def clean(corpus, routine):
print """
========================
---- CLEAN SEGMENTS ----
========================
"""
# change routine type
routine.type = "CLEAN"
routine.save()
transaction.commit()
number_of_links = Document_Segment.objects.filter(document__corpus=corpus).count()
loops = int(math.ceil(number_of_links / 25.0))
# print "corpus: %s" % corpus.json()
# print "number_of_links: %s" % number_of_links
# print "loops: %s" % loops
try:
# manually change
for i in range(0, loops):
for j in Document_Segment.objects.filter(document__corpus=corpus)[0:25]:
j.segment.delete()
j.delete()
log_routine(routine, completion=float(i) / loops)
transaction.commit()
log_routine(routine, completion=1.0)
except Exception, e:
close_routine(routine, error="Ho trovato Wally 149, Exception: %s" % e, status="ERR")
transaction.commit()
def importcsv(routine, csvfile, column="stemmed"):
print """
========================================
---- IMPORT SEGMENTS ROM REFINE CSV ----
========================================
"""
log_routine(routine, entry="importcsv started", completion=0)
transaction.commit()
rows = list(csvfile)
totalrows = len(rows)
for i, row in enumerate(rows):
# update stemmed_refined cell
try:
s = Segment.objects.get(id=row["segment_id"])
buffer_stemmed = s.stemmed
s.stemmed = row["concept"]
s.stemmed_refined = buffer_stemmed
s.save()
except Exception, e:
# print " segemnt id %s was not found!" % row['segment_id']
close_routine(routine, error="Exception: %s %s" % (e, row), status="ERR")
transaction.commit()
return
if i % 25 == 0:
log_routine(routine, entry="importcsv at line: %s" % i, completion=i / float(totalrows))
print i, i / float(totalrows)
transaction.commit()
def tf_tfidf( corpus, routine ):
number_of_documents = Document.objects.filter(corpus=corpus ).count()
if number_of_documents == 0:
return close_routine( routine, error="tfidf routine: no document found", status="OK")
logger.info("starting TF computation on corpus '%s' [%s], %s documents" % (corpus.name, corpus.id, number_of_documents))
tf( corpus=corpus, routine=routine, completion_start=0.0, completion_score=0.4 )
logger.info("TF computation done")
if routine.status == "ERR":
logger.error("TF computation failed on corpus '%s' [%s]" % (corpus.name, corpus.id))
return
logger.info("TF computation done on corpus '%s' [%s]" % (corpus.name, corpus.id ))
logger.info("starting TFIDF computation on corpus '%s' [%s], %s documents" % (corpus.name, corpus.id, number_of_documents))
tfidf( corpus=corpus, routine=routine, completion_start=0.4, completion_score=0.4 )
if routine.status == "ERR":
logger.error("TFIDF computation failed on corpus '%s' [%s]" % (corpus.name, corpus.id))
return
logger.info("TFIDF computation done on corpus '%s' [%s]" % (corpus.name, corpus.id ))
logger.info("starting SIMILARITY computation on corpus '%s' [%s], %s documents" % (corpus.name, corpus.id, number_of_documents ))
similarity( corpus=corpus, routine=routine, completion_start=0.8, completion_score=0.2 )
logger.info("SIMILARITY computation done on corpus '%s' [%s]" % (corpus.name, corpus.id ))
close_routine( routine, error="", status="OK" )
def tf( corpus, routine, completion_start=0.0, completion_score=1.0 ):
print """
======================
---- TF, RELOADED ----
======================
"""
# change routine type
routine.type = "TF"
routine.save()
transaction.commit()
# get percentage info:
number_of_documents_segments = Document_Segment.objects.count()
logger.info( "number_of_documents_segments: %s" % number_of_documents_segments )
if number_of_documents_segments == 0:
logger.error( "TF Not enought segments in your corpus. Try 'standard' routine first..." )
close_routine( routine, error="Not enought segments in your corpus. Try 'standard' routine first...", status="ERR")
transaction.commit()
return
current_segment = 0
for d in Document.objects.filter(corpus=corpus):
# print "document: %s" % d
number_of_stems_per_document = Document_Segment.objects.filter( document=d, segment__status='IN' ).values('segment__stemmed').distinct().count()
# print "number_of_stems_per_document: %s" % number_of_stems_per_document
logger.info( "document '%s' [%s], number of 'pseudo-stems': %s" % (d.title, d.id, number_of_stems_per_document) )
for ds in Document_Segment.objects.filter( document=d, segment__status='IN'):
# count alliases( segment with same stemmed version )
number_of_aliases = Document_Segment.objects.filter( document=d, segment__status='IN', segment__stemmed=ds.segment.stemmed ).count()
ds.tf = float(number_of_aliases) / number_of_stems_per_document
ds.save()
if number_of_aliases > 1: # print just some lines
pass
# print ds.segment.content, ds.segment.stemmed, number_of_aliases, ds.tf
if current_segment % 25 == 0:
logger.info( "document '%s' [%s], completion: %s" % (d.title, d.id, ( float(current_segment) / number_of_documents_segments ) ) )
log_routine( routine, completion = completion_start + ( float(current_segment) / number_of_documents_segments ) * (completion_score-completion_start) )
transaction.commit()
current_segment = current_segment + 1
logger.info( "document '%s' [%s] completed!" % (d.title, d.id ) )
if completion_score == 1.0:
logger.info( "closing routine, task completed" )
close_routine( routine, error="", status="OK" )
transaction.commit()
