2018-12-08¶Tests: "LG English", no limits, 10/50/500/1000/2000 clusters.
Agglomerative clustering, test_grammar updated 2018-10-19 , Link Grammar 5.4.4.
This notebook is shared as static Gutenberg-Children-Books-2018-12-08.html.
The "All tests" table is shared as 'all_tests_table.txt' in Gutenberg-Children-Books-2018-12-08 directory.
import os, sys, time
module_path = os.path.abspath(os.path.join('..'))
if module_path not in sys.path: sys.path.append(module_path)
from src.grammar_learner.utl import UTC
from src.grammar_learner.read_files import check_dir, check_corpus
from src.grammar_learner.write_files import list2file
from src.grammar_learner.widgets import html_table
from src.grammar_learner.pqa_table import table_rows, params, wide_rows
tmpath = module_path + '/tmp/'
check_dir(tmpath, True, 'none')
start = time.time()
runs = (1,1)
#print(UTC(), ':: module_path =', module_path)
corpus = 'Gutenberg-Children-Books-Caps'
dataset = 'LG-English'
kwargs = {
'left_wall' : '' ,
'period' : False ,
'context' : 1 ,
'min_word_count': 31 , # ~7K words
'word_space' : 'sparse' ,
'clustering' : ['agglomerative', 'ward'],
'clustering_metric' : ['silhouette', 'cosine'],
'cluster_range' : 1000 ,
'top_level' : 0.01 ,
'grammar_rules' : 2 ,
'max_disjuncts' : 1000000 , # off
'tmpath' : tmpath ,
'verbose' : 'min' ,
'template_path' : 'poc-turtle',
'linkage_limit' : 1000 } # no tests
lines = [
[45, corpus , 'LG-English' ,0,0, 'none' ],
[46, corpus , 'LG-ANY-all-parses-agm-opt' ,0,0, 'none' ]]
rp = module_path + '/data/' + corpus + '/LG-E-clean/GCB-LG-English-clean.ull'
# rp = module_path + '/data/' + corpus + '/LG-English/pg24878.txt_headless_split_U.ull'
cp = rp # corpus path = reference_path :: use 'gold' parses as test corpus
runs = (1,1)
out_dir = module_path + '/output/' + corpus + '-' + str(UTC())[:10]
#if check_corpus(rp, 'min'): print(UTC(), out_dir)
%%capture
table = []
kwargs['cluster_range'] = 2000
line = [[2.1, corpus, dataset, 0, 0, 'none']]
#a, _, header, log, rules = wide_rows([lines[0]], out_dir(**kwargs), cp, rp, runs, **kwargs)
a, _, header, log, rules = wide_rows(line, out_dir, cp, rp, runs, **kwargs)
table.extend(a)
display(html_table([header] + a))
%%capture
kwargs['cluster_range'] = 1000
line = [[2.2, corpus, dataset, 0, 0, 'none']]
a, _, header, log, rules = wide_rows(line, out_dir, cp, rp, runs, **kwargs)
table.extend(a)
display(html_table([header] + a))
%%capture
kwargs['cluster_range'] = 500
line = [[2.3, corpus, dataset, 0, 0, 'none']]
a, _, header, log, rules = wide_rows(line, out_dir, cp, rp, runs, **kwargs)
table.extend(a)
display(html_table([header] + a))
%%capture
kwargs['cluster_range'] = 100
line = [[2.4, corpus, dataset, 0, 0, 'none']]
a, _, header, log, rules = wide_rows(line, out_dir, cp, rp, runs, **kwargs)
table.extend(a)
display(html_table([header] + a))
%%capture
kwargs['cluster_range'] = 50
line = [[2.5, corpus, dataset, 0, 0, 'none']]
a, _, header, log, rules = wide_rows(line, out_dir, cp, rp, runs, **kwargs)
table.extend(a)
display(html_table([header] + a))
%%capture
kwargs['cluster_range'] = 20
line = [[2.6, corpus, dataset, 0, 0, 'none']]
a, _, header, log, rules = wide_rows(line, out_dir, cp, rp, runs, **kwargs)
table.extend(a)
display(html_table([header] + a))
%%capture
kwargs['cluster_range'] = 10
line = [[2.7, corpus, dataset, 0, 0, 'none']]
a, _, header, log, rules = wide_rows(line, out_dir, cp, rp, runs, **kwargs)
table.extend(a)
display(html_table([header] + a))
display(html_table([header] + table))
Interrupted after 51+ hours run with 10 clusters setting
print(UTC(), ':: finished, elapsed', str(round((time.time()-start)/3600.0, 1)), 'hours')
table_str = list2file(table, out_dir + '/all_tests_table.txt')
print('Results saved to', out_dir + '/all_tests_table.txt')