def load(self):
super(AnagramMap, self).load()
data = load(self.filename)
self.anagram_hashmap = data["hashmap"]
self.anagram_alphabet = data["alphabet"]
def correct(self, text_data):
"""Correct text data
Args:
text_data (`Text`): Text data
"""
unigrams = Unigrams(join(self.config["root"],
self.config["dirs"]["models_root"],
self.config["dirs"]["models"]["inline"],
self.config["models"]["inline"]["unigrams"],))
ml_classifier = load(join(self.config["dirs"]["models_root"],
self.config["dirs"]["models"]["learning"],
self.config["models"]["learning"]["classifier"]))
if ml_classifier is None:
return
self.model["algo"].set_classifier(ml_classifier)
for paragraph in text_data.text:
for line in paragraph:
if line.grade % 5 == 0:
continue
f = MachineLearningFeatures()
features = f.extract_features(line, unigrams.ngrams, text_data.stats)
line.grade = self.model["algo"].classify(features) * 5
def load(self):
super(AltCaseMap, self).load()
data = load(self.filename)
self.altcase_map = data["altcase"]
self.altcase_pruned_map = data["altcase_pruned"]
def load(self):
super(AnagramMap, self).load()
data = load(self.filename)
self.anagram_hashmap = data["hashmap"]
self.anagram_alphabet = data["alphabet"]
def load(self):
super(Bigrams, self).load()
data = load(self.filename)
self.ngrams = data["bigrams"]
self.ngrams_pruned = data["bigrams_pruned"]
def load(self):
super(AltCaseMap, self).load()
data = load(self.filename)
self.altcase_map = data["altcase"]
self.altcase_pruned_map = data["altcase_pruned"]
def load(self):
super(Bigrams, self).load()
data = load(self.filename)
self.ngrams = data["bigrams"]
self.ngrams_pruned = data["bigrams_pruned"]
def correct(self, text_data):
"""Correct text data
Args:
text_data (`Text`): Text data
"""
unigrams = Unigrams(
join(
self.config["root"],
self.config["dirs"]["models_root"],
self.config["dirs"]["models"]["inline"],
self.config["models"]["inline"]["unigrams"],
))
ml_classifier = load(
join(self.config["dirs"]["models_root"],
self.config["dirs"]["models"]["learning"],
self.config["models"]["learning"]["classifier"]))
if ml_classifier is None:
return
self.model["algo"].set_classifier(ml_classifier)
for paragraph in text_data.text:
for line in paragraph:
if line.grade % 5 == 0:
continue
f = MachineLearningFeatures()
features = f.extract_features(line, unigrams.ngrams,
text_data.stats)
line.grade = self.model["algo"].classify(features) * 5
def load(self):
super(Unigrams, self).load()
data = load(self.filename)
self.raw_unigrams = data["raw_unigrams"]
self.ngrams = data["unigrams"]
self.ngrams_pruned = data["unigrams_pruned"]
def load(self):
super(Unigrams, self).load()
data = load(self.filename)
self.raw_unigrams = data["raw_unigrams"]
self.ngrams = data["unigrams"]
self.ngrams_pruned = data["unigrams_pruned"]
def __init__(self, app_config):
self.config = app_config
self.logger = logging.getLogger('local')
self.hash_filename = join(app_config["dirs"]["models_root"], app_config["models"]["hashes"])
self.hash_list = []
if exists(self.hash_filename):
self.hash_list = load(self.hash_filename)
def __init__(self, app_config):
self.config = app_config
self.logger = logging.getLogger('local')
self.hash_filename = join(app_config["dirs"]["models_root"],
app_config["models"]["hashes"])
self.hash_list = []
if exists(self.hash_filename):
self.hash_list = load(self.hash_filename)
def load(self):
super(OcrKeyMap, self).load()
self.ocrkey_map = load(self.filename)
def load(self):
super(Dictionary, self).load()
self.dictionary = load(self.filename)
def load(self):
super(OcrKeyMap, self).load()
self.ocrkey_map = load(self.filename)
def load(self):
super(Dictionary, self).load()
self.dictionary = load(self.filename)
