def test_turtle_generalize_both(self):
base = module_path + '/tests/data/POC-Turtle/' + \
'generalized_categories_and_rules/dict_6C_2018-07-06_0005.4.0.dict'
#'generalized_categories_and_rules/poc-turtle_6C_2018-06-08_0004.4.0.dict'
input_parses = module_path + '/tests/data/POC-Turtle/MST_fixed_manually/'
batch_dir = module_path + '/output/Test_Grammar_Learner_' + str(
UTC())[:10] + '/'
prj_dir = batch_dir + 'generalized_categories_and_rules/'
if check_dir(prj_dir, create=True, verbose='max'):
outpath = prj_dir
kwargs = {
'left_wall': 'LEFT-WALL',
'period': True,
'context': 2,
'word_space': 'discrete',
'dim_reduction': 'none',
'clustering': 'group',
'grammar_rules': 2,
'categories_generalization': 'jaccard',
'rules_generalization': 'jaccard',
'tmpath': module_path + '/tmp/',
'verbose': 'none'
}
response = learn_grammar(input_parses, outpath, outpath, **kwargs)
with open(response['grammar_file'], 'r') as f:
rules = f.read().splitlines()
rule_list = [line for line in rules if line[0:1] in ['"', '(']]
with open(base, 'r') as f:
lst = f.read().splitlines()
base_list = [line for line in lst if line[0:1] in ['"', '(']]
if len(rule_list) == len(base_list):
assert rule_list == base_list
else:
assert len(rule_list) == len(base_list)
def learn_lexical_entries(input_dir, cat_path, dict_path, verbose='none', \
parse_mode='given'):
from IPython.display import display
from src.utl.turtle import html_table
from src.utl.read_files import check_dir, check_dir_files, check_corpus
from src.utl.write_files import list2file
from src.link_grammar.turtle import \
files2disjuncts, lexical_entries, entries2clusters, entries2categories, \
disjuncts2clusters, entries2rules, save_link_grammar
if check_dir(input_dir, create=False, verbose=verbose):
files = check_dir_files(input_dir, verbose=verbose)
if len(files) > 0:
if verbose == 'max': print(files)
for i, file in enumerate(files):
if check_corpus(file, verbose=verbose):
if verbose == 'max':
print('File #' + str(i), file, 'checked')
else:
print('File #' + str(i), file, 'check failed')
else:
print('Input directory', input_dir, 'is empty')
else:
print('No input directory', input_dir)
log = {'project': 'Grammar Learner -- Lexical entries'} # use OR DEL?
disjuncts = files2disjuncts(files, 'LEFT-WALL', True, verbose)
#TODO: parse_mode?
entries = lexical_entries(disjuncts)
category_list = entries2categories(entries)
if verbose == 'max':
display(
html_table(
[['Parent', 'Category', 'Quality', 'Words', 'Relevance']] +
category_list))
if cat_path[-1] != '/': cat_path += '/'
cat_file = cat_path + 'categories.txt'
categories = list2file(category_list, cat_file)
if verbose == 'max':
for line in categories.splitlines()[:3]:
print(line)
print('<...>\nTotal', len(categories.splitlines()), 'lines, saved to',
cat_file)
lg_rule_list = entries2rules(disjuncts2clusters(entries2clusters(entries)))
if verbose == 'max':
display(
html_table([['Cluster', 'Germs', 'L', 'R', 'Disjuncts']] +
lg_rule_list))
lg_rules_str = save_link_grammar(lg_rule_list, dict_path)
if verbose == 'max':
for line in lg_rules_str.splitlines():
print(line)
#-return categories, lg_rules_dict
#TODO: return paths to categories and dict?
