Added files to repositoryHEADmain

7 files changed, 4832 insertions, 0 deletions

diff --git a/src/neuralnetwork/clean_data.py b/src/neuralnetwork/clean_data.py
new file mode 100644
index 0000000..345218e
--- /dev/null
+++ b/src/neuralnetwork/clean_data.py
@@ -0,0 +1,59 @@
+import training
+import os
+import sys
+
+if __name__ == "__main__":
+
+    countries = training.get_countries()
+
+    for c, country in countries.items():
+        if c == "uk" or c == "usa":
+
+            # iterate through each dataset separately
+            for dataset, path in country.datasets.items():
+
+                # print information
+                print(f"filtering through {c}'s {dataset}...")
+                sys.stdout.flush()
+
+                names = country.get_names(dataset)
+
+                # store the names that are valid in a seperate list
+                names_output = []
+
+                # load the alphabet file for the country
+                alphabet = []
+
+                with open(os.path.join(country.path, "alphabet.txt"), "r") as file:
+                    for l in file.read().split("\n"):
+                        alphabet.append(l)
+
+                c = 0
+                t = len(names)
+                # iterate through names in the dataset
+                for name in names:
+                    name = country.preprocess(name)
+
+                    valid = True
+
+                    # invalidate the name if a single letter is not in the alphabet
+                    for letter in name:
+                        if not letter in alphabet:
+                            valid = False
+                            break
+
+                    if valid:
+                        names_output.append(name)
+
+                    c += 1
+                    if c % 128 == 0:
+                        print(f"\r{c}/{t}", end="")
+
+                # print how many names are left
+                print(f"kept {len(names_output)}/{len(names)} names")
+
+                # save dataset
+                with open(path, "w") as file:
+                    for name in names_output:
+                        file.write(name)
+                        file.write("\n")
diff --git a/src/neuralnetwork/data/ipa.csv b/src/neuralnetwork/data/ipa.csv
new file mode 100644
index 0000000..6965ce5
--- /dev/null
+++ b/src/neuralnetwork/data/ipa.csv
@@ -0,0 +1,174 @@
+p,p,vl bilabial plosive
+b,b,vd bilabial plosive
+t,t,vl alveolar plosive
+d,d,vd alveolar plosive
+ʈ,t`,vl retroflex plosive
+ɖ,d`,vd retroflex plosive
+c,c,vl palatal plosive
+ɟ,J\,vd palatal plosive
+k,k,ld velar plosive
+ɡ,g,vd velar plosive
+q,q,vl uvular plosive
+ɢ,G\,vd uvular plosive
+ʔ,?,glottal plosive
+m,m,bilabial nasal
+ɱ,F,vl labiodental nasal
+n,n,alveolar nasal
+ɳ,n`,vl retroflex nasal
+ɲ,J,vl palatal nasal
+ŋ,N,vl velar nasal
+ɴ,N\,vl uvular nasal
+ʙ,B\,vd bilabial trill
+r,r,vd alveolar trill
+ʀ,R\,vl uvular trill
+ɾ,4,vl alveolar tap
+ɽ,r`,vl retroflex flap
+ɸ,p\,vl bilabial fricative
+β,B,vd bilabial fricative
+f,f,vl labiodental fricative
+v,v,vd labiodental fricative
+θ,T,vl dental fricative
+ð,D,vd dental fricative
+s,s,vl alveolar fricative
+z,z,vd alveolar fricative
+ʃ,S,vl postalveolar fricative
+ʒ,Z,vd postalveolar fricative
+ʂ,s`,vl retroflex fricative
+ʐ,z`,vd retroflex fricative
+ç,C,vl palatal fricative
+ʝ,j\,vd palatal fricative
+x,x,vl velar fricative
+ɣ,G,vd velar fricative
+χ,X,vl uvular fricative
+ʁ,R,vd uvular fricative
+ħ,X\,vl pharyngeal fricative
+ʕ,?\,vd pharyngeal fricative
+h,h,vl glottal fricative
+ʔ,?,glottal plosive
+ɬ,K,vl alveolar lateral fricative
+ɮ,K\,vd alveolar lateral fricative
+ʋ,P,vd labiodental approximant
+ɹ,r\,vd (post)alveolar approximant
+ɻ,r\`,vd retroflex approximant
+j,j,vd palatal approximant
+ɰ,M\,vd velar approximant
+l,l,vd alveolar lateral approximant
+ɭ,l`,vd retroflex lateral approximant
+ʎ,L,vd palatal lateral approximant
+ʟ,L\,vd velar lateral approximant
+pʼ,p_>,ejective
+tʼ,t_>,ejective
+ʈʼ,t`_>,ejective
+cʼ,c_>,ejective
+kʼ,k_>,ejective
+qʼ,q_>,ejective
+ɓ,b_<,vl bilabial implosive
+ɗ,d_<,vl alveolar implosive
+ƙ,k_<,vl velar implosive
+ɠ,g_<,vl velar implosive
+i,i,close front unrounded
+y,y,close front rounded
+ɨ,1,close central unrounded
+ʉ,},close central rounded
+ɯ,M,close back unrounded
+u,u,close back rounded
+ɪ,I,lax close front unrounded
+ʏ,Y,lax close front rounded
+ʊ,U,lax close back rounded
+e,e,close-mid front unrounded
+ø,2,front close-mid rounded
+ɤ,7,close-mid back unrounded
+o,o,close-mid back rounded
+ə,@,schwa
+ɘ,@\,close-mid central unrounded vowel
+ɵ,8,rounded schwa
+ɛ,E,open-mid front unrounded
+œ,9,front open-mid rounded
+ʌ,V,open-mid back unrounded
+ɔ,O,open-mid back rounded
+æ,{,mid-open front unrounded vowel
+ɐ,6,open-mid schwa
+a,a,open front unrounded
+ă,a_X,extra short open front unrounded
+ɶ,&,front open rounded
+ɑ,A,open back unrounded
+ɒ,Q,open back rounded
+̥,_0,voiceless
+̬,_v,voiced
+ʰ,_h,aspirated
+̤,_t,breathy voiced
+̰,_k,creaky voiced
+̼,_N,linguolabial
+̪,_d,dental
+̺,_a,apical
+̻,_m,laminal
+̹,_O,more rounded
+̜,_c,less rounded
+̟,_+,advanced
+̠,_-,retracted
+̈,"_""",centralized
+̽,_x,mid-centralized
+̩,=,syllabic
+̯,_^,non-syllabic
+ʷ,_w,labialized
+ʲ,',palatalized
+ˠ,_G,velarized
+ˤ,_?\,pharyngealized
+̴,_e,velarized or pharyngealized
+̝,_r,raised
+̞,_o,lowered
+̃,~,nasalized
+ⁿ,_n,nasal release
+ˡ,_l,lateral release
+̚,_},not audibly released
+̘,_A,advanced tongue root
+̙,_q,retracted tongue root
+̋,_T,extra high tone
+́,_H,high tone
+̄,_M,mid tone
+̀,_L,low tone
+̏,_B,extra low tone
+ˈ,"""",(primary) stress mark
+ˌ,%,secondary stress
+ː,:,length mark
+ˑ,:\,half-length
+̆,_X,extra-short
+.,.,syllable break
+ʍ,W,vl labial-velar fricative
+w,w,vd labio-velar approximant
+ɥ,H,labial-palatal approximant
+ʜ,H\,vl epiglottal fricative
+ʢ,<\,vl epiglottal fricative
+ʡ,>\,vl epiglottal plosive
+ɕ,s\,vl alveolopalatal fricative
+ʑ,z\,vl alveolopalatal fricative
+ʘ,O\,bilabial click
+ǀ,|\,dental click
+ǃ,!\,click
+ǂ,'=\,alveolar click
+ǁ,|\|\,alveolar lateral click
+ɺ,l\,vl alveolar lateral flap
+ɜ,3,open-mid central
+ʛ,G\_<,vl uvular implosive
+ɚ,@`,rhotacized schwa
+ɞ,3\,open-mid central rounded
+ɦ,h\,vd glottal fricative
+ɫ,5,velarized vl alveolar lateral
+ʄ,J\_<,vl palatal implosive
+ʼ,_>,ejective
+ɝ,3`,rhotacized open-mid central
+t͡ʃ,tS,vl postalveolar affricate
+d͡ʒ,dZ,vd postalveolar affricate
+t͡ɕ,ts\,vl alveolo-palatal affricate
+d͡ʑ,dz\,vd alveolo-palatal affricate
+t͡ɬ,tK,vl alveolar lateral affricate
+k͡p,kp,vl labial-velar plosive
+g͡b,gb,vd labial-velar plosive
+ŋ͡m,Nm,labial-velar nasal stop
+ʈ͡ʂ,ts`,vl retroflex affricate
+ɖ͡ʐ,tz`,vd retroflex affricate
+˩,_B,extra low tone
+˨,_L,low tone
+˧,_M,mid tone 
+˦,_H,high tone
+˥,_T,extra high tone
diff --git a/src/neuralnetwork/data/names/English.txt b/src/neuralnetwork/data/names/English.txt
new file mode 100755
index 0000000..2b943a7
--- /dev/null
+++ b/src/neuralnetwork/data/names/English.txt
@@ -0,0 +1,3668 @@
+Abbas
+Abbey
+Abbott
+Abdi
+Abel
+Abraham
+Abrahams
+Abrams
+Ackary
+Ackroyd
+Acton
+Adair
+Adam
+Adams
+Adamson
+Adanet
+Addams
+Adderley
+Addinall
+Addis
+Addison
+Addley
+Aderson
+Adey
+Adkins
+Adlam
+Adler
+Adrol
+Adsett
+Agar
+Ahern
+Aherne
+Ahmad
+Ahmed
+Aikman
+Ainley
+Ainsworth
+Aird
+Airey
+Aitchison
+Aitken
+Akhtar
+Akram
+Alam
+Alanson
+Alber
+Albert
+Albrighton
+Albutt
+Alcock
+Alden
+Alder
+Aldersley
+Alderson
+Aldred
+Aldren
+Aldridge
+Aldworth
+Alesbury
+Alexandar
+Alexander
+Alexnader
+Alford
+Algar
+Ali
+Alker
+Alladee
+Allam
+Allan
+Allard
+Allaway
+Allcock
+Allcott
+Alldridge
+Alldritt
+Allen
+Allgood
+Allington
+Alliott
+Allison
+Allkins
+Allman
+Allport
+Allsop
+Allum
+Allwood
+Almond
+Alpin
+Alsop
+Altham
+Althoff
+Alves
+Alvey
+Alway
+Ambrose
+Amesbury
+Amin
+Amner
