utils.py

import os
import sys

import numpy as np

def split_num(s):
    head = s.rstrip('0123456789')
    tail = s[len(head):]
    return head, tail

def files_in_order(folderpath):
    npy_files = os.listdir(folderpath)

    no_extensions = [os.path.splitext(npy_file)[0] for npy_file in npy_files]

    splitted = [split_num(s) for s in no_extensions]

    splitted = np.array(splitted)

    indices = np.lexsort((splitted[:, 1].astype(int), splitted[:, 0]))

    npy_files = np.array(npy_files)
    return npy_files[indices]

# Generates binary labels (good=1, bad=0) given an array-like of filenames
def get_labels(array):
    labels = [1 if "good" in i else 0 for i in array]
    return np.array(labels)

# Compute Dynamic Time Warp Distance of two sequences
# http://alexminnaar.com/time-series-classification-and-clustering-with-python.html
def DTWDistance(s1, s2):
    DTW={}

    for i in range(len(s1)):
        DTW[(i, -1)] = float('inf')
    for i in range(len(s2)):
        DTW[(-1, i)] = float('inf')
    DTW[(-1, -1)] = 0

    for i in range(len(s1)):
        for j in range(len(s2)):
            dist= (s1[i]-s2[j])**2
            DTW[(i, j)] = dist + min(DTW[(i-1, j)],DTW[(i, j-1)], DTW[(i-1, j-1)])

    return np.sqrt(DTW[len(s1)-1, len(s2)-1])