Merge pull request #28 from microsoft/v0.2.4

v0.2.4

flaml/automl.py

@@ -402,7 +402,7 @@ class AutoML:
             self._X_train_all, self._y_train_all = \
                 self._transformer.fit_transform(X, y, self._state.task)
             self._label_transformer = self._transformer.label_transformer
-
+        self._sample_weight_full = self._state.fit_kwargs.get('sample_weight')      
         if X_val is not None and y_val is not None:
             if not (isinstance(X_val, np.ndarray) or
                 issparse(X_val) or
@@ -446,7 +446,8 @@ class AutoML:
             self._X_train_all, self._y_train_all
         if issparse(X_train_all): 
             X_train_all = X_train_all.tocsr()
-        if self._state.task != 'regression':
+        if self._state.task != 'regression' and self._state.fit_kwargs.get(
+            'sample_weight') is None:
             # logger.info(f"label {pd.unique(y_train_all)}")
             label_set, counts = np.unique(y_train_all, return_counts=True)
             # augment rare classes
@@ -1093,8 +1094,9 @@ class AutoML:
                             self._state.best_loss))
             else:
                 logger.info(f"no enough budget for learner {estimator}")
-                self.estimator_list.remove(estimator)
-                self._estimator_index -= 1
+                if self._estimator_index is not None:
+                    self.estimator_list.remove(estimator)
+                    self._estimator_index -= 1
             if self._retrain_full and best_config_sig and not better and (
                 self._search_states[self._best_estimator].sample_size ==
                 self._state.data_size) and (est_retrain_time <=
@@ -1151,7 +1153,11 @@ class AutoML:
                 stacker = Stacker(estimators, best_m,
                     n_jobs=self._state.n_jobs,
                     passthrough=True)
-                stacker.fit(self._X_train_all, self._y_train_all)
+                if self._sample_weight_full is not None:
+                    self._state.fit_kwargs[
+                        'sample_weight'] = self._sample_weight_full
+                stacker.fit(self._X_train_all, self._y_train_all,
+                 **self._state.fit_kwargs)
                 logger.info(f'ensemble: {stacker}')
                 self._trained_estimator = stacker
                 self._trained_estimator.model = stacker

flaml/searcher/flow2.py

@@ -121,8 +121,8 @@ class FLOW2(Searcher):
         self._unordered_cat_hp = {}
         self._cat_hp_cost = {}
         for key, domain in self.space.items():
-            assert not isinstance(domain, dict), \
-                key+"'s domain is grid search which is not supported in FLOW2."
+            assert not (isinstance(domain, dict) and 'grid_search' in domain
+            ), key+"'s domain is grid search which is not supported in FLOW2."
             if callable(getattr(domain, 'get_sampler', None)):
                 self._tunable_keys.append(key)
                 sampler = domain.get_sampler()

flaml/tune/README.md

@@ -6,6 +6,7 @@ The API is compatible with ray tune.
 Example:
 
 ```python
+# require: pip install flaml[blendsearch]
 from flaml import tune
 import time
 
@@ -42,6 +43,7 @@ print(analysis.best_config) # the best config
 
 Or, using ray tune's API:
 ```python
+# require: pip install flaml[blendsearch] ray[tune]
 from ray import tune as raytune
 from flaml import CFO, BlendSearch
 import time
@@ -146,6 +148,7 @@ based on optimism in face of uncertainty.
 Example:
 
 ```python
+# require: pip install flaml[blendsearch]
 from flaml import BlendSearch
 tune.run(...
     search_alg = BlendSearch(points_to_evaluate=[init_config]),

flaml/version.py

@@ -1 +1 @@
-__version__ = "0.2.3"
+__version__ = "0.2.4"

notebook/finetune_transformer_demo.ipynb

@@ -6,11 +6,16 @@
    "source": [
     "This notebook uses the Huggingface transformers library to finetune a transformer model.\n",
     "\n",
-    "**Requirements.** This notebook has additional requirements:\n",
-    "\n",
-    "```bash\n",
-    "pip install -r transformers_requirements.txt\n",
-    "```"
+    "**Requirements.** This notebook has additional requirements:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install torch transformers datasets ipywidgets"
    ]
   },
   {
@@ -699,7 +704,7 @@
    "source": [
     "### Step 3. Launch with `flaml.tune.run`\n",
     "\n",
-    "We are now ready to laungh the tuning using `flaml.tune.run`:"
+    "We are now ready to launch the tuning using `flaml.tune.run`:"
    ],
    "cell_type": "markdown",
    "metadata": {}
@@ -766,9 +771,13 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "flaml",
-   "language": "python",
-   "name": "flaml"
+   "name": "python3",
+   "display_name": "Python 3.7.7 64-bit ('flaml': conda)",
+   "metadata": {
+    "interpreter": {
+     "hash": "bfcd9a6a9254a5e160761a1fd7a9e444f011592c6770d9f4180dde058a9df5dd"
+    }
+   }
   },
   "language_info": {
    "codemirror_mode": {
@@ -780,7 +789,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.6"
+   "version": "3.7.7-final"
   }
  },
  "nbformat": 4,

notebook/transformers_requirements.txt

@@ -1,4 +0,0 @@
-torch
-transformers
-datasets
-ipywidgets

setup.py

@@ -20,7 +20,6 @@ install_requires = [
     "scipy>=1.4.1",
     "catboost>=0.23",
     "scikit-learn>=0.23.2",
-    "optuna==2.3.0"
 ],
 
 
@@ -48,6 +47,10 @@ setuptools.setup(
             "coverage>=5.3",
             "xgboost<1.3",
             "rgf-python",
+            "optuna==2.3.0",
+        ],
+        "blendsearch": [
+            "optuna==2.3.0"
         ],
         "ray": [
             "ray[tune]==1.1.0",

test/test_pytorch_cifar10.py

@@ -1,3 +1,5 @@
+'''Require: pip install torchvision ray
+'''
 import unittest
 import os
 import time

test/test_tune.py

@@ -1,5 +1,6 @@
+'''Require: pip install flaml[test,ray]
+'''
 import unittest
-import os
 import time
 from sklearn.model_selection import train_test_split
 import sklearn.metrics
@@ -138,6 +139,7 @@ def _test_xgboost(method='BlendSearch'):
                     scheduler=scheduler, search_alg=algo)
             ray.shutdown()
             # # Load the best model checkpoint
+            # import os
             # best_bst = xgb.Booster()
             # best_bst.load_model(os.path.join(analysis.best_checkpoint,
             #  "model.xgb"))