+Amod
+Amor
+Amos
+Anakin
+Anderson
+Andersson
+Anderton
+Andrew
+Andrews
+Angus
+Anker
+Anley
+Annan
+Anscombe
+Ansell
+Anstee
+Anthony
+Antic
+Anton
+Antony
+Antram
+Anwar
+Appleby
+Appleton
+Appleyard
+Apsley
+Arah
+Archer
+Ardern
+Arkins
+Armer
+Armitage
+Armour
+Armsden
+Armstrong
+Arnall
+Arnett
+Arnold
+Arnott
+Arrowsmith
+Arscott
+Arthur
+Artliff
+Ashbridge
+Ashbrook
+Ashby
+Ashcroft
+Ashdown
+Ashe
+Asher
+Ashford
+Ashley
+Ashman
+Ashton
+Ashurst
+Ashwell
+Ashworth
+Askew
+Aslam
+Asom
+Aspey
+Aspin
+Aspinall
+Astbury
+Astle
+Astley
+Aston
+Atherley
+Atherstone
+Atherton
+Atkin
+Atkins
+Atkinson
+Attard
+Atter
+Atterbury
+Atterton
+Attewell
+Attrill
+Attwood
+Auberton
+Auborn
+Aubrey
+Austen
+Austin
+Auton
+Avenue
+Avery
+Aves
+Avis
+Awad
+Axon
+Aylett
+Ayley
+Ayliffe
+Ayling
+Aylott
+Aylward
+Ayres
+Ayton
+Aziz
+Bacon
+Bailey
+Bain
+Bainbridge
+Baines
+Bains
+Baird
+Baker
+Baldwin
+Bale
+Ball
+Ballantyne
+Ballard
+Bamford
+Bancroft
+Banks
+Banner
+Bannister
+Barber
+Barclay
+Barker
+Barlow
+Barnard
+Barnes
+Barnett
+Baron
+Barr
+Barrett
+Barron
+Barrow
+Barry
+Bartlett
+Barton
+Bass
+Bassett
+Batchelor
+Bate
+Bateman
+Bates
+Batt
+Batten
+Batty
+Baxter
+Bayliss
+Beadle
+Beal
+Beale
+Beamish
+Bean
+Bear
+Beattie
+Beatty
+Beaumont
+Beck
+Bedford
+Beech
+Beer
+Begum
+Bell
+Bellamy
+Benfield
+Benjamin
+Bennett
+Benson
+Bentley
+Berger
+Bernard
+Berry
+Best
+Bethell
+Betts
+Bevan
+Beveridge
+Bickley
+Biddle
+Biggs
+Bill
+Bing
+Bingham
+Binnington
+Birch
+Bird
+Bishop
+Bithell
+Black
+Blackburn
+Blackman
+Blackmore
+Blackwell
+Blair
+Blake
+Blakeley
+Blakey
+Blanchard
+Bland
+Bloggs
+Bloom
+Blundell
+Blythe
+Bob
+Boden
+Boland
+Bolton
+Bond
+Bone
+Bonner
+Boon
+Booth
+Borland
+Bostock
+Boulton
+Bourne
+Bouvet
+Bowden
+Bowen
+Bower
+Bowers
+Bowes
+Bowler
+Bowles
+Bowman
+Boyce
+Boyd
+Boyle
+Bracey
+Bradbury
+Bradley
+Bradshaw
+Brady
+Brain
+Braithwaite
+Bramley
+Brandrick
+Bray
+Breen
+Brelsford
+Brennan
+Brett
+Brewer
+Bridges
+Briggs
+Bright
+Bristow
+Britton
+Broadbent
+Broadhurst
+Broadley
+Brock
+Brook
+Brooke
+Brooker
+Brookes
+Brookfield
+Brooks
+Broomfield
+Broughton
+Brown
+Browne
+Browning
+Bruce
+Brunet
+Brunton
+Bryan
+Bryant
+Bryson
+Buchan
+Buchanan
+Buck
+Buckingham
+Buckley
+Budd
+Bugg
+Bull
+Bullock
+Burch
+Burden
+Burdett
+Burford
+Burge
+Burgess
+Burke
+Burland
+Burman
+Burn
+Burnett
+Burns
+Burr
+Burrows
+Burt
+Burton
+Busby
+Bush
+Butcher
+Butler
+Butt
+Butter
+Butterworth
+Button
+Buxton
+Byrne
+Caddy
+Cadman
+Cahill
+Cain
+Cairns
+Caldwell
+Callaghan
+Callow
+Calveley
+Calvert
+Cameron
+Campbell
+Cann
+Cannon
+Caplan
+Capper
+Carey
+Carling
+Carmichael
+Carnegie
+Carney
+Carpenter
+Carr
+Carrington
+Carroll
+Carruthers
+Carson
+Carter
+Cartwright
+Carty
+Casey
+Cashmore
+Cassidy
+Caton
+Cavanagh
+Cawley
+Chadwick
+Chalmers
+Chamberlain
+Chambers
+Chan
+Chance
+Chandler
+Chantler
+Chaplin
+Chapman
+Chappell
+Chapple
+Charge
+Charles
+Charlton
+Charnock
+Chase
+Chatterton
+Chauhan
+Cheetham
+Chelmy
+Cherry
+Cheshire
+Chester
+Cheung
+Chidlow
+Child
+Childs
+Chilvers
+Chisholm
+Chong
+Christie
+Christy
+Chung
+Church
+Churchill
+Clamp
+Clancy
+Clark
+Clarke
+Clarkson
+Clay
+Clayton
+Cleary
+Cleaver
+Clegg
+Clements
+Cliff
+Clifford
+Clifton
+Close
+Clough
+Clowes
+Coates
+Coburn
+Cochrane
+Cockburn
+Cockle
+Coffey
+Cohen
+Cole
+Coleman
+Coles
+Coll
+Collard
+Collett
+Colley
+Collier
+Collingwood
+Collins
+Collinson
+Colman
+Compton
+Conneely
+Connell
+Connelly
+Connolly
+Connor
+Conrad
+Conroy
+Conway
+Cook
+Cooke
+Cookson
+Coomber
+Coombes
+Cooper
+Cope
+Copeland
+Copland
+Copley
+Corbett
+Corcoran
+Core
+Corlett
+Cormack
+Corner
+Cornish
+Cornock
+Corr
+Corrigan
+Cosgrove
+Costa
+Costello
+Cotter
+Cotterill
+Cotton
+Cottrell
+Couch
+Coulson
+Coulter
+Court
+Cousin
+Cousins
+Cove
+Cowan
+Coward
+Cowell
+Cowie
+Cowley
+Cox
+Coyle
+Crabb
+Crabtree
+Cracknell
+Craig
+Crane
+Craven
+Crawford
+Crawley
+Creasey
+Cresswell
+Crew
+Cripps
+Crisp
+Crocker
+Croft
+Crofts
+Cronin
+Crook
+Crosby
+Cross
+Crossland
+Crossley
+Crouch
+Croucher
+Crow
+Crowe
+Crowley
+Crown
+Crowther
+Crump
+Cullen
+Cumming
+Cummings
+Cummins
+Cunningham
+Curley
+Curran
+Currie
+Curry
+Curtis
+Curwood
+Cutts
+D arcy
+Dacey
+Dack
+Dalby
+Dale
+Daley
+Dallas
+Dalton
+Daly
+Dalzell
+Damon
+Danby
+Dandy
+Daniel
+Daniells
+Daniels
+Danks
+Dann
+Darby
+Darbyshire
+Darcy
+Dardenne
+Darlington
+Darr
+Daugherty
+Davenport
+Davey
+David
+Davidson
+Davie
+Davies
+Davis
+Davison
+Davy
+Dawe
+Dawes
+Dawkins
+Dawson
+Day
+Dayman
+De ath
+Deacon
+Deakin
+Dean
+Deane
+Deans
+Debenham
+Deegan
+Deeley
+Deighton
+Delamarre
+Delaney
+Dell
+Dempsey
+Dempster
+Denby
+Denham
+Denis
+Denney
+Dennis
+Dent
+Denton
+Depp
+Dermody
+Derrick
+Derrien
+Dervish
+Desai
+Devaney
+Devenish
+Deverell
+Devine
+Devlin
+Devon
+Devonport
+Dewar
+Dexter
+Diamond
+Dibble
+Dick
+Dickens
+Dickenson
+Dicker
+Dickinson
+Dickson
+Dillon
+Dimmock
+Dingle
+Dipper
+Dixon
+Dobbin
+Dobbins
+Doble
+Dobson
+Docherty
+Docker
+Dodd
+Dodds
+Dodson
+Doherty
+Dolan
+Dolcy
+Dolman
+Dolton
+Donald
+Donaldson
+Donkin
+Donlan
+Donn
+Donnachie
+Donnelly
+Donoghue
+Donohoe
+Donovan
+Dooley
+Doolin
+Doon
+Doors
+Dora
+Doran
+Dorman
+Dornan
+Dorrian
+Dorrington
+Dougal
+Dougherty
+Doughty
+Douglas
+Douthwaite
+Dove
+Dover
+Dowell
+Dowler
+Dowling
+Down
+Downer
+Downes
+Downey
+Downie
+Downing
+Downs
+Downton
+Dowson
+Doyle
+Drabble
+Drain
+Drake
+Draper
+Drew
+Drewett
+Dreyer
+Driffield
+Drinkwater
+Driscoll
+Driver
+Drummond
+Drury
+Drysdale
+Dubois
+Duck
+Duckworth
+Ducon
+Dudley
+Duff
+Duffield
+Duffin
+Duffy
+Dufour
+Duggan
+Duke
+Dukes
+Dumont
+Duncan
+Dundon
+Dunford
+Dunkley
+Dunlop
+Dunmore
+Dunn
+Dunne
+Dunnett
+Dunning
+Dunsford
+Dupont
+Durand
+Durant
+Durber
+Durham
+Durrant
+Dutt
+Duval
+Duvall
+Dwyer
+Dyde
+Dyer
+Dyerson
+Dykes
+Dymond
+Dymott
+Dyson
+Eade
+Eadie
+Eagle
+Eales
+Ealham
+Ealy
+Eames
+Eansworth
+Earing
+Earl
+Earle
+Earley
+Easdale
+Easdown
+Easen
+Eason
+East
+Eastaugh
+Eastaway
+Eastell
+Easterbrook
+Eastham
+Easton
+Eastwood
+Eatherington
+Eaton
+Eaves
+Ebbs
+Ebden
+Ebdon
+Ebeling
+Eburne
+Eccles
+Eccleston
+Ecclestone
+Eccott
+Eckersall
+Eckersley
+Eddison
+Eddleston
+Eddy
+Eden
+Edeson
+Edgar
+Edge
+Edgell
+Edgerton
+Edgley
+Edgson
+Edkins
+Edler
+Edley
+Edlington
+Edmond
+Edmonds
+Edmondson
+Edmunds
+Edmundson
+Edney
+Edon
+Edwards
+Edwick
+Eedie
+Egan
+Egerton
+Eggby
+Eggison
+Eggleston
+Eglan
+Egleton
+Eglin
+Eilers
+Ekin
+Elbutt
+Elcock
+Elder
+Eldeston
+Eldridge
+Eley
+Elfman
+Elford
+Elkin
+Elkington
+Ellam
+Ellans
+Ellard
+Elleray
+Ellerby
+Ellershaw
+Ellery
+Elliman
+Elling
+Ellingham
+Elliot
+Elliott
+Ellis
+Ellison
+Elliston
+Ellrott
+Ellwood
+Elmer
+Elmes
+Elmhirst
+Elmore
+Elms
+Elphick
+Elsdon
+Elsmore
+Elson
+Elston
+Elstone
+Eltis
+Elven
+Elvin
+Elvins
+Elwell
+Elwood
+Elworthy
+Elzer
+Emberey
+Emberson
+Embleton
+Emerick
+Emerson
+Emery
+Emmanuel
+Emmerson
+Emmery
+Emmett
+Emmings
+Emmins
+Emmons
+Emmott
+Emms
+Emsden
+Endroe
+England
+English
+Ennis
+Ennos
+Enright
+Enticott
+Entwistle
+Epsom
+Epton
+Ernest
+Erridge
+Errington
+Errity
+Esan
+Escott
+Eskins
+Eslick
+Espley
+Essam
+Essan
+Essop
+Estlick
+Etchells
+Etheridge
+Etherington
+Etherton
+Ettrick
+Evans
+Evason
+Evenden
+Everdell
+Everett
+Everill
+Everitt
+Everson
+Everton
+Eveson
+Evison
+Evrard
+Ewart
+Ewin
+Ewing
+Ewles
+Exley
+Exon
+Exton
+Eyett
+Eyles
+Eyre
+Eyres
+Fabb
+Fagan
+Fagon
+Fahy
+Fairbairn
+Fairbrace
+Fairbrother
+Fairchild
+Fairclough
+Fairhurst
+Fairley
+Fairlie
+Fairweather
+Falconer
+Falk
+Fall
+Fallon
+Fallows
+Falsh
+Farge
+Fargher
+Farhall
+Farley
+Farmer
+Farnsworth
+Farnum
+Farnworth
+Farr
+Farrant
+Farrar
+Farre
+Farrell
+Farrelly
+Farren
+Farrer
+Farrier
+Farrington
+Farrow
+Faulkner
+Faust
+Fawcett
+Fawn
+Faye
+Fearn
+Fearnley
+Fearns
+Fearon
+Featherstone
