.00676340383669454,\n",
937 " 'evening': 0.006742908673553041,\n",
938 " 'hold': 0.006742908673553041,\n",
939 " 'jordan': 0.006742908673553041,\n",
940 " 'sitting': 0.006742908673553041,\n",
941 " 'glass': 0.006722413510411543,\n",
942 " 'president': 0.006722413510411543,\n",
943 " 'times': 0.006722413510411543,\n",
944 " 'feels': 0.006701918347270045,\n",
945 " 'late': 0.006701918347270045,\n",
946 " 'alice': 0.0066814231841285454,\n",
947 " 'mary': 0.0066814231841285454,\n",
948 " 'thing': 0.0066814231841285454,\n",
949 " 'destroy': 0.006660928020987047,\n",
950 " 'driving': 0.006660928020987047,\n",
951 " 'follow': 0.006660928020987047,\n",
952 " 'visit': 0.006660928020987047,\n",
953 " 'doctor': 0.006640432857845549,\n",
954 " 'shooting': 0.00661993769470405,\n",
955 " 'might': 0.006599442531562551,\n",
956 " 'ripley': 0.006599442531562551,\n",
957 " 'boss': 0.006578947368421052,\n",
958 " 'camera': 0.006578947368421052,\n",
959 " 'remaining': 0.006558452205279554,\n",
960 " 'upset': 0.006558452205279554,\n",
961 " 'husband': 0.006537957042138056,\n",
962 " 'pistol': 0.006537957042138056,\n",
963 " 'whole': 0.006537957042138056,\n",
964 " 'archer': 0.0065174618789965565,\n",
965 " 'batman': 0.0065174618789965565,\n",
966 " 'works': 0.0065174618789965565,\n",
967 " 'agents': 0.006496966715855058,\n",
968 " 'fact': 0.006496966715855058,\n",
969 " 'system': 0.006496966715855058,\n",
970 " 'lead': 0.00647647155271356,\n",
971 " 'lincoln': 0.00647647155271356,\n",
972 " 'logan': 0.00647647155271356,\n",
973 " 'road': 0.00647647155271356,\n",
974 " 'murder': 0.006455976389572061,\n",
975 " 'insists': 0.0064354812264305625,\n",
976 " 'lot': 0.0064354812264305625,\n",
977 " 'rushes': 0.0064354812264305625,\n",
978 " 'search': 0.0064354812264305625,\n",
979 " 'known': 0.006414986063289063,\n",
980 " 'great': 0.006394490900147565,\n",
981 " 'helicopter': 0.006394490900147565,\n",
982 " 'saw': 0.006373995737006067,\n",
983 " 'leader': 0.006353500573864568,\n",
984 " 'dark': 0.006333005410723069,\n",
985 " 'kiss': 0.006333005410723069,\n",
986 " 'apparently': 0.006312510247581571,\n",
987 " 'led': 0.006292015084440072,\n",
988 " 'ring': 0.006292015084440072,\n",
989 " 'always': 0.006271519921298574,\n",
990 " 'far': 0.006271519921298574,\n",
991 " 'girls': 0.006271519921298574,\n",
992 " 'restaurant': 0.006271519921298574,\n",
993 " 'sets': 0.006271519921298574,\n",
994 " 'teddy': 0.006271519921298574,\n",
995 " 'form': 0.006251024758157075,\n",
996 " 'general': 0.006251024758157075,\n",
997 " 'angry': 0.006230529595015576,\n",
998 " 'mind': 0.006210034431874078,\n",
999 " 'present': 0.006210034431874078,\n",
1000 " 'causes': 0.006189539268732579,\n",
1001 " 'hiding': 0.006189539268732579,\n",
1002 " 'crowd': 0.00616904410559108,\n",
1003 " 'decide': 0.00616904410559108,\n",
1004 " 'rescue': 0.00616904410559108,\n",
1005 " 'within': 0.00616904410559108,\n",
