MAPE python

def percentage_error(actual, predicted):
    res = np.empty(actual.shape)
    for j in range(actual.shape[0]):
        if actual[j] != 0:
            res[j] = (actual[j] - predicted[j]) / actual[j]
        else:
            res[j] = predicted[j] / np.mean(actual)
    return res

def mean_absolute_percentage_error(y_true, y_pred): 
    return np.mean(np.abs(percentage_error(np.asarray(y_true), np.asarray(y_pred)))) * 100

Source: stackoverflow.com

Similar codes

0 vote252 views1 answer
Yahoo! Finance pyhton
Python
3 votes247 views1 answer
How to delete a turtle in python
Python
0 vote234 views1 answer
HOW AttributeError: module 'scipy.misc' has no attribute 'imread'
Python
1 vote242 views1 answer
Python list comprehension index, value
Python
2 votes282 views1 answer
Pandas groupby count unique rows
Python
0 vote276 views1 answer
Python get file path from in os.walk
Python
0 vote218 views1 answer
Add date and time of today in python
Python
0 vote251 views1 answer
Gene wilder pure imagination
Python
0 vote270 views1 answer
How to save multiple choices in django site:stackoverflow.com
Python
0 vote257 views1 answer
Select rainfall events and calculate rainfall event total from time-series data
Python