+Feeney
+Feetham
+Felix
+Fell
+Fellmen
+Fellows
+Feltham
+Felton
+Fenlon
+Fenn
+Fenton
+Fenwick
+Ferdinand
+Fereday
+Ferguson
+Fern
+Fernandez
+Ferns
+Fernyhough
+Ferreira
+Ferrier
+Ferris
+Ferry
+Fewtrell
+Field
+Fielder
+Fielding
+Fields
+Fifield
+Finan
+Finbow
+Finch
+Findlay
+Findley
+Finlay
+Finn
+Finnegan
+Finney
+Finnigan
+Finnimore
+Firth
+Fischer
+Fish
+Fisher
+Fishlock
+Fisk
+Fitch
+Fitchett
+Fitton
+Fitzgerald
+Fitzpatrick
+Fitzsimmons
+Flack
+Flaherty
+Flanagan
+Flanders
+Flannery
+Flavell
+Flaxman
+Fleetwood
+Fleming
+Fletcher
+Flett
+Florey
+Floss
+Flower
+Flowers
+Floyd
+Flynn
+Foden
+Fogg
+Foley
+Fontaine
+Foran
+Forbes
+Ford
+Forde
+Fordham
+Foreman
+Forester
+Forman
+Forrest
+Forrester
+Forshaw
+Forster
+Forsyth
+Forsythe
+Forth
+Fortin
+Foss
+Fossard
+Fosse
+Foster
+Foston
+Fothergill
+Fotheringham
+Foucher
+Foulkes
+Fountain
+Fowler
+Fowley
+Fox
+Foxall
+Foxley
+Frame
+Frampton
+France
+Francis
+Franco
+Frankish
+Frankland
+Franklin
+Franks
+Frary
+Fraser
+Frazer
+Frederick
+Frederikson
+Freeburn
+Freedman
+Freeman
+Freestone
+Freeth
+Freight
+French
+Fretwell
+Frey
+Fricker
+Friel
+Friend
+Frith
+Froggatt
+Froggett
+Frost
+Frostick
+Froy
+Frusher
+Fryer
+Fulker
+Fuller
+Fulleron
+Fullerton
+Fulton
+Funnell
+Furey
+Furlong
+Furnell
+Furness
+Furnish
+Furniss
+Furse
+Fyall
+Gadsden
+Gaffney
+Galbraith
+Gale
+Gales
+Gall
+Gallacher
+Gallagher
+Galliford
+Gallo
+Galloway
+Galvin
+Gamble
+Gammer
+Gammon
+Gander
+Gandham
+Ganivet
+Garber
+Garbett
+Garbutt
+Garcia
+Gardener
+Gardiner
+Gardner
+Garland
+Garner
+Garrard
+Garratt
+Garrett
+Garside
+Garvey
+Gascoyne
+Gaskell
+Gately
+Gates
+Gaudin
+Gaumont
+Gauntlett
+Gavin
+Gaynor
+Geaney
+Geary
+Geeson
+Geldard
+Geldart
+Gell
+Gemmell
+Gene
+George
+Gerard
+Gerrard
+Geyer
+Gibb
+Gibbins
+Gibbon
+Gibbons
+Gibbs
+Giblin
+Gibson
+Gifford
+Gilbert
+Gilbey
+Gilchrist
+Gilder
+Giles
+Gilfillan
+Gilks
+Gill
+Gillam
+Gillan
+Gillard
+Gillen
+Gillespie
+Gillett
+Gillies
+Gilmartin
+Gilmore
+Gilmour
+Ginty
+Girdwood
+Girling
+Given
+Gladwell
+Glaister
+Glasby
+Glasgow
+Glass
+Gleave
+Gledhill
+Gleeson
+Glen
+Glencross
+Glenn
+Glennie
+Glennon
+Glew
+Glossop
+Glover
+Glynn
+Goble
+Godby
+Goddard
+Godden
+Godfrey
+Godwin
+Goff
+Gold
+Goldberg
+Golding
+Goldman
+Goldsmith
+Goldsworthy
+Gomez
+Gonzalez
+Gooch
+Good
+Goodacre
+Goodall
+Goodchild
+Goode
+Gooding
+Goodman
+Goodridge
+Goodson
+Goodwin
+Goodyear
+Gordon
+Goring
+Gorman
+Gosden
+Gosling
+Gough
+Gould
+Goulden
+Goulding
+Gourlay
+Govender
+Govier
+Gower
+Gowing
+Grady
+Graham
+Grainger
+Grange
+Granger
+Grant
+Graves
+Gray
+Grayson
+Greaves
+Green
+Greenall
+Greenaway
+Greene
+Greener
+Greenhill
+Greening
+Greenleaf
+Greenshields
+Greenslade
+Greensmith
+Greenway
+Greenwood
+Greer
+Gregory
+Greig
+Grenard
+Grennan
+Gresham
+Grey
+Grierson
+Griff
+Griffin
+Griffith
+Griffiths
+Griggs
+Grimes
+Grimshaw
+Grinham
+Grivet
+Grogan
+Groom
+Grose
+Grosvenor
+Grout
+Groves
+Grundy
+Guest
+Guilmard
+Guinard
+Gulley
+Gunby
+Gunn
+Gunning
+Gunston
+Gunter
+Guthrie
+Gutteridge
+Guttridge
+Hackett
+Hadden
+Haddock
+Hadfield
+Hagan
+Haggett
+Haigh
+Haine
+Haines
+Hale
+Halford
+Hall
+Hallam
+Hallett
+Halliday
+Halliwell
+Halstead
+Hamer
+Hamill
+Hamilton
+Hammond
+Hamnett
+Hampson
+Hampton
+Hancock
+Hand
+Handley
+Hanlon
+Hannam
+Hansen
+Hanson
+Harden
+Harding
+Hardwick
+Hardy
+Hargreaves
+Harker
+Harkness
+Harley
+Harlow
+Harman
+Harness
+Harper
+Harries
+Harrington
+Harris
+Harrison
+Harrop
+Harry
+Hart
+Hartley
+Harvey
+Harwood
+Haslam
+Hassan
+Hassani
+Hastings
+Hatch
+Hatton
+Hawes
+Hawker
+Hawkes
+Hawkins
+Hawkridge
+Hawley
+Haworth
+Hawtin
+Hayes
+Haynes
+Hayward
+Head
+Healey
+Healy
+Heath
+Heathcote
+Heather
+Heatley
+Heaton
+Hedley
+Hegney
+Helley
+Hellier
+Helm
+Hemingway
+Hemmings
+Henderson
+Hendry
+Heneghan
+Hennessy
+Henry
+Hepburn
+Hepples
+Herbert
+Heritage
+Heron
+Herron
+Hetherington
+Hewitt
+Hewlett
+Heywood
+Hibbert
+Hickey
+Hickman
+Hicks
+Higgins
+Higginson
+Higgs
+Hill
+Hills
+Hilton
+Hind
+Hinde
+Hindle
+Hindley
+Hinds
+Hine
+Hinton
+Hirst
+Hiscocks
+Hitchcock
+Hoare
+Hobbs
+Hobson
+Hocking
+Hodder
+Hodge
+Hodges
+Hodgkins
+Hodgkinson
+Hodgson
+Hodkinson
+Hodson
+Hogan
+Hogg
+Holden
+Holder
+Holding
+Holdsworth
+Hole
+Holgate
+Holl
+Holland
+Hollis
+Holloway
+Holman
+Holmes
+Holt
+Homer
+Hood
+Hook
+Hooper
+Hooton
+Hope
+Hopes
+Hopkins
+Hopkinson
+Hopwood
+Horn
+Horne
+Horner
+Horrocks
+Horton
+Hough
+Houghton
+Hoult
+Houlton
+Houston
+Howard
+Howarth
+Howden
+Howe
+Howell
+Howells
+Howes
+Howie
+Hoyle
+Hubbard
+Hudson
+Huggins
+Hughes
+Hull
+Hulme
+Hume
+Humphrey
+Humphreys
+Humphries
+Hunt
+Hunter
+Hurley
+Hurrell
+Hurst
+Hussain
+Hussein
+Hussey
+Hutchings
+Hutchins
+Hutchinson
+Hutchison
+Hutton
+Hyde
+Ianson
+Ibbotson
+Ibbs
+Ibrahim
+Iddon
+Iggleden
+Iles
+Ilett
+Illing
+Illingworth
+Ilsley
+Impey
+Imran
+Ingermann
+Ingham
+Ingle
+Ingleby
+Ingledew
+Inglefield
+Ingles
+Inglethorpe
+Ingram
+Inker
+Inman
+Innalls
+Innes
+Inson
+Ireland
+Ireson
+Ironman
+Ironmonger
+Irvin
+Irvine
+Irving
+Irwin
+Isaac
+Isaacs
+Isbill
+Isbitt
+Isgate
+Isherwod
+Isherwood
+Islam
+Isman
+Isnard
+Issac
+Ivory
+Izzard
+Jackman
+Jacks
+Jackson
+Jacob
+Jacobs
+Jacobson
+Jacques
+Jaffray
+Jagger
+Jakeman
+James
+Jameson
+Jamieson
+Janes
+Jansen
+Jardine
+Jarman
+Jarram
+Jarratt
+Jarrett
+Jarrold
+Jarvis
+Jasper
+Jebson
+Jeffcock
+Jefferies
+Jeffers
+Jefferson
+Jeffery
+Jefford
+Jeffrey
+Jeffreys
+Jeffries
+Jeffs
+Jems
+Jenas
+Jenkin
+Jenkins
+Jenkinson
+Jenks
+Jenkyns
+Jenner
+Jennings
+Jennison
+Jennson
+Jensen
+Jepson
+Jermy
+Jerome
+Jerry
+Jervis
+Jesson
+Jessop
+Jevons
+Jewell
+Jewers
+Jewett
+Jewitt
+Jewkes
+Jewson
+Jiggens
+Jobson
+Johannson
+Johansen
+Johanson
+John
+Johns
+Johnson
+Johnston
+Johnstone
+Jolley
+Jolly
+Jonas
+Jones
+Jonhson
+Jopson
+Jordan
+Jordison
+Jordon
+Joseph
+Joss
+Jourdan
+Jowett
+Jowitt
+Joyce
+Joynson
+Jubb
+Judd
+Judge
+Jukes
+Jupp
+Jury
+Kacy
+Kaddour
+Kamara
+Kampfner
+Kane
+Kanes
+Kapoor
+Karim
+Karne
+Karras
+Kassell
+Kaufman
+Kaul
+Kaur
+Kavanagh
+Kay
+Kaye
+Kayes
+Keable
+Keal
+Kealey
+Keane
+Kearney
+Kearns
+Kearsley
+Kearton
+Keating
+Keaveney
+Keay
+Keeble
+Keefe
+Keegan
+Keelan
+Keeler
+Keeley
+Keeling
+Keenan
+Keene
+Keetley
+Keffler
+Kehoe
+Keighley
+Keight
+Keilty
+Keir
+Keith
+Kelk
+Kell
+Kelland
+Kellems
+Kellie
+Kelliher
+Kelly
+Kelsall
+Kelsey
+Kelso
+Kemp
+Kempson
+Kempster
+Kendall
+Kendell
+Kendrick
+Kenley
+Kennard
+Kennedy
+Kenneford
+Kennell
+Kenneth
+Kennett
+Kenney
+Kenning
+Kenny
+Kenrick
+Kensington
+Kent
+Kentwood
+Kenward
+Kenworthy
+Kenyon
+Keogh
+Kerby
+Kernick
+Kerr
+Kerrell
+Kerridge
+Kerrigan
+Kerrighen
+Kerrison
+Kershaw
+Ketley
+Kett
+Kettell
+Ketteringham
+Kettlewell
+Keward
+Kewley
+Keys
+Keyte
+Keywood
+Khalid
+Khalifa
+Khalil
+Khan
+Kibblewhite
+Kidd
+Kiddle
+Kidman
+Kidner
+Kiely
+Kiernan
+Kilb
+Kilbee
+Kilbey
+Kilbride
+Kilburn
+Kilford
+Kill
+Killeen
+Killen
+Killick
+Killock
+Kilminster
+Kilmurry
+Kilnan
+Kilner
+Kilroy
+Kilshaw
+Kimber
+Kimble
+Kinch
+Kinchin
+Kinder
+King
+Kingdon
+Kinghorn
+Kingman
+Kings
+Kingscott
+Kingsley
+Kingston
+Kinnaird
+Kinnear
+Kinnersley
+Kinniburgh
+Kinnison
+Kinrade
+Kinsella
+Kinsey
+Kinsley
+Kipling
+Kirby
+Kirk
+Kirkbride
+Kirkbright
+Kirkby
+Kirkland
+Kirkman
+Kirkpatrick
+Kirkwood
+Kirtley
+Kirwan
+Kirwin
+Kitchen
+Kitchin
+Kitching
+Kitson
+Kitt
+Klam
+Klein
+Knab
+Knappett
+Knibb
+Knigge
+Knight
+Knightley
+Knighton
+Knights
+Knott
+Knowler
+Knowles
+Knox
+Knoxville
+Knuckles
+Knutt
+Koban
+Kolt
+Kone
+Kore
+Kouma
+Kram
+Kreyling
+Kristensen
+Kromberg
+Kruger
+Kumar
+Kurian
+Kurray
+Kydd
+Kyle
+Kysel
+Labbe
+Lacey
+Lacy
+Laing
+Laird
+Lake
+Lakey
+Lakin
+Lamb
+Lambert
+Lambton
+Lame
+Lamond
+Lancaster
+Lander
+Lane
+Lang
+Langdon
+Lange
+Langford
+Langley
+Langridge
+Langston
+Langton
+Lanham
