Multiclass (#99)

* utility functions

* stepsize lower bound

README.md

@@ -140,7 +140,6 @@ For more technical details, please check our papers.
 ```
 * [Frugal Optimization for Cost-related Hyperparameters](https://arxiv.org/abs/2005.01571). Qingyun Wu, Chi Wang, Silu Huang. AAAI 2021.
 * [Economical Hyperparameter Optimization With Blended Search Strategy](https://www.microsoft.com/en-us/research/publication/economical-hyperparameter-optimization-with-blended-search-strategy/). Chi Wang, Qingyun Wu, Silu Huang, Amin Saied. ICLR 2021.
-
 * ChaCha for online AutoML. Qingyun Wu, Chi Wang, John Langford, Paul Mineiro and Marco Rossi. To appear in ICML 2021.
 
 ## Contributing

flaml/__init__.py

@@ -3,7 +3,8 @@ from flaml.automl import AutoML, logger_formatter
 try:
     from flaml.onlineml.autovw import AutoVW
 except ImportError:
-    print('need to install vowpalwabbit to use AutoVW')
+    # print('need to install vowpalwabbit to use AutoVW')
+    pass
 from flaml.version import __version__
 import logging
 

flaml/automl.py

@@ -809,14 +809,17 @@ class AutoML:
                 dataframe and label are ignored;
                 If not, dataframe and label must be provided.
             metric: A string of the metric name or a function,
-                e.g., 'accuracy', 'roc_auc', 'f1', 'micro_f1', 'macro_f1', 'log_loss', 'mae', 'mse', 'r2'
+                e.g., 'accuracy', 'roc_auc', 'f1', 'micro_f1', 'macro_f1',
+                'log_loss', 'mae', 'mse', 'r2'
                 if passing a customized metric function, the function needs to
                 have the follwing signature:
 
                 .. code-block:: python
 
-                    def custom_metric(X_test, y_test, estimator, labels,
-                     X_train, y_train, weight_test=None, weight_train=None):
+                    def custom_metric(
+                        X_test, y_test, estimator, labels,
+                        X_train, y_train, weight_test=None, weight_train=None
+                    ):
                         return metric_to_minimize, metrics_to_log
 
                 which returns a float number as the minimization objective,
@@ -1238,7 +1241,7 @@ class AutoML:
         for i, estimator in enumerate(estimator_list):
             if estimator in self._search_states and (
                 self._search_states[estimator].sample_size
-            ):  # sample_size=none meaning no result
+            ):  # sample_size=None meaning no result
                 search_state = self._search_states[estimator]
                 if (self._search_states[estimator].time2eval_best
                     > self._state.time_budget - self._state.time_from_start

flaml/ml.py

@@ -294,3 +294,45 @@ def get_classification_objective(num_labels: int) -> str:
     else:
         objective_name = 'multi:softmax'
     return objective_name
+
+
+def norm_confusion_matrix(y_true, y_pred):
+    '''normalized confusion matrix
+
+    Args:
+        estimator: A multi-class classification estimator
+        y_true: A numpy array or a pandas series of true labels
+        y_pred: A numpy array or a pandas series of predicted labels
+
+    Returns:
+        A normalized confusion matrix
+    '''
+    from sklearn.metrics import confusion_matrix
+    conf_mat = confusion_matrix(y_true, y_pred)
+    norm_conf_mat = conf_mat.astype('float') / conf_mat.sum(axis=1)[:, np.newaxis]
+    return norm_conf_mat
+
+
+def multi_class_curves(y_true, y_pred_proba, curve_func):
+    '''Binarize the data for multi-class tasks and produce ROC or precision-recall curves
+
+    Args:
+        y_true: A numpy array or a pandas series of true labels
+        y_pred_proba: A numpy array or a pandas dataframe of predicted probabilites
+        curve_func: A function to produce a curve (e.g., roc_curve or precision_recall_curve)
+
+    Returns:
+        A tuple of two dictionaries with the same set of keys (class indices)
+        The first dictionary curve_x stores the x coordinates of each curve, e.g.,
+            curve_x[0] is an 1D array of the x coordinates of class 0
+        The second dictionary curve_y stores the y coordinates of each curve, e.g.,
+            curve_y[0] is an 1D array of the y coordinates of class 0
+    '''
+    from sklearn.preprocessing import label_binarize
+    classes = np.unique(y_true)
+    y_true_binary = label_binarize(y_true, classes=classes)
+
+    curve_x, curve_y = {}, {}
+    for i in range(len(classes)):
+        curve_x[i], curve_y[i], _ = curve_func(y_true_binary[:, i], y_pred_proba[:, i])
+    return curve_x, curve_y

flaml/model.py

@@ -461,6 +461,7 @@ class XGBoostSklearnEstimator(SKLearnEstimator, LGBMEstimator):
             'booster': params.get('booster', 'gbtree'),
             'colsample_bylevel': float(colsample_bylevel),
             'colsample_bytree': float(colsample_bytree),
+            'use_label_encoder': params.get('use_label_encoder', False),
         }
 
         if 'regression' in task:

flaml/onlineml/autovw.py

@@ -1,4 +1,3 @@
-import numpy as np
 from typing import Optional, Union
