Data Exploration¶

Sanity checks on the parsed STEPBible data.

In [1]:

import sys
sys.path.insert(0, '../../../src')
import pandas as pd
from bible_grammar.query import query, reload
reload()

import sys sys.path.insert(0, '../../../src') import pandas as pd from bible_grammar.query import query, reload reload()

In [2]:

# Overall row counts
all_words = query()
print(f"Total words: {len(all_words):,}")
print(all_words.groupby('source').size())

# Overall row counts all_words = query() print(f"Total words: {len(all_words):,}") print(all_words.groupby('source').size())

Total words: 425,454
source
TAGNT    141720
TAHOT    283734
dtype: int64

In [3]:

# Genesis 1:1 — verify morphology decoding
query(book='Gen', chapter=1, verse=1)[['word','translation','part_of_speech','stem','conjugation','gender','number','state']]

# Genesis 1:1 — verify morphology decoding query(book='Gen', chapter=1, verse=1)[['word','translation','part_of_speech','stem','conjugation','gender','number','state']]

Out[3]:

	word	translation	part_of_speech	stem	conjugation	gender	number	state
0	בְּ/רֵאשִׁ֖ית	in/ beginning	Noun			Feminine	Singular	Absolute
1	בָּרָ֣א	he created	Verb	Qal	Perfect	Masculine	Singular
2	אֱלֹהִ֑ים	God	Noun			Masculine	Plural	Absolute
3	אֵ֥ת	<obj.>	Particle
4	הַ/שָּׁמַ֖יִם	the/ heavens	Noun			Masculine	Plural	Absolute
5	וְ/אֵ֥ת	and/ <obj.>	Particle
6	הָ/אָֽרֶץ\׃	the/ earth	Noun			Feminine	Singular	Absolute

In [4]:

# Matthew 1:1 — verify Greek decoding
query(book='Mat', chapter=1, verse=1)[['word','translation','part_of_speech','tense','voice','mood','case_','number','gender']]

# Matthew 1:1 — verify Greek decoding query(book='Mat', chapter=1, verse=1)[['word','translation','part_of_speech','tense','voice','mood','case_','number','gender']]

Out[4]:

	word	translation	part_of_speech	tense	voice	mood	case_	number	gender
0	Βίβλος	[The] book	Noun				Nominative	Singular	Feminine
1	γενέσεως	of [the] genealogy	Noun				Genitive	Singular	Feminine
2	Ἰησοῦ	of Jesus	Noun				Genitive	Singular	Masculine
3	Χριστοῦ	Christ	Noun				Genitive	Singular	Masculine
4	υἱοῦ	son	Noun				Genitive	Singular	Masculine
5	Δαυὶδ	of David	Noun				Genitive	Singular	Masculine
6	υἱοῦ	son	Noun				Genitive	Singular	Masculine
7	Ἀβραάμ.	of Abraham.	Noun				Genitive	Singular	Masculine

In [5]:

# Part-of-speech distribution (Hebrew)
from bible_grammar.stats import pos_distribution
pos_distribution('TAHOT')

# Part-of-speech distribution (Hebrew) from bible_grammar.stats import pos_distribution pos_distribution('TAHOT')

Out[5]:

	part_of_speech	count
0	Noun	116551
1	Verb	60916
2	Suffix	42745
3	Particle	30255
4	Preposition	10613
5	Adjective	8132
6	Pronoun	5735
7	Adverb	4036
8	a	1958
9	c	1489
10	Conjunction	679
11	o	612
12		13

In [6]:

# Part-of-speech distribution (Greek)
pos_distribution('TAGNT')

# Part-of-speech distribution (Greek) pos_distribution('TAGNT')

Out[6]:

	part_of_speech	count
0	Noun	29363
1	Verb	28517
2	Article	20701
3	Conjunction	18371
4	Pronoun	11518
5	Preposition	11461
6	Adjective	8536
7	Particle	4007
8	Adverb	2355
9	D	1756
10	R	1579
11	Conditional	926
12	I	616
13	X	542
14	Interjection	478
15	F	411
16	S	220
17	K	147
18	C	101
19	Q	27
20	CONJ + G1565=D	20
21	CONJ + G1437=COND	17
22	CONJ + G1564=ADV	10
23	CONJ + G1563=ADV	10
24	COND + G4007=CONJ	9
25	CONJ + G5101=I	6
26	PREP + G1537=PREP + G4057=ADV	3
27	CONJ + G5104=PRT	2
28	PREP + G3029=ADV	2
29	PREP + G4057=ADV	2
30	CONJ + G5104=PRT + G1065=PRT	1
31	PREP + G4155=V	1
32	PRT + G4225=ADV	1
33	PREP + G4521=N	1
34	PREP + G2955=V	1
35	PREP + G0826=V	1
36	ADV + G3461=N	1