Template
50 KiB
50 KiB
In [1]:
from cltk import NLPIn [2]:
cltk_nlp = NLP(language="lat")𐤀 CLTK version '1.1.1'. Pipeline for language 'Latin' (ISO: 'lat'): `LatinNormalizeProcess`, `LatinStanzaProcess`, `LatinEmbeddingsProcess`, `StopsProcess`, `LatinLexiconProcess`.
In [5]:
# read the first file, Gallic Wars Book 1, which is in the same directory as this notebook
with open("gall1.txt") as fo:
caesar_book1 = fo.read()In [6]:
# text snippet
caesar_book1[:200]Out [6]:
'Gallia est omnis divisa in partes tres, quarum unam incolunt Belgae, aliam Aquitani, tertiam qui ipsorum lingua Celtae, nostra Galli appellantur. Hi omnes lingua, institutis, legibus inter se differun'
In [7]:
# let's get some estimates
print("Character count:", len(caesar_book1))
print("Approximate token count:", len(caesar_book1.split()))Character count: 57955 Approximate token count: 8173
In [4]:
# removing ``LatinLexiconProcess`` before running cltk_nlp.analyze because it's slow
cltk_nlp.pipeline.processes.pop(-1)
print(cltk_nlp.pipeline.processes)[<class 'cltk.alphabet.processes.LatinNormalizeProcess'>, <class 'cltk.dependency.processes.LatinStanzaProcess'>, <class 'cltk.embeddings.processes.LatinEmbeddingsProcess'>, <class 'cltk.stops.processes.StopsProcess'>]
In [9]:
# now execute NLP algorithms upon input text
# execution time is ~60 sec on a my Thinkpad T460s
%time cltk_doc = cltk_nlp.analyze(text=caesar_book1)CPU times: total: 2min 56s Wall time: 2min 16s
In [41]:
# have a look at the first 10 words
cltk_doc.tokens[:10] # note that punctuation is included hereOut [41]:
['Gallia', 'est', 'omnis', 'divisa', 'in', 'partes', 'tres', ',', 'quarum', 'unam']
In [47]:
# let's remove punctuation
caesar_tokens_no_punct = [token for token in cltk_doc.tokens if token not in ['.', ',', ':', ';']]
caesar_word_tokens_no_punct[:10]Out [47]:
['Gallia', 'est', 'omnis', 'divisa', 'in', 'partes', 'tres', 'quarum', 'unam', 'incolunt']
In [43]:
# instead of tokens(words), let's find the root words, or the "lemmata"
cltk_doc.lemmata[:10]Out [43]:
['Gallia', 'sum', 'omnis', 'divisa', 'in', 'pars', 'tres', ',', 'qui', 'unus']
In [49]:
# let's remove punctuation
caesar_lemmata_no_punct = [token for token in cltk_doc.lemmata if token not in ['.', ',', ':', ';']]
caesar_lemmata_no_punct[:10]Out [49]:
['Gallia', 'sum', 'omnis', 'divisa', 'in', 'pars', 'tres', 'qui', 'unus', 'incaleo']
In [7]:
from collections import CounterIn [60]:
# here is a dictionary of every word in the Book 1 along with how many times each word appears
caesar_word_counts = Counter(caesar_lemmata_no_punct)
caesar_word_countsOut [60]:
Counter({'Gallia': 15,
'sum': 223,
'omnis': 66,
'divisa': 2,
'in': 177,
'pars': 26,
'tres': 7,
'qui': 213,
'unus': 23,
'incaleo': 4,
'Belgae': 3,
'alius': 12,
'Aquitani': 1,
'tertius': 10,
'ipse': 44,
'lingua': 3,
'Celtae': 1,
'noster': 39,
'Galli': 1,
'appello': 9,
'is': 269,
'instituo': 3,
'lex': 3,
'inter': 17,
'se': 162,
'differo': 1,
'Gallos': 4,
'ab': 102,
'Aquitanis': 1,
'Garumna': 3,
'flumen': 21,
'Belgis': 1,
'Matrona': 1,
'et': 193,
'Sequana': 1,
'disco': 5,
'fortis': 2,
'propterea': 15,
'quod': 82,
'cultus': 2,
'atque': 75,
'humanitas': 2,
'provinciae': 8,
'longe': 7,
'absum': 8,
'minimeque': 1,
'ad': 107,
'mercator': 1,
'saepe': 5,
'commeo': 1,
'effemino': 1,
'animus': 10,
'pertineo': 6,
'importo': 1,
'proximique': 1,
'Germanis': 5,
'trans': 7,
'Rhenum': 15,
'quicum': 3,
'continenter': 2,
'bellum': 29,
'gero': 8,
'Qua': 2,
'de': 36,
'causa': 25,
'Helvetii': 23,
'quoque': 1,
'reliquus': 17,
'virtute': 10,
'praecedo': 1,
'fere': 3,
'cotidianus': 2,
'proelium': 32,
'cum': 80,
'contendo': 18,
'aut': 35,
'suus': 104,
'finis': 37,
'prohibeo': 11,
'obtineo': 7,
'dico': 33,
'initium': 3,
'capio': 6,
'Rhodano': 2,
'contineo': 5,
'Oceanum': 2,
'Belgarum': 1,
'attingo': 1,
'etiam': 17,
'Sequanis': 10,
'Helvetiis': 11,
'vergit': 1,
'septentrio': 4,
'exterior': 2,
'Galliae': 22,
'orior': 2,
'inferus': 1,
'Rheni': 3,
'specto': 3,
'sol': 2,
'Aquitania': 1,
'Pyrenaeos': 1,
'mons': 20,
'Hispaniam': 1,
'occasum': 1,
'Apud': 1,
'Helvetios': 14,
'nobilis': 6,
'ditussus': 1,
'Orgetorix': 8,
'Is': 6,
'M.': 7,
'Messala': 2,
'[et': 1,
'P.': 2,
']': 12,
'Pisone': 3,
'consulus': 3,
'regnum': 7,
'cupiditas': 3,
'induco': 2,
'coniuratio': 1,
'nobilitas': 2,
'facio': 75,
'civitati': 1,
'persuatio': 2,
'ut': 73,
'copua': 5,
'exeo': 4,
'perfacilis': 1,
'praesto': 2,
'totus': 16,
'imperium': 8,
'potior': 3,
'hic': 50,
'faciliter': 3,
'undique': 2,
'locus': 32,
'natura': 3,
'ex': 59,
'Rheno': 1,
'latus': 1,
'altus': 3,
'ager': 16,
'Helvetium': 1,
'alter': 11,
'Iura': 1,
'Sequanos': 10,
'lacus': 2,
'Lemanno': 2,
'provinciam': 11,
'His': 4,
'res': 71,
'minus': 15,
'lates': 1,
'vagarentur': 1,
'facile': 3,
'finisimus': 3,
'infero': 11,
'possum': 65,
'homo': 21,
'bello': 1,
'cupidus': 3,
'magnus': 47,
'dolor': 3,
'adficio': 2,
'Pro': 1,
'multitudo': 11,
'autem': 8,
'pro': 14,
'gloria': 1,
'fortitudo': 1,
'angustos': 1,
'habeo': 45,
'arbitror': 6,
'longitudo': 1,
'minius': 3,
'passus': 11,
'CCXL': 1,
'latitudo': 1,
'CLXXX': 1,
'pateo': 2,
'adduco': 12,
'auctoritas': 4,
'permo': 1,
'constituo': 11,
'proficiscor': 6,
'comparo': 5,
'iumentum': 1,
'carrum': 1,
'quam': 27,
'numerus': 12,
'coemo': 1,
'sementis': 1,
'itiner': 12,
'copia': 23,
'frumentum': 13,
'suppeto': 2,
'proximus': 8,
'civitatibus': 1,
'pax': 9,
'amicitia': 11,
'confirmo': 5,
'Ad': 4,
'conficio': 8,
'biennium': 1,
'satis': 10,
'duco': 10,
'annus': 7,
'profectio': 2,
'deligo': 6,
'legatio': 4,
'civitates': 6,
'suscipio': 4,
'In': 3,
'persuadeo': 4,
'Castico': 1,
'Catamantaloedis': 1,
'filius': 4,
'Sequano': 1,
'pater': 6,
'multus': 21,
'senatus': 8,
'populus': 43,
'Romani': 30,
'amicus': 8,
'civitate': 6,
'occupo': 11,
'ante': 11,
'item': 4,
'Dumnorigi': 2,
'Haeduo': 1,
'frater': 11,
'Diviciaci': 4,
'tempus': 14,
'principatus': 4,
'magne': 4,
'plebs': 3,
'accipio': 8,
'idem': 19,
'conor': 10,
'filia': 3,
'matrimonium': 2,
'do': 20,
'Perfacile': 1,
'factus': 1,
'ille': 18,
'probo': 1,
'perficio': 3,
'civitatis': 5,
'obtendo': 1,
'non': 88,
'dubius': 1,
'quin': 6,
'suusquis': 1,
'exercitus': 27,
'regna': 1,
'concilio': 1,
'Hac': 4,
'oratio': 8,
'fides': 6,
'ius': 12,
'iuro': 5,
'per': 33,
'potens': 1,
'firmus': 2,
'spero': 2,
'indicium': 1,
'enuntio': 7,
'Moribus': 1,
'vinculis': 1,
'coego': 1,
'damno': 1,
'poena': 3,
'sequor': 7,
'oportet': 9,
'ignis': 2,
'cremoreo': 1,
'Die': 1,
'dictio': 1,
'iudicium': 4,
'familia': 2,
'mile': 14,
'decem': 1,
'unusquisque': 1,
'cogo': 5,
'cliens': 2,
'obaero': 1,
'conduco': 1,
'ne': 31,
'eripuo': 1,
'Cum': 8,
'civitas': 4,
'ob': 5,
'incito': 1,
'armis': 9,
'exsequor': 1,
'magistro': 3,
'morior': 1,
'neque': 50,
'suspicium': 1,
'mors': 3,
'consciverit': 1,
'Post': 1,
'nihil': 6,
'Ubi': 8,
'iam': 6,
'paro': 5,
'oppida': 4,
'duodecim': 1,
'vicos': 2,
'quadringo': 1,
'privata': 1,
'aedificium': 1,
'incendo': 2,
'praeter': 4,
'porto': 1,
'comburo': 1,
'domus': 14,
'reditio': 1,
'spes': 10,
'tollo': 4,
'periculum': 10,
'subeo': 2,
'mensus': 1,
'molitus': 1,
'cibarius': 1,
'quisque': 6,
'effero': 1,
'iubeo': 7,
'Persuadent': 1,
'Rauracis': 1,
'Tulingis': 1,
'Latobrigis': 1,
'utor': 32,
'consilium': 12,
'oppis': 2,
'vicisque': 1,
'exsumo': 1,
'Boiosque': 1,
'incolo': 1,
'Noricum': 1,
'transisro': 1,
'Noreiamque': 1,
'oppugno': 4,
'recipio': 10,
'socius': 6,
'ascisco': 1,
'Erant': 1,
'omnino': 7,
'duo': 10,
'itener': 5,
'angustus': 1,
'difficilis': 2,
'Iuram': 2,
'Rhodanum': 5,
'vix': 1,
'singulus': 5,
'caro': 3,
'impendo': 1,
'perpaux': 2,
'multo': 3,
'expedio': 3,
'Helvetiorum': 13,
'Allobrogum': 4,
'nuper': 3,
'paco': 1,
'Rhodanus': 2,
'fluo': 2,
'isqe': 1,
'nullus': 7,
'vado': 1,
'transeo': 13,
'Extremum': 1,
'oppidus': 4,
'proximusque': 1,
'Genava': 1,
'Ex': 4,
'oppido': 5,
'pons': 3,
'Allobrogibus': 4,
'vel': 7,
'persuatuo': 1,
'nondum': 2,
'bonum': 2,
'Romanum': 6,
'viderentur': 2,
'existimo': 12,
'vi': 1,
'cogco': 1,
'eo': 7,
'patior': 8,
'Omnus': 1,
'dies': 34,
'ripa': 4,
'Rhodani': 2,
'conveniant': 1,
'a.': 1,
'd.': 1,
'V.': 1,
'Kal.': 1,
'Apr.': 1,
'L.': 7,
'A.': 1,
'Gabinio': 1,
'Caesari': 12,
'nuntio': 6,
'iter': 16,
'maturo': 2,
'urbs': 2,
'Galliam': 13,
'ultimus': 4,
'Genavam': 2,
'pervenit': 4,
'Provinciae': 1,
'miles': 15,
