From 3dc7170bba784d4422152a942f9b4519721d81c5 Mon Sep 17 00:00:00 2001 From: benjas <909336740@qq.com> Date: Sun, 14 Feb 2021 20:16:52 +0800 Subject: [PATCH] Add. Text word frequency statistics --- .../酒店推荐.ipynb | 2134 +++++++++++++++++ 1 file changed, 2134 insertions(+) diff --git a/机器学习竞赛实战_优胜解决方案/基于相似度的酒店推荐系统/酒店推荐.ipynb b/机器学习竞赛实战_优胜解决方案/基于相似度的酒店推荐系统/酒店推荐.ipynb index 9fee747..64d22dd 100644 --- a/机器学习竞赛实战_优胜解决方案/基于相似度的酒店推荐系统/酒店推荐.ipynb +++ b/机器学习竞赛实战_优胜解决方案/基于相似度的酒店推荐系统/酒店推荐.ipynb @@ -214,6 +214,2140 @@ "df['desc'][0] # 查看酒店描述的个例" ] }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 文本词频统计\n", + "统计下酒店介绍文本里大多数描述的信息有哪些" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": {}, + "outputs": [], + "source": [ + "vec = CountVectorizer().fit(df['desc']) # 寄存器\n", + "bag_of_words = vec.transform(df['desc']) # 将文本转数值" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "array([[0, 1, 0, ..., 0, 0, 0],\n", + " [0, 0, 0, ..., 0, 0, 0],\n", + " [0, 0, 0, ..., 0, 0, 0],\n", + " ...,\n", + " [0, 0, 0, ..., 0, 0, 0],\n", + " [0, 0, 0, ..., 0, 0, 0],\n", + " [0, 0, 0, ..., 1, 0, 0]], dtype=int64)" + ] + }, + "execution_count": 8, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "bag_of_words.toarray()" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "(152, 3200)" + ] + }, + "execution_count": 9, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "bag_of_words.shape # 一共152含对应上面的数据,其中有3200个不同的词" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "matrix([[ 1, 11, 11, ..., 2, 6, 2]], dtype=int64)" + ] + }, + "execution_count": 10, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "sum_words = bag_of_words.sum(axis=0) # 计算每个词重复的次数\n", + "sum_words" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "[('located', 108),\n", + " ('on', 129),\n", + " ('the', 1258),\n", + " ('southern', 1),\n", + " ('tip', 1),\n", + " ('of', 536),\n", + " ('lake', 41),\n", + " ('union', 33),\n", + " ('hilton', 12),\n", + " ('garden', 11),\n", + " ('inn', 89),\n", + " ('seattle', 533),\n", + " ('downtown', 133),\n", + " ('hotel', 295),\n", + " ('is', 271),\n", + " ('perfectly', 6),\n", + " ('for', 216),\n", + " ('business', 87),\n", + " ('and', 1062),\n", + " ('leisure', 18),\n", + " ('neighborhood', 35),\n", + " ('home', 57),\n", + " ('to', 471),\n", + " ('numerous', 1),\n", + " ('major', 12),\n", + " ('international', 32),\n", + " ('companies', 6),\n", + " ('including', 47),\n", + " ('amazon', 19),\n", + " ('google', 6),\n", + " ('bill', 4),\n", + " ('melinda', 4),\n", + " ('gates', 5),\n", + " ('foundation', 4),\n", + " ('wealth', 1),\n", + " ('eclectic', 8),\n", + " ('restaurants', 35),\n", + " ('bars', 7),\n", + " ('make', 43),\n", + " ('this', 63),\n", + " ('area', 51),\n", + " ('one', 75),\n", + " ('most', 40),\n", + " ('sought', 1),\n", + " ('out', 23),\n", + " ('by', 71),\n", + " ('locals', 5),\n", + " ('visitors', 4),\n", + " ('our', 359),\n", + " ('proximity', 8),\n", + " ('allows', 3),\n", + " ('take', 31),\n", + " ('in', 449),\n", + " ('some', 22),\n", + " ('pacific', 42),\n", + " ('northwest', 42),\n", + " ('majestic', 4),\n", + " ('scenery', 2),\n", + " ('enjoy', 93),\n", + " ('outdoor', 23),\n", + " ('activities', 8),\n", + " ('like', 46),\n", + " ('kayaking', 3),\n", + " ('sailing', 1),\n", + " ('over', 14),\n", + " ('000', 11),\n", + " ('sq', 4),\n", + " ('ft', 4),\n", + " ('versatile', 3),\n", + " ('space', 97),\n", + " ('complimentary', 62),\n", + " ('center', 151),\n", + " ('state', 30),\n", + " ('art', 44),\n", + " ('technology', 4),\n", + " ('helpful', 2),\n", + " ('staff', 9),\n", + " ('will', 46),\n", + " ('guarantee', 3),\n", + " ('your', 186),\n", + " ('conference', 6),\n", + " ('cocktail', 6),\n", + " ('reception', 7),\n", + " ('or', 161),\n", + " ('wedding', 4),\n", + " ('success', 4),\n", + " ('refresh', 4),\n", + " ('sparkling', 2),\n", + " ('saltwater', 1),\n", + " ('pool', 37),\n", + " ('energize', 2),\n", + " ('with', 280),\n", + " ('latest', 4),\n", + " ('equipment', 3),\n", + " ('24', 42),\n", + " ('hour', 32),\n", + " ('fitness', 42),\n", + " ('tastefully', 4),\n", + " ('decorated', 4),\n", + " ('flooded', 1),\n", + " ('natural', 8),\n", + " ('light', 26),\n", + " ('guest', 57),\n", + " ('rooms', 106),\n", + " ('suites', 67),\n", + " ('offer', 59),\n", + " ('everything', 18),\n", + " ('you', 304),\n", + " ('need', 25),\n", + " ('relax', 25),\n", + " ('stay', 105),\n", + " ('productive', 4),\n", + " ('unwind', 11),\n", + " ('bar', 34),\n", + " ('american', 5),\n", + " ('cuisine', 11),\n", + " ('breakfast', 68),\n", + " ('lunch', 4),\n", + " ('dinner', 7),\n", + " ('restaurant', 32),\n", + " ('pavilion', 1),\n", + " ('pantry', 2),\n", + " ('stocks', 1),\n", + " ('variety', 12),\n", + " ('snacks', 9),\n", + " ('drinks', 6),\n", + " ('sundries', 2),\n", + " ('city', 79),\n", + " ('vibrant', 14),\n", + " ('core', 5),\n", + " ('sheraton', 8),\n", + " ('grand', 13),\n", + " ('provides', 9),\n", + " ('gateway', 4),\n", + " ('diverse', 5),\n", + " ('sights', 2),\n", + " ('sounds', 2),\n", + " ('step', 11),\n", + " ('front', 11),\n", + " ('doors', 8),\n", + " ('find', 31),\n", + " ('gourmet', 1),\n", + " ('dining', 36),\n", + " ('world', 24),\n", + " ('class', 13),\n", + " ('shopping', 31),\n", + " ('exciting', 7),\n", + " ('entertainment', 11),\n", + " ('iconic', 15),\n", + " ('local', 45),\n", + " ('attractions', 59),\n", + " ('pike', 90),\n", + " ('place', 102),\n", + " ('market', 97),\n", + " ('needle', 68),\n", + " ('chihuly', 3),\n", + " ('glass', 10),\n", + " ('museum', 43),\n", + " ('as', 117),\n", + " ('only', 34),\n", + " ('seven', 6),\n", + " ('hotels', 28),\n", + " ('north', 14),\n", + " ('america', 5),\n", + " ('earn', 3),\n", + " ('esteemed', 1),\n", + " ('designation', 1),\n", + " ('guests', 54),\n", + " ('can', 55),\n", + " ('book', 11),\n", + " ('confidently', 1),\n", + " ('knowing', 1),\n", + " ('they', 11),\n", + " ('re', 64),\n", + " ('receiving', 1),\n", + " ('highest', 2),\n", + " ('benchmark', 1),\n", + " ('product', 1),\n", + " ('service', 53),\n", + " ('offerings', 2),\n", + " ('available', 36),\n", + " ('experience', 52),\n", + " ('recently', 7),\n", + " ('completed', 1),\n", + " ('multimillion', 1),\n", + " ('dollar', 