{ "cells": [ { "cell_type": "code", "execution_count": 1, "id": "2c2bd12b", "metadata": {}, "outputs": [], "source": [ "import re\n", "from nltk.corpus import stopwords\n", "from nltk.stem.wordnet import WordNetLemmatizer\n", "\n", "stop_words = set(stopwords.words('english'))\n", "import pandas as pd\n", "import numpy as np\n", "import nltk\n", "import spacy\n", "nlp= spacy.load('en_core_web_md')" ] }, { "cell_type": "code", "execution_count": 2, "id": "7213f06f", "metadata": {}, "outputs": [], "source": [ "texts= pd.read_csv('synopsis.tsv', sep='\\t').iloc[:,-1]" ] }, { "cell_type": "code", "execution_count": 3, "id": "ca8c0d41", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0 In 1947, Andy Dufresne (Tim Robbins), a banker...\n", "1 The movie begins with a gang of men with clown...\n", "2 A young man, exhausted and delirious, washes u...\n", "3 We back out of the webbing of neurons and brai...\n", "4 Late one morning in the Hawthorne Grill, a res...\n", " ... \n", "8013 It looks like we don't have a Synopsis for thi...\n", "8014 It looks like we don't have a Synopsis for thi...\n", "8015 It looks like we don't have a Synopsis for thi...\n", "8016 It looks like we don't have a Synopsis for thi...\n", "8017 The opening scene begins with Maggie (Greta Ge...\n", "Name: 0, Length: 8018, dtype: object" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "texts" ] }, { "cell_type": "code", "execution_count": 4, "id": "43848462", "metadata": {}, "outputs": [], "source": [ "df= pd.read_csv(\"final data.tsv\", sep='\\t')" ] }, { "cell_type": "code", "execution_count": 5, "id": "5f930c0f", "metadata": {}, "outputs": [], "source": [ "df=df.sort_values(by='numVotes', ascending=False)[:len(texts)]" ] }, { "cell_type": "code", "execution_count": 6, "id": "dd94ee2e", "metadata": {}, "outputs": [], "source": [ "df['synopsis']=texts.values\n", "del texts" ] }, { "cell_type": "code", "execution_count": 7, "id": "bd336410", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
titleIdtitleaverageRatingnumVotessynopsis
71144tt0111161The Shawshank Redemption9.32405502In 1947, Andy Dufresne (Tim Robbins), a banker...
162596tt0468569The Dark Knight9.02365212The movie begins with a gang of men with clown...
215067tt1375666Inception8.82122723A young man, exhausted and delirious, washes u...
83435tt0137523Fight Club8.81899050We back out of the webbing of neurons and brai...
70952tt0110912Pulp Fiction8.91868911Late one morning in the Hawthorne Grill, a res...
..................
261030tt2704380Seeing Things8.916920It looks like we don't have a Synopsis for thi...
161072tt0458364Fast Track5.516919It looks like we don't have a Synopsis for thi...
316650tt6533240Night Hunter5.916915It looks like we don't have a Synopsis for thi...
172124tt0819714The Edge of Love6.216915It looks like we don't have a Synopsis for thi...
328822tt7715202Sarkar7.016914The opening scene begins with Maggie (Greta Ge...
\n", "

8018 rows × 5 columns

\n", "
" ], "text/plain": [ " titleId title averageRating numVotes \\\n", "71144 tt0111161 The Shawshank Redemption 9.3 2405502 \n", "162596 tt0468569 The Dark Knight 9.0 2365212 \n", "215067 tt1375666 Inception 8.8 2122723 \n", "83435 tt0137523 Fight Club 8.8 1899050 \n", "70952 tt0110912 Pulp Fiction 8.9 1868911 \n", "... ... ... ... ... \n", "261030 tt2704380 Seeing Things 8.9 16920 \n", "161072 tt0458364 Fast Track 5.5 16919 \n", "316650 tt6533240 Night Hunter 5.9 16915 \n", "172124 tt0819714 The Edge of Love 6.2 16915 \n", "328822 tt7715202 Sarkar 7.0 16914 \n", "\n", " synopsis \n", "71144 In 1947, Andy Dufresne (Tim Robbins), a banker... \n", "162596 The movie begins with a gang of men with clown... \n", "215067 A young man, exhausted and delirious, washes u... \n", "83435 We back out of the webbing of neurons and brai... \n", "70952 Late one morning in the Hawthorne Grill, a res... \n", "... ... \n", "261030 It looks like we don't have a Synopsis for thi... \n", "161072 It looks like we don't have a Synopsis for thi... \n", "316650 It looks like we don't have a Synopsis for thi... \n", "172124 It looks like we don't have a Synopsis for thi... \n", "328822 The opening scene begins with Maggie (Greta Ge... \n", "\n", "[8018 rows x 5 columns]" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df" ] }, { "cell_type": "code", "execution_count": 8, "id": "514572db", "metadata": {}, "outputs": [], "source": [ "unique= df.synopsis.unique().tolist()\n", "unique.extend(['OBV']*(len(df)-len(df.synopsis.unique()))) \n", "df=df[df.synopsis== unique]" ] }, { "cell_type": "code", "execution_count": 9, "id": "4ddd58da", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
titleIdtitleaverageRatingnumVotessynopsis
71144tt0111161The Shawshank Redemption9.32405502In 1947, Andy Dufresne (Tim Robbins), a banker...
162596tt0468569The Dark Knight9.02365212The movie begins with a gang of men with clown...
215067tt1375666Inception8.82122723A young man, exhausted and delirious, washes u...
83435tt0137523Fight Club8.81899050We back out of the webbing of neurons and brai...
70952tt0110912Pulp Fiction8.91868911Late one morning in the Hawthorne Grill, a res...
..................
176225tt0892769How to Train Your Dragon8.1680879A Viking boy called Hiccup (voice: Jay Baruche...
113903tt0241527Harry Potter and the Sorcerer's Stone7.6678551Lord Voldemort, an evil and powerful dark wiza...
114898tt0245429Sen to Chihiro no kamikakushi8.6674079Ten-year-old Chihiro (voice: Daveigh Chase in ...
185800tt1045658Silver Linings Playbook7.7672181Pat Solitano (Bradley Cooper), who has bipolar...
238101tt1877832X-Men: Days of Future Past7.9670447Patrick Stewart's Charles Xavier recounts how ...
\n", "

132 rows × 5 columns

\n", "
" ], "text/plain": [ " titleId title averageRating \\\n", "71144 tt0111161 The Shawshank Redemption 9.3 \n", "162596 tt0468569 The Dark Knight 9.0 \n", "215067 tt1375666 Inception 8.8 \n", "83435 tt0137523 Fight Club 8.8 \n", "70952 tt0110912 Pulp Fiction 8.9 \n", "... ... ... ... \n", "176225 tt0892769 How to Train Your Dragon 8.1 \n", "113903 tt0241527 Harry Potter and the Sorcerer's Stone 7.6 \n", "114898 tt0245429 Sen to Chihiro no kamikakushi 8.6 \n", "185800 tt1045658 Silver Linings Playbook 7.7 \n", "238101 tt1877832 X-Men: Days of Future Past 7.9 \n", "\n", " numVotes synopsis \n", "71144 2405502 In 1947, Andy Dufresne (Tim Robbins), a banker... \n", "162596 2365212 The movie begins with a gang of men with clown... \n", "215067 2122723 A young man, exhausted and delirious, washes u... \n", "83435 1899050 We back out of the webbing of neurons and brai... \n", "70952 1868911 Late one morning in the Hawthorne Grill, a res... \n", "... ... ... \n", "176225 680879 A Viking boy called Hiccup (voice: Jay Baruche... \n", "113903 678551 Lord Voldemort, an evil and powerful dark wiza... \n", "114898 674079 Ten-year-old Chihiro (voice: Daveigh Chase in ... \n", "185800 672181 Pat Solitano (Bradley Cooper), who has bipolar... \n", "238101 670447 Patrick Stewart's Charles Xavier recounts how ... \n", "\n", "[132 rows x 5 columns]" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df" ] }, { "cell_type": "code", "execution_count": null, "id": "d16a004a", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": 10, "id": "1bcdbebd", "metadata": {}, "outputs": [], "source": [ "def pre_process(text, allowed_pos=['NOUN',\"ADJ\",'JJ','JJR', 'VB']):\n", " doc= nlp(text)\n", " new_text=[ token.lemma_ for token in doc if token.pos_ in allowed_pos and token.tag_!= 'NNP']\n", " final=' '.join(new_text)\n", "\n", " return final" ] }, { "cell_type": "code", "execution_count": 11, "id": "b57e6e2f", "metadata": {}, "outputs": [], "source": [ "docs = df['synopsis'].apply(lambda x:pre_process(x)).to_list()" ] }, { "cell_type": "code", "execution_count": null, "id": "a2513c64", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": 12, "id": "dba708de", "metadata": {}, "outputs": [], "source": [ "from sklearn.feature_extraction.text import CountVectorizer\n", "#docs = docs.tolist()\n", "#create a vocabulary of words, \n", "cv=CountVectorizer(max_df=0.95, # ignore words that appear in 95% of documents\n", " max_features=100000, # the size of the vocabulary\n", " ngram_range=(1,3), # vocabulary contains single words, bigrams, trigrams\n", " lowercase=False\n", " )\n", "word_count_vector=cv.fit_transform(docs)" ] }, { "cell_type": "code", "execution_count": 13, "id": "7b9c5196", "metadata": {}, "outputs": [], "source": [ "def top_n_words(corpus, n=50):\n", " vec = CountVectorizer().fit(corpus)\n", " bag_of_words = vec.transform(corpus)\n", " sum_words = bag_of_words.sum(axis=0) \n", " words_freq = sorted([(word, sum_words[0, idx]) for word, idx in vec.vocabulary_.items()], key = lambda x: x[1], reverse=True)\n", " words=[w[0] for w in words_freq[:n] ]\n", " return words" ] }, { "cell_type": "code", "execution_count": 14, "id": "50f775e8", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "TfidfTransformer()" ] }, "execution_count": 14, "metadata": {}, "output_type": "execute_result" } ], "source": [ "from sklearn.feature_extraction.text import TfidfTransformer\n", "\n", "tfidf_transformer=TfidfTransformer(smooth_idf=True,use_idf=True)\n", "tfidf_transformer.fit(word_count_vector)" ] }, { "cell_type": "code", "execution_count": 15, "id": "e83ed404", "metadata": {}, "outputs": [], "source": [ "def sort_coo(coo_matrix):\n", " tuples = zip(coo_matrix.col, coo_matrix.data)\n", " return sorted(tuples, key=lambda x: (x[1], x[0]), reverse=True)" ] }, { "cell_type": "code", "execution_count": 16, "id": "aa859d50", "metadata": {}, "outputs": [], "source": [ "def extract_topn_from_vector(feature_names, sorted_items, topn=10):\n", " \"\"\"get the feature names and tf-idf score of top n items\"\"\"\n", " \n", " #use only topn items from vector\n", " sorted_items = sorted_items[:topn]\n", "\n", " score_vals = []\n", " feature_vals = []\n", "\n", " for idx, score in sorted_items:\n", " fname = feature_names[idx]\n", " \n", " #keep track of feature name and its corresponding score\n", " score_vals.append(round(score, 3))\n", " feature_vals.append(feature_names[idx])\n", "\n", " #create a tuples of feature,score\n", " #results = zip(feature_vals,score_vals)\n", " results= {}\n", " for idx in range(len(feature_vals)):\n", " results[feature_vals[idx]]=score_vals[idx]\n", " \n", " return results\n", "\n", "# get feature names\n", "\n", "\n" ] }, { "cell_type": "code", "execution_count": 17, "id": "bf66b02a", "metadata": {}, "outputs": [], "source": [ "feature_names=cv.get_feature_names()\n", "freq_words=top_n_words(docs)" ] }, { "cell_type": "code", "execution_count": 18, "id": "e77f7b36", "metadata": {}, "outputs": [], "source": [ "def get_keywords(idx, docs, n=10):\n", "\n", " #generate tf-idf for the given document\n", " #print(docs[idx])\n", " tf_idf_vector=tfidf_transformer.transform(cv.transform([docs[idx]]))\n", "\n", " #sort the tf-idf vectors by descending order of scores\n", " sorted_items=sort_coo(tf_idf_vector.tocoo())\n", "\n", " #extract only the top n; n here is 10\n", " keywords=extract_topn_from_vector(feature_names,sorted_items,2*n) #returns a dict\n", " keywords=list(keywords.keys()) #dict.keys to list\n", " keywords= [k for k in keywords if k not in freq_words][:n] # not in top n words\n", " return keywords\n", "\n" ] }, { "cell_type": "code", "execution_count": 19, "id": "808cc336", "metadata": {}, "outputs": [], "source": [ "def print_results(idx,keywords, df):\n", " # now print the results\n", " print(\"\\n=====Title=====\")\n", " print(df.iloc[idx,1])\n", " print(\"\\n===Keywords===\")\n", " #for k in keywords:\n", " print(keywords)\n" ] }, { "cell_type": "code", "execution_count": 20, "id": "9b9f477c", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "=====Title=====\n", "The Shawshank Redemption\n", "\n", "===Keywords===\n", "['prison', 'warden', 'inmate', 'cell', 'parole', 'rock', 'solitary', 'rock hammer', 'library', 'state', 'prisoner', 'hammer', 'red', 'poster', 'book', 'wall', 'wooden beam', 'warden office', 'prison library', 'message wooden beam', 'message wooden', 'giant poster', 'job', 'record', 'diploma', 'rest life', 'shoe', 'financial', 'other prisoner', 'infirmary', 'hope', 'life prison', 'fat', 'banker', 'prison guard', 'project', 'cold', 'scheme', 'stone', 'letter', 'high school', 'tax return', 'state senate', 'state police', 'school diploma', 'red remark', 'prison library state', 'police squad car', 'police squad', 'other contractor']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "The Dark Knight\n", "\n", "===Keywords===\n", "['mob', 'coin', 'mob member', 'clown', 'ferry', 'member', 'cell phone', 'mayor', 'bank', 'cell', 'goon', 'boat', 'phone', 'detonator', 'cop', 'sonar', 'clean side', 'mobster', 'criminal', 'side', 'dirty', 'location', 'convict', 'clean', 'chaos', 'card', 'city', 'mob money', 'honor guard', 'half face', 'coin clean side', 'coin clean', 'clown guard', 'batsignal', 'warden', 'penthouse', 'fall', 'innocent', 'hostage', 'time right', 'makeup', 'citizen', 'jail', 'bus', 'nickname', 'same time', 'window', 'monitor', 'convoy', 'honor']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Inception\n", "\n", "===Keywords===\n", "['dream', 'limbo', 'team', 'subconscious', 'kick', 'projection', 'top', 'level', 'mind', 'brass top', 'job', 'van', 'safe', 'totem', 'team dream', 'level dream', 'inception', 'gravity', 'brass', 'sedative', 'folder', 'real', 'fort', 'warehouse', 'elevator', 'reality', 'manila folder', 'manila', 'father own', 'father company', 'dream van', 'dream projection', 'table', 'spinning', 'room safe', 'interpretation', 'carpet', 'architect', 'moment', 'mob', 'positive', 'mountainside', 'grandmother', 'asleep', 'bridge', 'idea', 'impossible', 'combination', 'workshop', 'third']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Fight Club\n", "\n", "===Keywords===\n", "['narrator', 'fight club', 'soap', 'member', 'fight', 'club', 'burn', 'narrator more', 'narrator gun', 'gun mouth', 'recruit', 'insomnia', 'consumerism', 'fat', 'basement', 'meeting', 'testicular cancer', 'testicular', 'security narrator', 'night narrator', 'narrator support', 'narrator officer', 'narrator new', 'narrator narrator', 'narrator member', 'narrator insomnia', 'narrator house', 'narrator boss', 'lye', 'kitchen narrator', 'first fight', 'burn narrator', 'bomb narrator', 'act vandalism', 