'impero': 9,
'(': 4,
'legium': 2,
')': 4,
'rescindo': 1,
'adventu': 5,
'certus': 7,
'legatum': 15,
'mitto': 25,
'Nammeius': 1,
'Verucloetius': 1,
'princeps': 6,
'sine': 12,
'ullus': 4,
'maleficium': 3,
'rogo': 5,
'voluntate': 7,
'licet': 8,
'Caesar': 43,
'memoria': 6,
'teneo': 11,
'Cassium': 3,
'consul': 2,
'occis': 2,
'pulgo': 3,
'sub': 7,
'iugum': 3,
'concedo': 4,
'puto': 7,
'inimicus': 2,
'facultas': 5,
'tempero': 2,
'iniurius': 16,
'Tamen': 1,
'spatium': 5,
'intercedo': 3,
'dum': 2,
'convenirent': 1,
'respondeo': 8,
'delibero': 1,
'sumo': 4,
'si': 43,
'quis': 16,
'vellent': 5,
'April.': 1,
'reverterentur': 1,
'Interea': 1,
'legio': 17,
'miletis': 1,
'provincia': 4,
'convenerant': 1,
'influo': 2,
'Sequanorum': 7,
'XVIIII': 1,
'murus': 2,
'altitudo': 3,
'pes': 5,
'sedecim': 1,
'fossamque': 1,
'perduco': 1,
'Eo': 7,
'opus': 6,
'perfectus': 2,
'praesidium': 6,
'dispono': 1,
'castella': 1,
'communis': 5,
'invito': 2,
'venit': 2,
'lego': 7,
'reverterunt': 2,
'nego': 1,
'mos': 1,
'exemplum': 2,
'vim': 3,
'ostendo': 5,
'deiecto': 1,
'navibus': 2,
'iungo': 2,
'ratio': 6,
'complur': 2,
'vadis': 1,
'paruus': 6,
'numquam': 2,
'interdio': 1,
'saepius': 2,
'noctus': 1,
'perrumpo': 1,
'munitio': 3,
'concursus': 1,
'teles': 1,
'repuldo': 1,
'conatus': 1,
'desisto': 4,
'Relinquebatur': 1,
'via': 1,
'invitis': 1,
'propter': 12,
'angustia': 3,
'spons': 2,
'Dumnorigem': 4,
'Haeduum': 1,
'deprecator': 1,
'impetro': 5,
'Dumnorix': 2,
'gratia': 13,
'largitio': 1,
'apud': 12,
'novis': 1,
'studeo': 1,
'beneficium': 7,
'obstriho': 1,
'volebat': 2,
'Itaque': 4,
'Sequani': 3,
'renuntio': 2,
'Haeduorum': 10,
'Santonum': 1,
'Tolosatium': 1,
'intellego': 13,
'bellicosus': 1,
'maximeque': 1,
'frumentarius': 4,
'finitimus': 2,
'Ob': 2,
'T.': 2,
'Labienum': 3,
'praefico': 1,
'Italiam': 2,
'dui': 1,
'ibi': 4,
'conscribo': 2,
'circum': 3,
'Aquileiam': 1,
'hiemo': 1,
'hibernus': 3,
'educo': 4,
'Alpes': 1,
'quinque': 1,
'Ibi': 3,
'Ceutrones': 1,
'Graioceli': 1,
'Caturiges': 1,
'superior': 5,
'Compluribus': 1,
'puldeo': 3,
'Ocelus': 1,
'citer': 3,
'Vocontiorum': 1,
'septimus': 2,
'inde': 2,
'Segusiavos': 1,
'extra': 1,
'primus': 13,
'traduxo': 1,
'pervenerant': 1,
'iderque': 3,
'populo': 2,
'Haedui': 8,
'defendo': 4,
'Caesarem': 17,
'auxilium': 12,
'ita': 12,
'Romano': 10,
'mereo': 3,
'paes': 2,
'conspectus': 3,
'vastari': 1,
'liber': 5,
'[eorum': 1,
'servitutem': 2,
'abduco': 1,
'expugno': 1,
'debeo': 3,
'Ambarri': 1,
'necessarius': 3,
'consanguineus': 2,
'depopulo': 1,
'hostius': 14,
'Item': 4,
'Allobroges': 1,
'possessio': 3,
'fuga': 10,
'demonstro': 1,
'solum': 5,
'Quibus': 4,
'exspecto': 3,
'statuo': 5,
'fortuna': 5,
'socium': 1,
'consumo': 1,
'Santonos': 1,
'pervenirent': 1,
'Flumen': 1,
'Arar': 1,
'incredibilis': 2,