1),\n", + " ('transformation', 1),\n", + " ('featuring', 26),\n", + " ('all', 100),\n", + " ('new', 17),\n", + " ('an', 91),\n", + " ('expanded', 5),\n", + " ('club', 17),\n", + " ('lounge', 20),\n", + " ('modern', 34),\n", + " ('meeting', 27),\n", + " ('event', 29),\n", + " ('spaces', 11),\n", + " ('gather', 1),\n", + " ('stylish', 17),\n", + " ('lobby', 26),\n", + " ('private', 29),\n", + " ('collection', 6),\n", + " ('artists', 2),\n", + " ('while', 34),\n", + " ('enjoying', 5),\n", + " ('favorite', 7),\n", + " ('beverage', 5),\n", + " ('from', 224),\n", + " ('starbucks', 12),\n", + " ('features', 27),\n", + " ('several', 5),\n", + " ('options', 14),\n", + " ('loulay', 1),\n", + " ('kitchen', 17),\n", + " ('james', 1),\n", + " ('beard', 1),\n", + " ('award', 13),\n", + " ('winning', 11),\n", + " ('chef', 3),\n", + " ('thierry', 1),\n", + " ('rautureau', 1),\n", + " ('heart', 35),\n", + " ('crowne', 5),\n", + " ('plaza', 4),\n", + " ('offers', 43),\n", + " ('exceptional', 5),\n", + " ('blend', 3),\n", + " ('style', 27),\n", + " ('comfort', 24),\n", + " ('ll', 48),\n", + " ('notice', 1),\n", + " ('cool', 5),\n", + " ('comfortable', 30),\n", + " ('unconventional', 1),\n", + " ('touches', 4),\n", + " ('that', 65),\n", + " ('set', 4),\n", + " ('us', 21),\n", + " ('apart', 1),\n", + " ('soon', 3),\n", + " ('inside', 7),\n", + " ('marvel', 2),\n", + " ('at', 231),\n", + " ('stunning', 7),\n", + " ('views', 39),\n", + " ('lights', 4),\n", + " ('relaxing', 12),\n", + " ('sleep', 6),\n", + " ('advantage', 12),\n", + " ('beds', 17),\n", + " ('wireless', 9),\n", + " ('internet', 26),\n", + " ('throughout', 7),\n", + " ('amenities', 60),\n", + " ('help', 11),\n", + " ('temple', 1),\n", + " ('spa', 13),\n", + " ('tight', 1),\n", + " ('amenity', 1),\n", + " ('kits', 1),\n", + " ('lavender', 1),\n", + " ('spray', 1),\n", + " ('lotions', 1),\n", + " ('rejuvenate', 1),\n", + " ('invigorating', 2),\n", + " ('workout', 7),\n", + " ('get', 11),\n", + " ('suggestions', 1),\n", + " ('expert', 2),\n", + " ('concierge', 3),\n", + " ('savor', 6),\n", + " ('sumptuous', 1),\n", + " ('regatta', 1),\n", + " ('grille', 1),\n", + " ('where', 27),\n", + " ('happy', 6),\n", + " ('daily', 10),\n", + " ('4pm', 1),\n", + " ('7pm', 1),\n", + " ('monthly', 1),\n", + " ('drink', 5),\n", + " ('specials', 2),\n", + " ('come', 17),\n", + " ('emerald', 17),\n", + " ('has', 41),\n", + " ('what', 11),\n", + " ('near', 48),\n", + " ('location', 33),\n", + " ('better', 5),\n", + " ('question', 2),\n", + " ('might', 5),\n", + " ('be', 43),\n", + " ('not', 20),\n", + " ('nearby', 16),\n", + " ('addition', 4),\n", + " ('being', 1),\n", + " ('here', 19),\n", + " ('just', 82),\n", + " ('small', 8),\n", + " ('sampling', 2),\n", + " ('rest', 4),\n", + " ('columbia', 2),\n", + " ('whose', 1),\n", + " ('sky', 2),\n", + " ('view', 11),\n", + " ('observatory', 1),\n", + " ('73rd', 1),\n", + " ('floor', 11),\n", + " ('tallest', 1),\n", + " ('public', 6),\n", + " ('viewing', 1),\n", + " ('west', 15),\n", + " ('mississippi', 1),\n", + " ('historic', 24),\n", + " ('5th', 4),\n", + " ('avenue', 15),\n", + " ('theatre', 2),\n", + " ('musical', 1),\n", + " ('productions', 1),\n", + " ('central', 12),\n", + " ('library', 7),\n", + " ('architectural', 2),\n", + " ('within', 36),\n", + " ('half', 5),\n", + " ('mile', 14),\n", + " ('must', 5),\n", + " ('see', 15),\n", + " ('which', 14),\n", + " ('houses', 5),\n", + " ('original', 11),\n", + " ('pioneer', 15),\n", + " ('square', 28),\n", + " ('fantastic', 3),\n", + " ('flagship', 1),\n", + " ('nordstrom', 6),\n", + " ('rack', 1),\n", + " ('macy', 1),\n", + " ('sportswear', 1),\n", + " ('louis', 1),\n", + " ('vuitton', 1),\n", + " ('arcteryx', 1),\n", + " ('oodles', 1),\n", + " ('independent', 2),\n", + " ('boutiques', 5),\n", + " ('great', 39),\n", + " ('wheel', 2),\n", + " ('washington', 67),\n", + " ('convention', 24),\n", + " ('about', 11),\n", + " ('bell', 2),\n", + " ('street', 26),\n", + " ('pier', 5),\n", + " ('cruise', 11),\n", + " ('terminal', 6),\n", + " ('66', 1),\n", + " ('sports', 13),\n", + " ('stadiums', 5),\n", + " ('centurylink', 17),\n", + " ('field', 34),\n", + " ('safeco', 20),\n", + " ('seahawks', 10),\n", + " ('mariners', 9),\n", + " ('sounders', 4),\n", + " ('situated', 14),\n", + " ('amid', 3),\n", + " ('incredible', 3),\n", + " ('westin', 1),\n", + " ('contemporary', 12),\n", + " ('haven', 3),\n", + " ('prime', 3),\n", + " ('recharge', 2),\n", + " ('accommodations', 15),\n", + " ('comforts', 14),\n", + " ('signature', 14),\n", + " ('heavenly', 2),\n", + " ('gorgeous', 7),\n", + " ('skyline', 8),\n", + " ('puget', 16),\n", + " ('sound', 21),\n", + " ('cascade', 1),\n", + " ('mountain', 5),\n", + " ('range', 9),\n", + " ('newly', 5),\n", + " ('renovated', 10),\n", + " ('1900', 1),\n", + " ('fifth', 2),\n", + " ('offering', 21),\n", + " ('carefully', 2),\n", + " ('curated', 4),\n", + " ('wine', 10),\n", + " ('crafted', 3),\n", + " ('explore', 20),\n", + " ('spectacular', 6),\n", + " ('celebrated', 3),\n", + " ('waterfront', 38),\n", + " ('host', 9),\n", + " ('unforgettable', 3),\n", + " ('meetings', 16),\n", + " ('social', 11),\n", + " ('engagements', 1),\n", + " ('more', 29),\n", + " ('than', 19),\n", + " ('70', 2),\n", + " ('feet', 16),\n", + " ('enhanced', 1),\n", + " ('planning', 8),\n", + " ('custom', 6),\n", + " ('catering', 8),\n", + " ('mind', 8),\n", + " ('body', 1),\n", + " ('sleek', 5),\n", + " ('westinworkout', 1),\n", + " ('studio', 11),\n", + " ('designed', 21),\n", + " ('reflect', 3),\n", + " ('substance', 1),\n", + " ('welcoming', 5),\n", + " ('best', 50),\n", + " ('paramount', 4),\n", + " ('summons', 1),\n", + " ('feel', 11),\n", + " ('cozy', 10),\n", + " ('elegant', 5),\n", + " ('luxurious', 4),\n", + " ('residence', 5),\n", + " ('friendly', 29),\n", + " ('hosts', 3),\n", + " ('asian', 2),\n", + " ('right', 15),\n", + " ('downstairs', 1),\n", + " ('fall', 1),\n", + " ('love', 9),\n", + " ('simple', 6),\n", + " ('luxury', 18),\n", + " ('charm', 10),\n", + " ('boutique', 8),\n", + " ('warm', 8),\n", + " ('inviting', 10),\n", + " ('wood', 7),\n", + " ('finishes', 2),\n", + " ('comfy', 4),\n", + " ('seating', 7),\n", + " ('areas', 12),\n", + " ('fireplace', 