def test_weighted_avg(self):
y1, y2, y3 = [1, 2, 3], [4, 5, 6], [7, 8, 9]
df = pd.DataFrame({'y1': y1, 'y2': y2, 'y3': y3})
# Check unweighted mean
self.assertTrue(np.array_equal(
df.mean(axis=1).values,
ensemble.weighted_avg([y1, y2, y3])
))
# Check weighted mean
self.assertTrue(np.array_equal(
ensemble.weighted_avg([y1, y2, y3], weights=[1, 1, 2]),
np.array([19/4, 23/4, 27/4])
))
def weighted_avg_from_files(
fnames, outfile, weights=[],
sample_submission_file=DEFAULT_SAMPLE_SUBMISSION_FILE,
sample_submission_idx=DEFAULT_SAMPLE_SUBMISSION_IDX):
"""Compute weighted avg from submission files, and save results to a new file
Parameters
----------
fnames : Iterable of str's
Submission file names of y_hats to be averaged
outfile : str
Output file name, including path
weights : Iterable
Weights corresponding to y_hats in the same order.
If weights is empty, then the model just returns unweighted mean.
sample_submission_file : str
Path to example submission file provided by Kaggle
sample_submission_idx : str
Index column name in `sample_submission_file`
Returns
-------
y_hat_avg : numpy.ndarray
Weighted averages
"""
y_hat_avg = ensemble.weighted_avg(
[pd.read_csv(f, index_col=sample_submission_idx, squeeze=True).values
for f in fnames],
weights=weights
)
save_submission(y_hat_avg, outfile,
sample_submission_file=sample_submission_file)
return y_hat_avg