+Laraway
+Large
+Larkin
+Larkings
+Larsen
+Larsson
+Last
+Latham
+Lathan
+Lathey
+Lattimore
+Laurie
+Laver
+Laverick
+Lavery
+Lawal
+Lawler
+Lawlor
+Lawn
+Lawrance
+Lawrence
+Lawrie
+Laws
+Lawson
+Lawther
+Lawton
+Laycock
+Layton
+Le tissier
+Leach
+Leadley
+Leahy
+Leake
+Leal
+Leary
+Leaver
+Leck
+Leckie
+Ledger
+Lee
+Leech
+Leedham
+Leek
+Leeming
+Lees
+Leese
+Leeson
+Legg
+Legge
+Leggett
+Leigh
+Leighton
+Leitch
+Leith
+Lendon
+Lenihan
+Lennard
+Lennon
+Lennox
+Leonard
+Leroy
+Leslie
+Lester
+Lethbridge
+Levann
+Levett
+Levin
+Levine
+Levy
+Lewin
+Lewington
+Lewins
+Lewis
+Lewry
+Leyland
+Leys
+Leyshon
+Liddell
+Liddle
+Lightfoot
+Lilley
+Lilly
+Lilwall
+Lincoln
+Lind
+Linden
+Lindo
+Lindop
+Lindsay
+Line
+Lines
+Linford
+Ling
+Linley
+Linsby
+Linton
+Lister
+Litchfield
+Little
+Littlewood
+Livermore
+Livingstone
+Llewellyn
+Lloyd
+Loat
+Lobb
+Lock
+Locke
+Lockett
+Lockhart
+Lockie
+Lockwood
+Lockyer
+Lodge
+Loft
+Lofthouse
+Loftus
+Logan
+Lohan
+Lois
+Lomas
+Lomax
+London
+Long
+Longhurst
+Longley
+Longworth
+Lonsdale
+Lopes
+Lopez
+Lord
+Loudon
+Loughran
+Louth
+Lovatt
+Love
+Lovegrove
+Lovell
+Lovelock
+Lovett
+Lovey
+Lowbridge
+Lowdon
+Lowe
+Lowes
+Lowis
+Lowndes
+Lowrie
+Lowry
+Lucas
+Luce
+Lucey
+Luckhurst
+Ludgrove
+Ludkin
+Ludlow
+Luke
+Luker
+Lumb
+Lumley
+Lumsden
+Lunn
+Lunt
+Luscombe
+Luttrell
+Luxton
+Lyall
+Lyes
+Lyme
+Lynas
+Lynch
+Lynes
+Lynn
+Lyon
+Lyons
+Mac
+Macarthur
+Macaulay
+Macdonald
+Mace
+Macfarlane
+Macgregor
+Machin
+Macintyre
+Mack
+Mackay
+Mackenzie
+Mackie
+Maclean
+Macleod
+Macmillan
+Macpherson
+Macrae
+Madden
+Maddocks
+Magee
+Maguire
+Maher
+Mahoney
+Main
+Mair
+Major
+Makin
+Malley
+Mallinson
+Malone
+Maloney
+Mangnall
+Mann
+Manning
+Mansell
+Mansfield
+Manson
+Markham
+Marks
+Marlow
+Marr
+Marriott
+Marsden
+Marsh
+Marshall
+Martin
+Martinez
+Martins
+Mason
+Masters
+Mather
+Mathers
+Matheson
+Mathews
+Matthams
+Matthews
+Maughan
+Mawson
+Maxwell
+May
+Maynard
+Mcarthur
+Mcauley
+Mcavoy
+Mcbain
+Mccabe
+Mccaffrey
+Mccall
+Mccallum
+Mccann
+Mccarthy
+Mccartney
+Mccluskey
+Mcclymont
+Mcconnell
+Mccormack
+Mccormick
+Mccourt
+Mcculloch
+Mccullough
+Mcdermott
+Mcdonagh
+Mcdonald
+Mcdonnell
+Mcdougall
+Mcelroy
+Mcewan
+Mcfadden
+Mcfarlane
+Mcgee
+Mcghee
+Mcgill
+Mcginty
+Mcgowan
+Mcgrady
+Mcgrath
+Mcgregor
+Mcgrory
+Mcguinness
+Mcguire
+Mcintosh
+Mcintyre
+Mckay
+Mckee
+Mckenna
+Mckenzie
+Mckeown
+Mckie
+Mclaren
+Mclaughlin
+Mclean
+Mclellan
+Mcleod
+Mcloughlin
+Mcmahon
+Mcmanus
+Mcmillan
+Mcnally
+Mcnamara
+Mcnaught
+Mcneil
+Mcneill
+Mcnulty
+Mcphail
+Mcphee
+Mcpherson
+Mcrae
+Mcshane
+Mctaggart
+Meadows
+Meakin
+Mears
+Melia
+Mellor
+Meredith
+Merritt
+Metcalf
+Metcalfe
+Michael
+Michel
+Middleton
+Miles
+Milford
+Mill
+Millar
+Millard
+Miller
+Millett
+Milligan
+Millington
+Mills
+Millward
+Milne
+Milner
+Milward
+Mistry
+Mitchell
+Moffat
+Mohamed
+Mohammed
+Molloy
+Molyneux
+Monaghan
+Montague
+Montgomery
+Moody
+Moon
+Mooney
+Moore
+Moorhouse
+Moran
+More
+Moreno
+Moreton
+Morgan
+Moriarty
+Morley
+Moroney
+Morris
+Morrison
+Morrow
+Mortimer
+Morton
+Moseley
+Moss
+Mottram
+Mould
+Muir
+Mullen
+Mulligan
+Mullins
+Mundy
+Munro
+Murphy
+Murray
+Murrell
+Mustafa
+Myatt
+Myers
+Nair
+Nairn
+Nandi
+Nanson
+Nanton
+Napier
+Napper
+Nartey
+Nash
+Nason
+Naughton
+Naumann
+Nayler
+Naylor
+Naysmith
+Neal
+Neale
+Neary
+Neave
+Neaverson
+Nedd
+Needham
+Neeson
+Negros
+Neighbour
+Neill
+Neilsen
+Neilson
+Neish
+Nelmes
+Nelms
+Nelson
+Nemeth
+Nero
+Nesbitt
+Ness
+Nessbert
+Nettleton
+Neville
+Nevins
+Nevis
+Newall
+Newberry
+Newbold
+Newbury
+Newby
+Newcombe
+Newell
+Newey
+Newham
+Newill
+Newington
+Newland
+Newlands
+Newman
+Newsham
+Newsome
+Newson
+Newstead
+Newton
+Neyland
+Nichol
+Nicholas
+Nicholl
+Nicholls
+Nichols
+Nicholson
+Nickel
+Nickolls
+Nicks
+Nicol
+Nicolas
+Nicoll
+Nicolson
+Nield
+Nielsen
+Nielson
+Nightingale
+Niles
+Nilsen
+Nineham
+Nisbet
+Nixon
+Noach
+Noakes
+Nobbs
+Noble
+Noggins
+Nokes
+Nolan
+Nood
+Noon
+Noonan
+Norbert
+Norburn
+Norbury
+Norcross
+Nord
+Norgate
+Norgrove
+Norm
+Norman
+Normington
+Norris
+Norsworthy
+North
+Northcott
+Norton
+Norville
+Norwood
+Notman
+Nott
+Nourse
+Nova
+Nowak
+Nowell
+Noyce
+Noyes
+Nugent
+Number
+Nunn
+Nurse
+Nurton
+Nutella
+Nutman
+Nutt
+Nuttall
+Oakes
+Oakey
+Oakley
+Oaks
+Oakton
+Oates
+Oatridge
+Oatway
+Obrien
+Ocallaghan
+Oconnell
+Oconnor
+Odam
+Oddie
+Oddy
+Odea
+Odell
+Odling
+Odonnell
+Odonoghue
+Odriscoll
+Oflynn
+Ogden
+Ogilvie
+Ogilvy
+Ogrady
+Ohalloran
+Ohara
+Okeefe
+Okey
+Okten
+Olan
+Oldfield
+Oldham
+Olding
+Oldland
+Oldroyd
+Olds
+Oleary
+Oliver
+Olivier
+Ollerhead
+Olley
+Oloughlin
+Olsen
+Olson
+Omalley
+Oman
+Oneil
+Oneill
+Opayne
+Openshaw
+Oram
+Orbell
+Orchard
+Oreilly
+Oriley
+Orman
+Orme
+Ormiston
+Ormond
+Ormsby
+Ormston
+Orrell
+Orritt
+Orton
+Orvis
+Orwin
+Osborn
+Osborne
+Osman
+Osmond
+Ostcliffe
+Ostler
+Osullivan
+Oswald
+Otoole
+Otten
+Otter
+Ottey
+Ottley
+Otton
+Ould
+Oulton
+Overall
+Overett
+Overfield
+Overing
+Overson
+Overton
+Owen
+Owens
+Owings
+Oxby
+Oxenham
+Oxley
+Oxtoby
+Pack
+Packard
+Packer
+Pagan
+Page
+Paige
+Pailing
+Paine
+Painter
+Paisley
+Palfrey
+Palfreyman
+Palin
+Pallett
+Palmer
+Panesar
+Pankhurst
+Pannell
+Parish
+Park
+Parker
+Parkes
+Parkin
+Parkins
+Parkinson
+Parks
+Parmar
+Parnaby
+Parnell
+Parr
+Parratt
+Parrott
+Parry
+Parsons
+Partington
+Partlett
+Partridge
+Pascoe
+Pasfield
+Paskell
+Passmore
+Patchett
+Patel
+Pateman
+Paterson
+Paton
+Patrick
+Patten
+Patterson
+Pattinson
+Pattison
+Patton
+Paul
+Pavot
+Pawson
+Payne
+Peace
+Peach
+Peacock
+Peake
+Peal
+Peaper
+Pearce
+Pears
+Pearson
+Peat
+Peck
+Pedley
+Peebles
+Peel
+Peers
+Pegg
+Peigne
+Pell
+Pelling
+Pemberton
+Pender
+Pendlebury
+Pendleton
+Penfold
+Penn
+Pennell
+Penney
+Pennington
+Percival
+Pereira
+Perez
+Perkin
+Perkins
+Perks
+Perowne
+Perrett
+Perrin
+Perrins
+Perry
+Peters
+Petersen
+Peterson
+Petrova
+Pett
+Petticrew
+Peyton
+Phelan
+Phelps
+Philip
+Philips
+Phillips
+Philpott
+Phipps
+Phoenix
+Pick
+Pickard
+Pickering
+Pickersgill
+Pickett
+Pickford
+Pickthall
+Picot
+Pierce
+Piercey
+Pierre
+Pigott
+Pike
+Pilkington
+Pillay
+Pinder
+Pine
+Pinkney
+Pinner
+Pinnock
+Pinsmail
+Pipe
+Piper
+Pitcher
+Pitchford
+Pitt
+Pitts
+Plant
+Plastow
+Platt
+Platts
+Pledger
+Plouvin
+Plumb
+Plummer
+Pocock
+Pointer
+Pole
+Pollard
+Pollock
+Polson
+Pomeroy
+Pomphrey
+Pond
+Pooke
+Poole
+Poon
+Pope
+Porter
+Potter
+Potts
+Poulter
+Poulton
+Pounder
+Povey
+Powell
+Power
+Powers
+Powis
+Powles
+Poyser
+Pratt
+Preece
+Prendergast
+Prentice
+Prescott
+Preston
+Prevost
+Price
+Prime
+Prince
+Pringle
+Prior
+Pritchard
+Privett
+Probert
+Procter
+Proctor
+Prosser
+Provan
+Pryor
+Pugh
+Pullen
+Purcell
+Purkis
+Purnell
+Purse
+Purvis
+Putt
+Pyle
+Quigley
+Quinlivan
+Quinn
+Quinnell
+Quinton
+Quirk
+Quirke
+Rackham
+Radcliffe
+Radford
+Radley
+Raeburn
+Rafferty
+Rahman
+Raine
+Rainey
+Rainford
+Ralph
+Ralston
+Ramm
+Rampling
+Ramsay
+Ramsden
+Ramsey
+Rand
+Randall
+Randle
+Ranger
+Rankin
+Ranks
+Rann
+Ransom
+Ranson
+Rapson
+Rashid
+Ratcliffe
+Raval
+Raven
+Ravenscroft
+Rawlings
+Rawlinson
+Rawsthorne
+Raymond
+Rayner
+Read
+Reade
+Reader
+Reading
+Readle
+Readman
+Reardon
+Reasbeck
+Reay
+Redden
+Redding
+Reddy
+Redfern
+Redhead
+Redin
+Redman
+Redmond
+Redwood
+Reed
+Rees
+Reese
+Reeve
+Reeves
+Regan
+Regent
+Rehman
+Reid
+Reilly
+Reisser
+Render
+Renna
+Rennalls
+Rennie
+Renshaw
+Renwick
+Reveley
+Reyes
+Reygan
+Reynolds
+Rhoades
+Rhodes
+Rhys
+Ricci
+Rice
+Rich
+Richards
+Richardson
+Riches
+Richman
+Richmond
+Richter
+Rick
+Rickard
+Rickards
+Rickett
+Ricketts
+Riddell
+Riddle
+Riddler
+Ridge
+Ridgway
+Ridgwell
+Ridle
+Ridley
+Rigby
+Rigg
+Rigley
+Riley
+Ring
+Ripley
+Rippin
+Riseborough
+Ritchie
+Rivers
+Rixon
+Roach
+Robb
+Robbins
+Robe
+Robert
+Roberts
+Robertson
+Robin
+Robins
+Robinson
+Robishaw
+Robotham
+Robson
+Roche
+Rochford
+Rockliffe
+Rodden
+Roden
+Rodger
+Rodgers
+Rodham
+Rodrigues
+Rodriguez
+Rodwell
+Roebuck
+Roff
+Roffey
+Rogan
+Rogers
+Rogerson
+Roles
+Rolfe
+Rollinson
+Roman
+Romans
+Ronald
+Ronflard
+Rook
+Rooke
+Roome
+Rooney
+Rootham
+Roper
+Ropple
+Roscoe
+Rose
+Rosenblatt
+Rosenbloom
+Ross
+Rosser
+Rossi
+Rosso
+Roth
+Rothery
+Rothwell
+Rouse
+Roussel
+Rousset
+Routledge
+Rowan
+Rowe
+Rowland
+Rowlands
+Rowley
+Rowlinson
+Rowson
+Royall
+Royle
+Rudd
+Ruff
+Rugg
+Rumbold
+Rumsey
+Ruscoe
+Rush
+Rushbrooke
+Rushby
+Rushton
+Russel
+Russell
+Russon
+Rust
+Rutherford
+Rutter
+Ryan
+Ryans
+Rycroft
+Ryder
+Sadiq
+Sadler
+Said
+Saleh
+Salisbury
+Sallis
+Salmon
+Salt
+Salter
+Sampson
+Samuel
+Samuels
+Sanchez
+Sanders
+Sanderson
+Sandison
+Sands
+Santos
+Sargent
+Saunders
+Savage
+Saville
+Sawyer
+Saxton
+Sayers
+Schmid
+Schmidt
+Schofield
+Scott
+Searle
+Seddon
+Seer
+Selby
+Sellars
+Sellers
+Senior
+Sewell
+Sexton
+Seymour
+Shackleton
+Shah
+Shakespeare
+Shand
+Shanks
+Shannon
+Sharkey
+Sharma
+Sharp
+Sharpe
+Sharples
+Shaughnessy
+Shaw
+Shea
+Shearer
+Sheehan
+Sheldon
+Shelton
+Shepherd
+Sheppard
+Sheridan
+Sherman
+Sherriff
+Sherry
+Sherwood
+Shields
+Shipley
+Short
+Shotton
+Showell
+Shuttleworth
+Silcock
+Silva
+Simmonds
+Simmons
+Simms
+Simon
+Simons
+Simpson
+Sims
+Sinclair
+Singh
+Singleton
+Sinha
+Sisson
+Sissons
+Skelly
+Skelton
+Skinner
+Skipper
+Slade
+Slater
+Slattery
+Sloan
+Slocombe
+Small
+Smallwood
+Smart
+Smit
+Smith
+Smithson
+Smullen
+Smyth
+Smythe
+Sneddon
+Snell
+Snelling
+Snow
+Snowden
+Snowdon
+Somerville
+South
+Southern
+Southgate
+Southwick
+Sparkes
+Sparrow
+Spears
+Speed
+Speight
+Spence
+Spencer
+Spicer
+Spiller
+Spinks
+Spooner
+Squire
+Squires
+Stacey
+Stack
+Staff
+Stafford
+Stainton
+Stamp
+Stanfield
+Stanford
+Stanley
+Stannard
+Stanton
+Stark
+Steadman
+Stedman
+Steel
+Steele
+Steer
+Steere
+Stenhouse
+Stephen
+Stephens
+Stephenson
+Sterling
+Stevens
+Stevenson
+Steward
+Stewart
+Stock
+Stocker
+Stockley
+Stoddart
+Stokes
+Stokoe
+Stone
+Stoppard
+Storer
+Storey
+Storr
+Stott
+Stout
+Strachan
+Strange
+Street
+Stretton
+Strickland
+Stringer
+Strong
+Stroud
+Stuart
+Stubbs
+Stuckey
+Sturgess
+Sturrock
+Styles
+Sugden
+Sullivan
+Summers
+Sumner
+Sunderland
+Sutherland
+Sutton
+Swain
+Swales
+Swan
+Swann
+Swanson
+Sweeney
+Sweeting
+Swift
+Sykes
+Sylvester
+Symes
+Symonds
+Taggart
+Tailor
+Tait
+Talbot
+Tallett
+Tamber
+Tang
+Tanner
+Tansey
+Tansley
+Tappin
+Tapping
+Tapscott
+Tarr
+Tarrant
+Tasker
+Tate
+Tatlock
+Tatlow
+Tatnell
+Taurel
+Tayler
+Taylor
+Teague
+Teal
+Teale
+Teasdale
+Tedd
+Telford
+Tell
+Tellis
+Tempest
+Templar
+Temple
+Templeman
+Templeton
+Tennant
+Terry
+Thackeray
+Thackray
+Thake
+Thatcher
+Thelwell
+Thirlwall
+Thirlway
+Thirlwell
+Thistlethwaite
+Thom
+Thomas
+Thomason
+Thompson
+Thoms
+Thomson
+Thonon
+Thorley
+Thorndyke
+Thorne
+Thornes
+Thornhill
+Thornley
+Thornton
+Thorp
+Thorpe
+Thurbon
+Thurgood
+Thurling
+Thurlow
+Thurman
+Thurston
+Tickner
+Tidmarsh
+Tierney
+Till
+Tillett
+Tilley
+Tilson
+Tilston
+Timberlake
+Timmins
+Timms
+Timney
+Timson
+Tindall
+Tindell
+Tinker
+Tinkler
+Tinsley
+Tipping
+Tippins
+Tips
+Tisdall
+Titmarsh
+Titmus
+Titmuss
+Titterington
+Toal
+Tobin
+Tocher
+Todd
+Tohill
+Toland
+Tolley
+Tollis
+Tolmay
+Tomas
+Tombs
+Tomes
+Tomkins
+Tomlin
+Tomlinson
+Tompkin
+Tompkins
+Toms
+Tong
+Tonge
+Tonks
+Tonner
+Toomer
+Toomey
+Topham
+Topley
+Topliss
+Topp
+Torney
+Torrance
+Torrens
+Torres
+Tosh
+Totten
+Toucet
+Tovar
+Tovey
+Towell
+Towers
+Towle
+Townend
+Towns
+Townsend
+Townsley
+Tozer
+Trafford
+Train
+Trainor
+Trattles
+Travers
+Travill
+Travis
+Traynor
+Treble
+Trennery
+Trent
+Treseder
+Trevor
+Trew
+Trickett
+Trigg
+Trimble
+Trinder
+Trollope
+Troon
+Trotman
+Trott
+Trueman
+Truman
+Trump
+Truscott
+Tuck
+Tucker
+Tuckey
+Tudor
+Tuffnell
+Tufnall
+Tugwell
+Tully
+Tunks
+Tunstall
+Turford
+Turke
+Turkington
+Turland
+Turnbull
+Turner
+Turney
+Turnham
+Turnock
+Turrell
+Turton
+Turvey
+Tuthill
+Tuttle
+Tutton
+Tweddle
+Twigg
+Twiggs
+Twine
+Tyler
+Tyman
+Tyne
+Tyrer
+Tyrrell
+Uddin
+Ullman
+Ullmann
+Ulyatt
+Umney
+Underdown
+Underhill
+Underwood
+Unsworth
+Unwin
+Upfield
+Upjohn
+Upsdell
+Upson
+Upton
+Urwin
+Utley
+Utterson
+Uttley
+Utton
+Uttridge
+Vale
+Valentine
+Vallance
+Vallins
+Vallory
+Valmary
+Vancoller
+Vane
+Vann
+Vanstone
+Vanwell
+Vardy
+Varey
+Varley
+Varndell
+Vass
+Vaughan
+Vaughn
+Veale
+Veasey
+Veevers
+Veitch
+Velds
+Venables
+Ventura
+Verdon
+Verell
+Verney
+Vernon
+Vicary
+Vicens
+Vickars
+Vickerman
+Vickers
+Vickery
+Victor
+Vikers
+Villiger
+Villis
+Vince
+Vincent
+Vine
+Viner
+Vines
+Viney
+Vinicombe
+Vinny
+Vinton
+Virgo
+Voakes
+Vockins
+Vodden
+Vollans
+Voyse
+Vyner
+Wade
+Wadham
+Waghorn
+Wagstaff
+Wain
+Wainwright
+Waite
+Wakefield
+Wakeford
+Wakeham
+Wakelin
+Waldron
+Wale
+Wales
+Walkden
+Walker
+Wall
+Wallace
+Waller
+Walling
+Wallis
+Walls
+Walmsley
+Walpole
+Walsh
+Walshe
+Walter
+Walters
+Walton
+Wane
+Wang
+Warburton
+Warby
+Ward
+Warden
+Wardle
+Ware
+Wareing
+Waring
+Warn
+Warner
+Warren
+Warriner
+Warrington
+Warwick
+Water
+Waterfield
+Waterhouse
+Wateridge
+Waterman
+Waters
+Waterson
+Watkins
+Watkinson
+Watling
+Watson
+Watt
+Watters
+Watts
+Waugh
+Wears
+Weasley
+Weaver
+Webb
+Webber
+Webster
+Weeks
+Weir
+Welch
+Weldon
+Weller
+Wellington
+Wellman
+Wells
+Welsh
+Welton
+Were
+Werner
+Werrett
+West
+Western
+Westgate
+Westlake
+Weston
+Westwell
+Westwood
+Whalley
+Wharton
+Wheatcroft
+Wheatley
+Wheeldon
+Wheeler
+Whelan
+Whitaker
+Whitby
+White
+Whiteford
+Whitehead
+Whitehouse
+Whitelaw
+Whiteley
+Whitfield
+Whitham
+Whiting
+Whitley
+Whitlock
+Whitmore
+Whittaker
+Whittingham
+Whittington
+Whittle
+Whittley
+Whitworth
+Whyte
+Wickens
+Wickham
+Wicks
+Widdows
+Widdowson
+Wiggins
+Wigley
+Wilcox
+Wild
+Wilde
+Wildman
+Wileman
+Wiles
+Wilkes
+Wilkie
+Wilkin
+Wilkins
+Wilkinson
+Wilks
+Wilkshire
+Will
+Willett
+Willetts
+Williams
+Williamson
+Willis
+Wills
+Willson
+Wilmot
+Wilson
+Wilton
+Wiltshire
+Winder
+Windsor
+Winfer
+Winfield
+Winman
+Winn
+Winship
+Winstanley
+Winter
+Wintersgill
+Winward
+Wise
+Wiseman
+Wither
+Withers
+Wolf
+Wolfe
+Wolstencroft
+Wong
+Wood
+Woodcock
+Woodford
+Woodhall
+Woodham
+Woodhams
+Woodhead
+Woodhouse
+Woodland
+Woodley
+Woods
+Woodward
+Wooldridge
+Woollard
+Woolley
+Woolnough
+Wootton
+Worgan
+Wormald
+Worrall
+Worsnop
+Worth
+Worthington
+Wotherspoon
+Wragg
+Wraight
+Wray
+ren
+Wrench
+Wrenn
+Wrigglesworth
+Wright
+Wrightson
+Wyatt
+Wyer
+Yabsley
+Yallop
+Yang
+Yapp
+Yard
+Yardley
+Yarker
+Yarlett
+Yarnall
+Yarnold
+Yarwood
+Yasmin
+Yates
+Yeadon
+Yeardley
+Yeardsley
+Yeates
+Yeatman
+Yeldon
+Yeoman
+Yeomans
+Yetman
+Yeung
+Yoman
+Yomkins
+York
+Yorke
+Yorston
+Youlden
+Young
+Younge
+Younis
+Youssouf
+Yule
+Yusuf
+Zaoui
diff --git a/src/neuralnetwork/generate_alphabets.py b/src/neuralnetwork/generate_alphabets.py
new file mode 100644
index 0000000..0b1e18e
--- /dev/null
+++ b/src/neuralnetwork/generate_alphabets.py
@@ -0,0 +1,44 @@
+import training
+import os
+import sys
+
+if __name__ == "__main__":
+
+    # List all the directories containing country datasets to populate the countries dictionary
+    countries = training.get_countries()
+
+    for c, country in countries.items():
+        print(f"processing {c}...", end="")
+        sys.stdout.flush()
+
+        letters = {}
+
+        # get all the names in a country's dataset
+        all_names = country.get_all()
+
+        # iterate through all letters in the all of the names
+        for name in all_names:
+
+            # preprocess the name
+            name = country.preprocess(name)
+
+            for letter in name:
+                if letter in letters:
+                    letters[letter] += 1
+                else:
+                    letters[letter] = 1
+
