In [1]:
# import logging
# logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s', level=logging.INFO)
In [7]:
from gensim import corpora, models, similarities
from gensim.models.ldamodel import LdaModel
import os
from pprint import pprint
if (os.path.exists("assets/dictionary_today.dict")):
dictionary = corpora.Dictionary.load('assets/dictionary_today.dict')
corpus = corpora.MmCorpus('assets/corpus_today.mm')
print("Load Dictionary and Corpus : Success")
else:
print("Please following instruction : 4_Build_Dictionary_and_Corpus")
Load Dictionary and Corpus : Success
In [8]:
tfidf = models.TfidfModel(corpus)
In [9]:
print(tfidf)
TfidfModel(num_docs=297, num_nnz=28542)
In [10]:
new_doc = "raffi ahmad ahok jokowi"
new_vec = dictionary.doc2bow(new_doc.lower().split())
# pprint(new_vec)
entity = new_doc.lower().split()
entity = enumerate(entity)
vector_idf = tfidf[new_vec]
# vector_idf = enumerate(vector_idf)
for id, person in entity:
print(person)
print('tf : %s' % (new_vec[id][1]))
print('tf-idf : %s' % (vector_idf[id][1]))
print('=================')
raffi
tf : 1
tf-idf : 0.389844410571
=================
ahmad
tf : 1
tf-idf : 0.426404637311
=================
ahok
tf : 1
tf-idf : 0.449171521867
=================
jokowi
tf : 1
tf-idf : 0.681502285227
=================
In [11]:
corpus_tfidf_sample = tfidf[corpus[:1]]
for doc in corpus_tfidf_sample:
print(doc)
[(0, 0.07086305475366766), (1, 0.09366943253252122), (2, 0.08226624364309444), (3, 0.041386239085859325), (4, 0.08226624364309444), (5, 0.09366943253252122), (6, 0.029983050196432545), (7, 0.09366943253252122), (8, 0.09411864335046109), (9, 0.19257785059413862), (10, 0.07559580575413964), (11, 0.06419261686471288), (12, 0.0765459152476721), (13, 0.07086305475366766), (14, 0.06419261686471288), (15, 0.12331326815327275), (16, 0.09366943253252122), (17, 0.055788858989426995), (18, 0.07559580575413964), (19, 0.09045902541626202), (20, 0.16453248728618888), (21, 0.041386239085859325), (22, 0.1055788559505722), (23, 0.05945986586424088), (24, 0.0527894279752861), (25, 0.07559580575413964), (26, 0.047059321675230546), (27, 0.07559580575413964), (28, 0.06419261686471288), (29, 0.08142932645037262), (30, 0.06419261686471288), (31, 0.055788858989426995), (32, 0.03426505179359425), (33, 0.08226624364309444), (34, 0.09366943253252122), (35, 0.05752217897575808), (36, 0.06719204787885377), (37, 0.04611899008633131), (38, 0.2810082975975637), (39, 0.09366943253252122), (40, 0.09366943253252122), (41, 0.09366943253252122), (42, 0.09366943253252122), (43, 0.09366943253252122), (44, 0.07559580575413964), (45, 0.05147261945262117), (46, 0.28345221901467066), (47, 0.0542208803351447), (48, 0.04071466322518631), (49, 0.16453248728618888), (50, 0.08226624364309444), (51, 0.4935974618585667), (52, 0.0542208803351447), (53, 0.13315701030000063), (54, 0.08226624364309444), (55, 0.08226624364309444), (56, 0.09366943253252122), (57, 0.18733886506504244), (58, 0.055788858989426995), (59, 0.07086305475366766), (60, 0.07559580575413964), (61, 0.055788858989426995), (62, 0.09366943253252122), (63, 0.09366943253252122), (64, 0.08226624364309444), (65, 0.041386239085859325), (66, 0.15119161150827928), (67, 0.08277247817171865), (68, 0.16453248728618888), (69, 0.09366943253252122), (70, 0.07086305475366766), (71, 0.06719204787885377), (72, 0.08226624364309444), (73, 0.08226624364309444), (74, 0.09366943253252122), (75, 0.07330697617077467), (76, 0.07559580575413964), (77, 0.04611899008633131), (78, 0.06419261686471288), (79, 0.08226624364309444)]
In [12]:
corpus_tfidf = tfidf[corpus]
In [20]:
num_topics = 30
chunksize = 20
passes = 20
iterations = 200
eval_every = None
temp = dictionary[0]
id2word = dictionary.id2token
%time model = LdaModel(corpus=corpus, id2word=id2word, chunksize=chunksize, \
alpha='auto', eta='auto', \
iterations=iterations, num_topics=num_topics, \
passes=passes, eval_every=eval_every)
CPU times: user 59.8 s, sys: 2.26 s, total: 1min 2s
Wall time: 1min 2s
In [21]:
%time top_topics = model.top_topics(corpus, num_words=20)
avg_topic_coherence = sum([t[1] for t in top_topics]) / num_topics
print('Average topic coherence: %.4f.' % avg_topic_coherence)
from pprint import pprint
pprint(top_topics)
CPU times: user 2min 27s, sys: 1.79 s, total: 2min 29s
Wall time: 2min 33s
Average topic coherence: -298.8691.