6),\n", + " ('classically', 1),\n", + " ('appointed', 9),\n", + " ('dash', 1),\n", + " ('urban', 15),\n", + " ('flair', 1),\n", + " ('puts', 5),\n", + " ('good', 4),\n", + " ('company', 3),\n", + " ('block', 10),\n", + " ('walking', 21),\n", + " ('distance', 23),\n", + " ('cafes', 1),\n", + " ('there', 15),\n", + " ('are', 136),\n", + " ('many', 31),\n", + " ('reasons', 1),\n", + " ('annually', 1),\n", + " ('ranked', 1),\n", + " ('among', 7),\n", + " ('top', 17),\n", + " ('five', 12),\n", + " ('why', 4),\n", + " ('yours', 2),\n", + " ('shops', 14),\n", + " ('sightseeing', 4),\n", + " ('tour', 5),\n", + " ('rent', 1),\n", + " ('car', 7),\n", + " ('if', 19),\n", + " ('town', 13),\n", + " ('walk', 28),\n", + " ('via', 5),\n", + " ('underground', 3),\n", + " ('concourse', 1),\n", + " ('hungry', 1),\n", + " ('visit', 21),\n", + " ('redtrees', 1),\n", + " ('wide', 6),\n", + " ('satisfy', 2),\n", + " ('any', 12),\n", + " ('foodie', 1),\n", + " ('destination', 5),\n", + " ('steps', 20),\n", + " ('everywhere', 3),\n", + " ('want', 11),\n", + " ('motif', 1),\n", + " ('welcome', 20),\n", + " ('libation', 1),\n", + " ('rooftop', 8),\n", + " ('across', 16),\n", + " ('touchstones', 1),\n", + " ('sweeping', 2),\n", + " ('landscape', 3),\n", + " ('rich', 8),\n", + " ('arts', 7),\n", + " ('music', 16),\n", + " ('culture', 6),\n", + " ('infuse', 1),\n", + " ('surroundings', 1),\n", + " ('residences', 1),\n", + " ('hardwoods', 1),\n", + " ('colors', 2),\n", + " ('inspired', 12),\n", + " ('region', 3),\n", + " ('culinary', 5),\n", + " ('bounty', 3),\n", + " ('reflected', 1),\n", + " ('menus', 1),\n", + " ('frolik', 1),\n", + " ('cocktails', 5),\n", + " ('adjoining', 2),\n", + " ('patio', 6),\n", + " ('join', 6),\n", + " ('between', 5),\n", + " ('monorail', 5),\n", + " ('rail', 19),\n", + " ('airport', 99),\n", + " ('stroll', 2),\n", + " ('away', 59),\n", + " ('known', 8),\n", + " ('setting', 6),\n", + " ('trends', 2),\n", + " ('warwick', 5),\n", + " ('leading', 4),\n", + " ('way', 5),\n", + " ('upbeat', 1),\n", + " ('belltown', 13),\n", + " ('district', 27),\n", + " ('blocks', 21),\n", + " ('blends', 1),\n", + " ('classic', 8),\n", + " ('expected', 1),\n", + " ('name', 2),\n", + " ('styling', 1),\n", + " ('boasting', 1),\n", + " ('unique', 16),\n", + " ('staying', 12),\n", + " ('truly', 3),\n", + " ('finding', 2),\n", + " ('pleasant', 3),\n", + " ('surprises', 1),\n", + " ('along', 13),\n", + " ('refreshing', 4),\n", + " ('seaborne', 1),\n", + " ('mists', 1),\n", + " ('breeze', 3),\n", + " ('evergreen', 2),\n", + " ('covered', 4),\n", + " ('hills', 1),\n", + " ('lining', 1),\n", + " ('horizon', 2),\n", + " ('doorstep', 2),\n", + " ('anything', 2),\n", + " ('possible', 5),\n", + " ('surrounded', 4),\n", + " ('snow', 2),\n", + " ('capped', 2),\n", + " ('peaks', 1),\n", + " ('deep', 3),\n", + " ('blue', 1),\n", + " ('waters', 3),\n", + " ('swaths', 1),\n", + " ('forests', 1),\n", + " ('wild', 2),\n", + " ('it', 55),\n", + " ('trendy', 4),\n", + " ('side', 4),\n", + " ('another', 2),\n", + " ('elliott', 10),\n", + " ('bay', 14),\n", + " ('gleaming', 1),\n", + " ('wake', 6),\n", + " ('fresh', 18),\n", + " ('cup', 6),\n", + " ('coffee', 38),\n", + " ('delivered', 1),\n", + " ('straight', 3),\n", + " ('room', 77),\n", + " ('then', 10),\n", + " ('head', 5),\n", + " ('neighbourhoods', 1),\n", + " ('craft', 5),\n", + " ('breweries', 3),\n", + " ('spend', 9),\n", + " ('day', 39),\n", + " ('hiking', 6),\n", + " ('up', 44),\n", + " ('mount', 3),\n", + " ('rainer', 1),\n", + " ('nightfall', 1),\n", + " ('meet', 12),\n", + " ('goldfinch', 1),\n", + " ('tavern', 1),\n", + " ('ethan', 1),\n", + " ('stowell', 1),\n", + " ('let', 4),\n", + " ('chefs', 2),\n", + " ('show', 4),\n", + " ('flavours', 1),\n", + " ('favourite', 1),\n", + " ('soak', 3),\n", + " ('scene', 6),\n", + " ('living', 22),\n", + " ('mix', 2),\n", + " ('live', 10),\n", + " ('dj', 1),\n", + " ('series', 1),\n", + " ('before', 3),\n", + " ('heading', 3),\n", + " ('memorable', 4),\n", + " ('trace', 1),\n", + " ('seasonal', 10),\n", + " ('fare', 4),\n", + " ('atmosphere', 7),\n", + " ('missed', 1),\n", + " ('work', 25),\n", + " ('off', 19),\n", + " ('next', 20),\n", + " ('morning', 18),\n", + " ('fit', 7),\n", + " ('wandering', 1),\n", + " ('always', 7),\n", + " ('we', 128),\n", + " ('ve', 7),\n", + " ('got', 4),\n", + " ('during', 9),\n", + " ('time', 24),\n", + " ('whatever', 2),\n", + " ('whenever', 1),\n", + " ('wish', 2),\n", + " ('command', 1),\n", + " ('upscale', 11),\n", + " ('getaway', 6),\n", + " ('hyatt', 15),\n", + " ('theater', 6),\n", + " ('four', 9),\n", + " ('diamond', 4),\n", + " ('landmarks', 6),\n", + " ('destinations', 3),\n", + " ('scenic', 4),\n", + " ('luxuriate', 1),\n", + " ('opt', 2),\n", + " ('decadent', 1),\n", + " ('suite', 25),\n", + " ('bath', 10),\n", + " ('upgraded', 2),\n", + " ('access', 59),\n", + " ('ever', 3),\n", + " ('had', 1),\n", + " ('reading', 3),\n", + " ('couldn', 3),\n", + " ('put', 5),\n", + " ('down', 6),\n", + " ('but', 12),\n", + " ('never', 4),\n", + " ('wanted', 2),\n", + " ('end', 5),\n", + " ('know', 8),\n", + " ('kimpton', 5),\n", + " ('alexis', 3),\n", + " ('1901', 1),\n", + " ('building', 19),\n", + " ('close', 34),\n", + " ('enough', 5),\n", + " ('smell', 1),\n", + " ('sea', 23),\n", + " ('air', 11),\n", + " ('plot', 1),\n", + " ('peaceful', 2),\n", + " ('sanctuary', 2),\n", + " ('den', 1),\n", + " ('mixed', 1),\n", + " ('matched', 3),\n", + " ('characters', 1),\n", + " ('attentive', 3),\n", + " ('members', 1),\n", + " ('who', 5),\n", + " ('seem', 1),\n", + " ('plus', 15),\n", + " ('fellow', 2),\n", + " ('interesting', 3),\n", + " ('stories', 2),\n", + " ('tell', 4),\n", + " ('ending', 1),\n", + " ('without', 4),\n", + " ('giving', 3),\n", + " ('easy', 44),\n", + " ('perennial', 1),\n", + " ('seller', 1),\n", + " ('positioned', 1),\n", + " ('edge', 3),\n", + " ('borders', 1),\n", + " ('retail', 4),\n", + " ('guestrooms', 15),\n", + " ('turntables', 1),\n", + " ('vinyl', 1),\n", + " ('max', 1),\n", + " ('dedicated', 5),\n", + " ('lovers', 2),\n", + " ('indulge', 3),\n", + " ('provenance', 1),\n", + " ('locally', 7),\n", + " ('influenced', 1),\n", + " ('honor', 1),\n", + " ('beer', 5),\n", + " ('miller', 1),\n", + " ('guild', 1),\n", + " ('fell', 1),\n", + " ('former', 1),\n", + " ('maritime', 1),\n", + " ('workers', 1),\n", + " ('started', 1),\n", + " ('first', 19),\n", + " ('1999', 1),\n", + " ('roots', 1),\n", + " ('unfussy', 1),\n", + " ('intentional', 1),\n", + " ('design', 5),\n", + " ('ethos', 1),\n", + " ('drive', 12),\n", + " ('loft', 3),\n", + " ('ceilings', 3),\n", + " ('hardwood', 1),\n", + " ('floors', 7),\n", + " ('wherever', 1),\n", + " ('could', 5),\n", + " ('preserve', 1),\n", + " ('them', 3),\n", + " ('friends', 11),\n", + " ('kaws', 1),\n", + " ('shepard', 1),\n", + " ('fairey', 1),\n", + " ('were', 2),\n", + " ('elements', 3),\n", + " ('hotelier', 1),\n", + " ('map', 1),\n", + " ('still', 3),\n", + " ('touch', 1),\n", + " ('point', 1),\n", + " ('ace', 1),\n", + " ('today', 16),\n", + " ('when', 38),\n", + " ('marriott', 5),\n", + " ('reveals', 1),\n", + " ('mountains', 9),\n", + " ('famous', 15),\n", + " ('elevator', 2),\n", + " ('ride', 9),\n", + " ('sit', 3),\n", + " ('adjacent', 4),\n", + " ('harbor', 4),\n", + " ('also', 62),\n", + " ('port', 4),\n", + " ('aquarium', 10),\n", + " ('westlake', 5),\n", + " ('olympic', 13),\n", + " ('sculpture', 4),\n", + " ('park', 35),\n", + " ('outfitted', 3),\n", + " ('plush', 13),\n", + " ('bedding', 9),\n", + " ('mini', 7),\n", + " ('refrigerators', 5),\n", + " ('large', 11),\n", + " ('desks', 5),\n", + " ('wi', 37),\n", + " ('fi', 37),\n", + " ('balconies', 3),\n", + " ('junior', 1),\n", + " ('provide', 12),\n", + " ('perfect', 30),\n", + " ('extended', 15),\n", + " ('stays', 7),\n", + " ('reimagined', 2),\n", + " ('its', 21),\n", + " ('special', 13),\n", + " ('perks', 3),\n", + " ('indoor', 16),\n", + " ('gym', 3),\n", + " ('delicious', 8),\n", + " ('gastropub', 1),\n", + " ('tempting', 1),\n", + " ('libations', 1),\n", + " ('found', 5),\n", + " ('popular', 12),\n", + " ('look', 4),\n", + " ('no', 15),\n", + " ('further', 2),\n", + " ('10', 11),\n", + " ('redesigned', 1),\n", + " ('venues', 8),\n", + " ('well', 33),\n", + " ('supported', 1),\n", + " ('edgewater', 2),\n", + " ('reported', 1),\n", + " ('cnbc', 1),\n", + " ('amazing', 1),\n", + " ('breathtaking', 4),\n", + " ('sunset', 3),\n", + " ('ship', 5),\n", + " ('terminals', 5),\n", + " ('sites', 4),\n", + " ('decide', 1),\n", + " ('turn', 2),\n", + " ('tub', 8),\n", + " ('water', 10),\n", + " ('67', 1),\n", + " ('dynamic', 2),\n", + " ('soul', 1),\n", + " ('lodging', 6),\n", + " ('river', 1),\n", + " ('rock', 3),\n", + " ('fireplaces', 3),\n", + " ('wilderness', 2),\n", + " ('landscapes', 1),\n", + " ('outside', 13),\n", + " ('window', 1),\n", + " ('treat', 1),\n", + " ('yourself', 8),\n", + " ('rewarding', 1),\n", + " ('springhill', 2),\n", + " ('south', 19),\n", + " ('goal', 4),\n", + " ('whether', 23),\n", + " ('night', 13),\n", + " ('weekend', 2),\n", + " ('each', 28),\n", + " ('spacious', 29),\n", + " ('separate', 6),\n", + " ('kitchenette', 3),\n", + " ('fridge', 9),\n", + " ('maker', 7),\n", + " ('microwave', 12),\n", + " ('convenience', 18),\n", + " ('every', 29),\n", + " ('onsite', 8),\n", + " ('bistro', 3),\n", + " ('yale', 1),\n", + " ('innovative', 5),\n", + " ('additional', 4),\n", + " ('highlights', 1),\n", + " ('include', 19),\n", + " ('swimming', 10),\n", + " ('so', 12),\n", + " ('pamper', 2),\n", + " ('last', 2),\n", + " ('least', 1),\n", + " ('makes', 5),\n", + " ('mall', 11),\n", + " ('other', 21),\n", + " ('plan', 6),\n", + " ('forward', 1),\n", + " ('seeing', 1),\n", + " ('premier', 2),\n", + " ('fairmont', 3),\n", + " ('captures', 1),\n", + " ('old', 7),\n", + " ('elegance', 4),\n", + " ('italian', 2),\n", + " ('renaissance', 2),\n", + " ('built', 14),\n", + " ('1924', 1),\n", + " ('legendary', 2),\n", + " ('architecture', 1),\n", + " ('acclaimed', 3),\n", + " ('impeccable', 1),\n", + " ('corridors', 2),\n", + " ('full', 27),\n", + " ('shines', 1),\n", + " ('named', 4),\n", + " ('news', 3),\n", + " ('report', 3),\n", + " ('2018', 3),\n", + " ('hub', 6),\n", + " ('retreat', 6),\n", + " ('cozily', 2),\n", + " ('activity', 2),\n", + " ('streets', 2),\n", + " ('lined', 2),\n", + " ('diversified', 1),\n", + " ('sophisticated', 4),\n", + " ('chic', 5),\n", + " ('excursion', 2),\n", + " ('afternoon', 4),\n", + " ('gasworks', 1),\n", + " ('quiet', 11),\n", + " ('beauty', 5),\n", + " ('have', 35),\n", + " ('instant', 2),\n", + " ('both', 15),\n", + " ('worlds', 1),\n", + " ('travel', 25),\n", + " ('pleasure', 8),\n", + " ('trips', 1),\n", + " ('few', 16),\n", + " ('corporate', 10),\n", + " ('vacationers', 2),\n", + " ('museums', 6),\n", + " ('less', 11),\n", + " ('landmark', 9),\n", + " ('distinctly', 1),\n", + " ('charming', 1),\n", + " ('unmistakable', 1),\n", + " ('sprawling', 2),\n", + " ('system', 5),\n", + " ('shows', 3),\n", + " ('pristine', 2),\n", + " ('outdoors', 3),\n", + " ('performing', 1),\n", + " ('cultural', 7),\n", + " ('thriving', 6),\n", + " ('visitor', 1),\n", + " ('metro', 4),\n", + " ('attracts', 1),\n", + " ('deal', 1),\n", + " ('professional', 5),\n", + " ('travelers', 23),\n", + " ('booming', 1),\n", + " ('fortune', 2),\n", + " ('500', 4),\n", + " ('costco', 1),\n", + " ('wholesale', 1),\n", + " ('microsoft', 10),\n", + " ('facebook', 5),\n", + " ('furthermore', 1),\n", + " ('fans', 3),\n", + " ('athletic', 3),\n", + " ('three', 11),\n", + " ('teams', 2),\n", + " ('nestled', 4),\n", + " ('embassy', 2),\n", + " ('sleeping', 5),\n", + " ('queen', 28),\n", + " ('size', 6),\n", + " ('sofa', 7),\n", + " ('bed', 41),\n", + " ('50', 2),\n", + " ('inch', 11),\n", + " ('hdtv', 7),\n", + " ('kitchenettes', 6),\n", + " ('dine', 6),\n", + " ('institution', 1),\n", + " ('13', 1),\n", + " ('coins', 1),\n", + " ('hand', 6),\n", + " ('zephyr', 1),\n", + " ('stop', 12),\n", + " ('health', 4),\n", + " ('includes', 8),\n", + " ('heated', 12),\n", + " ('hot', 25),\n", + " ('sun', 2),\n", + " ('deck', 5),\n", + " ('begin', 3),\n", + " ('free', 123),\n", + " ('made', 5),\n", + " ('order', 3),\n", + " ('evening', 8),\n", + " ('55', 4),\n", + " ('cheer', 2),\n", + " ('team', 6),\n", + " ('football', 3),\n", + " ('fc', 2),\n", + " ('baseball', 2),\n", + " ('game', 7),\n", + " ('mobile', 4),\n", + " ('trip', 