How to beginner · 3 min read

How to plot ROC curve in Scikit-learn

Q: How to plot ROC curve in Scikit-learn

Use sklearn.metrics.roc_curve to compute false positive rate and true positive rate, then plot them with matplotlib.pyplot. Fit a classifier, get predicted probabilities, and pass true labels and probabilities to roc_curve for plotting the ROC curve.

Quick answer

Use sklearn.metrics.roc_curve to compute false positive rate and true positive rate, then plot them with matplotlib.pyplot. Fit a classifier, get predicted probabilities, and pass true labels and probabilities to roc_curve for plotting the ROC curve.

PREREQUISITES

Python 3.8+
pip install scikit-learn matplotlib numpy

Setup

Install required libraries with pip if not already installed:

pip install scikit-learn matplotlib numpy

bash

pip install scikit-learn matplotlib numpy

Step by step

This example trains a logistic regression classifier on a binary classification dataset, computes the ROC curve, and plots it using matplotlib.

python

import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets import make_classification
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import roc_curve, auc
from sklearn.model_selection import train_test_split

# Generate synthetic binary classification data
X, y = make_classification(n_samples=1000, n_features=20, random_state=42)

# Split into train and test sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)

# Train logistic regression classifier
model = LogisticRegression(solver='liblinear')
model.fit(X_train, y_train)

# Predict probabilities for positive class
y_scores = model.predict_proba(X_test)[:, 1]

# Compute ROC curve and ROC area
fpr, tpr, thresholds = roc_curve(y_test, y_scores)
roc_auc = auc(fpr, tpr)

# Plot ROC curve
plt.figure(figsize=(8, 6))
plt.plot(fpr, tpr, color='darkorange', lw=2, label=f'ROC curve (area = {roc_auc:.2f})')
plt.plot([0, 1], [0, 1], color='navy', lw=2, 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 (ROC) Curve')
plt.legend(loc='lower right')
plt.grid(True)
plt.show()

Common variations

Use roc_auc_score from sklearn.metrics to get a scalar AUC value directly.
Plot ROC curves for multi-class classification using one-vs-rest strategy.
Use other classifiers like RandomForestClassifier or XGBClassifier with the same approach.

python

from sklearn.metrics import roc_auc_score

# Calculate AUC score directly
auc_score = roc_auc_score(y_test, y_scores)
print(f'AUC score: {auc_score:.2f}')

output

AUC score: 0.91

Troubleshooting

If predict_proba is not available, use decision_function for classifiers like SVM.
Ensure binary labels are 0 and 1; otherwise, binarize labels before ROC computation.
If ROC curve looks like a diagonal line, check if predictions are random or model is not trained properly.

✅

Key Takeaways

Use roc_curve with true labels and predicted probabilities to get FPR and TPR for ROC plotting.
Plot ROC curve with matplotlib for visual evaluation of binary classifiers.
Use roc_auc_score to quantify classifier performance with a single scalar.
For classifiers without predict_proba, use decision_function scores instead.
Ensure labels are binary and properly formatted before ROC computation.

Verified 2026-04

Verify ↗