Converter file¶

Latest and Greatest¶

In [184]:

import os
import re
import collections
import json
import csv
# from glob import glob
from tf.fabric import Fabric
from tf.convert.walker import CV
# from tf.compose import modify

source_dirs = 'input' # "input" is the name of the input folder that contains the source file
output_dirs = 'output' # "output" is the name of the output folder to which the finished TF files will be dumped into

bo2book = {line.split()[0]:line.split()[1] for line in '''
OTt4 Old_Testament
'''.split('\n') if line} # "OT" is the name of the file in the input folder AND "split()" splits at space

# patts = {'section': re.compile('(\d*):(\d*)\.(\d*)')}

def director(cv):
        
    '''
    Walks through LXX and triggers
    slot and node creation events.
    '''
        
    # process books in order
    for bo, book in bo2book.items():
        
        book_loc = os.path.join(source_dirs, f'{bo}.txt')
        
        print(f'\thandling {book_loc}...')
        
        with open(book_loc, 'r', encoding="utf8") as infile:
            text = [w for w in infile.read().split('\n') if w]
            
        this_book = cv.node('book')
            
        # keep track of when to trigger paragraph, chapter, and verse objects
        # para_track = 1 # keep counts of paragraphs
        prev_book = "Gen" # start at Genesis
        prev_chap = 1 # start at 1
        prev_verse = 1 # start at 1
        prev_subverse = ''
        wrdnum = 0 # start at 0
        this_chap = cv.node('chapter')
        # this_para = cv.node('paragraph')
        this_verse = cv.node('verse')
        this_subverse = cv.node('subverse')
        
        # iterate through words and construct objects
        for word in text:

            wrdnum += 1

            data = word.split('\t')
            # word_data, lemmas = data[:7], data[7:]

            word_data = data[:26] #the number here is the amount of columns
            morphology = ' '.join(data[26:]) #the number here is the amount of columns
            
            # segment out word data
            # bo_code, ref, brake, ketiv, qere, morph, strongs = word_data
            orig_order, book, chapter, verse, subverse, word, lex_utf8, g_cons_utf8, translit_SBL, lemma_gloss, strong, sp, morphology, case, nu, gn, degree, tense, voice, mood, ps, lemma_translit, abc_order, freq_lemma, BOL_lexeme_dict, BOL_gloss = word_data

            # if chapter == "Prolog":
            #     chapter = 0

            subverse == ""


            #try:
            #    verse = int(verse)
            #except ValueError:
            #    subverse = verse[-1:]
            #    verse = verse[:-1]

            if verse == "":
                print(f'{orig_order}: {verse} {subverse}')


            # strongs_lemma, anlex_lemma = ' '.join(lemmas).split('!') # reconstitute lemmas and split on !

            # chapt, verse, wrdnum = [int(v) for v in patts['section'].match(ref).groups()]

            # -- handle TF events --

            # detect book boundary
            if prev_book != book:

                # end subverse
                cv.feature(this_subverse, subverse=prev_subverse)
                cv.terminate(this_subverse)

                # end verse
                cv.feature(this_verse, verse=prev_verse)
                cv.terminate(this_verse)
                
                # end chapter
                cv.feature(this_chap, chapter=prev_chap)
                cv.terminate(this_chap)

                # end book
                cv.feature(this_book, book=prev_book)
                cv.terminate(this_book)
                
                # new book, chapter, verse, and subverse begin
                this_book = cv.node('book')
                prev_book = book
                this_chap = cv.node('chapter')
                prev_chap = chapter
                this_verse = cv.node('verse')
                prev_verse = verse
                this_subverse = cv.node('subverse')
                prev_subverse = subverse
                wrdnum = 1
            
            # detect chapter boundary
            elif prev_chap != chapter:

                # end subverse
                cv.feature(this_subverse, subverse=prev_subverse)
                cv.terminate(this_subverse)
                
                # end verse
                cv.feature(this_verse, verse=prev_verse)
                cv.terminate(this_verse)
                
                # end chapter
                cv.feature(this_chap, chapter=prev_chap)
                cv.terminate(this_chap)
                
                # new chapter, verse, and subverse begin
                this_chap = cv.node('chapter')
                prev_chap = chapter
                this_verse = cv.node('verse')
                prev_verse = verse
                this_subverse = cv.node('subverse')
                prev_subverse = subverse
                wrdnum = 1
            
            # detect verse boundary
            elif prev_verse != verse:

                # end subverse
                cv.feature(this_subverse, subverse=prev_subverse)
                cv.terminate(this_subverse)

                # end verse
                cv.feature(this_verse, verse=prev_verse)
                cv.terminate(this_verse)

                # new verse and subverse begin
                this_verse = cv.node('verse')
                prev_verse = verse
                this_subverse = cv.node('subverse')
                prev_subverse = subverse
                wrdnum = 1

            # detect subverse boundary
            elif prev_subverse != subverse:
                cv.feature(this_subverse, subverse=prev_subverse)
                cv.terminate(this_subverse)
                this_subverse = cv.node('subverse')
                prev_subverse = subverse

                
            # detect paragraph boundary
            # if brake == 'P':
            #     cv.feature(this_para, para=para_track)
            #     cv.terminate(this_para)
            #     this_para = cv.node('paragraph') # start a new paragraph
            #     para_track += 1 # count paragraphs in the book
                
                
            # make word object
            this_word = cv.slot()
            cv.feature(this_word, 

                       orig_order=orig_order,
                       book=book,
                       chapter=chapter,
                       verse=verse,
                       subverse=subverse,
                       word=word,
                       lex_utf8=lex_utf8,
                       g_cons_utf8=g_cons_utf8,
                       translit_SBL=translit_SBL,
                       lemma_gloss=lemma_gloss,
                       strong=strong,
                       sp=sp,
                       morphology=morphology,
                       case=case,
                       nu=nu,
                       gn=gn,
                       degree=degree,
                       tense=tense,
                       voice=voice,
                       mood=mood,
                       ps=ps,
                       lemma_translit=lemma_translit,
                       abc_order=abc_order,
                       freq_lemma=freq_lemma,
                       BOL_lexeme_dict=BOL_lexeme_dict,
                       BOL_gloss=BOL_gloss,

                       
                       # ketiv=ketiv, 
                       # qere=qere, 
                       # strongs=strongs, 
                    #    str_lem=strongs_lemma.strip(),
                    #    anlex_lem=anlex_lemma.strip()
                      )
            cv.terminate(this_word)
        
        # end book and its objects
        # - end subverse
        cv.feature(this_subverse, subverse=prev_subverse)
        cv.terminate(this_subverse)

        # - end verse
        cv.feature(this_verse, verse=prev_verse)
        cv.terminate(this_verse)
        
        # - end paragraph
        # cv.feature(this_para, para=para_track)
        # cv.terminate(this_para)
        
        # - end chapter
        cv.feature(this_chap, chapter=prev_chap)
        cv.terminate(this_chap)
        
        # - end book
        cv.feature(this_book, book=prev_book)
        cv.terminate(this_book)


slotType = 'word'
otext = {'fmt:text-orig-full':'{word} ',
         'sectionTypes':'book,chapter,verse',
         'sectionFeatures':'book,chapter,verse'}

generic = {'Name': 'LXX',
           'Version': '1935',
           'Author': 'Rahlfs',
           'Editors': 'CCAT, Eliran Wong',
           'Converter': 'Adrian Negrea, Oliver Glanz', 
           'Source:':'https://github.com/eliranwong/LXX-Rahlfs-1935',
           'Note':'?'}

intFeatures = {'chapter', 'verse'}

featureMeta = {
                'orig_order': {'description': 'original word order in corpus'},
                'book': {'description': 'book'},
                'chapter': {'description': 'chapter'},
                'verse': {'description': 'verse'},
                'subverse': {'description': 'subverse'},
                'word': {'description': 'text realized word'},
                'lex_utf8': {'description': 'normalized word'},
                'g_cons_utf8': {'description': 'word without accents'},
                'translit_SBL': {'description': 'SBL transliteration'},
                'lemma_gloss': {'description': 'English gloss'},
                'strong': {'description': 'Strong numbers'},
                'sp': {'description': 'part of speech'},
                'morphology': {'description': 'morphology'},
                'case': {'description': 'case'},
                'nu': {'description': 'number'},
                'gn': {'description': 'gender'},
                'degree': {'description': 'degree'},
                'tense': {'description': 'tense'},
                'voice': {'description': 'voice'},
                'mood': {'description': 'mood'},
                'ps': {'description': 'person'},
                'lemma_translit': {'description': 'lemma transliteration'},
                'abc_order': {'description': 'dictionary order'},
                'freq_lemma': {'description': 'frequency of word in corpus'},
                'BOL_lexeme_dict': {'description': 'BOL dictionary form of lemma'},
                'BOL_gloss': {'description': 'BOL English gloss'},
    
               # 'para': {'description': 'A paragraph number'},
               # 'ketiv': {'descrption': 'The text as it is written in the printed Tischendorf'},
               # 'qere': {'description': 'The text as the editor thinks it should have been'},
               # 'strongs': {'description': 'A word\'s number in Strongs'},
               # 'str_lem': {'description': 'Word lemma that corresponds to The NEW Strong\'sComplete Dictionary of Bible Words'},
               # 'anlex_lem': {'description': 'Word lemma that corresponds to Friberg, Friberg and Miller\'s ANLEX'}
              }


# configure metadata/output
version = '1935'
generic['Version'] = version

output = os.path.join(output_dirs, version)

print(f'Processing Version {version}')
output_dir = output_dirs.format(version=version)

TF = Fabric(locations=output_dir, silent=True)
cv = CV(TF)

cv.walk(director,
                slotType,
                otext=otext,
                generic=generic,
                intFeatures=intFeatures,
                featureMeta=featureMeta,
                warn=True,
                force=False,)

Processing Version 1935
  0.00s Importing data from walking through the source ...
   |     0.00s Preparing metadata... 
   |     0.00s No structure nodes will be set up
   |   SECTION   TYPES:    book, chapter, verse
   |   SECTION   FEATURES: book, chapter, verse
   |   STRUCTURE TYPES:    
   |   STRUCTURE FEATURES: 
   |   TEXT      FEATURES:
   |      |   text-orig-full       word
   |     0.00s OK
   |     0.00s Following director... 
	handling input\OTt4.txt...
   |       11s "edge" actions: 0
   |       11s "feature" actions: 685735
   |       11s "node" actions: 62042
   |       11s "resume" actions: 0
   |       11s "slot" actions: 623693
   |       11s "terminate" actions: 685735
   |         57 x "book" node 
   |       1193 x "chapter" node 
   |      30420 x "subverse" node 
   |      30372 x "verse" node 
   |     623693 x "word" node  = slot type
   |     685735 nodes of all types
   |       11s OK
   |     0.03s Removing unlinked nodes ... 
   |      |     0.00s      1 unlinked "chapter" node: [1]
   |      |     0.00s      1 unlinked "verse" node: [1]
   |      |     0.00s      1 unlinked "subverse" node: [1]
   |      |     0.00s      3 unlinked nodes
   |      |     0.00s Leaving 685732 nodes
   |     0.00s checking for nodes and edges ... 
   |     0.00s OK
   |     0.00s checking features ... 
   |     0.48s OK
   |     0.00s reordering nodes ...
   |     0.18s Sorting 57 nodes of type "book"
   |     0.24s Sorting 1192 nodes of type "chapter"
   |     0.31s Sorting 30419 nodes of type "subverse"
   |     0.42s Sorting 30371 nodes of type "verse"
   |     0.53s Max node = 685732
   |     0.54s OK
   |     0.00s reassigning feature values ...
   |      |     1.14s node feature "BOL_gloss" with 623693 nodes
   |      |     1.36s node feature "BOL_lexeme_dict" with 623693 nodes
   |      |     1.58s node feature "abc_order" with 623693 nodes
   |      |     1.79s node feature "book" with 623750 nodes
   |      |     2.00s node feature "case" with 623693 nodes
   |      |     2.21s node feature "chapter" with 624885 nodes
   |      |     2.43s node feature "degree" with 623693 nodes
   |      |     2.65s node feature "freq_lemma" with 623693 nodes
   |      |     2.89s node feature "g_cons_utf8" with 623693 nodes
   |      |     3.11s node feature "gn" with 623693 nodes
   |      |     3.36s node feature "lemma_gloss" with 623693 nodes
   |      |     3.58s node feature "lemma_translit" with 623693 nodes
   |      |     3.83s node feature "lex_utf8" with 623693 nodes
   |      |     4.07s node feature "mood" with 623693 nodes
   |      |     4.32s node feature "morphology" with 623693 nodes
   |      |     4.53s node feature "nu" with 623693 nodes
   |      |     4.76s node feature "orig_order" with 623693 nodes
   |      |     4.98s node feature "ps" with 623693 nodes
   |      |     5.21s node feature "sp" with 623693 nodes
   |      |     5.41s node feature "strong" with 623693 nodes
   |      |     5.66s node feature "subverse" with 654112 nodes
   |      |     5.91s node feature "tense" with 623693 nodes
   |      |     6.13s node feature "translit_SBL" with 623693 nodes
   |      |     6.36s node feature "verse" with 654064 nodes
   |      |     6.59s node feature "voice" with 623693 nodes
   |      |     6.83s node feature "word" with 623693 nodes
   |     6.05s OK
  0.00s Exporting 27 node and 1 edge and 1 config features to output:
  0.00s VALIDATING oslots feature
  0.09s VALIDATING oslots feature
  0.09s maxSlot=     623693
  0.09s maxNode=     685732
  0.10s OK: oslots is valid
   |     1.12s T BOL_gloss            to output
   |     1.21s T BOL_lexeme_dict      to output
   |     1.13s T abc_order            to output
   |     1.14s T book                 to output
   |     1.00s T case                 to output
   |     1.00s T chapter              to output
   |     1.01s T degree               to output
   |     1.12s T freq_lemma           to output
   |     1.14s T g_cons_utf8          to output
   |     1.06s T gn                   to output
   |     1.15s T lemma_gloss          to output
   |     1.02s T lemma_translit       to output
   |     1.14s T lex_utf8             to output
   |     0.98s T mood                 to output
   |     1.07s T morphology           to output
   |     1.34s T nu                   to output
   |     1.66s T orig_order           to output
   |     0.32s T otype                to output
   |     1.20s T ps                   to output
   |     1.28s T sp                   to output
   |     1.17s T strong               to output
   |     1.08s T subverse             to output
   |     1.13s T tense                to output
   |     1.21s T translit_SBL         to output
   |     1.34s T verse                to output
   |     1.02s T voice                to output
   |     1.32s T word                 to output
   |     0.52s T oslots               to output
   |     0.00s M otext                to output
    31s Exported 27 node features and 1 edge features and 1 config features to output

Out[184]:

True

In [6]:

# First, I have to laod different modules that I use for analyzing the data and for plotting:
import sys, os, collections
import pandas as pd
import numpy as np
import re
import csv
import seaborn as sns
import matplotlib.pyplot as plt; plt.rcdefaults()
from matplotlib.pyplot import figure
from collections import Counter

# Second, I have to load the Text Fabric app
from tf.fabric import Fabric
from tf.app import use

In [133]:

featureadd=pd.read_excel('d:/OneDrive/1200_AUS-research/Fabric-TEXT/0_data_CCATLXX/LXX_source_v1.3.xlsx',sheet_name='FULL_data')
pd.set_option('display.max_columns', 50)
featureadd.head(10)

Out[133]:

	orig_order	book	chapter	verse	subverse	word	lex_utf8	g_cons_utf8	translit_SBL	lemma_gloss	strong	sp	morphology	case	nu	gn	degree	tense	voice	mood	ps
0	1	Gen	1	1	NaN	ἐν	ἐν	εν	en	in	G1722	preposition	P	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
1	2	Gen	1	1	NaN	ἀρχῇ	ἀρχή	αρχη	archē	origin; beginning	G746	noun	N.DSF	Dat	Sing	Fem	NaN	NaN	NaN	NaN	NaN
2	3	Gen	1	1	NaN	ἐποίησεν	ποιέω	ποιεω	epoiēsen	do; make	G4160	verb	V.AAI3S	NaN	Sing	NaN	NaN	Aor	Act	Ind	3rd
3	4	Gen	1	1	NaN	ὁ	ὁ	ο	ho	the	G3588	pronoun, article	RA.NSM	Nom	Sing	Masc	NaN	NaN	NaN	NaN	NaN
4	5	Gen	1	1	NaN	θεὸς	θεός	θεος	theos	God	G2316	noun	N.NSM	Nom	Sing	Masc	NaN	NaN	NaN	NaN	NaN
5	6	Gen	1	1	NaN	τὸν	ὁ	ο	ton	the	G3588	pronoun, article	RA.ASM	Acc	Sing	Masc	NaN	NaN	NaN	NaN	NaN
6	7	Gen	1	1	NaN	οὐρανὸν	οὐρανός	ουρανος	ouranon	sky; heaven	G3772	noun	N.ASM	Acc	Sing	Masc	NaN	NaN	NaN	NaN	NaN
7	8	Gen	1	1	NaN	καὶ	καί	και	kai	and; even	G2532	conjunction	C	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
8	9	Gen	1	1	NaN	τὴν	ὁ	ο	tēn	the	G3588	pronoun, article	RA.ASF	Acc	Sing	Fem	NaN	NaN	NaN	NaN	NaN
9	10	Gen	1	1	NaN	γῆν	γῆ	γη	gēn	earth; land	G1093	noun	N.ASF	Acc	Sing	Fem	NaN	NaN	NaN	NaN	NaN

In [134]:

from unidecode import unidecode

In [135]:

featureadd['lemma_translit']=featureadd['lex_utf8'].apply(unidecode)
featureadd.head(5)

Out[135]:

	orig_order	book	chapter	verse	subverse	word	lex_utf8	g_cons_utf8	translit_SBL	lemma_gloss	strong	sp	morphology	case	nu	gn	degree	tense	voice	mood	ps	lemma_translit
0	1	Gen	1	1	NaN	ἐν	ἐν	εν	en	in	G1722	preposition	P	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	en
1	2	Gen	1	1	NaN	ἀρχῇ	ἀρχή	αρχη	archē	origin; beginning	G746	noun	N.DSF	Dat	Sing	Fem	NaN	NaN	NaN	NaN	NaN	arkhe
2	3	Gen	1	1	NaN	ἐποίησεν	ποιέω	ποιεω	epoiēsen	do; make	G4160	verb	V.AAI3S	NaN	Sing	NaN	NaN	Aor	Act	Ind	3rd	poieo
3	4	Gen	1	1	NaN	ὁ	ὁ	ο	ho	the	G3588	pronoun, article	RA.NSM	Nom	Sing	Masc	NaN	NaN	NaN	NaN	NaN	o
4	5	Gen	1	1	NaN	θεὸς	θεός	θεος	theos	God	G2316	noun	N.NSM	Nom	Sing	Masc	NaN	NaN	NaN	NaN	NaN	theos

In [136]:

ABC1=featureadd[['orig_order','lex_utf8']]
ABC1.head(5)

Out[136]:

	orig_order	lex_utf8
0	1	ἐν
1	2	ἀρχή
2	3	ποιέω
3	4	ὁ
4	5	θεός

In [137]:

ABC1.describe()

Out[137]:

	orig_order
count	623693.000000
mean	311847.000000
std	180044.805057
min	1.000000
25%	155924.000000
50%	311847.000000
75%	467770.000000
max	623693.000000

In [138]:

ABCdict = ABC1.drop_duplicates(['lex_utf8']).sort_values(by='lex_utf8', ascending=[True])
ABCdict.head(10)

Out[138]:

	orig_order	lex_utf8
141279	141280	Ααλαφ
256210	256211	Ααρα
302080	302081	Αβαδια
296208	296209	Αβαδιας
256426	256427	Αβαδων
274105	274106	Αβαιαν
149542	149543	Αβαισαν
598778	598779	Αβαλ
579703	579704	Αβαμα
236283	236284	Αβανα

In [139]:

ABCdict.to_excel('d:/OneDrive/1200_AUS-research/Fabric-TEXT/0_data_CCATLXX/feature-dev/ABC1order.xlsx')

In [140]:

ABC2=pd.read_excel('d:/OneDrive/1200_AUS-research/Fabric-TEXT/0_data_CCATLXX/feature-dev/ABC2order.xlsx')
pd.set_option('display.max_columns', 50)
ABC2.head(10)

Out[140]:

	orig_order	lex_utf8	abc_order
0	1	ἐν	4638
1	2	ἀρχή	1835
2	3	ποιέω	10580
3	4	ὁ	9434
4	5	θεός	6191
5	7	οὐρανός	9842
6	8	καί	7030
7	10	γῆ	3082
8	12	δέ	3302
9	14	εἰμί	4092

In [141]:

ABC2=ABC2.drop(['orig_order'], axis=1)
ABC2.head()

Out[141]:

	lex_utf8	abc_order
0	ἐν	4638
1	ἀρχή	1835
2	ποιέω	10580
3	ὁ	9434
4	θεός	6191

In [142]:

featureadd.describe()

Out[142]:

	orig_order	chapter	verse
count	623693.000000	623693.000000	623693.000000
mean	311847.000000	19.200501	16.949878
std	180044.805057	20.679681	13.994139
min	1.000000	0.000000	0.000000
25%	155924.000000	6.000000	7.000000
50%	311847.000000	13.000000	14.000000
75%	467770.000000	25.000000	23.000000
max	623693.000000	151.000000	176.000000

In [143]:

featureadd=pd.merge (featureadd, ABC2,
                      on='lex_utf8',
                      how='outer')
featureadd.head(5)

Out[143]:

	orig_order	book	chapter	verse	subverse	word	lex_utf8	g_cons_utf8	translit_SBL	lemma_gloss	strong	sp	morphology	case	nu	gn	degree	tense	voice	mood	ps	lemma_translit	abc_order
0	1	Gen	1	1	NaN	ἐν	ἐν	εν	en	in	G1722	preposition	P	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	en	4638
1	86	Gen	1	6	NaN	ἐν	ἐν	εν	en	in	G1722	preposition	P	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	en	4638
2	232	Gen	1	11	NaN	ἐν	ἐν	εν	en	in	G1722	preposition	P	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	en	4638
3	264	Gen	1	12	NaN	ἐν	ἐν	εν	en	in	G1722	preposition	P	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	en	4638
4	291	Gen	1	14	NaN	ἐν	ἐν	εν	en	in	G1722	preposition	P	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	en	4638

In [144]:

featureadd.describe()

Out[144]:

	orig_order	chapter	verse	abc_order
count	623693.000000	623693.000000	623693.000000	623693.000000
mean	311847.000000	19.200501	16.949878	7261.430627
std	180044.805058	20.679681	13.994139	3447.810620
min	1.000000	0.000000	0.000000	1.000000
25%	155924.000000	6.000000	7.000000	4421.000000
50%	311847.000000	13.000000	14.000000	7096.000000
75%	467770.000000	25.000000	23.000000	9456.000000
max	623693.000000	151.000000	176.000000	14174.000000

In [159]:

featureaddstage2 = featureadd
featureaddstage2.head(5)

Out[159]:

	orig_order	book	chapter	verse	subverse	word	lex_utf8	g_cons_utf8	translit_SBL	lemma_gloss	strong	sp	morphology	case	nu	gn	degree	tense	voice	mood	ps	lemma_translit	abc_order	freq_lemma
0	1	Gen	1	1	NaN	ἐν	ἐν	εν	en	in	G1722	preposition	P	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	en	4638	14316
1	86	Gen	1	6	NaN	ἐν	ἐν	εν	en	in	G1722	preposition	P	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	en	4638	14316
2	232	Gen	1	11	NaN	ἐν	ἐν	εν	en	in	G1722	preposition	P	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	en	4638	14316
3	264	Gen	1	12	NaN	ἐν	ἐν	εν	en	in	G1722	preposition	P	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	en	4638	14316
4	291	Gen	1	14	NaN	ἐν	ἐν	εν	en	in	G1722	preposition	P	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	en	4638	14316

In [160]:

featureaddstage2.describe()

Out[160]:

	orig_order	chapter	verse	abc_order	freq_lemma
count	623693.000000	623693.000000	623693.000000	623693.000000	623693.000000
mean	311847.000000	19.200501	16.949878	7261.430627	21743.617390
std	180044.805058	20.679681	13.994139	3447.810620	32782.706194
min	1.000000	0.000000	0.000000	1.000000	1.000000
25%	155924.000000	6.000000	7.000000	4421.000000	244.000000
50%	311847.000000	13.000000	14.000000	7096.000000	2522.000000
75%	467770.000000	25.000000	23.000000	9456.000000	29396.000000
max	623693.000000	151.000000	176.000000	14174.000000	88444.000000

In [161]:

featureaddstage2["freq_lemma"]=featureaddstage2.groupby(["lex_utf8"])["lex_utf8"].transform("count")
featureaddstage2.head(5)

Out[161]:

	orig_order	book	chapter	verse	subverse	word	lex_utf8	g_cons_utf8	translit_SBL	lemma_gloss	strong	sp	morphology	case	nu	gn	degree	tense	voice	mood	ps	lemma_translit	abc_order	freq_lemma
0	1	Gen	1	1	NaN	ἐν	ἐν	εν	en	in	G1722	preposition	P	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	en	4638	14316
1	86	Gen	1	6	NaN	ἐν	ἐν	εν	en	in	G1722	preposition	P	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	en	4638	14316
2	232	Gen	1	11	NaN	ἐν	ἐν	εν	en	in	G1722	preposition	P	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	en	4638	14316
3	264	Gen	1	12	NaN	ἐν	ἐν	εν	en	in	G1722	preposition	P	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	en	4638	14316
4	291	Gen	1	14	NaN	ἐν	ἐν	εν	en	in	G1722	preposition	P	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	en	4638	14316

In [162]:

featureaddstage2.describe()