[([(0.028017315702492638, u'akun'),
(0.024807045145181311, u'toyota'),
(0.02200394467105185, u'mesin'),
(0.018682608460818182, u'tangga'),
(0.018175473429581781, u'suzuki'),
(0.018175473429581781, u'ignis'),
(0.016595763324207369, u'etios'),
(0.0155718411687147, u'surabaya'),
(0.014909607753720647, u'penjualan'),
(0.014753288631893624, u'hatchback'),
(0.014524457434506715, u'model'),
(0.014370018328535827, u'pemesanan'),
(0.013497477668602331, u'dijual'),
(0.01314838657769702, u'agya'),
(0.012910688863921778, u'rio'),
(0.011072939335850377, u'hafid'),
(0.0092251590004409426, u'segmen'),
(0.0091215100736121817, u'jiexpo'),
(0.0091215100736121817, u'kemayoran'),
(0.0085110961466815169, u'mike')],
-184.95368346078004),
([(0.045728233662885642, u'busa'),
(0.033889795323409043, u'proyek'),
(0.031882976594030298, u'salju'),
(0.030439423817001994, u'cairan'),
(0.024666051120400972, u'mrt'),
(0.023352442493672024, u'pt'),
(0.021680612540347956, u'sudirman'),
(0.018704455164034867, u'tanah'),
(0.017266878705383588, u'twitter'),
(0.016276813244962805, u'benda'),
(0.014171406314787225, u'lingkungan'),
(0.012410488939464347, u'hoax'),
(0.011672545885763511, u'selesai'),
(0.011525252690255937, u'februari'),
(0.011335075525321609, u'kawasan'),
(0.010896283024486319, u'bersih'),
(0.010738990614025952, u'kontraktor'),
(0.01052132882150065, u'material'),
(0.0096644761149604248, u'pembangunan'),
(0.0093541145901844883, u'jalanan')],
-190.11644652836742),
([(0.045040500367753304, u'prediabetes'),
(0.039188070840630786, u'diabetes'),
(0.024419617511785705, u'penyakit'),
(0.023799801744358067, u'ahmed'),
(0.023220985753526071, u'dokter'),
(0.01676853564446951, u'darah'),
(0.014920863454013864, u'glukosa'),
(0.013711964730133393, u'kali'),
(0.012873999344453047, u'mardi'),
(0.01228889448035772, u'prof'),
(0.011225572281668221, u'mengalami'),
(0.010887556208383624, u'gigi'),
(0.010463107344281849, u'pasien'),
(0.009598184286878567, u'tulang'),
(0.0095535502767680903, u'produksi'),
(0.0089699110146119268, u'intervensi'),
(0.0084885591636671143, u'melitus'),
(0.0081981895725383707, u'deteksi'),
(0.0081213451213143044, u'bobot'),
(0.0079086672642198676, u'pendek')],
-192.9802483024086),
([(0.089475335384024413, u'dio'),
(0.078099233525548706, u'sekolah'),
(0.04524979890528525, u'presiden'),
(0.018721704056529405, u'senden'),
(0.017632985084204383, u'yuliati'),
(0.015645593718967694, u'ditangkap'),
(0.015504804900120666, u'ibu'),
(0.01449994773262347, u'siswa'),
(0.012569345982618331, u'sepeda'),
(0.011596712422866595, u'ahad'),
(0.011570715933514266, u'sdn'),
(0.010197401279142506, u'kelainan'),
(0.0099614229863531651, u'sd'),
(0.0096800088273882885, u'bangku'),
(0.0094782102856693102, u'terlibat'),
(0.008824077640577457, u'syndrome'),
(0.008824077640577457, u'barre'),
(0.008824077640577457, u'guillain'),
(0.008824077640577457, u'iv'),
(0.008824077640577457, u'genetis')],
-193.11503623795696),
([(0.050280465288829013, u'dr'),
(0.034683109904550175, u'chika'),
(0.032985964674582001, u'ulang'),
(0.028312254353996445, u'obligasi'),
(0.027976515327623803, u'ng'),
(0.021703701095301682, u'd'),
