rebase

IT19001708/STG/dataset/df_filtered.csv

+,word
+7,instead
+9,ground
+14,wished
+22,search
+23,food
+28,whenever
+37,house
+43,thought
+45,closed
+54,please
+62,crash
+66,shouted
+74,strong
+75,commanded
+82,housebaby
+88,tricks
+96,beach
+98,family
+105,snatch
+107,catch
+112,tree
+115,fast
+125,cleaver
+132,chance
+135,fir
+142,ready
+144,bunch
+149,count
+157,around
+158,tops
+161,high
+162,top
+168,really
+175,wherever
+183,would
+184,think
+203,cool
+210,people
+214,without
+218,fight
+219,lights
+223,bright
+226,bounce
+233,steady
+239,shed
+244,beat
+248,every
+252,willing
+255,together
+268,buildings
+274,everywhere
+276,clothes
+280,things
+286,trolley
+294,shows
+295,toys
+297,choose
+299,round
+300,bought
+303,back
+311,whiskers
+315,catfish
+321,white
+322,snowflakes
+329,gates
+332,trying
+333,toy
+338,might
+345,something
+347,insect
+349,found
+356,scratch
+360,tight
+368,three
+375,eat
+387,country
+400,flower
+419,thing
+420,creep
+423,facts
+427,trout
+433,bear
+436,hat
+449,field
+452,tarctor
+462,horn
+464,flowers
+468,thankful
+471,healthy
+472,learn
+493,fox
+495,thank
+500,hear
+509,creams
+513,strawberry
+516,hour
+522,anywhere
+524,treehouse
+528,reading
+534,showed
+542,first
+548,light
+553,told
+558,art
+559,painted
+561,arrows
+577,washes
+581,clean
+589,shivering
+593,board
+600,mother
+605,thebutterfly
+610,higher
+613,sparrow
+617,easy
+623,though
+639,fools
+642,splash
+649,ate
+658,thin
+686,hate
+689,fool
+692,plate
+703,shout
+706,foot
+710,loft
+717,branch
+726,chase
+730,sounds
+749,crack
+763,spaceship
+771,thinks
+780,breathe
+784,hills
+788,right
+789,collects
+792,bot
+797,earth
+799,head
+805,another
+825,follows
+832,reach
+837,twisted
+844,everyone
+845,morning
+849,waved
+854,played
+872,gleamed
+884,ears
+890,tough
+892,tongue
+894,throat
+902,balanced
+906,feather
+907,feathers
+911,eating
+912,insects
+917,watches
+923,frees
+924,heal
+925,bounces
+934,thabi
+943,neighbour
+944,heard
+947,thanks
+948,boring
+966,throw
+988,sunflower
+989,crying
+990,thief
+994,officer
+996,crook
+998,chased
+999,hill
+1004,fires
+1009,caught
+1016,waves
+1019,four
+1041,clever
+1043,know
+1047,sandcastle
+1060,chewing
+1061,sound
+1070,cornflower
+1071,clear
+1076,fathom
+1081,beneath
+1085,nothing
+1100,branches
+1104,castle
+1106,built
+1108,gothic
+1114,flows
+1115,appearance
+1122,years
+1126,exceedingly
+1128,account
+1131,others
+1133,allowed
+1134,wear
+1136,however
+1145,youngest
+1154,houses
+1161,fire
+1164,fro
+1168,burning
+1170,everything
+1174,surrounded
+1177,weather
+1179,streaming
+1182,pleased
+1185,whale
+1192,thoughtful
+1196,obtained
+1213,fresh
+1220,crown
+1223,grandmother
+1224,knew
+1226,towns
+1229,reached
+1230,fifteenth
+1231,year
+1236,following
+1242,enough
+1243,information
+1244,longed
+1247,splashed
+1250,faintly
+1257,holding
+1275,eagerly
+1278,city
+1284,sight
+1285,whole
+1293,tints
+1295,third
+1297,broad
+1300,covered
+1303,castles
+1309,often
+1313,creek
+1316,sporting
+1318,fright
+1320,terribly
+1325,although
+1326,fourth
+1328,remained
+1337,whales
+1341,fountains
+1343,fifth
+1345,occurred
+1346,winter
+1348,floating
+1349,loftier
+1352,seated
+1360,thunder
+1362,flashed
+1365,tossed
+1366,heaving
+1369,fear
+1370,trembling
+1374,flashes
+1375,sights
+1377,become
+1379,month
+1381,hours
+1384,approach
+1386,expected
+1394,howling
+1400,tears
+1401,therefore
+1407,wreath
+1420,heavy
+1423,lightly
+1426,tinted
+1430,beamed
+1434,becalmed
+1444,lighted
+1451,welldressed
+1452,within
+1460,stretched
+1461,appeared
+1464,fireworks
+1466,spurted
+1468,fireflies
+1469,reflected
+1470,brightly
+1473,distinctly
+1474,plainly
+1477,resounded
+1479,extinguished
+1481,ceased
+1482,firing
+1495,approaching
+1502,lofty
+1503,foaming
+1509,creaked
+1510,thick
+1514,snapped
+1522,beams
+1524,pitch
+1533,father
+1537,crush
+1554,brought
+1556,health
+1559,smooth
+1560,forehead
+1561,presently
+1564,building
+1565,whether
+1572,sunshine
+1574,sounded
+1575,farther
+1578,watched
+1580,fetched
+1584,sorrowfully
+1587,gathered
+1589,sorrowful
+1599,known
+1600,whose
+1605,flights
+1612,costly
+1619,fountain
+1620,threw
+1631,boat
+1637,fishermen
+1638,torches
+1642,heartily
+1645,mount
+1654,rightly
+1664,flourish
+1665,contrary
+1667,turned
+1670,unknown
+1671,glorious
+1673,mournfully
+1674,knowing
+1680,thoughts
+1711,heart
+1714,charming
+1715,sorrow
+1719,sounding
+1720,certainly
+1721,wishes
+1724,witch
+1726,whirlpools
+1728,sorceress
+1729,neither
+1732,whirlpool
+1734,whirled
+1737,fathomless
+1738,crushing
+1747,heads
+1755,clutches
+1757,nearly
+1758,turning
+1761,flowing
+1764,shoots
+1774,chests
+1775,tightly
+1779,shocking
+1784,rolling
+1785,showing
+1787,bones
+1788,shipwrecked
+1789,allowing
+1790,toad
+1791,mouth
+1792,canary
+1807,tomorrow
+1818,treading
+1822,flow
+1824,allow
+1830,death
+1835,charm
+1842,surely
+1846,cleanliness
+1847,scouring
+1851,breast
+1853,horrible
+1860,torn
+1861,thousand
+1866,rushing
+1869,approached
+1874,recovered
+1876,earnestly
+1881,wrapped
+1885,bore
+1886,willingly
+1892,arrayed
+1911,appealed
+1912,directly
+1915,readily
+1916,touched
+1920,cushion
+1923,horseback
+1926,boughs
+1927,shoulders
+1934,household
+1935,eased
+1936,bathe
+1950,ashore
+1955,service
+1963,neighboring
+1976,forced
+1977,rather
+1985,distinguish
+1988,wringing
+1992,towers
+1999,educated
+2000,religious
+2001,learning
+2003,anxious
+2004,acknowledge
+2013,blushing
+2020,already
+2027,betrothal
+2039,ceremony
+2043,erected
+2046,reception
+2050,smoothly
+2053,thinking
+2080,leaned
+2082,east
+2083,blush
+2091,haste
+2101,resting
+2103,brighter
+2105,whispered
+2109,fainting
+2115,ethereal
+2118,earthly
+2120,answered
+2125,countries
+2131,restoration
+2139,searching
+2140,pearly
+2141,thrown
+2143,mounted
+2152,shortened
+2156,tear
+2163,hilt
+2165,weathercock
+2166,councillors
+2172,fearing
+2179,charity
+2180,cathedral
+2182,cloaks
+2184,mathematical
+2186,frowned
+2189,dreaming
+2193,early
+2194,moth
+2195,attracted
+2202,touching
+2204,courtship
+2209,twittered
+2210,money
+2211,relations
+2219,curtseys
+2223,finally
+2224,attached
+2230,alighted
+2232,softly
+2235,wing
+2239,north
+2249,drenched
+2258,chose
+2270,seamstress
+2288,tomb
+2289,coffin
+2295,withered
+2297,thirsty
+2303,throwing
+2307,famous
+2329,feverishly
+2332,thimble
+2337,action
+2339,phenomenon
+2340,professor
+2341,ornithology
+2342,wrote
+2345,newspaper
+2355,distinguished
+2363,throne
+2383,theatre
+2384,write
+2393,firewood
+2394,command
+2403,harbour
+2405,heave
+2417,cooing
+2420,match
+2421,matches
+2429,shoulder
+2433,sphinx
+2435,merchants
+2440,worships
+2443,honey
+2444,cakes
+2447,suffering
+2466,frost
+2480,brother
+2481,fact
+2489,actually
+2492,clerk
+2495,pulled
+2496,university
+2499,corporation
+2506,foundry
+2507,heap
+2509,chosen
+2516,written
+2518,philosophy
+2519,wretched
+2522,hyacinth
+2534,pearls
+2536,forth
+2538,purchased
+2555,outright
+2558,whiter
+2562,yellower
+2567,scythe
+2577,thorn
+2579,chariot
+2584,heather
+2590,mighty
+2591,coloured
+2592,breath
+2597,finished
+2603,sincerity
+2605,arts
+2606,selfish
+2625,perfected
+2627,eastern
+2633,burst
+2637,shepherds
+2647,nephew
+2654,wheel
+2661,metaphysics
+2665,peach
+2667,graphic
+2668,cornish
+2676,nowhere
+2680,invited
+2685,rattled
+2690,twittering
+2692,farthest
+2695,blowing
+2696,playground
+2697,downstairs
+2698,front
+2702,clock
+2711,hath
+2713,wound
+2714,thee
+2719,wounds
+2720,thou
+2728,teach
+2743,overheard
+2750,fiction
+2752,alighting
+2757,humoured
+2776,months
+2786,season
+2789,ideas
+2790,neighbours
+2796,woolly
+2798,troubled
+2804,pears
+2808,bothered
+2810,least
+2831,confused
+2859,windmill
+2861,ear
+2867,wheelbarrow
+2869,buttons
+2878,foolish
+2882,ease
+2883,easily
+2888,mentioned
+2890,worth
+2900,honeysuckle
+2905,carrying
+2907,creepers
+2910,refuse
+2913,sixth
+2922,exactly
+2928,hearing
+2933,cheery
+2938,theory
+2943,somehow
+2947,reflection
+2966,torrents
+2970,goatherds
+2978,blacksmith
+2979,comfortably
+2987,screamed
+2989,whisk
+2991,confirmed
+2992,bachelor
+3011,blushed
+3016,published
+3030,whatever
+3031,item
+3034,firework
+3039,borealis
+3043,appear
+3046,crackers
+3053,candle
+3055,thoroughly
+3058,catherine
+3060,fashionable
+3066,instance
+3067,dearly
+3073,becomes
+3074,cough
+3076,coughed
+3077,observation
+3082,cracker
+3097,renowned
+3102,french
+3108,shower
+3109,newspapers
+3110,performance
+3118,tone
+3119,crushed
+3131,treads
+3132,whisper
+3134,laughter
+3135,reason
+3143,indignantly
+3155,inferiority
+3157,hearts
+3163,hollow
+3169,affected
+3177,heaved
+3182,shield
+3183,leading
+3184,beautifully
