Confusion matrix

by: Chris Cave
(Feyn version 2.0 or newer)

A confusion matrix provides a summary or all correct and incorrect classifiactions made by a binary classifier Model. Here we provide an example

import feyn
import pandas as pd
from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import train_test_split


# Load into a pandas dataframe
breast_cancer = load_breast_cancer(as_frame=True)
data = breast_cancer.frame

# Train/test split
train, test = train_test_split(data, test_size=0.4, stratify=data['target'], random_state=666)

ql = feyn.connect_qlattice()
models = ql.auto_run(
    data=train,
    output_name = 'target',
    kind='classification'
)

best = models[0]

Confusion matrix

best.plot_confusion_matrix(train, threshold=0.5)

This provides all the True Positives, True Negatives, False Positives and False Negatives at the pass threshold. The default threshold is 0.5.

Location in feyn

This function can also be found in feyn.plots module.

from feyn.plots import plot_confusion_matrix

y_true = train['target']
y_pred = best.predict(train).round()

plot_confusion_matrix(y_true, y_pred)