11),\n", + " ('around', 14),\n", + " ('boat', 2),\n", + " ('wamu', 1),\n", + " ('pan', 1),\n", + " ('trust', 2),\n", + " ('settle', 4),\n", + " ('into', 13),\n", + " ('epicentre', 1),\n", + " ('wondering', 1),\n", + " ('vintage', 2),\n", + " ('spot', 2),\n", + " ('corner', 6),\n", + " ('spring', 3),\n", + " ('financial', 2),\n", + " ('spots', 3),\n", + " ('benaroya', 2),\n", + " ('hall', 5),\n", + " ('trade', 2),\n", + " ('transportation', 7),\n", + " ('easily', 7),\n", + " ('walkable', 3),\n", + " ('ferry', 3),\n", + " ('dozens', 2),\n", + " ('buses', 2),\n", + " ('driving', 3),\n", + " ('those', 4),\n", + " ('coming', 2),\n", + " ('tac', 15),\n", + " ...]" + ] + }, + "execution_count": 13, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "words_freq = [(word, sum_words[0,idx]) for word,idx in vec.vocabulary_.items()] # 得到词及对应出现的次数\n", + "words_freq" + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "[('the', 1258),\n", + " ('and', 1062),\n", + " ('of', 536),\n", + " ('seattle', 533),\n", + " ('to', 471),\n", + " ('in', 449),\n", + " ('our', 359),\n", + " ('you', 304),\n", + " ('hotel', 295),\n", + " ('with', 280),\n", + " ('is', 271),\n", + " ('at', 231),\n", + " ('from', 224),\n", + " ('for', 216),\n", + " ('your', 186),\n", + " ('or', 161),\n", + " ('center', 151),\n", + " ('are', 136),\n", + " ('downtown', 133),\n", + " ('on', 129),\n", + " ('we', 128),\n", + " ('free', 123),\n", + " ('as', 117),\n", + " ('located', 108),\n", + " ('rooms', 106),\n", + " ('stay', 105),\n", + " ('place', 102),\n", + " ('all', 100),\n", + " ('airport', 99),\n", + " ('space', 97),\n", + " ('market', 97),\n", + " ('enjoy', 93),\n", + " ('an', 91),\n", + " ('pike', 90),\n", + " ('inn', 89),\n", + " ('business', 87),\n", + " ('just', 82),\n", + " ('city', 79),\n", + " ('room', 77),\n", + " ('one', 75),\n", + " ('by', 71),\n", + " ('breakfast', 68),\n", + " ('needle', 68),\n", + " ('suites', 67),\n", + " ('washington', 67),\n", + " ('that', 65),\n", + " ('re', 64),\n", + " ('this', 63),\n", + " ('complimentary', 62),\n", + " ('also', 62),\n", + " ('amenities', 60),\n", + " ('offer', 59),\n", + " ('attractions', 59),\n", + " ('away', 59),\n", + " ('access', 59),\n", + " ('home', 57),\n", + " ('guest', 57),\n", + " ('can', 55),\n", + " ('it', 55),\n", + " ('guests', 54),\n", + " ('service', 53),\n", + " ('experience', 52),\n", + " ('area', 51),\n", + " ('best', 50),\n", + " ('ll', 48),\n", + " ('near', 48),\n", + " ('including', 47),\n", + " ('like', 46),\n", + " ('will', 46),\n", + " ('local', 45),\n", + " ('art', 44),\n", + " ('up', 44),\n", + " ('easy', 44),\n", + " ('make', 43),\n", + " ('museum', 43),\n", + " ('offers', 43),\n", + " ('be', 43),\n", + " ('minutes', 43),\n", + " ('university', 43),\n", + " ('pacific', 42),\n", + " ('northwest', 42),\n", + " ('24', 42),\n", + " ('fitness', 42),\n", + " ('lake', 41),\n", + " ('has', 41),\n", + " ('bed', 41),\n", + " ('most', 40),\n", + " ('views', 39),\n", + " ('great', 39),\n", + " ('day', 39),\n", + " ('waterfront', 38),\n", + " ('coffee', 38),\n", + " ('when', 38),\n", + " ('pool', 37),\n", + " ('wi', 37),\n", + " ('fi', 37),\n", + " ('dining', 36),\n", + " ('available', 36),\n", + " ('within', 36),\n", + " ('neighborhood', 35),\n", + " ('restaurants', 35),\n", + " ('heart', 35),\n", + " ('park', 35),\n", + " ('have', 35),\n", + " ('bar', 34),\n", + " ('only', 34),\n", + " ('modern', 34),\n", + " ('while', 34),\n", + " ('field', 34),\n", + " ('close', 34),\n", + " ('union', 33),\n", + " ('location', 33),\n", + " ('well', 33),\n", + " ('international', 32),\n", + " ('hour', 32),\n", + " ('restaurant', 32),\n", + " ('high', 32),\n", + " ('parking', 32),\n", + " ('take', 31),\n", + " ('find', 31),\n", + " ('shopping', 31),\n", + " ('many', 31),\n", + " ('shuttle', 31),\n", + " ('state', 30),\n", + " ('comfortable', 30),\n", + " ('perfect', 30),\n", + " ('event', 29),\n", + " ('private', 29),\n", + " ('more', 29),\n", + " ('friendly', 29),\n", + " ('spacious', 29),\n", + " ('every', 29),\n", + " ('hotels', 28),\n", + " ('square', 28),\n", + " ('walk', 28),\n", + " ('each', 28),\n", + " ('queen', 28),\n", + " ('meeting', 27),\n", + " ('features', 27),\n", + " ('style', 27),\n", + " ('where', 27),\n", + " ('district', 27),\n", + " ('full', 27),\n", + " ('light', 26),\n", + " ('featuring', 26),\n", + " ('lobby', 26),\n", + " ('internet', 26),\n", + " ('street', 26),\n", + " ('two', 26),\n", + " ('such', 26),\n", + " ('speed', 26),\n", + " ('tacoma', 26),\n", + " ('need', 25),\n", + " ('relax', 25),\n", + " ('work', 25),\n", + " ('suite', 25),\n", + " ('travel', 25),\n", + " ('hot', 25),\n", + " ('wifi', 25),\n", + " ('family', 25),\n", + " ('km', 25),\n", + " ('world', 24),\n", + " ('comfort', 24),\n", + " ('historic', 24),\n", + " ('convention', 24),\n", + " ('time', 24),\n", + " ('miles', 24),\n", + " ('out', 23),\n", + " ('outdoor', 23),\n", + " ('distance', 23),\n", + " ('sea', 23),\n", + " ('whether', 23),\n", + " ('travelers', 23),\n", + " ('some', 22),\n", + " ('living', 22),\n", + " ('flat', 22),\n", + " ('us', 21),\n", + " ('sound', 21),\n", + " ('offering', 21),\n", + " ('designed', 21),\n", + " ('walking', 21),\n", + " ('visit', 21),\n", + " ('blocks', 21),\n", + " ('its', 21),\n", + " ('other', 21),\n", + " ('hill', 21),\n", + " ('lounge', 20),\n", + " ('not', 20),\n", + " ('safeco', 20),\n", + " ('explore', 20),\n", + " ('steps', 20),\n", + " ('welcome', 20),\n", + " ('next', 20),\n", + " ('feature', 20),\n", + " ('site', 20),\n", + " ('sure', 20),\n", + " ('amazon', 19),\n", + " ('here', 19),\n", + " ('than', 19),\n", + " ('if', 19),\n", + " ('rail', 19),\n", + " ('off', 19),\n", + " ('building', 19),\n", + " ('first', 19),\n", + " ('south', 19),\n", + " ('include', 19),\n", + " ('property', 19),\n", + " ('wa', 19),\n", + " ('motel', 19),\n", + " ('leisure', 18),\n", + " ('everything', 18),\n", + " ('luxury', 18),\n", + " ('fresh', 18),\n", + " ('morning', 18),\n", + " ('convenience', 18),\n", + " ('through', 18),\n", + " ('minute', 18),\n", + " ('new', 17),\n", + " ('club', 17),\n", + " ('stylish', 17),\n", + " ('kitchen', 17),\n", + " ('beds', 17),\n", + " ('come', 17),\n", + " ('emerald', 17),\n", + " ('centurylink', 