+3189,marched
+3191,torch
+3193,whizz
+3203,becoming
+3205,frown
+3212,shattered
+3215,mottled
+3219,croak
+3220,croaking
+3231,hesitation
+3232,breakfasting
+3238,complacently
+3240,opinions
+3241,irritating
+3245,sympathetic
+3246,possibly
+3249,immediately
+3257,pleasures
+3266,born
+3269,otherwise
+3272,plough
+3277,accomplishments
+3279,industry
+3287,tedious
+3299,domesticity
+3318,straight
+3334,accustomed
+3341,weave
+3346,property
+3348,invisible
+3350,office
+3353,character
+3357,caused
+3362,reality
+3364,thread
+3366,cloth
+3374,throughout
+3376,neighbors
+3399,pleases
+3420,accordingly
+3430,officers
+3433,absolutely
+3434,pointed
+3436,workmanship
+3439,graciously
+3440,closely
+3442,strained
+3444,nevertheless
+3447,uncommonly
+3448,shared
+3452,knighthood
+3454,title
+3458,trousers
+3460,mantle
+3465,borne
+3466,announced
+3468,examining
+3469,lords
+3474,simplicity
+3485,sorrows
+3487,furthermore
+3500,delightfully
+3501,humored
+3503,charmant
+3504,chatter
+3509,knight
+3510,tones
+3513,positively
+3514,refused
+3533,whoever
+3536,cooking
+3537,hearth
+3544,perfectly
+3551,constructed
+3552,rattle
+3557,creation
+3564,whilst
+3570,counting
+3577,march
+3578,thrust
+3579,scolded
+3582,washed
+3584,princely
+3588,honorable
+3590,wast
+3591,trumpery
+3592,plaything
+3611,author
+3613,writing
+3632,scanty
+3643,exerted
+3649,antechamber
+3650,mackintoshes
+3665,serious
+3666,business
+3667,properly
+3680,instantly
+3683,seriously
+3685,assuredly
+3688,freed
+3720,fifes
+3723,gleams
+3725,bluish
+3734,astonished
+3741,reflecting
+3744,trusting
+3756,boatmen
+3759,bornholmish
+3765,coach
+3766,coaches
+3767,hoped
+3771,bushes
+3775,resembling
+3782,whimpered
+3786,slightly
+3787,thatched
+3792,increasing
+3793,anxiety
+3806,clay
+3809,consisting
+3810,seamen
+3811,burghers
+3812,scholars
+3820,examined
+3823,repeated
+3825,strengthened
+3829,pitcher
+3833,mechanically
+3834,sheet
+3835,councillorship
+3838,handed
+3839,replying
+3846,cheerful
+3849,meteorous
+3850,appearances
+3852,reflections
+3853,highly
+3856,electricity
+3859,respectfully
+3861,learned
+3863,topic
+3872,theologia
+3893,inquiringly
+3896,twisting
+3897,writhing
+3898,wit
+3899,history
+3903,arthur
+3904,knights
+3910,theologian
+3915,recollect
+3918,hastily
+3919,worthy
+3925,satisfactorily
+3926,buccaneers
+3927,ofwas
+3932,shamefully
+3934,herostratic
+3941,topics
+3942,threatened
+3945,observations
+3949,herostratus
+3951,ephesian
+3952,wantonlyset
+3954,tocommemorate
+3956,recollection
+3957,preceded
+3960,overpowering
+3967,force
+3980,intoxicated
+3981,assertion
+3982,implored
+3983,heathens
+4001,considerately
+4002,leather
+4004,stretch
+4006,infirm
+4008,torment
+4012,furnished
+4015,lyrical
+4026,oft
+4036,tonight
+4041,hint
+4044,necessity
+4045,transplanted
+4048,reflects
+4057,weary
+4063,rejected
+4064,twas
+4066,altogether
+4070,somewhat
+4073,twould
+4075,ought
+4081,railroads
+4083,crossing
+4086,velocity
+4090,shock
+4093,upwards
+4094,seconds
+4096,accomplish
+4097,heavenly
+4100,nearlyenglish
+4114,beating
+4117,fiery
+4121,created
+4127,relates
+4134,translation
+4136,richard
+4138,originally
+4145,cleverness
+4148,astounding
+4152,appears
+4156,inch
+4159,heroines
+4176,planetary
+4183,counter
+4187,baltic
+4193,meanwhile
+4196,headed
+4200,haunted
+4202,rounds
+4210,bout
+4213,motionless
+4216,authorities
+4221,announce
+4224,assert
+4236,asserted
+4244,readings
+4246,inspection
+4254,seriousness
+4260,introduction
+4261,physical
+4262,thickest
+4269,notwithstanding
+4278,outwitted
+4280,clearly
+4284,motion
+4285,booths
+4289,pillory
+4291,hissing
+4293,mounting
+4299,suffocation
+4300,recited
+4305,boasted
+4309,constantly
+4318,exhortations
+4320,assembled
+4321,whence
+4326,displayed
+4332,motley
+4336,touches
+4337,openly
+4339,wraps
+4340,witty
+4344,thundercloud
+4345,shooting
+4357,effective
+4361,invention
+4362,using
+4363,circumspectly
+4364,revelation
+4369,cleaning
+4370,stately
+4377,spectators
+4378,institution
+4380,crooked
+4382,casts
+4387,retained
+4395,writhings
+4404,streamed
+4405,rejoicingly
+4409,butcher
+4410,nought
+4413,directory
+4419,cock
+4420,connected
+4429,astonishing
+4433,confounded
+4438,perplexity
+4439,lively
+4449,heat
+4450,ofcourse
+4451,warmest
+4452,ascendsgradually
+4453,highest
+4461,completely
+4467,copying
+4473,reduced
+4476,clerks
+4477,scribes
+4485,awhile
+4486,reports
+4494,beast
+4502,leads
+4503,sedentary
+4511,agreeable
+4528,acknowledged
+4529,boast
+4531,memory
+4538,abyss
+4540,threateningly
+4550,heated
+4556,crews
+4557,screaming
+4558,crow
+4565,patiently
+4568,affects
+4570,refreshing
+4572,torrent
+4576,overflowing
+4577,official
+4578,consolingly
+4579,tigbrith
+4581,acts
+4583,handwriting
+4594,flatly
+4596,breathlessly
+4597,exhausted
+4599,bursting
+4601,botanist
+4606,related
+4616,bestowed
+4625,height
+4630,certainty
+4635,whirlwind
+4640,chirping
+4641,contentedly
+4642,innate
+4650,metamorphosed
+4655,comedy
+4659,northern
+4661,overshadowed
+4666,sought
+4671,constabulary
+4674,strictly
+4681,schoolboys
+4684,lowest
+4686,gother
+4688,accursed
+4697,polly
+4700,backwards
+4703,wired
+4708,covering
+4714,brothers
+4718,uncouth
+4719,education
+4722,outspread
+4724,cooling
+4729,treatment
+4730,profound
+4731,knowledge
+4733,sighted
+4749,witticism
+4750,liberty
+4752,instinctively
+4757,creeping
+4758,tomcat
+4761,perched
+4766,invitingly
+4785,instantaneously
+4786,overstrained
+4790,creaking
+4794,pinched
+4795,torturing
+4797,intermediate
+4800,government
+4802,leathern
+4809,wherefore
+4820,outward
+4826,crags
+4828,surrounding
+4832,cashed
+4838,defeated
+4853,thousands
+4858,crammed
+4861,horses
+4862,tortured
+4867,coachman
+4875,south
+4879,anxiously
+4880,charms
+4881,profusely
+4883,solitary
+4885,crippled
+4887,healthiest
+4892,filthiest
+4896,thrusting
+4906,breathing
+4908,whine
+4916,consisted
+4918,seasoned
+4924,roasted
+4925,cocks
+4932,chamber
+4936,unceasingly
+4937,whined
+4941,whither
+4948,apothegm
+4949,corpse
+4951,immortality
+4952,teaches
+4955,heaviest
+4956,seeth
+4960,mound
+4964,imperishable
+4973,youth
+4977,firs
+4981,threaded
+4986,winters
+4990,comely
+4991,cracking
+4992,lopped
+4998,hither
+5000,majestically
+5009,ornamented
+5012,bough
+5014,incomparably
+5017,follow
+5018,ornament
+5029,covers
+5032,sofas
+5034,crowns
+5035,upright
+5048,ornaments
+5050,headache
+5051,candles
+5054,famously
+5065,cracked
+5089,shelves
+5091,tallow
+5093,portly
+5096,recounted
+5100,courtyard
+5107,exultingly
+5110,tore
+5111,trampling
+5115,chopped
+5122,causing
+5123,shown
+5124,increased
+5127,frights
+5148,twined
+5152,farthings
+5153,farthing
+5156,rounded
+5169,flowered
+5174,beasts
+5180,displeasing
+5181,sticking
+5182,tease
+5188,rough
+5190,thickly
+5191,vehicle
+5194,hedges
+5198,fowls
+5199,whiteness
+5200,freezingly
+5207,whistled
+5208,seas
+5209,chilling
+5210,wolves
+5211,crackled
+5213,witchcraft
+5218,clambered
+5224,cherry
+5225,orchard
+5230,combed
+5234,practised
+5235,feared
+5241,coverlet
+5244,collected
+5251,hearest
+5260,ashes
+5267,fresher
+5275,twines
+5276,cords
+5283,hyacinths
+5284,moonshine
+5287,coffins
+5294,sorrowing
+5313,barefooted
+5314,thrice
+5321,comfortless
+5325,learnt
+5327,gibberish
+5333,sweetheart
+5334,forthwith
+5336,initials
+5337,crowds
+5341,staircase
+5346,cleverest
+5350,marching
+5364,haughtily
+5370,hears
+5371,closing
+5382,taught
+5383,affecting
+5387,distinction
+5397,soundly
+5398,offered
+5400,footmen
+5402,assisted
+5413,scrubby
+5414,beard
+5415,bushy
+5422,headstrong
+5425,shouldered
+5428,displeased
+5429,cracks
+5436,burnt
+5441,laths
+5442,perches
+5448,horns
+5449,tethered
+5470,bound
+5480,meat
+5483,heath
+5486,gleam
+5490,burns
+5492,warmed
+5493,eaten
+5507,characters
+5508,thereon
+5509,imploringly
+5514,hence
+5516,thither
+5523,outposts
+5525,knotted
+5526,bears
+5528,thicker
+5531,shields
+5534,spears
+5535,security
+5537,seventh
+5540,mirth
+5558,coating
+5570,repaired
+5571,boundary
+5580,wears
+5604,thinner
+5605,vexation
+5606,housedog
+5608,prophet
+5609,writes
+5611,dishonorable
+5619,worldly
+5626,cover
+5634,fiftieth
+5644,coffee
+5651,christian
+5664,polished
+5666,neighing
+5673,smithy
+5677,seat
+5695,atmosphere
+5701,soothsayers
+5718,thitherward
+5725,confectioner
+5726,booth
+5734,proceeded
+5739,yearly
+5740,treatise
+5742,touchingly
+5743,greatly
+5745,gloriously
+5747,borrowed
+5749,hitherto
+5755,overgrown
+5761,whereon
+5762,accompanying
+5764,wrists
+5768,thorns
+5769,scratched
+5770,scratches
+5773,thrash
+5774,disheartened
+5785,toads
+5807,rounder
+5815,shoot
+5816,cherished
+5823,clothespress
+5824,thankee
+5825,cranky
+5839,shears
+5861,hoarse
+5864,hearse
+5868,slashed
+5869,rights
+5874,chattered
+5879,correctly
+5887,fricassees
+5893,mastery
+5903,manorhouse
+5904,forefathers
+5905,treated
+5908,creeps
+5923,inheritance
+5924,honestly
+5930,concluded
+5938,burred
+5940,hast
+5946,thornbush
+5947,afflicted
+5948,sufficiently
+5961,flowering
+5971,threaten
+5980,thine
+5981,fished
+5986,horror
+5987,wretchedness
+6000,starched
+6004,offer
+6016,betrothed
+6018,boaster
+6019,sweethearts
+6020,ferocious
+6031,freshen
+6033,hooting
+6034,shouting
+6039,wearers
+6052,thence
+6063,vexatious
+6065,finely
+6066,purchase
+6067,freedom
+6073,recover
+6084,heavily
+6096,offers
+6109,furthest
+6117,relationship
+6121,cake
+6130,consternation
+6131,professors
+6136,sickness
+6138,hearted
+6139,childhood
+6148,highness
+6152,insinuations
+6161,pounds
+6165,reasonable
+6173,bareheaded
+6178,livelong
+6183,cowered
+6186,burnished
+6189,tablecloth
+6191,stuffing
+6194,merchant
+6214,scratching
+6224,theenglish
+6235,thorwaldsen
+6248,crumbled
+6252,stagecoaches
+6258,streams
+6260,splashing
+6261,hroar
+6276,bottle
+6280,founded
+6289,thirst
+6296,roasting
+6297,hissed
+6300,frightful
+6305,clearing
+6306,arrow
+6307,flown
+6308,heartache
+6309,astonishingly
+6312,thrusts
+6317,clumsy
+6319,mourning
+6323,cleanly
+6327,tombs
+6328,preachers
+6329,wives
+6337,firm
+6341,terrified
+6356,crutches
+6359,repented
+6361,industrious
+6367,cushioned
+6375,fathers
+6379,grandfather
+6382,forty
+6383,wretch
+6389,showered
+6403,benefactor
+6406,gather
+6407,physician
+6410,physicians
+6416,instructions
+6418,gathering
+6424,hearty
+6433,established
+6444,footed
+6449,anchor
+6451,enchantingly
+6454,charmed
+6456,unseaworthy
+6460,indignity
+6467,studying
+6469,astrology
+6476,hideous
+6487,exterminated
+6495,leaving
+6499,snatched
+6503,watchfulness
+6515,arching
+6516,sharply
+6520,fixing
+6522,horribly
+6524,threat
+6528,assured
+6530,teachers
+6536,banished
+6537,disrespectfully
+6547,snatching
+6549,induce
+6550,refusing
+6553,securely
+6554,fits
+6574,appeased
+6576,theatres
+6577,mentioning
+6579,ordinary
+6584,interests
+6587,clothing
+6588,bounds
+6589,thursday
+6592,wealth
+6594,readiness
+6596,brilliantly
+6601,farmhouse
+6611,bewitched
+6613,patch
+6614,stepmother
+6617,wearisome
+6620,arrive
+6623,whereabout
+6624,roamed
+6629,aspen
+6633,whiles
+6637,suspected
+6657,bonfires
+6667,hesitate
+6671,thistles
+6680,wilfulness
+6681,threatening
+6685,hunted
+6687,reasons
+6689,choice
+6690,mouthfuls
+6692,spitefully
+6694,clasping
+6696,ribbons
+6698,recommended
+6700,favorably
+6710,passesbrushing
+6713,landblithe
+6720,interference
+6727,numberless
+6728,containing
+6732,farthingale
+6735,brandishing
+6740,spanish
+6745,hairs
+6752,facing
+6754,crashed
+6756,mouths
+6760,actions
+6761,reassured
+6774,releasing
+6775,chains
+6779,protects
+6787,hotly
+6789,thicket
+6794,frowning
+6795,suspiciously
+6799,arches
+6812,shorelighten
+6820,furious
+6821,wavesand
+6822,billow
+6823,thirty
+6826,hesitated
+6831,fainted
+6833,cleverly
+6842,collecting
+6848,thanking
+6849,sphinxes
+6851,helpless
+6858,hindrance
+6861,chaining
+6862,crouching
+6864,irritated
+6866,summoned
+6870,hated
+6871,whispering
+6887,counterfeiting
+6890,expecting
+6897,mothers
+6898,perfections
+6899,feast
+6902,furnish
+6904,threats
+6908,perfection
+6914,whereby
+6924,bethought
+6925,prediction
+6934,foresight
+6938,cooks
+6941,beefeaters
+6949,pheasants
+6958,witches
+6961,countryman
+6965,amorous
+6967,fearless
+6979,charcoal
+6983,inform
+6990,expedition
+6997,cheat
+6999,fencing
+7000,cooked
+7008,stretching
+7010,conducted
+7012,invented
+7015,whip
+7025,scoured
+7030,fashion
+7032,commonly
+7036,mightily
+7037,choosing
+7040,plaited
+7050,patches
+7055,services
+7061,godmother
+7063,wishest
+7066,scooped
+7084,headdress
+7086,whereof
+7088,intently
+7091,whereupon
+7093,hasted
+7094,thanked
+7098,charlotte
+7101,counted
+7103,finery
+7105,meanly
+7109,hurried
+7114,thereupon
+7118,matched
+7124,african
+7135,fears
+7143,fearlessly
+7144,threshold
+7148,bottles
+7156,promising
+7163,withhold
+7165,breathless
+7166,overwhelmed
+7167,knowest
+7170,feasting
+7179,lastly
+7184,unfinished
+7190,finishing
+7194,hinting
+7195,bearing
+7200,miserably
+7201,accomplished
+7203,offering
+7214,concerned
+7215,weariness
+7222,beheaded
+7226,wines
+7247,ghostly
+7250,earn
+7253,shortly
+7254,sexton
+7255,purposed
+7260,secretly
+7264,earnest
+7270,scolding
+7279,fellows
+7286,lathe
+7293,fiercely
+7296,screwed
+7300,ghastly
+7302,thresholds
+7306,ghosts
+7317,fetching
+7323,peacefully
+7333,cleft
+7336,whimpering
+7338,bearded
+7339,heaps
+7345,whir
+7351,straightway
+7362,cruickshanks
+7368,damethat
+7373,enormously
+7378,shipwreck
+7379,trusted
+7383,attributed
+7386,roughly
+7387,clothed
+7392,recovering
+7402,crouched
+7407,roaming
+7412,refreshed
+7422,unpunished
+7436,excited
+7439,innocently
+7456,gratified
+7458,roused
+7464,tearing
+7467,candlesticks
+7468,tremblingly
+7472,fated
+7480,mysterious
+7482,acted
+7490,reproachfully
+7494,apparently
+7495,reproached
+7498,breathed
+7509,congratulations
+7516,hired
+7522,whosoever
+7523,cleaned
+7524,pitchforksful
+7525,pitchfork
+7530,wring
+7535,chatted
+7543,broth
+7547,sucker
+7557,thronged
+7564,scowled
+7566,sheriff
+7568,bushels
+7572,entreated
+7573,flayed
+7576,bushel
+7579,beaten
+7596,whipped
+7598,fighting
+7599,outhouse
+7603,outbid
+7615,howsoever
+7625,whichsoever
+7635,afflict
+7639,booted
+7642,forepaws
+7645,thistle
+7653,lordship
+7654,thieves
+7662,countrymen
+7672,civilly
+7676,surround
+7685,shepherdess
+7693,replanted
+7694,catching
+7697,charge
+7700,attempted
+7702,furiously
+7703,whisker
+7715,frighten
+7717,overwhelm
+7733,greyhounds
+7742,abovewill
+7745,welcomed
+7746,sixty
+7748,histories
+7756,wearing
+7760,fricassee
+7765,eagles
+7777,inventing
+7783,chariots
+7792,wheat
+7797,willingness
+7799,earned
+7808,reported
+7816,peaches
+7826,prolonged
+7827,reluctantly
+7838,shivered
+7841,worthily
+7842,chatte
+7843,blanche
+7849,coolness
+7851,infantry
+7853,tarnished
+7860,ninth
+7866,tongues
+7875,reared
+7879,honored
+7881,recalled
+7888,conveyed
+7894,smear
+7900,hesitating
+7901,smeared
+7903,mourned
+7916,drearyou
+7917,hearbillows
+7919,sleepingwith
+7924,somewhere
+7929,oath
+7931,sharpness
+7936,tooth
+7937,peoples
+7943,hollows
+7954,unfoldround
+7955,wallet
+7960,writhed
+7962,hounds
+7964,eastward
+7966,curly
+7975,boxers
+7977,throwers
+7979,prophecy
+7982,impatiently
+7987,chanced
+7991,promptly
+7994,earliest
+8001,catchers
+8023,eats
+8030,charmingwho
+8034,croaked
+8035,repaying
+8037,shouts
+8039,carelessly
+8042,chasing
+8048,bathed
+8050,whittington
+8055,charitable
+8059,cook
+8070,brushing
+8072,freight
+8076,billows
+8078,hallows
+8079,holloway
+8083,cicely
+8090,civility
+8091,factor
+8093,offensive
+8102,purring
+8104,amounted
+8116,critics
+8117,historians
+8121,besought
+8125,felicity
+8126,distributed
+8132,sprightly
+8137,sheriffs
+8145,allowance
+8147,liberally
+8149,charities
+8156,astonish
+8170,affection
+8175,stray
+8177,thorny
+8178,bleating
+8182,protected
+8186,shepherd
+8187,bounding
+8189,sheepishly
+8191,cushions
+8193,induced
+8199,showers
+8205,pleasantness
+8207,accounts
+8210,honeysuckles
+8212,distracted
+8216,respected
+8220,helplessly
+8228,fittingly
+8235,spirited
+8255,incommoded
+8259,whatsoever
+8260,guilty
+8264,tying
+8268,famished
+8270,teased
+8278,affliction
+8287,crossly
+8292,whetted
+8293,whet
+8296,wherewithal
+8299,suck
+8303,fumbling
+8305,throats
+8309,wretches
+8316,wearer
+8317,reposing
+8318,frightfully
+8325,thereby
+8337,borrow
+8341,feasted
+8347,apothecary
+8359,stitch
+8360,stitched
+8363,partly
+8376,assuring
+8380,withstand
+8383,tabor
+8393,boards
+8399,footing
+8401,heaped
+8403,threepenny
+8404,dearth
+8419,maliciously
+8426,dough
+8431,catches
+8440,bleat
+8456,faced
+8460,fishing
+8462,fin
+8472,pounced
+8473,screeching
+8474,shreds
+8477,ingratitude
+8491,plight
+8503,astray
+8515,knewher
+8523,withal
+8531,purely
+8537,protection
+8538,hurts
+8540,whichever
+8542,pricking
+8547,allowable
+8557,teasing
+8562,accused
+8563,thwart
+8576,outwardly
+8580,ungratefully
+8583,powerlessness
+8601,outcry
+8606,searched
+8610,appearing
+8619,rallying
+8636,informing
+8646,heirs
+8658,sighs
+8660,winning
+8662,tons
+8664,completed
+8667,wares
+8675,mounts
+8679,marrow
+8682,throws
+8687,conversed
+8689,concerning
+8692,predicted
+8693,bounded
+8695,proceeding
+8699,throve
+8712,strengthen
+8715,stitches
+8718,mercilessly
+8720,outstretched
+8727,surveying
+8731,whey
+8732,sooth
+8735,whistling