1006 " 'care': 0.006128053779308083,\n",
1007 " 'video': 0.006128053779308083,\n",
1008 " 'blue': 0.006107558616166585,\n",
1009 " 'met': 0.006107558616166585,\n",
1010 " 'said': 0.006107558616166585,\n",
1011 " 'steps': 0.006087063453025086,\n",
1012 " 'conversation': 0.006066568289883587,\n",
1013 " 'henry': 0.006066568289883587,\n",
1014 " 'location': 0.006066568289883587,\n",
1015 " 'rachel': 0.006066568289883587,\n",
1016 " 'went': 0.006066568289883587,\n",
1017 " 'drops': 0.006046073126742089,\n",
1018 " 'flies': 0.006046073126742089,\n",
1019 " 'matt': 0.006046073126742089,\n",
1020 " 'roof': 0.006046073126742089,\n",
1021 " 'catches': 0.006025577963600591,\n",
1022 " 'warns': 0.006025577963600591,\n",
1023 " \"'ve\": 0.0060050828004590915,\n",
1024 " 'camp': 0.0060050828004590915,\n",
1025 " 'revealed': 0.0060050828004590915,\n",
1026 " 'tree': 0.0060050828004590915,\n",
1027 " 'wearing': 0.005984587637317593,\n",
1028 " 'standing': 0.005964092474176094,\n",
1029 " 'attacked': 0.005943597311034596,\n",
1030 " 'holmes': 0.005943597311034596,\n",
1031 " 'lee': 0.005943597311034596,\n",
1032 " 'passes': 0.0059231021478930975,\n",
1033 " 'pull': 0.005902606984751598,\n",
1034 " 'couple': 0.0058821118216101,\n",
1035 " 'cover': 0.0058821118216101,\n",
1036 " 'sleep': 0.0058821118216101,\n",
1037 " 'billy': 0.005861616658468602,\n",
1038 " 'weapons': 0.005861616658468602,\n",
1039 " 'destroyed': 0.005841121495327103,\n",
1040 " 'knife': 0.005841121495327103,\n",
1041 " 'knocks': 0.005841121495327103,\n",
1042 " 'powers': 0.005841121495327103,\n",
1043 " 'castle': 0.005820626332185604,\n",
1044 " 'church': 0.005820626332185604,\n",
1045 " 'space': 0.005800131169044106,\n",
1046 " 'strange': 0.005800131169044106,\n",
1047 " 'william': 0.005800131169044106,\n",
1048 " 'dance': 0.005779636005902607,\n",
1049 " 'leading': 0.005779636005902607,\n",
1050 " 'thomas': 0.005779636005902607,\n",
1051 " 'woody': 0.005779636005902607,\n",
1052 " 'bathroom': 0.0057591408427611086,\n",
1053 " 'eye': 0.0057591408427611086,\n",
1054 " 'computer': 0.005738645679619609,\n",
1055 " 'discover': 0.005738645679619609,\n",
1056 " 'tommy': 0.005738645679619609,\n",
1057 " '&': 0.005718150516478111,\n",
1058 " 'military': 0.005718150516478111,\n",
1059 " 'stone': 0.005718150516478111,\n",
1060 " 'wanted': 0.005718150516478111,\n",
1061 " 'calling': 0.005697655353336613,\n",
1062 " 'change': 0.005697655353336613,\n",
1063 " 'god': 0.005697655353336613,\n",
1064 " 'scott': 0.005697655353336613,\n",
1065 " 'broken': 0.005677160190195114,\n",
1066 " 'captured': 0.005677160190195114,\n",
1067 " 'date': 0.005677160190195114,\n",
1068 " 'took': 0.005677160190195114,\n",
1069 " 'reaches': 0.005656665027053615,\n",
1070 " 'river': 0.005656665027053615,\n",
1071 " 'chest': 0.005636169863912117,\n",
1072 " 'figure': 0.005636169863912117,\n",
1073 " 'months': 0.005636169863912117,\n",
1074 " 'nearly': 0.005636169863912117,\n",
