def __separate_data(self, data_filename):
data_analyzer = DataAnalyzer(data_filename)
self.mean_list = data_analyzer.get_mean_list()
self.stdev_list = data_analyzer.get_stdev_list()
# feature scale, and add column of 1s to X
all_X = data_analyzer.X
all_X = self.__apply_feature_scaling(all_X)
all_X = np.c_[np.ones(all_X.shape[0]), all_X]
all_Y = data_analyzer.Y
all_data = np.c_[all_X, all_Y]
np.random.shuffle(all_data)
split_row_index = int(all_data.shape[0] *
0.8) # top 80% of rows will be for training
training_data = all_data[:split_row_index, :]
validation_data = all_data[split_row_index:, :]
self.training_X = training_data[:, :-1]
self.training_Y = training_data[:, -1]
self.training_Y = self.training_Y.reshape(self.training_Y.shape[0], 1)
self.validation_X = validation_data[:, :-1]
self.validation_Y = validation_data[:, -1]
self.validation_Y = self.validation_Y.reshape(
self.validation_Y.shape[0], 1)
def __init_training_data(self, training_filename):
data_analyzer = DataAnalyzer(training_filename)
self.mean_list = data_analyzer.get_mean_list()
self.stdev_list = data_analyzer.get_stdev_list()
# feature scale, and add column of 1s to X
self.training_X = data_analyzer.X
self.training_X = self.__apply_feature_scaling(self.training_X)
self.training_X = np.c_[np.ones(self.training_X.shape[0]),
self.training_X]
self.training_Y = data_analyzer.Y