Out[162]:

	orig_order	chapter	verse	abc_order	freq_lemma
count	623693.000000	623693.000000	623693.000000	623693.000000	623693.000000
mean	311847.000000	19.200501	16.949878	7261.430627	21743.617390
std	180044.805058	20.679681	13.994139	3447.810620	32782.706194
min	1.000000	0.000000	0.000000	1.000000	1.000000
25%	155924.000000	6.000000	7.000000	4421.000000	244.000000
50%	311847.000000	13.000000	14.000000	7096.000000	2522.000000
75%	467770.000000	25.000000	23.000000	9456.000000	29396.000000
max	623693.000000	151.000000	176.000000	14174.000000	88444.000000

In [163]:

featureaddstage2.sort_values(['orig_order'], ascending=True).head(10)

Out[163]:

	orig_order	book	chapter	verse	subverse	word	lex_utf8	g_cons_utf8	translit_SBL	lemma_gloss	strong	sp	morphology	case	nu	gn	degree	tense	voice	mood	ps	lemma_translit	abc_order	freq_lemma
0	1	Gen	1	1	NaN	ἐν	ἐν	εν	en	in	G1722	preposition	P	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	en	4638	14316
14316	2	Gen	1	1	NaN	ἀρχῇ	ἀρχή	αρχη	archē	origin; beginning	G746	noun	N.DSF	Dat	Sing	Fem	NaN	NaN	NaN	NaN	NaN	arkhe	1835	236
14552	3	Gen	1	1	NaN	ἐποίησεν	ποιέω	ποιεω	epoiēsen	do; make	G4160	verb	V.AAI3S	NaN	Sing	NaN	NaN	Aor	Act	Ind	3rd	poieo	10580	3386
17938	4	Gen	1	1	NaN	ὁ	ὁ	ο	ho	the	G3588	pronoun, article	RA.NSM	Nom	Sing	Masc	NaN	NaN	NaN	NaN	NaN	o	9434	88444
106382	5	Gen	1	1	NaN	θεὸς	θεός	θεος	theos	God	G2316	noun	N.NSM	Nom	Sing	Masc	NaN	NaN	NaN	NaN	NaN	theos	6191	4009
17939	6	Gen	1	1	NaN	τὸν	ὁ	ο	ton	the	G3588	pronoun, article	RA.ASM	Acc	Sing	Masc	NaN	NaN	NaN	NaN	NaN	o	9434	88444
110391	7	Gen	1	1	NaN	οὐρανὸν	οὐρανός	ουρανος	ouranon	sky; heaven	G3772	noun	N.ASM	Acc	Sing	Masc	NaN	NaN	NaN	NaN	NaN	ouranos	9842	682
111073	8	Gen	1	1	NaN	καὶ	καί	και	kai	and; even	G2532	conjunction	C	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	kai	7030	62231
17940	9	Gen	1	1	NaN	τὴν	ὁ	ο	tēn	the	G3588	pronoun, article	RA.ASF	Acc	Sing	Fem	NaN	NaN	NaN	NaN	NaN	o	9434	88444
173304	10	Gen	1	1	NaN	γῆν	γῆ	γη	gēn	earth; land	G1093	noun	N.ASF	Acc	Sing	Fem	NaN	NaN	NaN	NaN	NaN	ge	3082	3173

In [164]:

featureaddstage2.describe()

Out[164]:

	orig_order	chapter	verse	abc_order	freq_lemma
count	623693.000000	623693.000000	623693.000000	623693.000000	623693.000000
mean	311847.000000	19.200501	16.949878	7261.430627	21743.617390
std	180044.805058	20.679681	13.994139	3447.810620	32782.706194
min	1.000000	0.000000	0.000000	1.000000	1.000000
25%	155924.000000	6.000000	7.000000	4421.000000	244.000000
50%	311847.000000	13.000000	14.000000	7096.000000	2522.000000
75%	467770.000000	25.000000	23.000000	9456.000000	29396.000000
max	623693.000000	151.000000	176.000000	14174.000000	88444.000000

In [165]:

BOLgreekDICT=pd.read_excel('d:/OneDrive/1200_AUS-research/Fabric-TEXT/0_data_SBLGNT/feature-dev/NA1904_dictionary_v1.0.xlsx')
pd.set_option('display.max_columns', 50)
BOLgreekDICT.head(10)

Out[165]:

	orig abc order	Occurrences	Lexeme	orig abc order.1	Lexeme_dict	Strong's number	Strong's unreliable?	gloss
0	1	5	Ἀαρών	1	Ἀαρών, ὁ	2	no	Aaron
1	2	1	Ἀβαδδών	2	Ἀβαδδών, ὁ	3	no	Abaddon
2	3	1	ἀβαρής	3	ἀβαρής, -ές	4	no	not burdensome
3	4	3	ἀββά	4	ἀββά, ὁ	5	no	Father
4	5	4	Ἅβελ	5	Ἅβελ, ὁ	6	no	Abel
5	6	3	Ἀβιά	6	Ἀβιά, ὁ	7	no	Abijah
6	7	1	Ἀβιαθάρ	7	Ἀβιαθάρ, ὁ	8	no	Abiathar
7	8	1	Ἀβιληνή	8	Ἀβιληνή, -ῆς, ἡ	9	no	Abilene
8	9	2	Ἀβιούδ	9	Ἀβιούδ, ὁ	10	no	Abiud
9	10	73	Ἀβραάμ	10	Ἀβραάμ, ὁ	11	no	Abraham

In [166]:

BOLgreekDICT=BOLgreekDICT[['Lexeme','Lexeme_dict', 'gloss']]
BOLgreekDICT.head(10)

Out[166]:

	Lexeme	Lexeme_dict	gloss
0	Ἀαρών	Ἀαρών, ὁ	Aaron
1	Ἀβαδδών	Ἀβαδδών, ὁ	Abaddon
2	ἀβαρής	ἀβαρής, -ές	not burdensome
3	ἀββά	ἀββά, ὁ	Father
4	Ἅβελ	Ἅβελ, ὁ	Abel
5	Ἀβιά	Ἀβιά, ὁ	Abijah
6	Ἀβιαθάρ	Ἀβιαθάρ, ὁ	Abiathar
7	Ἀβιληνή	Ἀβιληνή, -ῆς, ἡ	Abilene
8	Ἀβιούδ	Ἀβιούδ, ὁ	Abiud
9	Ἀβραάμ	Ἀβραάμ, ὁ	Abraham

In [174]:

BOLgreekDICT = BOLgreekDICT.rename({'Lexeme':'lex_utf8', 'Lexeme_dict':'BOL_lexeme_dict', 'gloss':'BOL_gloss'}, axis=1)
BOLgreekDICT.head(5)

Out[174]:

	lex_utf8	BOL_lexeme_dict	BOL_gloss
0	Ἀαρών	Ἀαρών, ὁ	Aaron
1	Ἀβαδδών	Ἀβαδδών, ὁ	Abaddon
2	ἀβαρής	ἀβαρής, -ές	not burdensome
3	ἀββά	ἀββά, ὁ	Father
4	Ἅβελ	Ἅβελ, ὁ	Abel

In [175]:

BOLgreekDICT.describe()

Out[175]:

	lex_utf8	BOL_lexeme_dict	BOL_gloss
count	5433	5335	5433
unique	5400	5297	5172
top	ταχύς	ταχύς, -εῖα	leave behind
freq	4	4	4

In [176]:

featureaddstage3=featureaddstage2

In [177]:

featureaddstage3.describe()

Out[177]:

	orig_order	chapter	verse	abc_order	freq_lemma
count	623693.000000	623693.000000	623693.000000	623693.000000	623693.000000
mean	311847.000000	19.200501	16.949878	7261.430627	21743.617390
std	180044.805058	20.679681	13.994139	3447.810620	32782.706194
min	1.000000	0.000000	0.000000	1.000000	1.000000
25%	155924.000000	6.000000	7.000000	4421.000000	244.000000
50%	311847.000000	13.000000	14.000000	7096.000000	2522.000000
75%	467770.000000	25.000000	23.000000	9456.000000	29396.000000
max	623693.000000	151.000000	176.000000	14174.000000	88444.000000

In [178]:

featureaddstage4=pd.merge (featureaddstage3, BOLgreekDICT,
                      on='lex_utf8',
                      how='left')
featureaddstage4.head(5)

Out[178]:

	orig_order	book	chapter	verse	subverse	word	lex_utf8	g_cons_utf8	translit_SBL	lemma_gloss	strong	sp	morphology	case	nu	gn	degree	tense	voice	mood	ps	lemma_translit	abc_order	freq_lemma	BOL_lexeme_dict	BOL_gloss
0	1	Gen	1	1	NaN	ἐν	ἐν	εν	en	in	G1722	preposition	P	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	en	4638	14316	ἐν	in, on, among
1	86	Gen	1	6	NaN	ἐν	ἐν	εν	en	in	G1722	preposition	P	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	en	4638	14316	ἐν	in, on, among
2	232	Gen	1	11	NaN	ἐν	ἐν	εν	en	in	G1722	preposition	P	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	en	4638	14316	ἐν	in, on, among
3	264	Gen	1	12	NaN	ἐν	ἐν	εν	en	in	G1722	preposition	P	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	en	4638	14316	ἐν	in, on, among
4	291	Gen	1	14	NaN	ἐν	ἐν	εν	en	in	G1722	preposition	P	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	en	4638	14316	ἐν	in, on, among

In [180]:

featureaddstage4.describe()

Out[180]:

	orig_order	chapter	verse	abc_order	freq_lemma
count	628353.000000	628353.000000	628353.000000	628353.000000	628353.000000
mean	312013.178089	19.180892	16.949748	7267.016749	21585.945001
std	179969.157374	20.658195	13.994791	3445.968577	32711.827142
min	1.000000	0.000000	0.000000	1.000000	1.000000
25%	156202.000000	6.000000	7.000000	4425.000000	243.000000
50%	312320.000000	13.000000	14.000000	7103.000000	2223.000000
75%	467690.000000	25.000000	23.000000	9497.000000	29396.000000
max	623693.000000	151.000000	176.000000	14174.000000	88444.000000

In [181]:

featureaddstage4 = featureaddstage4.drop_duplicates(['orig_order']).sort_values(by='orig_order', ascending=[True])
featureaddstage4.head(10)

Out[181]:

	orig_order	book	chapter	verse	subverse	word	lex_utf8	g_cons_utf8	translit_SBL	lemma_gloss	strong	sp	morphology	case	nu	gn	degree	tense	voice	mood	ps	lemma_translit	abc_order	freq_lemma	BOL_lexeme_dict	BOL_gloss
0	1	Gen	1	1	NaN	ἐν	ἐν	εν	en	in	G1722	preposition	P	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	en	4638	14316	ἐν	in, on, among
14316	2	Gen	1	1	NaN	ἀρχῇ	ἀρχή	αρχη	archē	origin; beginning	G746	noun	N.DSF	Dat	Sing	Fem	NaN	NaN	NaN	NaN	NaN	arkhe	1835	236	ἀρχή, -ῆς, ἡ	ruler, beginning
14552	3	Gen	1	1	NaN	ἐποίησεν	ποιέω	ποιεω	epoiēsen	do; make	G4160	verb	V.AAI3S	NaN	Sing	NaN	NaN	Aor	Act	Ind	3rd	poieo	10580	3386	ποιέω	do, make
17938	4	Gen	1	1	NaN	ὁ	ὁ	ο	ho	the	G3588	pronoun, article	RA.NSM	Nom	Sing	Masc	NaN	NaN	NaN	NaN	NaN	o	9434	88444	ὁ, ἡ, τό	the
106382	5	Gen	1	1	NaN	θεὸς	θεός	θεος	theos	God	G2316	noun	N.NSM	Nom	Sing	Masc	NaN	NaN	NaN	NaN	NaN	theos	6191	4009	θεός, -οῦ, ὁ	God, god
17939	6	Gen	1	1	NaN	τὸν	ὁ	ο	ton	the	G3588	pronoun, article	RA.ASM	Acc	Sing	Masc	NaN	NaN	NaN	NaN	NaN	o	9434	88444	ὁ, ἡ, τό	the
110391	7	Gen	1	1	NaN	οὐρανὸν	οὐρανός	ουρανος	ouranon	sky; heaven	G3772	noun	N.ASM	Acc	Sing	Masc	NaN	NaN	NaN	NaN	NaN	ouranos	9842	682	οὐρανός, -οῦ, ὁ	sky, heaven
111073	8	Gen	1	1	NaN	καὶ	καί	και	kai	and; even	G2532	conjunction	C	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	kai	7030	62231	καί	and, even, also, namely
17940	9	Gen	1	1	NaN	τὴν	ὁ	ο	tēn	the	G3588	pronoun, article	RA.ASF	Acc	Sing	Fem	NaN	NaN	NaN	NaN	NaN	o	9434	88444	ὁ, ἡ, τό	the
173304	10	Gen	1	1	NaN	γῆν	γῆ	γη	gēn	earth; land	G1093	noun	N.ASF	Acc	Sing	Fem	NaN	NaN	NaN	NaN	NaN	ge	3082	3173	γῆ, γῆς, ἡ	earth, soil, land

In [182]:

featureaddstage4.describe()

Out[182]:

	orig_order	chapter	verse	abc_order	freq_lemma
count	623693.000000	623693.000000	623693.000000	623693.000000	623693.000000
mean	311847.000000	19.200501	16.949878	7261.430627	21743.617390
std	180044.805057	20.679681	13.994139	3447.810620	32782.706194
min	1.000000	0.000000	0.000000	1.000000	1.000000
25%	155924.000000	6.000000	7.000000	4421.000000	244.000000
50%	311847.000000	13.000000	14.000000	7096.000000	2522.000000
75%	467770.000000	25.000000	23.000000	9456.000000	29396.000000
max	623693.000000	151.000000	176.000000	14174.000000	88444.000000

In [183]:

featureaddstage4.to_excel('d:/OneDrive/1200_AUS-research/Fabric-TEXT/0_data_CCATLXX/LXX_source_v1.4.xlsx')

In [ ]:

Testing¶

In [185]:

%load_ext autoreload
%autoreload 2

In [1]:

# First, I have to laod different modules that I use for analyzing the data and for plotting:
import sys, os, collections
import pandas as pd
import numpy as np
import re
import csv
import seaborn as sns
import matplotlib.pyplot as plt; plt.rcdefaults()
from matplotlib.pyplot import figure
from collections import Counter

# Second, I have to load the Text Fabric app
from tf.fabric import Fabric
from tf.app import use

In [4]:

#LXX = use('CCATLXX/tf/1994_v1', hoist=globals())
LXX = use('CCATLXX/tf/1994_v2', hoist=globals())
LXX = use('D:/OneDrive/1200_AUS-research/Fabric-TEXT/0_data_CCATLXX/CCATLXX/tf/1994_v2', hoist=globals())

This is Text-Fabric 9.1.11
Api reference : https://annotation.github.io/text-fabric/tf/cheatsheet.html

29 features found and 0 ignored

Text-Fabric: Text-Fabric API 9.1.11, no app configured
Data: D:/OneDrive/1200_AUS-research/Fabric-TEXT/0_data_CCATLXX/CCATLXX/tf/1994_v2
Features:

D:/OneDrive/1200_AUS-research/Fabric-TEXT/0_data_CCATLXX/CCATLXX/tf/1994_v2

abc_order

str

dictionary order

Author:

Rahlfs

Converter:

Adrian Negrea, Oliver Glanz

Editors:

CCAT, Eliran Wong

Name:

LXX

Note:

?

Source::

https://github.com/eliranwong/LXX-Rahlfs-1935

Version:

1935

dateWritten:

2021-12-24T02:15:59Z

writtenBy:

Text-Fabric

bol_gloss

str

BOL English gloss

Author:

Rahlfs

Converter:

Adrian Negrea, Oliver Glanz

Editors:

CCAT, Eliran Wong

Name:

LXX

Note:

?

Source::

https://github.com/eliranwong/LXX-Rahlfs-1935

Version:

1935

dateWritten:

2021-12-24T02:15:57Z

writtenBy:

Text-Fabric

bol_lexeme_dict

str

BOL dictionary form of lemma

Author:

Rahlfs

Converter:

Adrian Negrea, Oliver Glanz

Editors:

CCAT, Eliran Wong

Name:

LXX

Note:

?

Source::

https://github.com/eliranwong/LXX-Rahlfs-1935

Version:

1935

dateWritten:

2021-12-24T02:15:58Z

writtenBy:

Text-Fabric

book

str

book

Author:

Rahlfs

Converter:

Adrian Negrea, Oliver Glanz

Editors:

CCAT, Eliran Wong

Name:

LXX

Note:

?

Source::

https://github.com/eliranwong/LXX-Rahlfs-1935

Version:

1935

dateWritten:

2021-12-24T02:16:00Z

writtenBy:

Text-Fabric

case

str

case

Author:

?

Converter:

Adrian Negrea

Editors:

Adrian Negrea, Oliver Glanz

Name:

LXX

Note:

?

Source::

?

Version:

?

dateWritten:

2021-12-23T04:29:04Z

writtenBy:

Text-Fabric

chapter

int

chapter

Author:

Rahlfs

Converter:

Adrian Negrea, Oliver Glanz

Editors:

CCAT, Eliran Wong

Name:

LXX

Note:

?

Source::

https://github.com/eliranwong/LXX-Rahlfs-1935

Version:

1935

dateWritten:

2021-12-24T02:16:02Z

writtenBy:

Text-Fabric

degree

str

degree

Author:

?

Converter:

Adrian Negrea

Editors:

Adrian Negrea, Oliver Glanz

Name:

LXX

Note:

?

Source::

?

Version:

?

dateWritten:

2021-12-23T04:29:04Z

writtenBy:

Text-Fabric

freq_lemma

str

frequency of word in corpus

Author:

Rahlfs

Converter:

Adrian Negrea, Oliver Glanz

Editors:

CCAT, Eliran Wong

Name:

LXX

Note:

?

Source::

https://github.com/eliranwong/LXX-Rahlfs-1935

Version:

1935

dateWritten:

2021-12-24T02:16:04Z

writtenBy:

Text-Fabric

g_cons_utf8

str

word without accents

Author:

Rahlfs

Converter:

Adrian Negrea, Oliver Glanz

Editors:

CCAT, Eliran Wong

Name:

LXX

Note:

?

Source::

https://github.com/eliranwong/LXX-Rahlfs-1935

Version:

1935

dateWritten:

2021-12-24T02:16:05Z

writtenBy:

Text-Fabric

gloss

str

gloss

Author:

?

Converter:

Adrian Negrea

Editors:

Adrian Negrea, Oliver Glanz

Name:

LXX

Note:

?

Source::

?

Version:

?

dateWritten:

2021-12-23T04:29:04Z

writtenBy:

Text-Fabric

gn

str

gender

Author:

?

Converter:

Adrian Negrea

Editors:

Adrian Negrea, Oliver Glanz

Name:

LXX

Note:

?

Source::

?

Version:

?

dateWritten:

2021-12-23T04:29:04Z

writtenBy:

Text-Fabric

lex

str

lemma transliteration

Author:

Rahlfs

Converter:

Adrian Negrea, Oliver Glanz

Editors:

CCAT, Eliran Wong

Name:

LXX

Note:

?

Source::

https://github.com/eliranwong/LXX-Rahlfs-1935

Version:

1935

dateWritten:

2021-12-24T02:16:09Z

writtenBy:

Text-Fabric

lex_utf8

str

normalized word

Author:

Rahlfs

Converter:

Adrian Negrea, Oliver Glanz

Editors:

CCAT, Eliran Wong

Name:

LXX

Note:

?

Source::

https://github.com/eliranwong/LXX-Rahlfs-1935

Version:

1935

dateWritten:

2021-12-24T02:16:10Z

writtenBy:

Text-Fabric

mood

str

mood

Author:

?

Converter:

Adrian Negrea

Editors:

Adrian Negrea, Oliver Glanz

Name:

LXX

Note:

?

Source::

?

Version:

?

dateWritten:

2021-12-23T04:29:04Z

writtenBy:

Text-Fabric

morphology

str

morphology

Author:

Rahlfs

Converter:

Adrian Negrea, Oliver Glanz

Editors:

CCAT, Eliran Wong

Name:

LXX

Note:

?

Source::

https://github.com/eliranwong/LXX-Rahlfs-1935

Version:

1935

dateWritten:

2021-12-24T02:16:12Z

writtenBy:

Text-Fabric

nu

str

number

Author:

?

Converter:

Adrian Negrea

Editors:

Adrian Negrea, Oliver Glanz

Name:

LXX

Note:

?

Source::

?

Version:

?

dateWritten:

2021-12-23T04:29:04Z

writtenBy:

Text-Fabric

orig_order

str

original word order

Author:

?

Converter:

Adrian Negrea

Editors:

Adrian Negrea, Oliver Glanz

Name:

LXX

Note:

?

Source::

?

Version:

?

dateWritten:

2021-12-23T04:29:04Z

writtenBy:

Text-Fabric

otype

str

Author:

Rahlfs

Converter:

Adrian Negrea, Oliver Glanz

Editors:

CCAT, Eliran Wong

Name:

LXX

Note:

?

Source::

https://github.com/eliranwong/LXX-Rahlfs-1935

Version:

1935

dateWritten:

2021-12-24T02:16:16Z

writtenBy:

Text-Fabric

ps

str

person

Author:

?

Converter:

Adrian Negrea

Editors:

Adrian Negrea, Oliver Glanz

Name:

LXX

Note:

?

Source::

?

Version:

?

dateWritten:

2021-12-23T04:29:04Z

writtenBy:

Text-Fabric

sp

str

part of speech

Author:

?

Converter:

Adrian Negrea

Editors:

Adrian Negrea, Oliver Glanz

Name:

LXX

Note:

?

Source::

?

Version:

?

dateWritten:

2021-12-23T04:29:04Z

writtenBy:

Text-Fabric

strong

str

strongs number

Author:

?

Converter:

Adrian Negrea

Editors:

Adrian Negrea, Oliver Glanz

Name:

LXX

Note:

?

Source::

?

Version:

?

dateWritten:

2021-12-23T04:29:04Z

writtenBy:

Text-Fabric

subverse

str

subverse

Author:

Rahlfs

Converter:

Adrian Negrea, Oliver Glanz

Editors:

CCAT, Eliran Wong

Name:

LXX

Note:

?

Source::

https://github.com/eliranwong/LXX-Rahlfs-1935

Version:

1935

dateWritten:

2021-12-24T02:16:20Z

writtenBy:

Text-Fabric

tense

str

tense

Author:

?

Converter:

Adrian Negrea

Editors:

Adrian Negrea, Oliver Glanz

Name:

LXX

Note:

?

Source::

?

Version:

?

dateWritten:

2021-12-23T04:29:04Z

writtenBy:

Text-Fabric

translit_SBL

str

SBL transliteration

Author:

Rahlfs

Converter:

Adrian Negrea, Oliver Glanz

Editors:

CCAT, Eliran Wong

Name:

LXX

Note:

?

Source::

https://github.com/eliranwong/LXX-Rahlfs-1935

Version:

1935

dateWritten:

2021-12-24T02:16:22Z

writtenBy:

Text-Fabric

verse

int

verse

Author:

Rahlfs

Converter:

Adrian Negrea, Oliver Glanz

Editors:

CCAT, Eliran Wong

Name:

LXX

Note:

?

Source::

https://github.com/eliranwong/LXX-Rahlfs-1935

Version:

1935

dateWritten:

2021-12-24T02:16:23Z

writtenBy:

Text-Fabric

voice

str

voice

Author:

?

Converter:

Adrian Negrea

Editors:

Adrian Negrea, Oliver Glanz

Name:

LXX

Note:

?

Source::

?

Version:

?

dateWritten:

2021-12-23T04:29:04Z

writtenBy:

Text-Fabric

word

str

text realized word

Author:

Rahlfs

Converter:

Adrian Negrea, Oliver Glanz

Editors:

CCAT, Eliran Wong

Name:

LXX

Note:

?

Source::

https://github.com/eliranwong/LXX-Rahlfs-1935

Version:

1935

dateWritten:

2021-12-24T02:16:26Z

writtenBy:

Text-Fabric

oslots

none

Author:

Rahlfs

Converter:

Adrian Negrea, Oliver Glanz

Editors:

CCAT, Eliran Wong

Name:

LXX

Note:

?