1075 " 'remains': 0.005615674700770618,\n",
1076 " 'lou': 0.00559517953762912,\n",
1077 " 'fly': 0.0055746843744876205,\n",
1078 " 'boys': 0.005554189211346122,\n",
1079 " 'middle': 0.005554189211346122,\n",
1080 " 'terminator': 0.005554189211346122,\n",
1081 " 'tv': 0.005554189211346122,\n",
1082 " 'attention': 0.005533694048204624,\n",
1083 " 'picks': 0.005533694048204624,\n",
1084 " 'ride': 0.005533694048204624,\n",
1085 " 'thinking': 0.005533694048204624,\n",
1086 " 'tower': 0.005533694048204624,\n",
1087 " 'chance': 0.005513198885063125,\n",
1088 " 'dave': 0.005513198885063125,\n",
1089 " 'doug': 0.005513198885063125,\n",
1090 " 'hidden': 0.005513198885063125,\n",
1091 " 'reach': 0.005513198885063125,\n",
1092 " 'speak': 0.005513198885063125,\n",
1093 " 'kate': 0.0054927037219216265,\n",
1094 " 'land': 0.0054927037219216265,\n",
1095 " 'pay': 0.0054927037219216265,\n",
1096 " 'wedding': 0.0054927037219216265,\n",
1097 " 'caught': 0.005472208558780128,\n",
1098 " 'stands': 0.005472208558780128,\n",
1099 " 'bus': 0.005451713395638629,\n",
1100 " 'forest': 0.005451713395638629,\n",
1101 " 'moves': 0.005451713395638629,\n",
1102 " 'race': 0.005451713395638629,\n",
1103 " 'rather': 0.005451713395638629,\n",
1104 " 'revealing': 0.005451713395638629,\n",
1105 " 'us': 0.005451713395638629,\n",
1106 " 'came': 0.005431218232497131,\n",
1107 " 'contact': 0.005431218232497131,\n",
1108 " 'mentions': 0.005431218232497131,\n",
1109 " 'realize': 0.005431218232497131,\n",
1110 " 'realizing': 0.005431218232497131,\n",
1111 " 'smith': 0.005431218232497131,\n",
1112 " 'jane': 0.0054107230693556324,\n",
1113 " 'convinces': 0.005390227906214133,\n",
1114 " 'jones': 0.005390227906214133,\n",
1115 " 'crash': 0.0053287424167896376,\n",
1116 " 'fighting': 0.0053287424167896376,\n",
1117 " 'stand': 0.0053287424167896376,\n",
1118 " 'heard': 0.005308247253648139,\n",
1119 " 'key': 0.005308247253648139,\n",
1120 " 'minutes': 0.005308247253648139,\n",
1121 " 'park': 0.005308247253648139,\n",
1122 " 'ron': 0.005308247253648139,\n",
1123 " 'short': 0.005308247253648139,\n",
1124 " 'lets': 0.00528775209050664,\n",
1125 " 'sure': 0.00528775209050664,\n",
1126 " 'village': 0.00528775209050664,\n",
1127 " 'keeps': 0.005267256927365142,\n",
1128 " 'slowly': 0.005267256927365142,\n",
1129 " 'drug': 0.0052467617642236435,\n",
1130 " 'exchange': 0.0052467617642236435,\n",
1131 " 'lands': 0.0052467617642236435,\n",
1132 " 'situation': 0.0052467617642236435,\n",
1133 " 'tank': 0.0052467617642236435,\n",
1134 " 'wrong': 0.005226266601082144,\n",
1135 " 'flying': 0.005205771437940646,\n",
1136 " 'mcclane': 0.005205771437940646,\n",
1137 " 'neck': 0.005205771437940646,\n",
1138 " 'questions': 0.005205771437940646,\n",
1139 " 'dream': 0.005185276274799148,\n",
1140 " 'elevator': 0.005185276274799148,\n",
1141 " 'threatens': 0.005164781111657649,\n",
1142 " 'american': 0.00514428594851615,\n",
