Docstrings

experiments/02_openml.py

@@ -31,7 +31,7 @@ def main():
     train_loader = ComposedDataLoaderFactory.create_composed_dataloader_from_path(
         Path(config["train_data_path"]),
         RandomFeaturesPandasDataset,
-        {},
+        {"total_random_feature_sampling": True},
         FewShotDataLoader,
         {"support_size": config["support_size"], "query_size": config["query_size"]},
         ComposedDataLoader,

liltab/data/dataloaders.py

@@ -68,23 +68,30 @@ def __init__(
                 self.class_values_idx[val] = np.where(self.y == val)[0]
 
         if sample_classes_equally:
-            self.samples_per_class_support = {
-                class_value: self.support_size // len(self.class_values)
-                for class_value in self.class_values
-            }
-            self.samples_per_class_query = {
-                class_value: self.query_size // len(self.class_values)
-                for class_value in self.class_values
-            }
-        if self.sample_classes_stratified:
-            self.samples_per_class_support = {
-                class_value: int(self.support_size * (self.y == class_value).sum() / len(self.y))
-                for class_value in self.class_values
-            }
-            self.samples_per_class_query = {
-                class_value: int(self.query_size * (self.y == class_value).sum() / len(self.y))
-                for class_value in self.class_values
-            }
+            self._init_samples_per_class_equal()
+
+        if sample_classes_stratified:
+            self._init_samples_per_class_stratified()
+
+    def _init_samples_per_class_equal(self):
+        self.samples_per_class_support = {
+            class_value: self.support_size // len(self.class_values)
+            for class_value in self.class_values
+        }
+        self.samples_per_class_query = {
+            class_value: self.query_size // len(self.class_values)
+            for class_value in self.class_values
+        }
+
+    def _init_samples_per_class_stratified(self):
+        self.samples_per_class_support = {
+            class_value: int(self.support_size * (self.y == class_value).sum() / len(self.y))
+            for class_value in self.class_values
+        }
+        self.samples_per_class_query = {
+            class_value: int(self.query_size * (self.y == class_value).sum() / len(self.y))
+            for class_value in self.class_values
+        }
 
     def __iter__(self):
         return deepcopy(self)

liltab/data/datasets.py

@@ -11,6 +11,12 @@
 
 
 class Dataset(ABC):
+    """
+    Abstract class for Datasets. It reads and stores data as Pandas
+    DataFrame. __getitem__ method is to be implemented with custom
+    indexing strategy.
+    """
+
     def __init__(
         self,
         data_path: str,
@@ -45,6 +51,10 @@ def __init__(
             self.y = self.df[self.response_columns].values
 
     def _preprocess_data(self):
+        """
+        Standardizes data using z-score method. If encode_categorical_target = True
+        then response variable isn't scaled.
+        """
         self.preprocessing_pipeline = get_preprocessing_pipeline()
         if self.encode_categorical_target:
             self.df.loc[:, self.attribute_columns] = self.preprocessing_pipeline.fit_transform(
@@ -56,6 +66,9 @@ def _preprocess_data(self):
             )
 
     def _encode_categorical_target(self):
+        """
+        Encodes categorical response using one-hot encoding.
+        """
         self.one_hot_encoder = OneHotEncoder(sparse=False)
         self.raw_y = self.df[self.response_columns]
         self.y = self.one_hot_encoder.fit_transform((self.df[self.response_columns]))