Source::

https://github.com/eliranwong/LXX-Rahlfs-1935

Version:

1935

dateWritten:

2021-12-24T02:16:27Z

writtenBy:

Text-Fabric

Text-Fabric API: names N F E L T S C TF directly usable

rate limit is 60 requests per hour, with 57 left for this hour
To increase the rate,see https://annotation.github.io/text-fabric/tf/advanced/repo.html/
	connecting to online GitHub repo annotation/app-D ... failed
GitHub says: 404 {"message": "Not Found", "documentation_url": "https://docs.github.com/rest/reference/repos#get-a-repository"}
The requested TF-app is not available offline

No online connection

This is Text-Fabric 9.1.11
Api reference : https://annotation.github.io/text-fabric/tf/cheatsheet.html

0 features found and 0 ignored
  0.00s Not all of the warp features otype and oslots are present in
None/D/
  0.00s Only the Feature and Edge APIs will be enabled
  0.00s Warp feature "otext" not found. Working without Text-API

Text-Fabric: Text-Fabric API 9.1.11, no app configured
Data: None/D
Features:

Text-Fabric API: names N F E L T S C TF directly usable

In [3]:

Search0 = '''
book book=Gen
  chapter chapter=1
    verse verse=1
      word
'''
Search0 = LXX.search(Search0)
LXX.show(Search0, start=1, end=1, condensed=True, colorMap={1:'pink'}, extraFeatures={'orig_order','book','chapter','verse','subverse','word','lex_utf8','g_cons_utf8','translit_SBL','lemma_gloss','strong','sp','morphology','case','nu','gn','degree','tense','voice','mood','ps','lemma_translit','abc_order','freq_lemma','BOL_lexeme_dict','BOL_gloss'})

  0.42s 10 results

verse 1

Gen 1:1

verse

verse=1

subverse

subverse=

ἐν 
BOL_gloss=in, on, amongBOL_lexeme_dict=ἐνabc_order=4638book=Gencase=chapter=1degree=freq_lemma=14316g_cons_utf8=ενgn=lemma_gloss=inlemma_translit=enlex_utf8=ἐνmood=morphology=Pnu=orig_order=1ps=sp=prepositionstrong=G1722subverse=tense=translit_SBL=enverse=1voice=word=ἐν
ἀρχῇ 
BOL_gloss=ruler, beginningBOL_lexeme_dict=ἀρχή, -ῆς, ἡabc_order=1835book=Gencase=Datchapter=1degree=freq_lemma=236g_cons_utf8=αρχηgn=Femlemma_gloss=origin; beginninglemma_translit=arkhelex_utf8=ἀρχήmood=morphology=N.DSFnu=Singorig_order=2ps=sp=nounstrong=G746subverse=tense=translit_SBL=archēverse=1voice=word=ἀρχῇ
ἐποίησεν 
BOL_gloss=do, makeBOL_lexeme_dict=ποιέωabc_order=10580book=Gencase=chapter=1degree=freq_lemma=3386g_cons_utf8=ποιεωgn=lemma_gloss=do; makelemma_translit=poieolex_utf8=ποιέωmood=Indmorphology=V.AAI3Snu=Singorig_order=3ps=3rdsp=verbstrong=G4160subverse=tense=Aortranslit_SBL=epoiēsenverse=1voice=Actword=ἐποίησεν
ὁ 
BOL_gloss=theBOL_lexeme_dict=ὁ, ἡ, τόabc_order=9434book=Gencase=Nomchapter=1degree=freq_lemma=88444g_cons_utf8=οgn=Masclemma_gloss=thelemma_translit=olex_utf8=ὁmood=morphology=RA.NSMnu=Singorig_order=4ps=sp=pronoun, articlestrong=G3588subverse=tense=translit_SBL=hoverse=1voice=word=ὁ
θεὸς 
BOL_gloss=God, godBOL_lexeme_dict=θεός, -οῦ, ὁabc_order=6191book=Gencase=Nomchapter=1degree=freq_lemma=4009g_cons_utf8=θεοςgn=Masclemma_gloss=Godlemma_translit=theoslex_utf8=θεόςmood=morphology=N.NSMnu=Singorig_order=5ps=sp=nounstrong=G2316subverse=tense=translit_SBL=theosverse=1voice=word=θεὸς
τὸν 
BOL_gloss=theBOL_lexeme_dict=ὁ, ἡ, τόabc_order=9434book=Gencase=Accchapter=1degree=freq_lemma=88444g_cons_utf8=οgn=Masclemma_gloss=thelemma_translit=olex_utf8=ὁmood=morphology=RA.ASMnu=Singorig_order=6ps=sp=pronoun, articlestrong=G3588subverse=tense=translit_SBL=tonverse=1voice=word=τὸν
οὐρανὸν 
BOL_gloss=sky, heavenBOL_lexeme_dict=οὐρανός, -οῦ, ὁabc_order=9842book=Gencase=Accchapter=1degree=freq_lemma=682g_cons_utf8=ουρανοςgn=Masclemma_gloss=sky; heavenlemma_translit=ouranoslex_utf8=οὐρανόςmood=morphology=N.ASMnu=Singorig_order=7ps=sp=nounstrong=G3772subverse=tense=translit_SBL=ouranonverse=1voice=word=οὐρανὸν
καὶ 
BOL_gloss=and, even, also, namelyBOL_lexeme_dict=καίabc_order=7030book=Gencase=chapter=1degree=freq_lemma=62231g_cons_utf8=καιgn=lemma_gloss=and; evenlemma_translit=kailex_utf8=καίmood=morphology=Cnu=orig_order=8ps=sp=conjunctionstrong=G2532subverse=tense=translit_SBL=kaiverse=1voice=word=καὶ
τὴν 
BOL_gloss=theBOL_lexeme_dict=ὁ, ἡ, τόabc_order=9434book=Gencase=Accchapter=1degree=freq_lemma=88444g_cons_utf8=οgn=Femlemma_gloss=thelemma_translit=olex_utf8=ὁmood=morphology=RA.ASFnu=Singorig_order=9ps=sp=pronoun, articlestrong=G3588subverse=tense=translit_SBL=tēnverse=1voice=word=τὴν
γῆν 
BOL_gloss=earth, soil, landBOL_lexeme_dict=γῆ, γῆς, ἡabc_order=3082book=Gencase=Accchapter=1degree=freq_lemma=3173g_cons_utf8=γηgn=Femlemma_gloss=earth; landlemma_translit=gelex_utf8=γῆmood=morphology=N.ASFnu=Singorig_order=10ps=sp=nounstrong=G1093subverse=tense=translit_SBL=gēnverse=1voice=word=γῆν

In [7]:

Search1 = '''
verse book=Gen chapter=1 verse=1
      word
'''
Search1 = LXX.search(Search1)
LXX.show(Search1, start=1, end=1, condensed=True, colorMap={1:'pink'}, extraFeatures={'subverse'})

  0.15s 0 results

In [8]:

Search2 = '''
book book=Gen
  chapter chapter=1
    verse verse=1
        word word* lex_utf8 g_cons_utf8 morphology* translit_SBL
'''
Search2 = LXX.search(Search2)
LXX.show(Search2, start=1, end=1, condensed=True, colorMap={1:'pink'}, extraFeatures={'subverse'})

  2.74s 10 results

verse 1

Gen 1:1

verse

verse=1

subverse

subverse=

ἐν 
g_cons_utf8=ενlex_utf8=ἐνmorphology=Ptranslit_SBL=enword=ἐν
ἀρχῇ 
g_cons_utf8=αρχηlex_utf8=ἀρχήmorphology=N.DSFtranslit_SBL=archēword=ἀρχῇ
ἐποίησεν 
g_cons_utf8=ποιεωlex_utf8=ποιέωmorphology=V.AAI3Stranslit_SBL=epoiēsenword=ἐποίησεν
ὁ 
g_cons_utf8=οlex_utf8=ὁmorphology=RA.NSMtranslit_SBL=howord=ὁ
θεὸς 
g_cons_utf8=θεοςlex_utf8=θεόςmorphology=N.NSMtranslit_SBL=theosword=θεὸς
τὸν 
g_cons_utf8=οlex_utf8=ὁmorphology=RA.ASMtranslit_SBL=tonword=τὸν
οὐρανὸν 
g_cons_utf8=ουρανοςlex_utf8=οὐρανόςmorphology=N.ASMtranslit_SBL=ouranonword=οὐρανὸν
καὶ 
g_cons_utf8=καιlex_utf8=καίmorphology=Ctranslit_SBL=kaiword=καὶ
τὴν 
g_cons_utf8=οlex_utf8=ὁmorphology=RA.ASFtranslit_SBL=tēnword=τὴν
γῆν 
g_cons_utf8=γηlex_utf8=γῆmorphology=N.ASFtranslit_SBL=gēnword=γῆν

In [18]:

Search3 = '''
book book=Num
 chapter chapter=21
   verse verse=3

'''
Search3 = LXX.search(Search3)
LXX.show(Search3, start=1, end=1, condensed=True, colorMap={1:'pink'}, extraFeatures={'word', 'lemma_translit', 'case'})

  0.03s 1 result

verse 1

Num 21:3

verse

verse=3

subverse

καὶ

book=Numcase=chapter=21lemma_translit=kaiverse=3word=καὶ

εἰσήκουσεν

book=Numcase=chapter=21lemma_translit=eisakouoverse=3word=εἰσήκουσεν

κύριος

book=Numcase=Nomchapter=21lemma_translit=kuriosverse=3word=κύριος

τῆς

book=Numcase=Genchapter=21lemma_translit=overse=3word=τῆς

φωνῆς

book=Numcase=Genchapter=21lemma_translit=phoneverse=3word=φωνῆς

Ισραηλ

book=Numcase=Genchapter=21lemma_translit=Israelverse=3word=Ισραηλ

καὶ

book=Numcase=chapter=21lemma_translit=kaiverse=3word=καὶ

παρέδωκεν

book=Numcase=chapter=21lemma_translit=paradidomiverse=3word=παρέδωκεν

τὸν

book=Numcase=Accchapter=21lemma_translit=overse=3word=τὸν

Χανανιν

book=Numcase=Accchapter=21lemma_translit=Khananisverse=3word=Χανανιν

ὑποχείριον

book=Numcase=Accchapter=21lemma_translit=upokheiriosverse=3word=ὑποχείριον

αὐτοῦ

book=Numcase=Genchapter=21lemma_translit=autosverse=3word=αὐτοῦ

καὶ

book=Numcase=chapter=21lemma_translit=kaiverse=3word=καὶ

ἀνεθεμάτισεν

book=Numcase=chapter=21lemma_translit=anathematizoverse=3word=ἀνεθεμάτισεν

αὐτὸν

book=Numcase=Accchapter=21lemma_translit=autosverse=3word=αὐτὸν

καὶ

book=Numcase=chapter=21lemma_translit=kaiverse=3word=καὶ

τὰς

book=Numcase=Accchapter=21lemma_translit=overse=3word=τὰς

πόλεις

book=Numcase=Accchapter=21lemma_translit=polisverse=3word=πόλεις

αὐτοῦ

book=Numcase=Genchapter=21lemma_translit=autosverse=3word=αὐτοῦ

καὶ

book=Numcase=chapter=21lemma_translit=kaiverse=3word=καὶ

ἐπεκάλεσαν

book=Numcase=chapter=21lemma_translit=epikaleoverse=3word=ἐπεκάλεσαν

τὸ

book=Numcase=Accchapter=21lemma_translit=overse=3word=τὸ

ὄνομα

book=Numcase=Accchapter=21lemma_translit=onomaverse=3word=ὄνομα

τοῦ

book=Numcase=Genchapter=21lemma_translit=overse=3word=τοῦ

τόπου

book=Numcase=Genchapter=21lemma_translit=toposverse=3word=τόπου

ἐκείνου

book=Numcase=Genchapter=21lemma_translit=ekeinosverse=3word=ἐκείνου

ἀνάθεμα

book=Numcase=Accchapter=21lemma_translit=anathemaverse=3word=ἀνάθεμα

In [39]:

Eisakouw = '''
book book#Esth
 verse
  word lemma_translit=epakouo
  word lemma_translit=theos|kurios
  word lemma_translit=phone case=Gen

'''
Eisakouw = LXX.search(Eisakouw)
LXX.show(Eisakouw, start=1, end=100, condensed=True, colorMap={1:'pink'}, extraFeatures={'word', 'lemma_translit', 'case', 'lex_utf8', 'BOL_lexeme_dict'})

  1.98s 12 results

verse 1

Gen 21:17

verse

subverse

εἰσήκουσεν

BOL_lexeme_dict=εἰσακούωbook=Gencase=lemma_translit=eisakouolex_utf8=εἰσακούωword=εἰσήκουσεν

δὲ

BOL_lexeme_dict=δέbook=Gencase=lemma_translit=delex_utf8=δέword=δὲ

ὁ

BOL_lexeme_dict=ὁ, ἡ, τόbook=Gencase=Nomlemma_translit=olex_utf8=ὁword=ὁ

θεὸς

BOL_lexeme_dict=θεός, -οῦ, ὁbook=Gencase=Nomlemma_translit=theoslex_utf8=θεόςword=θεὸς

τῆς

BOL_lexeme_dict=ὁ, ἡ, τόbook=Gencase=Genlemma_translit=olex_utf8=ὁword=τῆς

φωνῆς

BOL_lexeme_dict=φωνή, -ῆς, ἡbook=Gencase=Genlemma_translit=phonelex_utf8=φωνήword=φωνῆς

τοῦ

BOL_lexeme_dict=ὁ, ἡ, τόbook=Gencase=Genlemma_translit=olex_utf8=ὁword=τοῦ

παιδίου

BOL_lexeme_dict=παιδίον, -ου, τόbook=Gencase=Genlemma_translit=paidionlex_utf8=παιδίονword=παιδίου

ἐκ

BOL_lexeme_dict=ἐκ, ἐξbook=Gencase=lemma_translit=eklex_utf8=ἐκword=ἐκ

τοῦ

BOL_lexeme_dict=ὁ, ἡ, τόbook=Gencase=Genlemma_translit=olex_utf8=ὁword=τοῦ

τόπου

BOL_lexeme_dict=τόπος, -ου, ὁbook=Gencase=Genlemma_translit=toposlex_utf8=τόποςword=τόπου

οὗ

BOL_lexeme_dict=book=Gencase=lemma_translit=oulex_utf8=οὗword=οὗ

ἦν

BOL_lexeme_dict=εἰμίbook=Gencase=lemma_translit=eimilex_utf8=εἰμίword=ἦν

καὶ

BOL_lexeme_dict=καίbook=Gencase=lemma_translit=kailex_utf8=καίword=καὶ

ἐκάλεσεν

BOL_lexeme_dict=καλέωbook=Gencase=lemma_translit=kaleolex_utf8=καλέωword=ἐκάλεσεν