 import logging
 from flaml.tune import Trial, Categorical, Float, PolynomialExpansionSet, polynomial_expansion_set
@@ -6,6 +5,7 @@ from flaml.onlineml import OnlineTrialRunner
 from flaml.scheduler import ChaChaScheduler
 from flaml.searcher import ChampionFrontierSearcher
 from flaml.onlineml.trial import get_ns_feature_dim_from_vw_example
+
 logger = logging.getLogger(__name__)
 
 

flaml/onlineml/trial.py

@@ -4,10 +4,10 @@ import time
 import math
 import copy
 import collections
-from typing import Dict, Optional
+from typing import Optional
 from sklearn.metrics import mean_squared_error, mean_absolute_error
-from vowpalwabbit import pyvw
 from flaml.tune import Trial
+
 logger = logging.getLogger(__name__)
 
 
@@ -270,6 +270,7 @@ class VowpalWabbitTrial(BaseOnlineTrial):
         - Namespace vs features:
         https://stackoverflow.com/questions/28586225/in-vowpal-wabbit-what-is-the-difference-between-a-namespace-and-feature
     """
+    from vowpalwabbit import pyvw
     MODEL_CLASS = pyvw.vw
     cost_unit = 1.0
     interactions_config_key = 'interactions'

flaml/searcher/__init__.py

@@ -1,6 +1,3 @@
 from .blendsearch import CFO, BlendSearch, BlendSearchTuner
 from .flow2 import FLOW2
-try:
-    from .online_searcher import ChampionFrontierSearcher
-except ImportError:
-    print('need to install vowpalwabbit to use ChampionFrontierSearcher')
+from .online_searcher import ChampionFrontierSearcher

flaml/searcher/blendsearch.py

@@ -109,10 +109,10 @@ class BlendSearch(Searcher):
         init_config = low_cost_partial_config or {}
         if not init_config:
             logger.warning(
-                "No low-cost init config given to the search algorithm."
+                "No low-cost partial config given to the search algorithm. "
                 "For cost-frugal search, "
-                "consider providing init values for cost-related hps via "
-                "'init_config'."
+                "consider providing low-cost values for cost-related hps via "
+                "'low_cost_partial_config'."
             )
         self._points_to_evaluate = points_to_evaluate or []
         self._config_constraints = config_constraints

flaml/searcher/flow2.py

@@ -124,15 +124,16 @@ class FLOW2(Searcher):
             if callable(getattr(domain, 'get_sampler', None)):
                 self._tunable_keys.append(key)
                 sampler = domain.get_sampler()
-                # if isinstance(sampler, sample.Quantized):
-                #     sampler_inner = sampler.get_sampler()
-                #     if str(sampler_inner) == 'Uniform':
-                #         self._step_lb = min(
-                #             self._step_lb, sampler.q/(domain.upper-domain.lower))
-                # elif isinstance(domain, sample.Integer) and str(
-                #     sampler) == 'Uniform':
-                #     self._step_lb = min(
-                #         self._step_lb, 1.0/(domain.upper-domain.lower))
+                # the step size lower bound for uniform variables doesn't depend
+                # on the current config
+                if isinstance(sampler, sample.Quantized):
+                    sampler_inner = sampler.get_sampler()
+                    if str(sampler_inner) == 'Uniform':
+                        self._step_lb = min(
+                            self._step_lb, sampler.q / (domain.upper - domain.lower))
+                elif isinstance(domain, sample.Integer) and str(sampler) == 'Uniform':
+                    self._step_lb = min(
+                        self._step_lb, 1.0 / (domain.upper - domain.lower))
                 if isinstance(domain, sample.Categorical):
                     cat_hp_cost = self.cat_hp_cost
                     if cat_hp_cost and key in cat_hp_cost:
@@ -199,6 +200,8 @@ class FLOW2(Searcher):
                 continue
             domain = self.space[key]
             sampler = domain.get_sampler()
+            # the stepsize lower bound for log uniform variables depends on the
+            # current config
             if isinstance(sampler, sample.Quantized):
                 sampler_inner = sampler.get_sampler()
                 if str(sampler_inner) == 'LogUniform':

test/test_automl.py

@@ -260,6 +260,14 @@ class TestAutoML(unittest.TestCase):
             X_train=X_train, y_train=y_train, metric='micro_f1', **automl_settings)
         automl_experiment_macro.fit(
             X_train=X_train, y_train=y_train, metric='macro_f1', **automl_settings)
+        estimator = automl_experiment_macro.model
+        y_pred = estimator.predict(X_train)
+        y_pred_proba = estimator.predict_proba(X_train)
+        from flaml.ml import norm_confusion_matrix, multi_class_curves
+        print(norm_confusion_matrix(y_train, y_pred))
+        from sklearn.metrics import roc_curve, precision_recall_curve
+        print(multi_class_curves(y_train, y_pred_proba, roc_curve))
+        print(multi_class_curves(y_train, y_pred_proba, precision_recall_curve))
 
     def test_regression(self):
         automl_experiment = AutoML()