+8739,hurting
+8740,workshop
+8742,fights
+8754,followers
+8755,casting
+8758,pinching
+8762,wounded
+8771,warrior
+8774,chapter
+8775,nottinghamshire
+8777,fourteen
+8783,burton
+8786,pritchard
+8794,withinyards
+8798,directed
+8799,abated
+8805,inches
+8813,mouthful
+8815,ingenious
+8817,hogsheads
+8819,hogshead
+8821,attempting
+8832,officials
+8838,breadth
+8850,translated
+8852,writings
+8859,natives
+8866,overthrew
+8886,monarchs
+8892,proposeth
+8904,twelfth
+8908,secretary
+8909,flourishing
+8911,philosophers
+8915,commanding
+8927,hillock
+8929,packthread
+8936,searchers
+8937,anchors
+8939,resolutely
+8942,hostile
+8943,shallower
+8947,protested
+8957,hatred
+8959,treason
+8961,proceedings
+8975,inflicted
+8976,posterity
+8988,northeast
+8990,amount
+8993,offices
+8998,pledged
+9011,rumbling
+9012,earthquake
+9013,outlying
+9017,eatest
+9018,previous
+9029,roughen
+9033,thirds
+9046,foresaw
+9049,tracts
+9058,handicrafts
+9065,wrought
+9074,motive
+9075,assign
+9090,thickness
+9091,perspective
+9095,reparation
+9102,thereabouts
+9106,worthless
+9114,philosopher
+9118,apply
+9120,recovery
+9125,relation
+9126,serviceable
+9127,obligation
+9128,acknowledgment
+9132,contributed
+9137,insupportable
+9138,renounced
+9142,rebounded
+9146,entreaty
+9147,undoubtedly
+9152,infinitely
+9161,intermixed
+9164,inestimable
+9168,choruses
+9171,harmonious
+9180,complaining
+9181,fatherly
+9185,whereas
+9196,introduced
+9198,insurmountable
+9200,traced
+9206,commands
+9213,sheets
+9219,wholesome
+9227,extremity
+9229,offending
+9231,indiscreetly
+9234,treasury
+9237,incredulity
+9239,whit
+9243,clews
+9248,footstool
+9249,healthful
+9250,incredible
+9257,reduce
+9266,backed
+9268,victorious
+9272,intercede
+9273,chastised
+9280,assigned
+9285,cornwall
+9296,headlong
+9318,thighs
+9329,blowshall
+9330,overthrow
+9333,thumbs
+9336,chapbook
+9339,scotland
+9350,mither
+9359,washerwife
+9378,brither
+9393,beated
+9398,owre
+9399,ither
+9403,whaur
+9408,wherewi
+9413,whaever
+9421,wha
+9422,ther
+9428,anither
+9430,thegither
+9431,heardna
+9437,aught
+9439,chambers
+9440,traditions
+9442,ance
+9446,ane
+9461,herwith
+9468,ireland
+9483,patched
+9484,whould
+9487,brithers
+9500,hatchet
+9501,uplifted
+9519,cornmeal
+9522,soothe
+9523,teaching
+9527,insulting
+9530,surly
+9533,thrashing
+9535,fashions
+9537,stairway
+9540,fireplace
+9555,cricket
+9556,corrected
+9558,reaching
+9573,warmer
+9577,chick
+9585,puffing
+9587,nightcap
+9591,whipping
+9603,artist
+9609,theater
+9612,arithmetic
+9617,shamelessly
+9623,eater
+9628,reciting
+9631,orchestra
+9638,actors
+9641,racket
+9644,swished
+9658,hey
+9659,heartbreaking
+9665,scurrying
+9668,earns
+9687,coaxing
+9694,offend
+9695,pleasing
+9699,overnight
+9704,bothersome
+9709,victory
+9712,spurred
+9714,measured
+9725,seasick
+9731,whirr
+9750,wholly
+9755,lovingly
+9756,whining
+9759,bothers
+9769,sheared
+9780,tic
+9785,thorough
+9787,peevishly
+9790,beans
+9792,courthouse
+9804,thereof
+9807,tormented
+9808,raced
+9809,greyhound
+9810,heartless
+9813,soothing
+9815,artery
+9817,tempted
+9823,weasel
+9824,steals
+9828,doghouse
+9837,whisperings
+9838,stealthy
+9839,accusing
+9842,seashore
+9844,inscription
+9845,liesthe
+9848,byher
+9851,clutched
+9852,relish
+9854,reappear
+9855,reaches
+9856,cleared
+9861,bother
+9863,wearily
+9864,preached
+9865,earning
+9873,bribery
+9876,benefactress
+9881,profession
+9883,usually
+9886,classroom
+9888,tormentors
+9891,teacher
+9896,playmates
+9897,arrested
+9909,rarely
+9913,text
+9919,schoolfellow
+9934,fisherman
+9940,bass
+9942,whitefish
+9945,mortified
+9946,resentfully
+9948,fooling
+9953,coughing
+9960,wits
+9963,pitchforks
+9965,torture
+9969,weakness
+9970,examinations
+9971,schoolmates
+9978,accepting
+9988,boundaries
+10001,wheedling
+10007,uproariously
+10014,trained
+10016,hopscotch
+10028,theaters
+10029,investigation
+10036,wrist
+10039,classmate
+10044,earache
+10047,fours
+10048,lengthened
+10056,smoothed
+10057,currycomb
+10060,hardships
+10069,tonightleaps
+10071,artistsand
+10072,horsesof
+10073,thecompany
+10083,introducing
+10089,hates
+10093,threatens
+10115,redoubled
+10119,bleated
+10124,asthma
+10127,greasy
+10135,whitecaps
+10137,foods
+10142,unceremoniously
+10143,ceases
+10146,affectionately
+10150,cheated
+10154,lamplight
+10155,secondhand
+10156,whittled
+10166,motherjumpedducklingsplashswimbiggercalledbeganlittle
+10168,lovelyhelptherewalkedbushesafraid
+10170,housewouldawayhardlived
+10172,summerawaycakewinterswansspringflewbreadleaves
+10173,pineleavesotherwoodsneedlesbetterfairygoldsleep
+10174,wokecriedglasslittleagainpretty
+10180,aproncurlylightsbunchaboutsmelledcouldmatchescooking
+10181,knewwindowfiremoneyevenpile
+10182,frozencandlesittinglighted
+10183,thoughtstovenearthinkstep
+10184,dishesroasttableclothreadyforkknifeturkey
+10185,christmascandlesmanyuntil
+10189,foundnextburneddeadfrozedeath
+10190,sixtakecakecoatbutterbaskethoodalwaysoff
+10191,wolfmillshallgoingfirstwood
+10192,shortflowerssoftstopped
+10193,tappedpullpickvoicestring
+10194,tappedthankdear
+10196,betterheareyesearshow
+10197,teethatecruelpoor
+10198,justhunterscreamkilledheardopen
+10200,oncehillsfieldjourney
+10201,rockscattlewalkedpiecesthree
+10202,thor
+10204,meatsharetalkingcrosseagleright
+10205,supperstuckenoughminuteclawsstonespoleagainstflew
+10207,pleasegiantflyingtriedfeatherssuit
+10208,citybeautiful
+10209,applesfeltgrowingyoung
+10212,showbringpicked
+10214,breathoverchangedwallsblazedburned
+10215,proudporchlyingjourneystrickswifealwaysaloneasleep
+10217,wherearoundcryinganswerfoundsomebody
+10219,cuttingsomething
+10220,groundthumbbeadsdwarfscrookedcrown
+10221,showedlaughedspearwonderful
+10222,threeshipstandingbrothernobodysteppedelse
+10223,spear
+10225,anywheremissesspearmark
+10228,blewblowing
+10230,bellows
+10236,foldsailafraidsorryeachringshining
+10238,frostgiantsturnedblowing
+10239,touchneckwithout
+10240,everythingplanned
+10243,peoplecitythrymstrange
+10250,dinnersalmonmeadwholethirstybarrels
+10251,kisssteppedwhirledliftedshonelap
+10252,smythe
+10254,revised
+10256,agohornsfleecekinggreecelovedplaying
+10257,hellegrassgardencatchclouds
+10261,skydizzyseasisterlanddragonlosenailedcolchis
+10264,acrossuntiedwadejasonbravepartyrainedcreekbridgeshoe
+10268,shoeargonauts
+10271,wingsblindnobodystrongironhardskindriveclawsscratchedbrassharpies
+10275,byeoveraparticebergs
+10277,fishespiecesdovepastbreaktogetherrowalmostrocks
+10278,somethingplowbullsstrongerchainsnosesmouthssmokeplantstoneflewstall
+10280,daughtermedeacarriagesnakesthroughpulled
+10283,earlytiedprincessseatsholduntiedopenedplace
+10284,pushedkickeduntil
+10285,handleslowlynoonwheatlie
+10287,kneesmarblethrewgrowingfight
+10295,splasher
+10296,croaks
+10298,splish
+10300,perchance
+10304,yearning
+10306,coolly
+10312,threes
+10313,suspicious
+10315,thirteen
+10316,thirteenth
+10322,trinity
+10325,whithersoever
+10333,thereat
+10335,acknowledges
+10336,blockhead
+10338,scoundrel
+10340,thalers
+10343,shiverest
+10355,thankest
+10368,deathbed
+10369,shouldst
+10376,subtlety
+10389,thaler
+10392,splashers
+10394,screech
+10401,slaughtered
+10409,cooled
+10415,footpath
+10418,whoso
+10421,wheresoever
+10423,appease
+10425,coverings
+10431,impious
+10433,whirring
+10434,unity
+10439,thieving
+10440,objections
+10441,rioted
+10448,crusts
+10455,suffocated
+10456,nursery
+10469,resound
+10471,gothel
+10501,hateful
+10502,grethel
+10507,coined
+10511,grated
+10514,active
+10519,fatherland
+10522,outlive
+10529,chattering
+10534,chicks
+10539,scorned
+10544,emptying
+10547,tripped
+10554,wills
+10560,shameless
+10563,counts
+10569,pitching
+10572,toppled
+10574,cheap
+10576,inspected
+10595,heroic
+10596,roams
+10600,wrongs
+10602,screw
+10605,brushed
+10606,crowding
+10623,expounded
+10625,prompted
+10626,booty
+10637,shuttle
+10642,pitchy
+10648,craftily
+10651,trough
+10654,hound
+10660,crowing
+10663,housewife
+10674,shrewd
+10676,refresh
+10677,wherewith
+10678,blowest
+10680,fourteenth
+10682,prophesied
+10684,arrives
+10696,wither
+10698,released
+10709,shimmering
+10722,amicably
+10723,henceforth
+10728,anointed
+10729,consecrated
+10736,shear
+10744,peaceably
+10757,lathered
+10759,horsewhip
+10763,industriously
+10769,furnishes
+10779,sheetful
+10781,relatives
+10789,thievish
+10791,amply
+10793,shorn
+10794,thumbling
+10797,exhibited
+10804,precisely
+10807,unpleasing
+10811,aroused
+10817,astounded
+10818,neatly
+10819,customary
+10828,coverlids
+10835,eaters
+10837,sprouted
+10838,infamous
+10844,healed
+10866,overreached
+10871,flushed
+10874,countless
+10876,pleaded
+10877,purposely
+10880,dished
+10882,forsooth
