ValueError: multi_class must be in ('ovo', 'ovr')

Question

I get the error:

On Training Data: Traceback (most recent call last):

File "C:\Users\Roman\Desktop\Key\Poyd.py", line 80, in stock(AAPL, "AAPL")

File "C:\Users\Roman\Desktop\Key\Poyd.py", line 71, in stock evaluate_print(clf_name, yTrain, y_train_scores)

File "C:\Users\Roman\anaconda3\lib\site-packages\pyod\utils\data.py", line 283, in evaluate_print roc=np.round(roc_auc_score(y, y_pred), decimals=4),

File "C:\Users\Roman\anaconda3\lib\site-packages\sklearn\utils\validation.py", line 63, in inner_f return f(*args, **kwargs)

File "C:\Users\Roman\anaconda3\lib\site-packages\sklearn\metrics_ranking.py", line 536, in roc_auc_score raise ValueError("multi_class must be in ('ovo', 'ovr')")

ValueError: multi_class must be in ('ovo', 'ovr')

example of the data:

so I've taken the X the date column and Y the close\last column

I know there is roc_auc_score How to combine them together? The goal is to create visualization for anomaly detection, but currently it doesn't work.

from pandas import read_csv
from matplotlib import pyplot
import pandas as pd
import matplotlib.pyplot as plt
import matplotlib.dates as mdates
import numpy as np

#from IPython.core.debugger import set_trace

#import data

AAPL= pd.read_csv('AAPL.csv', header=0, squeeze=True)

#function to get stock
def stock(s, title):
    print(title)
#independent variables-Matrix
    X = s.iloc[:,1].values.reshape(-1,1)
    #np.atleast_2d(X)
    print(X)
    
    #dependent variables vectors
    #Y = df.iloc[:, -1].values
    Y = s.iloc[:, 2].values.reshape(-1,1)
    print(Y)
    
    from sklearn.model_selection import train_test_split
    xTrain, xTest, yTrain, yTest = train_test_split(X, Y, test_size = 0.3 ,random_state = 0)#70% on train and 30% on test

    # # train the COPOD detector
    # from pyod.models.copod import COPOD
    # clf = COPOD()
    # clf.fit(xTrain)
    # clf.reshape(-1,1)
    # # get outlier scores
    # y_train_scores = clf.decision_scores_  # raw outlier scores on the train data
    # y_test_scores = clf.decision_function(xTest)  # predict raw outlier scores on test
    # # print("#####################")
    # # print( "outlier:", y_test_scores)
    
    
    from pyod.models.knn import KNN   # kNN detector

    # train kNN detector
    clf_name = 'KNN'
    clf = KNN()
    clf.fit(xTrain)

    # get the prediction label and outlier scores of the training data
    y_train_pred = clf.labels_  # binary labels (0: inliers, 1: outliers)
    y_train_scores = clf.decision_scores_  # raw outlier scores

    # get the prediction on the test data
    y_test_pred = clf.predict(xTest)  # outlier labels (0 or 1)
    y_test_scores = clf.decision_function(xTest)  # outlier scores
    
    from pyod.utils.data import evaluate_print
    from sklearn.metrics import make_scorer
    from sklearn.metrics import roc_auc_score

    #myscore = make_scorer(roc_auc_score, multi_class='ovo',needs_proba=True)
    # evaluate and print the results
    print("\nOn Training Data:")
    evaluate_print(clf_name, yTrain, y_train_scores)
    print("\nOn Test Data:")
    evaluate_print(clf_name, yTest, y_test_scores)

    from pyod.utils.example import visualize
    
    visualize(clf_name, xTrain, yTrain, xTest, yTest, y_train_pred,
    y_test_pred, show_figure=True, save_figure=False)
    
stock(AAPL, "AAPL")

Thank you in advance!

Answer 1

Try this code, it worked for me:

clf = LogisticRegression(solver="liblinear").fit(x_train, y_train)
preds = clf.predict_proba(x_test)
roc_auc = roc_auc_score(y_test,preds, multi_class='ovr')
print(roc_auc)