s = lg_rules_str.splitlines()[-1]
lg_file = s[s.find(': ') + 2:]
response = {'categories_file': cat_file, 'grammar_file': lg_file}
return response
def params(corpus, dataset, module_path, out_dir, **kwargs):
from src.utl.read_files import check_dir
input_parses = module_path + '/data/' + corpus + '/' + dataset
if check_dir(input_parses, create=False, verbose='min'):
batch_dir = out_dir + '/' + corpus
spaces = ['connectors', 'disjuncts']
if kwargs['word_space'] == 'vectors': wtf = 'DRK'
else: wtf = 'ILE'
if kwargs['left_wall'] in ['', 'none']:
left_wall = 'no-LEFT-WALL'
else:
left_wall = 'LEFT-WALL'
if kwargs['period']:
period = 'period'
else:
period = 'no-period'
generalization = ['no_generalization', 'generalized_categories', \
'generalized_rules', 'generalized_categories_and_rules']
gen = 0
if 'categories_generalization' in kwargs:
if kwargs['categories_generalization'] not in ['', 'off']: gen += 1
if 'rules_generalization' in kwargs:
if kwargs['rules_generalization'] not in ['', 'off']: gen += 2
prj_dir = batch_dir + '/' + dataset + '/' + \
spaces[kwargs['context']-1] + '-'+wtf+'-' + spaces[kwargs['grammar_rules']-1] \
+ '/' + left_wall + '_' + period + '/' + generalization[gen]
#-print('params - kwargs[rules_generalization]:', kwargs['rules_generalization'])
#-print('params - kwargs[categories_generalization]:', kwargs['categories_generalization'])
#-print('params - generalization['+str(gen)+'] =', generalization[gen])
#-print('params - prj_dir:', prj_dir)
if check_dir(prj_dir, create=True, verbose='none'):
output_categories = prj_dir # no file name ⇒ auto file name
output_grammar = prj_dir # no file name ⇒ auto file name
return input_parses, output_categories, output_grammar
else:
return input_parses, out_dir, out_dir
else:
raise FileNotFoundError('File not found', input_parses)
def test_turtle_diled(self):
corpus = 'POC-Turtle'
dataset = 'MST_fixed_manually'
input_parses = module_path + '/tests/data/POC-Turtle/MST_fixed_manually/'
base = module_path + '/tests/data/POC-Turtle/' + \
'/2018-04-25/turtle_dILEd_LW+dot+_2018-04-25_0008.4.0.dict'
batch_dir = module_path + '/output/Test_Grammar_Learner_' + str(
UTC())[:10] + '/'
prj_dir = batch_dir + 'Turtle_dILEd_LW_and_period/'
if check_dir(prj_dir, create=True, verbose='max'):
output_categories = prj_dir
output_grammar = prj_dir
kwargs = {
'left_wall': 'LEFT-WALL',
'period': True,
'context': 2,
'word_space': 'discrete',
'dim_reduction': 'none',
'clustering': 'group',
'grammar_rules': 2,
'categories_generalization': 'off',
'rules_generalization': 'off',
'tmpath': module_path + '/tmp/',
'verbose': 'min'
}
response = learn_grammar(input_parses, output_categories,
output_grammar, **kwargs)
with open(response['grammar_file'], 'r') as f:
rules = f.read().splitlines()
rule_list = [line for line in rules if line[0:1] in ['"', '(']]
with open(base, 'r') as f:
lst = f.read().splitlines()
base_list = [line for line in lst if line[0:1] in ['"', '(']]
if len(rule_list) == len(base_list):
if kwargs['verbose'] == 'debug':
print('\nTest results vs baseline:')
for i, rule in enumerate(base_list):
print(rule_list[i])
print(rule)
assert rule_list == base_list
else:
assert len(rule_list) == len(base_list)
def learn_grammar(input_parses, output_categories, output_grammar, **kwargs):
# input_parses - dir with .txt files
# output_categories - path/file.ext / dir ⇒ auto file name
# output_grammar - path/file.ext / dir ⇒ auto file name
def kwa(v, k):
return kwargs[k] if k in kwargs else v
tmpath = kwa('', 'tmpath')
parse_mode = kwa('given', 'parse_mode')
left_wall = kwa('', 'left_wall')