+        print(f" found {len(letters)} in {len(all_names)} names... ", end="")
+        sys.stdout.flush()
+
+        # sort the letters by occurrence
+        letters_sorted = [l for l in letters]
+        letters_sorted.sort()
+        # output sorted letters to a file
+        with open(os.path.join(country.path, "alphabet.txt"), "w") as file:
+            for letter in letters_sorted:
+                file.write(letter)
+                file.write("\n")
+
+        print("saved!")
+        sys.stdout.flush()
diff --git a/src/neuralnetwork/rnn.py b/src/neuralnetwork/rnn.py
new file mode 100644
index 0000000..0662394
--- /dev/null
+++ b/src/neuralnetwork/rnn.py
@@ -0,0 +1,329 @@
+import random
+import time
+import math
+import torch
+import torch.nn as nn
+
+import warnings
+import sys
+
+import copy
+
+from util import AtomicNumber
+
+PRINT_INFORMATION_SECONDS = 2
+num_processes = 12
+
+#ignore warnings
+warnings.filterwarnings('ignore')
+
+
+if "--disable-cuda" in sys.argv:
+    cuda = False
+else:
+    cuda = torch.cuda.is_available()
+
+print(f"CUDA is {'enabled' if cuda else 'disabled'}")
+if cuda:
+    print("CUDA devices:")
+    for device_index in range(torch.cuda.device_count()):
+        print(f"{device_index}|\t{torch.cuda.get_device_name(device_index)}")
+
+device = torch.device("cuda") if cuda else torch.device("cpu")
+
+class RNN(nn.Module):
+    def __init__(self, input_size, hidden_size, output_size):
+        super(RNN, self).__init__()
+        self.hidden_size = hidden_size
+        self.output_size = output_size
+
+        # create the input, hidden and output linear transformation branches
+        self.input_to_hidden = nn.Linear(input_size + hidden_size, hidden_size, device=device)
+        self.input_to_output = nn.Linear(input_size + hidden_size, output_size, device=device)
+        self.output_to_output = nn.Linear(hidden_size + output_size, output_size, device=device)
+
+        # initialise a dropout function to be used on output data
+        self.dropout = nn.Dropout(0.1)
+
+        # initialise the softmax function to be used on output data
+        self.softmax = nn.LogSoftmax(dim=1)
+            
+        # do not introduce any randomness by default
+        self.random_factor = 0
+
+
+    def forward(self, inputs, hidden):
+        # combine the input layer with the hidden layer to create the output layer and new hidden layer
+        input_combined = torch.cat((inputs, hidden), 1)
+        hidden = self.input_to_hidden(input_combined)
+        output = self.input_to_output(input_combined)
+        output_combined = torch.cat((hidden, output), 1)
+
+        output = self.output_to_output(output_combined)
+        # apply the functions to the output data
+        output = self.dropout(output)
+        output = self.softmax(output)
+        
+        # add noise to the output, based on self.random_factor
+        if self.random_factor > 0:
+            # create a fully random tensor
+            random_tensor = torch.randn(self.output_size)
+            output = torch.add(output, random_tensor, alpha=self.random_factor)
+
+        return output, hidden
+
+    def initHidden(self):
+        # The hidden layer should be tensor with the length that we've specified
+        return torch.zeros(1, self.hidden_size, device=device)
+
+# instantiate the function to use to calculate loss
+#   we will use Mean Squared Error between the 
+criterion = nn.NLLLoss()
+
+# define the learning rate, to begin with, we can use 0.0005
+learning_rate = 0.0005
+
+"""Train a neural network on a single input name
+    Args:
+        rnn: (RNN) the rnn to train
+        input_tensors: (tensor) The input tensor: a one-hot-encoding from the first letter to the last letter, excluding the end of string marker
+        output_tensors: (tensor) The input tensor: a one-hot-encoding from the second letter to the end of the input data
+    Returns:
+        output: (tensor) the output of the training
+        loss:   (float)  the loss of the training
+"""
+def train_rnn(rnn, input_tensor, target_tensor):
+    # unsqueeze the target tensor, 
+    target_tensor.unsqueeze_(-1)
+    
+    # reset the parameters of the neural network
+    hidden = rnn.initHidden()
+    rnn.zero_grad()
+
+    # initiate an float called loss, this will store the error between each iteration output and its target
+    loss = 0
+    for i in range(input_tensor.size(0)):
+        output, hidden = rnn(input_tensor[i], hidden)
+
+        # calculate the error and add it to the overall loss
+        l = criterion(output, target_tensor[i])
+        loss += l
+
+    loss.backward()
+
+    # adjust the parameters of the rnn accordingly
+    for p in rnn.parameters():
+        p.data.add_(-learning_rate, p.grad.data)
+
+    return output, loss.item() / input_tensor.size(0)
+
+"""Create the input tensor for a name, a one hot matrix from the first letter to last letter (excluding EOS)
+    Args:
+        name: (str[]) an array of the letters in the name, can also be supplied as a string literal
+        alphabet: (str[]) The alphabet to use while encoding the name, an array starting with a "NULL" character and ending in an "EOS" character
+        value: (float) (default=1) The value to use for the "1" representing the letter 
+    Returns:
+        tensor: (tensor) the input tensor for the given name
+"""
+def input_tensor(name, alphabet, value=1):
+    tensor = torch.zeros(len(name), 1, len(alphabet), device=device)
+
+    #iterate through each letter in the name
+    for li in range(len(name)):
+        letter = name[li]
+        # If the letter isn't in the alphabet, use the first "NULL" character
+        index = alphabet.index(letter) if letter in alphabet else 0 
+
+        tensor[li][0][index] = value
+    
+    return tensor
+
+"""Create the target tensor for a name, a long tensor from the second letter to the EOS
+    Args:
+        name: (str[]) an array of the letters in the name, can also be supplied as a string literal
+        alphabet: (str[]) The alphabet to use while encoding the name, an array starting with a "NULL" character and ending in an "EOS" character
+    Returns:
+        tensor: (tensor) the input tensor for the given name
+"""
+def target_tensor(name, alphabet):
+    indexes = []
+    for li in range(1, len(name)):
+        letter = name[li]
+        index = alphabet.index(letter) if letter in alphabet else 0 
+        indexes.append(index)
+
+    # and add the end of string character
+    indexes.append(len(alphabet) - 1) 
+
+    #legacy tensor needs to be made this way
+    if cuda:
+        return torch.cuda.LongTensor(indexes)
+    else:
+        return torch.LongTensor(indexes)
+
+
+"""Train a neural network on a list of names with a given alphabet
+    Args: 
+        rnn (RNN): the neural network to train on
+        names: (str[]) the list of names to train on
+        alphabet: (str[]) the alphabet to use to encode characters
+        iterations: (int) (default=10000) The number of iterations of training that should be done
+"""
+def learn_names(rnn, names, alphabet, iterations=100000, num_processes=12):
+    
+    # keep track of total time spent training by knowing when we started training
+    start = time.time()
+
+    # define the number of iterations per process
+    iters_per_process = int(iterations/num_processes) 
+
+    processes = []
+
+    # keep track of the total loss
+    total_loss = AtomicNumber()
+
+    # keep track of total number of completed iterations
+    completed_iterations = AtomicNumber()
+
+    # keep track of the last time that the information was printed
+    #   this way we can print every x seconds
+    last_print = AtomicNumber()
+
+    print(f"Training on {len(names)} names...")