1143 " 'cross': 0.00514428594851615,\n",
1144 " 'picture': 0.00514428594851615,\n",
1145 " 'reveal': 0.00514428594851615,\n",
1146 " 'richard': 0.00514428594851615,\n",
1147 " 'storm': 0.00514428594851615,\n",
1148 " 'weapon': 0.00514428594851615,\n",
1149 " 'check': 0.005123790785374651,\n",
1150 " 'field': 0.005123790785374651,\n",
1151 " 'hearing': 0.005103295622233153,\n",
1152 " 'completely': 0.005082800459091655,\n",
1153 " 'pick': 0.005082800459091655,\n",
1154 " 'sophie': 0.005082800459091655,\n",
1155 " 'beast': 0.0050623052959501555,\n",
1156 " 'giant': 0.0050623052959501555,\n",
1157 " 'jon': 0.0050623052959501555,\n",
1158 " 'note': 0.0050623052959501555,\n",
1159 " 'shown': 0.0050623052959501555,\n",
1160 " 'woods': 0.0050623052959501555,\n",
1161 " 'appear': 0.005041810132808657,\n",
1162 " 'arms': 0.005041810132808657,\n",
1163 " 'evidence': 0.005041810132808657,\n",
1164 " 'hide': 0.005041810132808657,\n",
1165 " 'cars': 0.005021314969667159,\n",
1166 " 'band': 0.0049803246433841614,\n",
1167 " 'girlfriend': 0.0049803246433841614,\n",
1168 " 'huge': 0.0049803246433841614,\n",
1169 " 'mark': 0.0049803246433841614,\n",
1170 " 'visits': 0.0049803246433841614,\n",
1171 " 'ago': 0.004959829480242663,\n",
1172 " 'airport': 0.004959829480242663,\n",
1173 " 'bag': 0.004959829480242663,\n",
1174 " 'clear': 0.004959829480242663,\n",
1175 " 'act': 0.004939334317101164,\n",
1176 " 'opening': 0.004939334317101164,\n",
1177 " 'lights': 0.004918839153959666,\n",
1178 " 'shop': 0.004918839153959666,\n",
1179 " 'different': 0.0048983439908181665,\n",
1180 " 'dying': 0.0048983439908181665,\n",
1181 " 'hours': 0.0048983439908181665,\n",
1182 " 'longer': 0.0048983439908181665,\n",
1183 " 'castor': 0.004877848827676668,\n",
1184 " 'facility': 0.004877848827676668,\n",
1185 " 'married': 0.004877848827676668,\n",
1186 " 'report': 0.004877848827676668,\n",
1187 " 'rock': 0.004877848827676668,\n",
1188 " 'send': 0.004877848827676668,\n",
1189 " 'surprised': 0.004877848827676668,\n",
1190 " 'larry': 0.00485735366453517,\n",
1191 " 'protect': 0.00485735366453517,\n",
1192 " 'accidentally': 0.004836858501393671,\n",
1193 " 'annie': 0.004836858501393671,\n",
1194 " 'truth': 0.004836858501393671,\n",
1195 " 'yet': 0.004836858501393671,\n",
1196 " 'carrying': 0.0048163633382521725,\n",
1197 " 'drink': 0.0048163633382521725,\n",
1198 " 'lucy': 0.0048163633382521725,\n",
1199 " 'pass': 0.0048163633382521725,\n",
1200 " 'spots': 0.0048163633382521725,\n",
1201 " 'dom': 0.004775373011969175,\n",
1202 " 'previous': 0.004775373011969175,\n",
1203 " 'queen': 0.004775373011969175,\n",
1204 " 'state': 0.004775373011969175,\n",
1205 " 'sword': 0.004775373011969175,\n",
1206 " 'wounded': 0.004775373011969175,\n",
1207 " 'radio': 0.004754877848827677,\n",
1208 " 'wait': 0.004754877848827677,\n",
1209 " 'club': 0.004734382685686178,\n",
1210 " 'gave': 0.004734382685686178,\n",
