How to plot ROC curve in Python

Question

I am trying to plot a ROC curve to evaluate the accuracy of a prediction model I developed in Python using logistic regression packages. I have computed the true positive ra

Answer 1

Here are two ways you may try, assuming your model is an sklearn predictor:

import sklearn.metrics as metrics
# calculate the fpr and tpr for all thresholds of the classification
probs = model.predict_proba(X_test)
preds = probs[:,1]
fpr, tpr, threshold = metrics.roc_curve(y_test, preds)
roc_auc = metrics.auc(fpr, tpr)

# method I: plt
import matplotlib.pyplot as plt
plt.title('Receiver Operating Characteristic')
plt.plot(fpr, tpr, 'b', label = 'AUC = %0.2f' % roc_auc)
plt.legend(loc = 'lower right')
plt.plot([0, 1], [0, 1],'r--')
plt.xlim([0, 1])
plt.ylim([0, 1])
plt.ylabel('True Positive Rate')
plt.xlabel('False Positive Rate')
plt.show()

# method II: ggplot
from ggplot import *
df = pd.DataFrame(dict(fpr = fpr, tpr = tpr))
ggplot(df, aes(x = 'fpr', y = 'tpr')) + geom_line() + geom_abline(linetype = 'dashed')

or try

ggplot(df, aes(x = 'fpr', ymin = 0, ymax = 'tpr')) + geom_line(aes(y = 'tpr')) + geom_area(alpha = 0.2) + ggtitle("ROC Curve w/ AUC = %s" % str(roc_auc)) 

Answer 2

Here is python code for computing the ROC curve (as a scatter plot):

import matplotlib.pyplot as plt
import numpy as np

score = np.array([0.9, 0.8, 0.7, 0.6, 0.55, 0.54, 0.53, 0.52, 0.51, 0.505, 0.4, 0.39, 0.38, 0.37, 0.36, 0.35, 0.34, 0.33, 0.30, 0.1])
y = np.array([1,1,0, 1, 1, 1, 0, 0, 1, 0, 1,0, 1, 0, 0, 0, 1 , 0, 1, 0])

# false positive rate
fpr = []
# true positive rate
tpr = []
# Iterate thresholds from 0.0, 0.01, ... 1.0
thresholds = np.arange(0.0, 1.01, .01)

# get number of positive and negative examples in the dataset
P = sum(y)
N = len(y) - P

# iterate through all thresholds and determine fraction of true positives
# and false positives found at this threshold
for thresh in thresholds:
    FP=0
    TP=0
    for i in range(len(score)):
        if (score[i] > thresh):
            if y[i] == 1:
                TP = TP + 1
            if y[i] == 0:
                FP = FP + 1
    fpr.append(FP/float(N))
    tpr.append(TP/float(P))

plt.scatter(fpr, tpr)
plt.show()

Answer 3

You can also follow the offical documentation form scikit:

https://scikit-learn.org/stable/auto_examples/model_selection/plot_roc.html#sphx-glr-auto-examples-model-selection-plot-roc-py

Answer 4

AUC curve For Binary Classification using matplotlib

from sklearn import svm, datasets
from sklearn import metrics
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split
from sklearn.datasets import load_breast_cancer
import matplotlib.pyplot as plt

Load Breast Cancer Dataset

breast_cancer = load_breast_cancer()

X = breast_cancer.data
y = breast_cancer.target

Split the Dataset

X_train, X_test, y_train, y_test = train_test_split(X,y,test_size=0.33, random_state=44)

Model

clf = LogisticRegression(penalty='l2', C=0.1)
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)

Accuracy

print("Accuracy", metrics.accuracy_score(y_test, y_pred))

AUC Curve

y_pred_proba = clf.predict_proba(X_test)[::,1]
fpr, tpr, _ = metrics.roc_curve(y_test,  y_pred_proba)
auc = metrics.roc_auc_score(y_test, y_pred_proba)
plt.plot(fpr,tpr,label="data 1, auc="+str(auc))
plt.legend(loc=4)
plt.show()

Answer 5

There is a library called metriculous that will do that for you:

$ pip install metriculous

Let's first mock some data, this would usually come from the test dataset and the model(s):

import numpy as np

def normalize(array2d: np.ndarray) -> np.ndarray:
    return array2d / array2d.sum(axis=1, keepdims=True)

class_names = ["Cat", "Dog", "Pig"]
num_classes = len(class_names)
num_samples = 500

# Mock ground truth
ground_truth = np.random.choice(range(num_classes), size=num_samples, p=[0.5, 0.4, 0.1])

# Mock model predictions
perfect_model = np.eye(num_classes)[ground_truth]
noisy_model = normalize(
    perfect_model + 2 * np.random.random((num_samples, num_classes))
)
random_model = normalize(np.random.random((num_samples, num_classes)))

Now we can use metriculous to generate a table with various metrics and diagrams, including ROC curves:

import metriculous

metriculous.compare_classifiers(
    ground_truth=ground_truth,
    model_predictions=[perfect_model, noisy_model, random_model],
    model_names=["Perfect Model", "Noisy Model", "Random Model"],
    class_names=class_names,
    one_vs_all_figures=True, # This line is important to include ROC curves in the output
).save_html("model_comparison.html").display()

The ROC curves in the output:

The plots are zoomable and draggable, and you get further details when hovering with your mouse over the plot: