def get_document_class(row, batch, training=True):
"""
The class of a document corresponding to a row
in a batch.
@param row: row in the bag of words matrix in batch.
@param batch: the number of the batch.
@param training: is this the training set or the test set.
"""
class_indices_for_batch = s.load(open(env_paths.get_class_indices_path(training, batch), "rb"))
class_names_for_batch = s.load(open(env_paths.get_class_names_path(training), "rb"))
return class_names_for_batch[class_indices_for_batch[row]]
def get_document_class(row, batch, training=True):
"""
The class of a document corresponding to a row
in a batch.
@param row: row in the bag of words matrix in batch.
@param batch: the number of the batch.
@param training: is this the training set or the test set.
"""
class_indices_for_batch = s.load(open(env_paths.get_class_indices_path(training, batch), "rb"))
class_names_for_batch = s.load(open(env_paths.get_class_names_path(training), "rb"))
return class_names_for_batch[class_indices_for_batch[row]]
def __read_docs_from_filesystem(self):
"""
Read all docs and assign them to batches, so that each doc category is represented equally across batches.
"""
docs_names = []
docs_names_split = []
class_indices = []
class_indices_split = []
class_names = []
batches = []
print "Generating class indices and docs names list."
doc_count = 0
for folder in self.paths:
docs_names_split.append([])
class_indices_split.append([])
class_names.append(folder.split("/")[len(folder.split("/")) - 1])
if self.trainingset_size == None: # If data processing should be done on all data in the specified folders.
docs = os.listdir(folder)
elif (
not self.trainingset_size == None and self.trainingset_attributes == None
): # If data processing should be done on parts of the docs in the specified folders - for training and testing purposes.
docs = os.listdir(folder)[: int(len(os.listdir(folder)) * self.trainingset_size)]
else: # If data processing should be done on a test set.
docs = os.listdir(folder)[int(len(os.listdir(folder)) * self.trainingset_size) :]
for doc in docs:
if doc.endswith(".p"):
# Append the name of the document to the list containing document names.
docs_names_split[-1].append(folder + "/" + doc)
class_indices_split[-1].append(len(class_names) - 1)
doc_count += 1
if len(docs_names_split) == 0: # Check if docs have been stemmed.
print "Documents have not been stemmed. Please stem documents in order to create bag of words matrices."
return 0
# Ensure that batches contain an even amount of docs from each category.
print "Arranging the documents."
if doc_count < self.batchsize:
print "Number of documents must be greater than batchsize. Please revise the batchsize."
return 0
number_of_batches = doc_count / self.batchsize
number_of_classes = len(self.paths)
batches_collected_class_indices = []
batches_collected_docs_names = []
# Calculate fraction of category in each batch.
d = {}
for i in range(len(class_indices_split)):
d[i] = float(len(class_indices_split[i])) / number_of_batches
count = 0
for i in range(number_of_batches):
batch_class_indices = []
batch_docs_names = []
d_tmp = array([int(v) for v in d.values()])
while True:
if (
(len(batch_class_indices) == self.batchsize)
and (not doc_count - count < self.batchsize)
or (count == doc_count)
):
break
if len(d_tmp[d_tmp > 0]) == 0:
break
for j in range(number_of_classes):
if (
(len(batch_class_indices) == self.batchsize)
and (not doc_count - count < self.batchsize)
or (count == doc_count)
):
break
if len(class_indices_split[j]) > 0 and d_tmp[j] != 0:
batch_class_indices.append(class_indices_split[j].pop(0))
batch_docs_names.append(docs_names_split[j].pop(0))
d_tmp[j] -= 1
count += 1
batches_collected_class_indices.append(batch_class_indices)
batches_collected_docs_names.append(batch_docs_names)
for i in range(number_of_batches):
bsize = self.batchsize if i < number_of_batches - 1 else self.batchsize + (doc_count % self.batchsize)
batch_class_indices = batches_collected_class_indices[i]
batch_docs_names = batches_collected_docs_names[i]
if len(batch_class_indices) < bsize:
while True:
if len(batch_class_indices) == bsize:
break
for j in range(number_of_classes):
if len(batch_class_indices) == bsize:
break
if len(class_indices_split[j]) > 0:
batch_class_indices.append(class_indices_split[j].pop(0))
batch_docs_names.append(docs_names_split[j].pop(0))
# Shuffle the batch
batch_class_indices_shuf = []
batch_docs_names_shuf = []
index_shuf = range(len(batch_class_indices))
shuffle(index_shuf)
for k in index_shuf:
batch_class_indices_shuf.append(batch_class_indices[k])
batch_docs_names_shuf.append(batch_docs_names[k])
# Append batch to full lists
class_indices += batch_class_indices_shuf
docs_names += batch_docs_names_shuf
print "Reading and saving docs from file system"
count = 0
class_indices_batch = []
docs_names_batch = []
docs_list = []
for i in xrange(len(class_indices)):
if (
not count == 0 and (count % self.batchsize) == 0
): # Save the batch if batchsize is reached or if the last document has been read.
if not (len(class_indices) - count) < self.batchsize:
print "Read ", str(count), " of ", len(class_indices)
self.__save_batch_loading_docs(count, docs_list, docs_names_batch, class_indices_batch)
batches.append(count)
# Reset the lists
docs_list = []
docs_names_batch = []
class_indices_batch = []
d = s.load(open(docs_names[i], "rb"))
docs_list.append(d)
docs_names_batch.append(docs_names[i])
class_indices_batch.append(class_indices[i])
count += 1
# Save the remaining docs
if len(docs_list) > 0:
print "Read ", str(count), " of ", len(class_indices)
self.__save_batch_loading_docs(count, docs_list, docs_names_batch, class_indices_batch)
batches.append(count)
s.dump(class_names, open(env_paths.get_class_names_path(self.training), "wb"))
s.dump(batches, open(env_paths.get_batches_path(self.training), "wb"))
return 1
def get_all_class_names():
"""
Get all class names for training set.
"""
return s.load(open(env_paths.get_class_names_path(train=True), "rb"))
def __read_docs_from_filesystem(self):
"""
Read all docs and assign them to batches, so that each doc category is represented equally across batches.
"""
docs_names = []
docs_names_split = []
class_indices = []
class_indices_split = []
class_names = []
batches = []
print 'Generating class indices and docs names list.'
doc_count = 0
for folder in self.paths:
docs_names_split.append([])
class_indices_split.append([])
class_names.append(folder.split('/')[len(folder.split('/')) - 1])
if self.trainingset_size == None: # If data processing should be done on all data in the specified folders.
docs = os.listdir(folder)
elif not self.trainingset_size == None and self.trainingset_attributes == None: # If data processing should be done on parts of the docs in the specified folders - for training and testing purposes.
docs = os.listdir(folder)[:int(len(os.listdir(folder)) * self.trainingset_size)]
else: # If data processing should be done on a test set.
docs = os.listdir(folder)[int(len(os.listdir(folder)) * self.trainingset_size):]
for doc in docs:
if doc.endswith('.p'):
# Append the name of the document to the list containing document names.
docs_names_split[-1].append(folder + '/' + doc)
class_indices_split[-1].append(len(class_names) - 1)
doc_count += 1
if len(docs_names_split) == 0: # Check if docs have been stemmed.
print 'Documents have not been stemmed. Please stem documents in order to create bag of words matrices.'
return 0
# Ensure that batches contain an even amount of docs from each category.
print 'Arranging the documents.'
if doc_count < self.batchsize:
print 'Number of documents must be greater than batchsize. Please revise the batchsize.'
return 0
number_of_batches = doc_count / self.batchsize
number_of_classes = len(self.paths)
batches_collected_class_indices = []
batches_collected_docs_names = []
# Calculate fraction of category in each batch.
d = {}
for i in range(len(class_indices_split)):
d[i] = float(len(class_indices_split[i])) / number_of_batches
count = 0
for i in range(number_of_batches):
batch_class_indices = []
batch_docs_names = []
d_tmp = array([int(v) for v in d.values()])
while True:
if (len(batch_class_indices) == self.batchsize) and (not doc_count - count < self.batchsize) or (
count == doc_count):
break
if len(d_tmp[d_tmp > 0]) == 0:
break
for j in range(number_of_classes):
if (len(batch_class_indices) == self.batchsize) and (not doc_count - count < self.batchsize) or (
count == doc_count):
break
if len(class_indices_split[j]) > 0 and d_tmp[j] != 0:
batch_class_indices.append(class_indices_split[j].pop(0))
batch_docs_names.append(docs_names_split[j].pop(0))
d_tmp[j] -= 1
count += 1
batches_collected_class_indices.append(batch_class_indices)
batches_collected_docs_names.append(batch_docs_names)
for i in range(number_of_batches):
bsize = self.batchsize if i < number_of_batches - 1 else self.batchsize + (doc_count % self.batchsize)
batch_class_indices = batches_collected_class_indices[i]
batch_docs_names = batches_collected_docs_names[i]
if len(batch_class_indices) < bsize:
while True:
if len(batch_class_indices) == bsize: break
for j in range(number_of_classes):
if len(batch_class_indices) == bsize: break
if len(class_indices_split[j]) > 0:
batch_class_indices.append(class_indices_split[j].pop(0))
batch_docs_names.append(docs_names_split[j].pop(0))
# Shuffle the batch
batch_class_indices_shuf = []
batch_docs_names_shuf = []
index_shuf = range(len(batch_class_indices))
shuffle(index_shuf)
for k in index_shuf:
batch_class_indices_shuf.append(batch_class_indices[k])
batch_docs_names_shuf.append(batch_docs_names[k])
# Append batch to full lists
class_indices += batch_class_indices_shuf
docs_names += batch_docs_names_shuf
print 'Reading and saving docs from file system'
count = 0
class_indices_batch = []
docs_names_batch = []
docs_list = []
for i in xrange(len(class_indices)):
if not count == 0 and (
count % self.batchsize) == 0: # Save the batch if batchsize is reached or if the last document has been read.
if not (len(class_indices) - count) < self.batchsize:
print 'Read ', str(count), ' of ', len(class_indices)
self.__save_batch_loading_docs(count, docs_list, docs_names_batch, class_indices_batch)
batches.append(count)
# Reset the lists
docs_list = []
docs_names_batch = []
class_indices_batch = []
d = s.load(open(docs_names[i], 'rb'))
docs_list.append(d)
docs_names_batch.append(docs_names[i])
class_indices_batch.append(class_indices[i])
count += 1
# Save the remaining docs
if len(docs_list) > 0:
print 'Read ', str(count), ' of ', len(class_indices)
self.__save_batch_loading_docs(count, docs_list, docs_names_batch, class_indices_batch)
batches.append(count)
s.dump(class_names, open(env_paths.get_class_names_path(self.training), "wb"))
s.dump(batches, open(env_paths.get_batches_path(self.training), "wb"))
return 1
def get_all_class_names():
"""
Get all class names for training set.
"""
return s.load(open(env_paths.get_class_names_path(train=True), 'rb'))