def standard(corpus, routine):
number_of_documents = Document.objects.filter(corpus=corpus).count()
if number_of_documents == 0:
return close_routine(routine, error="No document found", status="ERR")
# 1. distiller.decant (tf computation )
try:
decant(corpus=corpus, routine=routine, settings=settings, ref_completion=0.5)
except Exception, e:
return close_routine(routine, error="Exception: %s" % e, status="ERR")
def tf(corpus, routine, completion_start=0.0, completion_score=1.0):
print """
======================
---- TF, RELOADED ----
======================
"""
# change routine type
routine.type = "TF"
routine.save()
transaction.commit()
# get percentage info:
number_of_documents_segments = Document_Segment.objects.count()
print "number_of_documents_segments: %s" % number_of_documents_segments
if number_of_documents_segments == 0:
close_routine(
routine, error="Not enought segments in your corpus. Try 'standard' routine first...", status="ERR"
)
transaction.commit()
return
current_segment = 0
for d in Document.objects.filter(corpus=corpus):
print "document: %s" % d
number_of_stems_per_document = (
Document_Segment.objects.filter(document=d).values("segment__stemmed").distinct().count()
)
print "number_of_stems_per_document: %s" % number_of_stems_per_document
for ds in Document_Segment.objects.filter(document=d):
# count alliases( segment with same stemmed version )
number_of_aliases = Document_Segment.objects.filter(document=d, segment__stemmed=ds.segment.stemmed).count()
ds.tf = float(number_of_aliases) / number_of_stems_per_document
ds.save()
if number_of_aliases > 1: # print just some lines
print ds.segment.content, ds.segment.stemmed, number_of_aliases, ds.tf
if current_segment % 25 == 0:
log_routine(
routine,
completion=completion_start
+ (float(current_segment) / number_of_documents_segments) * (completion_score - completion_start),
)
transaction.commit()
current_segment = current_segment + 1
if completion_score == 1.0:
close_routine(routine, error="", status="OK")
transaction.commit()
def standard( corpus, routine ):
number_of_documents = Document.objects.filter(corpus=corpus ).count()
logger.info("opening standard routine, corpus: '%s' [%s], %s documents" % ( corpus.name, corpus.id, number_of_documents) )
if number_of_documents == 0:
logger.error("routine closed, not enough documents")
return close_routine( routine, error="standard routine: No document found", status="OK")
# 1. distiller.decant (tf computation )
try:
decant( corpus=corpus, routine=routine, settings=settings, ref_completion=0.5 )
except Exception, e:
logger.exception("Exception: %s" % e)
return close_routine( routine, error="Exception: %s" % e, status="ERR")
def importcsv( routine, csvfile, corpus, column="stemmed" ): print """ ======================================== ---- IMPORT SEGMENTS ROM REFINE CSV ---- ======================================== """ log_routine( routine, entry="importcsv started", completion=0 ); transaction.commit() rows = list(csvfile) totalrows = len(rows) logger.info( "[corpus:%s] import csv, total rows: %s" % (corpus.name, totalrows) ) for i, row in enumerate(rows): try: segment_id = row['segment_id'] concept = row['concept'] status = 'IN' if row['status'] == 'IN' else 'OUT' except KeyError,e: logger.error( "KeyError exception: %s" % e ) close_routine( routine, error="Exception: %s %s" % (e,row), status="ERR" ) transaction.rollback() return # update stemmed_refined cell try: s = Segment.objects.get(id=segment_id) # update all the similar segment with the brand new segment Segment.objects.filter( stemmed=s.stemmed, documents__corpus=corpus ).update( stemmed=concept, status=status ) # buffer_stemmed = s.stemmed # s.stemmed = concept # s.status = status # s.stemmed_refined = buffer_stemmed # s.save() except Segment.DoesNotExist, e: logger.error( "[corpus:%s] import csv, row %s raised exception: %s" % (corpus.name, i,e) ) #print " segemnt id %s was not found!" % row['segment_id'] close_routine( routine, error="Exception: %s %s" % (e,row), status="ERR" ) transaction.commit() return
def tf_tfidf(corpus, routine):
number_of_documents = Document.objects.filter(corpus=corpus).count()
if number_of_documents == 0:
return close_routine(routine, error="No document found", status="ERR")
tf(corpus=corpus, routine=routine, completion_start=0.0, completion_score=0.4)
if routine.status == "ERR":
return
tfidf(corpus=corpus, routine=routine, completion_start=0.4, completion_score=0.4)
if routine.status == "ERR":
return
similarity(corpus=corpus, routine=routine, completion_start=0.8, completion_score=0.2)
close_routine(routine, error="", status="OK")
def tfidf(corpus, routine, completion_start=0.0, completion_score=1.0, column="stemmed"):
print """
===========================
---- TFIDF COMPUTATION ----
===========================
"""
# routine.type = "TFIDF"
# routine.save()
# 1. get number of document
number_of_documents = Document.objects.filter(corpus=corpus, status="IN").count()
logger.info("[%s:%s] TFIDF on %s 'IN' documents" % (corpus.name, corpus.id, number_of_documents))
# 2. get all languages in corpus
number_of_languages = Document.objects.values("language").distinct().count()
# 3. get GLOBAL number of segments (aka stems, segments grouped by their stemmed version: they do not need to be in the same corpus!!!)
number_of_stems = (
Segment.objects.values("stemmed", "language").annotate(Count("stemmed"), Count("language")).count()
)
logger.info("[%s:%s] %s segment groups" % (corpus.name, corpus.id, number_of_stems))
# SELECT COUNT(*), stemmed FROM anta_segment GROUP BY stemmed
# out some information
# print "[info] column:",column
# print "[info] corpus:",corpus.json()
# print "[info] document in corpus:",number_of_documents
# print "[info] stems in corpus (grouped by stemmed, language):",number_of_stems
cursor = connection.cursor()
# global counter (all languages cycle)
current_stem = 0
# 3. for each language, perform a tfidf
for i in (
Document.objects.filter(corpus=corpus, status="IN")
.values("language")
.annotate(num_document=Count("language"))
.distinct()
):
# print "[info] language info: ",i
logger.info("[%s:%s] language %s" % (corpus.name, corpus.id, i["language"]))
language = i["language"]
# count tfidf group
# SELECT COUNT(*), stemmed FROM anta_segment WHERE language="EN" GROUP BY stemmed
stem_count = Segment.objects.filter(language=language).values("stemmed").annotate(Count("stemmed")).count()
# check length. If it's 0, exit with error....
if stem_count == 0:
logger.error(
"[%s:%s] not enought segments in your corpus with language %s" % (corpus.name, corpus.id, i["language"])
)
close_routine(
routine, error="Not enought segments in your corpus. Try standard routine first...", status="ERR"
)
transaction.commit()
return
# 5. for each segment in this language...
number_of_groups = cursor.execute(
"""
SELECT
COUNT( DISTINCT ds.document_id ) as distribution,
s.language,
s.stemmed
FROM `anta_document_segment` ds
JOIN anta_segment s ON ds.segment_id = s.id
JOIN anta_document d ON d.id = ds.document_id
WHERE d.corpus_id = %s AND s.language = %s AND s.status = 'IN'
GROUP BY s.stemmed ORDER BY distribution DESC, stemmed ASC""",
[corpus.id, language],
)
logger.info("[%s:%s] distribution query executed for language '%s'" % (corpus.name, corpus.id, language))
language_cursor = 0.0
for row in dictfetchall(cursor):
# increment global runner (stats)
current_stem = current_stem + 1
language_cursor + 1
# store tfidf inside each segment-document relationships
try:
dss = Document_Segment.objects.filter(segment__stemmed=row["stemmed"], segment__language=language)
df = float(row["distribution"]) / number_of_documents
# print float(current_stem) / number_of_stems * 100.0, row[ column ], row['distribution'], df
except Exception, e:
logger.exception("[%s:%s] uhandled exception ..." % (corpus.name, corpus.id))
# print e
close_routine(
routine, error="Ho trovato Wally alla liena 281 di metrics.py, Exception: %s" % e, status="ERR"
)
transaction.commit()
return
for ds in dss:
ds.tfidf = ds.tf * math.log(1 / df)
ds.save()
if current_stem % 75 == 0:
try:
completion = completion_start + (float(current_stem) / number_of_stems) * (
completion_score - completion_start
)
logger.info(
"[%s:%s] language completion: %s"
% (corpus.name, corpus.id, (float(current_stem) / number_of_stems))
)
log_routine(routine, completion=completion)
# save percentage and commit transaction
transaction.commit()
except Exception, e:
logger.exception("[%s:%s] uhandled exception ..." % (corpus.name, corpus.id))
)
if number_of_documents == 0:
logger.error("routine closed, not enough documents")
return close_routine(routine, error="standard routine: No document found", status="OK")
# 1. distiller.decant (tf computation )
try:
decant(corpus=corpus, routine=routine, settings=settings, ref_completion=0.5)
except Exception, e:
logger.exception("Exception: %s" % e)
return close_routine(routine, error="Exception: %s" % e, status="ERR")
# 2. get all languages in corpus
tf_tfidf(corpus=corpus, routine=routine)
close_routine(routine, error="", status="OK")
@transaction.commit_manually
def entities_alchemy(corpus, routine):
print """
=================================
---- ENTITIES VIA ALCHEMYAPI ----
=================================
"""
from services import alchemy
number_of_documents = Document.objects.filter(corpus=corpus).count()
# print "[info] number_of_documents:",number_of_documents
# print "[info] alchmy apikey:", settings.ALCHEMY_API_KEY
