def grammar_learner(clusters, links, **kwargs):
def kwa(v, k):
return kwargs[k] if k in kwargs else v
#-clusters = kwargs['word_clusters']
#-links = kwargs['links']
grammar_rules = kwa(1, 'grammar_rules')
verbose = kwa('none', 'verbose')
if verbose == 'debug': print('\ngrammar_learner rules =', grammar_rules)
from src.grammar_learner.poc04 import links2stalks
from src.utl.turtle import html_table
stalks = links2stalks(links, clusters, grammar_rules, verbose)
rules = stalks.groupby('cluster') \
.agg({'words': 'sum', 'disjuncts': 'sum', 'count': 'sum'}).reset_index()
rules['disjuncts'] = rules['disjuncts'].apply(lambda x: sorted(set(x)))
if verbose == 'debug': print('\nrules', type(rules), '\n', rules)
#FIXME: remove duplicate disjuncts!
rule_list = list()
for row in rules.itertuples():
rule = []
rule.append(row[1]) # Cluster
rule.append(row[2]) # Words
rule.append([]) # Left Connectors
rule.append([]) # Right Connectors
rule.append(row[3]) # Disjuncts
rule_list.append(rule)
rule_list.sort()
if verbose not in ['min', 'none']:
display(
html_table([['Cluster', 'Germs', 'L', 'R', 'Disjuncts']] +
rule_list))
return rule_list, {'rule_list': len(rule_list)}
def save_cat_tree(cats, output_categories, verbose='none'): #80706 0.5
#80611 ~ cats2list without 'djs', children'...
# cats: {'cluster':[], 'words':[], ...} #80609
from copy import deepcopy
from src.utl.write_files import list2file
from src.utl.utl import UTC
tree_file = output_categories
if '.' not in tree_file: #auto file name
if tree_file[-1] != '/': tree_file += '/'
#-tree_file += (str(len(set([x[0] for x in cats_list]))) + '_cat_tree.txt')
n_cats = len(
[x for i, x in enumerate(cats['parent']) if i > 0 and x < 1])
tree_file += (str(n_cats) + '_cat_tree.txt')
categories = []
for i, cluster in enumerate(cats['cluster']):
if i == 0: continue
category = []
if cats['cluster'][i] is not None:
category.append(cats['cluster'][i])
else:
category.append('')
category.append(cats['parent'][i])
category.append(i)
category.append(round(cats['quality'][i], 2))
#!category.append(sorted(cats['words'][i])) #80704+06 tmp hack FIXME
wordz = deepcopy(sorted(cats['words'][i]))
#-80704 word@1, word@2 ⇒ word.a, word.b:
#-wordz = [x.replace('@1','.a') for x in wordz]
#-wordz = [x.replace('@2','.b') for x in wordz]
#-wordz = [x.replace('@3','.c') for x in wordz]
wordz = [x.replace('@', '.')
for x in wordz] #80706 WSD: word@1 ⇒ word.1
category.append(wordz) #80704+06 tmp hack FIXME
#80704+06 end
category.append(cats['similarities'][i])
#-category.append(cats['children'][i])
categories.append(category)
string = list2file(categories, tree_file)
if verbose in ['max', 'debug']:
print(UTC(),':: src/utl.writefiles.py save_cat_tree:', \
len(cats['cluster']) - 1, 'categories')
if verbose == 'debug':
from src.utl.widgets import html_table
from IPython.display import display
display(
html_table(
[['Code', 'Parent', 'Id', 'Sim', 'Words', 'Similarities']] +
categories))
return {'cat_tree_file': tree_file}
def save_category_tree(category_list, tree_file, verbose='none'): #80522
import os
cats = category_list
clusters = {}
m = 0
for i, x in enumerate(cats):
if x[0] not in clusters: clusters[x[0]] = []
clusters[x[0]].append(i)
if x[2] > m: m = x[2]
tree = []
for k, v in clusters.items():
if len(v) == 1:
tree.append(cats[v[0]])
elif len(v) > 1:
words = []
similarities = []
for j in v:
words.extend(cats[j][4])
similarities.extend(cats[j][5])
tree.append(
[cats[v[0]][0], 0, m + 1, cats[v[0]][3], words, similarities])
for j in v:
tree.append([
'', m + 1, cats[j][2], cats[j][3], cats[j][4], cats[j][5]
])
else:
print('WTF?', k, v)
if verbose in ['max', 'debug']:
from src.utl.widgets import html_table
from IPython.display import display
display(
html_table(
[['Code', 'Parent', 'Id', 'Sim', 'Words', 'Similarities']] +
tree))
from src.utl.write_files import list2file
#-tree_file = os.path.dirname(cat_file) + '/cat_tree.txt'
string = list2file(tree, tree_file)
return {'tree_file': tree_file}
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): #80509+10
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.poc04 import number_of_clusters, clusters2list
from src.utl.widgets import html_table, plot2d
from src.utl.write_files import list2file
from src.link_grammar.poc import save_link_grammar
from collections import OrderedDict
log = OrderedDict()
log.update({'category_learner': '80525'})
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('poc04.category_learner: tmpath = ', tmpath)
if verbose == 'debug':
print('category_learner: word_space:', word_space, '/ clustering:',
clustering)
if word_space == 'vectors':
#^from src.space.hyperwords import vector_space_dim, pmisvd
#-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 == 'min': print('Optimal vector space dimensionality:', dim)
#-vdf, sv, res3 = pmisvd(links, dict_path, tmpath, dim)
#-80420 dict_path ⇒ tmpath :: dir to save vectors.txt
vdf, sv, re01 = pmisvd(links, tmpath, tmpath, dim)
log.update(re01)
elif verbose in ['max', 'debug']:
print('category_learner: word_space:', word_space, '/ clustering:',
clustering)
if clustering == 'kmeans':
#^from src.clustering.kmeans import cluster_words_kmeans
#^from src.clustering.poc03 import number_of_clusters, clusters2list
n_clusters = number_of_clusters(vdf, cluster_range ,clustering, \
criteria=cluster_criteria, level=cluster_level, verbose=verbose)
clusters, silhouette, inertia = cluster_words_kmeans(vdf, n_clusters)
if verbose not in ['min', 'none']:
print('/poc04/category_learner: number of clusters =', n_clusters)
if verbose in ['max', 'debug']: print(clusters.applymap(round2))
if verbose in ['max', 'debug']: #80412 hack: plots for AGI-2018 :(
if context == 1: #FIXME:DEL?
plot2d(1, 2, clusters, 'cluster_words', 10)
else:
if len(clusters) < 6:
plot2d(1, 3, clusters, 'cluster_words', 10)
else:
plot2d(1, 4, clusters, 'cluster_words', 10)
elif clustering[:5] in ['group', 'ident']:
if verbose in ['max', 'debug']: print('clustering:', clustering)
#TODO: from src.clustering.grouping import group_links
clusters = group_links(links, verbose)
if verbose not in ['min', 'none']:
print('Total', len(clusters), \
'clusters of identical lexical entries', type(clusters))
if verbose in ['max', 'debug']:
print('\n', clusters[['cluster_words', 'disjuncts']]) #.head(12))
# Generalization = word categories aggregation
if generalization in ['auto', 'jaccard', 'cosine']:
#-print('generalization:', generalization)
#-categories, res2 = aggregate_word_categories(clusters, \
#- generalization, merge, aggregate, grammar_rules, verbose)
categories, re02 = aggregate_word_categories(clusters,
**kwargs) #80510
log.update(re02)
#-print(len(categories), 'categories', type(categories), '\n', categories)
else:
categories = clusters
#-print('generalization:', generalization, '⇒ categories = clusters')
#-Save categories #TODO: return & save outside?
#^from src.clustering.poc04 import clusters2list
#^from src.utl.write_files import list2file
category_list = clusters2list(categories)
if verbose not in ['min', 'none']:
display(html_table([['Code','Parent','Id','Quality','Words','Relevance']] \
+ category_list))
'''80522: save file outside
if '.' not in cats_file: #80508 auto file name
if cats_file[-1] != '/': cats_file += '/'
cats_file += (str(len(set(categories['cluster'].tolist()))) + '_categories.txt')
categories = list2file(category_list, cats_file)
log.update({'categories_file': cats_file})
'''
if verbose in ['debug']:
print('\nWord categories:\n', categories)
#for line in categories.splitlines()[:3]: print(line)
if verbose not in ['min', 'none']:
print('\nCategory list -', len(categories), 'lines, saved to',
cats_file)
return category_list, log
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')
print('learn_grammar: grammar_rules:', grammar_rules)
#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, pickle #, collections
from collections import OrderedDict
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.poc05 import files2links #80528 .poc05
from src.clustering.poc05 import clusters2dict
#+from src.link_grammar.poc05 import category_learner
#+from src.link_grammar.poc05 import induce_grammar
from src.utl.write_files import list2file, save_link_grammar, save_cat_tree
from src.utl.widgets import html_table, plot2d
from src.grammar_learner.generalization import generalize_categories, \
reorder, cats2list, generalize_rules #, aggregate, aggregate_word_categories\
log = OrderedDict({'start': str(UTC()), 'learn_grammar': '80605'})
#TODO: save kwargs?
files, re01 = check_mst_files(input_parses, verbose)
log.update(re01)
if os.path.isdir(output_categories):
prj_dir = output_categories
else:
prj_dir = os.path.dirname(output_categories)
log.update({'project_directory': prj_dir})
#-Save a copy of input parses to prj_dir + '/parses/' #FIXME:DEL? #80704
#-parse_dir = prj_dir + '/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
# files ⇒ links:
links, re02 = files2links(**kwargs)
log.update(re02)
# corpus_stats - implanted in files2links 80605
list2file(re02['corpus_stats'], prj_dir + '/corpus_stats.txt')
log.update({'corpus_stats_file': prj_dir + '/corpus_stats.txt'})
if verbose in ['max', '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)
# Learn categories: new 80619
categories, re03 = category_learner(links, **kwargs) #v.0.5 categories: {}
log.update(re03)
# Generalize categories #TODO? "gen_cats" ⇒ "categories"? no new name
if cats_gen == 'jaccard' or (cats_gen == 'auto' and clustering == 'group'):
if verbose in ['max', 'debug']:
print(UTC(), ':: learn_grammar ⇒ generalize_categories (jaccard)')
gen_cats, re04 = generalize_categories(categories, **kwargs)
log.update(re04)
elif cats_gen == 'cosine' or (cats_gen == 'auto'
and clustering == 'kmeans'):
#TODO: vectors g12n
gen_cats = categories
log.update({'generalization': 'vector-similarity based - #TODO'})
if verbose == 'debug':
print(
'#TODO: categories generalization based on cosine similarity')
else:
gen_cats = categories
log.update({'generalization': 'error: cats_gen = ' + str(cats_gen)})
if verbose in ['max', 'debug']:
print(UTC(),':: learn_grammar: generalization: else: cats_gen =', \
cats_gen, '⇒ gen_cats = categories')
# Save 1st cats_file = to control 2-step generalization #FIXME:DEL? #80704
#-re05 = save_cat_tree(gen_cats, output_categories, verbose)
#-log.update({'category_tree_file': re05['cat_tree_file']})
# Save cats.pkl
#-with open(re05['cat_tree_file'][:-3]+'pkl', 'wb') as f: #FIXME:DEL? #80704
#- pickle.dump(gen_cats, f)
#-if verbose in ['max','debug']:
#- print(UTC(),':: learn_grammar: 1st cat_tree saved')
# Learn grammar #80623
if grammar_rules != context:
context = kwargs['context']
kwargs['context'] = kwargs['grammar_rules']
if verbose in ['max', 'debug']:
print(UTC(), ':: learn_grammar ⇒ files2links(**kwargs)')
links, re06 = files2links(**kwargs)
kwargs['context'] = context
# add disjuncts to categories {} after k-means clustering #TOEO: speed!
def add_disjuncts(cats, links, verbose='none'):
if verbose in ['max', 'debug']:
print(UTC(), ':: add_disjuncts: cats:', len(cats['cluster']),
'clusters')
from copy import deepcopy
top_clusters = [i for i,x in enumerate(cats['cluster']) \
if i > 0 and x is not None]
word_clusters = dict()
for i in top_clusters:
for word in cats['words'][i]:
word_clusters[word] = i
if verbose in ['max', 'debug']:
print(UTC(), ':: add_disjuncts: word_clusters:',
len(word_clusters), 'words')
df = links.copy()
if verbose in ['max', 'debug']:
print(UTC(),
':: add_disjuncts: df[links] = [[x] for x in df[link]]')
df['links'] = [[x] for x in df['link']]
if verbose in ['max', 'debug']:
print(
UTC(),
':: add_disjuncts: df[cluster] = df[word].apply(lambda x: word_clusters[x])'
)
df['cluster'] = df['word'].apply(lambda x: word_clusters[x])
if verbose in ['max', 'debug']:
print(UTC(),
':: add_disjuncts: cdf = df.groupby("cluster").agg(...')
cdf = df.groupby('cluster').agg({
'links': 'sum',
'count': 'sum'
}).reset_index()
#TODO? del df[...] to free RAM?
disjuncts = [[]] + cdf['links'].tolist()
counts = [0] + cdf['count'].tolist()
if verbose in ['max', 'debug']:
print(UTC(),':: add_disjuncts: len(cluster, disjuncts):', \
len(rules['cluster']), len(disjuncts), '\ncounts:', counts)
fat_cats = deepcopy(cats)
fat_cats['counts'] = [0] + cdf['count'].tolist()
fat_cats['disjuncts'] = [[]] + cdf['links'].tolist()
#['djs']
djset = set()
[[djset.add(y) for y in x] for x in fat_cats['disjuncts']]
djlist = sorted(djset)
fat_cats['djs'] = [set([djlist.index(x) for x in y if x in djlist]) \
for y in fat_cats['disjuncts']]
if verbose in ['max', 'debug']:
print(UTC(), ':: add_disjuncts: return fat_cats')
return fat_cats
#TODO: def djs? vectors(disjuncts, **kwargs)
#if context < 2 and grammar_rules > 1:
if word_space == 'vectors' or clustering == 'kmeans':
if verbose in ['max', 'debug']:
print(UTC(), ':: learn_grammar ⇒ add_disjuncts')
#with open(re05['cat_tree_file'][:-9]+'s.pkl', 'wb') as f: #FIXME:DEL tmp 80601
# pickle.dump(gen_cats, f)
fat_cats = add_disjuncts(gen_cats, links)
if verbose in ['max', 'debug']:
print(UTC(), ':: learn_grammar: back from add_disjuncts')
#TODO: fat_cats['djs'] = djs(fat_cats[disjuncts], **kwargs) #TODO:
else:
fat_cats = gen_cats
# Learn Grammar
#+from src.grammar_learner.poc05 import induce_grammar
rules, re07 = induce_grammar(fat_cats, links)
if verbose == 'debug':
print('induce_grammar ⇒ rules:')
display(html_table([['Code','Parent','Id','Quality','Words', 'Disjuncts', 'djs','Relevance','Children']] \
+ [x for i,x in enumerate(cats2list(rules))]))
# Generalize grammar rules
gen_rules = rules
if 'rules_generalization' in kwargs:
if kwargs['rules_generalization'] not in ['', 'off']:
#-word_clusters, re06 = generalize_rules(rule_list, **kwargs)
from src.grammar_learner.generalization import generalize_rules
gen_rules, re08 = generalize_rules(rules, **kwargs)
log.update(re08)
if verbose == 'debug':
print('generalize_rules ⇒ gen_rules:')
display(html_table([['Code','Parent','Id','Quality','Words', 'Disjuncts', 'djs','Relevance','Children']] \
+ [x for i,x in enumerate(cats2list(gen_rules))]))
# Save cat_tree.txt file
#^from src.utl.write_files import save_cat_tree
re09 = save_cat_tree(gen_rules, output_categories,
verbose='none') #FIXME: verbose?
#TODO: check file save error?
log.update(re09)
# Save Link Grammar .dict
re10 = save_link_grammar(gen_rules, output_grammar, grammar_rules)
log.update(re10)
log.update({'finish': str(UTC())})
#TODO: elapsed execution time? Save log?
return log
def induce_grammar(categories,
links,
verbose='none'): #80620 learn_grammar replacement
# categories: {'cluster': [], 'words': [], ...}
# links: pd.DataFrame (legacy)
from src.grammar_learner.generalization import cats2list
import copy
rules = copy.deepcopy(categories)
clusters = [
i for i, x in enumerate(rules['cluster']) if i > 0 and x is not None
]
word_clusters = dict()
for i in clusters:
for word in rules['words'][i]:
word_clusters[word] = i
if verbose == 'debug':
print('induce_grammar: rules.keys():', rules.keys())
print('induce_grammar: clusters:', clusters)
print('induce_grammar: word_clusters:', word_clusters)
print('induce_grammar: rules ~ categories:')
display(html_table([['Code','Parent','Id','Quality','Words', 'Disjuncts', 'djs','Relevance','Children']] \
+ [x for i,x in enumerate(cats2list(rules)) if i < 4]))
for cluster in clusters:
djs = []
for rule in categories['disjuncts'][
cluster]: #FIXME: categories ⇒ rules 80621
# 'a- & was-' ⇒ (-9,-26)
#+TODO? (-x,-y,z) ⇒ (-x,z), (-y,z) ?
if type(rule) is str:
x = rule.split()
dj = []
for y in x:
if y not in ['&', ' ', '']:
if y[-1] == '+':
dj.append(word_clusters[y[:-1]])
elif y[-1] == '-':
dj.append(-1 * word_clusters[y[:-1]])
else:
print('no sign?', dj) #TODO:ERROR?
djs.append(tuple(dj))
if verbose == 'debug':
print('induce_gramma: cluster', cluster, '::', rule, '⇒',
tuple(dj))
#TODO? +elif type(rule) is tuple? connectors - tuples?
rules['disjuncts'][cluster] = set(djs)
if verbose == 'debug':
print('induce_grammar: rules["disjuncts"][' + str(cluster) + ']',
rules['disjuncts'][cluster])
#rules['djs'] = copy.deepcopy(rules['disjuncts']) #TODO: check jaccard with tuples else replace with numbers
if verbose == 'debug':
print('induce_grammar: updated disjuncts:')
from IPython.display import display
from src.utl.widgets import html_table
display(html_table([['Code','Parent','Id','Quality','Words', 'Disjuncts', 'djs','Relevance','Children']] \
+ [x for i,x in enumerate(cats2list(rules)) if i < 32]))
return rules, {'learned_rules': \
len([x for i,x in enumerate(rules['parent']) if x==0 and i>0]), \
'total_clusters': len(rules['cluster']) - 1}