'mouth', 'rule', 'vandalism', 'support group', 'list', 'sweat', 'support', 'kitchen', 'phone', 'boss', 'bomb', 'bar', 'homework', 'sex', 'parking', 'disgust']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Pulp Fiction\n", "\n", "===Keywords===\n", "['watch', 'apartment', 'tyranny', 'wallet', 'pawn shop', 'strip club', 'miracle', 'pawn', 'strip', 'gang', 'diner', 'briefcase', 'tyranny evil man', 'tyranny evil', 'evil man', 'bathroom', 'winning', 'gold watch', 'boxer', 'gang member', 'club', 'restaurant', 'grandfather', 'shop', 'small talk', 'passage', 'opponent', 'heroin', 'apartment building', 'valuable', 'rumor', 'motel', 'morning', 'cocaine', 'vengeance', 'gold', 'inside', 'girlfriend', 'incident', 'evil', 'talk', 'dream', 'store', 'furious', 'story', 'young naive guy', 'young naive', 'young couple pro', 'wristwatch bedroom alone', 'wristwatch bedroom']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Forrest Gump\n", "\n", "===Keywords===\n", "['feather', 'pong', 'ping pong', 'ping', 'bus stop', 'bus', 'boat', 'white feather', 'son school', 'shrimping', 'stop', 'first day school', 'shrimp', 'school', 'day school', 'first day', 'college', 'son', 'young son father', 'year famous present', 'year famous', 'woman listener bus', 'woman listener', 'white feather breeze', 'white feather beginning', 'whim run country', 'whim run', 'wedding prosthetic leg', 'wedding prosthetic', 'war rally reunite', 'war rally', 'war patrol platoon', 'war patrol', 'virus move wedding', 'virus move', 'veneration first day', 'veneration first', 'veneration', 'uncanny ability ping', 'uncanny ability', 'uncanny', 'tox uncanny ability', 'tox uncanny', 'tox', 'time leg brace', 'time leg', 'time half year', 'time half', 'television young son', 'team anti war']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Game of Thrones\n", "\n", "===Keywords===\n", "['king', 'ned', 'deserter', 'sister', 'bastard', 'horse', 'husband', 'queen', 'top compound', 'sex woman', 'pup', 'letter sister', 'imp', 'husband king', 'bran', 'brother', 'man horse', 'feast', 'wedding', 'wolf', 'kingdom', 'dwarf', 'young daughter', 'wall', 'dragon', 'eager', 'compound', 'throne', 'practice', 'daughter', 'snow', 'cat', 'kind', 'eye', 'son', 'sex', 'letter', 'young woman attention', 'young pup rare', 'young pup', 'young one smoke', 'young one', 'young daughter practice', 'young daughter other', 'year old deserter', 'year deserter crazy', 'year deserter', 'woman middle dance', 'woman middle', 'woman front sister']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "The Matrix\n", "\n", "===Keywords===\n", "['matrix', 'tank', 'phone', 'world', 'crew', 'spoon', 'hovercraft', 'helicopter', 'program', 'real world', 'chair', 'real', 'code', 'pill', 'simulation', 'subway', 'reality', 'computer', 'machine', 'line', 'policeman', 'elevator', 'wall', 'rule', 'call', 'black', 'spoon spoon', 'socket', 'green code', 'cypher', 'choice matrix', 'back skull', 'blow', 'booth', 'floor', 'rooftop', 'software', 'mankind', 'jack', 'hacker', 'pod', 'screen', 'city', 'rest crew', 'phone booth', 'power', 'system', 'skull', 'leap', 'choice']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "The Lord of the Rings: The Fellowship of the Ring\n", "\n", "===Keywords===\n", "['orc', 'hobbit', 'ring', 'elvish', 'temptation', 'heir', 'band', 'mountain', 'creature', 'finger', 'year creature century', 'year creature', 'year 111th birthday', 'year 111th', 'wizardry avalanche mountain', 'wizardry avalanche', 'wizardry', 'weapon army large', 'volunteer other hobbit', 'volunteer other', 'various people council', 'various people', 'ultimate plan forest', 'ultimate plan', 'travelling night hill', 'travelling night', 'travelling', 'time year 111th', 'throne son mountain', 'temptation strong rest', 'temptation strong', 'temptation orc year', 'temptation orc', 'sword hand stroke', 'sunlight orc aid', 'sunlight orc', 'strong rest large', 'strong rest', 'strong orc sunlight', 'strong orc', 'stroke finger army', 'stroke finger', 'story time year', 'spectre blade healing', 'spectre blade', 'spectre', 'source ring power', 'source ring', 'son mountain wizardry', 'son mountain']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "The Lord of the Rings: The Return of the King\n", "\n", "===Keywords===\n", "['hobbit', 'king', 'city', 'palantír', 'gondorian', 'army', 'sword', 'pyre', 'trebuchet', 'orcs', 'birthright', 'horse', 'power', 'son', 'treachery', 'lava', 'peace', 'vision', 'west', 'defender', 'quest', 'force', 'heir', 'wizard', 'arrow', 'immense', 'pass', 'grief', 'great', 'tower', 'unaware', 'lead', 'captain', 'love', 'river', 'mountain', 'creature', 'attack', 'stair', 'destruction', 'threat', 'evil', 'level', 'age', 'effect', 'year life last', 'wreckage tower center', 'wreckage tower', 'wound peace haven', 'wound peace']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "The Godfather\n", "\n", "===Keywords===\n", "['meeting', 'business', 'assassination', 'bodyguard', 'wedding', 'hitman', 'dealing', 'role', 'sicilian', 'family business', 'consigliere', 'button man', 'eld', 'request', 'daughter', 'political', 'trade', 'hospital', 'son', 'italian', 'corrupt', 'compound', 'associate', 'narcotic trade', 'meeting other', 'italian tradition', 'hero service', 'family lawyer', 'eld son', 'baptism', 'mob', 'non', 'favor', 'button', 'tradition', 'other family', 'caporegime', 'business dealing', 'attempt life', 'war', 'protection', 'bed', 'narcotic', 'family friend', 'exile', 'baker', 'legitimate', 'infidelity', 'young son', 'casino']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Interstellar\n", "\n", "===Keywords===\n", "['black hole', 'planet', 'equation', 'farmhouse', 'space', 'black', 'hole', 'wormhole', 'cryosleep', 'video', 'dust', 'centrifuge', 'humanity', 'brand', 'gravity', 'tar', 'beacon', 'ghost', 'bunker', 'mission', 'year old', 'datum', 'ranger', 'farmer', 'gravity equation', 'daughter', 'space station', 'crew', 'corn', 'station', 'wristwatch', 'shelf', 'crop', 'world', 'age', 'grandchild', 'book shelf', 'book', 'shuttle', 'orbit', 'bedroom', 'robot', 'message', 'same age', 'homestead', 'gravitational', 'father law', 'son', 'baseball', 'case']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "The Dark Knight Rises\n", "\n", "===Keywords===\n", "['bane', 'henchman', 'tunnel', 'bane man', 'reactor', 'mercenary', 'cop', 'pistol', 'bomb', 'hostage', 'cement', 'city', 'prisoner', 'officer', 'janitor', 'prison', 'nuclear', 'rope', 'submachine gun', 'submachine', 'weapon', 'sewer', 'plant', 'construction', 'mask', 'orphanage', 'driver', 'second', 'thug', 'autopilot', 'team', 'board', 'trader', 'explosion', 'trading floor', 'stock exchange', 'manhole', 'congressman', 'cement plant', 'bag', 'project', 'necklace', 'underground', 'trigger', 'hospital', 'police car', 'exchange', 'tunnel man', 'nuclear weapon', 'detonator']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Breaking Bad\n", "\n", "===Keywords===\n", "['meth', 'lab', 'season', 'meth lab', 'gang', 'cancer', 'operation', 'neo nazi gang', 'neo nazi', 'nazi gang', 'cancer treatment', 'partner', 'neo', 'distributor', 'henchman', 'distribution', 'cartel', 'enforcer', 'evidence', 'desert', 'production', 'nazi', 'informant', 'drug', 'business', 'product', 'compound', 'dealer', 'tie', 'lawyer', 'treatment', 'wrongdoing option desert', 'wrongdoing option', 'wrongdoing', 'wrath trust lab', 'wrath trust', 'wound police position', 'wound police', 'work detail meth', 'woman rehab group', 'woman rehab', 'willing pound meth', 'willing pound', 'wife season 5following', 'wife season', 'wife disabled son', 'wife disabled', 'vomit enemy frequent', 'vomit enemy', 'vomit']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "The Lord of the Rings: The Two Towers\n", "\n", "===Keywords===\n", "['keep', 'army', 'war', 'defender', 'fortress', 'battle', 'journey', 'hobbit', 'ring', 'rider', 'wizard', 'arrow', 'captive', 'white wizard', 'marsh', 'fell beast', 'fell', 'forest', 'horse', 'stronghold', 'gate', 'archer', 'rocky', 'lord', 'captor', 'defeat', 'cloak', 'wall', 'midst', 'loyal', 'rope', 'beast', 'ambush', 'hill', 'spirit', 'cliff', 'river', 'creature', 'attack', 'worth', 'evil', 'survivor', 'ride', 'effort', 'young brother capture', 'worth other full', 'worth other', 'worth father way', 'worth father', 'world worth other']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Se7en\n", "\n", "===Keywords===\n", "['mill', 'detective', 'victim', 'sliver', 'apartment', 'murder', 'painting', 'plastic like', 'obese man spaghetti', 'obese man', 'man spaghetti', 'picture', 'pregnant', 'wall painting', 'spaghetti', 'outskirt', 'obese', 'captain', 'lawyer', 'city', 'print', 'refrigerator', 'scene', 'gunpoint', 'fingerprint', 'crime', 'stomach', 'pill', 'physical', 'plastic', 'place', 'list', 'train', 'horror', 'evidence', 'desert', 'device', 'afraid', 'young woman prostitute', 'young detective action', 'young detective', 'young cop small', 'year day picture', 'year day', 'yard driver box', 'yard driver', 'wrath masterpiece helpless', 'wrath masterpiece', 'worth second part', 'worth second']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Django Unchained\n", "\n", "===Keywords===\n", "['slave', 'mandingo', 'bounty', 'horse', 'sheriff', 'cart', 'estate', 'marshal', 'white', 'bounty hunter', 'plantation', 'hunter', 'white man', 'saloon', 'brother', 'other slave', 'townspeople', 'legend', 'paper', 'town', 'rifle', 'intelligence', 'owner', 'black man', 'slave girl', 'slavery', 'ranch', 'hound', 'transporter', 'tracker', 'dentist', 'bullet wound', 'master', 'right', 'whip', 'bullet', 'freedom', 'german', 'winter', 'hell', 'free', 'tree', 'mask', 'revolver', 'white rancher', 'white brain', 'town marshal', 'speck', 'sheriff town', 'share reward']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Gladiator\n", "\n", "===Keywords===\n", "['gladiator', 'arena', 'praetorian', 'emperor', 'popularity', 'son', 'wife son', 'praetorian guard', 'stiletto', 'approval', 'afterlife', 'sword', 'audience', 'power senate', 'own stiletto', 'victor', 'successor', 'barbarian', 'senate', 'roman', 'young son', 'betrayal', 'crowd', 'involvement', 'thumb', 'affection', 'plot', 'victory', 'brother', 'skill', 'young son plot', 'young son execution', 'year prolonged war', 'year prolonged', 'wrenching interview father', 'wrenching interview', 'wrenching', 'wound gladiator armor', 'wound gladiator', 'wooden sword time', 'wooden sword', 'wife young son', 'wife son patch', 'wife son honor', 'wife son exhaustion', 'wife son afterlife', 'weapon own sword', 'weapon own', 'war esteem elderly', 'war esteem']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Batman Begins\n", "\n", "===Keywords===\n", "['toxin', 'bat', 'train', 'antidote', 'emitter', 'microwave', 'microwave emitter', 'thug', 'mask', 'city', 'rabbit', 'cave', 'distant flashback', 'burlap', 'blue flower', 'drug', 'foundation', 'water', 'member', 'prison', 'vigilante', 'gas', 'inmate', 'flower', 'flashback', 'vial', 'present', 'swarm bat', 'memory cloth', 'grapple', 'close flashback', 'burlap mask', 'parent', 'fear', 'justice', 'rooftop', 'assassin', 'blue', 'officer', 'water pipe', 'scarecrow', 'flashback year', 'corrupt', 'company', 'boss', 'street', 'distant', 'criminal', 'train train', 'swarm']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "The Silence of the Lambs\n", "\n", "===Keywords===\n", "['starling', 'victim', 'file', 'tailor', 'survivor ambulance', 'lamb', 'case file', 'body victim', 'riddle', 'basement', 'information', 'ambulance', 'serial', 'deal', 'team', 'phone call', 'patient', 'childhood', 'real', 'skin', 'address', 'survivor', 'work taste coroner', 'work taste', 'woman suit real', 'woman suit', 'windowless stone wall', 'windowless stone', 'whole life case', 'whole life', 'white well work', 'white well', 'well work taste', 'well work', 'weapon basement starling', 'weapon basement', 'way arrest note', 'way arrest', 'wall pleasant courteous', 'wall pleasant', 'vision goggle starling', 'vision goggle', 'victim throat victim', 'victim throat', 'victim tailor woman', 'victim tailor', 'victim real life', 'victim real', 'victim plane town', 'victim plane']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Inglourious Basterds\n", "\n", "===Keywords===\n", "['cinema', 'auditorium', 'german', 'tavern', 'chapter', 'film', 'soldier', 'swastika', 'nitrate film', 'nitrate', 'reel', 'american', 'premiere', 'accent', 'french', 'operator', 'german soldier', 'screen', 'swastika forehead', 'radio operator', 'fourth reel', 'american line', 'box', 'officer', 'fourth', 'nazi', 'radio', 'sergeant', 'finger', 'jewish', 'forehead', 'subtle hint', 'subtle', 'projection booth time', 'projection booth', 'pointer finger', 'pointer', 'opera box', 'french tavern', 'flammable nitrate film', 'flammable nitrate', 'flammable', 'filmmaker', 'film screen', 'explosive box', 'deal officer', 'booth time', 'auditorium door', 'projector', 'hint']\n", "\n", "**************************\n", "\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\n", "=====Title=====\n", "The Avengers\n", "\n", "===Keywords===\n", "['fury', 'portal', 'helicarrier', 'scepter', 'carrier', 'capability', 'council', 'nuke', 'aircraft carrier', 'earth', 'weapon', 'board', 'team', 'god', 'assignment', 'aircraft', 'shawarma', 'portal portal', 'device portal', 'date night', 'conference call', 'board helicarrier', 'cell', 'lighting', 'control', 'spear', 'nuclear', 'banner', 'hero', 'personnel', 'superior', 'electrical', 'world', 'option', 'missile', 'invasion', 'credit', 'agent', 'conference', 'beast', 'atmosphere', 'mind', 'master', 'easy', 'citizen', 'wave', 'engine', 'date', 'civilian', 'office']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Saving Private Ryan\n", "\n", "===Keywords===\n", "['squad', 'german', 'soldier', 'unit', 'tank', 'machine gun', 'beach', 'bridge', 'german soldier', 'machine', 'bunker', 'glider', 'sniper', 'letter', 'machine gun nest', 'half track', 'gun nest', 'grave', 'gi', 'position', 'mortar', 'brother', 'nest', 'cover', 'landing', 'captain', 'unit bridge', 'sticky bomb', 'sticky', 'medic', 'german troop', 'troop', 'sergeant', 'mission', 'village', 'comrade', 'machine gun fire', 'bomb', 'gun fire', 'rubble', 'town', 'chest', 'side', 'gear', 'blast', 'track', 'american', 'hearing', 'church', 