Peshitta NT — Syriac Morphology¶

Word-level morphological analysis of the Syriac Peshitta New Testament.

Data source: ETCBC/syrnt (Text-Fabric) — 109,640 words across all 27 NT books.
Features: part of speech, gender, number, person, state, verbal stem (vs), tense/aspect (vt), Sedra transliterated root and lemma.

Feature	Values
sp	noun, verb, particle, pronoun, adjective, numeral, interjection
gn	m, f, NA
nu	s (singular), p (plural), NA
ps	p1, p2, p3, NA
st	emphatic, construct, absolute, NA
vs	peal, pael, aphel, ethpeel, ethpaal, ettaphal, NA
vt	perf, impf, imptv, ptca (active participle), ptcp (passive participle), inf, NA

In [ ]:

import sys
sys.path.insert(0, '../../../src')

import pandas as pd
import matplotlib
matplotlib.use('Agg')
import matplotlib.pyplot as plt

from bible_grammar.peshitta_query import query_peshitta

df = query_peshitta()
print(f'Loaded {len(df):,} words')
df.head()

import sys sys.path.insert(0, '../../../src') import pandas as pd import matplotlib matplotlib.use('Agg') import matplotlib.pyplot as plt from bible_grammar.peshitta_query import query_peshitta df = query_peshitta() print(f'Loaded {len(df):,} words') df.head()

---

1. Part-of-Speech Distribution¶

In [ ]:

pos = df['sp'].value_counts()
print('Part-of-speech counts:')
print(pos.to_string())

fig, ax = plt.subplots(figsize=(9, 4))
pos.plot(kind='bar', ax=ax, color='#4292c6', edgecolor='white')
ax.set_title('Peshitta NT — Part-of-Speech Distribution', fontsize=12, fontweight='bold')
ax.set_xlabel('')
ax.set_ylabel('Token count')
ax.tick_params(axis='x', rotation=30)
ax.yaxis.grid(True, linestyle='--', alpha=0.4)
ax.set_axisbelow(True)
plt.tight_layout()
plt.savefig('../../../output/charts/nt/peshitta_pos.png', dpi=150, bbox_inches='tight')
plt.show()

pos = df['sp'].value_counts() print('Part-of-speech counts:') print(pos.to_string()) fig, ax = plt.subplots(figsize=(9, 4)) pos.plot(kind='bar', ax=ax, color='#4292c6', edgecolor='white') ax.set_title('Peshitta NT — Part-of-Speech Distribution', fontsize=12, fontweight='bold') ax.set_xlabel('') ax.set_ylabel('Token count') ax.tick_params(axis='x', rotation=30) ax.yaxis.grid(True, linestyle='--', alpha=0.4) ax.set_axisbelow(True) plt.tight_layout() plt.savefig('../../../output/charts/nt/peshitta_pos.png', dpi=150, bbox_inches='tight') plt.show()

---

2. Verbal Stem Distribution (Peshitta)¶

In [ ]:

verbs = df[df['sp'] == 'verb'].copy()
print(f'Total verb tokens: {len(verbs):,}')

stem_counts = verbs['vs'].value_counts()
print('\nVerbal stems:')
print(stem_counts.to_string())

fig, ax = plt.subplots(figsize=(8, 4))
stem_counts.plot(kind='bar', ax=ax, color='#d62728', edgecolor='white')
ax.set_title('Peshitta NT — Verbal Stem Distribution', fontsize=12, fontweight='bold')
ax.set_ylabel('Token count')
ax.tick_params(axis='x', rotation=30)
ax.yaxis.grid(True, linestyle='--', alpha=0.4)
ax.set_axisbelow(True)
plt.tight_layout()
plt.savefig('../../../output/charts/nt/peshitta_verbal_stems.png', dpi=150, bbox_inches='tight')
plt.show()

verbs = df[df['sp'] == 'verb'].copy() print(f'Total verb tokens: {len(verbs):,}') stem_counts = verbs['vs'].value_counts() print('\nVerbal stems:') print(stem_counts.to_string()) fig, ax = plt.subplots(figsize=(8, 4)) stem_counts.plot(kind='bar', ax=ax, color='#d62728', edgecolor='white') ax.set_title('Peshitta NT — Verbal Stem Distribution', fontsize=12, fontweight='bold') ax.set_ylabel('Token count') ax.tick_params(axis='x', rotation=30) ax.yaxis.grid(True, linestyle='--', alpha=0.4) ax.set_axisbelow(True) plt.tight_layout() plt.savefig('../../../output/charts/nt/peshitta_verbal_stems.png', dpi=150, bbox_inches='tight') plt.show()