17),\n", + " ('top', 17),\n", + " ('short', 17),\n", + " ('equipped', 17),\n", + " ('tv', 17),\n", + " ('food', 17),\n", + " ('screen', 17),\n", + " ('nearby', 16),\n", + " ('puget', 16),\n", + " ('meetings', 16),\n", + " ('feet', 16),\n", + " ('across', 16),\n", + " ('music', 16),\n", + " ('unique', 16),\n", + " ('today', 16),\n", + " ('indoor', 16),\n", + " ('few', 16),\n", + " ('convenient', 16),\n", + " ('capitol', 16),\n", + " ('fun', 16),\n", + " ('traveling', 16),\n", + " ('flight', 16),\n", + " ('iconic', 15),\n", + " ('west', 15),\n", + " ('avenue', 15),\n", + " ('see', 15),\n", + " ('pioneer', 15),\n", + " ('accommodations', 15),\n", + " ('right', 15),\n", + " ('urban', 15),\n", + " ('there', 15),\n", + " ('hyatt', 15),\n", + " ('plus', 15),\n", + " ('guestrooms', 15),\n", + " ('famous', 15),\n", + " ('extended', 15),\n", + " ('no', 15),\n", + " ('both', 15),\n", + " ('tac', 15),\n", + " ('anne', 15),\n", + " ('over', 14),\n", + " ('vibrant', 14),\n", + " ('north', 14),\n", + " ('options', 14),\n", + " ('mile', 14),\n", + " ('which', 14),\n", + " ('situated', 14),\n", + " ('comforts', 14),\n", + " ('signature', 14),\n", + " ('shops', 14),\n", + " ('bay', 14),\n", + " ('built', 14),\n", + " ('around', 14),\n", + " ('start', 14),\n", + " ('conveniently', 14),\n", + " ('events', 14),\n", + " ('continental', 14),\n", + " ('grand', 13),\n", + " ('class', 13),\n", + " ('award', 13),\n", + " ('spa', 13),\n", + " ('sports', 13),\n", + " ('town', 13),\n", + " ('belltown', 13),\n", + " ('along', 13),\n", + " ('olympic', 13),\n", + " ('plush', 13),\n", + " ('special', 13),\n", + " ('outside', 13),\n", + " ('night', 13),\n", + " ('into', 13),\n", + " ('after', 13),\n", + " ('facilities', 13),\n", + " ('long', 13),\n", + " ('pet', 13),\n", + " ('medical', 13),\n", + " ('hilton', 12),\n", + " ('major', 12),\n", + " ('variety', 12),\n", + " ('starbucks', 12),\n", + " ('relaxing', 12),\n", + " ('advantage', 12),\n", + " ('central', 12),\n", + " ('contemporary', 12),\n", + " ('areas', 12),\n", + " ('five', 12),\n", + " ('any', 12),\n", + " ('inspired', 12),\n", + " ('staying', 12),\n", + " ('meet', 12),\n", + " ('but', 12),\n", + " ('drive', 12),\n", + " ('provide', 12),\n", + " ('popular', 12),\n", + " ('microwave', 12),\n", + " ('so', 12),\n", + " ('stop', 12),\n", + " ('heated', 12),\n", + " ('bathroom', 12),\n", + " ('house', 12),\n", + " ('laundry', 12),\n", + " ('beautiful', 12),\n", + " ('seatac', 12),\n", + " ('garden', 11),\n", + " ('000', 11),\n", + " ('unwind', 11),\n", + " ('cuisine', 11),\n", + " ('step', 11),\n", + " ('front', 11),\n", + " ('entertainment', 11),\n", + " ('book', 11),\n", + " ('they', 11),\n", + " ('spaces', 11),\n", + " ('winning', 11),\n", + " ('help', 11),\n", + " ('get', 11),\n", + " ('what', 11),\n", + " ('view', 11),\n", + " ('floor', 11),\n", + " ('original', 11),\n", + " ('about', 11),\n", + " ('cruise', 11),\n", + " ('social', 11),\n", + " ('studio', 11),\n", + " ('feel', 11),\n", + " ('want', 11),\n", + " ('upscale', 11),\n", + " ('air', 11),\n", + " ('friends', 11),\n", + " ('large', 11),\n", + " ('10', 11),\n", + " ('mall', 11),\n", + " ('quiet', 11),\n", + " ('less', 11),\n", + " ('three', 11),\n", + " ('inch', 11),\n", + " ('trip', 11),\n", + " ('link', 11),\n", + " ('check', 11),\n", + " ('hospitality', 11),\n", + " ('back', 11),\n", + " ('cable', 11),\n", + " ('was', 11),\n", + " ('boeing', 11),\n", + " ('visiting', 11),\n", + " ('desk', 11),\n", + " ('glass', 10),\n", + " ('daily', 10),\n", + " ('seahawks', 10),\n", + " ('renovated', 10),\n", + " ('wine', 10),\n", + " ('cozy', 10),\n", + " ('charm', 10),\n", + " ('inviting', 10),\n", + " ('block', 10),\n", + " ('elliott', 10),\n", + " ('then', 10),\n", + " ('live', 10),\n", + " ('seasonal', 10),\n", + " ('bath', 10),\n", + " ('aquarium', 10),\n", + " ('water', 10),\n", + " ('swimming', 10),\n", + " ('corporate', 10),\n", + " ('microsoft', 10),\n", + " ('fully', 10),\n", + " ('history', 10),\n", + " ('ideal', 10),\n", + " ('furnishings', 10),\n", + " ('tvs', 10),\n", + " ('hours', 10),\n", + " ('campus', 10),\n", + " ('door', 10),\n", + " ('hospital', 10),\n", + " ('mason', 10),\n", + " ('staff', 9),\n", + " ('snacks', 9),\n", + " ('provides', 9),\n", + " ('wireless', 9),\n", + " ('mariners', 9),\n", + " ('range', 9),\n", + " ('host', 9),\n", + " ('love', 9),\n", + " ('appointed', 9),\n", + " ('spend', 9),\n", + " ('during', 9),\n", + " ('four', 9),\n", + " ('mountains', 9),\n", + " ('ride', 9),\n", + " ('bedding', 9),\n", + " ('fridge', 9),\n", + " ('landmark', 9),\n", + " ('20', 9),\n", + " ('use', 9),\n", + " ('vacation', 9),\n", + " ('choice', 9),\n", + " ('community', 9),\n", + " ('businesses', 9),\n", + " ('value', 9),\n", + " ('bedroom', 9),\n", + " ('windows', 9),\n", + " ('days', 9),\n", + " ('courtyard', 9),\n", + " ('catch', 9),\n", + " ('extra', 9),\n", + " ('red', 9),\n", + " ('road', 9),\n", + " ('virginia', 9),\n", + " ('mansion', 9),\n", + " ('eclectic', 8),\n", + " ('proximity', 8),\n", + " ('activities', 8),\n", + " ('natural', 8),\n", + " ('sheraton', 8),\n", + " ('doors', 8),\n", + " ('small', 8),\n", + " ('skyline', 8),\n", + " ('planning', 8),\n", + " ('catering', 8),\n", + " ('mind', 8),\n", + " ('boutique', 8),\n", + " ('warm', 8),\n", + " ('rooftop', 8),\n", + " ('rich', 8),\n", + " ('known', 8),\n", + " ('classic', 8),\n", + " ('know', 8),\n", + " ('delicious', 8),\n", + " ('venues', 8),\n", + " ('tub', 8),\n", + " ('yourself', 8),\n", + " ('onsite', 8),\n", + " ('pleasure', 8),\n", + " ('includes', 8),\n", + " ('evening', 8),\n", + " ('directly', 8),\n", + " ('alike', 8),\n", + " ('cancer', 8),\n", + " ('traveler', 8),\n", + " ('stadium', 8),\n", + " ('even', 8),\n", + " ('escape', 8),\n", + " ('king', 8),\n", + " ('refrigerator', 8),\n", + " ('premium', 8),\n", + " ('budget', 8),\n", + " ('facility', 8),\n", + " ('renton', 8),\n", + " ('alfred', 8),\n", + " ('silver', 8),\n", + " ('cloud', 8),\n", + " ('bars', 7),\n", + " ('reception', 7),\n", + " ('dinner', 7),\n", + " ('exciting', 7),\n", + " ('recently', 7),\n", + " ('favorite', 7),\n", + " ('inside', 7),\n", + " ('stunning', 7),\n", + " ('throughout', 7),\n", + " ('workout', 7),\n", + " ('library', 