'lenitas': 1,
'oculus': 2,
'uter': 1,
'iudico': 6,
'ratus': 1,
'lintus': 2,
'explorator': 5,
'trado': 5,
'quartus': 4,
'vero': 3,
'citra': 1,
'Ararim': 1,
'vigilia': 5,
'castra': 40,
'profectus': 3,
'transero': 1,
'Eos': 1,
'impedio': 3,
'inopino': 1,
'adgredior': 2,
'concido': 1,
'mando': 4,
'silvas': 1,
'abdo': 2,
'pagus': 2,
'Tigurinus': 1,
'nam': 3,
'Helvetia': 1,
'quattuor': 4,
'Hic': 3,
'exedo': 2,
'interfecio': 2,
'Ita': 5,
'sive': 5,
'casus': 1,
'deus': 2,
'immortalis': 2,
'Helvetiae': 1,
'insignus': 2,
'calamitas': 5,
'persolo': 1,
'publicus': 5,
'sed': 19,
'privatas': 1,
'ultus': 1,
'socer': 1,
'Pisonis': 1,
'avum': 1,
'Pisonem': 1,
'Tigurini': 1,
'Hoc': 3,
'consequor': 3,
'Arari': 3,
'curo': 2,
'traduco': 7,
'repentinus': 1,
'commo': 2,
'XX': 3,
'aegerrime': 1,
'Divico': 2,
'Cassiano': 1,
'dux': 2,
'Caesare': 8,
'ago': 8,
'Romanus': 2,
'iturus': 1,
'ubi': 4,
'esse': 5,
'voluisset': 2,
'sin': 1,
'persequor': 1,
'perseveraret': 1,
'reminiscor': 1,
'veteris': 2,
'incommodus': 1,
'pristinus': 1,
'virtutis': 2,
'Quod': 15,
'improviso': 1,
'pag': 1,
'adoro': 1,
'ii': 3,
'fero': 8,
'magnopere': 2,
'virtuti': 1,
'tribuo': 2,
'despiceo': 1,
'ego': 3,
'magis': 4,
'dolus': 1,
'insidius': 1,
'nitor': 1,
'Quare': 1,
'committo': 10,
'constitto': 2,
'internecio': 1,
'nomen': 4,
'prodeo': 3,
'dubitatio': 1,
'commemoro': 2,
'gravius': 5,
'meritum': 1,
'accido': 8,
'aliqui': 4,
'conscius': 1,
'cavere': 1,
'decipio': 1,
'quare': 4,
'timeo': 5,
'contumelia': 1,
'oblivisci': 1,
'vellet': 6,
'num': 1,
'recentius': 1,
'tempto': 2,
'Haeduos': 10,
'Ambarros': 1,
'Allobrogas': 1,
'vexassent': 1,
'depono': 1,
'?': 9,
'victoria': 3,
'tam': 7,
'insolenter': 1,
'glorio': 1,
'quodque': 2,
'diu': 5,
'impeno': 1,
'toleo': 2,
'admiror': 1,
'Consuesse': 1,
'enim': 3,
'commutatio': 1,
'doleo': 1,
'scelus': 1,
'ulcio': 1,
'velint': 3,
'secundus': 3,
'interdum': 2,
'diuturnus': 1,
'impunitas': 1,
'tamen': 8,
'obsis': 17,
'polliceo': 1,
'Haeduis': 11,
'sociisque': 2,
'consuero': 3,
'testis': 2,
'responluo': 1,
'discedo': 5,
'Postero': 1,
'movent': 1,
'Idem': 1,
'equitasque': 3,
'mineus': 4,
'praemitto': 2,
'videant': 1,
'hos': 14,
'Qui': 5,
'cupidae': 1,
'nosus': 4,
'agmen': 3,
'insequor': 4,
'alienus': 1,
'equitas': 12,
'paucus': 7,
'cado': 1,
'Quo': 1,
'quingo': 2,
'equis': 7,
'tantus': 9,
'equitus': 8,
'propulo': 1,
'audacius': 2,
'subsisto': 1,
'agmo': 2,
'lacesso': 3,
'coepi': 9,
'praesentia': 1,
'hoso': 4,
'rapina': 1,
'pabulatio': 1,
'populatio': 1,
'circiter': 10,
'XV': 3,
'ample': 7,
'quinis': 1,
'senis': 1,
'milus': 5,
'interseo': 1,
'Interim': 2,
'cognodo': 1,
'publice': 1,
'pollicio': 4,
'flagito': 1,
'Nam': 3,
'frigus': 1,
'[': 3,
'pono': 4,
'modus': 7,
'maturus': 2,
'pabulus': 1,
'quidem': 8,