+10883,dishcloth
+10886,inspect
+10888,recommenced
+10901,sharpens
+10903,fitcher
+10911,wroth
+10915,marlinchen
+10923,hick
+10928,ceasing
+10930,feeding
+10941,treachery
+10946,plenteously
+10947,rattles
+10950,youths
+10957,thrushbeard
+10959,thereto
+10961,earls
+10966,lighting
+10967,earthenware
+10969,crockery
+10974,haughtiness
+10975,humbled
+10980,fathoms
+10986,counterpanes
+10988,owners
+10990,ore
+10994,cunningly
+11005,warriors
+11006,fired
+11008,fortifications
+11009,clover
+11019,befool
+11025,shortribs
+11031,transformation
+11034,cocked
+11041,withstood
+11043,whims
+11046,watchers
+11051,hiss
+11053,trailed
+11054,furrows
+11056,counters
+11058,earthen
+11061,forewarned
+11080,huntsmanship
+11081,release
+11082,covey
+11096,trampled
+11099,fought
+11102,butchers
+11106,corners
+11107,twitched
+11109,confectionery
+11113,invites
+11114,victor
+11132,prophesy
+11133,thirdly
+11134,fourthly
+11135,launched
+11143,inscribed
+11148,tormenting
+11153,troubling
+11157,inherited
+11178,learns
+11185,whoo
+11189,bewitch
+11190,ridiculously
+11191,profitably
+11192,scythes
+11197,windmills
+11200,blower
+11206,ton
+11212,throwest
+11218,painfully
+11237,basted
+11240,sharpened
+11255,cookery
+11256,abruptly
+11257,tomfool
+11262,hints
+11263,wasted
+11274,clamorously
+11275,alack
+11281,purgatory
+11286,click
+11290,barrow
+11296,whirred
+11298,foundation
+11301,straighten
+11305,berth
+11312,existed
+11316,cackled
+11319,cackling
+11321,meditations
+11327,warped
+11328,followest
+11329,shinest
+11333,therewith
+11337,clucking
+11339,thenceforth
+11341,scorched
+11346,clutch
+11352,freshly
+11353,furrow
+11356,ploughed
+11358,harrow
+11359,harrowed
+11360,harrows
+11362,powerfully
+11374,honourably
+11376,lowered
+11377,repeatedly
+11379,sealed
+11380,purchases
+11384,raspberry
+11385,thoughtlessly
+11387,secondly
+11410,background
+11412,hilloa
+11414,catchest
+11418,plotted
+11420,suspecting
+11422,incessantly
+11427,grethe
+11430,sweat
+11434,smothered
+11435,cork
+11437,releases
+11438,feat
+11444,tested
+11445,hire
+11451,unwashed
+11458,greencoat
+11462,refraining
+11471,lighthearted
+11477,wrens
+11482,commander
+11484,watchword
+11489,colouring
+11498,redbreast
+11499,orphan
+11500,filagree
+11508,whetstone
+11512,barefoot
+11515,thumped
+11516,forecast
+11517,mouldy
+11522,thoughtless
+11528,clocks
+11529,switch
+11533,touchest
+11537,boasts
+11552,aloft
+11553,journeying
+11555,slaughter
+11557,expectation
+11562,shroud
+11563,worshipped
+11568,fleeced
+11569,halfpence
+11574,locksmith
+11577,sharpshooter
+11582,truthfulness
+11585,threshing
+11590,christopher
+11598,preaching
+11608,composedly
+11619,affectionate
+11623,tobacco
+11626,brighten
+11627,counteract
+11629,wreaths
+11633,practising
+11636,twitches
+11662,headsman
+11664,bowling
+11666,wrestled
+11667,theft
+11669,bearest
+11677,thenceforward
+11682,sorceries
+11686,increase
+11689,reassumed
+11691,beatings
+11698,flourished
+11700,cornfield
+11703,plentifully
+11706,wineglass
+11712,feats
+11716,neverthless
+11721,neglected
+11722,branched
+11729,instruction
+11731,hatching
+11735,seaworthy
+11736,shortest
+11741,fetches
+11746,treating
+11747,downright
+11752,hollenthe
+11761,clown
+11768,splits
+11769,companionship
+11772,meditated
+11774,frosty
+11784,mortally
+11785,appearest
+11787,boundless
+11791,polluted
+11800,hurricane
+11803,townsfolk
+11819,whetting
+11820,whets
+11826,uprightly
+11835,humouredly
+11844,healing
+11847,becomest
+11848,infirmity
+11849,torments
+11858,indemnity
+11862,extinguish
+11871,tenth
+11880,wheatfield
+11884,shiftiness
+11892,thresh
+11894,mountaineers
+11897,specially
+11901,heareth
+11909,ploughing
+11911,ratisbon
+11913,threshed
+11916,heating
+11918,breasts
+11919,whitsuntide
+11920,ploughshare
+11923,trustfully
+11926,prying
+11931,thanklessness
+11934,honors
+11936,hoary
+11948,intermingled
+11955,comply
+11956,comforting
+11961,nourishes
+11962,hive
+11963,pitcherful
+11967,belabour
+11971,seame
+11976,unexpectedly
+11977,whistle
+11979,weapons
+11981,crunching
+11986,hypocrite
+11988,belaboured
+11989,fists
+12002,threatenest
+12005,finches
+12007,hooted
+12018,clack
+12023,chaffinches
+12026,assemblage
+12032,cheating
+12033,steadfastly
+12037,herring
+12042,horned
+12044,townsmen
+12049,tuwhit
+12050,tuwhoo
+12064,subjection
+12072,strengthening
+12083,appeal
+12090,recollected
+12092,unreasonably
+12093,burthen
+12097,bearable
+12107,severity
+12108,threads
+12110,bleach
+12112,neighbouring
+12113,strayed
+12114,offence
+12118,decorously
+12119,burgher
+12120,favoured
+12125,blacksmiths
+12127,coffers
+12128,nightly
+12134,steadily
+12138,laboriously
+12144,whirling
+12145,charmingly
+12149,monastery
+12150,beards
+12156,boasting
+12158,clownish
+12160,boars
+12166,nourishing
+12171,invisibly
+12179,neath
+12183,relating
+12184,buckwheat
+12195,fasting
+12198,firstly
+12199,weaving
+12200,forlorn
+12201,curtsey
+12222,asthmatic
+12225,countess
+12229,burries
+12232,burying
+12246,cleanse
+12253,scornfully
+12257,handfuls
+12270,inspecting
+12282,blear
+12294,immeasurable
+12315,sweetmeat
+12326,frolicked
+12327,tottery
+12346,curry
+12357,effecting
+12364,establishing
+12371,entreating
+12373,consists
+12374,calamity
+12376,chattees
+12377,chattee
+12379,liberated
+12383,overthrown
+12385,imploring
+12398,combined
+12407,freely
+12412,subjected
+12415,outwit
+12423,outwitting
+12427,witted
+12436,founds
+12439,repeating
+12443,feasts
+12452,oaths
+12453,cooped
+12456,whimper
+12464,noplease
+12465,whirl
+12468,bequeathed
+12474,coasts
+12476,chombu
+12487,fluency
+12505,recollections
+12506,outshone
+12515,ushered
+12517,issued
+12518,bandicoots
+12523,sincerely
+12524,sympathises
+12526,deaths
+12529,acting
+12539,respective
+12540,lavishly
+12549,unwittingly
+12553,worshipper
+12556,worshipping
+12563,forthcoming
+12579,propitiated
+12582,honoured
+12591,dishonest
+12604,curiously
+12605,expeditions
+12609,yearn
+12612,community
+12617,eventually
+12618,reappeared
+12630,himselfwhilst
+12631,overmuch
+12655,whereabouts
+12656,leadings
+12661,worship
+12665,absurdity
+12666,clenched
+12672,hooded
+12677,youthful
+12678,cursing
+12685,outlet
+12689,threading
+12691,incredibly
+12692,parched
+12695,potsherd
+12696,treacherous
+12699,foolishness
+12703,confectioners
+12712,thrones
+12714,righteousness
+12720,charioteer
+12726,tribe
+12727,righteous
+12728,chorister
+12730,overthrows
+12735,notorious
+12750,purchaser
+12763,pitchers
+12765,worthier
+12774,headless
+12776,fashioned
+12779,charger
+12784,crickets
+12796,alight
+12799,wiles
+12804,moulded
+12815,trafficking
+12816,clothe
+12817,chanks
+12818,panther
+12828,preyed
+12836,cowherd
+12843,chooses
+12845,pitched
+12849,offences
+12857,assembly
+12864,fisherwoman
+12866,behaviour
+12869,satisfactory
+12870,trickery
+12872,professing
+12875,cemetery
+12885,inhospitable
+12886,foolishly
+12923,offerings
+12924,admonished
+12925,thereabout
+12926,righteously
+12931,bondsthat
+12932,sainthood
+12936,archery
+12940,obeying
+12944,investigated
+12953,footmarks
+12959,inviting
+12963,whim
+12970,conversing
+12972,grounds
+12973,assented
+12976,thankfulness
+12994,ghoul
+13000,ingratiate
+13001,cloths
+13002,plead
+13004,inmates
+13007,scorching
+13012,ingrates
+13013,previously
+13015,sympathised
+13030,basse
+13039,type
+13041,washhouse
+13044,fenced
+13050,convulsively
+13054,shooter
+13062,cornered
+13063,overflows
+13066,cowering
+13081,bathroom
+13083,sorcery
+13085,overhead
+13089,trelliswork
+13112,archbishop
+13119,witnessed
+13122,sackcloth
+13126,seasons
+13131,crackle
+13132,coverlid
+13133,sheltering
+13134,century
+13135,towered
+13137,echoing
+13142,watchfires
+13143,hospitable
+13147,thrilling
+13152,fervently
+13155,feathery
+13161,festivity
+13162,oration
+13164,redemption
+13175,sympathize
+13179,shrillness
+13180,whispers
+13187,onions
+13194,twitter
+13198,clucked
+13202,whips
+13206,hoarfrost
+13212,starch
+13213,clank
+13217,crackling
+13218,stretches
+13219,thaw
+13229,weathercocks
+13236,tolerably
+13245,cornfields
+13251,preacher
+13267,eyelashes
+13275,sightly
+13278,shedding
+13283,tether
+13286,buttonhole
+13287,scotch
+13288,treasured
+13290,secluded
+13291,scottish
+13292,flowerpot
+13298,housed
+13306,mechanical
+13314,laboratory
+13321,imperfections
+13322,imperfection
+13325,thirsting
+13338,associated
+13340,initiated
+13357,steamed
+13366,indicated
+13367,loftiest
+13368,cautiously
+13369,indefinitely
+13370,prominently
+13374,overshadow
+13379,literally
+13384,hobbyhorses
+13386,phrases
+13394,brightest
+13405,highroad
+13410,sturdily
+13424,hatch
+13425,shriveled
+13426,schoolmistress