period = kwa(False, 'period')
context = kwa(1, 'context')
window = kwa('mst', 'window')
weighting = kwa('ppmi', 'weighting')
#? distance = kwa(??, 'distance')
group = kwa(True, 'group')
word_space = kwa('vectors', 'word_space')
dim_max = kwa(100, 'dim_max')
sv_min = kwa(0.1, 'sv_min')
dim_reduction = kwa('svm', 'dim_reduction')
clustering = kwa('kmeans', 'clustering')
#-cluster_range = kwa((2,48,1), 'cluster_range')
#-cluster_criteria = kwa('silhouette', 'cluster_criteria')
#-cluster_level = kwa(0.9, 'cluster_level')
cats_gen = kwa('off', 'categories_generalization')
#-cats_merge = kwa(0.8, 'categories_merge')
#-cats_aggr = kwa(0.2, 'categories_aggregation')
grammar_rules = kwa(1, 'grammar_rules')
rules_gen = kwa('off',
'rules_generalization') # 'off', 'cosine', 'jaccard'
#-rules_merge = kwa(0.8, 'rules_merge'), # merge rules with similarity > this 'merge' criteria
#-rules_aggr = kwa(0.3, 'rules_aggregation'), # aggregate rules with similarity > this criteria
verbose = kwa('none', 'verbose')
#80509 kwargs tests ~OK
#-print('poc04 learn_grammar kwargs:')
#-for k,v in kwargs.items(): print(('- '+k+': ')[:20], v)
#-response = print_kwargs(**kwargs)
#-return response
#80509 TODO: renamed parameters ⇒ update code
kwargs['input_parses'] = input_parses
kwargs['output_categories'] = output_categories
kwargs['output_grammar'] = output_grammar
#TODO: if parameter != file: auto file name
input_dir = input_parses
#cat_path = output_categories
#-dict_path = output_grammar
import os #, collections
import pandas as pd
from shutil import copy2 as copy
from src.utl.utl import UTC
from src.utl.read_files import check_dir, check_mst_files
from src.space.poc04 import files2links
#+from src.link_grammar.poc04 import category_learner
from src.clustering.poc04 import clusters2dict
#+from src.link_grammar.poc04 import grammar_learner
#-from src.link_grammar.poc import save_link_grammar
from src.utl.write_files import list2file, save_link_grammar
from src.utl.widgets import html_table, plot2d
from collections import OrderedDict
log = OrderedDict({'datime': str(UTC()), 'learn_grammar': '80511'})
#log.update({'datime': str(UTC()), 'learn_grammar': '80510'})
files, re01 = check_mst_files(input_parses, verbose)
log.update(re01)
#for file in files: copy(file, output_categories)
#TODO: output_categories file ⇒ dir
if os.path.isdir(output_categories):
parse_dir = output_categories + '/parses/'
else:
parse_dir = os.path.dirname(output_categories) + '/parses/'
if check_dir(parse_dir, True, verbose):
for file in files:
copy(file, os.path.dirname(parse_dir))
else:
raise FileNotFoundError('File not found', input_parses)
# group = True #? always? False option for context = 0 (words)?
kwargs['input_files'] = files
links, re02 = files2links(**kwargs)
log.update(re02)
if verbose == 'debug':
print('\nfiles2links returns links', type(links), ':\n')
with pd.option_context('display.max_rows', 6):
print(links, '\n')
print('learn_grammar: word_space:', word_space, '/ clustering:',
clustering)
category_list, re03 = category_learner(links, **kwargs)
log.update(re03)
word_clusters = clusters2dict(category_list)
# Save 1st cats_file = to control 2-step generalization #FIXME:DEL
cats_file = output_categories
if '.' not in cats_file: #80508 auto file name
if cats_file[-1] != '/': cats_file += '/'
cats_file += (str(len(set([x[0] for x in category_list]))) +
'_categories.txt')
#TODO: comment saving cats_file and run tests 80523
#+categories = list2file(category_list, cats_file)
log.update({'categories_file': cats_file})
#...TODO... hierarchical categories 80523 snooze
#...display(html_table([['Code','Parent','Id','Quality','Words','Relevance']] \
#... + category_list))
if grammar_rules != context:
#-links, res4 = files2links(files, parse_mode, grammar_rules, group, left_wall, period, verbose)
context = kwargs['context']
kwargs['context'] = kwargs['grammar_rules']
links, re04 = files2links(**kwargs)
kwargs['context'] = context
rule_list, re05 = grammar_learner(word_clusters, links, **kwargs)
log.update(re05)
#...display(html_table([['Rules','','','','','']] + rule_list))
if 'rules_generalization' in kwargs:
if kwargs['rules_generalization'] not in ['', 'off']:
#-word_clusters, re06 = generalize_rules(rule_list, **kwargs)
cats_list, re06 = generalise_rules(rule_list, **kwargs)
#TODO: = generalise_rules(rule_list, **kwargs)
log.update(re06)
if len(set([x[0] for x in cats_list])) < len(
set([x[0] for x in category_list])):
category_list = cats_list
# Save 2nd cats_file - overwrite in case of equal
cats_file = output_categories
if '.' not in cats_file: #80508 auto file name
if cats_file[-1] != '/': cats_file += '/'
cats_file += (str(len(set([x[0]
for x in category_list]))) +
'_categories.txt')
#TODO: comment saving cats_file and run tests 80523
#+categories = list2file(category_list, cats_file)
log.update({'categories_file': cats_file})
word_clusters = clusters2dict(category_list)
rule_list, re07 = grammar_learner(word_clusters, links,
**kwargs)
#...display(html_table([['Rules','','','','','']] + rule_list))
log.update(re07)
if verbose == 'debug':
print('\nrules_generalisation ⇒ category_list:',
category_list)
if verbose not in ['min', 'none']:
display(html_table([['Code','Parent','Id','Quality','Words','Relevance']] \
+ category_list))
# Save cat_tree.txt file
from src.utl.write_files import save_category_tree
tree_file = cats_file[:cats_file.rindex('_')] + '_cat_tree.txt'
re08 = save_category_tree(category_list, tree_file,
verbose) #FIXME: verbose?
log.update(re08)
# Save Link Grammar .dict
re09 = save_link_grammar(rule_list, output_grammar)
log.update(re09)
return log
def category_learner(links, **kwargs): #80619 POC.0.5
# links - DataFrame ['word', 'link', 'count']
def kwa(v, k):
return kwargs[k] if k in kwargs else v
#-links = kwargs['links'] # links - check?
cats_file = kwa('/output', 'output_categories') # to define tmpath
#-dict_path = kwa('/output', 'output_grammar') # not used here
tmpath = kwa('', 'tmpath')
parse_mode = kwa('given', 'parse_mode')
left_wall = kwa('', 'left_wall')
period = kwa(False, 'period')
context = kwa(1, 'context')
window = kwa('mst', 'window')
weighting = kwa('ppmi', 'weighting')
#? distance = kwa(??, 'distance')
group = kwa(True, 'group')
word_space = kwa('vectors', 'word_space')
dim_max = kwa(100, 'dim_max')
sv_min = kwa(0.1, 'sv_min')
dim_reduction = kwa('svm', 'dim_reduction')
clustering = kwa('kmeans', 'clustering')
cluster_range = kwa((2, 48, 1), 'cluster_range')
cluster_criteria = kwa('silhouette', 'cluster_criteria')
cluster_level = kwa(0.9, 'cluster_level')
generalization = kwa('off', 'categories_generalization')
merge = kwa(0.8, 'categories_merge')
aggregate = kwa(0.2, 'categories_aggregation')
grammar_rules = kwa(1, 'grammar_rules')
verbose = kwa('none', 'verbose')
from src.utl.utl import UTC, round1, round2 #, round3, round4, round5
from src.space.hyperwords import vector_space_dim, pmisvd
from src.clustering.kmeans import cluster_words_kmeans
from src.clustering.poc05 import number_of_clusters, clusters2list
from src.utl.widgets import html_table, plot2d
from src.utl.read_files import check_dir #, check_mst_files
from src.utl.write_files import list2file, save_link_grammar
