def load_data(config, base_dir):
# load config
feats = config['features']
target_name = config['target_name']
cloud = config['cloud']
# load data
X_train_all, X_test = load_datasets(feats, base_dir=base_dir, cloud=cloud)
y_train_all = load_target(target_name, base_dir=base_dir, cloud=cloud)
return X_train_all, y_train_all, X_test
def subtype_select(subtype):
"""
this function returns Features (X) and labels (y) representing subtype.
"""
X = data_loader.load_dataset()
y = data_loader.load_target()
X = X.subtract(X.mean())
subtypes = ['HER2+', 'HR+', 'Triple Neg']
subtypes.remove(subtype)
y = y.replace(subtype, 1)
y = y.replace(subtypes, 0)
return X, y
def select_subtype(subtype):
"""
this function returns Features (X) and labels (y) representing subtype.
"""
X = data_loader.load_dataset()
y = data_loader.load_target()
# apply mean centering to for each region
X = X.subtract(X.mean())
# all subtypes
subtypes = ['HER2+', 'HR+', 'Triple Neg']
# remove the current subtype from the whole subtype set
subtypes.remove(subtype)
# re-coding the subtypes to 0 and 1
y = y.replace(subtype, 1)
y = y.replace(subtypes, 0)
return X, y
models = []
for i in range(100):
print("iteration #", i)
training_set, test_set, training_labels, test_labels = train_test_split(
dataset, target, test_size=0.33, random_state=i)
# create a dictionary to store the train and test results
# in (as used in below functions)
# using 2/3 original dataset - applying in the inner loop
records, rfecv = train(training_set, training_labels, i)
curr_results.append(records)
models.append(rfecv)
# using 1/3 original dataset
result_record.append(test(rfecv, test_set, test_labels))
# store run summary of each iteration
# optimisation_results.append(curr_results)
# print run summary per iteration
# print(curr_results)
# print("---------------------------------------------------")
return curr_results, result_record, models
if __name__ == "__main__":
dataset = data_loader.load_dataset()
target = data_loader.load_target()
optimisation_results = optimiseParametersAndFeatures(dataset, target)
data_loader.save_optimisation_results(optimisation_results)
