Release 1190 (nubank#139)

* Bump version * Update CHANGELOG * Fix flake8 version Goal here is to keep the tests consistent and deterministic. Rellying in major bumps would lead to unexpected behaviours, like previous code that used to pass our lint stopping. * Fix E741 * Pin numba version * Pin distributed version
MarianaBlaz · Jun 17, 2020 · 11fa607 · 11fa607
1 parent e4f8b3f
commit 11fa607
Show file tree

Hide file tree

Showing 7 changed files with 11 additions and 5 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,5 +1,9 @@
 # Changelog
 
+## [1.19.0] - 2020-06-17
+- **Enhancement**
+    - Improve `space_time_split_dataset` performance
+
 ## [1.18.0] - 2020-05-08
 - **Enhancement**
     - Allow users to inform a Placeholder value in imputer learner

diff --git a/requirements.txt b/requirements.txt
@@ -5,3 +5,4 @@ pandas>=0.24.1,<0.25
 scikit-learn>=0.21.2,<0.22.0
 statsmodels>=0.9.0,<1
 toolz>=0.9.0,<1
+numba==0.48.0
diff --git a/requirements_tools.txt b/requirements_tools.txt
@@ -1,2 +1,3 @@
 shap>=0.31.0,<=0.34
 swifter>=0.284,<0.300
+distributed>=2.14.0,<2.17.0
diff --git a/scripts/lint.sh b/scripts/lint.sh
@@ -7,7 +7,7 @@ source $cur_dir/helpers.sh
 
 activate_venv
 
-venv/bin/python3 -m pip install -q flake8
+venv/bin/python3 -m pip install -q flake8==3.8.0
 venv/bin/python3 -m flake8 \
 --ignore=E731,W503 \
 --filename=*.py \

diff --git a/src/fklearn/resources/VERSION b/src/fklearn/resources/VERSION
@@ -1 +1 @@
-1.18.0
+1.19.0
diff --git a/src/fklearn/training/pipeline.py b/src/fklearn/training/pipeline.py
@@ -60,8 +60,8 @@ def _no_variable_args(learner: LearnerFnType, predict_fn: PredictFnType) -> None
                              .format(learner.__name__, ', '.join(var_args)))
 
     # Check for unfilled arguments of learners
-    for l in learners:
-        _has_one_unfilled_arg(l)
+    for learner in learners:
+        _has_one_unfilled_arg(learner)
 
     def pipeline(data: pd.DataFrame) -> LearnerReturnType:
         current_data = data.copy()

diff --git a/src/fklearn/validation/splitters.py b/src/fklearn/validation/splitters.py
@@ -457,7 +457,7 @@ def spatial_learning_curve_splitter(train_data: pd.DataFrame,
 
     folds_indices = _lc_fold_to_indexes(folds)  # final formatting with idx
 
-    logs = [assoc(l, "percentage", p) for l, p in zip(map(_log_time_fold, folds), train_percentages)]
+    logs = [assoc(learner, "percentage", p) for learner, p in zip(map(_log_time_fold, folds), train_percentages)]
 
     return folds_indices, logs