utils.py

# -*- coding: utf-8 -*-
#!/usr/bin/env python

import glob
import itertools
import os
import re
from textwrap import wrap

import matplotlib
import numpy as np
import tfplot
from sklearn.metrics import confusion_matrix


def split_path(path):
    '''
    'a/b/c.wav' => ('a/b', 'c', 'wav')
    :param path: filepath = 'a/b/c.wav'
    :return: basename, filename, and extension = ('a/b', 'c', 'wav')
    '''
    basepath, filename = os.path.split(path)
    filename, extension = os.path.splitext(filename)
    return basepath, filename, extension


def remove_all_files(path):
    files = glob.glob('{}/*'.format(path))
    for f in files:
        os.remove(f)


def normalize_0_1(values, max, min):
    normalized = np.clip((values - min) / (max - min), 0, 1)
    return normalized


def denormalize_0_1(normalized, max, min):
    values =  np.clip(normalized, 0, 1) * (max - min) + min
    return values


def plot_confusion_matrix(correct_labels, predict_labels, labels, tensor_name='confusion_matrix', normalize=False):
    ''' 
    Parameters:
        correct_labels                  : These are your true classification categories.
        predict_labels                  : These are you predicted classification categories
        labels                          : This is a list of labels which will be used to display the axix labels
        title='Confusion matrix'        : Title for your matrix
        tensor_name = 'MyFigure/image'  : Name for the output summay tensor

    Returns:
        summary: TensorFlow summary 

    Other itema to note:
        - Depending on the number of category and the data , you may have to modify the figzie, font sizes etc. 
        - Currently, some of the ticks dont line up due to rotations.
    '''
    cm = confusion_matrix(correct_labels, predict_labels, labels=labels)
    if normalize:
        cm = cm.astype('float') * 10 / cm.sum(axis=1)[:, np.newaxis]
        cm = np.nan_to_num(cm, copy=True)
        cm = cm.astype('int')

    np.set_printoptions(precision=2)
    ###fig, ax = matplotlib.figure.Figure()

    fig = matplotlib.figure.Figure(figsize=(7, 7), dpi=320, facecolor='w', edgecolor='k')
    ax = fig.add_subplot(1, 1, 1)
    im = ax.imshow(cm, cmap='Oranges')

    classes = [re.sub(r'([a-z](?=[A-Z])|[A-Z](?=[A-Z][a-z]))', r'\1 ', x) for x in labels]
    classes = ['\n'.join(wrap(l, 40)) for l in classes]

    tick_marks = np.arange(len(classes))

    ax.set_xlabel('Predicted', fontsize=7)
    ax.set_xticks(tick_marks)
    c = ax.set_xticklabels(classes, fontsize=4, rotation=-90, ha='center')
    ax.xaxis.set_label_position('bottom')
    ax.xaxis.tick_bottom()

    ax.set_ylabel('True Label', fontsize=7)
    ax.set_yticks(tick_marks)
    ax.set_yticklabels(classes, fontsize=4, va='center')
    ax.yaxis.set_label_position('left')
    ax.yaxis.tick_left()

    for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])):
        ax.text(j, i, format(cm[i, j], 'd') if cm[i, j] != 0 else '.', horizontalalignment="center", fontsize=6,
                verticalalignment='center', color="black")
    fig.set_tight_layout(True)
    summary = tfplot.figure.to_summary(fig, tag=tensor_name)
    return summary