'effort']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Star Wars\n", "\n", "===Keywords===\n", "['imperial', 'droid', 'troop', 'fighter', 'station', 'planet', 'trench', 'compactor', 'docking', 'port', 'imperial troop', 'base', 'wingman', 'docking bay', 'tractor beam', 'tractor', 'stormtrooper', 'princess', 'moon', 'bay', 'squadron', 'exhaust port', 'bomber', 'firefight', 'message', 'plan', 'lightsaber', 'power', 'exhaust', 'board', 'uncle', 'bolt', 'space', 'utility', 'pod', 'laser', 'pilot', 'escape', 'snubfighter', '3PO', 'run', 'beam', 'star', 'creature', 'wing', 'battle', 'attack', 'computer', 'location', 'hall']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Schindler's List\n", "\n", "===Keywords===\n", "['factory', 'worker', 'ghetto', 'camp', 'german', 'grave', 'train', 'worker factory', 'stone grave actor', 'stone grave', 'problem woman', 'guard factory', 'grave actor', 'list', 'child woman', 'woman child', 'polish', 'labor', 'abuse', 'army', 'town', 'jewish', 'release', 'actor', 'successful', 'official', 'many', 'contact', 'stone', 'card', 'world entire distraught', 'world entire', 'worker train schindler', 'worker train', 'worker particular housekeeper', 'worker particular', 'worker motive safe', 'worker motive', 'worker list worker', 'worker list', 'worker letter criminal', 'worker letter', 'worker guard factory', 'worker guard', 'worker factory old', 'worker factory ghetto', 'work meantime problem', 'work meantime', 'womanizer factory money', 'womanizer factory']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "The Wolf of Wall Street\n", "\n", "===Keywords===\n", "['broker', 'stock', 'quaalude', 'hooker', 'sale', 'gay', 'company', 'pen', 'cocaine', 'coke', 'account', 'yacht', 'drug', 'investor', 'whole', 'divorce', 'wedding', 'garage', 'office', 'month', 'big', 'effect', 'guy', 'woman shoe', 'whole floor', 'swiss', 'seminar', 'plane captain', 'little people', 'floor company', 'effect quaalude', 'co conspirator', 'broker office', 'shoe', 'wire', 'place', 'rich', 'co', 'cash', 'sober', 'place small', 'payphone', 'infomercial', 'heart attack', 'deal', 'business', 'captain', 'floor', 'hopeful', 'harbor']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "The Prestige\n", "\n", "===Keywords===\n", "['trick', 'cutter', 'diary', 'machine', 'stage', 'bird', 'magician', 'trapdoor', 'hat', 'secret', 'audience', 'knot', 'cage', 'cat', 'double', 'tank', 'own act', 'collector', 'bird cage', 'act', 'box', 'performance', 'version', 'top hat', 'prestige', 'coil', 'show', 'rivalry', 'magic', 'narrative', 'goldfish', 'bullet', 'left hand', 'underwater', 'engineer', 'electrical', 'frame', 'bowl', 'finger', 'word diary', 'water tank', 'underwater escape', 'trick own', 'trick little girl', 'trick little', 'trick cutter', 'trick bird', 'trapdoor door', 'top hat forest', 'stage name']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "The Departed\n", "\n", "===Keywords===\n", "['mole', 'crew', 'informant', 'identity', 'shop owner', 'owner', 'academy', 'organization', 'crew member', 'store', 'envelope', 'shop', 'security number other', 'protection money', 'police academy', 'owner man', 'organized crime', 'member crew', 'job police officer', 'guy bar', 'civilian identity', 'member', 'crime', 'store owner', 'social security number', 'social security', 'security number', 'organized', 'number other', 'job police', 'civilian', 'irish', 'more money', 'boy', 'bar', 'undercover', 'rat', 'mobster', 'force', 'roof', 'cop', 'social', 'environment', 'product', 'cousin', 'counter', 'period', 'meeting', 'tie', 'theater']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Star Wars: Episode V - The Empire Strikes Back\n", "\n", "===Keywords===\n", "['imperial', 'light saber', 'walker', 'base', 'asteroid', 'droid', 'cave', 'saber', 'creature', 'planet', 'city', 'fleet', 'weather vane', 'vane', 'energy shield', 'carbon', 'light', 'asteroid field', 'hyperspace', 'flagship', 'surface', 'energy', 'galaxy', 'weather', 'wampa', 'tauntaun', 'massive asteroid', 'legged', 'hyper drive', 'hyper', 'dozen legged', 'city central', 'carbon chamber', 'at', 'space', 'training', 'powerful', 'field', 'ration', 'imperial force', 'escape plan', 'displeasure', 'fighter', 'massive', 'escape', 'medical', 'transmission', 'patience', 'infantry', 'vision']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "The Green Mile\n", "\n", "===Keywords===\n", "['execution', 'mouse', 'inmate', 'other guard', 'padded room', 'padded', 'spore', 'sponge', 'infection', 'cell', 'electricity', 'pain', 'memory', 'chair', 'prison', 'pendant', 'new inmate', 'next day', 'movie', 'new job', 'job', 'mental hospital', 'electric chair', 'electric', 'rehearsal', 'mental', 'girl', 'show', 'wet', 'connection', 'audience', 'innocent', 'wife night next', 'urinary infection', 'urinary', 'upcoming execution', 'straitjacket padded room', 'straitjacket padded', 'straitjacket', 'spore mouth', 'sponge wet', 'scared dark', 'powerful memory', 'night execution', 'nephew governor wife', 'nephew governor', 'job mental', 'inmate finger', 'governor wife', 'execution pendant']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Shutter Island\n", "\n", "===Keywords===\n", "['patient', 'lighthouse', 'island', 'doctor', 'warden', 'hospital', 'staff', 'orderly', 'man violence', 'ferry', 'cliff', 'mental hospital', 'vacation', 'fantasy', 'psychotropic drug', 'psychotropic', 'lobotomy', 'hospital ground', 'dream sequence', 'kid', 'violence', 'mental', 'dream', 'water', 'cell', 'interview', 'drug', 'ground', 'federal', 'therapy', 'storm', 'rifle', 'lake', 'government', 'little girl', 'investigation', 'woman patient', 'wife lot', 'wife island', 'water notebook', 'truth doctor', 'surgical', 'role play', 'rifle guard', 'psychiatry', 'personnel record', 'patient day', 'patient building', 'other doctor', 'new pack']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "The Godfather: Part II\n", "\n", "===Keywords===\n", "['brother', 'committee', 'bodyguard', 'business', 'gambling', 'party', 'rebel', 'local', 'compound', 'assassination', 'miscarriage', 'gaming license', 'gaming', 'dead bodyguard', 'communist', 'brother revenge', 'murder', 'witness', 'problem', 'favor', 'neighborhood', 'first movie', 'button man', 'military base', 'hitman', 'assassination attempt', 'stroke', 'right hand man', 'partnership', 'guerrilla', 'statement', 'dealing', 'casino', 'birthday party', 'film', 'license', 'hand man', 'revenge', 'traitor', 'flashback', 'respect', 'recent', 'old brother', 'hearing', 'businessman', 'policeman', 'italian', 'father father', 'associate', 'right hand']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Memento\n", "\n", "===Keywords===\n", "['second attacker', 'attacker', 'caller', 'chronological order', 'chronological', 'second', 'motel', 'black white', 'condition', 'plate number', 'color', 'note', 'reverse', 'new memory', 'license plate number', 'license plate', 'plate', 'story', 'order', 'escort', 'white', 'tattoo', 'memory', 'license', 'clothe', 'lie', 'white sequence', 'reverse chronological order', 'reverse chronological', 'reservoir', 'plate number leg', 'photo body', 'number leg', 'motel motel', 'memory condition', 'condition story', 'black white sequence', 'anterograde amnesia', 'anterograde', 'amnesia', 'black', 'drug', 'town', 'clue', 'disc', 'sequence', 'insurance', 'number', 'motel room', 'movie']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Avatar\n", "\n", "===Keywords===\n", "['avatar', 'toruk', 'grace', 'banshee', 'thanator', 'queue', 'military', 'animal', 'tree', 'unobtanium', 'norm', 'bombship', 'pod', 'lab', 'bulldozer', 'base', 'tribe', 'avatar human', 'avatar body', 'sacred', 'objective', 'warrior', 'suit', 'forest', 'fleet', 'viperwolve', 'videolog', 'seed', 'rda', 'operation', 'planet', 'shuttle', 'use leg', 'prayer', 'neural', 'deposit', 'command ship', 'ground', 'atmosphere', 'brother', 'corporate', 'clan', 'native', 'form', 'mission', 'command', 'attack', 'human form', 'soldier', 'sky']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "American Beauty\n", "\n", "===Keywords===\n", "['gay', 'relationship', 'son gay', 'camcorder', 'affair', 'boring', 'rain', 'marijuana', 'dismayed', 'much', 'narrator', 'footage', 'gunshot', 'sexual', 'surprise', 'image', 'son', 'wrong idea rain', 'world much heart', 'world much', 'wind sexual relationship', 'wind sexual', 'wife materialistic ambitious', 'wife materialistic', 'wife infidelity indifference', 'wife camcorder marijuana', 'wife camcorder', 'vitriol drug rendezvous', 'vitriol drug', 'vitriol', 'virgin innocent child', 'virgin innocent', 'violent father house', 'violent father', 'vantage point narrator', 'unsuccessful potential year', 'unsuccessful potential', 'unsatisfying life indifferent', 'unsatisfying life', 'unsatisfying', 'unhappy self esteem', 'unhappy self', 'unaware gun back', 'unaware gun', 'turn event moment', 'time unaware gun', 'time unaware', 'thing final narration', 'thing final', 'table photograph family']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Back to the Future\n", "\n", "===Keywords===\n", "['clock', 'flux', 'doc', 'clock tower', 'flux capacitor', 'capacitor', 'skateboard', 'parking lot', 'future', 'square', 'radiation suit', 'parking', 'bolt', 'tower', 'plutonium', 'amplifier', 'radiation', 'band', 'dance', 'guitar', 'lot', 'garage', 'tree', 'town square', 'flyer', 'van', 'town', 'street', 'mph', 'lightning bolt', 'pine', 'suit', 'mayor', 'lightning', 'vision flux capacitor', 'vision flux', 'pine tree', 'manure', 'kiosk', 'exact time', 'date', 'driver', 'tin', 'road', 'diner', 'photo', 'minute', 'cable', 'time machine', 'vehicle']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Titanic\n", "\n", "===Keywords===\n", "['stern', 'necklace', 'butler', 'passenger', 'iceberg', 'class', 'lifeboat', 'first class', 'water', 'deck', 'stern water', 'boat deck', 'wreck', 'boat', 'watertight compartment', 'watertight', 'third class', 'starboard', 'sex automobile', 'passenger crew', 'first class passenger', 'deck lifeboat', 'collapsible', 'class passenger', 'cargo hold', 'boat deck lifeboat', 'automobile', 'marriage', 'bottom', 'sketch', 'compartment', 'rail', 'drawing', 'collision', 'bow', 'arrangement', 'cargo', 'board', 'minute', 'damage', 'hold', 'coat', 'officer', 'suicide', 'third', 'survivor', 'pocket', 'edge', 'sex', 'young woman necklace']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Guardians of the Galaxy\n", "\n", "===Keywords===\n", "['rocket', 'mom', 'space', 'prison', 'space dog', 'soviet space dog', 'soviet space', 'no', 'planet', 'goon', 'plan', 'broker', 'stone', 'stick', 'soviet', 'wrist device prisoner', 'wrist device', 'space prison', 'ship giant', 'security droid', 'guard station', 'device prisoner', 'big fight', 'assistant stone', 'hammer', 'bridge', 'pot', 'daughter', 'assistant', 'giant', 'dog', 'droid', 'crew', 'double', 'battery', 'leg', 'cannon', 'station', 'tired', 'security', 'song', 'wrist', 'favorite', 'music', 'voice', 'many', 'baby', 'fight', 'drunk', 'device']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Léon\n", "\n", "===Keywords===\n", "['hotel clerk', 'hotel', 'clerk', 'houseplant', 'apartment', 'hitman', 'girl', 'school', 'hotel lobby', 'family apartment', 'year old', 'cleaner', 'pig', 'cartoon', 'guy', 'grocery', 'grenade', 'agent', 'plant', 'lobby', 'hostage', 'bank', 'cigarette', 'hallway', 'brother', 'work', 'little', 'year old plant', 'year old brother', 'wound chest brother', 'work year old', 'work year', 'work training money', 'work training', 'work mafioso retail', 'work mafioso', 'window form several', 'window form', 'whore mother eld', 'whore mother', 'whereabouts grocery shopping', 'whereabouts grocery', 'well many people', 'weirdo hotel clerk', 'weirdo hotel', 'weirdo', 'way year old', 'vest several grenade', 'vest several', 'unnoticed hotel lobby']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "American History X\n", "\n", "===Keywords===\n", "['white', 'supremacist', 'black man', 'white supremacist', 'white kid', 'black', 'kid', 'jail', 'brother', 'suburban white', 'paper', 'black man car', 'suburban', 'bathroom', 'teacher', 'man car', 'boy', 'young black', 'truck window', 'suburban white kid', 'non white', 'man truck window', 'history teacher', 'boy white', 'black inmate', 'sunrise', 'man jail', 'man truck', 'school', 'stall', 'principal', 'next scene', 'gang', 'office', 'man other', 'only thing', 'window', 'narrator', 'gun hand', 'conclusion', 'shower', 'inmate', 'assignment', 'non', 'history', 'friendly', 'scene', 'wave', 'scared', 'due']\n", "\n", "**************************\n", "\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\n", "=====Title=====\n", "V for Vendetta\n", "\n", "===Keywords===\n", "['terrorist', 'evey', 'government', 'mask', 'fifth', 'surveillance', 'costume', 'scarlet carson', 'scarlet', 'carson', 'bespectacled girl', 'country', 'broadcast', 'bespectacled', 'investigation', 'black', 'virus', 'party member', 'curfew', 'broadcasting', 'black bag', 'fear', 'officer', 'man mask', 'station', 'train', 'rose', 'other officer', 'notebook', 'note', 'party', 'soldier', 'girl', 'studio', 'bed', 'video', 'parent', 'interrogation', 'information', 'real', 'wine cabinet', 'unity', 'secret police', 'room wine cabinet', 'room wine', 'past curfew', 'own home', 'hidden room wine', 'evey thank', 'emergency broadcast system']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Goodfellas\n", "\n", "===Keywords===\n", "['drug', 'lucchese', 'spider', 'heist', 'crime family', 'cocaine', 'mob', 'mistress', 'cargo', 'connection', 'career', 'drug connection', 'dollar cargo', 'cargo terminal', 'pistol', 'crime', 'dollar', 'shovel', 'trunk', 'prison', 'terminal', 'irish', 'coke', 'title card', 'man several', 'load', 'federal', 'final shot', 'gangster', 'rest', 'rest life', 'jewish', 'associate', 'court', 'simple', 'major', 'bloody', 'shot', 'meal', 'final', 'title', 'marriage', 'card', 'young waiter spider', 'young waiter', 'young sell carton', 'young sell', 'young lucchese crime', 'young lucchese', 'young jewish woman']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Pirates of the Caribbean: The Curse of the Black Pearl\n", "\n", "===Keywords===\n", "['pirate', 'island', 'medallion', 'curse', 'crew', 'coin', 'immortal', 'chest', 'rum', 'medallion mysterious', 'cursed', 'crew help', 'cache rum', 'blood