(0.018547369023572242, u'tahap'),
(0.017172988064289452, u'b'),
(0.014466503772392079, u'fajri'),
(0.012680573503232572, u'perseroan'),
(0.012444512898655665, u'n'),
(0.012013170610215724, u'bahagia'),
(0.011532847020544384, u'gubernur'),
(0.011489829671031024, u'sekuritas'),
(0.011410091566732778, u'kupon'),
(0.010983469250041599, u'penerbitan'),
(0.01055680644058141, u'berkelanjutan'),
(0.010462812490782467, u'triliun'),
(0.01034764532246671, u'struktur'),
(0.0091970924082479168, u'penawaran')],
-197.94143250928502),
([(0.027682371558377026, u'reklamasi'),
(0.023131365902388342, u'pulau'),
(0.019283878344564454, u'pesisir'),
(0.019049079496594894, u'luhut'),
(0.018422701803184227, u'undang'),
(0.015670342717366361, u'edukasi'),
(0.015479481725904741, u'dki'),
(0.014686111716744856, u'mengikuti'),
(0.014288961906170501, u'muhamad'),
(0.014197448798772373, u'menyambut'),
(0.013195263715586792, u'cita'),
(0.011599808133990086, u'terumbu'),
(0.011044844942671647, u'bilang'),
(0.010608936808148678, u'up'),
(0.0096611087740485942, u'kendati'),
(0.0093162037021669412, u'poros'),
(0.0090709416003996509, u'pantai'),
(0.0087751385276053778, u'rangkaian'),
(0.0085299485813012197, u'maritim'),
(0.0080709681869778893, u'provinsi')],
-208.10977612944495),
([(0.032206513999805057, u'messi'),
(0.031754861314776894, u'sby'),
(0.031418747501302129, u'demokrat'),
(0.02961432359177097, u'aktivitas'),
(0.021499667743490245, u'capres'),
(0.019944044282110249, u'guru'),
(0.019271332371751736, u'fitnah'),
(0.019176588868087267, u'mataram'),
(0.015064049274298396, u'pebalap'),
(0.014246728138255817, u'rekor'),
(0.01258738568490423, u'bali'),
(0.011965532631159967, u'kalimantan'),
(0.011706771042393229, u'rapat'),
(0.011454724419969456, u'cawapres'),
(0.011289464105891711, u'car'),
(0.010605509609555641, u'dibiarkan'),
(0.010393771792409743, u'ahy'),
(0.010158945653029411, u'ntb'),
(0.010113009547674615, u'pilpres'),
(0.0097634890157720332, u'yudhoyono')],
-216.44601413100671),
([(0.094610897354623205, u'rumah'),
(0.051157876736632926, u'sheila'),
(0.041605636552879161, u'sakit'),
(0.033699888839919735, u'mengalami'),
(0.025477042427528664, u'pulang'),
(0.022859513159313425, u'kecelakaan'),
(0.022275808662936006, u'marcia'),
(0.022064133345226642, u'kondisi'),
(0.01978022085844609, u'vanesha'),
(0.018863631541618076, u'akibat'),
(0.018742032455918808, u'honda'),
(0.013681753838993043, u'teman'),
(0.012986028320186537, u'erie'),
(0.01001063531829449, u'sambungan'),
(0.0097507958702889846, u'mobil'),
(0.0080973173859748889, u'anji'),
(0.0080553400964984336, u'ditemui'),
(0.0078993981215702939, u'lari'),
(0.0077978055184616136, u'selatan'),
(0.0074366212773336925, u'medistra')],
-253.23399141984027),
([(0.029640385665252754, u'macron'),
(0.026524174395745951, u'persen'),
(0.022994873442337371, u'partai'),
(0.020038118731165268, u'presiden'),
(0.019894182444700474, u'mei'),
(0.019653157043555275, u'pen'),
(0.019550141789402762, u'le'),
(0.018397040060328215, u'eropa'),
(0.017878161801041008, u'as'),
(0.016571816695686629, u'menit'),
(0.01655418129477846, u'baca'),
(0.013360253471285092, u'prancis'),
(0.013261769646909541, u'program'),
