How to plot a ROC Curve in Python?
DATA VISUALIZATION DATA CLEANING PYTHON DATA MUNGING MACHINE LEARNING RECIPES PANDAS CHEATSHEET     ALL TAGS

How to plot a ROC Curve in Python?

How to plot a ROC Curve in Python?

This recipe helps you plot a ROC Curve in Python

0

Recipe Objective

While working on a classification model, we feel a need of a metric which can show us how our model is performing. A metric which can also give a graphical representation of the performance will be very helpful.

ROC curve can efficiently give us the score that how our model is performing in classifing the labels. We can also plot graph between False Positive Rate and True Positive Rate with this ROC(Receiving Operating Characteristic) curve. The area under the ROC curve give is also a metric. Greater the area means better the performance.
Note that we can use ROC curve for a classification problem with two classes in the target. For Data having more than two classes we have to plot ROC curve with respect to each class taking rest of the combination of other classes as False Class.

So this recipe is a short example of how to use ROC and AUC to see the performance of our model.Here we will use it on two models for better understanding.

Step 1 - Import the library - GridSearchCv

from sklearn import datasets from sklearn.tree import DecisionTreeClassifier from sklearn.linear_model import LogisticRegression from sklearn.metrics import roc_curve, roc_auc_score from sklearn.model_selection import train_test_split import matplotlib.pyplot as plt

Here we have imported various modules like: datasets from which we will get the dataset, DecisionTreeClassifier and LogisticRegression which we will use a models, roc_curve and roc_auc_score will be used to get the score and help us to plot the graph, train_test_split will split the data into two parts train and test and plt will be used to plot the graph.

Step 2 - Setup the Data

Here we have used datasets to load the inbuilt wine dataset and we have created objects X and y to store the data and the target value respectively. dataset = datasets.load_wine() X = dataset.data y = dataset.target

Step 3 - Spliting the data and Training the model

The module train_test_split is used to split the data into two parts, one is train which is used to train the model and the other is test which is used to check how our model is working on unseen data. Here we are passing 0.3 as a parameter in the train_test_split which will split the data such that 30% of data will be in test part and rest 70% will be in the train part. X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3)

Now we are creating objects for classifier and training the classifier with the train split of the dataset i.e x_train and y_train. clf_tree = DecisionTreeClassifier(); clf_reg = LogisticRegression(); clf_tree.fit(X_train, y_train); clf_reg.fit(X_train, y_train);

Step 5 - Using the models on test dataset

After traing the classifier on test dataset, we are using the model to predict the target values for test dataset. We are storing the predicted class by both of the models and we will use it to get the ROC AUC score y_score1 = clf_tree.predict_proba(X_test)[:,1] y_score2 = clf_reg.predict_proba(X_test)[:,1]

Step 6 - Creating False and True Positive Rates and printing Scores

We have to get False Positive Rates and True Postive rates for the Classifiers because these will be used to plot the ROC Curve. This can be done by roc_curve module by passing the test dataset and the predicted data through it. Here we are doing this for both the classifier. false_positive_rate1, true_positive_rate1, threshold1 = roc_curve(y_test, y_score1) false_positive_rate2, true_positive_rate2, threshold2 = roc_curve(y_test, y_score2) Now, For getting ROC_AUC score we can simply pass the test data and the predected data into the function ruc_auc_score. We are printing it with print statements for better understanding. print('roc_auc_score for DecisionTree: ', roc_auc_score(y_test, y_score1)) print('roc_auc_score for Logistic Regression: ', roc_auc_score(y_test, y_score2))

Step 7 - Ploting ROC Curves

We are ploting two ROC Curve as subplots one for DecisionTreeClassifier and another for LogisticRegression. Both have their respective False Positive Rate on X-axis and True Positive Rate on Y-axis. plt.subplots(1, figsize=(10,10)) plt.title('Receiver Operating Characteristic - DecisionTree') plt.plot(false_positive_rate1, true_positive_rate1) plt.plot([0, 1], ls="--") plt.plot([0, 0], [1, 0] , c=".7"), plt.plot([1, 1] , c=".7") plt.ylabel('True Positive Rate') plt.xlabel('False Positive Rate') plt.show() plt.subplots(1, figsize=(10,10)) plt.title('Receiver Operating Characteristic - Logistic regression') plt.plot(false_positive_rate2, true_positive_rate2) plt.plot([0, 1], ls="--") plt.plot([0, 0], [1, 0] , c=".7"), plt.plot([1, 1] , c=".7") plt.ylabel('True Positive Rate') plt.xlabel('False Positive Rate') plt.show() As an output we get:

roc_auc_score for DecisionTree:  0.9539141414141414
roc_auc_score for Logistic Regression:  0.9875140291806959

Relevant Projects

Predict Employee Computer Access Needs in Python
Data Science Project in Python- Given his or her job role, predict employee access needs using amazon employee database.

Build an Image Classifier for Plant Species Identification
In this machine learning project, we will use binary leaf images and extracted features, including shape, margin, and texture to accurately identify plant species using different benchmark classification techniques.

Data Science Project on Wine Quality Prediction in R
In this R data science project, we will explore wine dataset to assess red wine quality. The objective of this data science project is to explore which chemical properties will influence the quality of red wines.

Predict Macro Economic Trends using Kaggle Financial Dataset
In this machine learning project, you will uncover the predictive value in an uncertain world by using various artificial intelligence, machine learning, advanced regression and feature transformation techniques.

Identifying Product Bundles from Sales Data Using R Language
In this data science project in R, we are going to talk about subjective segmentation which is a clustering technique to find out product bundles in sales data.

Resume parsing with Machine learning - NLP with Python OCR and Spacy
In this machine learning resume parser example we use the popular Spacy NLP python library for OCR and text classification.

Learn to prepare data for your next machine learning project
Text data requires special preparation before you can start using it for any machine learning project.In this ML project, you will learn about applying Machine Learning models to create classifiers and learn how to make sense of textual data.

Mercari Price Suggestion Challenge Data Science Project
Data Science Project in Python- Build a machine learning algorithm that automatically suggests the right product prices.

Ensemble Machine Learning Project - All State Insurance Claims Severity Prediction
In this ensemble machine learning project, we will predict what kind of claims an insurance company will get. This is implemented in python using ensemble machine learning algorithms.

Predict Churn for a Telecom company using Logistic Regression
Machine Learning Project in R- Predict the customer churn of telecom sector and find out the key drivers that lead to churn. Learn how the logistic regression model using R can be used to identify the customer churn in telecom dataset.