curse', 'blood chest', 'son crew', 'pirate ship', 'loophole', 'blacksmith', 'cache', 'mysterious', 'blood', 'treasure', 'agreement', 'exchange', 'gold', 'cave', 'will', 'bay', 'young wreckage gold', 'young wreckage', 'year immortal dead', 'year immortal', 'year crew brig', 'year ceremony able', 'year ceremony', 'wreckage gold medallion', 'wreckage gold', 'will early marriage', 'will early', 'will cursed pirate', 'will cursed', 'water pirate ship', 'water pirate', 'vessel shipwreck sole', 'vessel shipwreck', 'underwater crew pirate', 'underwater crew', 'unconscious next day', 'unconscious next']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "WALL·E\n", "\n", "===Keywords===\n", "['plant', 'robot', 'pod', 'special machine', 'pod plant', 'machine platform', 'garbage', 'repair', 'auto', 'voice', 'special', 'platform', 'special machine platform', 'plasma cannon', 'plant special', 'hover chair', 'hibernation mode', 'electric kiss', 'deck special machine', 'deck special', 'central deck special', 'central deck', 'space', 'mother ship', 'mode', 'hibernation', 'directive', 'garage', 'machine', 'other human', 'garbage chute', 'confused', 'plasma', 'hover', 'find', 'chute', 'artifact', 'escape pod', 'chair', 'central', 'deck', 'century', 'cannon', 'escape', 'spaceship', 'dirt', 'earth', 'cabin', 'electric', 'return']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Kill Bill: Vol. 1\n", "\n", "===Keywords===\n", "['bride', 'sword', 'japanese', 'yakuza', 'chapter', 'orderly', 'yellow', 'mobile', 'coma', 'pickup', 'fight', 'vermin', 'name list', 'motorbike', 'bar keeper', 'knife', 'leg', 'trucker', 'syringe', 'dressed', 'distinctive', 'chapel', 'restaurant', 'age', 'bar', 'keeper', 'blood', 'revenge', 'murder', 'lieutenant', 'leather', 'red', 'flashback', 'floor', 'sheriff', 'massacre', 'limb', 'origin', 'fist', 'long', 'vicious', 'style', 'hospital', 'early', 'list', 'party', 'member', 'film', 'baby', 'american']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Terminator 2: Judgment Day\n", "\n", "===Keywords===\n", "['1000', 'metal', 'chip', 'grenade', 'liquid', 'launcher', 'mile', 'android', 'canal', 'grenade launcher', 'biker', 'elevator', 'arm', 'motorcycle', 'lab', 'computer', 'bike', 'orderly', 'cop', 'shot', 'floor', 'helicopter', 'molten', 'steel', 'foot', 'shotgun', 'van', 'pool', 'bar', 'nitrogen', 'key', 'processing', 'liquid nitrogen', 'foster parent', 'picture', 'nuclear', 'eye', 'playground', 'large truck', 'foster', 'form', 'desk', 'cigar', 'shoulder', 'guy', 'gas', 'processing screen', 'molten metal', 'liquid metal', 'cyborg']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "The Usual Suspects\n", "\n", "===Keywords===\n", "['smuggler', 'hungarian', 'verbal', 'criminal', 'hispanic', 'artist', 'boat', 'thief', 'cocaine', 'story', 'present story', 'immunity', 'hispanic passenger', 'hijacker', 'man ship', 'harbor', 'officer', 'phrase', 'mobster', 'jewel', 'present', 'corrupt', 'police station', 'passenger', 'unseen', 'lawyer', 'office', 'police officer', 'beginning', 'word various object', 'word various', 'will information mean', 'will information', 'wild streak middle', 'wild streak', 'whole affair beginning', 'week armored truck', 'week armored', 'way boat distance', 'way boat', 'version flashback attempt', 'version flashback', 'verbal whole affair', 'verbal whole', 'verbal personal effect', 'verbal personal', 'verbal depart immunity', 'verbal depart', 'vendetta business alia', 'vendetta business']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Joker\n", "\n", "===Keywords===\n", "['clown', 'show', 'subway', 'comedy', 'audience', 'apartment', 'joke', 'subway murder', 'murder', 'clip', 'detective', 'worker', 'train', 'sign', 'social worker', 'news murder', 'full clown', 'comedy show', 'clown up', 'clown gun', 'citizen clown', 'apartment subway murder', 'apartment subway', 'alley', 'subway train', 'self defense', 'rioter', 'death apartment', 'clown mask', 'theater', 'up', 'file', 'laughter', 'boss', 'only person', 'humor', 'condition', 'issue', 'depression', 'social', 'man room', 'co worker', 'involvement', 'funny', 'awkward', 'routine', 'front', 'document', 'news', 'terrified']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Braveheart\n", "\n", "===Keywords===\n", "['english', 'scottish', 'nobleman', 'king', 'magistrate', 'army', 'treachery', 'clan', 'garrison', 'mercy', 'invasion', 'son', 'throne', 'freedom', 'threat', 'crowd', 'year nobleman land', 'year nobleman', 'year affair meeting', 'year affair', 'worried threat rebellion', 'worried threat', 'word mercy quick', 'word mercy', 'wife distraction landing', 'wife distraction', 'watching crowd valor', 'watching crowd', 'watching', 'war next year', 'war next', 'vision crowd king', 'vision crowd', 'valor magistrate final', 'valor magistrate', 'troop field english', 'troop field', 'treason public torture', 'treason public', 'treachery father revenge', 'treachery father', 'treachery death father', 'treachery death', 'torture beheading king', 'torture beheading', 'throne treachery death', 'throne treachery', 'throne son worried', 'threat rebellion son', 'threat rebellion']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Star Wars: Episode VI - Return of the Jedi\n", "\n", "===Keywords===\n", "['fleet', 'imperial', 'dark side', 'imperial fleet', 'dark', 'shuttle', 'sail barge', 'battle', 'sail', 'barge', 'commander', 'scout', 'forest', 'moon', 'lightsaber', 'generator', 'sarlacc', 'imperial shuttle', 'forest moon', 'team', 'confirmation', 'carbonite', 'plank', 'pit', 'space', 'star destroyer', 'fighter', 'space station', 'star', 'side', 'destroyer', 'shield', 'station', 'bounty', 'court', 'bike', 'shuttle confirmation code', 'shuttle confirmation', 'shield generator', 'rancor', 'hand battle', 'fleet star', 'fleet meeting', 'fleet imperial fleet', 'fleet imperial', 'confirmation code', 'construction', 'sister', 'strike team', 'plan fleet']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Finding Nemo\n", "\n", "===Keywords===\n", "['fish', 'dentist', 'whale', 'other fish', 'filter', 'tank', 'turtle', 'sea', 'fish tank', 'pelican', 'boat', 'baggie', 'harbor', 'mask', 'sea turtle', 'reef', 'jellyfish', 'dory', 'diver', 'chum', 'anglerfish', 'shark', 'net', 'water', 'squirt', 'piping', 'mouth', 'school', 'torpedo', 'submarine', 'tank dentist', 'school fish', 'fish net', 'fish baggie', 'dental', 'barracuda', 'anemone', 'window', 'egg', 'tiny', 'ocean', 'direction', 'bag', 'son', 'drain', 'dock', 'right', 'counter', 'journey', 'whale tongue back']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "The Truman Show\n", "\n", "===Keywords===\n", "['island', 'sky', 'work', 'world', 'homeless man', 'wish', 'transmission', 'homeless', 'dome', 'basement', 'show', 'evening', 'sea', 'weather', 'real', 'young woman courtyard', 'work radio', 'woman courtyard', 'video feed', 'rotary', 'red sweater', 'good night', 'good evening good', 'good evening', 'good afternoon good', 'good afternoon', 'fear water', 'evening good night', 'evening good', 'case good afternoon', 'case good', 'afternoon good evening', 'afternoon good', 'actor', 'search', 'sweater', 'piece paper', 'album', 'entire', 'feed', 'shock', 'object', 'boat', 'road car', 'courtyard', 'water', 'idea', 'real world', 'frantic', 'street']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "The Lion King\n", "\n", "===Keywords===\n", "['hyena', 'king', 'lioness', 'scar', 'cub', 'gorge', 'jungle', 'tree', 'lion', 'herd', 'wildebeest', 'animal', 'paw', 'stampede', 'throne', 'past', 'roar', 'simba', 'hyena cub', 'cub cub', 'brave', 'graveyard', 'edge', 'place', 'night sky', 'sky', 'bone', 'warthog', 'throne thing', 'side gorge', 'position king', 'newborn cub', 'meerkat', 'king lioness', 'hyena real', 'herd wildebeest', 'glare', 'future king', 'elephant graveyard', 'chameleon', 'broken tree', 'bramble', 'base hyena', 'wind', 'singing', 'rightful', 'beetle', 'staff', 'newborn', 'grass']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Iron Man\n", "\n", "===Keywords===\n", "['reactor', 'suit', 'arc reactor', 'arc', 'weapon', 'terrorist', 'missile', 'armored suit', 'jet', 'developer', 'capture', 'flight', 'repulsor', 'armored', 'chest', 'cave', 'reactor reactor', 'chest piece', 'armor', 'system', 'project', 'guard suit', 'company', 'power', 'shrapnel', 'mini', 'reporter', 'heart', 'robotic', 'convoy', 'desert', 'computer', 'device', 'furious', 'conference', 'weapon developer', 'way cave', 'system suit', 'suit way cave', 'suit terrorist', 'stockpile weapon', 'stabilizer', 'robotic system', 'research facility', 'reactor shock wave', 'reactor shock', 'pepper', 'mini arc reactor', 'mini arc', 'injunction']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Up\n", "\n", "===Keywords===\n", "['balloon', 'zeppelin', 'bird', 'dog', 'collar', 'badge', 'explorer', 'device collar', 'porch', 'adventure', 'walker', 'alpha', 'device', 'master', 'snipe', 'red light collar', 'red light', 'light collar', 'house hose', 'helium balloon', 'helium', 'giant bird', 'adventure book', 'Dug', 'retirement home', 'air house', 'fog', 'find', 'chocolate', 'elderly', 'book', 'hose', 'retirement', 'journey', 'city', 'construction', 'promise', 'famous', 'worker', 'various', 'fall', 'thank', 'baby', 'one', 'giant', 'chair', 'high', 'zookeeper unable child', 'zookeeper unable', 'zookeeper']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Reservoir Dogs\n", "\n", "===Keywords===\n", "['heist', 'warehouse', 'blonde', 'diamond', 'jewelry store', 'flashback', 'jewelry', 'policeman', 'store', 'robbery', 'gasoline', 'orange', 'nightclub', 'getaway', 'meeting', 'upcoming', 'gang', 'criminal', 'warehouse police', 'upcoming robbery', 'policeman car', 'jeweler', 'criminal past', 'black', 'present', 'car woman', 'back seat', 'friendship', 'detective', 'detail', 'alarm', 'marijuana', 'story', 'handler', 'alias', 'cover', 'police detective', 'straight', 'rendezvous', 'pink', 'man room', 'informant', 'diner', 'beating', 'month', 'long', 'torture', 'long time', 'real name', 'local']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "One Flew Over the Cuckoo's Nest\n", "\n", "===Keywords===\n", "['ward', 'patient', 'orderly', 'vote', 'upset', 'session', 'hospital', 'supervisor office', 'submissive', 'stutter', 'patient ward', 'detention area', 'office', 'window', 'marble', 'counseling session', 'counseling', 'cigarette', 'girlfriend', 'supervisor', 'mental institution', 'basketball', 'institution', 'detention', 'player', 'submission', 'term', 'game', 'prison', 'size', 'nurse', 'friendship', 'mental', 'authority', 'rest', 'sex', 'youth session violence', 'youth session', 'young man ward', 'young brother figure', 'work schedule patient', 'work schedule', 'work detail battle', 'wisdom scene defiant', 'wisdom scene', 'wisdom', 'window patient girlfriend', 'window patient', 'window friend hospital', 'window friend']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Eternal Sunshine of the Spotless Mind\n", "\n", "===Keywords===\n", "['memory', 'procedure', 'affair', 'relationship', 'year nasty fight', 'year nasty', 'worthwhile', 'wife relationship lonely', 'way memory techie', 'way memory', 'unconscious second thought', 'unconscious second', 'time former lover', 'time former', 'thought memory much', 'thought memory', 'techie memory love', 'techie memory', 'techie', 'tape recording life', 'tape recording', 'story line relationship', 'story line', 'story arcs employee', 'story arcs', 'spirit other different', 'spirit other', 'separate related story', 'separate related', 'second thought memory', 'scene harm memory', 'scene harm', 'same procedure unconscious', 'same procedure', 'romantic entanglement critical', 'romantic entanglement', 'reverse memory good', 'reverse memory', 'relationship worthwhile', 'relationship mind doctor', 'relationship mind', 'relationship lonely inept', 'relationship lonely', 'relationship affair company', 'relationship affair', 'related story arcs', 'related story', 'related', 'recording life perfect', 'recording life']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "The Sixth Sense\n", "\n", "===Keywords===\n", "['ghost', 'illness', 'unfinished business', 'unfinished', 'videotape', 'boy', 'second', 'failure', 'patient', 'sick', 'wedding', 'funeral', 'young sister sick', 'young man gun', 'year old condition', 'wrist voice dark', 'wrist voice', 'world second job', 'world second', 'world living', 'work wife world', 'work wife', 'work trust dead', 'work trust', 'wife world second', 'wife world', 'wife second reason', 'wife second', 'wife husband wrist', 'wife husband', 'wife focus work', 'wife focus', 'wife event work', 'wife event', 'wife couch couple', 'wife couch', 'wife asleep home', 'wife asleep', 'wedding video background', 'wedding ring twist', 'voice dark cupboard', 'voice dark', 'videotape mother floor', 'videotape mother', 'videotape father videotape', 'videotape father', 'video background first', 'video background', 'unfinished business ghost', 'unfinished business failure']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Deadpool\n", "\n", "===Keywords===\n", "['thug', 'bar', 'cancer', 'mutant', 'carrier', 'van', 'chamber', 'goon', 'cab', 'blade', 'oxygen', 'hand bar', 'barometric chamber', 'barometric', 'ajax', 'superhero', 'men', 'movie', 'facility', 'mask', 'studio', 'bridge', 'cousin', 'round', 'big', 'motorcycle', 'speech', 'garbage', 'wrist', 'match', 'target', 'drink', 'girl', 'power', 'appearance', 'audience', 'hero', 'year mercenary hire', 'year mercenary', 'wrist hand garbage', 'wrist ankle wrist', 'worker ex boyfriend', 'worker ex', 'woman uggams back', 'woman uggams', 'whereabouts time blind', 'whereabouts time', 'weird life sexual', 'weird life', 'weapon round gun']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "The Shining\n", "\n", "===Keywords===\n", "['hotel', 'maze', 'snow cat', 'snow', 'axe', 'bathroom', 'caretaker', 'cat', 'hedge', 'footprint', 'bathroom door', 'butler', 'bat', 'sound', 'woman corpse', 'trail footprint', 'seizure', 'pediatrician', 'lounge', 'hotel maze', 'door bathroom', 'knife', 'pantry', 'drink', 'reflection', 'same', 'cabinet', 'bathtub', 'empty', 'bartender', 'direction', 'crazy', 'trail', 'mirror', 'hallway', 'vision', 'corpse', 'ball', 'job', 'accident', 'end', 'image', 'flight', 'step', 'story', 'young lady elderly', 'young caption 