2018-12-13_beta¶500 clusters, min_word_count = 361, 21, 11, 2
Link Grammar 5.5.1, test_grammar updated 2018-10-19.
This notebook is shared as static Gutenberg-Children-Books-2018-12-13.html.
Output data shared via Gutenberg-Children-Books-2018-12-13 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)
#print(UTC(), ':: module_path =', module_path)
corpus = 'GCB' # 'Gutenberg-Children-Books-Caps'
dataset = 'LG-English'
kwargs = {
'left_wall' : '' ,
'period' : False ,
'context' : 1 ,
'min_word_count': 31 , # 31/21/11/2
'word_space' : 'sparse' ,
'clustering' : ['agglomerative', 'ward'],
'clustering_metric' : ['silhouette', 'cosine'],
'cluster_range' : 500 ,
'top_level' : 0.01 ,
'grammar_rules' : 2 ,
'max_disjuncts' : 1000000 , # off
'tmpath' : tmpath ,
'verbose' : 'min' ,
'template_path' : 'poc-turtle',
'linkage_limit' : 1000 }
rp = module_path + '/data/' + corpus + '/LG-E-clean/GCB-LG-English-clean.ull'
cp = rp # corpus path = reference_path
runs = (1,1)
out_dir = module_path + '/output/' + 'Gutenberg-Children-Books-Caps-' + str(UTC())[:10]
if check_corpus(rp, 'min'): print(UTC(), out_dir)
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))
%%capture
kwargs['min_word_count'] = 1
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)); print(test_stats(log))
display(html_table([header] + table))