roc_curve_ii.py

# precision-recall curve and f1
from itertools import cycle

import numpy as np
from numpy import interp
from sklearn.datasets import make_classification
from sklearn.ensemble import RandomForestClassifier
from sklearn.datasets import load_iris
# from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split
from sklearn.metrics import precision_recall_curve, roc_curve, RocCurveDisplay
from sklearn.metrics import f1_score
from sklearn.metrics import auc
from matplotlib import pyplot, pyplot as plt
# generate 2 class dataset
# Import some data to play with
from sklearn.preprocessing import label_binarize

iris = load_iris()
X = iris.data
y = iris.target

# Binarize the output
y = label_binarize(y, classes=[0, 1, 2])
n_classes = y.shape[1]

# shuffle and split training and test sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.5, random_state=0)

# Learn to predict each class against the other
rfc = RandomForestClassifier(n_estimators=10, random_state=42)
rfc.fit(X_train, y_train)

# predict probabilities
lr_probs = rfc.predict_proba(X_test)
# keep probabilities for the positive outcome only
# print("lr_probs\n", lr_probs)
lr_probs = lr_probs[:1]
# predict class values
yhat = rfc.predict(X_test)

# Compute ROC curve and ROC area for each class
fpr = dict()
tpr = dict()
roc_auc = dict()
for i in range(n_classes):
    fpr[i], tpr[i], _ = roc_curve(y_test[:, i], yhat[:, i])
    roc_auc[i] = auc(fpr[i], tpr[i])

    plt.figure()
    lw = 2
    plt.plot(
        fpr[i],
        tpr[i],
        color="darkorange",
        lw=lw,
        label="ROC curve (area = %0.2f)" % roc_auc[i],
    )
    plt.plot([0, 1], [0, 1], color="navy", lw=lw, linestyle="--")
    plt.xlim([0.0, 1.0])
    plt.ylim([0.0, 1.05])
    plt.xlabel("False Positive Rate")
    plt.ylabel("True Positive Rate")
    plt.title("Receiver operating characteristic example")
    plt.legend(loc="lower right")
    plt.show()

# Compute micro-average ROC curve and ROC area
fpr["micro"], tpr["micro"], _ = roc_curve(y_test.ravel(), yhat.ravel())
roc_auc["micro"] = auc(fpr["micro"], tpr["micro"])

# First aggregate all false positive rates
all_fpr = np.unique(np.concatenate([fpr[i] for i in range(n_classes)]))

# Then interpolate all ROC curves at this points
mean_tpr = np.zeros_like(all_fpr)
for i in range(n_classes):
    mean_tpr += interp(all_fpr, fpr[i], tpr[i])

# Finally average it and compute AUC
mean_tpr /= n_classes

fpr["macro"] = all_fpr
tpr["macro"] = mean_tpr
roc_auc["macro"] = auc(fpr["macro"], tpr["macro"])

# Plot all ROC curves
plt.figure()
plt.plot(
    fpr["micro"],
    tpr["micro"],
    label="micro-average ROC curve (area = {0:0.2f})".format(roc_auc["micro"]),
    color="deeppink",
    linestyle=":",
    linewidth=4,
)

plt.plot(
    fpr["macro"],
    tpr["macro"],
    label="macro-average ROC curve (area = {0:0.2f})".format(roc_auc["macro"]),
    color="navy",
    linestyle=":",
    linewidth=4,
)

colors = cycle(["aqua", "darkorange", "cornflowerblue"])
for i, color in zip(range(n_classes), colors):
    plt.plot(
        fpr[i],
        tpr[i],
        color=color,
        lw=lw,
        label="ROC curve of class {0} (area = {1:0.2f})".format(i, roc_auc[i]),
    )

plt.plot([0, 1], [0, 1], "k--", lw=lw)
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel("False Positive Rate")
plt.ylabel("True Positive Rate")
plt.title("Some extension of Receiver operating characteristic to multiclass")
plt.legend(loc="lower right")
plt.show()