{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# Explore edges." ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "from tf.app import use" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [ { "data": { "text/html": [ "TF-app: ~/github/annotation/app-bhsa/code" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "data: ~/text-fabric-data/etcbc/bhsa/tf/c" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "data: ~/text-fabric-data/etcbc/phono/tf/c" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "data: ~/text-fabric-data/etcbc/parallels/tf/c" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "Text-Fabric: Text-Fabric API 8.3.0, app-bhsa, Search Reference
Data: BHSA, Character table, Feature docs
Features:
Parallel Passagescrossref
BHSA = Biblia Hebraica Stuttgartensia Amstelodamensisbook
book@ll
chapter
code
det
domain
freq_lex
function
g_cons
g_cons_utf8
g_lex
g_lex_utf8
g_word
g_word_utf8
gloss
gn
label
language
lex
lex_utf8
ls
nametype
nme
nu
number
otype
pargr
pdp
pfm
prs
prs_gn
prs_nu
prs_ps
ps
qere
qere_trailer
qere_trailer_utf8
qere_utf8
rank_lex
rela
sp
st
tab
trailer
trailer_utf8
txt
typ
uvf
vbe
vbs
verse
voc_lex
voc_lex_utf8
vs
vt
mother
oslots
Phonetic Transcriptionsphono
phono_trailer
" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "
Text-Fabric API: names N F E L T S C TF directly usable
" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "A = use(\"ETCBC/bhsa:clone\", hoist=globals())" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "First determine the from-types and the to-types of nodes connected by a mother edge:" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "From types: ['clause', 'clause_atom', 'phrase', 'phrase_atom', 'subphrase']\n", "To types: ['clause', 'clause_atom', 'phrase', 'phrase_atom', 'subphrase', 'word']\n" ] } ], "source": [ "fromTypes = set()\n", "toTypes = set()\n", "\n", "for f in N.walk():\n", " ts = E.mother.f(f)\n", " if ts:\n", " fromTypes.add(F.otype.v(f))\n", " for t in ts:\n", " toTypes.add(F.otype.v(t))\n", "\n", "print(f\"From types: {sorted(fromTypes)}\")\n", "print(f\"To types: {sorted(toTypes)}\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Now list how many edges there are between all these types:" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " clause =mother( 13897x)=> clause\n", " clause =mother( 13897x)=> clause_atom\n", " clause =mother( 5305x)=> phrase\n", " clause =mother( 5305x)=> phrase_atom\n", " clause =mother( 5305x)=> subphrase\n", " clause =mother( 1567x)=> word\n", " clause_atom =mother( 13897x)=> clause\n", " clause_atom =mother(103496x)=> clause_atom\n", " clause_atom =mother( 5305x)=> phrase\n", " clause_atom =mother( 5305x)=> phrase_atom\n", " clause_atom =mother( 5305x)=> subphrase\n", " clause_atom =mother( 1567x)=> word\n", " phrase =mother( 51x)=> clause\n", " phrase =mother( 51x)=> clause_atom\n", " phrase =mother( 507x)=> phrase\n", " phrase =mother( 507x)=> phrase_atom\n", " phrase =mother( 507x)=> subphrase\n", " phrase =mother( 8x)=> word\n", " phrase_atom =mother( 51x)=> clause\n", " phrase_atom =mother( 51x)=> clause_atom\n", " phrase_atom =mother( 507x)=> phrase\n", " phrase_atom =mother( 13007x)=> phrase_atom\n", " phrase_atom =mother( 507x)=> subphrase\n", " phrase_atom =mother( 1842x)=> word\n", " subphrase =mother( 51x)=> clause\n", " subphrase =mother( 51x)=> clause_atom\n", " subphrase =mother( 507x)=> phrase\n", " subphrase =mother( 507x)=> phrase_atom\n", " subphrase =mother( 22453x)=> subphrase\n", " subphrase =mother( 34968x)=> word\n" ] } ], "source": [ "for fT in sorted(fromTypes):\n", " for tT in sorted(toTypes):\n", " n = E.mother.freqList(nodeTypesFrom=fT, nodeTypesTo=tT)\n", " if n:\n", " print(f\"{fT:>20} =mother({n:>6}x)=> {tT}\")" ] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.7.7" } }, "nbformat": 4, "nbformat_minor": 4 }