1211 " 'hard': 0.004734382685686178,\n",
1212 " 'loves': 0.004734382685686178,\n",
1213 " 'star': 0.004734382685686178,\n",
1214 " 'among': 0.004713887522544679,\n",
1215 " 'guys': 0.004713887522544679,\n",
1216 " 'leg': 0.004713887522544679,\n",
1217 " 'memory': 0.004713887522544679,\n",
1218 " 'miles': 0.004713887522544679,\n",
1219 " 'hole': 0.004693392359403181,\n",
1220 " 'piece': 0.004693392359403181,\n",
1221 " 'san': 0.004693392359403181,\n",
1222 " 'snow': 0.004693392359403181,\n",
1223 " 'green': 0.004672897196261682,\n",
1224 " 'half': 0.004672897196261682,\n",
1225 " 'held': 0.004672897196261682,\n",
1226 " 'main': 0.004672897196261682,\n",
1227 " 'responds': 0.004672897196261682,\n",
1228 " 'shocked': 0.004672897196261682,\n",
1229 " 'cops': 0.004652402033120184,\n",
1230 " 'moving': 0.004652402033120184,\n",
1231 " 'music': 0.004652402033120184,\n",
1232 " 'neil': 0.004652402033120184,\n",
1233 " 'soldier': 0.004652402033120184,\n",
1234 " 'suicide': 0.004652402033120184,\n",
1235 " 'device': 0.004631906869978685,\n",
1236 " 'andrew': 0.004611411706837186,\n",
1237 " 'reason': 0.004611411706837186,\n",
1238 " 'receives': 0.004611411706837186,\n",
1239 " 'screams': 0.004611411706837186,\n",
1240 " 'showing': 0.004611411706837186,\n",
1241 " 'bedroom': 0.004590916543695688,\n",
1242 " 'charles': 0.004590916543695688,\n",
1243 " 'mrs': 0.004590916543695688,\n",
1244 " 'thought': 0.004590916543695688,\n",
1245 " 'arrest': 0.00457042138055419,\n",
1246 " 'catch': 0.00457042138055419,\n",
1247 " 'gordon': 0.00457042138055419,\n",
1248 " 'recognizes': 0.00457042138055419,\n",
1249 " 'simply': 0.00457042138055419,\n",
1250 " 'song': 0.00457042138055419,\n",
1251 " 'word': 0.00457042138055419,\n",
1252 " 'adam': 0.00454992621741269,\n",
1253 " 'benjamin': 0.00454992621741269,\n",
1254 " 'cop': 0.00454992621741269,\n",
1255 " 'empty': 0.00454992621741269,\n",
1256 " 'han': 0.00454992621741269,\n",
1257 " 'jerry': 0.00454992621741269,\n",
1258 " 'ryan': 0.00454992621741269,\n",
1259 " 'safety': 0.00454992621741269,\n",
1260 " 'arrested': 0.004529431054271192,\n",
1261 " 'convince': 0.004529431054271192,\n",
1262 " 'letter': 0.004529431054271192,\n",
1263 " 'norris': 0.004529431054271192,\n",
1264 " 'private': 0.004529431054271192,\n",
1265 " 'promises': 0.004529431054271192,\n",
1266 " 'duke': 0.004508935891129693,\n",
1267 " 'hair': 0.004508935891129693,\n",
1268 " 'public': 0.004508935891129693,\n",
1269 " 'test': 0.004508935891129693,\n",
1270 " 'cooper': 0.004488440727988195,\n",
1271 " 'crime': 0.004488440727988195,\n",
1272 " 'plays': 0.004488440727988195,\n",
1273 " 'read': 0.004488440727988195,\n",
1274 " 'whose': 0.004488440727988195,\n",
1275 " 'answers': 0.004467945564846696,\n",
1276 " 'fbi': 0.004467945564846696,\n",
1277 " 'fear': 0.004467945564846696,\n",
1278 " 'helps': 0.004467945564846696,\n",
1279 " 'katniss': 0.004467945564846696,\n",