'subvexerat': 1,
'averterant': 1,
'nolo': 3,
'Diem': 1,
'confero': 9,
'comporto': 1,
'adsum': 3,
'diutius': 3,
'inster': 2,
'metior': 2,
'convocatis': 1,
'principis': 1,
'Diviciaco': 3,
'Lisco': 1,
'summus': 15,
'praeo': 3,
'vergobretum': 1,
'creo': 1,
'annuus': 1,
'vitae': 1,
'nex': 1,
'potestas': 5,
'graviter': 1,
'accuso': 2,
'necessario': 2,
'propinquus': 2,
'hostis': 5,
'sublevetur': 1,
'praesertim': 2,
'prex': 2,
'destituo': 1,
'quer': 1,
'Tum': 3,
'demum': 3,
'Liscus': 1,
'Caesaris': 7,
'antea': 3,
'taceo': 2,
'propono': 2,
'valeat': 1,
'privatim': 1,
'plus': 4,
'Hos': 1,
'seditio': 1,
'imprus': 1,
'deterreo': 2,
'Gallorum': 8,
'Romanorum': 1,
'perfero': 2,
'dubito': 3,
'[debeant': 1,
'supero': 6,
'libertas': 2,
'ero': 2,
'Ab': 1,
'coerceo': 1,
'Quin': 1,
'quanto': 1,
'Lisci': 1,
'designo': 1,
'sentio': 2,
'praesum': 5,
'iacto': 2,
'celeriter': 2,
'concilium': 6,
'dimitto': 3,
'Liscum': 1,
'retineo': 2,
'Quaerit': 1,
'solus': 4,
'conventu': 1,
'Dicit': 1,
'libere': 1,
'secretum': 2,
'quaero': 7,
'repereo': 1,
'vera': 2,
'audacium': 1,
'liberalitas': 2,
'novarum': 1,
'Complures': 1,
'portoria': 1,
'resiquuque': 1,
'vectigalia': 2,
'parvo': 1,
'pretium': 1,
'redeoueo': 1,
'contra': 3,
'audeo': 4,
'nemo': 5,
'familiaris': 4,
'augio': 1,
'largior': 1,
'equitatus': 1,
'sumptus': 1,
'semper': 1,
'aliero': 1,
'largiter': 1,
'potentia': 2,
'mater': 3,
'Biturigibus': 1,
'illic': 1,
'conloco': 5,
'uxor': 2,
'sorus': 1,
'nuptus': 1,
'Favere': 1,
'cupeo': 1,
'adfinitas': 1,
'odi': 1,
'Romanos': 2,
'deminuo': 2,
'Diviciacus': 3,
'antiquus': 2,
'honor': 2,
'restituo': 4,
'Si': 6,
'Romanis': 4,
'venire': 6,
'despero': 4,
'Reperiebat': 1,
'equester': 2,
'adversum': 2,
'Dumnorige': 2,
'perterro': 5,
'cognosco': 12,
'suspicio': 3,
'accedo': 3,
'iniussus': 1,
'inscio': 1,
'magistratus': 1,
'animadverteret': 1,
'civitatem': 3,
'animadvertere': 1,
'repugno': 1,
'studium': 1,
'voluntatem': 2,
'egregius': 2,
'iustitia': 1,
'temperantia': 1,
'cognoverat': 1,
'supplicium': 3,
'offendo': 1,
'verebatur': 1,
'prius': 4,
'quisquam': 3,
'Diviciacum': 2,
'vocari': 1,
'interpretus': 1,
'remoueo': 3,
'C.': 6,
'Valerium': 2,
'Troucillum': 1,
'conloquor': 2,
'simul': 1,
'commonefacio': 1,
'[Gallorum': 1,
'separatim': 2,
'Petit': 1,
'hortor': 1,
'offensio': 1,
'lacrima': 2,
'compleo': 2,
'obsecro': 1,
'scio': 4,
'nec': 2,
'quimquam': 1,
'domeo': 1,
'adulescentia': 1,
'credo': 1,
'nervis': 1,
'minuo': 1,
'paene': 1,
'pernicies': 1,
'Sese': 1,
'amor': 1,
'fraternus': 2,
'existimatio': 1,
'vulgi': 1,
'commoveri': 2,
'averterentur': 1,
'Haec': 5,
'verbis': 2,
'fleo': 1,
'peto': 10,
...})In [93]:
caesar_word_counts['Ariovistus']Out [93]:
20
In [76]:
caesar_word_counts['Ariovistum']Out [76]:
10
In [84]:
# show me how many times Ariovistus is named in this text, for every case of the word "Ariovistus", namely: nominative, vocative, accusative, genative, dative, ablative
nom = caesar_word_counts['Ariovistus']
voc = caesar_word_counts['Arioviste']
acc = caesar_word_counts['Ariovistum']
gen = caesar_word_counts['Ariovisti']
abl = caesar_word_counts['Ariovisto'] # same as dative case
print(nom + acc + voc + gen + abl)42
In [100]:
fo.close()
with open("gall2.txt") as fo:
caesar_book2 = fo.read()
cltk_doc2 = cltk_nlp.analyze(text=caesar_book2)In [113]:
caesar_word_counts = Counter(cltk_doc2.tokens)
nom = caesar_word_counts['Diviciacus']
voc = caesar_word_counts['Diviciace']
acc = caesar_word_counts['Diviciacum']
gen = caesar_word_counts['Diviciaci']
abl = caesar_word_counts['Diviciaco'] # same as dative case
print(nom + acc + voc + gen + abl)
5
In [18]:
fo.close()
with open("gall3.txt") as fo:
caesar_book3 = fo.read()
cltk_doc3 = cltk_nlp.analyze(text=caesar_book3)In [19]:
caesar_word_counts = Counter(cltk_doc3.tokens)
nom = caesar_word_counts['Viridovix']
# voc = caesar_word_counts['Viridovix'] # same as nominative
acc = caesar_word_counts['Viridovigem']
gen = caesar_word_counts['Viridovigis']
dat = caesar_word_counts['Viridovigi']
abl = caesar_word_counts['Viridovige']
print(nom + acc + voc + gen + abl)
5
In [15]:
fo.close()
with open("gall5.txt") as fo:
caesar_book5 = fo.read()
cltk_doc5 = cltk_nlp.analyze(text=caesar_book5)In [17]:
caesar_word_counts = Counter(cltk_doc5.tokens)
nom = caesar_word_counts['Ambiorix']
# voc = caesar_word_counts['Ambiorix'] # same as nominative
acc = caesar_word_counts['Ambiorigem']
gen = caesar_word_counts['Ambiorigis']
dat = caesar_word_counts['Ambiorigi']
abl = caesar_word_counts['Ambiorige']
print(nom + acc + voc + gen + abl)
20
In [20]:
fo.close()
with open("gall6.txt") as fo:
caesar_book6 = fo.read()
cltk_doc6 = cltk_nlp.analyze(text=caesar_book6)In [21]:
caesar_word_counts = Counter(cltk_doc6.tokens)
nom = caesar_word_counts['Ambiorix']
# voc = caesar_word_counts['Ambiorix'] # same as nominative
acc = caesar_word_counts['Ambiorigem']
gen = caesar_word_counts['Ambiorigis']
dat = caesar_word_counts['Ambiorigi']
abl = caesar_word_counts['Ambiorige']
print(nom + acc + voc + gen + abl)
18
In [24]:
fo.close()
with open("gall7.txt") as fo:
caesar_book7 = fo.read()
cltk_doc7 = cltk_nlp.analyze(text=caesar_book7)In [26]:
caesar_word_counts = Counter(cltk_doc7.tokens)
nom = caesar_word_counts['Vercingetorix']
# voc = caesar_word_counts['Vercingetorix'] # same as nominative
acc = caesar_word_counts['Vercingetorigem']
gen = caesar_word_counts['Vercingetorigis']
dat = caesar_word_counts['Vercingetorigi']
abl = caesar_word_counts['Vercingetorige']
print(nom + acc + voc + gen + abl)
46