4th', 'young caption', 'young beautiful naked', 'young beautiful']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Toy Story\n", "\n", "===Keywords===\n", "['toy', 'other toy', 'voice', 'rocket', 'mom', 'mdash', 'bed', 'frog', 'doll', 'launch', 'window', 'string', 'toy window', 'sid', 'mutant toy', 'toy toy', 'mutant', 'fuse', 'baby', 'match', 'eyed', 'western', 'sarge', 'pull string', 'mission control', 'jug', 'bush', 'space', 'kid', 'poster', 'box', 'stair', 'toy room', 'rocket launch', 'alien', 'style', 'hall', 'speaker', 'soundtrack', 'cowboy', 'arm', 'back', 'dinosaur', 'birthday', 'light', 'pull', 'birthday party', 'present', 'spider', 'wind frog']\n", "\n", "**************************\n", "\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\n", "=====Title=====\n", "Mad Max: Fury Road\n", "\n", "===Keywords===\n", "['rig', 'biker', 'fuel', 'canyon', 'war rig', 'splendid', 'rictus', 'supply', 'water supply', 'water', 'switch', 'chase', 'hose', 'capable', 'sand', 'mask', 'transfusion', 'rig fuel', 'rig canyon', 'part face', 'kill switch', 'gallon fuel', 'fuel trailer', 'biker bandit', 'bandit', 'blood', 'wheel', 'army', 'muzzle', 'mud', 'human shield', 'gallon', 'face mask', 'chain', 'pursuer', 'overpass', 'storm', 'cutter', 'baby', 'image', 'kill', 'trailer', 'vehicle', 'old woman', 'lung', 'shoot', 'leader', 'road', 'pod', 'war']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Raiders of the Lost Ark\n", "\n", "===Keywords===\n", "['headpiece', 'idol', 'snake', 'nazi', 'ancient', 'precise', 'stone', 'sub', 'statue', 'idol idol', 'archaeologist', 'chamber', 'indy', 'bullwhip', 'mammoth', 'excavation', 'basket', 'german', 'crate', 'gigantic', 'location', 'site', 'plane', 'stone tablet', 'side headpiece', 'shaman', 'roof chamber', 'pedestal', 'nazi soldier', 'inscription', 'headpiece precise', 'headpiece man', 'headpiece indy', 'french archaeologist', 'burial site', 'cave', 'trap', 'tavern', 'tablet', 'burial', 'spirit', 'agent', 'dig', 'boulder', 'whip', 'jungle', 'elaborate', 'dart', 'soul', 'height']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Jurassic Park\n", "\n", "===Keywords===\n", "['raptor', 'dinosaur', 'park', 'tour', 'island', 'animal', 'visitor', 'velociraptor', 'amber', 'kid', 'creature', 'main', 'prey', 'embryo', 'resort', 'control room', 'velociraptor prey', 'raptor main', 'process animal', 'park tour', 'magnificent creature', 'magnificent', 'kid main', 'fossilized', 'foliage', 'electrified fence', 'death worker', 'meantime', 'security system', 'mosquito', 'grant', 'electrified', 'enclosure', 'dig', 'cunning', 'worker', 'system', 'control', 'kitchen', 'eccentric', 'containment', 'image', 'jeep', 'expert', 'unique', 'attraction', 'central', 'mine', 'sight', 'chase']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Gone Girl\n", "\n", "===Keywords===\n", "['clue', 'pregnancy', 'parent', 'sex', 'disappearance', 'medium', 'reporter', 'interview', 'blood', 'anniversary', 'question', 'diary', 'pregnant', 'hunt', 'woodshed', 'third clue', 'gift box', 'cunt', 'affair', 'sugar', 'credit card', 'gift', 'married', 'neighbor', 'hair', 'item', 'alarm', 'suicide', 'marriage', 'sample', 'test', 'walk', 'sheet', 'volunteer center', 'urine', 'untrustworthy', 'treasure hunt', 'smug', 'side story', 'semen sample', 'scavenger hunt', 'red pantie office', 'red pantie', 'real daughter', 'pregnancy test', 'police home', 'plan suicide', 'pie', 'pantie office', 'mallet']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Avengers: Endgame\n", "\n", "===Keywords===\n", "['quantum', 'stone', 'quantum realm', 'gauntlet', 'snap', 'time line', 'realm', 'banner', 'past', 'universe', 'present', 'past self', 'nanotech', 'plan', 'mantle', 'radiation', 'further', 'team', 'order', 'worthy', 'line', 'convincing', 'army', 'theory', 'purpose', 'future', 'self', 'briefcase', 'daughter', 'hammer', 'grief', 'energy', 'consciousness', 'battle', 'loss', 'survivor', 'rest', 'effect', 'effort', 'year quantum realm', 'year quantum', 'year hour quantum', 'year hour', 'worthy present nebula', 'worthy present', 'worthy army land', 'worthy army', 'world convincing team', 'world convincing', 'wife picnic lunch']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Avengers: Infinity War\n", "\n", "===Keywords===\n", "['gauntlet', 'quill', 'forge', 'goal', 'dwarf', 'strange', 'stone ship', 'new weapon', 'army', 'planet', 'stone', 'distress', 'battle', 'weapon', 'contact', 'giant', 'world planet keeper', 'world planet', 'world child goal', 'witness scene street', 'witness scene', 'weapon travel way', 'weapon travel', 'weapon power task', 'weapon capable dwarven', 'weapon capable', 'way situation quill', 'way situation', 'vision forehead place', 'vision forehead', 'universe fruition people', 'universe fruition', 'united army defense', 'united army', 'unable battle strange', 'unable battle', 'ultimate goal post', 'ultimate goal', 'travel way situation', 'travel way', 'torture chamber ship', 'torture chamber', 'tide obsidian tearful', 'tide obsidian', 'technology stone ship', 'technology stone', 'tearful event chest', 'tearful event', 'task outrider army', 'task outrider']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Good Will Hunting\n", "\n", "===Keywords===\n", "['romantic relationship', 'relationship', 'theorem', 'premature death', 'premature', 'laborer', 'romantic', 'potential', 'steady', 'job interview', 'future', 'interview', 'later', 'genius', 'defensive', 'challenge', 'level', 'bar', 'therapy', 'job', 'talent', 'session', 'wish', 'emotional', 'self', 'professional', 'hostile', 'victim', 'good friend', 'student', 'work', 'defense', 'knowledge', 'government', 'step', 'youth year kindergarten', 'youth year', 'young woman bar', 'year primary reason', 'year primary', 'year kindergarten imprisonment', 'year kindergarten', 'year act board', 'year act', 'world movie fulfillment', 'world movie', 'work joke incapable', 'work joke', 'work goodbye honesty', 'work goodbye']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "No Country for Old Men\n", "\n", "===Keywords===\n", "['motel', 'case', 'deputy', 'catalog case', 'catalog', 'captive bolt pistol', 'captive bolt', 'bolt pistol', 'duct', 'hotel', 'pickup', 'sheriff', 'bolt', 'border', 'pit bull', 'money case', 'driver', 'pistol', 'businessman', 'mexican', 'bull', 'coin', 'shotgun', 'captive', 'chicken', 'room money case', 'first room', 'room money', 'pit', 'motel room', 'farmer', 'trailer', 'clerk', 'station', 'room room', 'pickup truck', 'desert', 'boot', 'rise', 'device', 'phone', 'beer', 'truck man truck', 'truck chicken', 'transponder', 'tent pole duct', 'tent pole', 'shotgun round', 'room signal', 'pronghorn']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "The Walking Dead\n", "\n", "===Keywords===\n", "['zombie', 'comic', 'survivor', 'zombie toll survivor', 'zombie toll', 'zombie country time', 'zombie country', 'zombie apocalypse group', 'zombie apocalypse', 'year zombie apocalypse', 'year zombie', 'world zombie toll', 'world zombie', 'willing official', 'toll survivor interpersonal', 'toll survivor', 'time character constant', 'time character', 'survivor police officer', 'survivor police', 'survivor interpersonal conflict', 'survivor interpersonal', 'survival zombie country', 'survival zombie', 'story month year', 'story month', 'series story month', 'series story', 'secure home comic', 'secure home', 'search safe secure', 'search safe', 'safe secure home', 'safe secure', 'police officer search', 'officer search safe', 'officer search', 'month year zombie', 'death willing official', 'death willing', 'danger survival zombie', 'danger survival', 'country time character', 'country time', 'constant exposure death', 'constant exposure', 'conflict great danger', 'conflict great', 'comic challenge life', 'comic challenge']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Star Wars: Episode VII - The Force Awakens\n", "\n", "===Keywords===\n", "['stormtrooper', 'first order', 'lightsaber', 'fighter', 'map', 'planet', 'saber', 'base', 'blaster', 'order', 'forest', 'pilot', 'snowy', 'resistance', 'droid', 'vision', 'wing', 'snowy forest', 'mind', 'destroyer', 'shield', 'sand', 'weak point', 'rest base', 'red fiery', 'red beam', 'pilot seat', 'order stormtrooper', 'map location', 'lightsaber stormtrooper', 'lightsaber saber', 'cantina', 'jacket', 'impressed', 'red', 'town', 'troop ship', 'secret mission', 'fiery', 'crash land', 'troop', 'beam', 'escape', 'wing pilot', 'wing fighter', 'scrap', 'scavenger', 'hut', 'crash', 'trench']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "A Beautiful Mind\n", "\n", "===Keywords===\n", "['hallucination', 'psychiatric', 'student', 'mathematic', 'intellectual', 'delusion', 'soviet', 'medication', 'psychiatric hospital', 'psychiatric facility', 'prestigious', 'friend year', 'antipsychotic', 'agent secret', 'thesis', 'graduate student', 'roommate', 'graduate', 'facility', 'niece', 'mailbox', 'work', 'theory', 'secret', 'assignment', 'fact', 'office', 'goodbye', 'good friend', 'class', 'condition', 'young niece mysterious', 'young niece', 'year tearful goodbye', 'year tearful', 'year class interesting', 'year class', 'work house child', 'work harsh rejection', 'work harsh', 'work game theory', 'work game', 'work concept dynamic', 'work concept', 'woman local bar', 'woman local', 'woman bar fruitful', 'wife thing ground', 'wife thing', 'wife intellectual capacity']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Stranger Things\n", "\n", "===Keywords===\n", "['monster', 'light', 'trio', 'agent', 'bike', 'compass', 'gate', 'creature', 'comm radio', 'comm', 'school', 'deer', 'same', 'radio', 'deputy', 'handyman', 'astral', 'same time', 'forest', 'root', 'information', 'trap', 'nosebleed', 'duo', 'scared', 'supply', 'bathroom', 'search party', 'quarry', 'gym', 'fireball', 'owner', 'funeral', 'wood', 'shed', 'ok', 'wallpaper', 'waffle', 'slug like creature', 'slug like', 'sensory deprivation', 'morgue', 'light monster', 'flea', 'black root', 'acrobat', 'wall', 'picture', 'like', 'residence']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Friends\n", "\n", "===Keywords===\n", "['member group', 'series', 'roommate', 'later season', 'member', 'relationship', 'job', 'traumatic', 'season', 'later', 'frequent', 'several year', 'relation', 'humor', 'self', 'share', 'period', 'lover', 'parent', 'behavior', 'marriage', 'various', 'brother', 'sex', 'year series runaway', 'year series', 'year other several', 'year old few', 'year new roommate', 'year new', 'woman career later', 'woman career', 'witted gregarious charming', 'witted gregarious', 'wife lesbian lover', 'wife lesbian', 'wealthy father expense', 'wealthy father', 'waitress coffeehouse actual', 'waitress coffeehouse', 'vegetarian tree hugger', 'vegetarian tree', 'various woman career', 'various woman', 'various colleague period', 'various colleague', 'upset people homosexual', 'upset people', 'unsteady nature profession', 'unsteady nature']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Catch Me If You Can\n", "\n", "===Keywords===\n", "['check', 'pilot', 'airline', 'uniform', 'fraud', 'parent', 'airport', 'bank', 'substitute teacher', 'substitute', 'pilot uniform', 'lawyer doctor', 'check fraud', 'airline pilot', 'hotel', 'stewardess', 'french', 'lawyer', 'medical', 'ruse', 'agent', 'class', 'engagement', 'prison', 'plane', 'time check', 'teller', 'staff medical', 'scam', 'printer', 'million dollar', 'french police', 'forgery', 'fake check', 'class substitute teacher', 'class substitute', 'checkbook', 'boss check', 'bank teller', 'agent man', 'doctor', 'fake', 'visit', 'dollar', 'loan', 'forger', 'exam', 'diploma', 'mother father', 'suit']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "The Hunger Games\n", "\n", "===Keywords===\n", "['tribute', 'district', 'reaping', 'other tribute', 'stylist', 'opening ceremony', 'district tribute', 'victor', 'ceremony', 'baker', 'kindness', 'hunting', 'wood', 'girl', 'train', 'strength', 'age', 'young sister girl', 'young mother survival', 'young man little', 'year young mother', 'year young', 'year old narrator', 'year hunting game', 'year hunting', 'wracking time boy', 'wracking time', 'wracking', 'wood prowess bow', 'wood prowess', 'wood people district', 'wood people', 'winner district fight', 'winner district', 'weight lifting other', 'weight lifting', 'way home wood', 'volunteer place young', 'volunteer place', 'victor victor district', 'victor victor', 'victor district gift', 'victor district', 'uprising tyrannical cruel', 'uprising tyrannical', 'unrivaled skill feistiness', 'unrivaled skill', 'unrivaled', 'tyrannical cruel odd', 'tyrannical cruel']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Monsters, Inc.