1280 " 'kim': 0.004467945564846696,\n",
1281 " 'means': 0.004467945564846696,\n",
1282 " 'sign': 0.004467945564846696,\n",
1283 " 'feet': 0.004447450401705197,\n",
1284 " 'flashback': 0.004447450401705197,\n",
1285 " 'flight': 0.004447450401705197,\n",
1286 " 'hope': 0.004447450401705197,\n",
1287 " 'prepares': 0.004447450401705197,\n",
1288 " 'clearly': 0.004426955238563699,\n",
1289 " 'guns': 0.004426955238563699,\n",
1290 " 'invites': 0.004426955238563699,\n",
1291 " 'ken': 0.004426955238563699,\n",
1292 " 'words': 0.004426955238563699,\n",
1293 " 'brothers': 0.004406460075422201,\n",
1294 " 'places': 0.004406460075422201,\n",
1295 " 'asked': 0.0043859649122807015,\n",
1296 " 'bob': 0.0043859649122807015,\n",
1297 " 'chief': 0.0043859649122807015,\n",
1298 " 'doors': 0.0043859649122807015,\n",
1299 " 'events': 0.0043859649122807015,\n",
1300 " 'ice': 0.0043859649122807015,\n",
1301 " 'jean': 0.0043859649122807015,\n",
1302 " 'pair': 0.0043859649122807015,\n",
1303 " 'thanks': 0.0043859649122807015,\n",
1304 " 'training': 0.0043859649122807015,\n",
1305 " 'travel': 0.0043859649122807015,\n",
1306 " 'cuts': 0.004365469749139203,\n",
1307 " 'explain': 0.004344974585997705,\n",
1308 " 'million': 0.004344974585997705,\n",
1309 " 'beach': 0.004324479422856206,\n",
1310 " 'gas': 0.004324479422856206,\n",
1311 " 'partner': 0.004324479422856206,\n",
1312 " 'shrek': 0.004324479422856206,\n",
1313 " 'fights': 0.0043039842597147075,\n",
1314 " 'forward': 0.0043039842597147075,\n",
1315 " 'horse': 0.0043039842597147075,\n",
1316 " 'moments': 0.0043039842597147075,\n",
1317 " 'stephen': 0.0043039842597147075,\n",
1318 " 'fox': 0.004283489096573208,\n",
1319 " 'share': 0.004283489096573208,\n",
1320 " 'speaks': 0.004283489096573208,\n",
1321 " 'bourne': 0.00426299393343171,\n",
1322 " 'chair': 0.00426299393343171,\n",
1323 " 'track': 0.00426299393343171,\n",
1324 " 'carter': 0.004242498770290212,\n",
1325 " 'murphy': 0.004242498770290212,\n",
1326 " 'rifle': 0.004242498770290212,\n",
1327 " 'bit': 0.004222003607148713,\n",
1328 " 'class': 0.004222003607148713,\n",
1329 " 'german': 0.004222003607148713,\n",
1330 " 'introduces': 0.004222003607148713,\n",
1331 " 'member': 0.004222003607148713,\n",
1332 " 'buy': 0.004201508444007214,\n",
1333 " 'christian': 0.004201508444007214,\n",
1334 " 'jesse': 0.004201508444007214,\n",
1335 " 'lying': 0.004201508444007214,\n",
1336 " 'notes': 0.004201508444007214,\n",
1337 " 'returning': 0.004201508444007214,\n",
1338 " 'richie': 0.004201508444007214,\n",
1339 " 'streets': 0.004201508444007214,\n",
1340 " 'assures': 0.004181013280865716,\n",
1341 " 'caesar': 0.004181013280865716,\n",
1342 " 'command': 0.004181013280865716,\n",
1343 " 'stage': 0.004181013280865716,\n",
1344 " 'lord': 0.004160518117724217,\n",
1345 " 'pilot': 0.004160518117724217,\n",
1346 " 'allow': 0.004140022954582719,\n",
1347 " 'happens': 0.004140022954582719,\n",
