helpers.py
a2aa8d535d7bmaster

helpers.py
View Options

			# -- coding: utf-8 --
			"""some helper functions."""
			import numpy as np


			def load_data(sub_sample=True, add_outlier=False):
			"""Load data and convert it to the metric system."""
			path_dataset = "height_weight_genders.csv"
			data = np.genfromtxt(
			path_dataset, delimiter=",", skip_header=1, usecols=[1, 2])
			height = data[:, 0]
			weight = data[:, 1]
			gender = np.genfromtxt(
			path_dataset, delimiter=",", skip_header=1, usecols=[0],
			converters={0: lambda x: 0 if b"Male" in x else 1})
			# Convert to metric system
			height *= 0.025
			weight *= 0.454
			return height, weight, gender


			def sample_data(y, x, seed, size_samples):
			"""sample from dataset."""
			np.random.seed(seed)
			num_observations = y.shape[0]
			random_permuted_indices = np.random.permutation(num_observations)
			y = y[random_permuted_indices]
			x = x[random_permuted_indices]
			return y[:size_samples], x[:size_samples]


			def standardize(x):
			"""Standardize the original data set."""
			mean_x = np.mean(x, axis=0)
			x = x - mean_x
			std_x = np.std(x, axis=0)
			x = x / std_x
			return x, mean_x, std_x


			def de_standardize(x, mean_x, std_x):
			"""Reverse the procedure of standardization."""
			x = x * std_x
			x = x + mean_x
			return x


			def build_model_data(height, weight):
			"""Form (y,tX) to get regression data in matrix form."""
			y = weight
			x = height
			num_samples = len(y)
			tx = np.c_[np.ones(num_samples), x]
			return y, tx