Feature/groupby2

examples/README.md

@@ -14,3 +14,4 @@
 12. `demo11.py` - AutoML NLP preset usage for tabular datasets with text columns
 13. `demo12.py` - AutoML tabular preset usage with custom validation scheme and multiprocessed inference
 14. `demo13.py` - AutoML TS preset usage with lag and diff transformers' parameters selection
+15. `demo14.py` - Groupby features (using TabularAutoML preset and custom pipeline)

examples/demo14.py

@@ -0,0 +1,109 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+import numpy as np
+import pandas as pd
+
+from sklearn.model_selection import train_test_split
+
+from lightautoml.automl.base import AutoML
+from lightautoml.automl.presets.tabular_presets import TabularAutoML
+from lightautoml.dataset.roles import CategoryRole
+from lightautoml.dataset.roles import NumericRole
+from lightautoml.ml_algo.boost_lgbm import BoostLGBM
+from lightautoml.pipelines.features.lgb_pipeline import LGBAdvancedPipeline
+from lightautoml.pipelines.features.lgb_pipeline import LGBSimpleFeatures
+from lightautoml.pipelines.ml.base import MLPipeline
+from lightautoml.pipelines.selection.importance_based import ImportanceCutoffSelector
+from lightautoml.pipelines.selection.importance_based import (
+    ModelBasedImportanceEstimator,
+)
+from lightautoml.reader.base import PandasToPandasReader
+from lightautoml.tasks import Task
+
+
+################################
+# Features:
+# - group_by transformer
+################################
+
+N_FOLDS = 3  # number of folds for cross-validation inside AutoML
+RANDOM_STATE = 42  # fixed random state for various reasons
+N_THREADS = 4  # threads cnt for lgbm and linear models
+TIMEOUT = 100
+USED_COLS = ["SK_ID_CURR", "TARGET", "NAME_CONTRACT_TYPE", "CODE_GENDER", "AMT_INCOME_TOTAL", "DAYS_BIRTH"]
+TARGET = "TARGET"
+
+# load data
+data = pd.read_csv("./data/sampled_app_train.csv")
+data = data[USED_COLS]
+train, test = train_test_split(data, test_size=2000, random_state=42)
+
+# Using TabularAutoML preset
+task = Task("binary")
+roles = {
+    "target": TARGET,
+    CategoryRole(dtype=str): ["NAME_CONTRACT_TYPE", "CODE_GENDER"],
+    NumericRole(np.float32): ["AMT_INCOME_TOTAL"],
+}
+
+# specify groupby triplets: [("group_col", "feature", "transform_type"),]
+groupby_triplets = [
+    ("CODE_GENDER", "AMT_INCOME_TOTAL", "max"),
+    ("NAME_CONTRACT_TYPE", "CODE_GENDER", "mode"),
+    ("NAME_CONTRACT_TYPE", "AMT_INCOME_TOTAL", "delta_mean"),
+]
+
+print(f"Try TabularAutoML with the following groupby_triplets:\n{groupby_triplets}")
+
+automl = TabularAutoML(
+    task=task,
+    timeout=TIMEOUT,
+    cpu_limit=N_THREADS,
+    reader_params={"n_jobs": N_THREADS, "cv": N_FOLDS, "random_state": RANDOM_STATE},
+    general_params={"use_algos": [["lgb"]]},
+    gbm_pipeline_params={"use_groupby": True, "groupby_triplets": groupby_triplets},
+)
+automl.fit_predict(train, roles=roles)
+
+feature_scores = automl.levels[0][0].ml_algos[0].get_features_score()
+
+print(f"Feature importances of BoostLGBM model. Pay attention to groupby features:\n{feature_scores}")
+
+# Custom pipeline with groupby features defined by importance
+print("\nTry custom pipeline with groupby features defined by importance:\n")
+
+task = Task("binary")
+reader = PandasToPandasReader(task, cv=N_FOLDS, random_state=RANDOM_STATE)
+model0 = BoostLGBM(default_params={"learning_rate": 0.1, "num_leaves": 64, "seed": 42, "num_threads": N_THREADS})
+pie = ModelBasedImportanceEstimator()
+selector = ImportanceCutoffSelector(LGBSimpleFeatures(), model0, pie, cutoff=-9999)
+
+
+pipe = LGBAdvancedPipeline(
+    use_groupby=True, pre_selector=selector, groupby_types=["delta_median", "std"], groupby_top_based_on="importance"
+)
+
+model = BoostLGBM(
+    default_params={
+        "learning_rate": 0.05,
+        "num_leaves": 128,
+        "seed": 1,
+        "num_threads": N_THREADS,
+    }
+)
+
+pipeline = MLPipeline([model], pre_selection=selector, features_pipeline=pipe, post_selection=None)
+
+automl = AutoML(
+    reader,
+    [[pipeline]],
+    skip_conn=False,
+)
+
+oof_pred = automl.fit_predict(
+    train,
+    roles={"target": TARGET},
+)
+
+print(f"Feature used by BoostLGBM model. Pay attention to groupby features:\n{pipe.output_features}")

lightautoml/automl/presets/image_config.yml

@@ -128,8 +128,21 @@ gbm_pipeline_params:
   auto_unique_co: 10
   # n_classes to use target encoding for multiclass task
   multiclass_te_co: 3
+  # use groupby features
+  use_groupby: False
+  # groupby types used in feature engeneering
+  groupby_types: [ 'delta_median', 'delta_mean', 'min', 'max', 'std', 'mode', 'is_mode' ]
+  # top features are choosen by cardinality or feature importance
+  groupby_top_based_on: 'cardinality'
+  # top categorical features to use in groupby transformer
+  groupby_top_categorical: 3
+  # top numerical features to use in groupby transformer
+  groupby_top_numerical: 3
+  # list of groupby triplets ("group_col", "feat", "groupby_type") for manual setting
+  # disables groupby_types, groupby_top_based_on and other groupby parameters if defined
+  groupby_triplets: [ ]
   # text_features in gbm feature pipeline. embed or simple
-  cv_features: "simple"
+  cv_features: 'simple'
 
 linear_pipeline_params:
   # max number of categories to generate intersections
@@ -141,8 +154,21 @@ linear_pipeline_params:
   auto_unique_co: 50
   # n_classes to use target encoding for multiclass task
   multiclass_te_co: 3
+  # use groupby features
+  use_groupby: False
+  # groupby types used in feature engeneering
+  groupby_types: [ 'delta_median', 'delta_mean', 'min', 'max', 'std', 'mode', 'is_mode' ]
+  # top features are choosen by cardinality or feature importance
+  groupby_top_based_on: 'cardinality'
+  # top categorical features to use in groupby transformer
+  groupby_top_categorical: 3
+  # top numerical features to use in groupby transformer
+  groupby_top_numerical: 3
+  # list of groupby triplets ("group_col", "feat", "groupby_type") for manual setting
+  # disables groupby_types, groupby_top_based_on and other groupby parameters if defined
+  groupby_triplets: [ ]
   # text_features in linear feature pipeline. embed or simple
-  cv_features: "embed"
+  cv_features: 'embed'
 
 timing_params:
   # select timing mode:

lightautoml/automl/presets/image_presets.py

@@ -231,7 +231,7 @@ def get_gbms(
     ):
         """Get gbm pipeline."""
         cv_gbm_feats = self.get_cv_pipe(self.gbm_pipeline_params["cv_features"])
-        gbm_feats = LGBAdvancedPipeline(output_categories=False, **self.gbm_pipeline_params)
+        gbm_feats = LGBAdvancedPipeline(feats_imp=pre_selector, output_categories=False, **self.gbm_pipeline_params)
         if cv_gbm_feats is not None:
             gbm_feats.append(cv_gbm_feats)
 

lightautoml/automl/presets/tabular_config.yml

@@ -244,6 +244,19 @@ gbm_pipeline_params:
   multiclass_te_co: 3
   # DEV feature: output categorical features as categories (if True, can totally overfit your model - be careful!)
   output_categories: False
+  # use groupby features
+  use_groupby: False
+  # groupby types used in feature engeneering
+  groupby_types: [ 'delta_median', 'delta_mean', 'min', 'max', 'std', 'mode', 'is_mode' ]
+  # top features are choosen by cardinality or feature importance
+  groupby_top_based_on: 'cardinality'
+  # top categorical features to use in groupby transformer
+  groupby_top_categorical: 3
+  # top numerical features to use in groupby transformer
+  groupby_top_numerical: 3
+  # list of groupby triplets ("group_col", "feat", "groupby_type") for manual setting
+  # disables groupby_types, groupby_top_based_on and other groupby parameters if defined
+  groupby_triplets: [ ]
 
 linear_pipeline_params:
   # max number of categories to generate intersections
@@ -255,6 +268,19 @@ linear_pipeline_params:
   auto_unique_co: 50
   # n_classes to use target encoding for multiclass task
   multiclass_te_co: 3
+  # use groupby features
+  use_groupby: False
+  # groupby types used in feature engeneering
+  groupby_types: [ 'delta_median', 'delta_mean', 'min', 'max', 'std', 'mode', 'is_mode' ]
+  # top features are choosen by cardinality or feature importance
+  groupby_top_based_on: 'cardinality'
+  # top categorical features to use in groupby transformer
+  groupby_top_categorical: 3
+  # top numerical features to use in groupby transformer
+  groupby_top_numerical: 3
+  # list of groupby triplets ("group_col", "feat", "groupby_type") for manual setting
+  # disables groupby_types, groupby_top_based_on and other groupby parameters if defined
+  groupby_triplets: [ ]
 
 nn_pipeline_params:
   # use quantile transformer for numerical columns

lightautoml/automl/presets/tabular_presets.py

@@ -429,7 +429,7 @@ def get_gbms(
         pre_selector: Optional[SelectionPipeline] = None,
     ):
 
-        gbm_feats = LGBAdvancedPipeline(**self.gbm_pipeline_params)
+        gbm_feats = LGBAdvancedPipeline(**self.gbm_pipeline_params, feats_imp=pre_selector)
 
         ml_algos = []
         force_calc = []
@@ -464,7 +464,7 @@ def get_gbms(
 
     def get_rfs(self, keys: Sequence[str], n_level: int = 1, pre_selector: Optional[SelectionPipeline] = None):
 
-        rf_feats = LGBAdvancedPipeline(**self.gbm_pipeline_params, fill_na=True)
+        rf_feats = LGBAdvancedPipeline(**self.gbm_pipeline_params, feats_imp=pre_selector, fill_na=True)
 
         ml_algos = []
         force_calc = []

lightautoml/automl/presets/text_config.yml

@@ -187,6 +187,19 @@ gbm_pipeline_params:
   auto_unique_co: 10
   # n_classes to use target encoding for multiclass task
   multiclass_te_co: 3
+  # use groupby features
+  use_groupby: False
+  # groupby types used in feature engeneering
+  groupby_types: [ 'delta_median', 'delta_mean', 'min', 'max', 'std', 'mode', 'is_mode' ]
+  # top features are choosen by cardinality or feature importance
+  groupby_top_based_on: 'cardinality'
+  # top categorical features to use in groupby transformer
+  groupby_top_categorical: 3
+  # top numerical features to use in groupby transformer
+  groupby_top_numerical: 3
+  # list of groupby triplets ("group_col", "feat", "groupby_type") for manual setting
+  # disables groupby_types, groupby_top_based_on and other groupby parameters if defined
+  groupby_triplets: [ ]
   # text_features in gbm feature pipeline. embed or tfidf
   text_features: "embed"
 
@@ -200,6 +213,19 @@ linear_pipeline_params:
   auto_unique_co: 50
   # n_classes to use target encoding for multiclass task
   multiclass_te_co: 3
+  # use groupby features
+  use_groupby: False
+  # groupby types used in feature engeneering
+  groupby_types: [ 'delta_median', 'delta_mean', 'min', 'max', 'std', 'mode', 'is_mode' ]
+  # top features are choosen by cardinality or feature importance
+  groupby_top_based_on: 'cardinality'
+  # top categorical features to use in groupby transformer
+  groupby_top_categorical: 3
+  # top numerical features to use in groupby transformer
+  groupby_top_numerical: 3
+  # list of groupby triplets ("group_col", "feat", "groupby_type") for manual setting
+  # disables groupby_types, groupby_top_based_on and other groupby parameters if defined
+  groupby_triplets: [ ]
   # text_features in linear feature pipeline. embed or tfidf
   text_features: "tfidf"
 

lightautoml/automl/presets/text_presets.py

@@ -348,7 +348,7 @@ def get_gbms(
     ):
 
         text_gbm_feats = self.get_nlp_pipe(self.gbm_pipeline_params["text_features"])
-        gbm_feats = LGBAdvancedPipeline(output_categories=False, **self.gbm_pipeline_params)
+        gbm_feats = LGBAdvancedPipeline(feats_imp=pre_selector, output_categories=False, **self.gbm_pipeline_params)
         if text_gbm_feats is not None:
             gbm_feats.append(text_gbm_feats)