1348 " 'joins': 0.004140022954582719,\n",
1349 " 'older': 0.004140022954582719,\n",
1350 " 'process': 0.004140022954582719,\n",
1351 " 'series': 0.004140022954582719,\n",
1352 " 'special': 0.004140022954582719,\n",
1353 " 'spot': 0.004140022954582719,\n",
1354 " 'staff': 0.004140022954582719,\n",
1355 " 'mask': 0.00411952779144122,\n",
1356 " 'position': 0.00411952779144122,\n",
1357 " 'robin': 0.00411952779144122,\n",
1358 " 'shortly': 0.00411952779144122,\n",
1359 " 'trip': 0.00411952779144122,\n",
1360 " 'abandoned': 0.004099032628299721,\n",
1361 " 'allows': 0.004099032628299721,\n",
1362 " 'crashes': 0.004099032628299721,\n",
1363 " 'mouth': 0.004099032628299721,\n",
1364 " 'pain': 0.004099032628299721,\n",
1365 " 'turned': 0.004099032628299721,\n",
1366 " 'claiming': 0.004078537465158223,\n",
1367 " 'discuss': 0.004078537465158223,\n",
1368 " 'steal': 0.004078537465158223,\n",
1369 " 'country': 0.004058042302016724,\n",
1370 " 'government': 0.004058042302016724,\n",
1371 " 'kind': 0.004058042302016724,\n",
1372 " 'london': 0.004058042302016724,\n",
1373 " 'miller': 0.004058042302016724,\n",
1374 " 'reads': 0.004058042302016724,\n",
1375 " 'sending': 0.004058042302016724,\n",
1376 " 'whether': 0.004058042302016724,\n",
1377 " 'joker': 0.004037547138875225,\n",
1378 " 'judy': 0.004037547138875225,\n",
1379 " 'manage': 0.004037547138875225,\n",
1380 " 'nina': 0.004037547138875225,\n",
1381 " 'apologizes': 0.004017051975733727,\n",
1382 " 'blade': 0.004017051975733727,\n",
1383 " 'breaking': 0.004017051975733727,\n",
1384 " 'killer': 0.004017051975733727,\n",
1385 " 'angrily': 0.003996556812592228,\n",
1386 " 'bullet': 0.003996556812592228,\n",
1387 " 'flee': 0.003996556812592228,\n",
1388 " 'furious': 0.003996556812592228,\n",
1389 " 'center': 0.00397606164945073,\n",
1390 " 'ethan': 0.00397606164945073,\n",
1391 " 'eve': 0.00397606164945073,\n",
1392 " 'evil': 0.00397606164945073,\n",
1393 " 'knew': 0.00397606164945073,\n",
1394 " 'major': 0.00397606164945073,\n",
1395 " 'offer': 0.00397606164945073,\n",
1396 " 'tunnel': 0.00397606164945073,\n",
1397 " ...}"
1398 ]
1399 },
1400 "execution_count": 88,
1401 "metadata": {},
1402 "output_type": "execute_result"
1403 }
1404 ],
1405 "source": [
1406 "find_most_probable('subconcious')"
1407 ]
1408 },
1409 {
1410 "cell_type": "code",
1411 "execution_count": null,
1412 "id": "737c55ac",
1413 "metadata": {},
1414 "outputs": [],
1415 "source": []
1416 }
1417 ],
1418 "metadata": {
1419 "kernelspec": {
1420 "display_name": "Python 3",
1421 "language": "python",
1422 "name": "python3"
1423 },
1424 "language_info": {
1425 "codemirror_mode": {
1426 "name": "ipython",
1427 "version": 3
1428 },
1429 "file_extension": ".py",
1430 "mimetype": "text/x-python",
1431 "name": "python",
1432 "nbconvert_exporter": "python",
1433 "pygments_lexer": "ipython3",
1434 "version": "3.8.8"
1435 }
1436 },
1437 "nbformat": 4,
1438 "nbformat_minor": 5
1439 }
1440