I have a label prediction of the testing data set y. It is an array of 0 and 1. I also transfer it into a 20000 by 1 array as a label.
y_pred = classifier.predict(X_test)
y_pred = (y_pred > 0.5)
y_pred=y_pred.astype(int)
y_pred1=np.reshape(y_pred, (20000,1))
print(y_pred1)
print(y_pred1.shape)
[[1 1 1 ... 0 0 0]]
(1, 20000)
I want to write such y into a .csv file (one column is ID and one column is our predict labeled y). I saw the following code:
result = pd.DataFrame({'Id':test['Id'].values, 'Default':y_pred.astype(np.int32)})
result.to_csv("1.csv", index=False)
result.head(10)
But there is an error report: ValueError: Data must be 1-dimensional