7),\n", + " ('gorgeous', 7),\n", + " ('wood', 7),\n", + " ('seating', 7),\n", + " ('among', 7),\n", + " ('car', 7),\n", + " ('arts', 7),\n", + " ('atmosphere', 7),\n", + " ('fit', 7),\n", + " ('always', 7),\n", + " ('ve', 7),\n", + " ('locally', 7),\n", + " ('floors', 7),\n", + " ('mini', 7),\n", + " ('stays', 7),\n", + " ('maker', 7),\n", + " ('old', 7),\n", + " ('cultural', 7),\n", + " ('sofa', 7),\n", + " ('hdtv', 7),\n", + " ('game', 7),\n", + " ('transportation', 7),\n", + " ('easily', 7),\n", + " ('open', 7),\n", + " ('executive', 7),\n", + " ('apartment', 7),\n", + " ('kitchens', 7),\n", + " ('been', 7),\n", + " ('non', 7),\n", + " ('bathrooms', 7),\n", + " ('table', 7),\n", + " ('hostel', 7),\n", + " ('roof', 7),\n", + " ('ballard', 7),\n", + " ('proud', 7),\n", + " ('station', 7),\n", + " ('services', 7),\n", + " ('european', 7),\n", + " ('southcenter', 7),\n", + " ('people', 7),\n", + " ('100', 7),\n", + " ('needs', 7),\n", + " ('looking', 7),\n", + " ('don', 7),\n", + " ('15', 7),\n", + " ('shoreline', 7),\n", + " ('much', 7),\n", + " ('broadway', 7),\n", + " ('perfectly', 6),\n", + " ('companies', 6),\n", + " ('google', 6),\n", + " ('conference', 6),\n", + " ('cocktail', 6),\n", + " ('drinks', 6),\n", + " ('seven', 6),\n", + " ('collection', 6),\n", + " ('sleep', 6),\n", + " ('savor', 6),\n", + " ('happy', 6),\n", + " ('public', 6),\n", + " ('nordstrom', 6),\n", + " ('terminal', 6),\n", + " ('spectacular', 6),\n", + " ('custom', 6),\n", + " ('simple', 6),\n", + " ('fireplace', 6),\n", + " ('wide', 6),\n", + " ('culture', 6),\n", + " ('patio', 6),\n", + " ('join', 6),\n", + " ('setting', 6),\n", + " ('wake', 6),\n", + " ('cup', 6),\n", + " ('hiking', 6),\n", + " ('scene', 6),\n", + " ('getaway', 6),\n", + " ('theater', 6),\n", + " ('landmarks', 6),\n", + " ('down', 6),\n", + " ('lodging', 6),\n", + " ('separate', 6),\n", + " ('plan', 6),\n", + " ('hub', 6),\n", + " ('retreat', 6),\n", + " ('museums', 6),\n", + " ('thriving', 6),\n", + " ('size', 6),\n", + " ('kitchenettes', 6),\n", + " ('dine', 6),\n", + " ('hand', 6),\n", + " ('team', 6),\n", + " ('corner', 6),\n", + " ('do', 6),\n", + " ('ready', 6),\n", + " ('centers', 6),\n", + " ('own', 6),\n", + " ('experiences', 6),\n", + " ('complete', 6),\n", + " ('brings', 6),\n", + " ('furnished', 6),\n", + " ('ideally', 6),\n", + " ('kind', 6),\n", + " ('creative', 6),\n", + " ('discover', 6),\n", + " ('television', 6),\n", + " ('bus', 6),\n", + " ('homewood', 6),\n", + " ('nightlife', 6),\n", + " ('regency', 6),\n", + " ('level', 6),\n", + " ('go', 6),\n", + " ('flexible', 6),\n", + " ('grill', 6),\n", + " ('key', 6),\n", + " ('mt', 6),\n", + " ('rainier', 6),\n", + " ('buffet', 6),\n", + " ('zoo', 6),\n", + " ('matter', 6),\n", + " ('headquarters', 6),\n", + " ('play', 6),\n", + " ('shower', 6),\n", + " ('westfield', 6),\n", + " ('quick', 6),\n", + " ('smoking', 6),\n", + " ('channels', 6),\n", + " ('rate', 6),\n", + " ('tea', 6),\n", + " ('enjoyable', 6),\n", + " ('research', 6),\n", + " ('busy', 6),\n", + " ('fred', 6),\n", + " ('hutchinson', 6),\n", + " ('very', 6),\n", + " ('apartments', 6),\n", + " ('resort', 6),\n", + " ('gates', 5),\n", + " ('locals', 5),\n", + " ('american', 5),\n", + " ('core', 5),\n", + " ('diverse', 5),\n", + " ('america', 5),\n", + " ('expanded', 5),\n", + " ('enjoying', 5),\n", + " ('beverage', 5),\n", + " ('several', 5),\n", + " ('crowne', 5),\n", + " ('exceptional', 5),\n", + " ('cool', 5),\n", + " ('drink', 5),\n", + " ('better', 5),\n", + " ('might', 5),\n", + " ('half', 5),\n", + " ('must', 5),\n", + " ('houses', 5),\n", + " ('boutiques', 5),\n", + " ('pier', 5),\n", + " ('stadiums', 5),\n", + " ('mountain', 5),\n", + " ('newly', 5),\n", + " ('sleek', 5),\n", + " ('welcoming', 5),\n", + " ('elegant', 5),\n", + " ('residence', 5),\n", + " ('puts', 5),\n", + " ('tour', 5),\n", + " ('via', 5),\n", + " ('destination', 5),\n", + " ('culinary', 5),\n", + " ('cocktails', 5),\n", + " ('between', 5),\n", + " ('monorail', 5),\n", + " ('warwick', 5),\n", + " ('way', 5),\n", + " ('possible', 5),\n", + " ('head', 5),\n", + " ('craft', 5),\n", + " ('put', 5),\n", + " ('end', 5),\n", + " ('kimpton', 5),\n", + " ('enough', 5),\n", + " ('who', 5),\n", + " ('dedicated', 5),\n", + " ('beer', 5),\n", + " ('design', 5),\n", + " ('could', 5),\n", + " ('marriott', 5),\n", + " ('westlake', 5),\n", + " ('refrigerators', 5),\n", + " ('desks', 5),\n", + " ('found', 5),\n", + " ('ship', 5),\n", + " ('terminals', 5),\n", + " ('innovative', 5),\n", + " ('makes', 5),\n", + " ('chic', 5),\n", + " ('beauty', 5),\n", + " ('system', 5),\n", + " ('professional', 5),\n", + " ('facebook', 5),\n", + " ('sleeping', 5),\n", + " ('deck', 5),\n", + " ('made', 5),\n", + " ('hall', 5),\n", + " ('30', 5),\n", + " ('connected', 5),\n", + " ('customer', 5),\n", + " ('panel', 5),\n", + " ('televisions', 5),\n", + " ('wines', 5),\n", + " ('course', 5),\n", + " ('too', 5),\n", + " ('list', 5),\n", + " ('ensure', 5),\n", + " ('holiday', 5),\n", + " ('either', 5),\n", + " ('districts', 5),\n", + " ('fremont', 5),\n", + " ('choose', 5),\n", + " ('soft', 5),\n", + " ('lifestyle', 5),\n", + " ('adventure', 5),\n", + " ('adventures', 5),\n", + " ('simply', 5),\n", + " ('these', 5),\n", + " ('beverages', 5),\n", + " ('forget', 5),\n", + " ('store', 5),\n", + " ('intimate', 5),\n", + " ('receptions', 5),\n", + " ('details', 5),\n", + " ('century', 5),\n", + " ('cities', 5),\n", + " ('oasis', 5),\n", + " ('communal', 5),\n", + " ('express', 5),\n", + " ('residential', 5),\n", + " ('runs', 5),\n", + " ('woodland', 5),\n", + " ('personal', 5),\n", + " ('yet', 5),\n", + " ('bellevue', 5),\n", + " ('interior', 5),\n", + " ('healthy', 5),\n", + " ('above', 5),\n", + " ('stress', 5),\n", + " ('term', 5),\n", + " ('accessible', 5),\n", + " ('run', 5),\n", + " ('lodge', 5),\n", + " ('filled', 5),\n", + " ('boardroom', 5),\n", + " ('green', 5),\n", + " ('self', 5),\n", + " ('units', 5),\n", + " ('bustling', 5),\n", + " ('college', 5),\n", + " ('northgate', 5),\n", + " ('round', 5),\n", + " ('hit', 5),\n", + " ('won', 5),\n", + " ('ten', 5),\n", + " ('pride', 5),\n", + " ('landing', 5),\n", + " ('linens', 5),\n", + " ('ourselves', 5),\n", + " ('bill', 