chore: remove debugging print statements

This commit removes the debugging print statements from the `extractor.py` file

Signed-off-by: vprashar2929 <[email protected]>

Author: vprashar2929

.github/workflows/lint.yml

@@ -9,7 +9,7 @@ jobs:
     steps:
       # checkout soruce code
       - name: Checkout code
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
 
       # setup Python environment
       - name: Set up Python

src/kepler_model/train/extractor/extractor.py

@@ -174,8 +174,6 @@ def get_workload_feature_data(self, query_results, features, use_vm_metrics=Fals
                     aggr_query_data = aggr_query_data.loc[aggr_query_data["job"] == VM_JOB_NAME]
                 else:
                     aggr_query_data = aggr_query_data.loc[aggr_query_data["job"] != VM_JOB_NAME]
-                print("aggr query data feature")
-                print(aggr_query_data.to_string())
                 aggr_query_data.rename(columns={query: feature}, inplace=True)
                 aggr_query_data[container_id_colname] = aggr_query_data[cols_to_use].apply(lambda x: "/".join([str(xi) for xi in x]), axis=1)
                 # separate for each container_id
@@ -228,7 +226,6 @@ def get_workload_feature_data(self, query_results, features, use_vm_metrics=Fals
         if len(feature_to_remove) != 0:
             features = self.process_feature(features, feature_to_remove, cur_accelerator_features)
         # return with reset index for later aggregation
-        # print(feature_data.reset_index().to_string())
         return feature_data.reset_index(), features
 
     def get_system_feature_data(self, query_results, features):
@@ -262,8 +259,6 @@ def get_power_data(self, query_results, energy_components, source, use_vm_metric
                 aggr_query_data = aggr_query_data.loc[aggr_query_data["job"] != VM_JOB_NAME]
             # filter source
             aggr_query_data = aggr_query_data[aggr_query_data[SOURCE_COL] == source]
-            # print("aggr query data power")
-            # print(aggr_query_data.to_string())
             if len(aggr_query_data) == 0:
                 return None
             if unit_col is not None:
@@ -311,7 +306,6 @@ def get_power_data(self, query_results, energy_components, source, use_vm_metric
         if len(power_data_list) == 0:
             return None
         power_data = pd.concat(power_data_list, axis=1).dropna()
-        # print(power_data.to_string())
         return power_data
 
     def get_system_category(self, query_results):

tests/estimator_model_request_test.py

@@ -126,9 +126,9 @@ def test_model_request():
     power_request = json.loads(data, object_hook=lambda d: PowerRequest(**d))
     output_path = get_achived_model(power_request)
     assert output_path is None, f"model should be invalid\n {output_path}"
-    os.environ[
-        "MODEL_CONFIG"
-    ] = f"{estimator_enable_key}=true\n{init_url_key}={get_url(energy_source=energy_source, output_type=output_type, feature_group=FeatureGroup.BPFOnly, model_topurl=model_topurl, pipeline_name=default_train_output_pipeline)}\n"
+    os.environ["MODEL_CONFIG"] = (
+        f"{estimator_enable_key}=true\n{init_url_key}={get_url(energy_source=energy_source, output_type=output_type, feature_group=FeatureGroup.BPFOnly, model_topurl=model_topurl, pipeline_name=default_train_output_pipeline)}\n"
+    )
     set_env_from_model_config()
     print("Requesting from ", os.environ[init_url_key])
     reset_failed_list()