ἄγγελος

BOL_lexeme_dict=ἄγγελος, -ου, ὁbook=Gencase=Nomlemma_translit=aggeloslex_utf8=ἄγγελοςword=ἄγγελος

τοῦ

BOL_lexeme_dict=ὁ, ἡ, τόbook=Gencase=Genlemma_translit=olex_utf8=ὁword=τοῦ

θεοῦ

BOL_lexeme_dict=θεός, -οῦ, ὁbook=Gencase=Genlemma_translit=theoslex_utf8=θεόςword=θεοῦ

τὴν

BOL_lexeme_dict=ὁ, ἡ, τόbook=Gencase=Acclemma_translit=olex_utf8=ὁword=τὴν

Αγαρ

BOL_lexeme_dict=book=Gencase=Acclemma_translit=Agarlex_utf8=Ἄγαρword=Αγαρ

ἐκ

BOL_lexeme_dict=ἐκ, ἐξbook=Gencase=lemma_translit=eklex_utf8=ἐκword=ἐκ

τοῦ

BOL_lexeme_dict=ὁ, ἡ, τόbook=Gencase=Genlemma_translit=olex_utf8=ὁword=τοῦ

οὐρανοῦ

BOL_lexeme_dict=οὐρανός, -οῦ, ὁbook=Gencase=Genlemma_translit=ouranoslex_utf8=οὐρανόςword=οὐρανοῦ

καὶ

BOL_lexeme_dict=καίbook=Gencase=lemma_translit=kailex_utf8=καίword=καὶ

εἶπεν

BOL_lexeme_dict=book=Gencase=lemma_translit=epolex_utf8=ἔπωword=εἶπεν

αὐτῇ

BOL_lexeme_dict=αὐτός, -ή, -όbook=Gencase=Datlemma_translit=autoslex_utf8=αὐτόςword=αὐτῇ

τί

BOL_lexeme_dict=τίς, τίbook=Gencase=Nomlemma_translit=tislex_utf8=τίςword=τί

ἐστιν

BOL_lexeme_dict=εἰμίbook=Gencase=lemma_translit=eimilex_utf8=εἰμίword=ἐστιν

Αγαρ

BOL_lexeme_dict=book=Gencase=Voclemma_translit=Agarlex_utf8=Ἄγαρword=Αγαρ

μὴ

BOL_lexeme_dict=μήbook=Gencase=lemma_translit=melex_utf8=μήword=μὴ

φοβοῦ

BOL_lexeme_dict=φοβέομαιbook=Gencase=lemma_translit=phobeolex_utf8=φοβέωword=φοβοῦ

ἐπακήκοεν

BOL_lexeme_dict=ἐπακούωbook=Gencase=lemma_translit=epakouolex_utf8=ἐπακούωword=ἐπακήκοεν

γὰρ

BOL_lexeme_dict=γάρbook=Gencase=lemma_translit=garlex_utf8=γάρword=γὰρ

ὁ

BOL_lexeme_dict=ὁ, ἡ, τόbook=Gencase=Nomlemma_translit=olex_utf8=ὁword=ὁ

θεὸς

BOL_lexeme_dict=θεός, -οῦ, ὁbook=Gencase=Nomlemma_translit=theoslex_utf8=θεόςword=θεὸς

τῆς

BOL_lexeme_dict=ὁ, ἡ, τόbook=Gencase=Genlemma_translit=olex_utf8=ὁword=τῆς

φωνῆς

BOL_lexeme_dict=φωνή, -ῆς, ἡbook=Gencase=Genlemma_translit=phonelex_utf8=φωνήword=φωνῆς

τοῦ

BOL_lexeme_dict=ὁ, ἡ, τόbook=Gencase=Genlemma_translit=olex_utf8=ὁword=τοῦ

παιδίου

BOL_lexeme_dict=παιδίον, -ου, τόbook=Gencase=Genlemma_translit=paidionlex_utf8=παιδίονword=παιδίου

σου

BOL_lexeme_dict=book=Gencase=Genlemma_translit=soulex_utf8=σοῦword=σου

ἐκ

BOL_lexeme_dict=ἐκ, ἐξbook=Gencase=lemma_translit=eklex_utf8=ἐκword=ἐκ

τοῦ

BOL_lexeme_dict=ὁ, ἡ, τόbook=Gencase=Genlemma_translit=olex_utf8=ὁword=τοῦ

τόπου

BOL_lexeme_dict=τόπος, -ου, ὁbook=Gencase=Genlemma_translit=toposlex_utf8=τόποςword=τόπου

οὗ

BOL_lexeme_dict=book=Gencase=lemma_translit=oulex_utf8=οὗword=οὗ

ἐστιν

BOL_lexeme_dict=εἰμίbook=Gencase=lemma_translit=eimilex_utf8=εἰμίword=ἐστιν

verse 2

Gen 30:6

verse

subverse

καὶ

BOL_lexeme_dict=καίbook=Gencase=lemma_translit=kailex_utf8=καίword=καὶ

εἶπεν

BOL_lexeme_dict=book=Gencase=lemma_translit=epolex_utf8=ἔπωword=εἶπεν

Ραχηλ

BOL_lexeme_dict=Ῥαχήλ, ἡbook=Gencase=Nomlemma_translit=Rakhellex_utf8=Ῥαχήλword=Ραχηλ

ἔκρινέν

BOL_lexeme_dict=κρίνωbook=Gencase=lemma_translit=krinolex_utf8=κρίνωword=ἔκρινέν

μοι

BOL_lexeme_dict=book=Gencase=Datlemma_translit=moilex_utf8=μοιword=μοι

ὁ

BOL_lexeme_dict=ὁ, ἡ, τόbook=Gencase=Nomlemma_translit=olex_utf8=ὁword=ὁ

θεὸς

BOL_lexeme_dict=θεός, -οῦ, ὁbook=Gencase=Nomlemma_translit=theoslex_utf8=θεόςword=θεὸς

καὶ

BOL_lexeme_dict=καίbook=Gencase=lemma_translit=kailex_utf8=καίword=καὶ

ἐπήκουσεν

BOL_lexeme_dict=ἐπακούωbook=Gencase=lemma_translit=epakouolex_utf8=ἐπακούωword=ἐπήκουσεν

τῆς

BOL_lexeme_dict=ὁ, ἡ, τόbook=Gencase=Genlemma_translit=olex_utf8=ὁword=τῆς

φωνῆς

BOL_lexeme_dict=φωνή, -ῆς, ἡbook=Gencase=Genlemma_translit=phonelex_utf8=φωνήword=φωνῆς

μου

BOL_lexeme_dict=book=Gencase=Genlemma_translit=moulex_utf8=μουword=μου

καὶ

BOL_lexeme_dict=καίbook=Gencase=lemma_translit=kailex_utf8=καίword=καὶ

ἔδωκέν

BOL_lexeme_dict=δίδωμιbook=Gencase=lemma_translit=didomilex_utf8=δίδωμιword=ἔδωκέν

μοι

BOL_lexeme_dict=book=Gencase=Datlemma_translit=moilex_utf8=μοιword=μοι

υἱόν

BOL_lexeme_dict=υἱός, -οῦ, ὁbook=Gencase=Acclemma_translit=uioslex_utf8=υἱόςword=υἱόν

διὰ

BOL_lexeme_dict=διάbook=Gencase=lemma_translit=dialex_utf8=διάword=διὰ

τοῦτο

BOL_lexeme_dict=οὗτος, αὕτη, τοῦτοbook=Gencase=Acclemma_translit=outoslex_utf8=οὗτοςword=τοῦτο

ἐκάλεσεν

BOL_lexeme_dict=καλέωbook=Gencase=lemma_translit=kaleolex_utf8=καλέωword=ἐκάλεσεν

τὸ

BOL_lexeme_dict=ὁ, ἡ, τόbook=Gencase=Acclemma_translit=olex_utf8=ὁword=τὸ

ὄνομα

BOL_lexeme_dict=ὄνομα, -τος, τόbook=Gencase=Acclemma_translit=onomalex_utf8=ὄνομαword=ὄνομα

αὐτοῦ

BOL_lexeme_dict=αὐτός, -ή, -όbook=Gencase=Genlemma_translit=autoslex_utf8=αὐτόςword=αὐτοῦ

Δαν

BOL_lexeme_dict=book=Gencase=Genlemma_translit=Danlex_utf8=Δανword=Δαν

verse 3

Josh 22:2

verse

subverse

καὶ

BOL_lexeme_dict=καίbook=Joshcase=lemma_translit=kailex_utf8=καίword=καὶ

εἶπεν

BOL_lexeme_dict=book=Joshcase=lemma_translit=epolex_utf8=ἔπωword=εἶπεν

αὐτοῖς

BOL_lexeme_dict=αὐτός, -ή, -όbook=Joshcase=Datlemma_translit=autoslex_utf8=αὐτόςword=αὐτοῖς

ὑμεῖς

BOL_lexeme_dict=book=Joshcase=Nomlemma_translit=umeislex_utf8=ὑμεῖςword=ὑμεῖς

ἀκηκόατε

BOL_lexeme_dict=ἀκούωbook=Joshcase=lemma_translit=akouolex_utf8=ἀκούωword=ἀκηκόατε

πάντα

BOL_lexeme_dict=πᾶς, πᾶσα, πᾶνbook=Joshcase=Acclemma_translit=paslex_utf8=πᾶςword=πάντα

ὅσα

BOL_lexeme_dict=ὅσος, -η, -ονbook=Joshcase=Acclemma_translit=ososlex_utf8=ὅσοςword=ὅσα

ἐνετείλατο

BOL_lexeme_dict=ἐντέλλομαιbook=Joshcase=lemma_translit=entellomailex_utf8=ἐντέλλομαιword=ἐνετείλατο

ὑμῖν

BOL_lexeme_dict=book=Joshcase=Datlemma_translit=uminlex_utf8=ὑμῖνword=ὑμῖν

Μωυσῆς

BOL_lexeme_dict=book=Joshcase=Nomlemma_translit=Moseuslex_utf8=Μωσεύςword=Μωυσῆς

ὁ

BOL_lexeme_dict=ὁ, ἡ, τόbook=Joshcase=Nomlemma_translit=olex_utf8=ὁword=ὁ

παῖς

BOL_lexeme_dict=παῖς, -παιδός, ὁ, ἡbook=Joshcase=Nomlemma_translit=paislex_utf8=παῖςword=παῖς

κυρίου

BOL_lexeme_dict=κύριος, -ου, ὁbook=Joshcase=Genlemma_translit=kurioslex_utf8=κύριοςword=κυρίου

καὶ

BOL_lexeme_dict=καίbook=Joshcase=lemma_translit=kailex_utf8=καίword=καὶ

ἐπηκούσατε

BOL_lexeme_dict=ἐπακούωbook=Joshcase=lemma_translit=epakouolex_utf8=ἐπακούωword=ἐπηκούσατε

τῆς

BOL_lexeme_dict=ὁ, ἡ, τόbook=Joshcase=Genlemma_translit=olex_utf8=ὁword=τῆς

φωνῆς

BOL_lexeme_dict=φωνή, -ῆς, ἡbook=Joshcase=Genlemma_translit=phonelex_utf8=φωνήword=φωνῆς

μου

BOL_lexeme_dict=book=Joshcase=Genlemma_translit=moulex_utf8=μουword=μου

κατὰ

BOL_lexeme_dict=κατάbook=Joshcase=lemma_translit=katalex_utf8=κατάword=κατὰ

πάντα

BOL_lexeme_dict=πᾶς, πᾶσα, πᾶνbook=Joshcase=Acclemma_translit=paslex_utf8=πᾶςword=πάντα

ὅσα

BOL_lexeme_dict=ὅσος, -η, -ονbook=Joshcase=Acclemma_translit=ososlex_utf8=ὅσοςword=ὅσα

ἐνετειλάμην

BOL_lexeme_dict=ἐντέλλομαιbook=Joshcase=lemma_translit=entellomailex_utf8=ἐντέλλομαιword=ἐνετειλάμην

ὑμῖν

BOL_lexeme_dict=book=Joshcase=Datlemma_translit=uminlex_utf8=ὑμῖνword=ὑμῖν

verse 4

Judg 13:9

verse

subverse

καὶ

BOL_lexeme_dict=καίbook=Judgcase=lemma_translit=kailex_utf8=καίword=καὶ

ἐπήκουσεν

BOL_lexeme_dict=ἐπακούωbook=Judgcase=lemma_translit=epakouolex_utf8=ἐπακούωword=ἐπήκουσεν

ὁ

BOL_lexeme_dict=ὁ, ἡ, τόbook=Judgcase=Nomlemma_translit=olex_utf8=ὁword=ὁ

θεὸς

BOL_lexeme_dict=θεός, -οῦ, ὁbook=Judgcase=Nomlemma_translit=theoslex_utf8=θεόςword=θεὸς