4),\n", + " ('melinda', 4),\n", + " ('foundation', 4),\n", + " ('visitors', 4),\n", + " ('majestic', 4),\n", + " ('sq', 4),\n", + " ('ft', 4),\n", + " ('technology', 4),\n", + " ('wedding', 4),\n", + " ('success', 4),\n", + " ('refresh', 4),\n", + " ('latest', 4),\n", + " ('tastefully', 4),\n", + " ('decorated', 4),\n", + " ('productive', 4),\n", + " ('lunch', 4),\n", + " ('gateway', 4),\n", + " ('plaza', 4),\n", + " ('touches', 4),\n", + " ('set', 4),\n", + " ('lights', 4),\n", + " ('addition', 4),\n", + " ('rest', 4),\n", + " ('5th', 4),\n", + " ('sounders', 4),\n", + " ('curated', 4),\n", + " ('paramount', 4),\n", + " ('luxurious', 4),\n", + " ('comfy', 4),\n", + " ('good', 4),\n", + " ('why', 4),\n", + " ('sightseeing', 4),\n", + " ('leading', 4),\n", + " ('refreshing', 4),\n", + " ('covered', 4),\n", + " ('surrounded', 4),\n", + " ('trendy', 4),\n", + " ('side', 4),\n", + " ('let', 4),\n", + " ('show', 4),\n", + " ('memorable', 4),\n", + " ('fare', 4),\n", + " ('got', 4),\n", + " ('diamond', 4),\n", + " ('scenic', 4),\n", + " ('never', 4),\n", + " ('tell', 4),\n", + " ('without', 4),\n", + " ('retail', 4),\n", + " ('adjacent', 4),\n", + " ('harbor', 4),\n", + " ('port', 4),\n", + " ('sculpture', 4),\n", + " ('look', 4),\n", + " ('breathtaking', 4),\n", + " ('sites', 4),\n", + " ('goal', 4),\n", + " ('additional', 4),\n", + " ('elegance', 4),\n", + " ('named', 4),\n", + " ('sophisticated', 4),\n", + " ('afternoon', 4),\n", + " ('metro', 4),\n", + " ('500', 4),\n", + " ('nestled', 4),\n", + " ('health', 4),\n", + " ('55', 4),\n", + " ('mobile', 4),\n", + " ('settle', 4),\n", + " ('those', 4),\n", + " ('getting', 4),\n", + " ('things', 4),\n", + " ('science', 4),\n", + " ('42', 4),\n", + " ('keep', 4),\n", + " ('watch', 4),\n", + " ('coast', 4),\n", + " ('bright', 4),\n", + " ('plug', 4),\n", + " ('selection', 4),\n", + " ('stand', 4),\n", + " ('unparalleled', 4),\n", + " ('expansive', 4),\n", + " ('energy', 4),\n", + " ('ours', 4),\n", + " ('4th', 4),\n", + " ('would', 4),\n", + " ('board', 4),\n", + " ('active', 4),\n", + " ('kick', 4),\n", + " ('fuel', 4),\n", + " ('western', 4),\n", + " ('romantic', 4),\n", + " ('clean', 4),\n", + " ('same', 4),\n", + " ('upgrade', 4),\n", + " ('monday', 4),\n", + " ('something', 4),\n", + " ('casual', 4),\n", + " ('marble', 4),\n", + " ('12', 4),\n", + " ('movie', 4),\n", + " ('arena', 4),\n", + " ('served', 4),\n", + " ('accommodate', 4),\n", + " ('week', 4),\n", + " ('owned', 4),\n", + " ('mediterranean', 4),\n", + " ('delivers', 4),\n", + " ('hip', 4),\n", + " ('leave', 4),\n", + " ('products', 4),\n", + " ('twin', 4),\n", + " ('early', 4),\n", + " ('train', 4),\n", + " ('exercise', 4),\n", + " ('freshly', 4),\n", + " ('menu', 4),\n", + " ('function', 4),\n", + " ('deluxe', 4),\n", + " ('redmond', 4),\n", + " ('snack', 4),\n", + " ('seafood', 4),\n", + " ('dip', 4),\n", + " ('overnight', 4),\n", + " ('greet', 4),\n", + " ('relaxed', 4),\n", + " ('exploring', 4),\n", + " ('shop', 4),\n", + " ('affordable', 4),\n", + " ('give', 4),\n", + " ('rewards', 4),\n", + " ('program', 4),\n", + " ('making', 4),\n", + " ('pillow', 4),\n", + " ('authentic', 4),\n", + " ('inspiring', 4),\n", + " ('how', 4),\n", + " ('smoke', 4),\n", + " ('405', 4),\n", + " ('hampton', 4),\n", + " ('kids', 4),\n", + " ('everyone', 4),\n", + " ('meals', 4),\n", + " ('99', 4),\n", + " ('11', 4),\n", + " ('accommodation', 4),\n", + " ('training', 4),\n", + " ('beach', 4),\n", + " ('points', 4),\n", + " ('tours', 4),\n", + " ('econo', 4),\n", + " ('microwaves', 4),\n", + " ('outlets', 4),\n", + " ('little', 4),\n", + " ('conditioned', 4),\n", + " ('americas', 4),\n", + " ('money', 4),\n", + " ('historical', 4),\n", + " ('year', 4),\n", + " ('attention', 4),\n", + " ('jimmy', 4),\n", + " ('national', 4),\n", + " ('theodore', 4),\n", + " ('warmth', 4),\n", + " ('maxwell', 4),\n", + " ('creature', 4),\n", + " ('definition', 4),\n", + " ('bacon', 4),\n", + " ('georgetown', 4),\n", + " ('grove', 4),\n", + " ('watertown', 4),\n", + " ('gaslight', 4),\n", + " ('oak', 4),\n", + " ('southport', 4),\n", + " ('allows', 3),\n", + " ('kayaking', 3),\n", + " ('versatile', 3),\n", + " ('guarantee', 3),\n", + " ('equipment', 3),\n", + " ('chihuly', 3),\n", + " ('earn', 3),\n", + " ('chef', 3),\n", + " ('blend', 3),\n", + " ('soon', 3),\n", + " ('concierge', 3),\n", + " ('fantastic', 3),\n", + " ('amid', 3),\n", + " ('incredible', 3),\n", + " ('haven', 3),\n", + " ('prime', 3),\n", + " ('crafted', 3),\n", + " ('celebrated', 3),\n", + " ('unforgettable', 3),\n", + " ('reflect', 3),\n", + " ('hosts', 3),\n", + " ('company', 3),\n", + " ('underground', 3),\n", + " ('everywhere', 3),\n", + " ('landscape', 3),\n", + " ('region', 3),\n", + " ('bounty', 3),\n", + " ('truly', 3),\n", + " ('pleasant', 3),\n", + " ('breeze', 3),\n", + " ('deep', 3),\n", + " ('waters', 3),\n", + " ('straight', 3),\n", + " ('breweries', 3),\n", + " ('mount', 3),\n", + " ('soak', 3),\n", + " ('before', 3),\n", + " ('heading', 3),\n", + " ('destinations', 3),\n", + " ('ever', 3),\n", + " ('reading', 3),\n", + " ('couldn', 3),\n", + " ('alexis', 3),\n", + " ('matched', 3),\n", + " ('attentive', 3),\n", + " ('interesting', 3),\n", + " ('giving', 3),\n", + " ('edge', 3),\n", + " ('indulge', 3),\n", + " ('loft', 3),\n", + " ('ceilings', 3),\n", + " ('them', 3),\n", + " ('elements', 3),\n", + " ('still', 3),\n", + " ('sit', 3),\n", + " ('outfitted', 3),\n", + " ('balconies', 3),\n", + " ('perks', 3),\n", + " ('gym', 3),\n", + " ('sunset', 3),\n", + " ('rock', 3),\n", + " ('fireplaces', 3),\n", + " ('kitchenette', 3),\n", + " ('bistro', 3),\n", + " ('fairmont', 3),\n", + " ('acclaimed', 3),\n", + " ('news', 3),\n", + " ('report', 3),\n", + " ('2018', 3),\n", + " ('shows', 3),\n", + " ('outdoors', 3),\n", + " ('fans', 3),\n", + " ('athletic', 3),\n", + " ('begin', 3),\n", + " ...]" + ] + }, + "execution_count": 14, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "words_freq = sorted(words_freq, key=lambda x:x[1],reverse=True) # 排序重复的次数\n", + "words_freq" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "这里重复最多的the我们并不是重要的信息词,后面我们需要进行怎样的优化呢" + ] + }, { "cell_type": "code", "execution_count": null,