hitvoice · October 16, 2024 13:24 · seovchinnikov · May 13, 2018 · Mahi-Mai · Jun 26, 2018
diff --git a/plot_confusion_matrix.png b/plot_confusion_matrix.png
diff --git a/plot_confusion_matrix.py b/plot_confusion_matrix.py
 import numpy as np
 import pandas as pd
 import matplotlib.pyplot as plt
 import seaborn as sns
 from sklearn.metrics import confusion_matrix

 def cm_analysis(y_true, y_pred, filename, labels, ymap=None, figsize=(10,10)):
    """
    Generate matrix plot of confusion matrix with pretty annotations.
    The plot image is saved to disk.
    args: 
      y_true:    true label of the data, with shape (nsamples,)
      y_pred:    prediction of the data, with shape (nsamples,)
      filename:  filename of figure file to save
      labels:    string array, name the order of class labels in the confusion matrix.
                 use `clf.classes_` if using scikit-learn models.
                 with shape (nclass,).
      ymap:      dict: any -> string, length == nclass.
                 if not None, map the labels & ys to more understandable strings.
                 Caution: original y_true, y_pred and labels must align.
      figsize:   the size of the figure plotted.
    """
    if ymap is not None:
        y_pred = [ymap[yi] for yi in y_pred]
        y_true = [ymap[yi] for yi in y_true]
        labels = [ymap[yi] for yi in labels]
    cm = confusion_matrix(y_true, y_pred, labels=labels)
    cm_sum = np.sum(cm, axis=1, keepdims=True)
    cm_perc = cm / cm_sum.astype(float) * 100
    annot = np.empty_like(cm).astype(str)
    nrows, ncols = cm.shape
    for i in range(nrows):
        for j in range(ncols):
            c = cm[i, j]
            p = cm_perc[i, j]
            if i == j:
                s = cm_sum[i]
                annot[i, j] = '%.1f%%\n%d/%d' % (p, c, s)
            elif c == 0:
                annot[i, j] = ''
            else:
                annot[i, j] = '%.1f%%\n%d' % (p, c)
    cm = pd.DataFrame(cm, index=labels, columns=labels)
    cm.index.name = 'Actual'
    cm.columns.name = 'Predicted'
    fig, ax = plt.subplots(figsize=figsize)
    sns.heatmap(cm, annot=annot, fmt='', ax=ax)
    plt.savefig(filename)
	import numpy as np
	import pandas as pd
	import matplotlib.pyplot as plt
	import seaborn as sns
	from sklearn.metrics import confusion_matrix

	def cm_analysis(y_true, y_pred, filename, labels, ymap=None, figsize=(10,10)):
	"""
	Generate matrix plot of confusion matrix with pretty annotations.
	The plot image is saved to disk.
	args:
	y_true: true label of the data, with shape (nsamples,)
	y_pred: prediction of the data, with shape (nsamples,)
	filename: filename of figure file to save
	labels: string array, name the order of class labels in the confusion matrix.
	use `clf.classes_` if using scikit-learn models.
	with shape (nclass,).
	ymap: dict: any -> string, length == nclass.
	if not None, map the labels & ys to more understandable strings.
	Caution: original y_true, y_pred and labels must align.
	figsize: the size of the figure plotted.
	"""
	if ymap is not None:
	y_pred = [ymap[yi] for yi in y_pred]
	y_true = [ymap[yi] for yi in y_true]
	labels = [ymap[yi] for yi in labels]
	cm = confusion_matrix(y_true, y_pred, labels=labels)
	cm_sum = np.sum(cm, axis=1, keepdims=True)
	cm_perc = cm / cm_sum.astype(float) * 100
	annot = np.empty_like(cm).astype(str)
	nrows, ncols = cm.shape
	for i in range(nrows):
	for j in range(ncols):
	c = cm[i, j]
	p = cm_perc[i, j]
	if i == j:
	s = cm_sum[i]
	annot[i, j] = '%.1f%%\n%d/%d' % (p, c, s)
	elif c == 0:
	annot[i, j] = ''
	else:
	annot[i, j] = '%.1f%%\n%d' % (p, c)
	cm = pd.DataFrame(cm, index=labels, columns=labels)
	cm.index.name = 'Actual'
	cm.columns.name = 'Predicted'
	fig, ax = plt.subplots(figsize=figsize)
	sns.heatmap(cm, annot=annot, fmt='', ax=ax)
	plt.savefig(filename)