Expose models objects (#89)

* Expose models objects * Update CHANGELOG
nubank · Aug 16, 2019 · 0809c75 · 0809c75
1 parent fe2908b
commit 0809c75
Show file tree

Hide file tree

Showing 5 changed files with 25 additions and 19 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,5 +1,9 @@
 # Changelog
 
+## [1.15.1] - 2019-08-16
+- **Enhancement**
+    - Now learners that have a model exposes it in the logs as `object` key
+
 ## [1.15.0] - 2019-08-12
 - **Enhancement**
     - Make `custom_transformer` a pure function

diff --git a/src/fklearn/resources/VERSION b/src/fklearn/resources/VERSION
@@ -1 +1 @@
-1.15.0
+1.15.1
diff --git a/src/fklearn/training/calibration.py b/src/fklearn/training/calibration.py
@@ -51,8 +51,8 @@ def p(new_df: pd.DataFrame) -> pd.DataFrame:
         'prediction_column': prediction_column,
         'package': "sklearn",
         'package_version': sklearn.__version__,
-        'training_samples': len(df)
-    }}
+        'training_samples': len(df)},
+        'object': clf}
 
     return p, p(df), log
 

diff --git a/src/fklearn/training/classification.py b/src/fklearn/training/classification.py
@@ -86,8 +86,8 @@ def p(new_df: pd.DataFrame) -> pd.DataFrame:
         'package': "sklearn",
         'package_version': sk_version,
         'feature_importance': dict(zip(features, clf.coef_.flatten())),
-        'training_samples': len(df)
-    }}
+        'training_samples': len(df)},
+        'object': clf}
 
     return p, p(df), log
 
@@ -219,8 +219,8 @@ def p(new_df: pd.DataFrame, apply_shap: bool = False) -> pd.DataFrame:
         'package_version': xgb.__version__,
         'parameters': assoc(params, "num_estimators", num_estimators),
         'feature_importance': bst.get_score(),
-        'training_samples': len(df)
-    }}
+        'training_samples': len(df)},
+        'object': bst}
 
     return p, p(df), log
 
@@ -357,8 +357,8 @@ def p(new_df: pd.DataFrame, apply_shap: bool = False) -> pd.DataFrame:
         'package_version': catboost.__version__,
         'parameters': assoc(params, "num_estimators", num_estimators),
         'feature_importance': cbr.feature_importances_,
-        'training_samples': len(df)
-    }}
+        'training_samples': len(df)},
+        'object': cbr}
 
     return p, p(df), log
 
@@ -446,8 +446,8 @@ def p(new_df: pd.DataFrame) -> pd.DataFrame:
         'parameters': assoc(params, "vocab_size", sparse_vect.shape[1]),
         'package': "sklearn",
         'package_version': sk_version,
-        'training_samples': len(df)
-    }}
+        'training_samples': len(df)},
+        'object': clf}
 
     return p, p(df), log
 

diff --git a/src/fklearn/training/regression.py b/src/fklearn/training/regression.py
@@ -78,8 +78,8 @@ def p(new_df: pd.DataFrame) -> pd.DataFrame:
         'package': "sklearn",
         'package_version': sk_version,
         'feature_importance': dict(zip(features, regr.coef_.flatten())),
-        'training_samples': len(df)
-    }}
+        'training_samples': len(df)},
+        'object': regr}
 
     return p, p(df), log
 
@@ -190,8 +190,8 @@ def p(new_df: pd.DataFrame, apply_shap: bool = False) -> pd.DataFrame:
         'package_version': xgb.__version__,
         'parameters': assoc(params, "num_estimators", num_estimators),
         'feature_importance': bst.get_score(),
-        'training_samples': len(df)
-    }}
+        'training_samples': len(df)},
+        'object': bst}
 
     return p, p(df), log
 
@@ -295,8 +295,8 @@ def p(new_df: pd.DataFrame, apply_shap: bool = False) -> pd.DataFrame:
         'package_version': catboost.__version__,
         'parameters': assoc(params, "num_estimators", num_estimators),
         'feature_importance': cbr.feature_importances_,
-        'training_samples': len(df)
-    }}
+        'training_samples': len(df)},
+        'object': cbr}
 
     return p, p(df), log
 
@@ -395,8 +395,8 @@ def p(new_df: pd.DataFrame) -> pd.DataFrame:
         'prediction_column': prediction_column,
         'package': "sklearn",
         'package_version': sk_version,
-        'training_samples': len(df)
-    }}
+        'training_samples': len(df)},
+        'object': gp}
 
     return p, p(df), log
 
@@ -592,6 +592,8 @@ def p(new_df: pd.DataFrame) -> pd.DataFrame:
 
     p.__doc__ = learner_pred_fn_docstring("custom_supervised_model_learner")
 
+    log["object"] = model
+
     return p, p(df), log