Issue58 (#59)

* iter per learner

* code cleanup

flaml/__init__.py

@@ -6,4 +6,3 @@
 # Set the root logger.
 logger = logging.getLogger(__name__)
 logger.setLevel(logging.INFO)
-

flaml/config.py

@@ -1,12 +1,12 @@
 '''!
  * Copyright (c) 2020-2021 Microsoft Corporation. All rights reserved.
- * Licensed under the MIT License. 
+ * Licensed under the MIT License.
 '''
 
 N_SPLITS = 5
 RANDOM_SEED = 1
 SPLIT_RATIO = 0.1
-MEM_THRES = 4*(1024**3)
+MEM_THRES = 4 * (1024 ** 3)
 SMALL_LARGE_THRES = 10000000
 MIN_SAMPLE_TRAIN = 10000
 CV_HOLDOUT_THRESHOLD = 100000

flaml/data.py

@@ -1,6 +1,6 @@
 '''!
  * Copyright (c) 2020-2021 Microsoft Corporation. All rights reserved.
- * Licensed under the MIT License. 
+ * Licensed under the MIT License.
 '''
 
 import numpy as np
@@ -10,7 +10,7 @@
 
 
 def load_openml_dataset(dataset_id, data_dir=None, random_state=0):
-    '''Load dataset from open ML. 
+    '''Load dataset from open ML.
 
     If the file is not cached locally, download it from open ML.
 
@@ -23,7 +23,7 @@ def load_openml_dataset(dataset_id, data_dir=None, random_state=0):
         X_train: A 2d numpy array of training data
         X_test:  A 2d numpy array of test data
         y_train: A 1d numpy arrya of labels for training data
-        y_test:  A 1d numpy arrya of labels for test data        
+        y_test:  A 1d numpy arrya of labels for test data
     '''
     import os
     import openml
@@ -58,9 +58,9 @@ def load_openml_dataset(dataset_id, data_dir=None, random_state=0):
 
 
 def load_openml_task(task_id, data_dir):
-    '''Load task from open ML. 
+    '''Load task from open ML.
 
-    Use the first fold of the task. 
+    Use the first fold of the task.
     If the file is not cached locally, download it from open ML.
 
     Args:
@@ -71,7 +71,7 @@ def load_openml_task(task_id, data_dir):
         X_train: A 2d numpy array of training data
         X_test:  A 2d numpy array of test data
         y_train: A 1d numpy arrya of labels for training data
-        y_test:  A 1d numpy arrya of labels for test data        
+        y_test:  A 1d numpy arrya of labels for test data
     '''
     import os
     import openml
@@ -115,12 +115,12 @@ def get_output_from_log(filename, time_budget):
 
     Returns:
         training_time_list: A list of the finished time of each logged iter
-        best_error_list: 
+        best_error_list:
             A list of the best validation error after each logged iter
         error_list: A list of the validation error of each logged iter
-        config_list: 
+        config_list:
             A list of the estimator, sample size and config of each logged iter
-        logged_metric_list: A list of the logged metric of each logged iter 
+        logged_metric_list: A list of the logged metric of each logged iter
     '''
 
     best_config = None
@@ -186,7 +186,6 @@ class DataTransformer:
     '''transform X, y
     '''
 
-
     def fit_transform(self, X, y, task):
         if isinstance(X, pd.DataFrame):
             X = X.copy()
@@ -223,17 +222,18 @@ def fit_transform(self, X, y, task):
                 X_num = X[num_columns]
                 if drop and np.issubdtype(X_num.columns.dtype, np.integer):
                     X_num.columns = range(X_num.shape[1])
-                else: drop = False
+                else:
+                    drop = False
                 from sklearn.impute import SimpleImputer
                 from sklearn.compose import ColumnTransformer
                 self.transformer = ColumnTransformer([(
                     'continuous',
                     SimpleImputer(missing_values=np.nan, strategy='median'),
-                        X_num.columns)])
+                    X_num.columns)])
                 X[num_columns] = self.transformer.fit_transform(X_num)
             self._cat_columns, self._num_columns = cat_columns, num_columns
             self._drop = drop
-            
+
         if task == 'regression':
             self.label_transformer = None
         else: