2018-11-10¶This notebook is shared as static LE-clustering-KLE-MLE-2018-11-10_.html.
Data: LE-clustering-KLE-MLE-2018-11-10_.
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
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
tmpath = module_path + '/tmp/'
check_dir(tmpath, True, 'none')
table = []
long_table = []
start = time.time()
print(UTC(), ':: module_path =', module_path)
out_dir = module_path + '/output/LE-clustering-KLE-MLE-' + str(UTC())[:10] + '_'
# corpus = 'CDS-caps-br-text+brent9mos'
corpus = 'CDS-caps-br-text'
# dataset = 'LG-English'
dataset = 'LG-English-clean-clean' # only 100% parsed sentences
runs = (1,1)
if runs != (1,1): out_dir += '-multi'
kwargs = {
'left_wall' : '' ,
'period' : False ,
'context' : 2 ,
'min_word_count': 1 ,
'min_link_count': 1 ,
'max_words' : 100000 ,
'max_features' : 100000 ,
'min_co-occurrence_count': 1 ,
'word_space' : 'sparse' ,
'clustering' : ('agglomerative', 'ward'),
'cluster_range' : 200 ,
'clustering_metric' : ('silhouette', 'cosine'),
'grammar_rules' : 2 ,
'max_disjuncts' : 100000 ,
'tmpath' : tmpath ,
'template_path' : 'poc-turtle',
'linkage_limit' : 1000 ,
'verbose' : 'min' }
lines = [
[33, corpus , 'LG-English' ,0,0, 'none' ],
[34, corpus , 'LG-English' ,0,0, 'rules' ],
[35, corpus , 'R=6-Weight=6:R-mst-weight=+1:R' ,0,0, 'none' ],
[36, corpus , 'R=6-Weight=6:R-mst-weight=+1:R' ,0,0, 'rules' ]]
# rp = module_path + '/data/CDS-caps-br-text+brent9mos/LG-English'
# rp = module_path + '/data/CDS-caps-br-text/LG-English' # shorter test 81025
rp = module_path + '/data/CDS-caps-br-text/LG-English-clean-clean'
cp = rp # corpus path = reference_path :: use 'gold' parses as test corpus
corpus = 'CDS-caps-br-text'
dataset = 'LG-English-clean-clean' # only 100% parsed sentences
lines = [[33, corpus, 'LG-English-clean-clean',0, 0, 'none'],
[34, corpus, 'LG-English-clean-clean',0, 0, 'rules']]
%%capture
a, _, header = table_rows(lines, out_dir, cp, rp, runs, **kwargs)
table.extend(a)
display(html_table([header] + a))
%%capture
kwargs['clustering'] = ('k-means', 'kmeans++', 10)
k, _, header = table_rows(lines, out_dir, cp, rp, runs, **kwargs)
table.extend(k)
display(html_table([header] + k))
%%capture
kwargs['clustering'] = ('mean_shift', 2)
m, _, header = table_rows(lines, out_dir, cp, rp, runs, **kwargs)
table.extend(m)
display(html_table([header] + m))
Both "br-text" and "brent9mos" corpora, no cleanup
corpus = 'CDS-caps-br-text+brent9mos'
dataset = 'LG-English'
rp = module_path + '/data/CDS-caps-br-text/LG-English-clean-clean'
cp = rp # corpus path = reference_path
lines = [
[33, corpus , 'LG-English' ,0,0, 'none' ],
[34, corpus , 'LG-English' ,0,0, 'rules' ],
[35, corpus , 'R=6-Weight=6:R-mst-weight=+1:R' ,0,0, 'none' ],
[36, corpus , 'R=6-Weight=6:R-mst-weight=+1:R' ,0,0, 'rules' ]]
%%capture
kwargs['clustering'] = ('agglomerative', 'ward')
a2, _, header = table_rows(lines, out_dir, cp, rp, runs, **kwargs)
table.extend(a2)
display(html_table([header] + a2))
%%capture
kwargs['clustering'] = ('k-means', 'kmeans++', 10)
k2, _, header = table_rows(lines, out_dir, cp, rp, runs, **kwargs)
table.extend(k2)
display(html_table([header] + k2))
%%capture
kwargs['clustering'] = ('mean_shift', 2)
m2, _, header = table_rows(lines, out_dir, cp, rp, runs, **kwargs)
table.extend(m2)
display(html_table([header] + m2))
display(html_table([header] + table))
print(UTC(), ':: finished, elapsed', str(round((time.time()-start)/3600.0, 1)), 'hours')
table_str = list2file(table, out_dir + '/short_table.txt')
print('Results saved to', out_dir + '/short_table.txt')