+13428,factory
+13432,authority
+13433,overpowered
+13434,respecting
+13435,whomsoever
+13445,flowerpots
+13446,chives
+13453,thickets
+13458,candlestick
+13459,intellect
+13460,flourishes
+13462,antlers
+13468,creaks
+13485,cribbley
+13486,crabbley
+13487,scrambling
+13519,radiantly
+13526,indifference
+13530,heathen
+13534,hopeful
+13540,tombstone
+13559,clashed
+13571,reasoned
+13575,incomprehensible
+13583,yearthere
+13584,exhibition
+13590,shillings
+13594,instructive
+13597,highborn
+13600,affectation
+13610,distractedly
+13617,chrysanthemums
+13622,criticisms
+13623,theatricals
+13625,earrings
+13629,watcher
+13632,carousing
+13638,overflowed
+13641,instructed
+13643,aspect
+13649,furnishings
+13653,ancestors
+13661,brotherhood
+13664,rears
+13666,thespis
+13668,clergy
+13672,announcing
+13675,thrilled
+13677,wafted
+13678,headforemost
+13686,exceptionally
+13687,shuttles
+13690,cheats
+13693,explaining
+13694,selected
+13697,buttonholes
+13701,tethering
+13707,bushelful
+13711,thrashed
+13717,mounds
+13718,thingsmerry
+13719,romping
+13720,boystear
+13724,sweeterthan
+13725,traycame
+13732,tellwhat
+13734,aboutand
+13735,thisand
+13738,foundamong
+13750,bitwhat
+13751,foams
+13755,treeand
+13756,thenon
+13757,placethe
+13759,upher
+13760,therethe
+13768,showshow
+13778,childgrowing
+13779,thenthat
+13782,howthey
+13790,tryingwhich
+13793,shiverwhen
+13794,forgetwhat
+13798,whistlesthrough
+13801,tellwhere
+13803,hearthrug
+13809,rumpled
+13814,wistfully
+13816,firelight
+13820,childie
+13825,handicraft
+13827,lather
+13829,tramped
+13830,unceasing
+13833,bellowing
+13836,whack
+13846,stealthily
+13851,ambitious
+13877,leasing
+13878,leased
+13879,andscalded
+13883,moulted
+13884,sheds
+13885,thatching
+13893,henceforward
+13898,grease
+13925,anonymous
+13927,moneywrapped
+13929,shillingyour
+13939,harepeeping
+13942,highto
+13948,builds
+13959,cryingtill
+13963,nicerfor
+13965,housewhen
+13966,easierfor
+13967,wiserthan
+13969,earnestand
+13972,thankfulyou
+13973,creationwill
+13975,cary
+13980,hemlock
+13984,additions
+13988,counterpane
+13993,stillthat
+13995,curlright
+13998,headin
+14004,emphatic
+14005,wadsworth
+14006,longfellow
+14007,nearwould
+14015,playmate
+14017,whene
+14019,tinthat
+14021,threeon
+14025,antwho
+14026,housein
+14028,bookwith
+14031,catwho
+14033,ccrafty
+14034,duckwith
+14037,fishwho
+14040,goatwho
+14043,hatwhich
+14052,kitewhich
+14054,lightwhich
+14057,millwhich
+14058,roundwith
+14061,netwhich
+14069,quailwith
+14070,cornin
+14074,flowersin
+14075,rnaughty
+14080,ttorty
+14085,villawhich
+14088,whalewith
+14091,wmonstrous
+14094,fashionof
+14098,abodenear
+14105,heatand
+14106,townwith
+14108,soundas
+14111,leetlebrowny
+14113,beetledined
+14119,thomas
+14127,clustering
+14128,awaylittle
+14131,buttercups
+14140,healthby
+14142,hardshipsand
+14143,strengthand
+14144,howitt
+14147,bowerinstead
+14149,perfumewithin
+14161,bumble
+14163,froi
+14164,bycarrying
+14165,feetdown
+14168,sitwhere
+14171,highsee
+14177,boatround
+14182,stitching
+14187,whiting
+14189,shingle
+14191,scaly
+14194,foreverwith
+14195,boating
+14197,childrenshall
+14201,heapof
+14203,highin
+14205,thinned
+14207,enoughto
+14209,airnowherewas
+14215,shoneon
+14216,thronein
+14220,treewho
+14226,treefarther
+14228,handlead
+14230,seethe
+14233,disgracethough
+14245,houghton
+14247,highand
+14261,gathers
+14262,flowerssoon
+14264,wearycalm
+14269,evilfrom
+14270,watchesmay
+14271,spreadtheir
+14281,housetop
+14286,overthe
+14290,plowman
+14301,chatting
+14306,hose
+14310,clumsily
+14312,thoughtfully
+14334,loitered
+14339,chat
+14343,transacted
+14351,fi
+14357,chopper
+14359,bedclothes
+14364,orchards
+14369,aching
+14370,godmothers
+14372,clashing
+14373,trailing
+14376,scowling
+14379,heartsease
+14381,deary
+14384,writh
+14394,intimutly
+14395,crick
+14396,whee
+14397,whimm
+14400,whing
+14401,authentic
+14407,whann
+14416,whitcomb
+14418,copyright
+14419,publishers
+14436,catechis
+14443,warewho
+14452,ridewith
+14453,whycan
+14455,itwith
+14457,whackagainst
+14464,agesof
+14468,ascribed
+14470,carney
+14471,wouldthat
+14472,pridethe
+14474,besideshould
+14476,catkins
+14484,abound
+14485,shootpromises
+14490,titled
+14491,friendwith
+14496,thanksgiving
+14497,sleighthrough
+14503,groundwill
+14505,cellwithin
+14513,turnthe
+14515,laughwhen
+14517,windsthat
+14521,blithe
+14523,croft
+14524,outrightwhen
+14530,lowthere
+14531,lowthe
+14533,stonesthat
+14534,seenthe
+14544,firelit
+14545,scout
+14548,housenot
+14560,roofthe
+14568,orphant
+14577,watchout
+14578,onc
+14589,wheres
+14590,thist
+14592,roundabout
+14605,churish
+14607,chatterbox
+14612,tonguewith
+14615,earthby
+14617,flowersby
+14619,wreathes
+14623,hesperian
+14625,iceland
+14626,founts
+14627,flashing
+14631,resounds
+14632,dorothea
+14634,lackey
+14636,clouting
+14640,acorns
+14641,heights
+14650,crowdthat
+14653,transitory
+14655,fount
+14664,creedshall
+14667,familyshall
+14673,reformation
+14675,thenby
+14677,whirls
+14680,brighty
+14683,chaliced
+14685,shakespeare
+14692,buttercup
+14696,rillhow
+14697,hillof
+14699,feetthe
+14700,rillthe
+14703,wintry
+14704,hourof
+14707,foundwithin
+14709,bounteous
+14713,frolic
+14715,downshutters
+14716,whisking
+14723,matronly
+14731,rearing
+14732,thatch
+14733,lanewith
+14734,schoolboy
+14735,panted
+14736,twirled
+14737,stoodwith
+14741,southern
+14743,breaston
+14744,showersits
+14745,playedbeneath
+14746,prayedaround
+14747,childthat
+14748,curlthat
+14749,clustered
+14752,conway
+14755,stillthe
+14756,wordsworth
+14758,wingsbear
+14765,belowdemosthenes
+14774,highwho
+14780,rehearse
+14784,forthenough
+14785,enoughfor
+14787,flowerto
+14791,manmight
+14795,hopewhene
+14796,careth
+14797,flowerswill
+14802,cheaper
+14807,comforts
+14808,southey
+14809,heighti
+14810,dressedwith
+14811,breastof
+14815,fearthe
+14816,spearthat
+14820,therethat
+14823,tchick
+14833,hereabout
+14834,plowthe
+14835,plowshare
+14837,upwith
+14839,roundwas
+14840,childing
+14841,thenand
+14843,herelay
+14847,dukewho
+14848,chameleon
+14857,discoursed
+14864,pother
+14865,candlelight
+14867,sightproduced
+14869,eyesight
+14871,phebe
+14873,worldthat
+14876,tearwas
+14879,fearoffending
+14883,grandmotherthis
+14884,theethis
+14885,wheaten
+14886,yestermorn
+14888,painthe
+14889,waterfrom
+14890,woodthe
+14891,peoplefrom
+14897,boughwithin
+14903,grandmotherthe
+14909,yetthe
+14911,whate
+14913,woodbeneath
+14914,sear
+14915,boughsshe
+14918,brownieswithin
+14926,flowernor
+14927,ewewithin
+14930,childis
+14935,grandmotherwent
+14937,blessingsshe
+14939,spearmen
+14944,lovedthe
+14946,unpleased
+14948,chieftain
+14957,groundwith
+14967,beneathlay
+14968,lowthis
+14973,hearpoor
+14974,spencer
+14975,snowbird
+14980,povertywha
+14989,coof
+15006,hatched
+15016,noticeable
+15022,inclosed
+15024,township
+15030,inexorable
+15034,narrated
+15040,nutcracker
+15046,gnashed
+15050,shouldering
+15053,ardently
+15062,chambermaid
+15071,breastpin
+15077,seasickness
+15078,crushes
+15079,thumbelina
+15082,thirstily
+15086,cockchafer
+15089,smother
+15091,blackthorn
+15099,goloshes
+15102,twopence
+15103,councilors
+15109,stouter
+15114,shoveling
+15121,swearing
+15124,routing
+15126,thigh
+15128,breadths
+15129,goldtooth
+15149,unearthly
+15152,prythee
+15154,waywhatever
+15156,cramped
+15161,uneasily
+15164,priestly
+15167,coverlets
+15168,insolently
+15173,helplessness
+15175,noted
+15177,vicious
+15186,whimsical
+15187,wasting
+15196,cherish
+15199,platform
+15202,cherrystone
+15206,resisted
+15207,languished
+15208,incurred
+15211,plea
+15214,birdcatchers
+15220,claiming
+15223,victims
+15224,whomay
+15236,tiewith
+15242,tommy
+15244,woful
+15250,activity
+15253,knighted
+15257,thunstone
+15260,tournament
+15264,county
+15267,foundations
+15274,throttled
+15275,brutish
+15280,prithee
+15281,flitches
+15290,witness
+15292,wallowed
+15293,scoff
+15298,courted
+15314,plennypennytinchery
+15328,whew
+15346,earl
+15350,sthronshuch
+15361,cryin
+15362,footman
+15368,townland
+15369,hips
+15371,twelvemonth
+15374,poorly
+15380,sheltery
+15384,fourpence
+15387,bastes
+15392,bosthoon
+15394,stomached
+15396,plowmen
+15405,cowhouses
+15411,throwin
+15413,hip
+15419,neary
+15423,downhearted
+15425,whisky

IT19001708/STG/script/.ipynb_checkpoints/Untitled-checkpoint.ipynb

+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "51481245-33cd-4f7c-ae5e-2376e8006545",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Collecting transformers\n",
+      "  Using cached transformers-4.26.1-py3-none-any.whl (6.3 MB)\n",
+      "Collecting tokenizers!=0.11.3,<0.14,>=0.11.1\n",
+      "  Using cached tokenizers-0.13.2-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (7.6 MB)\n",
+      "Requirement already satisfied: tqdm>=4.27 in /opt/conda/lib/python3.7/site-packages (from transformers) (4.64.1)\n",
+      "Requirement already satisfied: pyyaml>=5.1 in /opt/conda/lib/python3.7/site-packages (from transformers) (6.0)\n",
+      "Requirement already satisfied: requests in /opt/conda/lib/python3.7/site-packages (from transformers) (2.28.2)\n",
+      "Requirement already satisfied: packaging>=20.0 in /opt/conda/lib/python3.7/site-packages (from transformers) (23.0)\n",
+      "Requirement already satisfied: regex!=2019.12.17 in /opt/conda/lib/python3.7/site-packages (from transformers) (2022.10.31)\n",
+      "Requirement already satisfied: numpy>=1.17 in /opt/conda/lib/python3.7/site-packages (from transformers) (1.21.6)\n",
+      "Requirement already satisfied: filelock in /opt/conda/lib/python3.7/site-packages (from transformers) (3.9.0)\n",
+      "Collecting huggingface-hub<1.0,>=0.11.0\n",
+      "  Using cached huggingface_hub-0.12.1-py3-none-any.whl (190 kB)\n",
+      "Requirement already satisfied: importlib-metadata in /opt/conda/lib/python3.7/site-packages (from transformers) (6.0.0)\n",
+      "Requirement already satisfied: typing-extensions>=3.7.4.3 in /opt/conda/lib/python3.7/site-packages (from huggingface-hub<1.0,>=0.11.0->transformers) (4.5.0)\n",
+      "Requirement already satisfied: zipp>=0.5 in /opt/conda/lib/python3.7/site-packages (from importlib-metadata->transformers) (3.14.0)\n",
+      "Requirement already satisfied: urllib3<1.27,>=1.21.1 in /opt/conda/lib/python3.7/site-packages (from requests->transformers) (1.26.14)\n",
+      "Requirement already satisfied: certifi>=2017.4.17 in /opt/conda/lib/python3.7/site-packages (from requests->transformers) (2022.12.7)\n",
+      "Requirement already satisfied: charset-normalizer<4,>=2 in /opt/conda/lib/python3.7/site-packages (from requests->transformers) (2.1.1)\n",
+      "Requirement already satisfied: idna<4,>=2.5 in /opt/conda/lib/python3.7/site-packages (from requests->transformers) (3.4)\n",
+      "Installing collected packages: tokenizers, huggingface-hub, transformers\n",
+      "Successfully installed huggingface-hub-0.12.1 tokenizers-0.13.2 transformers-4.26.1\n"
+     ]
+    }
+   ],
+   "source": [
+    "!pip install transformers\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "aeea3911-8296-40a7-9770-9834031fb3d5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "from transformers import AutoTokenizer, TFAutoModel\n",
+    "import tensorflow as tf"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "70bad982-8669-4559-a579-e8b7ba905517",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased')\n",
+    "model = TFAutoModel.from_pretrained('bert-base-uncased')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "ab859a35-451e-4168-8277-e4d4d6e30e78",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "encoded_inputs = [tokenizer(word, return_tensors='tf') for word in words]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "a3ad97ea-6074-4a09-b66e-ae8b79d816ef",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = pd.read_csv('../dataset/df_filtered.csv')\n",
+    "words = df['word'].tolist()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "de2ce194-c5b6-48c6-bab9-6687abd51077",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'input_ids': <tf.Tensor: shape=(1, 3), dtype=int32, numpy=array([[ 101, 2612,  102]], dtype=int32)>, 'token_type_ids': <tf.Tensor: shape=(1, 3), dtype=int32, numpy=array([[0, 0, 0]], dtype=int32)>, 'attention_mask': <tf.Tensor: shape=(1, 3), dtype=int32, numpy=array([[1, 1, 1]], dtype=int32)>}"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "encoded_inputs[0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d2d4363e-eec8-4559-8ea1-850ce2319b2c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "embeddings = []\n",
+    "with tf.device('/GPU:0'):\n",
+    "    for encoded_input in encoded_inputs:\n",
+    "        outputs = model(encoded_input)\n",
+    "        embedding = outputs[0][0].numpy()\n",
+    "        embeddings.append(embedding)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "dff2f4e7-a31b-439c-93b4-a9b75819d56a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_emb = pd.DataFrame(embeddings)\n",
+    "df_emb"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "55cb94bc-ce3c-4b4e-a58a-eb7ab728b34e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_emb.to_csv('../dataset/word_embeddings.csv')"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "TensorFlow 2 (Local)",
+   "language": "python",
+   "name": "local-tf2"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

IT19001708/STG/script/.ipynb_checkpoints/word_embeddings_for_train_dataset-checkpoint.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "metadata": {
     "colab": {
      "base_uri": "https://localhost:8080/"
@@ -10,15 +10,29 @@
     "id": "wrohN8tt5Ty8",
     "outputId": "a7b1b675-0f13-4e6d-c554-a4e6fb6f23e1"
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Installing collected packages: tokenizers, sentencepiece, regex, huggingface-hub, transformers, nltk, sentence-transformers\n",
+      "Successfully installed huggingface-hub-0.12.1 nltk-3.8.1 regex-2022.10.31 sentence-transformers-2.2.2 sentencepiece-0.1.97 tokenizers-0.13.2 transformers-4.26.1\n",
+      "Collecting langdetect\n",
+      "  Using cached langdetect-1.0.9-py3-none-any.whl\n",
+      "Requirement already satisfied: six in /opt/conda/lib/python3.7/site-packages (from langdetect) (1.16.0)\n",
+      "Installing collected packages: langdetect\n",
+      "Successfully installed langdetect-1.0.9\n"
+     ]
+    }
+   ],
    "source": [
     "!pip install sentence-transformers \n",
-    "!pip install langdetect"
+    "#!pip install langdetect"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": null,
    "metadata": {
     "id": "XK-Fhom65eWi"
    },
@@ -28,12 +42,12 @@
     "from sklearn.metrics.pairwise import cosine_similarity\n",
     "import numpy as np\n",
     "import pandas as pd\n",
-    "from langdetect import detect"
+    "#from langdetect import detect"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": null,
    "metadata": {
     "id": "hqMzBp6m5iV6"
    },
@@ -44,7 +58,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": null,
    "metadata": {
     "id": "P4Prq9HG7d4j"
    },
@@ -56,7 +70,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": null,
    "metadata": {
     "id": "lxn2CudUEAGz"
    },
@@ -72,7 +86,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": null,
    "metadata": {
     "id": "PH45i7Ym5wCF"
    },
@@ -83,6 +97,7 @@
     "\n",
     "  for index, value in df['word'].iteritems():\n",
     "    embedding_list.append(model.encode(value))\n",
+    "    print(value)\n",
     "  \n",
     "  print('Done')\n",
     "  \n",
@@ -98,7 +113,7 @@
    },
    "outputs": [],
    "source": [
-    "df_filtered = df_word[df_word['word'].apply(detect_language)]"
+    "#df_filtered = df_word[df_word['word'].apply(detect_language)]"
    ]
   },
   {
@@ -136,7 +151,11 @@
    "metadata": {},
    "outputs": [],
    "source": [
+<<<<<<< HEAD
     "df_embedding.to_csv(\"../dataset/word_embeddings.csv\")"
+=======
+    "df_embbeding.to_csv('../dataset/word_embeddings.csv')"
+>>>>>>> e5255808ccac5081b6253049b2c08282f39bc16c
    ]
   },
   {
@@ -152,9 +171,9 @@
    "provenance": []
   },
   "kernelspec": {
-   "display_name": "default:Python",
+   "display_name": "Pytorch (Local)",
    "language": "python",
-   "name": "conda-env-default-py"
+   "name": "local-pytorch"
   },
   "language_info": {
    "codemirror_mode": {
@@ -166,7 +185,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.13"
+   "version": "3.7.12"
   }
  },
  "nbformat": 4,

IT19001708/STG/script/Untitled.ipynb

+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "51481245-33cd-4f7c-ae5e-2376e8006545",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install transformers\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "aeea3911-8296-40a7-9770-9834031fb3d5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "from transformers import AutoTokenizer, TFAutoModel\n",
+    "import tensorflow as tf"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "70bad982-8669-4559-a579-e8b7ba905517",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased')\n",
+    "model = TFAutoModel.from_pretrained('bert-base-uncased')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "a3ad97ea-6074-4a09-b66e-ae8b79d816ef",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = pd.read_csv('../dataset/df_filtered.csv')\n",