τῆς

BOL_lexeme_dict=ὁ, ἡ, τόbook=Judgcase=Genlemma_translit=olex_utf8=ὁword=τῆς

φωνῆς

BOL_lexeme_dict=φωνή, -ῆς, ἡbook=Judgcase=Genlemma_translit=phonelex_utf8=φωνήword=φωνῆς

Μανωε

BOL_lexeme_dict=book=Judgcase=Genlemma_translit=Manoelex_utf8=Μανωεword=Μανωε

καὶ

BOL_lexeme_dict=καίbook=Judgcase=lemma_translit=kailex_utf8=καίword=καὶ

παρεγένετο

BOL_lexeme_dict=παραγίνομαιbook=Judgcase=lemma_translit=paraginomailex_utf8=παραγίνομαιword=παρεγένετο

ὁ

BOL_lexeme_dict=ὁ, ἡ, τόbook=Judgcase=Nomlemma_translit=olex_utf8=ὁword=ὁ

ἄγγελος

BOL_lexeme_dict=ἄγγελος, -ου, ὁbook=Judgcase=Nomlemma_translit=aggeloslex_utf8=ἄγγελοςword=ἄγγελος

τοῦ

BOL_lexeme_dict=ὁ, ἡ, τόbook=Judgcase=Genlemma_translit=olex_utf8=ὁword=τοῦ

θεοῦ

BOL_lexeme_dict=θεός, -οῦ, ὁbook=Judgcase=Genlemma_translit=theoslex_utf8=θεόςword=θεοῦ

ἔτι

BOL_lexeme_dict=ἔτιbook=Judgcase=lemma_translit=etilex_utf8=ἔτιword=ἔτι

πρὸς

BOL_lexeme_dict=πρόςbook=Judgcase=lemma_translit=proslex_utf8=πρόςword=πρὸς

τὴν

BOL_lexeme_dict=ὁ, ἡ, τόbook=Judgcase=Acclemma_translit=olex_utf8=ὁword=τὴν

γυναῖκα

BOL_lexeme_dict=γυνή, -αικός, ἡbook=Judgcase=Acclemma_translit=gunelex_utf8=γυνήword=γυναῖκα

αὐτῆς

BOL_lexeme_dict=αὐτός, -ή, -όbook=Judgcase=Genlemma_translit=autoslex_utf8=αὐτόςword=αὐτῆς

καθημένης

BOL_lexeme_dict=κάθημαιbook=Judgcase=lemma_translit=kathemailex_utf8=κάθημαιword=καθημένης

ἐν

BOL_lexeme_dict=ἐνbook=Judgcase=lemma_translit=enlex_utf8=ἐνword=ἐν

τῷ

BOL_lexeme_dict=ὁ, ἡ, τόbook=Judgcase=Datlemma_translit=olex_utf8=ὁword=τῷ

ἀγρῷ

BOL_lexeme_dict=ἀγρός, -οῦ, ὁbook=Judgcase=Datlemma_translit=agroslex_utf8=ἀγρόςword=ἀγρῷ

καὶ

BOL_lexeme_dict=καίbook=Judgcase=lemma_translit=kailex_utf8=καίword=καὶ

Μανωε

BOL_lexeme_dict=book=Judgcase=Nomlemma_translit=Manoelex_utf8=Μανωεword=Μανωε

ὁ

BOL_lexeme_dict=ὁ, ἡ, τόbook=Judgcase=Nomlemma_translit=olex_utf8=ὁword=ὁ

ἀνὴρ

BOL_lexeme_dict=ἀνήρ, ἀνδρός, ὁbook=Judgcase=Nomlemma_translit=anerlex_utf8=ἀνήρword=ἀνὴρ

αὐτῆς

BOL_lexeme_dict=αὐτός, -ή, -όbook=Judgcase=Genlemma_translit=autoslex_utf8=αὐτόςword=αὐτῆς

οὐκ

BOL_lexeme_dict=οὐbook=Judgcase=lemma_translit=oulex_utf8=οὐword=οὐκ

ἦν

BOL_lexeme_dict=εἰμίbook=Judgcase=lemma_translit=eimilex_utf8=εἰμίword=ἦν

μετ᾿

BOL_lexeme_dict=μετάbook=Judgcase=lemma_translit=metalex_utf8=μετάword=μετ᾿

αὐτῆς

BOL_lexeme_dict=αὐτός, -ή, -όbook=Judgcase=Genlemma_translit=autoslex_utf8=αὐτόςword=αὐτῆς

verse 5

2Sam 22:7

verse

subverse

ἐν

BOL_lexeme_dict=ἐνbook=2Samcase=lemma_translit=enlex_utf8=ἐνword=ἐν

τῷ

BOL_lexeme_dict=ὁ, ἡ, τόbook=2Samcase=Datlemma_translit=olex_utf8=ὁword=τῷ

θλίβεσθαί

BOL_lexeme_dict=θλίβωbook=2Samcase=lemma_translit=thlibolex_utf8=θλίβωword=θλίβεσθαί

με

BOL_lexeme_dict=book=2Samcase=Acclemma_translit=melex_utf8=μέword=με

ἐπικαλέσομαι

BOL_lexeme_dict=ἐπικαλέωbook=2Samcase=lemma_translit=epikaleolex_utf8=ἐπικαλέωword=ἐπικαλέσομαι

κύριον

BOL_lexeme_dict=κύριος, -ου, ὁbook=2Samcase=Acclemma_translit=kurioslex_utf8=κύριοςword=κύριον

καὶ

BOL_lexeme_dict=καίbook=2Samcase=lemma_translit=kailex_utf8=καίword=καὶ

πρὸς

BOL_lexeme_dict=πρόςbook=2Samcase=lemma_translit=proslex_utf8=πρόςword=πρὸς

τὸν

BOL_lexeme_dict=ὁ, ἡ, τόbook=2Samcase=Acclemma_translit=olex_utf8=ὁword=τὸν

θεόν

BOL_lexeme_dict=θεός, -οῦ, ὁbook=2Samcase=Acclemma_translit=theoslex_utf8=θεόςword=θεόν

μου

BOL_lexeme_dict=book=2Samcase=Genlemma_translit=moulex_utf8=μουword=μου

βοήσομαι

BOL_lexeme_dict=βοάωbook=2Samcase=lemma_translit=boaolex_utf8=βοάωword=βοήσομαι

καὶ

BOL_lexeme_dict=καίbook=2Samcase=lemma_translit=kailex_utf8=καίword=καὶ

ἐπακούσεται

BOL_lexeme_dict=ἐπακούωbook=2Samcase=lemma_translit=epakouolex_utf8=ἐπακούωword=ἐπακούσεται

ἐκ

BOL_lexeme_dict=ἐκ, ἐξbook=2Samcase=lemma_translit=eklex_utf8=ἐκword=ἐκ

ναοῦ

BOL_lexeme_dict=ναός, -οῦ, ὁbook=2Samcase=Genlemma_translit=naoslex_utf8=ναόςword=ναοῦ

αὐτοῦ

BOL_lexeme_dict=αὐτός, -ή, -όbook=2Samcase=Genlemma_translit=autoslex_utf8=αὐτόςword=αὐτοῦ

φωνῆς

BOL_lexeme_dict=φωνή, -ῆς, ἡbook=2Samcase=Genlemma_translit=phonelex_utf8=φωνήword=φωνῆς

μου

BOL_lexeme_dict=book=2Samcase=Genlemma_translit=moulex_utf8=μουword=μου

καὶ

BOL_lexeme_dict=καίbook=2Samcase=lemma_translit=kailex_utf8=καίword=καὶ

ἡ

BOL_lexeme_dict=ὁ, ἡ, τόbook=2Samcase=Nomlemma_translit=olex_utf8=ὁword=ἡ

κραυγή

BOL_lexeme_dict=κραυγή, -ῆς, ἡbook=2Samcase=Nomlemma_translit=kraugelex_utf8=κραυγήword=κραυγή

μου

BOL_lexeme_dict=book=2Samcase=Genlemma_translit=moulex_utf8=μουword=μου

ἐν

BOL_lexeme_dict=ἐνbook=2Samcase=lemma_translit=enlex_utf8=ἐνword=ἐν

τοῖς

BOL_lexeme_dict=ὁ, ἡ, τόbook=2Samcase=Datlemma_translit=olex_utf8=ὁword=τοῖς

ὠσὶν

BOL_lexeme_dict=οὖς, ὠτός, τόbook=2Samcase=Datlemma_translit=ouslex_utf8=οὖςword=ὠσὶν

αὐτοῦ

BOL_lexeme_dict=αὐτός, -ή, -όbook=2Samcase=Genlemma_translit=autoslex_utf8=αὐτόςword=αὐτοῦ

New Feature Development¶

Morphology¶

MorphGNT:sblgnt Data Description¶

Here: https://github.com/morphgnt/sblgnt

In [406]:

translitadd['lemma']=translitadd[0]
translitadd.head(5)

Out[406]:

	0	lemma
0	βίβλος	βίβλος
1	γένεσις	γένεσις
2	Ἰησοῦς	Ἰησοῦς
3	Χριστός	Χριστός
4	υἱός	υἱός

In [407]:

translitadd=translitadd[['lemma']]
translitadd.head(5)

Out[407]:

	lemma
0	βίβλος
1	γένεσις
2	Ἰησοῦς
3	Χριστός
4	υἱός

In [408]:

translitadd['orig_order'] = translitadd.index +1
translitadd.head(5)

Out[408]:

	lemma	orig_order
0	βίβλος	1
1	γένεσις	2
2	Ἰησοῦς	3
3	Χριστός	4
4	υἱός	5

In [409]:

from unidecode import unidecode

In [410]:

s = "βίβλος"
s = unidecode(s)
print(s)

biblos

In [411]:

translitadd['translit'] = translitadd['lemma'].apply(unidecode)

In [412]:

translitadd.head(5)

Out[412]:

	lemma	orig_order	translit
0	βίβλος	1	biblos
1	γένεσις	2	genesis
2	Ἰησοῦς	3	Iesous
3	Χριστός	4	Khristos
4	υἱός	5	uios

In [413]:

translitadd['translit'].to_csv('d:/OneDrive/1200_AUS-research/Fabric-TEXT/0_data_SBLGNT/feature-dev/lemma_translit.tf', index=None)

ABC dictionary order¶

In [414]:

ABC1=pd.read_csv('d:/OneDrive/1200_AUS-research/Fabric-TEXT/0_data_SBLGNT/feature-dev/lemma_copy.tf',header=None, delimiter='\t',encoding='utf-8')
pd.set_option('display.max_columns', 50)
ABC1.head(10)

Out[414]:

	0
0	βίβλος
1	γένεσις
2	Ἰησοῦς
3	Χριστός
4	υἱός
5	Δαυίδ
6	υἱός
7	Ἀβραάμ
8	Ἀβραάμ
9	γεννάω

In [415]:

ABC1['lemma']=lemma[0]
ABC1.head(5)

Out[415]:

	0	lemma
0	βίβλος	βίβλος
1	γένεσις	γένεσις
2	Ἰησοῦς	Ἰησοῦς
3	Χριστός	Χριστός
4	υἱός	υἱός

In [416]:

ABC1['orig_order'] = ABC1.index +1
ABC1.head(5)

Out[416]:

	0	lemma	orig_order
0	βίβλος	βίβλος	1
1	γένεσις	γένεσις	2
2	Ἰησοῦς	Ἰησοῦς	3
3	Χριστός	Χριστός	4
4	υἱός	υἱός	5

In [417]:

ABC1=ABC1[['orig_order','lemma']]
ABC1.head(5)

Out[417]:

	orig_order	lemma
0	1	βίβλος
1	2	γένεσις
2	3	Ἰησοῦς
3	4	Χριστός
4	5	υἱός

In [418]:

ABC1.describe()

Out[418]:

	orig_order
count	137554.000000
mean	68777.500000
std	39708.563801
min	1.000000
25%	34389.250000
50%	68777.500000
75%	103165.750000
max	137554.000000

In [419]:

ABCdict = ABC1.drop_duplicates(['lemma']).sort_values(by='lemma', ascending=[True])
ABCdict.head(10)

Out[419]:

	orig_order	lemma
68479	68480	Αἰγύπτιος
69633	69634	Αἰθίοψ
70464	70465	Αἰνέας
50739	50740	Αἰνών
679	680	Αἴγυπτος
30811	30812	Αὐγοῦστος
87589	87590	Βάαλ
75520	75521	Βέροια
171	172	Βαβυλών
128506	128507	Βαλάκ

In [420]:

ABCdict.describe()

Out[420]:

	orig_order
count	5461.000000
mean	55051.110969
std	42441.209940
min	1.000000
25%	12643.000000
50%	48785.000000
75%	90141.000000
max	137334.000000

In [421]:

ABC1.to_excel('d:/OneDrive/1200_AUS-research/Fabric-TEXT/0_data_SBLGNT/feature-dev/ABC1order.xlsx', encoding='utf-8')

Now I am ordering the word alphabetically iwth libreoffice writer since I cannot do that in pandas (yet?).

