Code quality improvement

sklbench/benchmarks/custom_function.py

@@ -104,11 +104,14 @@ def main(bench_case: BenchCase, filters: List[BenchCase]):
         "function": function_name,
     }
     result = enrich_result(result, bench_case)
-    # TODO: replace `x_train` data_desc with more informative values
-    result.update(data_description["x_train"])
+    # Replace `x_train` data_desc with more informative values
+    result.update({
+        "memory_usage": x_train.nbytes,
+        "feature_names": list(x_train.columns) if isinstance(x_train, pd.DataFrame) else None,
+        "class_distribution": dict(pd.Series(y_train).value_counts()) if y_train is not None else None
+    })
     result.update(metrics)
     return [result]
 
-
 if __name__ == "__main__":
     main_template(main)

sklbench/datasets/loaders.py

@@ -802,7 +802,8 @@ def load_ann_dataset_template(url, raw_data_cache):
     }
     del x_train, x_test
     # TODO: remove placeholding zeroed y
-    y = np.zeros((x.shape[0],))
+    #y = np.zeros((x.shape[0],))
+    y = np.zeros(x.shape[0])
     return {"x": x, "y": y}, data_desc
 
 

sklbench/report/implementation.py

@@ -89,12 +89,15 @@
     "dataset",
     "samples",
     "features",
+    "feature_names",
     "format",
     "dtype",
     "order",
     "n_classes",
+    "class_distribution",
     "n_clusters",
     "batch_size",
+    "memory_usage",
 ]
 
 DIFFBY_COLUMNS = ["environment_name", "library", "format", "device"]

sklbench/runner/commands_helper.py

@@ -18,6 +18,7 @@
 import os
 import sys
 from time import time
+from datetime import datetime
 from typing import Dict, List, Tuple
 
 from ..utils.bench_case import get_bench_case_name, get_bench_case_value
@@ -61,7 +62,7 @@ def generate_benchmark_command(
                         get_bench_case_name(bench_case, shortened=True, separator="_"),
                         hash_from_json_repr(bench_case),
                         # TODO: replace unix time in ms with datetime
-                        str(int(time() * 1000)),
+                        datetime.now().strftime("%Y-%m-%d %H:%M"),
                     ]
                 ),
             )

sklbench/utils/special_params.py

@@ -36,6 +36,10 @@
 def is_special_value(value) -> bool:
     return isinstance(value, str) and value.startswith(SP_VALUE_STR)
 
+def float_range(start,stop,step):
+    while start < stop:
+        yield start
+        start += step
 
 def explain_range(range_str: str) -> List:
     def check_range_values_size(range_values: List[int], size: int):
@@ -47,13 +51,15 @@ def check_range_values_size(range_values: List[int], size: int):
     range_values = range_str.replace("[RANGE]", "").split(":")
     # TODO: add float values
     range_type = range_values[0]
-    range_values = list(map(int, range_values[1:]))
+    #range_values = list(map(int, range_values[1:]))
+    range_values = list(map(float, range_values[1:]))
     # - add:start{int}:end{int}:step{int} - Arithmetic progression
     #   Sequence: start + step * i <= end
     if range_type == "add":
         check_range_values_size(range_values, 3)
         start, end, step = range_values
-        return list(range(start, end + step, step))
+        #return list(range(start, end + step, step))
+        return list(float_range(start, end + step, step))
     # - mul:current{int}:end{int}:step{int} - Geometric progression
     #   Sequence: current * step <= end
     elif range_type == "mul":
@@ -71,7 +77,8 @@ def check_range_values_size(range_values: List[int], size: int):
             range_values.append(1)
         check_range_values_size(range_values, 4)
         base, start, end, step = range_values
-        return [base**i for i in range(start, end + step, step)]
+        #return [base**i for i in range(start, end + step, step)]
+        return [base**i for i in float_range(start, end + step, step)]
     else:
         raise ValueError(f'Unknown "{range_type}" range type')