Generate confusion matrix from spacy v3 multi label classification

[CodeCheetah]

I'm trying to generate confusion matrix using SpaCy v3 model on multi label classification but cannot find any sources online on how to achieve this.

Any ideas? Thank you.

[CodeCheetah]

I was able to generate confusion matrix without skilearn library which generates classification matrix but one image per label (TN/TP). The code below generates one image with all labels shown.

def generate_confusion_matrix(y_test, y_pred):
    """
    Generate confusion matrix
    """
    if len(y_test.shape) != 2:
        raise IOError('y_test must be a 2D array (Matrix)')
    elif len(y_pred.shape) != 2:
        raise IOError('y_pred must be a 2D array (Matrix)')

    # Create matrix grid 
    cm = np.zeros((y_test.shape[1], y_test.shape[1]))

    for obs in range(0, len(y_pred[:, 0])):
        j = y_pred[obs, :].argmax()
        i = y_test[obs, :].argmax()
        cm[i, j] += 1

    accuracy = 0.0
    for i in range(0, cm.shape[1]):
        accuracy += cm[i, i]
    accuracy /= len(y_test.argmax(axis=1))
    log("accuracy", accuracy)
    return cm

def plot_confusion_matrix(cm, classes, normalize=False, title='Confusion Matrix', cmap=plt.cm.Blues):
    """
    Plot confusion matrix as image
    """
    plt.figure(figsize=(10,10))
    plt.imshow(cm, interpolation='nearest', cmap=cmap)
    plt.title(title)
    plt.colorbar()
    tick_marks = np.arange(len(classes))
    plt.xticks(tick_marks, classes, rotation=90)
    plt.yticks(tick_marks, classes)

    threshold = cm.max() / 2.
    for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])):
        plt.text(j, i, math.ceil(cm[i, j]),
                 horizontalalignment='center',
                 color='white' if cm[i, j] > threshold else 'black')

    plt.tight_layout()
    plt.ylabel('True label')
    plt.xlabel('Predicted label')
    return plt

cm = generate_confusion_matrix(actuals, predictions) *** The actuals and predictions can be taken from Corpus and nlp(text)

cm_img = plot_confusion_matrix(cm, labels)
cm_img.show