In [422]:

ABC2=pd.read_excel('d:/OneDrive/1200_AUS-research/Fabric-TEXT/0_data_SBLGNT/feature-dev/ABC2order.xlsx')
pd.set_option('display.max_columns', 50)
ABC2.head(10)

Out[422]:

	Unnamed: 0	orig_order	lemma	ABC order
0	29678	29679	Ἀαρών	1
1	131340	131341	Ἀβαδδών	2
2	100253	100254	ἀβαρής	3
3	28001	28002	αββα	4
4	14094	14095	Ἅβελ	5
5	108	109	Ἀβιά	6
6	19523	19524	Ἀβιαθάρ	7
7	31682	31683	Ἀβιληνή	8
8	190	191	Ἀβιούδ	9
9	7	8	Ἀβραάμ	10

Now we merge the ABCorder dataframe with the original lemma DF.

In [423]:

lemma_ABC=pd.merge (ABC1, ABC2,
                      on='lemma',
                      how='outer')
lemma_ABC.head(5)

Out[423]:

	orig_order_x	lemma	orig_order_y	ABC order
0	1	βίβλος	1	970
1	26440	βίβλος	1	970
2	31717	βίβλος	1	970
3	45660	βίβλος	1	970
4	64886	βίβλος	1	970

In [424]:

lemma_ABC.describe()

Out[424]:

	orig_order_x	Unnamed: 0	orig_order_y	ABC order
count	137554.000000	137554.000000	137554.000000	137554.00000
mean	68777.500000	7050.531566	7051.531566	2676.19798
std	39708.563801	20152.248998	20152.248998	1339.74175
min	1.000000	0.000000	1.000000	1.00000
25%	34389.250000	25.000000	26.000000	1501.00000
50%	68777.500000	400.000000	401.000000	2727.00000
75%	103165.750000	2097.250000	2098.250000	3598.00000
max	137554.000000	137333.000000	137334.000000	5461.00000

In [425]:

lemma_ABC.sort_values(['orig_order_x'], ascending=True).head(10)

Out[425]:

	orig_order_x	lemma	Unnamed: 0	orig_order_y	ABC order
0	1	βίβλος	0	1	970
10	2	γένεσις	1	2	1074
15	3	Ἰησοῦς	2	3	2406
921	4	Χριστός	3	4	5385
1449	5	υἱός	4	5	5053
1824	6	Δαυίδ	5	6	1156
1450	7	υἱός	4	5	5053
1883	8	Ἀβραάμ	7	8	10
1884	9	Ἀβραάμ	7	8	10
1956	10	γεννάω	9	10	1077

In [426]:

lemma_ABC.to_excel('d:/OneDrive/1200_AUS-research/Fabric-TEXT/0_data_SBLGNT/feature-dev/lemma_abc.xlsx')

Word Frequency¶

In [427]:

frequencyadd=pd.read_csv('d:/OneDrive/1200_AUS-research/Fabric-TEXT/0_data_SBLGNT/feature-dev/lemma_copy.tf',header=None, delimiter='\t',encoding='utf-8')
pd.set_option('display.max_columns', 50)
frequencyadd.head(20)

Out[427]:

	0
0	βίβλος
1	γένεσις
2	Ἰησοῦς
3	Χριστός
4	υἱός
5	Δαυίδ
6	υἱός
7	Ἀβραάμ
8	Ἀβραάμ
9	γεννάω
10	ὁ
11	Ἰσαάκ
12	Ἰσαάκ
13	δέ
14	γεννάω
15	ὁ
16	Ἰακώβ
17	Ἰακώβ
18	δέ
19	γεννάω

In [428]:

frequencyadd['orig_order'] = frequencyadd.index +1
frequencyadd['lemma']=frequencyadd[0]
frequencyadd=frequencyadd[['orig_order','lemma']]
frequencyadd.head(5)

Out[428]:

	orig_order	lemma
0	1	βίβλος
1	2	γένεσις
2	3	Ἰησοῦς
3	4	Χριστός
4	5	υἱός

In [429]:

frequencyadd["freq_lemma"]=frequencyadd.groupby(["lemma"])["lemma"].transform("count")
#("count") is actually utilizing the 'count' function!
frequencyadd.head(20)

Out[429]:

	orig_order	lemma	freq_lemma
0	1	βίβλος	10
1	2	γένεσις	5
2	3	Ἰησοῦς	906
3	4	Χριστός	528
4	5	υἱός	375
5	6	Δαυίδ	59
6	7	υἱός	375
7	8	Ἀβραάμ	73
8	9	Ἀβραάμ	73
9	10	γεννάω	97
10	11	ὁ	19769
11	12	Ἰσαάκ	20
12	13	Ἰσαάκ	20
13	14	δέ	2766
14	15	γεννάω	97
15	16	ὁ	19769
16	17	Ἰακώβ	27
17	18	Ἰακώβ	27
18	19	δέ	2766
19	20	γεννάω	97

In [430]:

frequencyadd.to_excel('d:/OneDrive/1200_AUS-research/Fabric-TEXT/0_data_SBLGNT/feature-dev/lemma_freq.xlsx')

English Dictionary¶

Lets first load the NA1904 BibleOL dictionary:

In [431]:

BOLgreekDICT=pd.read_excel('d:/OneDrive/1200_AUS-research/Fabric-TEXT/0_data_SBLGNT/feature-dev/NA1904_dictionary_v1.0.xlsx')
pd.set_option('display.max_columns', 50)
BOLgreekDICT.head(20)

Out[431]:

	orig abc order	Occurrences	Lexeme	Lexeme_dict	Strong's number	Strong's unreliable?	gloss
0	1	5	Ἀαρών	Ἀαρών, ὁ	2	no	Aaron
1	2	1	Ἀβαδδών	Ἀβαδδών, ὁ	3	no	Abaddon
2	3	1	ἀβαρής	ἀβαρής, -ές	4	no	not burdensome
3	4	3	ἀββά	ἀββά, ὁ	5	no	Father
4	5	4	Ἅβελ	Ἅβελ, ὁ	6	no	Abel
5	6	3	Ἀβιά	Ἀβιά, ὁ	7	no	Abijah
6	7	1	Ἀβιαθάρ	Ἀβιαθάρ, ὁ	8	no	Abiathar
7	8	1	Ἀβιληνή	Ἀβιληνή, -ῆς, ἡ	9	no	Abilene
8	9	2	Ἀβιούδ	Ἀβιούδ, ὁ	10	no	Abiud
9	10	73	Ἀβραάμ	Ἀβραάμ, ὁ	11	no	Abraham
10	11	9	ἄβυσσος	ἄβυσσος, -ου, ἡ	12	no	abyss, unfathomable depth
11	12	2	Ἅγαβος	Ἅγαβος, -ου, ὁ	13	no	Agabus
12	13	2	ἀγαθοεργέω	ἀγαθοεργέω	14	no	perform good deeds
13	14	9	ἀγαθοποιέω	ἀγαθοποιέω	15	no	do that which is good
14	15	1	ἀγαθοποιΐα	ἀγαθοποιΐα, -ας, ἡ	16	no	doing of that which is good
15	16	1	ἀγαθοποιός	ἀγαθοποιός, -οῦ, ὁ	17	no	a doer of that which is good
16	17	102	ἀγαθός	ἀγαθός, -ή, -όν	18	no	good
17	18	4	ἀγαθωσύνη	ἀγαθωσύνη, -ης, ἡ	19	no	goodness
18	19	5	ἀγαλλίασις	ἀγαλλίασις, -εως, ἡ	20	no	exultation, exhilaration
19	20	11	ἀγαλλιάω	ἀγαλλιάω	21	no	exult, am full of joy

In [432]:

BOLgreekDICT=BOLgreekDICT[['Lexeme','Lexeme_dict', 'Strong\'s number', 'gloss']]
BOLgreekDICT.head(10)

Out[432]:

	Lexeme	Lexeme_dict	Strong's number	gloss
0	Ἀαρών	Ἀαρών, ὁ	2	Aaron
1	Ἀβαδδών	Ἀβαδδών, ὁ	3	Abaddon
2	ἀβαρής	ἀβαρής, -ές	4	not burdensome
3	ἀββά	ἀββά, ὁ	5	Father
4	Ἅβελ	Ἅβελ, ὁ	6	Abel
5	Ἀβιά	Ἀβιά, ὁ	7	Abijah
6	Ἀβιαθάρ	Ἀβιαθάρ, ὁ	8	Abiathar
7	Ἀβιληνή	Ἀβιληνή, -ῆς, ἡ	9	Abilene
8	Ἀβιούδ	Ἀβιούδ, ὁ	10	Abiud
9	Ἀβραάμ	Ἀβραάμ, ὁ	11	Abraham

In [433]:

BOLgreekDICT.describe()

Out[433]:

	Strong's number
count	5433.000000
mean	2798.407878
std	1638.197697
min	1.000000
25%	1370.000000
50%	2754.000000
75%	4237.000000
max	5624.000000

Lets load the SBLGNT lemmas

In [434]:

SBLGNTlemmas=pd.read_csv('d:/OneDrive/1200_AUS-research/Fabric-TEXT/0_data_SBLGNT/feature-dev/lemma_copy.tf',header=None, delimiter='\t',encoding='utf-8')
pd.set_option('display.max_columns', 50)
SBLGNTlemmas.head(2)

Out[434]:

	0
0	βίβλος
1	γένεσις

In [436]:

SBLGNTlemmas['orig_order']=SBLGNTlemmas.index +1
SBLGNTlemmas['Lexeme']=SBLGNTlemmas[0]
SBLGNTlemmas=SBLGNTlemmas[['orig_order','Lexeme']]
SBLGNTlemmas.head(5)

Out[436]:

	orig_order	Lexeme
0	1	βίβλος
1	2	γένεσις
2	3	Ἰησοῦς
3	4	Χριστός
4	5	υἱός

In [437]:

SBLGNTlemmas.describe()

Out[437]:

	orig_order
count	137554.000000
mean	68777.500000
std	39708.563801
min	1.000000
25%	34389.250000
50%	68777.500000
75%	103165.750000
max	137554.000000

Now lets try a merge of the two files

In [438]:

SBLGNTglosses=pd.merge (SBLGNTlemmas,BOLgreekDICT,
                      on='Lexeme',
                      how='outer')
SBLGNTglosses.head(5)

Out[438]:

	orig_order	Lexeme	Lexeme_dict	Strong's number	gloss
0	1.0	βίβλος	NaN	NaN	NaN
1	26440.0	βίβλος	NaN	NaN	NaN
2	31717.0	βίβλος	NaN	NaN	NaN
3	45660.0	βίβλος	NaN	NaN	NaN
4	64886.0	βίβλος	NaN	NaN	NaN

In [439]:

SBLGNTglosses.describe()

Out[439]:

	orig_order	Strong's number
count	138318.000000	54761.000000
mean	68756.590379	3008.488377
std	39712.532678	1209.032138
min	1.000000	1.000000
25%	34366.250000	2041.000000
50%	68753.500000	3588.000000
75%	103162.750000	3706.000000
max	137554.000000	5624.000000

In [440]:

SBLGNTglosses.head(20)

Out[440]:

	orig_order	Lexeme	Lexeme_dict	Strong's number	gloss
0	1.0	βίβλος	NaN	NaN	NaN
1	26440.0	βίβλος	NaN	NaN	NaN
2	31717.0	βίβλος	NaN	NaN	NaN
3	45660.0	βίβλος	NaN	NaN	NaN
4	64886.0	βίβλος	NaN	NaN	NaN
5	68873.0	βίβλος	NaN	NaN	NaN
6	76865.0	βίβλος	NaN	NaN	NaN
7	107214.0	βίβλος	NaN	NaN	NaN
8	128928.0	βίβλος	NaN	NaN	NaN
9	136490.0	βίβλος	NaN	NaN	NaN
10	2.0	γένεσις	NaN	NaN	NaN
11	281.0	γένεσις	NaN	NaN	NaN
12	29821.0	γένεσις	NaN	NaN	NaN
13	120472.0	γένεσις	NaN	NaN	NaN
14	121080.0	γένεσις	NaN	NaN	NaN
15	3.0	Ἰησοῦς	Ἰησοῦς	2424.0	Jesus
16	243.0	Ἰησοῦς	Ἰησοῦς	2424.0	Jesus
17	278.0	Ἰησοῦς	Ἰησοῦς	2424.0	Jesus
18	357.0	Ἰησοῦς	Ἰησοῦς	2424.0	Jesus
19	436.0	Ἰησοῦς	Ἰησοῦς	2424.0	Jesus

In [441]:

SBLGNTglosses.to_excel('d:/OneDrive/1200_AUS-research/Fabric-TEXT/0_data_SBLGNT/feature-dev/SBLGNTglosses.xlsx')

In [ ]:

Table of Contents

Converter file¶

Latest and Greatest¶

Testing¶

New Feature Development¶

Morphology¶

MorphGNT:sblgnt Data Description¶

ABC dictionary order¶

Word Frequency¶

English Dictionary¶