tasks.py 文件源码

def calculate_feature_statistics(feature_id):
    feature = Feature.objects.get(pk=feature_id)

    dataframe = _get_dataframe(feature.dataset.id)
    feature_col = dataframe[feature.name]

    feature.min = np.amin(feature_col).item()
    feature.max = np.amax(feature_col).item()
    feature.mean = np.mean(feature_col).item()
    feature.variance = np.nanvar(feature_col).item()
    unique_values = np.unique(feature_col)
    integer_check = (np.mod(unique_values, 1) == 0).all()
    feature.is_categorical = integer_check and (unique_values.size < 10)
    if feature.is_categorical:
        feature.categories = list(unique_values)
    feature.save(update_fields=['min', 'max', 'variance', 'mean', 'is_categorical', 'categories'])

    del unique_values, feature