Python Forum

Dear all,
I am working on a pandas dataframe df and I would like to implement a K-Neighbors Classifier with sklearn. I have three variables that would make one parameter and one variable for the labels. I generated 3 arrays from df with numpy, and concatenated them into a matrix

A = np.array(df.smoke_code)
B = np.array(df.drug_code)
C = np.array(df.drink_code)
mat = np.column_stack((A,B,C))
mat
Out[77]:
array([[0.25 , 0. , 0.4 ],
[0. , 0.33333333, 0.6 ],
[0. , 0. , 0.4 ],
…,
[0. , 0.33333333, 0.6 ],
[0. , 0. , 0. ],
[0.5 , 1. , 0.4 ]]

The matrix has 3 columns as expected. I then created and fed the classifier as follows:

x = mat
y = pd.factorize(new_df[‘label_code’].values)[0].reshape(-1, 1) # label
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=42)

model = KNeighborsClassifier(n_neighbors = 12)
model.fit(x_train, y_train)
prediction = model.predict_proba(x_test)
print(accuracy_score(y_test, prediction))
main:11: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
Traceback (most recent call last):

File “”, line 13, in 
print(accuracy_score(y_test, prediction))

File “/home/gigiux/.local/lib/python3.6/site-packages/sklearn/metrics/classification.py”, line 176, in accuracy_score
y_type, y_true, y_pred = _check_targets(y_true, y_pred)

File “/home/gigiux/.local/lib/python3.6/site-packages/sklearn/metrics/classification.py”, line 81, in _check_targets
“and {1} targets”.format(type_true, type_pred))

ValueError: Classification metrics can’t handle a mix of multiclass and continuous-multioutput targets

I don’t understand how I am getting the last error. How can I solve this?
Thank you