#-from src.grammar_learner.poc05 import group_links, \
#- aggregate_cosine, aggregate_jaccard, aggregate_word_categories
from collections import OrderedDict
log = OrderedDict()
log.update({'category_learner': '80619'})
if tmpath == '' or tmpath == 'auto': # temporary files path
if '.' not in cats_file: tmpath = cats_file
else: tmpath = cats_file[:cats_file.rindex('/')]
if tmpath[-1] != '/': tmpath += '/'
tmpath += 'tmp/'
print('tmpath:', tmpath)
if check_dir(tmpath, True, verbose):
log.update({'tmpath': tmpath})
#TODO:ERROR
if verbose == 'debug':
print('category_learner: word_space:', word_space, '/ clustering:',
clustering)
#-if word_space == 'vectors': #80619 Category-Tree-2018-06-19.ipynb
if context == 1 or word_space[0] in ['v', 'e'] or clustering == 'kmeans':
#word_space options: v,e: 'vectors'='embeddings', d,w: 'discrete'='word_vectors'
print('DRK: context =',
str(context) + ', word_space: ' + word_space + ', clustering:',
clustering)
#-dim = vector_space_dim(links, dict_path, tmpath, dim_max, sv_min, verbose)
#-80420 dict_path ⇒ tmpath :: dir to save vectors.txt
dim = vector_space_dim(links, tmpath, tmpath, dim_max, sv_min, verbose)
log.update({'vector_space_dim': dim})
if verbose in ['mid', 'max', 'debug']:
print('Optimal vector space dimensionality:', dim)
#-vdf, sv, res3 = pmisvd(links, dict_path, tmpath, dim)
vdf, sv, re01 = pmisvd(links, tmpath, tmpath, dim)
log.update(re01)
#-if clustering == 'kmeans':
if verbose in ['max', 'debug']:
print(UTC(), ':: category_learner ⇒ number_of_clusters')
n_clusters = number_of_clusters(vdf, cluster_range, clustering, \
criteria=cluster_criteria, level=cluster_level, verbose=verbose)
log.update({'n_clusters': n_clusters})
if verbose in ['max', 'debug']:
print(UTC(), ':: category_learner ⇒ cluster_words_kmeans:',
n_clusters, 'clusters')
clusters, silhouette, inertia = cluster_words_kmeans(vdf, n_clusters)
log.update({'silhouette': silhouette, 'inertia': inertia})
#-elif clustering[:5] in ['group','ident']:
else:
if verbose in ['max', 'debug']:
print(UTC(),':: category_learner ⇒ iLE group_links: context =', \
str(context)+', word_space: '+str(word_space)+', clustering:', clustering)
#TODO: from src.clustering.grouping import group_links
clusters = group_links(links, verbose)
log.update({'n_clusters': len(clusters)})
if verbose not in ['min', 'none']:
print('Total', len(clusters), \
'clusters of identical lexical entries', type(clusters))
# Convert clusters DataFrame ⇒ cats {} #80619 0.5
#TODO?: if clusters == pd.dataframe:
if verbose in ['max', 'debug']:
print(UTC(), ':: category_learner: convert clusters ⇒ cats {}')
cats = {} #80609 dict instead of DataFrame
cats['cluster'] = ['C0'] + clusters['cluster'].tolist()
cats['parent'] = [0 for x in cats['cluster']]
cats['words'] = [[]] + [set(x) for x in clusters['cluster_words'].tolist()]
if 'disjuncts' in clusters:
cats['disjuncts'] = [[]] + clusters['disjuncts'].tolist()
djset = set()
[[djset.add(y) for y in x] for x in cats['disjuncts']]
djlist = sorted(djset)
cats['djs'] = [set([djlist.index(x) for x in y if x in djlist]) \
for y in cats['disjuncts']]
if 'counts' in clusters:
cats['counts'] = [0] + clusters['counts'].tolist()
if word_space == 'vectors' or clustering == 'kmeans':
cats['quality'] = [0 for x in cats['words']]
cats['similarities'] = [[0 for y in x] for x in cats['words']]
else:
cats['quality'] = [1 for x in cats['words']]
cats['quality'][0] = 0
cats['similarities'] = [[1 for y in x] for x in cats['words']]
cats['similarities'][0] = [0]
cats['children'] = [0 for x in cats['words']]
return cats, log