(0.013188272089521356, u'ribu'),
(0.012555659585361119, u'spanyol'),
(0.011511026984820892, u'mantan'),
(0.011103100111835667, u'perancis'),
(0.010605479141027978, u'kanan'),
(0.010572065111523681, u'memiliki'),
(0.010523387745989181, u'politik')],
-262.74066719126239),
([(0.048750346691432418, u'xmax'),
(0.041177978964002361, u'yamaha'),
(0.023104138432286554, u'konsumen'),
(0.022103591271677915, u'masyarakat'),
(0.019719843494631455, u'yimm'),
(0.014861394768332502, u'korea'),
(0.013564405553404255, u'bagus'),
(0.01179386959196015, u'imos'),
(0.010342451418551198, u'skutik'),
(0.010083977875824806, u'banget'),
(0.010024629761163743, u'tito'),
(0.0090035592335379611, u'kim'),
(0.0087813524575710705, u'xmaxfirstowners'),
(0.0086256495720654427, u'budidarmo'),
(0.0075706802298524025, u'penyerahan'),
(0.0074797745787499367, u'saksi'),
(0.0073549871409182253, u'mengumumkan'),
(0.0071543840559085857, u'petrus'),
(0.0071214643563874361, u'simbolis'),
(0.0070640490538576746, u'x')],
-268.01364645992084),
([(0.0314965133318095, u'layanan'),
(0.022179791363313561, u'pabrik'),
(0.016621023597769572, u'milik'),
(0.015707581815958608, u'kunci'),
(0.014386210992836313, u'diumumkan'),
(0.013778622994790952, u'dinosaurus'),
(0.013489710105040582, u'menentang'),
(0.012919576533265356, u'market'),
(0.0118083570669003, u'kecepatan'),
(0.011106662825647635, u'maduro'),
(0.01029119920041897, u'menangani'),
(0.0099897410146571677, u'c919'),
(0.0098856116976912822, u'udara'),
(0.00977851134624615, u'tembus'),
(0.0097736124150443436, u'standar'),
(0.0091694778902725697, u'venezuela'),
(0.0086813670606628937, u'board'),
(0.0085643935382773376, u'komodo'),
(0.0083741749951809566, u'perdana'),
(0.0082389116452656289, u'panjaitan')],
-270.06191798386635),
([(0.047267064931074236, u'mandiri'),
(0.026778879225855423, u'online'),
(0.02348241157198425, u'nasabah'),
(0.017112769420733816, u'balapan'),
(0.016056007861893519, u'madrid'),
(0.015427835564935087, u'marquez'),
(0.014626846097559794, u'pedrosa'),
(0.012694362982213913, u'real'),
(0.012282098727641797, u'rohan'),
(0.011609307558866466, u'banking'),
(0.011459568649027699, u'dana'),
(0.010978162587376206, u'diluncurkan'),
(0.010575899426566964, u'jerez'),
(0.010541574840552796, u'lorenzo'),
(0.0099333903430678279, u'sirkuit'),
(0.0099322293287754694, u'gp'),
(0.009885303566962076, u'transaksi'),
(0.0089684134185436526, u'morata'),
(0.0084272745350924341, u'mencetak'),
(0.0082691389299048863, u'merilis')],
-283.10129718679298),
([(0.038164478783393095, u'tim'),
(0.032042456939103431, u'gol'),
(0.02692233569568828, u'laga'),
(0.026057477671164543, u'pemain'),
(0.024331437611906936, u'liga'),
(0.020255227035756319, u'jokowi'),
(0.020119188226188436, u'widodo'),
(0.019996206657006282, u'kemenangan'),
(0.019547921299805811, u'persib'),
(0.017051519569044452, u'menang'),
(0.014986102465004102, u'pertandingan'),
(0.012238300984811361, u'persipura'),
(0.011310553676997721, u'kali'),
(0.010922422735721317, u'posisi'),
(0.01014626679889302, u'klasemen'),
(0.0094271860870491376, u'bermain'),
(0.0086404831264444756, u'normal'),
(0.0084919521186417862, u'tampil'),
(0.0084546533221270641, u'gaya'),
(0.0082006039686409824, u'babak')],
-304.40409150015296),
([(0.045028038037978564, u'iims'),
(0.041817893153721371, u'tahanan'),
(0.038210844716457845, u'kelas'),
(0.031792152904449998, u'show'),
(0.028467111443010916, u'pekanbaru'),
(0.026087121245149631, u'mei'),
(0.024420145784107759, u'kabur'),
(0.02423721091829472, u'yasonna'),
(0.023095196973656605, u'rutan'),
(0.021575984345442351, u'international'),
(0.021118252149241973, u'pameran'),
(0.020170557836101746, u'kasus'),
(0.019534354102759159, u'orang'),
(0.017312714327284748, u'riau'),
(0.013729446826892016, u'sialang'),
(0.011980540619322921, u'bungkuk'),
(0.010629451338907433, u'lp'),
(0.010143410236352519, u'hukuman'),
(0.0099951876241950975, u'lembaga'),
(0.0097696173163050355, u'metro')],
-305.09313967285442),
([(0.02757788184916218, u'manusia'),
(0.024057414797126954, u'hak'),
(0.020577855799335104, u'planet'),
(0.017083963361794068, u'mencari'),
(0.013910908054300401, u'hawking'),
(0.012995897700689818, u'gejala'),
(0.01256254445421477, u'terang'),
(0.012475383813811797, u'november'),
(0.012355841348495551, u'china'),
(0.012039175536756212, u'university'),
(0.011865998181401305, u'muncul'),
(0.010481536731733489, u'menderita'),
(0.0097670956357321804, u'mengeluarkan'),
(0.0093802115622447502, u'sayangnya'),
(0.0093614042291313999, u'cassini'),
(0.0093614042291313999, u'saturnus'),
(0.009245722381697909, u'diprediksi'),
(0.0087783495110238981, u'otot'),
(0.0083739893777235088, u'pria'),
(0.0079448192688815322, u'hewan')],
-305.41434066280277),
([(0.025300191685859244, u'video'),
(0.024574787625278271, u'smartphone'),
(0.024435191811658288, u'bandung'),
(0.024102390137092162, u'kamera'),
(0.01917122408244782, u'ponsel'),
(0.018730171891719462, u'nokia'),
(0.018695220359995466, u'iphone'),
(0.016306287999076137, u'hujan'),
(0.013851357239980407, u'fitur'),
(0.013550337500322016, u'air'),
(0.012546094977058869, u'tablet'),
(0.01225093273829763, u'snapdragon'),
(0.011264957908148148, u'meter'),
(0.010941120953698395, u'c'),
(0.01092860683165788, u'galaxy'),
(0.010049028141277061, u'penjualan'),
(0.0099621127759779021, u'menjual'),
(0.0085757295852196894, u'menimbulkan'),
(0.0085648480536972271, u'varian'),
(0.0084492771860291381, u'apple')],
-310.85341035688685),
([(0.048501336029622373, u'balon'),
(0.028940881803205032, u'kerja'),
(0.024996932164534792, u'ahmad'),
(0.022193627640029134, u'sidang'),
(0.019563364149477375, u'menyerahkan'),
(0.019412900351957082, u'djarot'),
(0.019013391662173425, u'balai'),
(0.017279330982403269, u'apresiasi'),
(0.014934464164483862, u'lulus'),
(0.014411964221482788, u'el'),
(0.014019705489133207, u'sma'),
(0.012513579430417752, u'ucapan'),
(0.012045138473633478, u'positif'),
(0.011648932144573427, u'ramah'),
(0.010587255534102325, u'peduli'),
(0.010504714453795702, u'maia'),
(0.010350085135708498, u'memimpin'),
(0.0098934440964562401, u'dani'),
(0.0096988020516056081, u'weni'),
(0.0094575506984684848, u'pengadilan')],
-318.01657716842794),
([(0.043528114908040594, u'acara'),
(0.031707473439761803, u'pasangan'),
(0.031602591059522407, u'foto'),
