Mainly updated get_default_configuration_space.py to use Datasets (or Iterator[TTSplit]) as data.

Also updated some imports in bayesian_optimization.py, implicit_evaler.py and lkauto.py

Author: Max

lkauto/implicit/implicit_evaler.py

@@ -1,7 +1,8 @@
 import numpy as np
 import pandas as pd
 from ConfigSpace import ConfigurationSpace
-from lenskit import topn, batch
+from lenskit.basic import topn
+from lenskit import batch
 import logging
 
 from lkauto.utils.filer import Filer

lkauto/lkauto.py

@@ -26,7 +26,7 @@
 def get_best_prediction_model(train: pd.DataFrame,
                               validation: pd.DataFrame = None,
                               cs: ConfigurationSpace = None,
-                              optimization_metric=rmse,
+                              optimization_metric=RMSE,
                               optimization_strategie: str = 'bayesian',
                               time_limit_in_sec: int = 2700,
                               num_evaluations: int = 500,
@@ -228,7 +228,7 @@ def get_best_prediction_model(train: pd.DataFrame,
 def get_best_recommender_model(train: pd.DataFrame,
                                validation: pd.DataFrame = None,
                                cs: ConfigurationSpace = None,
-                               optimization_metric=ndcg,
+                               optimization_metric=NDCG,
                                optimization_strategie: str = 'bayesian',
                                time_limit_in_sec: int = 2700,
                                num_evaluations: int = 500,

lkauto/optimization_strategies/bayesian_optimization.py

@@ -1,7 +1,7 @@
 import pandas as pd
 from ConfigSpace import Configuration, ConfigurationSpace
-from smac.facade.smac_hpo_facade import SMAC4HPO
-from smac.scenario.scenario import Scenario
+from smac.facade import HyperparameterOptimizationFacade as SMAC4HPO
+from smac.scenario import Scenario
 
 from lkauto.explicit.explicit_evaler import ExplicitEvaler
 from lkauto.implicit.implicit_evaler import ImplicitEvaler

lkauto/utils/get_default_configuration_space.py

@@ -1,6 +1,10 @@
 import pandas as pd
+
+from typing import Iterator, Union
 from ConfigSpace import Categorical
 from ConfigSpace import ConfigurationSpace
+from lenskit.data import Dataset
+from lenskit.splitting import TTSplit
 
 from lkauto.algorithms.als import BiasedMF
 from lkauto.algorithms.als import ImplicitMF
@@ -11,13 +15,13 @@
 from lkauto.algorithms.user_knn import UserUser
 
 
-def get_default_configuration_space(data: pd.DataFrame,
+def get_default_configuration_space(data: Union[Dataset, Iterator[TTSplit]],
                                     val_fold_indices,
                                     feedback: str,
-                                    validation: pd.DataFrame = None,
+                                    validation: Iterator[TTSplit] = None,
                                     random_state=42) -> ConfigurationSpace:
     """
-        returns the default configuration space for all included rating predictions algorithms
+        returns the default configuration space for all included rating prediction algorithms
 
         Parameters
         ----------
@@ -42,6 +46,7 @@ def get_default_configuration_space(data: pd.DataFrame,
 
     # get minimum number of items and users for the given train split
 
+    """
     num_items = 0
     num_users = 0
     if validation is None:
@@ -57,6 +62,22 @@ def get_default_configuration_space(data: pd.DataFrame,
             num_items = data['item'].nunique()
         if data['user'].nunique() < num_users or num_users == 0:
             num_users = data['user'].nunique()
+            """
+
+    num_items = 0
+    num_users = 0
+
+    if validation is None and not isinstance(data, Dataset):
+        for fold in data:
+            if fold.train.item_count < num_items or num_items == 0:
+                num_items = fold.train.item_count
+            if fold.train.user_count < num_users or num_users == 0:
+                num_users = fold.train.user_count
+    else:
+        if data.item_count < num_items or num_items == 0:
+            num_items = data.item_count
+        if data.user_count < num_users or num_users == 0:
+            num_users = data.user_count
 
     # define configuration space
     cs = ConfigurationSpace(

tests/utils/test_get_default_configuration_space.py

@@ -5,6 +5,7 @@
 import pandas as pd
 
 from ConfigSpace import ConfigurationSpace
+from lenskit.data import from_interactions_df, DatasetBuilder
 
 from lkauto.utils.get_default_configuration_space import get_default_configuration_space
 from lkauto.utils.validation_split import validation_split
@@ -16,12 +17,28 @@ class TestGetDefaultConfigurationSpace(unittest.TestCase):
 
     def setUp(self):
         self.random_state = 42
-        self.df = pd.DataFrame(np.ones((100, 3)), columns=["user", "item", "rating", ])
-        self.val_fold_indices = validation_split(data=self.df, random_state=42)
+        self.df = pd.DataFrame(np.array([[1,1,1],
+                            [1,2,2],
+                            [1,3,3],
+                            [2,1,1],
+                            [2,2,2],
+                            [2,3,3],
+                            [3,1,1],
+                            [3,2,2],
+                            [3,3,3],
+                            [4,1,1],
+                            [4,2,2],
+                            [4,3,3],
+                            [5,1,1],
+                            [5,2,2],
+                            [5,3,3]]), columns=["user", "item", "rating", ])
+        # self.df = pd.DataFrame(np.ones((100, 3), dtype=int), columns=["user", "item", "rating", ])
+        self.ds = from_interactions_df(self.df, user_col="user", item_col="item", rating_col="rating")
+        self.val_fold_indices = validation_split(data=self.ds, random_state=42)
 
     def test_getDefaultConfigurationSpace_givenInvalidFeedback_valueErrorThrown(self):
         with self.assertRaises(ValueError) as cm:
-            get_default_configuration_space(feedback="", data=self.df,
+            get_default_configuration_space(feedback="", data=self.ds,
                                             val_fold_indices=self.val_fold_indices,
                                             random_state=self.random_state)
         self.assertEqual("Unknown feedback type: ", cm.exception.args[0])
@@ -34,7 +51,7 @@ def test_getDefaultConfigurationSpace_givenInvalidFeedback_valueErrorThrown(self
     def test_getDefaultConfigurationSpace_GivenImplicitAndValidInputs_CorrectConfigSpaceReturnedExpected(self):
         algorithm_list_string = 'ItemItem, FunkSVD, UserUser, ImplicitMF, BiasedSVD'
 
-        result = get_default_configuration_space(feedback='implicit', data=self.df,
+        result = get_default_configuration_space(feedback='implicit', data=self.ds,
                                                  val_fold_indices=self.val_fold_indices,
                                                  random_state=self.random_state)
 
@@ -50,7 +67,7 @@ def test_getDefaultConfigurationSpace_GivenImplicitAndValidInputs_CorrectConfigS
     def test_getDefaultConfigurationSpace_GivenExplicitAndValidInputs_CorrectConfigSpaceReturnedExpected(self):
         algorithm_list_string = 'ItemItem, UserUser, FunkSVD, BiasedSVD, ALSBiasedMF, Bias'
 
-        result = get_default_configuration_space(feedback='explicit', data=self.df,
+        result = get_default_configuration_space(feedback='explicit', data=self.ds,
                                                  val_fold_indices=self.val_fold_indices,
                                                  random_state=self.random_state)