Gutenberg Children Books agglomerative clustering 2018-12-16

ULLPP Line 50: LG "ANY", all parses, no mst-weight, agm=opt, min_word_count = 11; 2000/1000/500/50/20 clusters

Link Grammar 5.5.1, test_grammar updated 2018-10-19.
This notebook is shared as static Gutenberg-Children-Books-2018-12-16.html.
Output data shared via Gutenberg-Children-Books-2018-12-16 directory.

Basic settings

In [1]:
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)

2018-12-16 17:25:46 UTC :: module_path: /home/obaskov/94/language-learning

Corpus test settings

In [2]:
corpus = 'GCB' # 'Gutenberg-Children-Books-Caps' 
dataset = 'LG-ANY-all-parses-agm-opt'
kwargs = {
    'left_wall'     :   ''          ,
    'period'        :   False       ,
    'context'       :   1           ,
    'min_word_count':   11          ,
    'word_space'    :   'sparse'    ,
    'clustering'    :   ['agglomerative', 'ward'],
    'clustering_metric' : ['silhouette', 'cosine'],
    'cluster_range' :   2000        ,   # 2000/1000/500/50/20
    '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-MST-agm-opt-' + str(UTC())[:10]
if check_corpus(rp, 'min'): print(UTC(), '\n', out_dir)

2018-12-16 17:25:46 UTC 
 /home/obaskov/94/language-learning/output/Gutenberg-Children-MST-agm-opt-2018-12-16

Tests: "LG "ANY", all parses, no mst-weight, agm=opt"

In [3]:
%%capture
table = []
kwargs['cluster_range'] = 2000
line = [['ALE2000', corpus, dataset, 0, 0, 'none']]
a, _, header, log, rules = wide_rows(line, out_dir, cp, rp, runs, **kwargs)
header[0] = 'Cell'
table.extend(a)
In [4]:
display(html_table([header] + a)); print(test_stats(log))
CellCorpusParsingSpaceLinkageAffinityG12nThresholdRulesMWCNNSIPAPQF1Top 5 cluster sizes
ALE2000GCBLG-ANY-all-parses-agm-optcALWEdwardeuclideannone---200011---0.048%27%0.32[]
Cleaned dictionary: 21807 words, grammar learn time: 03:53:13, test time: 00:47:01 (hh:mm:ss)
In [5]:
%%capture
kwargs['cluster_range'] = 1000
line = [['ALE1000', corpus, dataset, 0, 0, 'none']]
a, _, h, log, rules = wide_rows(line, out_dir, cp, rp, runs, **kwargs)
table.extend(a)
In [6]:
display(html_table([header] + a)); print(test_stats(log))
CellCorpusParsingSpaceLinkageAffinityG12nThresholdRulesMWCNNSIPAPQF1Top 5 cluster sizes
ALE1000GCBLG-ANY-all-parses-agm-optcALWEdwardeuclideannone---100011---0.052%29%0.34[]
Cleaned dictionary: 21807 words, grammar learn time: 02:37:14, test time: 01:14:24 (hh:mm:ss)
In [7]:
%%capture
kwargs['cluster_range'] = 500
line = [['ALE500', corpus, dataset, 0, 0, 'none']]
a, _, h, log, rules = wide_rows(line, out_dir, cp, rp, runs, **kwargs)
table.extend(a)
In [8]:
display(html_table([header] + a)); print(test_stats(log))
CellCorpusParsingSpaceLinkageAffinityG12nThresholdRulesMWCNNSIPAPQF1Top 5 cluster sizes
ALE500GCBLG-ANY-all-parses-agm-optcALWEdwardeuclideannone---50011---0.057%32%0.36[]
Cleaned dictionary: 21807 words, grammar learn time: 02:20:44, test time: 02:22:49 (hh:mm:ss)
In [11]:
%%capture
kwargs['cluster_range'] = 50
line = [['ALE50', corpus, dataset, 0, 0, 'none']]
a, _, h, log, rules = wide_rows(line, out_dir, cp, rp, runs, **kwargs)
table.extend(a)
In [12]:
display(html_table([header] + a)); print(test_stats(log))
CellCorpusParsingSpaceLinkageAffinityG12nThresholdRulesMWCNNSIPAPQF1Top 5 cluster sizes
ALE50GCBLG-ANY-all-parses-agm-optcALWEdwardeuclideannone---5011---0.00%0%0.00[]
Cleaned dictionary: 21807 words, grammar learn time: 02:14:54, test time: 00:00:49 (hh:mm:ss)
In [ ]:
%%capture
kwargs['cluster_range'] = 20
line = [['ALE20', corpus, dataset, 0, 0, 'none']]
a, _, h, log, rules = wide_rows(line, out_dir, cp, rp, runs, **kwargs)
table.extend(a)
In [ ]:
display(html_table([header] + a)); print(test_stats(log))

Grammar test failed to complete in 24++ hours. Execution interrupted.

Save results

In [13]:
display(html_table([header] + table))
CellCorpusParsingSpaceLinkageAffinityG12nThresholdRulesMWCNNSIPAPQF1Top 5 cluster sizes
ALE2000GCBLG-ANY-all-parses-agm-optcALWEdwardeuclideannone---200011---0.048%27%0.32[]
ALE1000GCBLG-ANY-all-parses-agm-optcALWEdwardeuclideannone---100011---0.052%29%0.34[]
ALE500GCBLG-ANY-all-parses-agm-optcALWEdwardeuclideannone---50011---0.057%32%0.36[]
ALE50GCBLG-ANY-all-parses-agm-optcALWEdwardeuclideannone---5011---0.00%0%0.00[]
In [14]:
print(UTC(), ':: 2000/1000/500/50 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')

2018-12-17 08:57:02 UTC :: 2000/1000/500/50 finished, elapsed 15.5 hours
Results saved to /home/obaskov/94/language-learning/output/Gutenberg-Children-MST-agm-opt-2018-12-16/all_tests_table.txt