+
+    # spawn processes, each running the _train function
+    torch.multiprocessing.spawn(_train, args=(rnn, names, alphabet, iters_per_process,
+            total_loss, completed_iterations, last_print, start, iterations),
+            nprocs=num_processes,
+            join=True)
+    print()
+
+"""Thread function to use when multiprocessing learn_names
+
+"""
+def _train(rank, rnn, names, alphabet, iterations, 
+            total_loss, completed_iterations, last_print,
+            start, total_iterations):
+    for i in range(1, iterations+1):
+        try:
+            # choose a random name to train on
+            name = random.choice(names) 
+
+            # create the input and trainint tensors
+            input_name_tensor = input_tensor(name, alphabet)
+            target_name_tensor = target_tensor(name, alphabet)
+
+            # train the rnn on the input and target tensors 
+            output, loss = train_rnn(rnn, input_name_tensor, target_name_tensor)
+            total_loss.increment(loss)
+
+            # increment number of completed iterations
+            completed_iterations.increment()
+
+            # to prevent overloading the console, potentially slowing down the training process,
+            #   only print information every PRINT_INFORMATION_SECONDS
+            if time.time() - last_print.get() > PRINT_INFORMATION_SECONDS:
+                # set last print to now to prevent other threads from also printing
+                last_print.set(time.time())
+
+                # calculate and display information
+                seconds_elapsed = time.time() - start
+                time_elapsed = "%dm %ds" % (math.floor(seconds_elapsed / 60), seconds_elapsed % 60)
+
+                percentage = completed_iterations.get() / total_iterations * 100
+
+                # print information on the same line as before
+                print("\r%s (%d %d%%) %.4f" % (time_elapsed, completed_iterations.get(), percentage, loss), end="")
+        except:
+            pass
+
+
+"""Sample a random name from the network using a starting letter
+    Args:
+        rnn: (RNN) the neural network to sample from
+        alphabet: (str[]) the alphabet to use to decode the outputs from the network
+        start_letter: (str) the letter to use to start the neural network
+        max_length: (int) (default=50) the maximum length for a name
+    Returns:
+        output_name: (str) the characters that the rnn has generated from the starting letter
+"""
+def sample(rnn, alphabet, start_letter, max_length=50):
+    # disable gradient calculation
+    #with torch.no_grad():
+        # create the input tensor from the start letter, using a randomized value
+        #random_value = random.random()
+        random_value = 1 
+        sample_input = input_tensor(start_letter, alphabet, value=random_value)
+    
+        rnn.dropout(sample_input)
+
+        # reset hidden layer
+        hidden = rnn.initHidden()
+
+        output_name = [start_letter]
+    
+        # use a max length to prevent names from being too long
+        for i in range(max_length): 
+            # call the rnn for the next letter
+            output, hidden = rnn(sample_input[0], hidden)
+            
+            top_v, top_i = output.topk(1)
+            top_i = top_i[0][0]
+
+            if top_i == len(alphabet)-1: # EOS has been reached
+                break;
+            else: 
+                # append next letter to output
+
+                letter = alphabet[top_i]
+                output_name.append(letter)
+                
+                sample_input = input_tensor(letter, alphabet)
+
+        return output_name
+
+
+import warnings
+# testing
+if __name__ == "__main__":
+    with warnings.catch_warnings():
+        warnings.simplefilter("ignore")
+
+        english_alphabet = [c for c in " abcdefghijklmnopqrstuvwxyz"]
+        english_alphabet.append("") # add the EOS character
+
+
+        option = input("(t)rain or (s)ample?")
+        if option == "t":
+
+            names = []
+            with open("data/datasets/usa/surname.txt", "r") as datafile:
+                # convert all names to lowercase and remove newline character
+                names = [name[:-1].lower() for name in datafile.readlines()]
+
+            # create the neural network with a hidden layer of size 128
+            rnn = RNN(len(english_alphabet), 128, len(english_alphabet))
+            
+            # transfer to cuda if cuda is enabled
+            if cuda:
+                rnn.cuda()
+
+            def provide_name():
+                return random.choice(names)
+
+            learn_names(rnn, names, english_alphabet, iterations=100000, num_processes=12)
+            print()
+
+
+            torch.save(rnn, "data/english_names.pt")
+        elif option == "s":
+            rnn = torch.load("data/english_names.pt")
+            if cuda:
+                rnn.cuda()
+            rnn.eval()
+            rnn.random_factor = 0.7
+
+            for start_letter in [i for i in "abcdefghijklmnopqrstuvwxyz"]:
+                print(sample(rnn, english_alphabet, start_letter))
+        else:
+            print("invalid option!")
diff --git a/src/neuralnetwork/training.py b/src/neuralnetwork/training.py
new file mode 100644
index 0000000..85c6dbd
--- /dev/null
+++ b/src/neuralnetwork/training.py
@@ -0,0 +1,373 @@
+import os
+import types
+import json
+import random
+
+from util import *
+from rnn import *
+
+cuda = False
+num_processes = 12
+
+
+class Country:
+    def __init__(self, path):
+        self.path = path
+        self.datasets = {
+            "female": os.path.join(path, "female.txt"),
+            "male": os.path.join(path, "male.txt"),
+            "surname": os.path.join(path, "surname.txt"),
+        }
+
+        # initialise the pre and post proccess function lists
+        self.pre_process = []
+        self.post_process = []
+
+        # load the data file
+        self.load_data()
+
+        # load the alphabet file
+        self.alphabet = self.load_alphabet()
+
+        # initialise the rnn models
+        hidden_size = 128
+        self.rnn = {}
+
+        for dataset in self.datasets:
+            self.rnn[dataset] = RNN(
+                len(self.alphabet), hidden_size, len(self.alphabet))
+
+    """ Load the alphabet from the alphabet file
+        Returns:
+            alphabet: (str[]) the list of the letters/characters to use while training
+    """
+
+    def load_alphabet(self):
+        alphabet_path = os.path.join(self.path, "alphabet.txt")
+
+        # check if the alphabet file exists, if not, raise an exception
+        if os.path.exists(alphabet_path):
+            with open(alphabet_path, "r") as alphabet_file:
+                # Split the file by lines: on letter/character should be on each line
+                letters = alphabet_file.read().split("\n")
+                return letters
+        else:
+            raise Exception(
+                f"The alphabet file {alphabet_path} could not be found")
+            return []
+
+    """ load the data from the data file
+    """
+
+    def load_data(self):
+        data_path = os.path.join(self.path, "data.json")
+        if os.path.exists(data_path):
+            with open(data_path, "r") as data_file:
+                j = json.loads(data_file.read())
+
+                # match the imported global function with the ones listed in the json file
+                for pre in j["pre"]:
+                    if pre in globals():
+                        func = globals()[pre]
+
+                        # check if the requested object is a function
+                        if type(func) is types.FunctionType:
+                            self.pre_process.append(func)
+                        else:
+                            raise Exception(
+                                f"The function '{pre}' is not a function")
+                    else:
+                        # If the function was not loaded, throw an exception
+                        raise Exception(
+                            f"The function '{pre}' was not loaded or does not exist")
+
+                for post in j["post"]:
+                    if post in globals():
+                        func = globals()[post]
+
+                        # check if the requested object is a function
+                        if type(func) is types.FunctionType:
+                            self.post_process.append(func)
+                        else:
+                            raise Exception(
+                                f"The function '{post}' is not a function")
+                    else:
+                        # If the function was not loaded, throw an exception
+                        raise Exception(
+                            f"The function '{post}' was not loaded or does not exist")
+
+        else:
+            # load the default pre and post processing functions
+            self.pre_process = [uncapitalise]
+            self.post_process = [deserialise, capitalise]
+
+    """ List all the names from a given category file
+        Args:
+            category: (str) the category to select names from
+        Returns:
+            data: (str[]) an array containing all of the names from the given category file
+    """
+
+    def get_names(self, category):
+        with open(self.datasets[category], "r") as datafile:
+            return [name for name in datafile.read().split("\n")]
+
+    """ List all names in all categories
+        Returns:
+            data: (str[]) an array with all of the names in this country's datasets
+    """
+
+    def get_all(self):
+        return [name for k in self.datasets for name in self.get_names(k)]
+
+    """ Pre-process a name for training
+        Args:
+            name: the name loaded from the dataset
+        Returns:
+            name: the name after being processed
+    """
+
+    def postprocess(self, name):
+        for f in self.post_process:
+            name = f(name)
+        return name
+
+    """ Post-process a name after sampling
+        Args:
+            name: the name output from the recurrent neural network
+        Returns:
+            name: the name after being processed
+    """
+
+    def preprocess(self, name):
+        for f in self.pre_process:
+            name = f(name)
+        return name
+
+    """ Train a neural network on the given dataset
+        Args:
+            category: (str) the category to sample training names from
+    """
+
+    def train(self, category):
+        # select the RNN model to be training on
+        rnn = self.rnn[category]
+
+        # load names from that dataset and pre proccess them
+        print("preprocessing names...")
