class Corpus():
# ---------------- __init__() ----------------
def __init__(self, corpus_dir):
self.lock_meta = Lock()
self.open(corpus_dir)
# ---------------- __del__() ----------------
def __del__(self):
self.close()
# ---------------- open_db_meta() ----------------
def open_db_meta(self):
logging.debug(Logger.debug("Corpus open_db_meta() %s" % (self.meta_dir) ))
db_meta = leveldb.LevelDB(self.meta_dir)
return db_meta
# ---------------- close_db_meta() ----------------
def close_db_meta(self, db_meta):
db_meta = None
def lock(self):
self.lock_meta.acquire()
def unlock(self):
self.lock_meta.release()
# ---------------- open() ----------------
def open(self, corpus_dir):
self.root_dir = corpus_dir
if not path.isdir(corpus_dir):
os.mkdir(corpus_dir)
self.meta_dir = self.root_dir + "/meta"
self.samples_dir = self.root_dir + "/samples"
if not path.isdir(self.samples_dir):
os.mkdir(self.samples_dir)
self.vocabulary_dir = self.root_dir + "/vocabulary"
self.vocabulary = Vocabulary(self.vocabulary_dir)
self.categories_dir = self.root_dir + "/categories"
self.categories = Categories(self.categories_dir)
self.categories.load_categories()
self.categories.print_categories()
# ---------------- close() ----------------
def close(self):
pass
# ---------------- acquire_sample_id() ----------------
# 线程安全方式获取num_samples个sample_id(全Corpus唯一)。
def acquire_sample_id(self, num_samples):
self.lock()
sample_id = self.get_sample_maxid()
sample_maxid = sample_id + num_samples
self.set_sample_maxid(sample_maxid)
self.unlock()
return sample_id
def get_sample_maxid(self):
sample_maxid = 0
db_meta = self.open_db_meta()
try:
str_maxid = db_meta.Get("__sample_maxid__")
sample_maxid = int(str_maxid)
except KeyError:
db_meta.Put("__sample_maxid__", "0")
self.close_db_meta(db_meta)
return sample_maxid
def set_sample_maxid(self, sample_maxid):
db_meta = self.open_db_meta()
db_meta.Put("__sample_maxid__", str(sample_maxid))
self.close_db_meta(db_meta)
# ---------------- export_svm_file() ----------------
def export_svm_file(self, samples_name, svm_file):
samples = Samples(self, samples_name)
logging.debug(Logger.debug("Export svm file..."))
tm_tfidf = samples.load_tfidf_matrix()
save_term_matrix_as_svm_file(tm_tfidf, svm_file)
# ---------------- transform_sensitive_terms() ----------------
def transform_sensitive_terms(self, sensitive_words, vocabulary):
sensitive_terms = {}
if not sensitive_words is None:
for word in sensitive_words:
w = sensitive_words[word]
term_id = vocabulary.get_term_id(word)
sensitive_terms[term_id] = w
return sensitive_terms
# ---------------- query_by_id() ----------------
def query_by_id(self, samples_positive, samples_unlabeled, sample_id):
tsm_positive = samples_positive.tsm
tsm_unlabeled = samples_unlabeled.tsm
sensitive_words = {
##u"立案":3.0,
##u"获刑":3.0,
##u"受贿":3.0,
##u"有期徒刑":3.0,
##u"宣判":3.0,
##u"审计":2.0,
##u"调查":2.0
}
sensitive_terms = self.transform_sensitive_terms(sensitive_words, self.vocabulary)
try:
sample_content = samples_unlabeled.db_content.Get(str(sample_id))
#(_, category, date, title, key, url, content) = msgpack.loads(sample_content)
(_, category, date, title, key, url, msgext) = decode_sample_meta(sample_content)
(version, content, (cat1, cat2, cat3)) = msgext
print "sample id: %d" % (sample_id)
print "category: %d" % (category)
print "key: %s" % (key)
print "url: %s" % (url)
print "date: %s" % (date)
print "title: %s" % (title)
print "---------------- content ----------------"
#print "%s" % (content)
sample_terms, term_map = self.vocabulary.seg_content(content)
print "sample_terms: %d terms_count: %d" % (sample_terms, len(term_map))
#for term_id in term_map:
terms_list = sorted_dict_by_values(term_map, reverse=True)
for (term_id, term_used_in_sample) in terms_list:
term_text = self.vocabulary.get_term_text(term_id)
#term_used_in_sample = term_map[term_id]
print "%s(%d): %d" % (term_text, term_id, term_used_in_sample)
except KeyError:
print "Sample %d not found in db_content." % (sample_id)
db_sm = samples_unlabeled.tsm.open_db_sm()
try:
str_sample_info = db_sm.Get(str(sample_id))
(category, sample_terms, term_map) = msgpack.loads(str_sample_info)
print ""
print "---------------- keywords ----------------"
print ""
terms = {}
for term_id in term_map:
term_text = self.vocabulary.get_term_text(term_id)
term_used = term_map[term_id]
(pd_word, speciality, popularity) = calculate_term_positive_degree(term_id, tsm_positive, tsm_unlabeled, sensitive_terms)
terms[term_id] = (pd_word, speciality, popularity, term_used, term_text)
terms_list = sorted_dict_by_values(terms, reverse = True)
for (term_id, (pd_word, speciality, popularity, term_used, term_text)) in terms_list:
print "%s\t%d\t[%.6f,%.6f,%.6f]\t(id:%d)" % (term_text, term_used, pd_word, speciality, popularity, term_id)
except KeyError:
print "Sample %d not found in db_sm." % (sample_id)
samples_unlabeled.tsm.close_db(db_sm)