---

3. Verbal Tense/Aspect by Stem¶

In [ ]:

vt_by_stem = verbs[verbs['vs'] != 'NA'].groupby(['vs', 'vt']).size().unstack(fill_value=0)
print(vt_by_stem)

vt_by_stem = verbs[verbs['vs'] != 'NA'].groupby(['vs', 'vt']).size().unstack(fill_value=0) print(vt_by_stem)

---

4. Lexeme Search — Look Up Any Root¶

In [ ]:

# Search by Sedra transliteration of the root
# e.g. CTB = write, ;MR = say, QDM = before/come before
ROOT = 'CTB'  # write

hits = df[df['root_sedra'] == ROOT].copy()
hits['ref'] = hits['book'] + ' ' + hits['chapter'].astype(str) + ':' + hits['verse'].astype(str)
print(f'Root {ROOT}: {len(hits)} tokens')
print(hits[['ref', 'word', 'sp', 'vs', 'vt', 'st']].to_string())

# Search by Sedra transliteration of the root # e.g. CTB = write, ;MR = say, QDM = before/come before ROOT = 'CTB' # write hits = df[df['root_sedra'] == ROOT].copy() hits['ref'] = hits['book'] + ' ' + hits['chapter'].astype(str) + ':' + hits['verse'].astype(str) print(f'Root {ROOT}: {len(hits)} tokens') print(hits[['ref', 'word', 'sp', 'vs', 'vt', 'st']].to_string())

---

5. Word Distribution by Book¶

In [ ]:

book_order = ['Mat','Mrk','Luk','Jhn','Act','Rom','1Co','2Co','Gal','Eph',
              'Php','Col','1Th','2Th','1Ti','2Ti','Tit','Phm','Heb','Jas',
              '1Pe','2Pe','1Jn','2Jn','3Jn','Jud','Rev']
book_counts = df.groupby('book').size().reindex(book_order).dropna()

fig, ax = plt.subplots(figsize=(13, 4))
ax.bar(range(len(book_counts)), book_counts.values, color='#41ab5d', edgecolor='white')
ax.set_xticks(range(len(book_counts)))
ax.set_xticklabels(book_counts.index, rotation=45, ha='right', fontsize=8)
ax.set_ylabel('Word tokens')
ax.set_title('Peshitta NT — Word Tokens per Book', fontsize=12, fontweight='bold')
ax.yaxis.grid(True, linestyle='--', alpha=0.4)
ax.set_axisbelow(True)
plt.tight_layout()
plt.savefig('../../../output/charts/nt/peshitta_words_per_book.png', dpi=150, bbox_inches='tight')
plt.show()

book_order = ['Mat','Mrk','Luk','Jhn','Act','Rom','1Co','2Co','Gal','Eph', 'Php','Col','1Th','2Th','1Ti','2Ti','Tit','Phm','Heb','Jas', '1Pe','2Pe','1Jn','2Jn','3Jn','Jud','Rev'] book_counts = df.groupby('book').size().reindex(book_order).dropna() fig, ax = plt.subplots(figsize=(13, 4)) ax.bar(range(len(book_counts)), book_counts.values, color='#41ab5d', edgecolor='white') ax.set_xticks(range(len(book_counts))) ax.set_xticklabels(book_counts.index, rotation=45, ha='right', fontsize=8) ax.set_ylabel('Word tokens') ax.set_title('Peshitta NT — Word Tokens per Book', fontsize=12, fontweight='bold') ax.yaxis.grid(True, linestyle='--', alpha=0.4) ax.set_axisbelow(True) plt.tight_layout() plt.savefig('../../../output/charts/nt/peshitta_words_per_book.png', dpi=150, bbox_inches='tight') plt.show()

---

6. Peshitta Verse Lookup (via translations module)¶

In [ ]:

from bible_grammar.translations import load_translations

trans = load_translations()
peshitta = trans[trans['translation'] == 'Peshitta']

# Sample John 1:1-5
sample = peshitta[(peshitta['book_id'] == 'Jhn') & (peshitta['chapter'] == 1) & (peshitta['verse'] <= 5)]
for _, row in sample.iterrows():
    print(f"John {row['chapter']}:{row['verse']}: {row['text']}")

from bible_grammar.translations import load_translations trans = load_translations() peshitta = trans[trans['translation'] == 'Peshitta'] # Sample John 1:1-5 sample = peshitta[(peshitta['book_id'] == 'Jhn') & (peshitta['chapter'] == 1) & (peshitta['verse'] <= 5)] for _, row in sample.iterrows(): print(f"John {row['chapter']}:{row['verse']}: {row['text']}")