2019-04-05
TMWC=21¶"Gutenberg Children Books" corpus, new "LG-E-noQuotes" dataset (GC_LGEnglish_noQuotes_fullyParsed.ull),
trash filter off: min_word_count = 31,21,11,6,2,1
, max_sentence_length
off, Link Grammar 5.5.1;
Test dataset min_word_count = 21
.
This notebook is shared as static TMWC_21_cALEd-500-GCB-LG-E-noQuotes-2019-04-05.html.
Output data shared via TMWC_21_cALEd-500-GCB-LG-E-noQuotes-2019-04-05 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, test_stats
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)
out_dir = module_path + '/output/' + 'TMWC_21_cALEd-500-GCB-LG-E-noQuotes-' + str(UTC())[:10]
if check_dir(out_dir, True): print(out_dir[13:])
corpus = 'GCB' # 'Gutenberg-Children-Books'
dataset = 'LG-E-noQuotes' # 'LG-E-clean'
kwargs = {
'left_wall' : '' ,
'period' : False ,
'context' : 1 , # 1: connector-based word space
'min_word_count': 1 , # 31,21,11,6,1
'word_space' : 'sparse' ,
'clustering' : ['agglomerative', 'ward'],
'clustering_metric' : ['silhouette', 'cosine'],
'cluster_range' : [500] ,
'top_level' : 0.01 ,
'grammar_rules' : 2 , # disjunct-based grammar rules
'max_disjuncts' : 1000000 , # off
'stop_words' : [] ,
'tmpath' : tmpath ,
'verbose' : 'log+' ,
'template_path' : 'poc-turtle',
'linkage_limit' : 1000 }
#rp = module_path + '/data/GCB/LG-E-noQuotes/'
rp = module_path + \
'/data/GCB/GCB-LG-E-noQuotes-filtered-parses/GCB-LG-E-noQuotes-MWC=021.ull'
cp = rp # corpus path = reference_path
if check_dir(rp, False): print(rp[13:])
else: print('Test set not found!')
min_word_count = 51, 31, 21, 11, 6, 2, 1
¶%%capture
table = []
line = [['', corpus, dataset, 0, 0, 'none']]
kwargs['min_word_count'] = 51
a, _, header, log, rules = wide_rows(line, out_dir, cp, rp, runs, **kwargs)
header[0] = ''
table.extend(a)
display(html_table([header] + a)); print(test_stats(log))
display(html_table([header] + a)); print(test_stats(log))
display(html_table([header] + a)); print(test_stats(log))
display(html_table([header] + a)); print(test_stats(log))
display(html_table([header] + a)); print(test_stats(log))
display(html_table([header] + a)); print(test_stats(log))
display(html_table([header] + a)); print(test_stats(log))
display(html_table([header] + table))
print(UTC(), ':: 6 tests 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')