\n", "\n", "===Keywords===\n", "['monster', 'boo', 'scare', 'scream', 'energy', 'scare floor', 'monster world', 'energy scream', 'human world', 'company', 'world', 'human child', 'door door', 'bedroom', 'work area scare', 'training room', 'scream machine', 'scream human child', 'scream human', 'scare skill', 'scare floor door', 'room employee scare', 'room employee', 'monster costume', 'human world child', 'huge warehouse', 'girl monster world', 'girl monster', 'energy scream human', 'energy crisis', 'employee scare skill', 'employee scare', 'door work area', 'door work', 'door scare floor', 'door scare', 'door portal', 'child energy', 'child bedroom closet', 'child bedroom', 'boo door', 'bedroom closet', 'area scare floor', 'area scare', 'factory', 'girl', 'work area', 'simulator', 'crisis', 'employee']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Sherlock\n", "\n", "===Keywords===\n", "['camera phone', 'british government', 'series', 'cabbie', 'puzzle', 'british', 'crime', 'case', 'phone', 'pool', 'government', 'year hallucinogenic drug', 'year hallucinogenic', 'wrath british government', 'wrath british', 'woman mind month', 'woman mind', 'weapon nearby military', 'weapon nearby', 'veteran brilliant consulting', 'veteran brilliant', 'unseen puzzle undetected', 'unseen puzzle', 'unnoticed scene cabbie', 'unnoticed scene', 'undetected crime additional', 'undetected crime', 'time death innocent', 'swimming pool series', 'study cabbi serial', 'study cabbi', 'smuggling ring series', 'smuggling ring', 'side encounter cellphone', 'side encounter', 'series swimming pool', 'series swimming', 'series puzzle unseen', 'series puzzle', 'series 2moriarty pool', 'series 2moriarty', 'series 1wounded afghan', 'series 1wounded', 'serial killer confrontation', 'security message list', 'security message', 'security leak last', 'security leak', 'scene cabbie fear', 'scene cabbie']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Slumdog Millionaire\n", "\n", "===Keywords===\n", "['chapter story', 'question', 'slum', 'chapter', 'story', 'answer', 'young man apparent', 'year old orphan', 'whole nation question', 'whole nation', 'viewer about', 'vicious encounter local', 'vicious encounter', 'suspicion cheating street', 'suspicion cheating', 'street kid desperate', 'story life slum', 'story key answer', 'story key', 'story answer impossible', 'story answer', 'staggering rupee india¹s', 'staggering rupee', 'slum brother adventure', 'slum brother', 'slum about big', 'slum about', 'show¹s question chapter', 'show¹s question', 'show¹s', 'show night police', 'show night', 'rupee india¹s millionaire', 'rupee india¹s', 'rupee', 'road vicious encounter', 'road vicious', 'rich game new', 'rich game', 'quiz question mystery', 'quiz question', 'question viewer about', 'question viewer', 'question staggering rupee', 'question staggering', 'question mystery young', 'question mystery', 'question chapter story', 'question chapter', 'police suspicion cheating']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "The Terminator\n", "\n", "===Keywords===\n", "['killer', 'punk', 'motel', 'precinct', 'future', 'cop', 'shotgun', 'club', 'alley', 'pipe bomb', 'bomb', 'owner', 'squad car', 'android', 'pistol', 'muscular', 'blast', 'sergeant', 'tank', 'dog', 'phone', 'weaponry future', 'reese', 'police precinct', 'phone book name', 'man punk', 'listing', 'killer several', 'killer killer', 'floor killer', 'desk sergeant', 'dance club', 'club killer', 'car killer', 'book name', 'squad', 'voice', 'shotgun blast', 'phone book', 'muscular man', 'homeless man', 'future human', 'pipe', 'date', 'machine', 'city', 'woman name', 'valiant', 'gas', 'front door']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Die Hard\n", "\n", "===Keywords===\n", "['hostage', 'terrorist', 'detonator', 'roof', 'walkie talkie', 'walkie', 'talkie', 'vault', 'elevator', 'limo', 'conference room', 'helicopter', 'situation', 'demand', 'conference', 'way building', 'roof walkie talkie', 'roof walkie', 'man hostage', 'maiden name', 'maiden', 'lock vault', 'helipad', 'detonator hostage', 'bag detonator', 'attempt man', 'bag', 'limo driver', 'car front', 'security', 'radio', 'part plan', 'building man', 'man fire', 'getaway', 'party', 'window', 'vehicle', 'confusion', 'airport', 'team', 'attention', 'able', 'trap', 'rocket', 'henchman', 'lock', 'bond', 'alarm', 'force']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Alien\n", "\n", "===Keywords===\n", "['alien', 'creature', 'shuttle', 'crew', 'flamethrower', 'hypersleep', 'signal', 'duct', 'planet', 'airlock', 'cat', 'console', 'space', 'infirmary', 'deck', 'egg', 'low deck', 'strange', 'mechanism', 'refinery', 'organism', 'wall', 'ladder', 'container', 'self destruct', 'repair', 'destruct', 'white liquid', 'self destruct mechanism', 'science officer', 'quarantine', 'planetoid', 'mother console', 'mother answer', 'mess hall', 'lifeform', 'harpoon', 'destruct mechanism', 'creature face', 'science', 'space suit', 'low', 'computer', 'procedure', 'protocol', 'mood', 'liquid', 'intercom', 'air shaft', 'team']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Snatch\n", "\n", "===Keywords===\n", "['turkish', 'pawnbroker', 'diamond', 'gypsy', 'caravan', 'dog', 'bookie', 'goon', 'hare', 'briefcase', 'other fighter', 'pawnshop', 'window', 'campsite', 'fourth', 'interested', 'bet', 'cold', 'fighter', 'punch', 'new caravan', 'karat', 'defective', 'replica', 'dog dog', 'bare knuckle', 'round', 'knuckle', 'bout', 'fight', 'milk', 'arm', 'bare', 'pound', 'vet', 'van cold', 'unseen man turkish', 'unseen man', 'turkish ready', 'turkish dog', 'turkish car', 'turkish campsite', 'turkish big', 'slot machine', 'slot', 'sack head', 'punch other fighter', 'punch other', 'pissed', 'pawnbroker gun']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Harry Potter and the Deathly Hallows: Part 2\n", "\n", "===Keywords===\n", "['wand', 'master', 'master wand', 'spell', 'castle', 'vault', 'trio', 'curse', 'spell other', 'snitch', 'boathouse', 'basilisk', 'alive alive', 'sword', 'army', 'alive', 'dragon', 'thief', 'hat', 'school', 'year parent other', 'wizard help curse', 'wizard help', 'witness boathouse tear', 'witness boathouse', 'way group resistance', 'way diadem basilisk', 'way diadem', 'way castle office', 'way castle', 'wand wand forever', 'wand true master', 'wand true', 'wand previous master', 'wand previous', 'wand master wand', 'wand master', 'wand forever 19', 'wand forever', 'vulnerable ready speech', 'vulnerable ready', 'voldemort alive alive', 'voldemort alive', 'voldemort', 'vision news angry', 'vision news', 'vault sword thief', 'vault sword', 'vault exchange chance', 'vault exchange']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Requiem for a Dream\n", "\n", "===Keywords===\n", "['drug', 'tv', 'heroin', 'mental hospital', 'refrigerator', 'supplier', 'diet', 'doctor', 'arm', 'hospital', 'infomercial', 'tv set', 'dress', 'work detail', 'purchase', 'mental', 'set', 'hallucination', 'pill', 'spot arm', 'new tv', 'mob figure', 'hallucination refrigerator', 'drug gang', 'doctor drug', 'doctor arm', 'cot', 'black spot arm', 'black spot', 'television', 'shoe box', 'red dress', 'psychosis', 'detail', 'drug money', 'summer', 'dream', 'winter', 'ass', 'lot', 'regular', 'couch', 'clothing', 'shoe', 'mob', 'prison', 'apartment', 'weight', 'nurse', 'major']\n", "\n", "**************************\n", "\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\n", "=====Title=====\n", "Intouchables\n", "\n", "===Keywords===\n", "['carer', 'music', 'aunt', 'young cousin', 'suburb', 'quadriplegic', 'parisian', 'paragliding', 'music music', 'mansion', 'candidate', 'disability', 'care', 'film', 'flat', 'job', 'painting', 'private', 'uncle', 'modern', 'wheelchair', 'cousin', 'date', 'accident', 'young cousin trouble', 'young cousin new', 'worried contact story', 'worried contact', 'woman reaction disability', 'woman reaction', 'window film', 'wife child order', 'wheelchair suburb friend', 'wheelchair suburb', 'wheelchair aide picture', 'wheelchair aide', 'welfare benefit casual', 'welfare benefit', 'weekend envelope euro', 'weekend envelope', 'view table good', 'view table', 'up artist young', 'up artist', 'uncle aunt bore', 'uncle adoptive parent', 'uncle adoptive', 'trouble gang refuge', 'trouble gang', 'trial period carer']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Gravity\n", "\n", "===Keywords===\n", "['capsule', 'debris', 'thruster', 'tether', 'station', 'debris field', 'space', 'space station', 'parachute', 'spacecraft', 'thruster pack', 'spacesuit', 'parachute line', 'module', 'orbit', 'oxygen', 'hatch', 'extinguisher', 'fuel', 'chinese', 'pack', 'unable capsule', 'thruster pack tether', 'thruster fuel', 'spacewalk', 'pack tether', 'debris field orbit', 'chinese space station', 'chinese space', 'capsule station', 'field', 'field orbit', 'capsule capsule', 'satellite', 'flow', 'line', 'fire extinguisher', 'shuttle', 'last moment', 'engineer', 'crew', 'strike', 'atmosphere', 'robot', 'cabin', 'consciousness', 'wrong tank empty', 'wrong tank', 'way module fire', 'way module']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "The Martian\n", "\n", "===Keywords===\n", "['crew', 'rover', 'habitat', 'mission', 'martian', 'battery', 'solar', 'satellite', 'potato', 'food', 'rocket', 'video log', 'solar panel', 'probe', 'sol', 'able message', 'antenna', 'airlock', 'launch', 'supply', 'plan', 'storm', 'site', 'log', 'year worth food', 'worth food', 'potato crop', 'martian landscape', 'landing site', 'hydrazine', 'habitat potato', 'botanist', 'year worth', 'international', 'food supply', 'booster rocket', 'booster', 'panel', 'camera', 'month', 'message', 'crop', 'course', 'control', 'tether', 'video', 'able', 'touch', 'crew member', 'landscape']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Iron Man Three\n", "\n", "===Keywords===\n", "['suit', 'bombing', 'attack', 'dog tag', 'airwave', 'potato gun', 'tag', 'user', 'flaw', 'power', 'potato', 'reporter', 'visitor', 'experimental', 'tv', 'piece', 'flight', 'dog', 'user body', 'suit piece', 'several suit', 'potato gun thank', 'piece course', 'man suit', 'live television', 'gun thank', 'backing', 'anxiety attack', 'american airwave', 'prototype suit', 'mansion', 'soldier', 'agent', 'anxiety', 'experiment', 'course', 'blast', 'brain', 'address', 'disability', 'demon', 'biological', 'badge', 'american', 'prototype', 'personnel', 'military', 'oil', 'frustrated', 'estate']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Toy Story 3\n", "\n", "===Keywords===\n", "['toy', 'other toy', 'voice', 'box', 'mom', 'daycare', 'attic', 'voice voice', 'trash bag', 'playtime', 'dumpster', 'voice voice voice', 'toddler', 'trash', 'toy toy', 'playground', 'dump', 'toy voice', 'room toy', 'recess', 'mom box', 'dump truck', 'demo', 'attic box', 'mode', 'alien', 'donation', 'garbage', 'bag', 'chute', 'kid', 'lid', 'telephone', 'excited', 'doll', 'example', 'little', 'machine', 'tag', 'trash bag toy', 'toy voice voice', 'toy porch', 'toy machine', 'toy first playtime', 'toy first', 'toy excited group', 'toy excited', 'toy box', 'time toy', 'room mom']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "A Clockwork Orange\n", "\n", "===Keywords===\n", "['droog', '9th', 'constable', 'chaplain', 'prison', 'gang', 'bum', 'government', 'prison chaplain', 'health farm', 'parent', 'violence', 'treatment', 'writer', 'conditioning', 'health', 'second floor', 'rape', 'auditorium', 'milk', 'bath', 'political', 'victim modern age', 'victim modern', 'underpass', 'ultra violence', 'truncheon', 'sign home', 'sex violence', 'second floor window', 'plate spaghetti', 'modern age', 'lad', 'homeowner', 'gang rape', 'country house', 'farm', 'eye', 'subject', 'spaghetti', 'proprietress', 'floor window', 'victim', 'music', 'second', 'ultra', 'violent', 'apartment', 'wine', 'stereo']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Avengers: Age of Ultron\n", "\n", "===Keywords===\n", "['sceptre', 'drone', 'synthetic', 'synthetic body', 'gem', 'vibranium', 'team', 'synthetic body body', 'sceptre gem', 'robot drone', 'global', 'body body', 'twin', 'machine', 'vision', 'evacuation', 'base', 'hallucination', 'humanity', 'ally', 'robot', 'city', 'mind', 'program', 'worthy ally hammer', 'worthy ally', 'worldwide backlash destruction', 'worldwide backlash', 'wife child secret', 'weapon company trio', 'weapon company', 'vulnerable vengeful post', 'vulnerable vengeful', 'vision worthy ally', 'vision worthy', 'vision nearby city', 'vision bleak possible', 'vision bleak', 'victory party recapture', 'victory party', 'vibranium vision nearby', 'vibranium vision', 'vibranium sceptre gem', 'vibranium sceptre', 'vibranium machine large', 'vibranium machine', 'vengeful post primary', 'vengeful post', 'vengeful', 'unwilling depart last']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "The Hobbit: An Unexpected Journey\n", "\n", "===Keywords===\n", "['dwarf', 'goblin', 'orc', 'troll', 'sword', 'pony', 'adventure', 'kingdom', 'hobbit', 'cave', 'elf', 'elven', 'evil', 'riddle', 'eagle', 'burglar', 'mountain', 'wizard', 'map', 'dragon', 'gold', 'warg', 'troll troll', 'sword blue', 'sleigh', 'rabbit sleigh', 'other dwarf', 'object cloth', 'moth', 'member expedition', 'goblin dwarf', 'goblin cave', 'elven sword', 'elf dwarf', 'dwarven kingdom', 'dwarf sword', 'crevice', 'wooden', 'king', 'party', 'expedition', 'dwarven', 'company', 'cloth', 'blue', 'rabbit', 'quest', 'invisible', 'contract', 'tree']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Thor\n", "\n", "===Keywords===\n", "['frost giant', 'frost', 'casket', 'power casket', 'hammer', 'giant', 'portal', 'earth', 'power', 'crater', 'worthy', 'van', 'frozen', 'satellite crash', 'giant power casket', 'giant power', 'frost giant power', 'king', 'blond', 'scientist', 'agent', 'realm', 'west', 'satellite', 'conscious', 'return', 'intruder', 'ex', 'beast', 'planet', 'peace', 'site', 'desert', 'crash', 'hero', 'young group side', 'young group', 'year elaborate ceremony', 'year elaborate', 'worthy power earth', 'worthy power', 'worthy one king', 'worthy one', 'worthy crater return', 'worthy crater', 'worth look', 'wormhole frost giant', 'wormhole frost', 'whosoever hammer worthy', 'whosoever hammer']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Captain America: The First Avenger\n", "\n", "===Keywords===\n", "['cube', 'shield', 'plane', 'capsule', 'application', 'caretaker', 'base', 'soldier', '107th', 'serum', 'map', 'lab', 'bully', 'blue', 'muscle', 'movie', 'tall', 'weapon', 'bunker', 'white blue', 'roadster', 'red white blue', 'red white', 'taxi', 'procedure', 'prior', 'basis', 'remain', 'white', 'army', 'uniform', 'success', 'energy', 'front', 'platoon', 'cockpit', 'radio', 'craft', 'facility', 'surprised', 'pole', 'fury', 'weapon lab', 'war man', 'vita ray', 'vita', 'unstoppable energy', 'team zip line', 'team zip', 'secret military']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Scarface\n", "\n", "===Keywords===\n", "['cocaine', 'journalist', 'cartel', 'drug', 'mansion', 'cuban', 'hit', 'risk job', 'kilogram cocaine', 'kilogram', 'bolivian', 'assassin', 'hit man', 'distributor', 'distribution', 'balcony', 'nightclub', 'deal', 'business', 'job', 'mercenary', 'risk', 'time return', 'north american distributor', 'north american', 'nationwide', 'man balcony', 'low risk job', 'low risk', 'journalist car', 'flashy', 'cocaine money', 'boulevard', 'bomb journalist car', 'bomb journalist', 'big cartel', 'american distributor', 'office', 'dealer', 'bodyguard', 'crew', 'cash', 'transportation', 'strung', 'grand staircase', 'deal time', 'altercation', 'henchman', 'sub machine gun', 'sub machine']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Captain America: The Winter Soldier\n", "\n", "===Keywords===\n", "['fury', 'agent', 'flash drive', 'flash', 'drive', 'chip', 'assassin', 'police car', 'shield', 'computer', 'car car', 'pirate', 'elevator', 'other agent', 'police car car', 'car fury', 'window', 'target', 'goon', 'duo', 'intersection', 'hero', 'member', 'file', 'arm', 'display', 'second', 'missile', 'team', 'disguise', 'roof', 'tripod', 'protection fury', 'police car fury', 'pirate hostage', 'onboard computer', 'onboard', 'intersection police car', 'intersection police', 'first police car', 'first police', 'eyepatch', 'duo other agent', 'duo other', 'council member', 'computer safe', 'chip system', 'car black man', 'agent car', 'strike team']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Donnie Darko\n", "\n", "===Keywords===\n", "['troubled', 'school', 'high school', 'time travel', 'time tunnel', 'red eye flight', 'eye flight', 'tunnel', 'bunny', 'medication', 'travel', 'red eye', 'high', 'eye', 'hallucination', 'responsible vandalism', 'jet engine', 'fluid light', 'conservative', 'bunny costume', 'jet', 'vandalism', 'ax', 'engine', 'therapist', 'day hour', 'right eye', 'flight', 'teenager', 'fluid', 'red', 'town', 'tube', 'costume', 'material', 'boyfriend', 'party', 'use', 'responsible', 'class', 'teacher', 'bedroom', 'roof', 'young boy family', 'young adult gruesome', 'young adult', 'wound sorry attention', 'wound sorry', 'wound right eye', 'wound right']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "The Pianist\n", "\n", "===Keywords===\n", "['ghetto', 'jewish', 'polish', 'german', 'piano', 'pianist', 'russian', 'uprising', 'apartment', 'resistance', 'brick', 'radio', 'wall ghetto', 'vacant apartment', 'starvation', 'russian army', 'polish resistance', 'jewish ghetto', 'german officer', 'father paper', 'family war', 'officer', 'wall', 'radio station', 'musician', 'few more', 'war', 'city', 'vacant', 'rest family', 'candy', 'sack', 'caretaker', 'train', 'family member', 'condition', 'husband', 'food', 'fence', 'non', 'camp', 'weapon', 'street', 'job', 'address', 'emergency', 'card', 'zloty piece candy', 'zloty piece', 'zloty']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "The Big Lebowski\n", "\n", "===Keywords===\n", "['dude', 'rug', 'kidnapper', 'bowling', 'nihilist', 'toe', 'alley', 'lane', 'joint', 'briefcase', 'mansion', 'thug', 'ringer', 'bowling ball', 'bowling alley', 'ball', 'apartment', 'phone', 'fucking', 'ashe', 'rug bowling', 'pinky toe', 'pinky', 'german nihilist', 'ball lane', 'ransom', 'doctor', 'portable', 'polish', 'league', 'german', 'ring', 'study', 'issue', 'drink', 'clothe', 'blue', 'window', 'floor', 'strike', 'pin', 'phone ring', 'tire', 'iron', 'beer', 'woman rug', 'white russian drink', 'white russian', 'urn', 'sarsaparilla']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "300\n", "\n", "===Keywords===\n", "['persian', 'spartan', 'leonida', 'army', 'persian army', 'dome', 'narrow', 'shield', 'warrior', 'spartan warrior', 'leonida reluctant', 'goat path', 'goat', 'ephialte', 'age young', 'phalanx', 'messenger', 'emissary', 'terrain', 'surrender', 'priest', 'necklace', 'battle', 'passage', 'wealth', 'council', 'submission', 'general', 'arrow', 'soldier', 'gold', 'king', 'boy', 'reluctant', 'rock', 'age', 'young wolf narrow', 'young wolf', 'young boy mother', 'year messenger submission', 'year messenger', 'woman wealth wish', 'wolf narrow passage', 'wolf narrow', 'wish god king', 'wish god', 'wilderness man rite', 'wilderness man', 'wife rain arrow', 'wife goodbye shield']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Star Wars: Episode I - The Phantom Menace\n", "\n", "===Keywords===\n", "['droid', 'palace', 'capital', 'apprentice', 'reactor', 'droid army', 'reactor core', 'planet', 'vote', 'alliance', 'core', 'army', 'master', 'freedom', 'battle', 'mysterious', 'year old human', 'worried old training', 'worried old', 'world liberation newborn', 'world liberation', 'way throne room', 'way throne', 'way palace dogfight', 'way palace', 'way command center', 'way command', 'vote power nomination', 'vote power', 'vote confidence vote', 'vote confidence', 'victory career great', 'victory career', 'unsure large celebration', 'unsure large', 'unknown league mysterious', 'unknown league', 'underwater settlement leader', 'underwater settlement', 'trick submarine capital', 'trick submarine', 'training fear anger', 'training fear', 'trade dispute apprentice', 'trade dispute', 'torpedo droid army', 'torpedo droid', 'throne room infiltration', 'throne room', 'team other alternate']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Taxi Driver\n", "\n", "===Keywords===\n", "['taxi', 'sport', 'cab', 'bouncer', 'shift', 'pimp', 'driver', 'senator', 'apartment', 'coffee', 'taxi driver', 'presidential', 'personnel officer', 'bouncer hand', 'porn theater', 'apartment gun', 'theater', 'night shift', 'porn', 'night time', 'medium', 'depressed', 'campaign', 'rally', 'personnel', 'impression', 'bullet', 'social', 'intense', 'grocery', 'prostitute', 'diner', 'dealer', 'spy', 'failure', 'break', 'mirror', 'date', 'job', 'sex', 'public', 'letter', 'hero', 'crowd', 'young man year', 'young boy school', 'year origin hometown', 'year origin', 'year old child', 'worker nerve date']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Sin City\n", "\n", "===Keywords===\n", "['prostitute', 'tar pit', 'other prostitute', 'tar', 'beautiful', 'pit', 'police officer', 'love', 'crime', 'officer', 'priest', 'mercenary', 'apartment', 'yellow man', 'misshapen', 'cell', 'hail', 'cannibal', 'surgery', 'cop', 'responsible death', 'powerful', 'yellow', 'mob', 'farm', 'prison', 'trial', 'hospital', 'silent', 'bar', 'violence', 'responsible', 'evil', 'letter', 'young woman other', 'young hospital prison', 'yellow man wretched', 'yellow man title', 'year solitary confinement', 'year solitary', 'year old voiceover', 'wrist ability pet', 'wrist ability', 'wretched stench cell', 'wretched stench', 'wretched', 'wound month hospital', 'wound month', 'worried exchange release', 'worried exchange']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Whiplash\n", "\n", "===Keywords===\n", "['drum', 'class', 'tempo', 'drummer', 'band', 'core drummer', 'core', 'sheet', 'music sheet', 'jazz', 'drumstick', 'band new', 'music', 'song', 'competition', 'whiplash', 'song whiplash', 'sheet music', 'saxophonist', 'pitcher', 'new core drummer', 'new core', 'jazz competition', 'hour class', 'home drum', 'drumstick car', 'classroom class', 'class drum', 'wrath', 'classroom', 'left hand', 'school', 'parent', 'break', 'stage', 'lawyer', 'ice', 'left', 'student', 'club', 'chair', 'audience', 'wreckage injury face', 'wreckage injury', 'wrath tempo process', 'wrath tempo', 'wrath class break', 'wrath class', 'whole band upset', 'whole band']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Iron Man 2\n", "\n", "===Keywords===\n", "['drone', 'suit', 'armor', 'palladium', 'whip', 'poisoning', 'ceo', 'world peace', 'palladium poisoning', 'diorama', 'armored suit', 'reactor', 'element', 'armored', 'stark', 'potato', 'arc reactor', 'arc', 'birthday party', 'chest', 'peace', 'issue', 'race', 'hearing', 'version', 'investigation', 'version armor', 'palladium chest', 'notary', 'new element', 'late invention', 'last birthday party', 'last birthday', 'hungover', 'expo', 'energy whip', 'blood palladium', 'armor drone', 'particle', 'first movie', 'doughnut', 'chest arc reactor', 'chest arc', 'birthday', 'agent', 'world', 'event', 'energy', 'committee', 'medal']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "The Big Bang Theory\n", "\n", "===Keywords===\n", "['page', 'title first page', 'title first', 'submission guide', 'page more submission', 'page more', 'page button bottom', 'page button', 'more submission guide', 'more submission', 'guide', 'submission', 'button', 'title', 'bottom']\n", "\n", "**************************\n", "\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\n", "=====Title=====\n", "Gran Torino\n", "\n", "===Keywords===\n", "['gang', 'neighborhood', 'gang member', 'confession', 'gift', 'officer house', 'gang house', 'basement', 'sin', 'eulogy', 'lawn', 'hispanic', 'grandmother', 'conflict', 'funeral', 'teenager', 'cake', 'sergeant', 'confrontation', 'porch', 'son', 'shootout', 'jacket', 'neighbor', 'birthday', 'cigarette', 'member', 'drive', 'rifle', 'anger', 'young little patience', 'young little', 'young enemy soldier', 'young enemy', 'worker veteran memory', 'worker veteran', 'work face cigarette', 'work face', 'woman knowledge taxis', 'woman knowledge', 'will house church', 'will house', 'wife funeral shallow', 'wife funeral', 'wife desire confession', 'wife desire', 'wife birthday cake', 'wife birthday', 'whole neighborhood quiet', 'whole neighborhood']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "The Hangover\n", "\n", "===Keywords===\n", "['tiger', 'trio', 'hotel', 'guy', 'tooth', 'wedding', 'statue', 'tuxedo', 'trio car', 'roofy', 'gangster', 'bachelor party', 'bachelor', 'roof', 'mattress', 'baby', 'trio head', 'tiger hour tiger', 'tiger hour', 'mattress statue', 'hour tiger', 'guy night', 'grandmother ring', 'cruise', 'casino chip', 'asleep blonde', 'doctor', 'ring', 'police car', 'stripper', 'car officer', 'mansion', 'valet', 'hotel way', 'dentist', 'chapel', 'asian', 'strip club', 'grandmother', 'chip', 'phone', 'photo', 'officer', 'casino', 'card', 'strip', 'asleep', 'mad', 'bunch', 'happy']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "The Grand Budapest Hotel\n", "\n", "===Keywords===\n", "['concierge', 'hotel', 'author', 'painting', 'lobby', 'pastry', 'soldier', 'lobby boy', 'numerous', 'story', 'sister', 'train', 'will', 'prison', 'author hotel', 'amendment', 'boy', 'inmate', 'part', 'key', 'paper', 'escape', 'old woman', 'edge', 'tool', 'owner', 'rear', 'absence', 'world hotel', 'monastery', 'man lobby', 'hotel vault', 'favorite cologne', 'family lobby', 'executor', 'cologne', 'barley field', 'barley', 'witness', 'pass', 'hill', 'snow', 'matter', 'cat', 'telegram', 'story part', 'peak', 'candle', 'article', 'mansion']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Star Wars: Episode III - Revenge of the Sith\n", "\n", "===Keywords===\n", "['council', 'temple', 'chancellor', 'apprentice', 'separatist', 'clone', 'bail', 'planet', 'meeting', 'galaxy', 'force lightning', 'pregnant', 'uncle aunt', 'greed', 'river', 'war', 'medical', 'news', 'lava', 'saber', 'trooper', 'aunt', 'force', 'lightsaber', 'powerful', 'unwilling', 'duel', 'droid', 'uncle', 'pod', 'master', 'lightning', 'twin', 'request', 'chamber', 'power', 'upper', 'emergency', 'baby', 'care', 'decision', 'young couple twin', 'young attempt trooper', 'young attempt', 'year galaxy separatist', 'year galaxy', 'worry secret marriage', 'worry secret', 'work baby birth', 'work baby']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "The Revenant\n", "\n", "===Keywords===\n", "['horse', 'bear', 'fur', 'hunting party', 'creek', 'indian', 'wood', 'tribe', 'rifle', 'party', 'hunting', 'warmth', 'carcass', 'french', 'outpost', 'son', 'cold', 'payment', 'dirt', 'vision wife', 'trapper', 'son indian', 'outpost french hunter', 'outpost french', 'man hunting party', 'man hunting', 'fur trapper', 'french hunter', 'french fur', 'hill', 'organ', 'river', 'wound', 'settlement', 'misery', 'knife', 'other man', 'arrow', 'glass', 'food', 'material', 'hunter', 'chief', 'side', 'offer', 'snow', 'pile', 'eye', 'vision', 'boat']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Man of Steel\n", "\n", "===Keywords===\n", "['pod', 'zod', 'planet', 'kryptonian', 'follower', 'vision', 'heat vision', 'rig', 'atmosphere', 'key ship', 'sentry', 'ice', 'heat', 'craft', 'alien', 'son', 'plane', 'key', 'plane ship', 'power', 'council', 'object', 'trucker', 'gravitational', 'drilling', 'stop', 'vessel', 'military', 'word', 'story', 'bus', 'spacecraft', 'destruction', 'able', 'strange', 'world', 'hearing', 'sound', 'shape', 'zod follower', 'various planet', 'stop trucker', 'ship sentry', 'ship gestation chamber', 'ship gestation', 'ray vision', 'pod son', 'hardy', 'gestation chamber', 'gestation']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Le fabuleux destin d'Amélie Poulain\n", "\n", "===Keywords===\n", "['album', 'picture', 'box', 'photo album', 'café', 'photo', 'letter', 'apartment building', 'husband', 'waitress', 'decade', 'co worker', 'note', 'ex', 'apartment', 'co', 'childhood', 'worker', 'contact', 'owner', 'young man hobby', 'year intention other', 'year intention', 'worker hypochondriac georgette', 'worker hypochondriac', 'worker cafe ex', 'worker cafe', 'wife infidelity false', 'weep cake daydream', 'weep cake', 'weep', 'wanderlust day train', 'wanderlust day', 'wanderlust', 'wall bathroom picture', 'wall bathroom', 'waitress private good', 'waitress private', 'waitress life simple', 'waitress life', 'visit same painting', 'visit same', 'videotape man eternal', 'videotape man', 'unhappiness door other', 'unhappiness door', 'unhappiness', 'train station eccentric', 'toy memento decade', 'toy memento']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Black Swan\n", "\n", "===Keywords===\n", "['ballet', 'dressing', 'role', 'dressing room', 'studio', 'dancer', 'dance', 'nail', 'door door', 'stage', 'mirror', 'performance', 'troupe', 'nail file', 'mother hand', 'bathroom', 'princess', 'costume', 'hall', 'bed', 'girl', 'sweet girl', 'item', 'file', 'light', 'blood', 'magician', 'sweet', 'rehearsal', 'principal', 'lead', 'company', 'dream', 'pill', 'next day', 'perfect', 'swan', 'stain', 'several girl', 'role mother', 'principal studio', 'posting', 'pill few hour', 'pill few', 'length mirror', 'length', 'knock door door', 'item table', 'full length mirror', 'full length']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Cidade de Deus\n", "\n", "===Keywords===\n", "['gang', 'rocket', 'picture', 'drug', 'chicken', 'newspaper', 'boy', 'picture dead body', 'picture dead', 'newspaper rocket', 'Li', 'dealer', 'slum', 'peace', 'movie', 'photo', 'cop', 'paper', 'crime', 'dead body', 'business', 'drug dealer', 'story', 'rival', 'armed', 'violent', 'film', 'good friend', 'brother', 'danger', 'criminal', 'youth smoking pot', 'youth smoking', 'young child local', 'young brother violent', 'young boy friend', 'year story position', 'year story', 'year childhood friend', 'year childhood', 'west film viewpoint', 'west film', 'way untimely end', 'way untimely', 'warning shot inhabitant', 'war rival faction', 'war rival', 'violent side man', 'violent side', 'violent crime boy']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "12 Angry Men\n", "\n", "===Keywords===\n", "['juror', 'vote', 'guilty', 'guilty vote', 'defendant', 'verdict', 'reasonable', 'jury', 'slum', 'boy', 'vote guilty', 'reasonable doubt', 'juror vote', 'murder', 'witness', 'question', 'other juror', 'defendant guilty', 'boy guilty', 'doubt', 'unanimous', 'switchblade', 'discussion', 'evidence', 'vote point', 'vote juror', 'vote guilty vote', 'short opponent', 'several juror', 'secret ballot', 'people slum', 'juror question', 'juror guilty vote', 'juror guilty', 'juror boy', 'guilty verdict', 'guilty reasonable doubt', 'guilty reasonable', 'event previous day', 'event previous', 'emotional stress', 'deliberation', 'baseball game', 'ballot', 'woman murder', 'prejudice', 'argument', 'point', 'previous day', 'courthouse']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Blade Runner\n", "\n", "===Keywords===\n", "['replicant', 'lifespan', 'apartment', 'street', 'test', 'dove', 'edition', 'club', 'snake', 'artificial', 'unicorn', 'creator', 'photograph', 'roof', 'piano', 'colony', 'rain', 'date', 'memory', 'elevator', 'ledge', 'finger', 'year lifespan', 'world colony', 'spinner', 'rain dove', 'nexus 6s', 'nexus', 'incept date', 'incept', 'gaff', '6s', 'question', 'subject', 'scale', 'new employee', 'impossible', 'employee', 'despondent', 'headquarters', 'sky', 'skin', 'animal', 'short', 'test subject', 'dancer', 'android', 'tattoo', 'stack', 'niece']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Indiana Jones and the Last Crusade\n", "\n", "===Keywords===\n", "['grail', 'diary', 'knight', 'temple', 'marker', 'cup', 'artifact', 'cross', 'project leader', 'panama hat', 'panama', 'mercenary', 'immortality', 'museum', 'ancient', 'castle', 'tunnel', 'oil', 'leather', 'tank', 'second marker', 'oil tunnel', 'grail true', 'fedora', 'dirigible', 'cult', 'artifact museum', 'hat', 'trap', 'leader', 'glass window', 'german', 'second', 'trek', 'scout', 'roman', 'project', 'chamber', 'pal', 'train', 'plane', 'package', 'horseback', 'book', 'convoy', 'process', 'moment', 'father father', 'soldier', 'scar']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "The Imitation Game\n", "\n", "===Keywords===\n", "['machine', 'code', 'message', 'hut', 'war', 'puzzle', 'spy', 'homosexual', 'crossword', 'detective', 'crossword puzzle', 'beer hut', 'setting', 'code breaker', 'breaker', 'work', 'one', 'secret', 'thing', 'midnight', 'very people one', 'thing one', 'soviet spy', 'people one thing', 'one thing one', 'one thing', 'hormonal', 'team', 'very people', 'people one', 'beer', 'computer', 'smart', 'letter', 'able', 'holiday', 'normal', 'flashback', 'record', 'soviet', 'flat', 'british', 'radio', 'convoy', 'parent', 'weather', 'possibility', 'weather report', 'unbreakable', 'therapy homosexual']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Il buono, il brutto, il cattivo\n", "\n", "===Keywords===\n", "['grave', 'coin', 'partnership', 'blondie', 'cemetery', 'graveyard', 'soldier', 'desert', 'bounty', 'gold', 'prison camp', 'confederate soldier', 'confederate', 'coin grave', 'camp', 'noose', 'loot', 'bounty hunter', 'gunpoint', 'hunter', 'location', 'other side', 'character', 'wooden cross grave', 'wooden cross', 'whereabouts gold thirst', 'whereabouts gold', 'way shootout blondie', 'way shootout', 'water name grave', 'water name', 'water intent revenge', 'water intent', 'value cemetery other', 'value cemetery', 'unstable wooden cross', 'unstable wooden', 'unknown loot grave', 'unknown loot', 'uniform dead soldier', 'uniform dead', 'twist rope head', 'twist rope', 'turn gunpoint grave', 'turn gunpoint', 'trunk gold soldier', 'trunk gold', 'tree unstable wooden', 'tree unstable', 'treasure coin first']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Spider-Man\n", "\n", "===Keywords===\n", "['spider', 'spider man', 'jet glider', 'glider', 'robber', 'wrestling', 'formula', 'jet', 'photo', 'wrestling match', 'trolley car', 'spider way', 'spider death', 'power great', 'jet glider spider', 'glider spider', 'exoskeleton jet glider', 'exoskeleton jet', 'desire own', 'trolley', 'exoskeleton', 'agility', 'promoter', 'loft', 'school', 'great', 'few day', 'persona', 'genetic', 'crush', 'advertisement', 'personality', 'power', 'high school', 'library', 'responsibility', 'offer', 'match', 'desire', 'cut', 'newspaper', 'feeling', 'class', 'fight', 'wrist own new', 'wrist own', 'wrestling match minute', 'wrestling match editor', 'wrestling league minute', 'wrestling league']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "I Am Legend\n", "\n", "===Keywords===\n", "['infected', 'deer', 'vampire', 'vaccine', 'virus', 'alpha', 'female', 'mouse', 'infected female', 'alpha vampire', 'trap', 'cure', 'form', 'human form', 'survivor', 'virus vaccine human', 'virus vaccine', 'vampire other vampire', 'vampire other', 'vaccine human form', 'vaccine human', 'shutter', 'radio message', 'other vampire', 'mouse aggressive', 'infected female virus', 'infected dog', 'human survivor', 'glass chamber', 'form alpha vampire', 'form alpha', 'female virus vaccine', 'female virus', 'deer old', 'alpha vampire other', 'wife child', 'store mannequin', 'syringe', 'previous day', 'tv', 'radio', 'helicopter', 'mannequin', 'dog', 'previous', 'lion', 'aggressive', 'community', 'leader', 'road']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Kill Bill: Vol. 2\n", "\n", "===Keywords===\n", "['bride', 'trailer', 'coffin', 'technique', 'fiancé', 'sword', 'chapter', 'flute', 'blow', 'chapel', 'lid', 'assassin', 'step', 'truth serum', 'technique technique', 'point palm heart', 'point palm', 'palm heart technique', 'palm heart', 'mamba', 'heart technique technique', 'heart technique', 'coffin lid', 'close range', 'blow hand', 'black mamba', 'bamboo flute', 'bamboo', 'grave', 'present', 'groom', 'heart', 'point', 'plank', 'accomplice', 'suitcase', 'palm', 'black', 'flashlight', 'brother', 'revenge', 'relative', 'serum', 'nice', 'boot', 'range', 'hole', 'hotel room', 'fist', 'foot']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Full Metal Jacket\n", "\n", "===Keywords===\n", "['recruit', 'squad', 'sniper', 'rifle', 'vietnamese', 'platoon', 'combat', 'obstacle course', 'obstacle', 'drill', 'base', 'enemy', 'command', 'insane', 'vietnamese civilian', 'verbal abuse', 'squad building', 'rifleman', 'mass grave', 'good story', 'enemy force', 'command squad', 'colonel', 'building squad', 'building sniper', 'verbal', 'gunner', 'gi', 'experience', 'sidearm', 'instructor', 'basic training', 'barrack', 'course', 'overweight', 'holiday', 'south', 'training', 'mass', 'lieutenant', 'basic', 'abuse', 'ruin', 'prostitute', 'patrol', 'yard', 'grave', 'reluctant', 'civilian', 'argument']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Captain America: Civil War\n", "\n", "===Keywords===\n", "['team', 'accord', 'vial', 'explosion', 'shield', 'super soldier', 'facility', 'prince', 'super', 'motorcycle', 'mercenary', 'claw', 'footage', 'team mercenary', 'mission team', 'state', 'mission', 'task force', 'other team', 'panel', 'list', 'supervision', 'headquarters', 'destruction', 'wing', 'hotel', 'metal', 'bomb', 'able', 'chopper', 'roof', 'picture', 'bullet', 'soldier', 'chase', 'psychiatrist', 'pound', 'tunnel', 'force', 'van', 'task', 'strength', 'crash', 'mask', 'hero', 'year people hero', 'year people', 'wrong man prince', 'wrong man', 'world numerous civilian']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "How to Train Your Dragon\n", "\n", "===Keywords===\n", "['dragon', 'hiccup', 'toothless', 'giant dragon', 'village', 'fin', 'nest', 'tail fin', 'giant', 'voice', 'viking', 'practice dragon', 'dragon toothless', 'dragon nest', 'tail', 'voice voice', 'practice', 'voice hiccup', 'toothless hiccup', 'tail fin prosthetic', 'saddle', 'nest dragon', 'hiccup dragon', 'giant dragon toothless', 'fin prosthetic', 'dragon training', 'dragon hiccup', 'battle giant dragon', 'battle giant', 'island', 'voice voice voice', 'sheep', 'food', 'valley', 'prosthetic', 'fleet', 'classmate', 'training', 'cat', 'chain', 'one', 'flight', 'wrong dragon ceremony', 'wrong dragon', 'workshop test flight', 'workshop test', 'wood distance village', 'wood distance', 'wing most home', 'wing most']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Harry Potter and the Sorcerer's Stone\n", "\n", "===Keywords===\n", "['magical', 'dragon', 'wand', 'unicorn', 'hut', 'hooded', 'unicorn blood', 'blood unicorn', 'scar', 'hooded figure', 'troll', 'broom', 'castle', 'theft', 'vault', 'relative', 'trio', 'forehead', 'egg', 'curse', 'school', 'birthday', 'blood', 'famous', 'stone', 'letter', 'year owl wand', 'year owl', 'year feast total', 'year feast', 'year eleventh birthday', 'year eleventh', 'world reckless nature', 'world reckless', 'world first time', 'world first', 'word broom dark', 'word broom', 'wizard year old', 'wizard year', 'witch arrival place', 'witch arrival', 'wing mother infant', 'wing mother', 'week bank vault', 'week bank', 'wearer invisible library', 'wearer invisible', 'wealthy different vault', 'wealthy different']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Sen to Chihiro no kamikakushi\n", "\n", "===Keywords===\n", "['spirit', 'bathhouse', 'bird', 'silent spirit', 'pig', 'gold', 'parent', 'tub', 'river', 'dragon', 'baby', 'big tub', 'mouse', 'boiler', 'silent', 'big', 'spell', 'token', 'sootball', 'paper bird', 'seal', 'frog', 'train', 'voice', 'bug', 'river spirit', 'bug bird', 'bridge', 'boiler room', 'paper', 'stink spirit', 'stink', 'soap token', 'pig parent', 'soap', 'contract', 'spirit gift', 'river spirit gift', 'parent pig', 'mouse bug bird', 'mouse bug', 'mouse baby', 'lump', 'green head', 'dragon form', 'coal', 'big baby', 'food', 'shoe', 'job']\n", "\n", "**************************\n", "\n", "\n", "=====Title=====\n", "Silver Linings Playbook\n", "\n", "===Keywords===\n", "['competition', 'game', 'letter', 'dance', 'tiffany', 'dance competition', 'practice', 'restaurant', 'sex', 'condition', 'young widow sex', 'young widow', 'work bookmaking money', 'work bookmaking', 'wife father work', 'wife father', 'widow sex addict', 'widow sex', 'well man reply', 'well man', 'week competition good', 'week competition', 'wedding song stereo', 'wedding song', 'way well man', 'way well', 'way sign lucky', 'way sign', 'vodkas frantic spot', 'vodkas frantic', 'vodkas', 'violent episode court', 'violent episode', 'upset bar vodkas', 'upset bar', 'upcoming dance competition', 'upcoming dance', 'treatment wife father', 'treatment wife', 'track restraining order', 'track restraining', 'time couple restaurant', 'tiffany short conversation', 'tiffany short', 'tiffany letter return', 'tiffany letter', 'thing father game', 'thing father', 'therapist high school', 'therapist high']\n", "\n", "**************************\n", "\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\n", "=====Title=====\n", "X-Men: Days of Future Past\n", "\n", "===Keywords===\n", "['sentinel', 'mutant', 'future', 'sentinel mutant', 'past', 'sentinel program', 'safe room', 'metal', 'serum', 'consciousness', 'power', 'ice', 'program', 'warpath', 'time sentinel', 'sentinel sentinel', 'sentinel future', 'past body', 'consciousness time', 'body future', 'army officer', 'energy', 'vietnamese', 'stadium', 'energy beam', 'defense', 'beast', 'press', 'form', 'bullet', 'ability', 'mansion', 'army', 'concrete', 'event', 'threat', 'safe', 'claw', 'scene', 'mind', 'plane', 'bone', 'public', 'conference', 'warpath sentinel', 'threat mutant', 'sentinel sentinel mutant', 'sentinel fighting', 'sentinel car', 'sentinel assault']\n", "\n", "**************************\n", "\n" ] } ], "source": [ "idx=range(len(df))\n", "for i in idx:\n", " keywords=get_keywords(i, docs,50)\n", " print_results(i,keywords, df)\n", " print('\\n**************************\\n')" ] }, { "cell_type": "code", "execution_count": null, "id": "7ad89c83", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "bad5bf21", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "bb18a605", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": 21, "id": "1b2b5c3f", "metadata": {}, "outputs": [], "source": [ "def features(df, docs, num=50):\n", " ids= range(len(df))\n", " test= np.array(['']*num)\n", " for i in ids:\n", " #print(df.iloc[i,1])\n", " keyword= get_keywords(i,docs,num)\n", " if len(keyword)']*(num-len(keyword)))\n", " test= np.vstack((test, np.array(keyword).astype('object')))\n", " return test" ] }, { "cell_type": "code", "execution_count": 22, "id": "05970d95", "metadata": {}, "outputs": [], "source": [ "test= features(df,docs)" ] }, { "cell_type": "code", "execution_count": null, "id": "5c18b987", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": 23, "id": "149103de", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "(133, 50)" ] }, "execution_count": 23, "metadata": {}, "output_type": "execute_result" } ], "source": [ "test.shape" ] }, { "cell_type": "code", "execution_count": 34, "id": "8afd51d7", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array(['sentinel', 'mutant', 'future', 'sentinel mutant', 'past',\n", " 'sentinel program', 'safe room', 'metal', 'serum', 'consciousness',\n", " 'power', 'ice', 'program', 'warpath', 'time sentinel',\n", " 'sentinel sentinel', 'sentinel future', 'past body',\n", " 'consciousness time', 'body future', 'army officer', 'energy',\n", " 'vietnamese', 'stadium', 'energy beam', 'defense', 'beast',\n", " 'press', 'form', 'bullet', 'ability', 'mansion', 'army',\n", " 'concrete', 'event', 'threat', 'safe', 'claw', 'scene', 'mind',\n", " 'plane', 'bone', 'public', 'conference', 'warpath sentinel',\n", " 'threat mutant', 'sentinel sentinel mutant', 'sentinel fighting',\n", " 'sentinel car', 'sentinel assault'], dtype=object)" ] }, "execution_count": 34, "metadata": {}, "output_type": "execute_result" } ], "source": [ "test[132]" ] }, { "cell_type": "code", "execution_count": 35, "id": "60b33728", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "'X-Men: Days of Future Past'" ] }, "execution_count": 35, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.iloc[-1,1]" ] }, { "cell_type": "code", "execution_count": null, "id": "1b04ba07", "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.8.8" } }, "nbformat": 4, "nbformat_minor": 5 }