+        names = [self.preprocess(name) for name in self.get_names(category)]
+        print(f"processed {len(names)} names!")
+
+        # calculate optimum number of iterations (using 80% of whole dataset)
+        iters = int(len(names) * 0.8)
+
+        # start training
+        learn_names(rnn, names, self.alphabet, iterations=iters,
+                    num_processes=num_processes)
+
+    """ Sample a name from the neural network with a given starting letter
+        Args:
+            category: (str) the category to sample generated names from
+        Returns:
+            name: the output from the neural network
+    """
+
+    def sample(self, category, start_letter):
+
+        # select the RNN model to be sampling from
+        rnn = self.rnn[category]
+
+        # set the random factor of the RNN to randomise names that are generated
+        rnn.random_factor = 0.7
+
+        # call the rnn sample function to generate a single name
+        name = sample(rnn, self.alphabet, start_letter)
+
+        # post process the name and return
+        return self.postprocess(name)
+
+    """ Load the rnn from its file
+        Args:
+            category: (str) the category to load
+            parent_directory: (str) where to find the model
+    """
+
+    def load_rnn(self, category, parent_directory):
+        model_file = os.path.join(parent_directory, f"{category}.pt")
+        self.rnn[category] = torch.load(model_file)
+
+    """ Save the rnn of a given category to its file
+        Args:
+            category: (str) the category to save
+            parent_directory: (str) the directory to save the model file to  
+    """
+
+    def save_rnn(self, category, parent_directory):
+        rnn = self.rnn[category]
+        model_file = os.path.join(parent_directory, f"{category}.pt")
+        torch.save(rnn, model_file)
+
+
+def get_countries():
+    return {
+        country: Country(os.path.join(countries_path, country)) for country in os.listdir(countries_path) if os.path.isdir(os.path.join(countries_path, country))
+    }
+
+
+""" train all of the datasets from a specific country
+    Args:
+        country: (Country) 
+"""
+
+
+def train_country(country, name):
+    datasets = country.datasets
+    for dataset in datasets:
+        print(f"Training {dataset} in {name}")
+        country.train(dataset)
+
+        print(f"Finished training on {dataset}... saving...", end="")
+        path = os.path.join("data", "models", name)
+
+        # check if the path already exists before trying to make directories
+        if not os.path.exists(path):
+            os.makedirs(path)
+
+        country.save_rnn(dataset, path)
+        print("saved!")
+
+
+def sample_country(country, country_name, number_of_samples=10000):
+
+    datasets = country.datasets
+    for dataset in datasets:
+
+        # ensure that the model exists before sampling
+        path = os.path.join("data", "models", country_name)
+        if os.path.exists(os.path.join(path, dataset + ".pt")):
+
+            # load the country's rnn
+            country.load_rnn(dataset, path)
+
+            # load the names from the country's dataset, and pre-process them
+            names = [country.preprocess(name)
+                     for name in country.get_names(dataset)]
+
+            # make a dictionary full of start letters and their frequency
+            start_letters = {}
+
+            for name in names:
+                if len(name) > 0:
+                    start_letter = name[0]
+
+                    # if the start letter isn't already in the dictionary, add it with value 1
+                    if start_letter in start_letters:
+                        start_letters[start_letter] += 1
+                    else:
+                        start_letters[start_letter] = 1
+
+            # turn each integer count into a float where: letter_weight=frequency/total_names
+            total = len(names)
+
+            for letter in start_letters:
+                weight = float(start_letters[letter] / total)
+                start_letters[letter] = weight
+
+            # sample names from the RNN
+            sampled_names = []
+
+            for i in range(number_of_samples):
+                try:
+                    letter = weighted_choice(start_letters)
+                    sample = country.sample(dataset, letter)
+                    sampled_names.append(sample)
+                except:
+                    pass
+
+            # remove duplicate names
+            sampled_names = list(dict.fromkeys(sampled_names))
+
+            # create a sqlite connection
+            connection = sqlite3.connect(database)
+
+            # always close the connection when finished
+            with connection:
+                cursor = connection.cursor()
+                for name in sampled_names:
+                    sql = "INSERT INTO names(Name, Origin, Category) VALUES(?, ?, ?)"
+
+                    # insert the current name and options into the database
+                    cursor.execute(sql, (name, country_name, dataset))
+
+                # commit changes and save the database
+                connection.commit()
+
+            print(
+                f"Saved {len(sampled_names)} names for {country_name}/{dataset}")
+
+        else:
+            print(f"the model: {country_name}/{dataset} was not found.")
+
+
+countries_path = "data/datasets"
+database = os.path.join("data", "names.db")
+if __name__ == "__main__":
+    with warnings.catch_warnings():
+        warnings.simplefilter("ignore")
+
+        # allow processes on this model to share memory
+        torch.multiprocessing.set_start_method('spawn')
+
+        # List all the directories containing country datasets to populate the countries dictionary
+        countries = get_countries()
+
+        country_count = len(countries)
+        # Display debug information
+        print(f"Loaded {country_count} countries!")
+
+        # list all countries in neat collumns
+        collumns = 4
+        width = 14
+        i = 0
+        for country in countries:
+            i += 1
+
+            # print the country and then its index
+            print(country, end="")
+
+            # organise into rows and collumns
+            if i % collumns == 0:
+                print("")
+            else:
+                # separate collumns with spaces
+                print(" " * (width - len(country)), end="")
+
+        # keep asking until the country selection is valid
+        good_selection = False
+        while not good_selection:
+            # prompt user to select a country to train, or train all
+            country_selection = input(
+                "select the name of a country to train on, or (all) to train on all countries: ")
+
+            good_selection = True
+            selected_countries = []
+
+            # if the user selected all, then add all countries to list, if not, add the selected country
+            if country_selection.lower() == "all":
+                [selected_countries.append(country) for country in countries]
+            elif country_selection.lower() in countries:
+                selected_countries.append(country_selection)
+            else:
+                print("Country not found, try again")
+                good_selection = False
+
+            choice = input("(t)rain on data, or (s)ample from weights?")
+
+            if choice.lower()[0] == "t":
+                for country in selected_countries:
+                    train_country(countries[country], country)
+
+            elif choice.lower()[0] == "s":
+                create_table(database)
+                for country in selected_countries:
+                    sample_country(countries[country], country)
diff --git a/src/neuralnetwork/util.py b/src/neuralnetwork/util.py
new file mode 100644
index 0000000..268819e
--- /dev/null
+++ b/src/neuralnetwork/util.py
@@ -0,0 +1,185 @@
+import sqlite3
+import tensorflow as tf
+from pincelate import Pincelate
+from multiprocessing import Value
+import random
+
+"""Atomic Number
+A multiprocessing-safe Number that you can increment and set a value to.
+"""
+class AtomicNumber:
+    def __init__(self, initial=0):
+        # set the initial value of the number
+        self._v = Value("d", initial)
+
+        # use python thread locks
+        self._lock = self._v.get_lock()
+
+    def set(self, num):
+        with self._lock:
+            # set the value of the number and return it
+            self._v.value = num
+            return self._v.value
+
+    def increment(self, num=1):
+        with self._lock:
+            # increase the value of the number and then return it
+            self._v.value += num
+            return self._v.value
+
+    def get(self):
+        return self._v.value
+
+
+""" Capitalise the first letter of a name
+    Args:
+        name: (str) the name to transform
+    Returns:
+        name: (str) the output name
+"""
+
+
+def capitalise(name):
+    return str(name).capitalize()
+
+
+""" uncapitalise the first letter of a name
+    Args:
+        name: (str) the name to transform
+    Returns:
+        name: (str) the output name
+"""
+
+
+def uncapitalise(name):
+    return str(name).lower()
+
+
+# import pincelate
+
+# tell tensorflow to only log ERRORS rather than all problems
+tf.get_logger().setLevel('ERROR')
+
+pin = Pincelate()
+
+""" Transliterate names into their phonetic spelling 
+    Args:
+        name: (str) the name to transliterate
+    Returns:
+        name: (str) the pronunciation of the name as an arpabet list
+"""
+
+
+def transliterate(name):
+    output = []
+
+    # iterate through each word and sound out separately
+    for word in name.split(" "):
+        try:
+            for phoneme in pin.soundout(word):
+                output.append(phoneme)
+        except Exception as e:
+            output.append(word)
+        output.append(" ")
+
+    # remove the trailing " "
+    output.pop()
+
+    return output
+
+
+""" Transliterate phonetic spellings back into names
+    Args:
+        name: (str) the pronunciation of the name as an arpabet list
+    Returns:
+        name: (str) a guessed spelling of the given phoneme list
+"""
+
+
+def reverse_transliterate(name):
+    words = []
+
+    current_word = []
+    # iterate through all phonemes, spliting groups between " " into words
+    for phoneme in name:
+        if phoneme == " ":
+            words.append(current_word)
+
+            # reset current word
+            current_word = []
+        else:
+            current_word.append(phoneme)
+
+    # add whats left of the current word to the list of words
+    words.append(current_word)
+
+    # spell each word separately
+    spellings = [pin.spell(word) for word in words]
+    return " ".join(spellings)
+
+
+"""Load random line from a given filename
+"""
+
+
+def get_random_line(file_name):
+    total_bytes = os.stat(file_name).st_size
+    random_point = random.randint(0, total_bytes)
+    file = open(file_name)
+    file.seek(random_point)
+    file.readline()  # skip this line to clear the partial line
+    return file.readline()
+
+
+""" Concatenate elemnts of a list
+    Args:
+        name: (str[]) the letters of a name in an array 
+    Returns:
+        name: (str) 
+"""
+
+
+def deserialise(name):
+    return "".join(name)
+
+
+""" return a random item from a dictionary of weighted items
+    Args:
+        weights: (dict) a dictionary containing the items as keys and float values as weights
+    Returns:
+        item: a random item selected from the dictionary
+"""
+
+
+def weighted_choice(weights):
+    # choose a randm number between 0 and 1
+    choice = random.uniform(0.0, 1.0)
+
+    # iterate through weights, subtracting the weight from the choice each time
+    for item, weight in weights.items():
+        choice -= weight
+
+        # if we are currently on the chosen item, return it
+        if choice < 0:
+            return item
+
+    # in case the input dictionary is incorrectly setup, return the last item
+    return list(weights)[-1]
+
+
+def create_table(database_path):
+    # connect to the database and get the cursor
+    connection = sqlite3.connect(database_path)
+
+    # always close the connection at the end
+    with connection:
+        cursor = connection.cursor()
+
+        cursor.execute("CREATE TABLE IF NOT EXISTS names (\
+                                Name TEXT,\
+                                Origin TEXT,\
+                                Category TEXT\
+                                )")
+
+        # commit the changes, saving them
+        connection.commit()