Small fixes for runner/utils and code owners update (#118)

* Fix for dummy run work and error type addition in SW configuration

* pd.DataFrame.drop calls with keywords

* Codeowners update

* Python version and requirements update

Author: Alexsandruss

.github/CODEOWNERS

@@ -1,9 +1,9 @@
 #owners and reviewers
-cuml_bench/*          @Pahandrovich @Alexsandruss @masdevas
-daal4py_bench/*       @Pahandrovich @Alexsandruss @agorshk
-datasets/*            @Alexsandruss @itearsl @masdevas
-modelbuilders_bench/* @Pahandrovich @agorshk
-report_generator/*    @Pahandrovich @Alexsandruss
-sklearn_bench/*       @Pahandrovich @Alexsandruss @agorshk
-xgboost_bench/*       @Pahandrovich @agorshk
-*.md                  @outoftardis
+cuml_bench/*          @Alexsandruss
+daal4py_bench/*       @Alexsandruss @samir-nasibli
+datasets/*            @Alexsandruss
+modelbuilders_bench/* @Alexsandruss
+report_generator/*    @Alexsandruss
+sklearn_bench/*       @Alexsandruss @samir-nasibli
+xgboost_bench/*       @Alexsandruss
+*.md                  @Alexsandruss @maria-Petrova

azure-pipelines.yml

@@ -1,6 +1,6 @@
 variables:
   - name: python.version
-    value: "3.8"
+    value: "3.9"
 
 jobs:
   - job: Linux_Sklearn
@@ -45,7 +45,7 @@ jobs:
     steps:
       - script: |
           conda update -y -q conda
-          conda create -n bench -q -y -c conda-forge python=3.7 pandas xgboost scikit-learn daal4py tqdm requests
+          conda create -n bench -q -y -c conda-forge python=3.9 pandas xgboost scikit-learn daal4py tqdm requests
         displayName: Create Anaconda environment
       - script: |
           . /usr/share/miniconda/etc/profile.d/conda.sh

daal4py_bench/requirements.txt

@@ -1,5 +1,5 @@
-scikit-learn
-pandas < 1.3.0
+scikit-learn < 1.1 # TODO: remove after scikit-learn-intelex release with fix
+pandas
 daal4py
 openpyxl
 tqdm

datasets/loader_classification.py

@@ -159,7 +159,7 @@ def airline_ohe(dataset_dir: Path) -> bool:
     for local_url in [local_url_train, local_url_test]:
         df = pd.read_csv(local_url, nrows=1000000
                          if local_url.endswith('train-10m.csv') else None)
-        X = df.drop('dep_delayed_15min', 1)
+        X = df.drop(labels=['dep_delayed_15min'], axis=1)
         y: Any = df["dep_delayed_15min"]
 
         y_num = np.where(y == "Y", 1, 0)
@@ -208,7 +208,7 @@ def bosch(dataset_dir: Path) -> bool:
     logging.info(f'{dataset_name} is loaded, started parsing...')
     X = pd.read_csv(local_url, index_col=0, compression='zip', dtype=np.float32)
     y = X.iloc[:, -1].to_numpy(dtype=np.float32)
-    X.drop(X.columns[-1], axis=1, inplace=True)
+    X.drop(labels=[X.columns[-1]], axis=1, inplace=True)
     X_np = X.to_numpy(dtype=np.float32)
     X_train, X_test, y_train, y_test = train_test_split(X_np, y, random_state=77,
                                                         test_size=0.2,

runner.py

@@ -258,14 +258,13 @@ class GenerationArgs:
 
                     dataset_name = f'synthetic_{gen_args.type}'
 
-                    if not args.dummy_run:
-                        dataset_path = utils.find_or_gen_dataset(gen_args,
-                                                                 datasets_root, files.values())
-                        if dataset_path is None:
-                            logging.warning(
-                                f'Dataset {dataset_name} could not be generated. \n'
-                            )
-                            continue
+                    dataset_path = utils.find_or_gen_dataset(gen_args,
+                                                             datasets_root, files.values())
+                    if dataset_path is None:
+                        logging.warning(
+                            f'Dataset {dataset_name} could not be generated. \n'
+                        )
+                        continue
 
                     paths = ''
                     for data_path, data_file in files.items():

sklearn_bench/requirements.txt

@@ -1,4 +1,4 @@
-scikit-learn
+scikit-learn < 1.1 # TODO: remove after scikit-learn-intelex release with fix
 pandas
 scikit-learn-intelex
 openpyxl

utils.py

@@ -172,7 +172,7 @@ def get_sw_parameters() -> Dict[str, Dict[str, Any]]:
         if gpu_processes != '':
             print(f'There are running processes on GPU:\n{gpu_processes}',
                   file=sys.stderr)
-    except (FileNotFoundError, json.JSONDecodeError):
+    except (FileNotFoundError, json.JSONDecodeError, TypeError):
         pass
 
     # get python packages info from conda
@@ -186,7 +186,7 @@ def get_sw_parameters() -> Dict[str, Dict[str, Any]]:
                 if col in pkg:
                     pkg_info[col] = pkg[col]
             sw_params[pkg['name']] = pkg_info
-    except (FileNotFoundError, json.JSONDecodeError):
+    except (FileNotFoundError, json.JSONDecodeError, TypeError):
         pass
 
     return sw_params

xgboost_bench/requirements.txt

@@ -1,5 +1,5 @@
 scikit-learn
-pandas==1.3.5
+pandas
 xgboost
 openpyxl
 tqdm