Skip to content

Feature/features multi index #16

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 6 commits into from
Dec 11, 2019
Merged

Feature/features multi index #16

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
c42cf0f
fix issue in `features_labels` and add sanity check
somefreestring Dec 7, 2019
1ce80f0
use multi index for feature engineering (i.e. lagging)
somefreestring Dec 7, 2019
2e2eabd
optimize the prediction_to_frame function
somefreestring Dec 8, 2019
0f51e11
optimize the prediction_to_frame function
somefreestring Dec 8, 2019
d2ca8a6
fix multi model unbalanced predictions from skit learn
somefreestring Dec 11, 2019
d3e9a80
update readme
somefreestring Dec 11, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
optimize the prediction_to_frame function
  • Loading branch information
@somefreestring
somefreestring committed Dec 8, 2019
commit 0f51e119649a3ad2112ae3a0358e79349c50d5b2
1 change: 1 addition & 0 deletions pandas_ml_utils/model/features_and_labels/target_encoder.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -109,6 +109,7 @@ def labels_source_columns(self) -> List[str]:

@property
def encoded_labels_columns(self) -> List[str]:
#return [str(11) if isinstance(cat, pd._libs.interval.Interval) else str(cat) for cat in self.buckets]
return [str(cat) for cat in self.buckets]

def encode(self, df: pd.DataFrame) -> pd.DataFrame:
Expand Down
6 changes: 3 additions & 3 deletions test/z_component_tests/test__classification.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -76,14 +76,14 @@ def make_targets(t, frame):
"""then"""
self.assertEqual(len(fit_summary_df), 4023)
self.assertListEqual(fit_summary_df.columns.tolist(),
[(PREDICTION_COLUMN_NAME, 'label #0'), (PREDICTION_COLUMN_NAME, 'label #1'), (PREDICTION_COLUMN_NAME, 'label #2'), (PREDICTION_COLUMN_NAME, 'label #3'),
(LABEL_COLUMN_NAME, 'label #0'), (LABEL_COLUMN_NAME, 'label #1'), (LABEL_COLUMN_NAME, 'label #2'), (LABEL_COLUMN_NAME, 'label #3'),
[(PREDICTION_COLUMN_NAME, '(-inf, -0.05]'), (PREDICTION_COLUMN_NAME, '(-0.05, 0.0]'), (PREDICTION_COLUMN_NAME, '(0.0, 0.05000000000000002]'), (PREDICTION_COLUMN_NAME, '(0.05000000000000002, inf]'),
(LABEL_COLUMN_NAME, '(-inf, -0.05]'), (LABEL_COLUMN_NAME, '(-0.05, 0.0]'), (LABEL_COLUMN_NAME, '(0.0, 0.05000000000000002]'), (LABEL_COLUMN_NAME, '(0.05000000000000002, inf]'),
(TARGET_COLUMN_NAME, 'close <0.1'), (TARGET_COLUMN_NAME, 'close <0.05'), (TARGET_COLUMN_NAME, 'close >0'), (TARGET_COLUMN_NAME, 'close >0.05')])

self.assertListEqual(bt_summary_df.columns.tolist(), fit_summary_df.columns.tolist())

self.assertListEqual(predict_df.columns.tolist(),
[(PREDICTION_COLUMN_NAME, 'label #0'), (PREDICTION_COLUMN_NAME, 'label #1'), (PREDICTION_COLUMN_NAME, 'label #2'), (PREDICTION_COLUMN_NAME, 'label #3'),
[(PREDICTION_COLUMN_NAME, '(-inf, -0.05]'), (PREDICTION_COLUMN_NAME, '(-0.05, 0.0]'), (PREDICTION_COLUMN_NAME, '(0.0, 0.05000000000000002]'), (PREDICTION_COLUMN_NAME, '(0.05000000000000002, inf]'),
(TARGET_COLUMN_NAME, 'close <0.1'), (TARGET_COLUMN_NAME, 'close <0.05'), (TARGET_COLUMN_NAME, 'close >0'), (TARGET_COLUMN_NAME, 'close >0.05')])

def test_target_classification(self):
Expand Down
14 changes: 8 additions & 6 deletions test/z_component_tests/test__multi_model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,6 +17,7 @@


class MultiModelTest(unittest.TestCase):
maxDiff = None

def test_invalid_multi_model(self):
"""expect"""
Expand Down Expand Up @@ -80,18 +81,19 @@ def test_multi_model_multi_class_classifications(self):
predict_df = df.predict(fit.model, tail=1)

"""then"""
print(fit_summary_df.columns.tolist())
self.assertListEqual(fit_summary_df.columns.tolist(),
[('1', 'prediction', 'is_above_1.0 #0'), ('1', 'prediction', 'is_above_1.0 #1'), ('1', 'prediction', 'is_above_1.0 #2'), ('1', 'prediction', 'is_above_1.0 #3'),
('2', 'prediction', 'is_above_1.2 #0'), ('2', 'prediction', 'is_above_1.2 #1'), ('2', 'prediction', 'is_above_1.2 #2'), ('2', 'prediction', 'is_above_1.2 #3'),
('1', 'label', 'is_above_1.0 #0'), ('1', 'label', 'is_above_1.0 #1'), ('1', 'label', 'is_above_1.0 #2'), ('1', 'label', 'is_above_1.0 #3'),
('2', 'label', 'is_above_1.2 #0'), ('2', 'label', 'is_above_1.2 #1'), ('2', 'label', 'is_above_1.2 #2'), ('2', 'label', 'is_above_1.2 #3'),
[('1', 'prediction', '(-inf, 0.95]'), ('1', 'prediction', '(0.95, 1.0]'), ('1', 'prediction', '(1.0, 1.05]'), ('1', 'prediction', '(1.05, inf]'),
('2', 'prediction', '(-inf, 1.95]'), ('2', 'prediction', '(1.95, 2.0]'), ('2', 'prediction', '(2.0, 2.05]'), ('2', 'prediction', '(2.05, inf]'),
('1', 'label', '(-inf, 0.95]'), ('1', 'label', '(0.95, 1.0]'), ('1', 'label', '(1.0, 1.05]'), ('1', 'label', '(1.05, inf]'),
('2', 'label', '(-inf, 1.95]'), ('2', 'label', '(1.95, 2.0]'), ('2', 'label', '(2.0, 2.05]'), ('2', 'label', '(2.05, inf]'),
('1', 'loss', '1'), ('2', 'loss', '2'),
('1', 'target', 'sma 1'), ('2', 'target', 'sma 2')])

self.assertListEqual(bt_summary_df.columns.tolist(), fit_summary_df.columns.tolist())

self.assertListEqual(predict_df.columns.tolist(),
[('1', 'prediction', 'is_above_1.0 #0'), ('1', 'prediction', 'is_above_1.0 #1'), ('1', 'prediction', 'is_above_1.0 #2'), ('1', 'prediction', 'is_above_1.0 #3'),
('2', 'prediction', 'is_above_1.2 #0'), ('2', 'prediction', 'is_above_1.2 #1'), ('2', 'prediction', 'is_above_1.2 #2'), ('2', 'prediction', 'is_above_1.2 #3'),
[('1', 'prediction', '(-inf, 0.95]'), ('1', 'prediction', '(0.95, 1.0]'), ('1', 'prediction', '(1.0, 1.05]'), ('1', 'prediction', '(1.05, inf]'),
('2', 'prediction', '(-inf, 1.95]'), ('2', 'prediction', '(1.95, 2.0]'), ('2', 'prediction', '(2.0, 2.05]'), ('2', 'prediction', '(2.05, inf]'),
('1', 'target', 'sma 1'), ('2', 'target', 'sma 2')])