(0.031297407525918287, u'new'),
(0.030583609779711082, u'sang'),
(0.030410141041988904, u'kabar'),
(0.025778122881706514, u'media'),
(0.02300679536511269, u'pasar'),
(0.020112918568716075, u'and'),
(0.017839366573742511, u'tangan'),
(0.01737218690566621, u'tulis'),
(0.016048044025458976, u'bukti'),
(0.014156393485174579, u'rekan'),
(0.014064037318780037, u'jenjang'),
(0.012933382978655704, u'berita'),
(0.012800620442721927, u'raffi'),
(0.01180193341833324, u'lihat'),
(0.011509604929411367, u'digelar'),
(0.011453700566095511, u'resmi'),
(0.011400720018666618, u'jakarta')],
-319.06897494354814),
([(0.051714102778553497, u'utara'),
(0.027820490081574504, u'tinggal'),
(0.026001449590995804, u'gas'),
(0.024648430305951451, u'korut'),
(0.02442818813411364, u'kota'),
(0.021808038818537382, u'warga'),
(0.018770408998027895, u'ruang'),
(0.018634947294185057, u'nomor'),
(0.015949638884984123, u'aids'),
(0.014898595429754918, u'hiv'),
(0.01137242284889323, u'pyongyang'),
(0.01009172107261979, u'ditahan'),
(0.0095308684134836931, u'restoran'),
(0.0093971122368720315, u'alias'),
(0.0093217510125022333, u'komunitas'),
(0.0082488329158641911, u'sukabumi'),
(0.0080886003567901144, u'berencana'),
(0.0079789760684943374, u'persero'),
(0.0079465111319934265, u'news'),
(0.0075665453790271734, u'apbn')],
-319.13998252446942),
([(0.04976089938174847, u'berdasarkan'),
(0.045191343585559207, u'posisi'),
(0.036763479421394844, u'barat'),
(0.035665106322099814, u'jawa'),
(0.033529078604929811, u'polda'),
(0.02761281469194956, u'hamas'),
(0.020372676296453136, u'mei'),
(0.012458889009552752, u'menengah'),
(0.012053508147613115, u'gaza'),
(0.011346394459605778, u'haniya'),
(0.010879994053916391, u'korps'),
(0.010802264668253427, u'surat'),
(0.010562972857459886, u'dipindahkan'),
(0.010461447317660846, u'kali'),
(0.01044894993691531, u'wilayah'),
(0.010322022635956742, u'andi'),
(0.0094171318390486852, u'bhayangkara'),
(0.0090775588824922645, u'melaju'),
(0.0085084000761645098, u'iman'),
(0.0083160189240112335, u'mengumumkan')],
-328.20159339249784),
([(0.053714158428966839, u'liputan6'),
(0.043494152557514439, u'khusus'),
(0.036812647085607539, u'seks'),
(0.03035937139032456, u'bercinta'),
(0.02918732968960875, u'dikutip'),
(0.023009000475019806, u'kehidupan'),
(0.021241908886696907, u'kondisi'),
(0.02116805445253981, u'sesi'),
(0.019149359498703888, u'hasil'),
(0.013330547332080214, u'tubuh'),
(0.01078665604200189, u'main'),
(0.010474282432375841, u'lelah'),
(0.0099605942417072216, u'pijatan'),
(0.0099241002822455255, u'menyebabkan'),
(0.009788958952829897, u'kecewa'),
(0.0094398951527135105, u'laman'),
(0.0090409445291130507, u'ekspedisi'),
(0.0089877127668554404, u'singkat'),
(0.0089318686429220254, u'merasakan'),
(0.0082278878638108351, u'lomba')],
-344.42608106220212),
([(0.20168259158172613, u'jakarta'),
(0.053550080756219628, u'unit'),
(0.05120012713988404, u'jalan'),
(0.032829993312102831, u'dki'),
(0.031015258746524707, u'wib'),
(0.021889841054292161, u'putih'),
(0.021164241652861283, u'polisi'),
(0.01972260697387716, u'proses'),
(0.018886291257503577, u'nama'),
(0.016739992278083766, u'jam'),
