lint

Author: md-shafiul-alam

sklbench/benchmarks/sklearn_estimator.py

@@ -145,7 +145,7 @@ def get_subset_metrics_of_estimator(
                 "balanced accuracy": float(balanced_accuracy_score(y_compat, y_pred)),
             }
         )
-        '''if hasattr(estimator_instance, "predict_proba") and not (
+        """if hasattr(estimator_instance, "predict_proba") and not (
             hasattr(estimator_instance, "probability")
             and getattr(estimator_instance, "probability") == False
         ):
@@ -165,7 +165,7 @@ def get_subset_metrics_of_estimator(
                     ),
                     "logloss": float(log_loss(y_compat, y_pred_proba)),
                 }
-            )'''
+            )"""
     elif task == "regression":
         y_pred = convert_to_numpy(estimator_instance.predict(x))
         metrics.update(
@@ -463,7 +463,7 @@ def measure_sklearn_estimator(
                     metrics[method]["time std[ms]"],
                     metrics[method]["first iter[ms]"],
                     metrics[method]["box filter mean[ms]"],
-                    metrics[method]["box filter std[ms]"]
+                    metrics[method]["box filter std[ms]"],
                 ) = measure_case(bench_case, method_instance, *data_args)
                 if ensure_sklearnex_patching:
                     full_method_name = f"{estimator_class.__name__}.{method}"
@@ -546,7 +546,7 @@ def main(bench_case: BenchCase, filters: List[BenchCase]):
     result_template = enrich_result(result_template, bench_case)
     if "assume_finite" in context_params:
         result_template["assume_finite"] = context_params["assume_finite"]
-    #if hasattr(estimator_instance, "get_params"):
+    # if hasattr(estimator_instance, "get_params"):
     #    estimator_params = estimator_instance.get_params()
     # note: "handle" is not JSON-serializable
     if "handle" in estimator_params:

sklbench/datasets/transformer.py

@@ -109,7 +109,10 @@ def split_and_transform_data(bench_case, data, data_description):
         y_train, y_test = None, None
 
     distributed_split = get_bench_case_value(bench_case, "data:distributed_split", None)
-    knn_split_train = "KNeighbors" in get_bench_case_value(bench_case, "algorithm:estimator", "") and int(get_bench_case_value(bench_case, "bench:mpi_params:n", 1)) > 1
+    knn_split_train = (
+        "KNeighbors" in get_bench_case_value(bench_case, "algorithm:estimator", "")
+        and int(get_bench_case_value(bench_case, "bench:mpi_params:n", 1)) > 1
+    )
     if distributed_split == "rank_based" or knn_split_train:
         from mpi4py import MPI
 

sklbench/runner/commands_helper.py

@@ -47,6 +47,7 @@ def generate_benchmark_command(
             mpi_prefix += f" -{mpi_param_name} {mpi_param_value}"
             if mpi_param_name == "-hostfile":
                 import os
+
                 mpi_prefix += os.environ.get("PBS_NODEFILE")
         command_prefix = f"{mpi_prefix} {command_prefix}"
     # 3. Intel(R) VTune* profiling command prefix

sklbench/utils/measurement.py

@@ -48,9 +48,9 @@ def large_scale_measurements(timing):
     Q1, Q3 = np.percentile(timing_sorted, [25, 75])
     IQ = Q3 - Q1
     lower, upper = Q1 - 1.5 * IQ, Q3 + 1.5 * IQ
-    
+
     filtered_times = timing_sorted[(timing_sorted >= lower) & (timing_sorted <= upper)]
-    
+
     box_filter_mean = np.mean(filtered_times) * 1000 if filtered_times.size > 0 else 0
     box_filter_stdev = np.std(filtered_times) * 1000 if filtered_times.size > 0 else 0
     return mean, stdev, first_iter, box_filter_mean, box_filter_stdev
@@ -89,8 +89,8 @@ def measure_time(
             )
             break
     logger.debug(times)
-    #mean, std = box_filter(times)
-    #if std / mean > std_mean_ratio:
+    # mean, std = box_filter(times)
+    # if std / mean > std_mean_ratio:
     #    logger.warning(
     #        f'Measured "std / mean" time ratio of "{str(func)}" function is higher '
     #        f"than threshold ({round(std / mean, 3)} vs. {std_mean_ratio})"