Is there a way to plot confusion matrix from H2O?

Question

I know H2O can use

model_perf = model.model_performance(input)
model_perf.confusion_matrix

to output the confusion matrix. But is there a way to get the confusion matrix table to create plot?

Answer 1

You have the function you need as indicated here. So you just need to convert the output of your H2OFrames to a Pandas Dataframe. Example is shown below:

import h2o
from h2o.estimators.gbm import H2OGradientBoostingEstimator
import numpy as np
import matplotlib.pyplot as plt

from sklearn import svm, datasets
from sklearn.model_selection import train_test_split
from sklearn.metrics import confusion_matrix
from sklearn.utils.multiclass import unique_labels
%matplotlib inline

h2o.init()
h2o.cluster().show_status()

# import the cars dataset:
# this dataset is used to classify whether or not a car is economical based on
# the car's displacement, power, weight, and acceleration, and the year it was made
cars = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/junit/cars_20mpg.csv")


# print(cars["economy_20mpg"].isna().sum())
cars[~cars["economy_20mpg"].isna()]["economy_20mpg"].isna().sum()
cars = cars[~cars["economy_20mpg"].isna()]


# convert response column to a factor
cars["economy_20mpg"] = cars["economy_20mpg"].asfactor()

# set the predictor names and the response column name
predictors = ["displacement","power","weight","acceleration","year"]
response = "economy_20mpg"

# split into train and validation sets
train, valid = cars.split_frame(ratios = [.8], seed = 1234)

# try using the `y` parameter:
# first initialize your estimator
cars_gbm = H2OGradientBoostingEstimator(seed = 1234, sample_rate=.5)

# then train your model, where you specify your 'x' predictors, your 'y' the response column
# training_frame and validation_frame
cars_gbm.train(x = predictors, y = response, training_frame = train, validation_frame = valid)

function from sklearn:

def plot_confusion_matrix(y_true, y_pred, classes,
                          normalize=False,
                          title=None,
                          cmap=plt.cm.Blues):
    """
    This function prints and plots the confusion matrix.
    Normalization can be applied by setting `normalize=True`.
    """
    if not title:
        if normalize:
            title = 'Normalized confusion matrix'
        else:
            title = 'Confusion matrix, without normalization'

    # Compute confusion matrix
    cm = confusion_matrix(y_true, y_pred)
    # Only use the labels that appear in the data
    classes = classes[unique_labels(y_true, y_pred)]
    if normalize:
        cm = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis]
        print("Normalized confusion matrix")
    else:
        print('Confusion matrix, without normalization')

    print(cm)

    fig, ax = plt.subplots()
    im = ax.imshow(cm, interpolation='nearest', cmap=cmap)
    ax.figure.colorbar(im, ax=ax)
    # We want to show all ticks...
    ax.set(xticks=np.arange(cm.shape[1]),
           yticks=np.arange(cm.shape[0]),
           # ... and label them with the respective list entries
           xticklabels=classes, yticklabels=classes,
           title=title,
           ylabel='True label',
           xlabel='Predicted label')

    # Rotate the tick labels and set their alignment.
    plt.setp(ax.get_xticklabels(), rotation=45, ha="right",
             rotation_mode="anchor")

    # Loop over data dimensions and create text annotations.
    fmt = '.2f' if normalize else 'd'
    thresh = cm.max() / 2.
    for i in range(cm.shape[0]):
        for j in range(cm.shape[1]):
            ax.text(j, i, format(cm[i, j], fmt),
                    ha="center", va="center",
                    color="white" if cm[i, j] > thresh else "black")
    fig.tight_layout()
    return ax

extract values

# specify the threshold you want to use to create integer labels
maxf1_threshold = cars_gbm.find_threshold_by_max_metric('f1')

# specify your tru and prediciton labels
y_true = cars["economy_20mpg"].as_data_frame()
y_pred = cars_gbm.predict(cars)

# convert prediction labels (original uncalibrated probabilities into integer labels)
y_pred = (y_pred['p1'] >= maxf1_threshold).ifelse(1,0)
y_pred = y_pred.as_data_frame()
y_pred.columns = ['p1']

y_true1 = y_true.economy_20mpg 
y_pred1 = y_pred.p1
class_names = np.array(cars["economy_20mpg"].levels()[0])

# Plot non-normalized confusion matrix
plot_confusion_matrix(y_true1, y_pred1, classes=class_names,
                      title='Confusion matrix')

image result:

Please note that there is a bug in the H2O-3 confusion matrix that has been noted here