(0.0164965832673243, u'kepala'),
(0.016165505664690022, u'lokasi'),
(0.016128103695955052, u'informasi'),
(0.015897522018310382, u'kejadian'),
(0.015602057471657946, u'mobil'),
(0.015142275498328575, u'timur'),
(0.014625955745120087, u'pagi'),
(0.013350117549286257, u'm'),
(0.012629502463910945, u'napi'),
(0.012419923000038588, u'daerah')],
-347.49052816868368),
([(0.04879476222928214, u'anak'),
(0.04203530039178667, u'perempuan'),
(0.040902668039839926, u'kota'),
(0.037483874729811205, u'pemerintah'),
(0.027392791945803487, u'ibu'),
(0.022873377972017397, u'bom'),
(0.020211109756371106, u'afghanistan'),
(0.018238985076461264, u'perbatasan'),
(0.016960316741054984, u'all'),
(0.015690073553332216, u'selamat'),
(0.015136195544611391, u'paus'),
(0.015123100042736724, u'merah'),
(0.014274691232949752, u'dilaporkan'),
(0.013803492975790891, u'laut'),
(0.012330920011926884, u'pemimpin'),
(0.011321618374321675, u'sesuai'),
(0.011301300158506764, u'militer'),
(0.010933910820775302, u'menolak'),
(0.01001626566333829, u'semenjak'),
(0.0098869333452510626, u'smp')],
-354.16746335446203),
([(0.036979570211119896, u'data'),
(0.035891159777615991, u'poin'),
(0.031604285443066517, u'rossi'),
(0.025972702526381529, u'angka'),
(0.020384042920790858, u'pekan'),
(0.019626659019736883, u'badan'),
(0.017849814699142579, u'roma'),
(0.017731919362440163, u'fisik'),
(0.01582427875908262, u'gubernur'),
(0.015237514775855523, u'pelatih'),
(0.014363220416137449, u'cepat'),
(0.013997468939763261, u'senang'),
(0.013307753738744136, u'milan'),
(0.012530798083903977, u'berharap'),
(0.011745602347327969, u'terima'),
(0.011650396989317009, u'provinsi'),
(0.011537246950107612, u'mengakui'),
(0.011296355959690073, u'montella'),
(0.011260384951485809, u'premium'),
(0.011256471091115763, u'hitam')],
-360.83577326984113),
([(0.042375978262602615, u'berjalan'),
(0.041603723598440299, u'pusat'),
(0.028633018880654386, u'perjalanan'),
(0.026577195235083721, u'wakil'),
(0.024741727652866703, u'melanjutkan'),
(0.022406607899568682, u'pasukan'),
(0.020805863642141709, u'maju'),
(0.019461791680505693, u'kaum'),
(0.016023493899576229, u'perwakilan'),
(0.015155594090680393, u'bertemu'),
(0.014376845029964676, u'lengkap'),
(0.012931840056748091, u'ma'),
(0.012456516306791749, u'masjid'),
(0.011812927779258226, u'baswedan'),
(0.010785199586422541, u'gnpf'),
(0.0095557020210823504, u'launching'),
(0.0093898884617155953, u'damai'),
(0.0092801754992736449, u'diambil'),
(0.0090730047623139159, u'istiqlal'),
(0.0088248133938767168, u'mengapresiasi')],
-368.2475834546853),
([(0.037795870000083422, u'malam'),
(0.033157185664018679, u'berbeda'),
(0.031840616763138437, u'hidup'),
(0.029396647630392243, u'kesehatan'),
(0.029160607186053664, u'menjaga'),
(0.028955587937533212, u'i'),
(0.025807972958144233, u'memilih'),
(0.025406368204388827, u'keluarga'),
(0.025203274259353852, u'bentuk'),
(0.025077289869146119, u'faktor'),
(0.024990108129793697, u'berasal'),
(0.023865514756024026, u'utama'),
(0.021897546254475223, u'meraih'),
(0.020926412686943476, u'pakistan'),
(0.020298980365007328, u'pilihan'),
(0.018999534499661352, u'seri'),
(0.018995850350443884, u'jajaran'),
(0.018861720319180209, u'memiliki'),
(0.017075184987165055, u'jenis'),
(0.016715869074599397, u'membantu')],
-382.05920914955561),
([(0.024353578357453297, u'juta'),
(0.01928360494672568, u'rp'),
(0.018854051212849731, u'bank'),
(0.0142193799892267, u'harga'),
(0.011775536304833694, u'pergi'),
(0.010336114168615507, u'kaki'),
(0.0098794563246423824, u'biaya'),
(0.0097535746032813078, u'jupe'),
(0.0097029994725298212, u'produk'),
(0.0094307387339577029, u'sistem'),
(0.0092798631972942896, u'sandiaga'),
(0.0092203947509715087, u'kantor'),
(0.0091878965408051586, u'anies'),
(0.0087950912445275368, u'uang'),
(0.0087935790946160105, u'sandi'),
(0.008586601811974074, u'eko'),
(0.0078340479779589016, u'pendidikan'),
(0.007351703152558205, u'pt'),
(0.0071724572203839161, u'barcelona'),
(0.0071568124142239167, u'uno')],
-384.8344582107685),
([(0.028885900405905364, u'menerima'),
(0.026157412277977941, u'menjalani'),
(0.02582148916607379, u'pesawat'),
(0.024496504440327447, u'wanita'),
(0.023648620414279564, u'duduk'),
(0.023537186707280802, u'laki'),
(0.022392599725781046, u'makanan'),
(0.022043509458844399, u'kemarin'),
(0.021390781121012, u'berat'),
(0.017810415121795362, u'pesan'),
(0.016983285335749478, u'membuka'),
(0.016567276898449064, u'bantuan'),
(0.015496489388790731, u'taman'),
(0.015266525739716555, u'berharap'),
(0.011976588557039026, u'dibuka'),
(0.011755587395950139, u'manager'),
(0.011450202570141425, u'terbaik'),
(0.010564379064619598, u'global'),
(0.010290249371443579, u'berwarna'),
(0.010282094021562278, u'bergerak')],
-385.6965123906445),
([(0.041846600979228002, u'negara'),
(0.020461255882337784, u'aksi'),
(0.019850855947025483, u'jenderal'),
(0.016991597589004908, u'ahok'),
(0.016593883442988434, u'mengaku'),
(0.015136079576203077, u'kasus'),
(0.014781315498554638, u'bumi'),
(0.014715691970794264, u'perusahaan'),
(0.014429150167476321, u'menyebut'),
(0.013919655795830287, u'negeri'),
(0.013563884524215079, u'bernama'),
(0.013528850097880471, u'amerika'),
(0.013512729535111857, u'mencapai'),
(0.013484005167144854, u'dukungan'),
(0.012917227763095306, u'ketua'),
(0.012742911228263725, u'of'),
(0.012702003620862696, u'hukum'),
(0.011999027016604925, u'basuki'),
(0.011651519504972901, u'wahana'),
(0.011052523373064772, u'internet')],
-394.74709457355067),
([(0.1048965897204301, u'indonesia'),
(0.068062656577812616, u'motor'),
(0.031246213773456301, u'masuk'),
(0.028424010418839577, u'warga'),
(0.027656393167920512, u'ajang'),
(0.022809205170660068, u'kegiatan'),
(0.02209769294861617, u'memiliki'),
(0.020331139510819649, u'menarik'),
(0.020204927862822367, u'keterangan'),
(0.019417100162142216, u'bicara'),
(0.018630049115319989, u'hasil'),
(0.018194901609052027, u'mudah'),
(0.016913967927307559, u'resmi'),
(0.016248823209322368, u'dunia'),
(0.015591859654194004, u'kompas'),
(0.015427298425761252, u'turun'),
(0.015210846561780943, u'sisi'),
(0.010993412318257383, u'ya'),
(0.01055379786933189, u'makassar'),
(0.010426353039598392, u'lapas')],
-412.56324991057539)]
In [ ]:
Content source: kunbud1989/scraping-google-news-indonesia
Similar notebooks: