def getNbrFeatures(self, *filenames):
''' Get the number of features directly from the data file (in case we do not have an info file)'''
if 'feat_num' not in self.info.keys():
self.getFormatData(filenames[0])
if self.info['format'] == 'dense':
data = data_converter.file_to_array(filenames[0])
self.info['feat_num'] = len(data[0])
elif self.info['format'] == 'sparse':
self.info['feat_num'] = 0
for filename in filenames:
sparse_list = data_converter.sparse_file_to_sparse_list(
filename)
last_column = [
sparse_list[i][-1] for i in range(len(sparse_list))
]
last_column_feature = [a for (a, b) in last_column]
self.info['feat_num'] = max(self.info['feat_num'],
max(last_column_feature))
elif self.info['format'] == 'sparse_binary':
self.info['feat_num'] = 0
for filename in filenames:
data = data_converter.file_to_array(filename)
last_column = [int(data[i][-1]) for i in range(len(data))]
self.info['feat_num'] = max(self.info['feat_num'],
max(last_column))
return self.info['feat_num']
def getTypeProblem(self, solution_filename):
''' Get the type of problem directly from the solution file (in case we do not have an info file)'''
if 'task' not in self.info.keys():
solution = np.array(
data_converter.file_to_array(solution_filename))
target_num = solution.shape[1]
self.info['target_num'] = target_num
if target_num == 1: # if we have only one column
solution = np.ravel(solution) # flatten
nbr_unique_values = len(np.unique(solution))
if nbr_unique_values < len(solution) / 8:
# Classification
self.info['label_num'] = nbr_unique_values
if nbr_unique_values == 2:
self.info['task'] = 'binary.classification'
self.info['target_type'] = 'Binary'
else:
self.info['task'] = 'multiclass.classification'
self.info['target_type'] = 'Categorical'
else:
# Regression
self.info['label_num'] = 0
self.info['task'] = 'regression'
self.info['target_type'] = 'Numerical'
else:
# Multilabel or multiclass
self.info['label_num'] = target_num
self.info['target_type'] = 'Binary'
if any(item > 1 for item in map(np.sum, solution.astype(int))):
self.info['task'] = 'multilabel.classification'
else:
self.info['task'] = 'multiclass.classification'
return self.info['task']
def getFormatData(self, filename):
''' Get the data format directly from the data file (in case we do not have an info file)'''
if 'format' in self.info.keys():
return self.info['format']
if 'is_sparse' in self.info.keys():
if self.info['is_sparse'] == 0:
self.info['format'] = 'dense'
else:
data = data_converter.read_first_line(filename)
if ':' in data[0]:
self.info['format'] = 'sparse'
else:
self.info['format'] = 'sparse_binary'
else:
data = data_converter.file_to_array(filename)
if ':' in data[0][0]:
self.info['is_sparse'] = 1
self.info['format'] = 'sparse'
else:
nbr_columns = len(data[0])
for row in range(len(data)):
if len(data[row]) != nbr_columns:
self.info['format'] = 'sparse_binary'
if 'format' not in self.info.keys():
self.info['format'] = 'dense'
self.info['is_sparse'] = 0
return self.info['format']
def getTypeProblem(self, solution_filename):
''' Get the type of problem directly from the solution file (in case we do not have an info file)'''
if 'task' not in self.info.keys():
solution = np.array(data_converter.file_to_array(solution_filename))
target_num = solution.shape[1]
self.info['target_num'] = target_num
if target_num == 1: # if we have only one column
solution = np.ravel(solution) # flatten
nbr_unique_values = len(np.unique(solution))
if nbr_unique_values < len(solution) / 8:
# Classification
self.info['label_num'] = nbr_unique_values
if nbr_unique_values == 2:
self.info['task'] = 'binary.classification'
self.info['target_type'] = 'Binary'
else:
self.info['task'] = 'multiclass.classification'
self.info['target_type'] = 'Categorical'
else:
# Regression
self.info['label_num'] = 0
self.info['task'] = 'regression'
self.info['target_type'] = 'Numerical'
else:
# Multilabel or multiclass
self.info['label_num'] = target_num
self.info['target_type'] = 'Binary'
if any(item > 1 for item in map(np.sum, solution.astype(int))):
self.info['task'] = 'multilabel.classification'
else:
self.info['task'] = 'multiclass.classification'
return self.info['task']
def getFormatData(self, filename):
''' Get the data format directly from the data file (in case we do not have an info file)'''
if 'format' in self.info.keys():
return self.info['format']
if 'is_sparse' in self.info.keys():
if self.info['is_sparse'] == 0:
self.info['format'] = 'dense'
else:
data = data_converter.read_first_line(filename)
if ':' in data[0]:
self.info['format'] = 'sparse'
else:
self.info['format'] = 'sparse_binary'
else:
data = data_converter.file_to_array(filename)
if ':' in data[0][0]:
self.info['is_sparse'] = 1
self.info['format'] = 'sparse'
else:
nbr_columns = len(data[0])
for row in range(len(data)):
if len(data[row]) != nbr_columns:
self.info['format'] = 'sparse_binary'
if 'format' not in self.info.keys():
self.info['format'] = 'dense'
self.info['is_sparse'] = 0
return self.info['format']
def getNbrFeatures(self, *filenames):
''' Get the number of features directly from the data file (in case we do not have an info file)'''
if 'feat_num' not in self.info.keys():
self.getFormatData(filenames[0])
if self.info['format'] == 'dense':
data = data_converter.file_to_array(filenames[0])
self.info['feat_num'] = len(data[0])
elif self.info['format'] == 'sparse':
self.info['feat_num'] = 0
for filename in filenames:
sparse_list = data_converter.sparse_file_to_sparse_list(filename)
last_column = [sparse_list[i][-1] for i in range(len(sparse_list))]
last_column_feature = [a for (a, b) in last_column]
self.info['feat_num'] = max(self.info['feat_num'], max(last_column_feature))
elif self.info['format'] == 'sparse_binary':
self.info['feat_num'] = 0
for filename in filenames:
data = data_converter.file_to_array(filename)
last_column = [int(data[i][-1]) for i in range(len(data))]
self.info['feat_num'] = max(self.info['feat_num'], max(last_column))
return self.info['feat_num']
def loadType(self, filename, verbose=True):
''' Get the variable types'''
if verbose: print("========= Reading " + filename)
start = time.time()
type_list = []
if os.path.isfile(filename):
type_list = data_converter.file_to_array(filename, verbose=False)
else:
n = self.info['feat_num']
type_list = [self.info['feat_type']] * n
type_list = np.array(type_list).ravel()
end = time.time()
if verbose: print("[+] Success in %5.2f sec" % (end - start))
return type_list
def loadType(self, filename, verbose=True):
''' Get the variable types'''
if verbose: print("========= Reading " + filename)
start = time.time()
type_list = []
if os.path.isfile(filename):
type_list = data_converter.file_to_array(filename, verbose=False)
else:
n = self.info['feat_num']
type_list = [self.info['feat_type']] * n
type_list = np.array(type_list).ravel()
end = time.time()
if verbose: print( "[+] Success in %5.2f sec" % (end - start))
return type_list