roc curve

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')

roc curve

#ROC curve code snippet from external source(Module notes)
def draw_roc( actual, probs ):
    fpr, tpr, thresholds = metrics.roc_curve( actual, probs,
                                              drop_intermediate = False )
    auc_score = metrics.roc_auc_score( actual, probs )
    plt.figure(figsize=(5, 5))
    plt.plot( fpr, tpr, label='ROC curve (area = %0.2f)' % auc_score )
    plt.plot([0, 1], [0, 1], 'k--')
    plt.xlim([0.0, 1.0])
    plt.ylim([0.0, 1.05])
    plt.xlabel('False Positive Rate or [1 - True Negative Rate]')
    plt.ylabel('True Positive Rate')
    plt.title('Receiver operating characteristic example')
    plt.legend(loc="lower right")
    plt.show()

    return None

fpr, tpr, thresholds = metrics.roc_curve( y_train_pred_final.Converted, y_train_pred_final.Converted_prob, drop_intermediate = False )

draw_roc(y_train_pred_final.Converted, y_train_pred_final.Converted_prob)

Posted by: Guest on November-19-2020

y_pred_logreg_proba = classifier_logreg.predict_proba(X_test) from sklearn.metrics import roc_curve fpr, tpr, thresholds = roc_curve(y_test, y_pred_logreg_proba[:,1]) plt.figure(figsize=(6,4)) plt.plot(fpr,tpr,'-g',linewidth=1) plt.plot([0,1], [0,1], 'k--' ) plt.title('ROC curve for Logistic Regression Model') plt.xlabel("False Positive Rate") plt.ylabel('True Positive Rate') plt.show()

# Now let's calculate accuracy sensitivity and specificity for various probability cutoffs. cutoff_df = pd.DataFrame( columns = ['prob','accuracy','sensi','speci']) from sklearn.metrics import confusion_matrix # TP = confusion[1,1] # true positive # TN = confusion[0,0] # true negatives # FP = confusion[0,1] # false positives # FN = confusion[1,0] # false negatives num = [0.0,0.1,0.2,0.3,0.4,0.5,0.6,0.7,0.8,0.9] for i in num: cm1 = metrics.confusion_matrix(y_train_pred_final.Churn, y_train_pred_final[i] ) total1=sum(sum(cm1)) accuracy = (cm1[0,0]+cm1[1,1])/total1 speci = cm1[0,0]/(cm1[0,0]+cm1[0,1]) sensi = cm1[1,1]/(cm1[1,0]+cm1[1,1]) cutoff_df.loc[i] =[ i ,accuracy,sensi,speci] print(cutoff_df)

Code answers related to "roc curve"

Code answers related to "Whatever"

Browse Popular Code Answers by Language

Answers for "roc curve"

Code answers related to "roc curve"

Code answers related to "Whatever"

Browse Popular Code Answers by Language

Popular Programming Languages

Advertisements

Company

Compilers

Help

Connect with us