Helper Functions for ML

helper_functions.py

# Python 3

import numpy as np
from PIL import Image
from io import BytesIO
from IPython import display


def split_test_train(dataset,percent):
  '''Randomly splits the data set into test and train sets'''
  mask = np.random.rand(dataset.shape[0]) < percent
  train = dataset[mask]
  test = dataset[~mask]
  
  return train,test


def dense_to_one_hot(dense_labels,num_classes=10):
    """converts dense labels into one-hot sparse vectors"""
    
    num_labels = dense_labels.shape[0]
    index_offset = np.arange(num_labels) * num_classes
    oh_labels = np.zeros((num_labels,num_classes),dtype='int')
    oh_labels.flat[index_offset + dense_labels.reshape(-1).astype('int')] = 1
    
    return oh_labels

def preproc(x):
    '''Normalize the data to 0-1'''
    return x / x.max()

def generate_batch(dataset,batch_size):
    '''Generate a random normalized batch of size batch_size'''
    seq = dataset['features']
    batch_mask = np.random.choice(range(0,seq.shape[0]),batch_size,replace=False)
    
    batch_x = preproc(seq[batch_mask])
    batch_y = dense_to_one_hot(dataset['target'][batch_mask])
    
    return batch_x,batch_y


def show_array(a,size,fmt='png'):
    '''Display a numpy array'''
    a = np.uint8(a)
    f = BytesIO()
    Image.fromarray(a).save(f,fmt)
    display.display(display.Image(data=f.getvalue(),height=size[1],width=size[0]))