+    "words = df['word'].tolist()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "ab859a35-451e-4168-8277-e4d4d6e30e78",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "encoded_inputs = [tokenizer(word, return_tensors='tf') for word in words]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "de2ce194-c5b6-48c6-bab9-6687abd51077",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "encoded_inputs[0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "d2d4363e-eec8-4559-8ea1-850ce2319b2c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "embeddings = []\n",
+    "with tf.device('/GPU:0'):\n",
+    "    for encoded_input in encoded_inputs:\n",
+    "        outputs = model(encoded_input)\n",
+    "        embedding = outputs[0][0].numpy()\n",
+    "        embeddings.append(embedding)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "dff2f4e7-a31b-439c-93b4-a9b75819d56a",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/opt/conda/lib/python3.7/site-packages/pandas/core/internals/construction.py:540: VisibleDeprecationWarning: Creating an ndarray from ragged nested sequences (which is a list-or-tuple of lists-or-tuples-or ndarrays with different lengths or shapes) is deprecated. If you meant to do this, you must specify 'dtype=object' when creating the ndarray.\n",
+      "  values = np.array([convert(v) for v in values])\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>0</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>[[-0.2112137, -0.057769418, -0.01924374, -0.00...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>[[-0.32676977, 0.032084987, -0.52493036, -0.44...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>[[-0.19533601, 0.24660303, -0.002797313, -0.06...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>[[-0.4519474, 0.18390995, -0.53327066, -0.2371...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>[[-0.052097924, 0.30908817, -0.039699733, 0.01...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3305</th>\n",
+       "      <td>[[-0.1235517, 0.43329853, -0.13414639, -0.1531...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3306</th>\n",
+       "      <td>[[-0.5598528, -0.07930106, -0.13959903, -0.069...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3307</th>\n",
+       "      <td>[[-0.39649808, 0.12856255, 0.21035239, -0.1410...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3308</th>\n",
+       "      <td>[[-0.5090915, 0.18303792, -0.29818898, 0.09537...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3309</th>\n",
+       "      <td>[[-0.25211066, 0.5173553, -0.0053291023, -0.33...</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>3310 rows × 1 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                                                      0\n",
+       "0     [[-0.2112137, -0.057769418, -0.01924374, -0.00...\n",
+       "1     [[-0.32676977, 0.032084987, -0.52493036, -0.44...\n",
+       "2     [[-0.19533601, 0.24660303, -0.002797313, -0.06...\n",
+       "3     [[-0.4519474, 0.18390995, -0.53327066, -0.2371...\n",
+       "4     [[-0.052097924, 0.30908817, -0.039699733, 0.01...\n",
+       "...                                                 ...\n",
+       "3305  [[-0.1235517, 0.43329853, -0.13414639, -0.1531...\n",
+       "3306  [[-0.5598528, -0.07930106, -0.13959903, -0.069...\n",
+       "3307  [[-0.39649808, 0.12856255, 0.21035239, -0.1410...\n",
+       "3308  [[-0.5090915, 0.18303792, -0.29818898, 0.09537...\n",
+       "3309  [[-0.25211066, 0.5173553, -0.0053291023, -0.33...\n",
+       "\n",
+       "[3310 rows x 1 columns]"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df_emb = pd.DataFrame(embeddings)\n",
+    "df_emb"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "55cb94bc-ce3c-4b4e-a58a-eb7ab728b34e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_emb.to_csv('../dataset/word_embeddings.csv')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "bacca570-1e23-4ca7-b6ce-d6e29be434bd",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "TensorFlow 2 (Local)",
+   "language": "python",
+   "name": "local-tf2"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

IT19001708/STG/script/word_embeddings_for_train_dataset.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 16,
    "metadata": {
     "colab": {
      "base_uri": "https://localhost:8080/"
@@ -10,7 +10,19 @@
     "id": "wrohN8tt5Ty8",
     "outputId": "a7b1b675-0f13-4e6d-c554-a4e6fb6f23e1"
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Collecting langdetect\n",
+      "  Using cached langdetect-1.0.9-py3-none-any.whl\n",
+      "Requirement already satisfied: six in /opt/conda/lib/python3.7/site-packages (from langdetect) (1.16.0)\n",
+      "Installing collected packages: langdetect\n",
+      "Successfully installed langdetect-1.0.9\n"
+     ]
+    }
+   ],
    "source": [
     "!pip install sentence-transformers \n",
     "!pip install langdetect"
@@ -18,7 +30,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 17,
    "metadata": {
     "id": "XK-Fhom65eWi"
    },
@@ -33,7 +45,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 3,
    "metadata": {
     "id": "hqMzBp6m5iV6"
    },
@@ -44,11 +56,107 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 4,
    "metadata": {
     "id": "P4Prq9HG7d4j"
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>word</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>peacock</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>kind</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>gentle</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>bird</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>lived</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>15423</th>\n",
+       "      <td>downhearted</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>15424</th>\n",
+       "      <td>slits</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>15425</th>\n",
+       "      <td>whisky</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>15426</th>\n",
+       "      <td>pocketful</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>15427</th>\n",
+       "      <td>sackfuls</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>15428 rows × 1 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "              word\n",
+       "0          peacock\n",
+       "1             kind\n",
+       "2           gentle\n",
+       "3             bird\n",
+       "4            lived\n",
+       "...            ...\n",
+       "15423  downhearted\n",
+       "15424        slits\n",
+       "15425       whisky\n",
+       "15426    pocketful\n",
+       "15427     sackfuls\n",
+       "\n",
+       "[15428 rows x 1 columns]"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "df_word = pd.read_csv('../dataset/word_no_label.csv')\n",
     "df_word"
@@ -56,7 +164,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 18,
    "metadata": {
     "id": "lxn2CudUEAGz"
    },
@@ -72,7 +180,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 6,
    "metadata": {
     "id": "PH45i7Ym5wCF"
    },
@@ -80,9 +188,13 @@
    "source": [
     "def generate_embeddings(df):\n",
     "  embedding_list = []\n",
+    "  i = 0\n",
+    "\n",
     "\n",
     "  for index, value in df['word'].iteritems():\n",
+    "    i = i+1\n",
     "    embedding_list.append(model.encode(value))\n",
+    "    print(i)\n",
     "  \n",
     "  print('Done')\n",
     "  \n",
@@ -92,7 +204,11 @@
   },
   {
    "cell_type": "code",
+<<<<<<< HEAD
    "execution_count": 17,
+=======
+   "execution_count": 19,
+>>>>>>> e5255808ccac5081b6253049b2c08282f39bc16c
    "metadata": {
     "id": "CSvPFot643YO"
    },
@@ -101,6 +217,15 @@
     "df_filtered = df_word[df_word['word'].apply(detect_language)]"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_filtered.to_csv('../dataset/df_filtered.csv')"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -127,7 +252,25 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "df_embbeding = pd.dataframe(li, columns=['embedding'])"
+    "df_embbeding = pd.DataFrame(li, columns=['embedding'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_embbeding.to_csv('../dataset/word_embeddings.csv')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "l"
    ]
   },
   {
@@ -152,9 +295,9 @@
    "provenance": []
   },
   "kernelspec": {
-   "display_name": "default:Python",
+   "display_name": "Pytorch (Local)",
    "language": "python",
-   "name": "conda-env-default-py"
+   "name": "local-pytorch"
   },
   "language_info": {
    "codemirror_mode": {
@@ -166,7 +309,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.13"
+   "version": "3.7.12"
   }
  },
  "nbformat": 4,