micro/macro f1 metrics added. (#80)

* micro/macro f1 metrics added.

* format lines.

flaml/automl.py

@@ -809,7 +809,7 @@ 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', '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:
 
@@ -902,7 +902,7 @@ class AutoML:
             else:
                 metric = 'r2'
         self._state.metric = metric
-        if metric in ['r2', 'accuracy', 'roc_auc', 'f1', 'ap']:
+        if metric in ['r2', 'accuracy', 'roc_auc', 'f1', 'ap', 'micro_f1', 'macro_f1']:
             error_metric = f"1-{metric}"
         elif isinstance(metric, str):
             error_metric = metric

flaml/ml.py

@@ -54,9 +54,9 @@ def sklearn_metric_loss_score(
     '''Loss using the specified metric
 
     Args:
-        metric_name: A string of the mtric name, one of
+        metric_name: A string of the metric name, one of
             'r2', 'rmse', 'mae', 'mse', 'accuracy', 'roc_auc', 'log_loss',
-            'f1', 'ap'
+            'f1', 'ap', 'micro_f1', 'macro_f1'
         y_predict: A 1d or 2d numpy array of the predictions which can be
             used to calculate the metric. E.g., 2d for log_loss and 1d
             for others.
@@ -88,6 +88,10 @@ def sklearn_metric_loss_score(
     elif 'log_loss' in metric_name:
         score = log_loss(
             y_true, y_predict, labels=labels, sample_weight=sample_weight)
+    elif 'micro_f1' in metric_name:
+        score = 1 - f1_score(y_true, y_predict, sample_weight=sample_weight, average='micro')
+    elif 'macro_f1' in metric_name:
+        score = 1 - f1_score(y_true, y_predict, sample_weight=sample_weight, average='macro')
     elif 'f1' in metric_name:
         score = 1 - f1_score(y_true, y_predict, sample_weight=sample_weight)
     elif 'ap' in metric_name:

test/test_automl.py

@@ -241,6 +241,23 @@ class TestAutoML(unittest.TestCase):
 
         y_pred = automl_experiment.predict(fake_df)
 
+    def test_micro_macro_f1(self):
+        automl_experiment = AutoML()
+        automl_experiment_macro = AutoML()
+
+        automl_settings = {
+            "time_budget":         2,
+            "task":                'classification',
+            "log_file_name":       "test/micro_macro_f1.log",
+            "log_training_metric": True,
+            "n_jobs":              1,
+            "model_history":       True
+        }
+
+        X_train, y_train = load_iris(return_X_y=True)
+        automl_experiment.fit(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)
+
     def test_regression(self):
 
         automl_experiment = AutoML()