annofabcli 1.102.0__py3-none-any.whl → 1.103.0__py3-none-any.whl

annofabcli/statistics/list_annotation_count.py

@@ -219,13 +219,9 @@ class ListAnnotationCounterByInputData:
 
         annotation_count_by_label = collections.Counter([e["label"] for e in details])
         if self.target_labels is not None:
-            annotation_count_by_label = collections.Counter(
-                {label: count for label, count in annotation_count_by_label.items() if label in self.target_labels}
-            )
+            annotation_count_by_label = collections.Counter({label: count for label, count in annotation_count_by_label.items() if label in self.target_labels})
         if self.non_target_labels is not None:
-            annotation_count_by_label = collections.Counter(
-                {label: count for label, count in annotation_count_by_label.items() if label not in self.non_target_labels}
-            )
+            annotation_count_by_label = collections.Counter({label: count for label, count in annotation_count_by_label.items() if label not in self.non_target_labels})
 
         attributes_list: list[AttributeValueKey] = []
         for detail in details:
@@ -413,10 +409,9 @@ class AttributeCountCsv:
     Args:
         selective_attribute_value_max_count: 選択肢系の属性の値の個数の上限。これを超えた場合は、非選択肢系属性（トラッキングIDやアノテーションリンクなど）とみなす
 
-    """  # noqa: E501
+    """
 
-    def __init__(self, selective_attribute_value_max_count: int = 20, csv_format: Optional[dict[str, Any]] = None) -> None:
-        self.csv_format = csv_format
+    def __init__(self, selective_attribute_value_max_count: int = 20) -> None:
         self.selective_attribute_value_max_count = selective_attribute_value_max_count
 
     def _only_selective_attribute(self, columns: list[AttributeValueKey]) -> list[AttributeValueKey]:
@@ -429,23 +424,13 @@ class AttributeCountCsv:
         for label, attribute_name, _ in columns:
             attribute_name_list.append((label, attribute_name))
 
-        non_selective_attribute_names = {
-            key for key, value in collections.Counter(attribute_name_list).items() if value > self.selective_attribute_value_max_count
-        }
+        non_selective_attribute_names = {key for key, value in collections.Counter(attribute_name_list).items() if value > self.selective_attribute_value_max_count}
         if len(non_selective_attribute_names) > 0:
-            logger.debug(
-                f"以下の属性は値の個数が{self.selective_attribute_value_max_count}を超えていたため、集計しません。 :: {non_selective_attribute_names}"
-            )
+            logger.debug(f"以下の属性は値の個数が{self.selective_attribute_value_max_count}を超えていたため、集計しません。 :: {non_selective_attribute_names}")
 
-        return [
-            (label, attribute_name, attribute_value)
-            for (label, attribute_name, attribute_value) in columns
-            if (label, attribute_name) not in non_selective_attribute_names
-        ]
+        return [(label, attribute_name, attribute_value) for (label, attribute_name, attribute_value) in columns if (label, attribute_name) not in non_selective_attribute_names]
 
-    def _value_columns(
-        self, counter_list: Collection[AnnotationCounter], prior_attribute_columns: Optional[list[AttributeValueKey]]
-    ) -> list[AttributeValueKey]:
+    def _value_columns(self, counter_list: Collection[AnnotationCounter], prior_attribute_columns: Optional[list[AttributeValueKey]]) -> list[AttributeValueKey]:
         all_attr_key_set = {attr_key for c in counter_list for attr_key in c.annotation_count_by_attribute}
         if prior_attribute_columns is not None:
             remaining_columns = sorted(all_attr_key_set - set(prior_attribute_columns))
@@ -511,7 +496,7 @@ class AttributeCountCsv:
         # `task_id`列など`basic_columns`も`fillna`対象だが、nanではないはずので問題ない
         df.fillna(0, inplace=True)
 
-        print_csv(df, output=str(output_file), to_csv_kwargs=self.csv_format)
+        print_csv(df, output=str(output_file))
 
     def print_csv_by_input_data(
         self,
@@ -555,7 +540,7 @@ class AttributeCountCsv:
         value_columns = self._value_columns(counter_list, prior_attribute_columns)
         df = df.fillna(dict.fromkeys(value_columns, 0))
 
-        print_csv(df, output=str(output_file), to_csv_kwargs=self.csv_format)
+        print_csv(df, output=str(output_file))
 
 
 class LabelCountCsv:
@@ -565,9 +550,6 @@ class LabelCountCsv:
 
     """
 
-    def __init__(self, csv_format: Optional[dict[str, Any]] = None) -> None:
-        self.csv_format = csv_format
-
     def _value_columns(self, counter_list: Collection[AnnotationCounter], prior_label_columns: Optional[list[str]]) -> list[str]:
         all_attr_key_set = {attr_key for c in counter_list for attr_key in c.annotation_count_by_label}
         if prior_label_columns is not None:
@@ -615,7 +597,7 @@ class LabelCountCsv:
         # NaNを0に変換する
         # `basic_columns`は必ずnanではないので、すべての列に対してfillnaを実行しても問題ないはず
         df.fillna(0, inplace=True)
-        print_csv(df, output=str(output_file), to_csv_kwargs=self.csv_format)
+        print_csv(df, output=str(output_file))
 
     def print_csv_by_input_data(
         self,
@@ -658,7 +640,7 @@ class LabelCountCsv:
         value_columns = self._value_columns(counter_list, prior_label_columns)
         df = df.fillna(dict.fromkeys(value_columns, 0))
 
-        print_csv(df, output=str(output_file), to_csv_kwargs=self.csv_format)
+        print_csv(df, output=str(output_file))
 
 
 class AnnotationSpecs:
@@ -693,9 +675,7 @@ class AnnotationSpecs:
         result = [to_label_name(label) for label in self._labels_v1]
         duplicated_labels = [key for key, value in collections.Counter(result).items() if value > 1]
         if len(duplicated_labels) > 0:
-            logger.warning(
-                f"アノテーション仕様のラベル英語名が重複しています。アノテーション個数が正しく算出できない可能性があります。:: {duplicated_labels}"
-            )
+            logger.warning(f"アノテーション仕様のラベル英語名が重複しています。アノテーション個数が正しく算出できない可能性があります。:: {duplicated_labels}")
         return result
 
     def attribute_name_keys(
@@ -734,9 +714,7 @@ class AnnotationSpecs:
 
         duplicated_attribute_names = [key for key, value in collections.Counter(result).items() if value > 1]
         if len(duplicated_attribute_names) > 0:
-            logger.warning(
-                f"アノテーション仕様の属性情報（ラベル英語名、属性英語名）が重複しています。アノテーション個数が正しく算出できない可能性があります。:: {duplicated_attribute_names}"  # noqa: E501
-            )
+            logger.warning(f"アノテーション仕様の属性情報（ラベル英語名、属性英語名）が重複しています。アノテーション個数が正しく算出できない可能性があります。:: {duplicated_attribute_names}")
 
         return result
 
@@ -776,7 +754,7 @@ class AnnotationSpecs:
         duplicated_attributes = [key for key, value in collections.Counter(target_attribute_value_keys).items() if value > 1]
         if len(duplicated_attributes) > 0:
             logger.warning(
-                f"アノテーション仕様の属性情報（ラベル英語名、属性英語名、選択肢英語名）が重複しています。アノテーション個数が正しく算出できない可能性があります。:: {duplicated_attributes}"  # noqa: E501
+                f"アノテーション仕様の属性情報（ラベル英語名、属性英語名、選択肢英語名）が重複しています。アノテーション個数が正しく算出できない可能性があります。:: {duplicated_attributes}"
             )
 
         return target_attribute_value_keys
@@ -874,9 +852,7 @@ class ListAnnotationCountMain:
             non_selective_attribute_name_keys = annotation_specs.non_selective_attribute_name_keys()
 
         frame_no_map = self.get_frame_no_map(task_json_path) if task_json_path is not None else None
-        counter_by_input_data = ListAnnotationCounterByInputData(
-            non_target_attribute_names=non_selective_attribute_name_keys, frame_no_map=frame_no_map
-        )
+        counter_by_input_data = ListAnnotationCounterByInputData(non_target_attribute_names=non_selective_attribute_name_keys, frame_no_map=frame_no_map)
         counter_list_by_input_data = counter_by_input_data.get_annotation_counter_list(
             annotation_path,
             target_task_ids=target_task_ids,
@@ -957,9 +933,7 @@ class ListAnnotationCountMain:
             non_selective_attribute_name_keys = None
 
         frame_no_map = self.get_frame_no_map(task_json_path) if task_json_path is not None else None
-        counter_list_by_input_data = ListAnnotationCounterByInputData(
-            non_target_attribute_names=non_selective_attribute_name_keys, frame_no_map=frame_no_map
-        ).get_annotation_counter_list(
+        counter_list_by_input_data = ListAnnotationCounterByInputData(non_target_attribute_names=non_selective_attribute_name_keys, frame_no_map=frame_no_map).get_annotation_counter_list(
             annotation_path,
             target_task_ids=target_task_ids,
             task_query=task_query,
@@ -1198,7 +1172,7 @@ def parse_args(parser: argparse.ArgumentParser) -> None:
     parser.add_argument(
         "--latest",
         action="store_true",
-        help="``--annotation`` を指定しないとき、最新のアノテーションzipを参照します。このオプションを指定すると、アノテーションzipを更新するのに数分待ちます。",  # noqa: E501
+        help="``--annotation`` を指定しないとき、最新のアノテーションzipを参照します。このオプションを指定すると、アノテーションzipを更新するのに数分待ちます。",
     )
 
     parser.set_defaults(subcommand_func=main)

annofabcli/statistics/list_annotation_duration.py

@@ -203,14 +203,10 @@ class ListAnnotationDurationByInputData:
             annotation_duration_by_label[detail["label"]] += calculate_annotation_duration_second(detail)
 
         if self.target_labels is not None:
-            annotation_duration_by_label = {
-                label: duration for label, duration in annotation_duration_by_label.items() if label in self.target_labels
-            }
+            annotation_duration_by_label = {label: duration for label, duration in annotation_duration_by_label.items() if label in self.target_labels}
 
         if self.non_target_labels is not None:
-            annotation_duration_by_label = {
-                label: duration for label, duration in annotation_duration_by_label.items() if label not in self.non_target_labels
-            }
+            annotation_duration_by_label = {label: duration for label, duration in annotation_duration_by_label.items() if label not in self.non_target_labels}
 
         annotation_duration_by_attribute: dict[AttributeValueKey, float] = defaultdict(float)
         for detail in range_details:
@@ -307,7 +303,7 @@ class AnnotationDurationCsvByAttribute:
     Args:
         selective_attribute_value_max_count: 選択肢系の属性の値の個数の上限。これを超えた場合は、非選択肢系属性（トラッキングIDやアノテーションリンクなど）とみなす
 
-    """  # noqa: E501
+    """
 
     def __init__(self, selective_attribute_value_max_count: int = 20) -> None:
         self.selective_attribute_value_max_count = selective_attribute_value_max_count
@@ -322,23 +318,13 @@ class AnnotationDurationCsvByAttribute:
         for label, attribute_name, _ in columns:
             attribute_name_list.append((label, attribute_name))
 
-        non_selective_attribute_names = {
-            key for key, value in collections.Counter(attribute_name_list).items() if value > self.selective_attribute_value_max_count
-        }
+        non_selective_attribute_names = {key for key, value in collections.Counter(attribute_name_list).items() if value > self.selective_attribute_value_max_count}
         if len(non_selective_attribute_names) > 0:
-            logger.debug(
-                f"以下の属性は値の個数が{self.selective_attribute_value_max_count}を超えていたため、集計しません。 :: {non_selective_attribute_names}"
-            )
+            logger.debug(f"以下の属性は値の個数が{self.selective_attribute_value_max_count}を超えていたため、集計しません。 :: {non_selective_attribute_names}")
 
-        return [
-            (label, attribute_name, attribute_value)
-            for (label, attribute_name, attribute_value) in columns
-            if (label, attribute_name) not in non_selective_attribute_names
-        ]
+        return [(label, attribute_name, attribute_value) for (label, attribute_name, attribute_value) in columns if (label, attribute_name) not in non_selective_attribute_names]
 
-    def _value_columns(
-        self, annotation_duration_list: Collection[AnnotationDuration], prior_attribute_columns: Optional[list[AttributeValueKey]]
-    ) -> list[AttributeValueKey]:
+    def _value_columns(self, annotation_duration_list: Collection[AnnotationDuration], prior_attribute_columns: Optional[list[AttributeValueKey]]) -> list[AttributeValueKey]:
         all_attr_key_set = {attr_key for c in annotation_duration_list for attr_key in c.annotation_duration_second_by_attribute}
         if prior_attribute_columns is not None:
             remaining_columns = sorted(all_attr_key_set - set(prior_attribute_columns))
@@ -482,9 +468,7 @@ class ListAnnotationDurationMain:
     def __init__(self, service: annofabapi.Resource) -> None:
         self.service = service
 
-    def print_annotation_duration_csv(
-        self, annotation_duration_list: list[AnnotationDuration], csv_type: CsvType, output_file: Path, *, annotation_specs: Optional[AnnotationSpecs]
-    ) -> None:
+    def print_annotation_duration_csv(self, annotation_duration_list: list[AnnotationDuration], csv_type: CsvType, output_file: Path, *, annotation_specs: Optional[AnnotationSpecs]) -> None:
         if csv_type == CsvType.LABEL:
             # ラベル名の列順が、アノテーション仕様にあるラベル名の順番に対応するようにする。
             label_columns: Optional[list[str]] = None
@@ -522,9 +506,7 @@ class ListAnnotationDurationMain:
             annotation_specs = AnnotationSpecs(self.service, project_id, annotation_type=DefaultAnnotationType.RANGE.value)
             non_selective_attribute_name_keys = annotation_specs.non_selective_attribute_name_keys()
 
-        annotation_duration_list = ListAnnotationDurationByInputData(
-            non_target_attribute_names=non_selective_attribute_name_keys
-        ).get_annotation_duration_list(
+        annotation_duration_list = ListAnnotationDurationByInputData(non_target_attribute_names=non_selective_attribute_name_keys).get_annotation_duration_list(
             annotation_path,
             input_data_json_path=input_data_json_path,
             target_task_ids=target_task_ids,
@@ -535,9 +517,7 @@ class ListAnnotationDurationMain:
 
         if arg_format == FormatArgument.CSV:
             assert csv_type is not None
-            self.print_annotation_duration_csv(
-                annotation_duration_list, output_file=output_file, csv_type=csv_type, annotation_specs=annotation_specs
-            )
+            self.print_annotation_duration_csv(annotation_duration_list, output_file=output_file, csv_type=csv_type, annotation_specs=annotation_specs)
 
         elif arg_format in [FormatArgument.PRETTY_JSON, FormatArgument.JSON]:
             json_is_pretty = arg_format == FormatArgument.PRETTY_JSON
@@ -577,9 +557,7 @@ class ListAnnotationDuration(CommandLine):
             super().validate_project(project_id, project_member_roles=[ProjectMemberRole.OWNER, ProjectMemberRole.TRAINING_DATA_USER])
             project, _ = self.service.api.get_project(project_id)
             if project["input_data_type"] != InputDataType.MOVIE.value:
-                logger.warning(
-                    f"project_id='{project_id}'であるプロジェクトは、動画プロジェクトでないので、出力される区間アノテーションの長さはすべて0秒になります。"
-                )
+                logger.warning(f"project_id='{project_id}'であるプロジェクトは、動画プロジェクトでないので、出力される区間アノテーションの長さはすべて0秒になります。")
 
         annotation_path = Path(args.annotation) if args.annotation is not None else None
 
@@ -622,16 +600,12 @@ class ListAnnotationDuration(CommandLine):
 
         if project_id is not None:
             if args.temp_dir is not None:
-                download_and_print_annotation_duration(
-                    project_id=project_id, temp_dir=args.temp_dir, is_latest=args.latest, annotation_path=annotation_path
-                )
+                download_and_print_annotation_duration(project_id=project_id, temp_dir=args.temp_dir, is_latest=args.latest, annotation_path=annotation_path)
             else:
                 # `NamedTemporaryFile`を使わない理由: Windowsで`PermissionError`が発生するため
                 # https://qiita.com/yuji38kwmt/items/c6f50e1fc03dafdcdda0 参考
                 with tempfile.TemporaryDirectory() as str_temp_dir:
-                    download_and_print_annotation_duration(
-                        project_id=project_id, temp_dir=Path(str_temp_dir), is_latest=args.latest, annotation_path=annotation_path
-                    )
+                    download_and_print_annotation_duration(project_id=project_id, temp_dir=Path(str_temp_dir), is_latest=args.latest, annotation_path=annotation_path)
         else:
             assert annotation_path is not None
             main_obj.print_annotation_duration(
@@ -694,7 +668,7 @@ def parse_args(parser: argparse.ArgumentParser) -> None:
     parser.add_argument(
         "--latest",
         action="store_true",
-        help="``--annotation`` を指定しないとき、最新のアノテーションzipを参照します。このオプションを指定すると、アノテーションzipを更新するのに数分待ちます。",  # noqa: E501
+        help="``--annotation`` を指定しないとき、最新のアノテーションzipを参照します。このオプションを指定すると、アノテーションzipを更新するのに数分待ちます。",
     )
 
     parser.add_argument(

annofabcli/statistics/list_video_duration.py

@@ -71,7 +71,7 @@ class ListVideoDuration(CommandLine):
     def validate(self, args: argparse.Namespace) -> bool:
         if args.project_id is None and (args.input_data_json is None or args.task_json is None):
             print(  # noqa: T201
-                f"{self.COMMON_MESSAGE} argument --project_id: '--input_data_json'または'--task_json'が未指定のときは、'--project_id' を指定してください。",  # noqa: E501
+                f"{self.COMMON_MESSAGE} argument --project_id: '--input_data_json'または'--task_json'が未指定のときは、'--project_id' を指定してください。",
                 file=sys.stderr,
             )
             return False
@@ -171,8 +171,7 @@ def parse_args(parser: argparse.ArgumentParser) -> None:
         "--input_data_json",
         type=Path,
         required=False,
-        help="入力データ情報が記載されたJSONファイルのパスを指定します。\n"
-        "JSONファイルは ``$ annofabcli input_data download`` コマンドで取得できます。",
+        help="入力データ情報が記載されたJSONファイルのパスを指定します。\nJSONファイルは ``$ annofabcli input_data download`` コマンドで取得できます。",
     )
 
     parser.add_argument(

annofabcli/statistics/list_worktime.py

@@ -156,7 +156,6 @@ def parse_args(parser: argparse.ArgumentParser) -> None:
     )
 
     argument_parser.add_output()
-    argument_parser.add_csv_format()
 
     parser.set_defaults(subcommand_func=main)
 

annofabcli/statistics/scatter.py

@@ -142,15 +142,11 @@ class ScatterGraph:
         if legend_label == "":
             legend_label = "none"
 
-        self._scatter_glyphs[legend_label] = self.figure.scatter(
-            x=x_column_name, y=y_column_name, source=source, legend_label=legend_label, color=color, muted_alpha=0.2, size=6
-        )
+        self._scatter_glyphs[legend_label] = self.figure.scatter(x=x_column_name, y=y_column_name, source=source, legend_label=legend_label, color=color, muted_alpha=0.2, size=6)
 
         # 1点ごとに`text`で名前を表示している理由：
         # `add_multi_choice_widget_for_searching_user`関数で追加したMultiChoice Widgetで、名前の表示スタイルを変更するため
-        for x, y, username, user_id in zip(
-            source.data[x_column_name], source.data[y_column_name], source.data[username_column_name], source.data[user_id_column_name]
-        ):
+        for x, y, username, user_id in zip(source.data[x_column_name], source.data[y_column_name], source.data[username_column_name], source.data[user_id_column_name]):
             self.text_glyphs[user_id] = self.figure.text(
                 x=x,
                 y=y,
@@ -204,9 +200,7 @@ class ScatterGraph:
 
         # 1点ごとに`text`で名前を表示している理由：
         # `add_multi_choice_widget_for_searching_user`関数で追加したMultiChoice Widgetで、名前の表示スタイルを変更するため
-        for x, y, username, user_id in zip(
-            source.data[x_column_name], source.data[y_column_name], source.data[username_column_name], source.data[user_id_column_name]
-        ):
+        for x, y, username, user_id in zip(source.data[x_column_name], source.data[y_column_name], source.data[username_column_name], source.data[user_id_column_name]):
             self.text_glyphs[user_id] = self.figure.text(
                 x=x,
                 y=y,

annofabcli/statistics/summarize_task_count.py

@@ -64,15 +64,13 @@ def get_step_for_current_phase(task: Task, number_of_inspections: int) -> int:
 
     elif current_phase == TaskPhase.ANNOTATION:
         number_of_rejections_by_inspection = sum(
-            get_number_of_rejections(histories_by_phase, phase=TaskPhase.INSPECTION, phase_stage=phase_stage)
-            for phase_stage in range(1, number_of_inspections + 1)
+            get_number_of_rejections(histories_by_phase, phase=TaskPhase.INSPECTION, phase_stage=phase_stage) for phase_stage in range(1, number_of_inspections + 1)
         )
         return number_of_rejections_by_inspection + number_of_rejections_by_acceptance + 1
 
     elif current_phase == TaskPhase.INSPECTION:
         number_of_rejections_by_inspection = sum(
-            get_number_of_rejections(histories_by_phase, phase=TaskPhase.INSPECTION, phase_stage=phase_stage)
-            for phase_stage in range(current_phase_stage, number_of_inspections + 1)
+            get_number_of_rejections(histories_by_phase, phase=TaskPhase.INSPECTION, phase_stage=phase_stage) for phase_stage in range(current_phase_stage, number_of_inspections + 1)
         )
         return number_of_rejections_by_inspection + number_of_rejections_by_acceptance + 1
 
@@ -119,9 +117,7 @@ def create_task_count_summary(task_list: list[Task], number_of_inspections: int)
     # `observed=True`を指定する理由：以下の警告に対応するため
     # FutureWarning: The default value of observed=False is deprecated and will change to observed=True in a future version of pandas.
     # Specify observed=False to silence this warning and retain the current behavior
-    summary_df = df.pivot_table(
-        values="task_id", index=["step", "phase", "phase_stage", "simple_status"], aggfunc="count", observed=False
-    ).reset_index()
+    summary_df = df.pivot_table(values="task_id", index=["step", "phase", "phase_stage", "simple_status"], aggfunc="count", observed=False).reset_index()
     summary_df.rename(columns={"task_id": "task_count"}, inplace=True)
 
     summary_df.sort_values(["step", "phase", "phase_stage"])
@@ -146,7 +142,7 @@ class SummarizeTaskCount(CommandLine):
             # タスク全件ファイルをダウンロードするので、オーナロールかアノテーションユーザロールであることを確認する。
             super().validate_project(project_id, project_member_roles=[ProjectMemberRole.OWNER, ProjectMemberRole.TRAINING_DATA_USER])
 
-        if is_execute_get_tasks_api:
+        if is_execute_get_tasks_api:  # noqa: SIM108
             task_list = self.service.wrapper.get_all_tasks(project_id)
         else:
             task_list = self.get_task_list_with_downloading_file(project_id, task_json_path, is_latest=is_latest)
@@ -157,7 +153,7 @@ class SummarizeTaskCount(CommandLine):
 
         number_of_inspections = self.get_number_of_inspections_for_project(project_id)
         task_count_df = create_task_count_summary(task_list, number_of_inspections=number_of_inspections)
-        annofabcli.common.utils.print_csv(task_count_df, output=self.output, to_csv_kwargs=self.csv_format)
+        annofabcli.common.utils.print_csv(task_count_df, output=self.output)
 
     def get_task_list_with_downloading_file(self, project_id: str, task_json_path: Optional[Path], is_latest: bool) -> list[Task]:  # noqa: FBT001
         if task_json_path is None:
@@ -207,10 +203,9 @@ def parse_args(parser: argparse.ArgumentParser) -> None:
     parser.add_argument(
         "--execute_get_tasks_api",
         action="store_true",
-        help="[EXPERIMENTAL] ``getTasks`` APIを実行して、タスク情報を参照します。タスク数が少ないプロジェクトで、最新のタスク情報を参照したいときに利用できます。",  # noqa: E501
+        help="[EXPERIMENTAL] ``getTasks`` APIを実行して、タスク情報を参照します。タスク数が少ないプロジェクトで、最新のタスク情報を参照したいときに利用できます。",
     )
 
-    argument_parser.add_csv_format()
     argument_parser.add_output()
 
     parser.set_defaults(subcommand_func=main)
@@ -226,7 +221,7 @@ def add_parser(subparsers: Optional[argparse._SubParsersAction] = None) -> argpa
     subcommand_name = "summarize_task_count"
     subcommand_help = "タスクのフェーズ、ステータス、ステップごとにタスク数を出力します。"
     description = "タスクのフェーズ、ステータス、ステップごとにタスク数を、CSV形式で出力します。"
-    epilog = "アノテーションユーザまたはオーナロールを持つユーザで実行できます。ただし``--execute_get_tasks_api``を指定した場合は、どのロールでも実行できます。"  # noqa: E501
+    epilog = "アノテーションユーザまたはオーナロールを持つユーザで実行できます。ただし``--execute_get_tasks_api``を指定した場合は、どのロールでも実行できます。"
     parser = annofabcli.common.cli.add_parser(subparsers, subcommand_name, subcommand_help, description=description, epilog=epilog)
     parse_args(parser)
     return parser

annofabcli/statistics/summarize_task_count_by_task_id_group.py

@@ -97,9 +97,7 @@ def get_task_id_prefix(task_id: str, delimiter: str) -> str:
         return delimiter.join(tmp_list[0 : len(tmp_list) - 1])
 
 
-def create_task_count_summary_df(
-    task_list: list[Task], task_id_delimiter: Optional[str], task_id_groups: Optional[dict[str, list[str]]]
-) -> pandas.DataFrame:
+def create_task_count_summary_df(task_list: list[Task], task_id_delimiter: Optional[str], task_id_groups: Optional[dict[str, list[str]]]) -> pandas.DataFrame:
     """
     タスク数を集計したDataFrameを生成する。
 
@@ -131,16 +129,12 @@ def create_task_count_summary_df(
 
     df_task.fillna({"task_id_group": TASK_ID_GROUP_UNKNOWN}, inplace=True)
 
-    df_summary = df_task.pivot_table(
-        values="task_id", index=["task_id_group"], columns=["status_for_summary"], aggfunc="count", fill_value=0
-    ).reset_index()
+    df_summary = df_task.pivot_table(values="task_id", index=["task_id_group"], columns=["status_for_summary"], aggfunc="count", fill_value=0).reset_index()
 
     for status in TaskStatusForSummary:
         add_columns_if_not_exists(df_summary, status.value)
 
-    df_summary["sum"] = (
-        df_task.pivot_table(values="task_id", index=["task_id_group"], aggfunc="count", fill_value=0).reset_index().fillna(0)["task_id"]
-    )
+    df_summary["sum"] = df_task.pivot_table(values="task_id", index=["task_id_group"], aggfunc="count", fill_value=0).reset_index().fillna(0)["task_id"]
 
     return df_summary
 
@@ -152,7 +146,6 @@ class SummarizeTaskCountByTaskId(CommandLine):
             df[columns],
             format=FormatArgument(FormatArgument.CSV),
             output=self.output,
-            csv_format=self.csv_format,
         )
 
     def main(self) -> None:
@@ -207,7 +200,6 @@ def parse_args(parser: argparse.ArgumentParser) -> None:
         help="最新のタスク一覧ファイルを参照します。このオプションを指定すると、タスク一覧ファイルを更新するのに数分待ちます。",
     )
 
-    argument_parser.add_csv_format()
     argument_parser.add_output()
 
     parser.set_defaults(subcommand_func=main)

annofabcli/statistics/summarize_task_count_by_user.py

@@ -80,9 +80,7 @@ def create_task_count_summary_df(task_list: list[Task]) -> pandas.DataFrame:
             df[column] = 0
 
     df_task = pandas.DataFrame([add_info_to_task(t) for t in task_list])
-    df_summary = df_task.pivot_table(
-        values="task_id", index=["account_id"], columns=["status_for_summary"], aggfunc="count", fill_value=0
-    ).reset_index()
+    df_summary = df_task.pivot_table(values="task_id", index=["account_id"], columns=["status_for_summary"], aggfunc="count", fill_value=0).reset_index()
     for status in TaskStatusForSummary:
         add_columns_if_not_exists(df_summary, status.value)
 
@@ -116,7 +114,6 @@ class SummarizeTaskCountByUser(CommandLine):
             target_df,
             format=FormatArgument(FormatArgument.CSV),
             output=self.output,
-            csv_format=self.csv_format,
         )
 
     def main(self) -> None:
@@ -160,7 +157,6 @@ def parse_args(parser: argparse.ArgumentParser) -> None:
         help="最新のタスク一覧ファイルを参照します。このオプションを指定すると、タスク一覧ファイルを更新するのに数分待ちます。",
     )
 
-    argument_parser.add_csv_format()
     argument_parser.add_output()
 
     parser.set_defaults(subcommand_func=main)

annofabcli/statistics/visualization/dataframe/annotation_count.py

@@ -42,9 +42,7 @@ class AnnotationCount:
         self.df = df
 
     @classmethod
-    def from_annotation_zip(
-        cls, annotation_zip: Path, project_id: str, *, get_annotation_count_func: Optional[Callable[[dict[str, Any]], int]] = None
-    ) -> AnnotationCount:
+    def from_annotation_zip(cls, annotation_zip: Path, project_id: str, *, get_annotation_count_func: Optional[Callable[[dict[str, Any]], int]] = None) -> AnnotationCount:
         """
         アノテーションZIPファイルからインスタンスを生成します。
 

annofabcli/statistics/visualization/dataframe/cumulative_productivity.py

@@ -72,9 +72,7 @@ def _create_cumulative_dataframe(task_worktime_by_phase_user: TaskWorktimeByPhas
 class AbstractPhaseCumulativeProductivity(abc.ABC):
     """ロールごとの累積の生産性をプロットするための抽象クラス"""
 
-    def __init__(
-        self, df: pandas.DataFrame, phase: TaskPhase, *, custom_production_volume_list: Optional[list[ProductionVolumeColumn]] = None
-    ) -> None:
+    def __init__(self, df: pandas.DataFrame, phase: TaskPhase, *, custom_production_volume_list: Optional[list[ProductionVolumeColumn]] = None) -> None:
         self.df = df
         self.phase = phase
         self.phase_name = self._get_phase_name(phase)
@@ -104,9 +102,7 @@ class AbstractPhaseCumulativeProductivity(abc.ABC):
             return False
 
         if len(self.default_user_id_list) == 0:
-            logger.info(
-                f"{self.phase_name}作業したタスクが0件なので（'first_{self.phase.value}_user_id'がすべて空欄）、{output_file} を出力しません。"
-            )
+            logger.info(f"{self.phase_name}作業したタスクが0件なので（'first_{self.phase.value}_user_id'がすべて空欄）、{output_file} を出力しません。")
             return False
 
         return True
@@ -138,9 +134,7 @@ class AbstractPhaseCumulativeProductivity(abc.ABC):
             たとえば、20000件をプロットする際、すべての列を出力すると、そうでないときに比べてファイルサイズが3倍以上になる
             """
             xy_columns = set(itertools.chain.from_iterable(columns for columns in columns_list))
-            tooltip_columns = set(
-                itertools.chain.from_iterable(line_graph.tooltip_columns for line_graph in line_graph_list if line_graph.tooltip_columns is not None)
-            )
+            tooltip_columns = set(itertools.chain.from_iterable(line_graph.tooltip_columns for line_graph in line_graph_list if line_graph.tooltip_columns is not None))
             return list(xy_columns | tooltip_columns)
 
         df = self.df

annofabcli/statistics/visualization/dataframe/productivity_per_date.py

@@ -41,9 +41,7 @@ def create_df_productivity_per_date(task_worktime_by_phase_user: TaskWorktimeByP
     df = df[df["phase"] == str_phase]
     df = df.rename(columns={"pointed_out_inspection_comment_count": "inspection_comment_count", "worktime_hour": f"{str_phase}_worktime_hour"})
 
-    df[f"first_{str_phase}_started_date"] = df["started_datetime"].map(
-        lambda e: datetime_to_date(e) if e is not None and isinstance(e, str) else None
-    )
+    df[f"first_{str_phase}_started_date"] = df["started_datetime"].map(lambda e: datetime_to_date(e) if e is not None and isinstance(e, str) else None)
 
     # first_annotation_user_id と first_annotation_usernameの両方を指定している理由：
     # first_annotation_username を取得するため
@@ -82,9 +80,7 @@ class AbstractPhaseProductivityPerDate(abc.ABC):
     PLOT_WIDTH = 1200
     PLOT_HEIGHT = 600
 
-    def __init__(
-        self, df: pandas.DataFrame, phase: TaskPhase, *, custom_production_volume_list: Optional[list[ProductionVolumeColumn]] = None
-    ) -> None:
+    def __init__(self, df: pandas.DataFrame, phase: TaskPhase, *, custom_production_volume_list: Optional[list[ProductionVolumeColumn]] = None) -> None:
         self.df = df
         self.phase = phase
         self.custom_production_volume_list = custom_production_volume_list if custom_production_volume_list is not None else []
@@ -209,9 +205,7 @@ class AbstractPhaseProductivityPerDate(abc.ABC):
             *self.production_volume_columns,
         ]
 
-        velocity_columns = [
-            f"{numerator}/{denominator}" for numerator in [f"{str_phase}_worktime_hour"] for denominator in self.production_volume_columns
-        ]
+        velocity_columns = [f"{numerator}/{denominator}" for numerator in [f"{str_phase}_worktime_hour"] for denominator in self.production_volume_columns]
 
         columns = production_columns + velocity_columns
 
@@ -337,15 +331,13 @@ class AnnotatorProductivityPerDate(AbstractPhaseProductivityPerDate):
                 continue
 
             df_subset = self._get_df_sequential_date(df_subset)
-            df_subset[f"annotation_worktime_minute/{production_volume_column}"] = (
-                df_subset["annotation_worktime_hour"] * 60 / df_subset[production_volume_column]
-            )
+            df_subset[f"annotation_worktime_minute/{production_volume_column}"] = df_subset["annotation_worktime_hour"] * 60 / df_subset[production_volume_column]
             df_subset[f"annotation_worktime_minute/{production_volume_column}{WEEKLY_MOVING_AVERAGE_COLUMN_SUFFIX}"] = (
                 get_weekly_sum(df_subset["annotation_worktime_hour"]) * 60 / get_weekly_sum(df_subset[production_volume_column])
             )
-            df_subset[f"inspection_comment_count/{production_volume_column}{WEEKLY_MOVING_AVERAGE_COLUMN_SUFFIX}"] = get_weekly_sum(
-                df_subset["inspection_comment_count"]
-            ) / get_weekly_sum(df_subset[production_volume_column])
+            df_subset[f"inspection_comment_count/{production_volume_column}{WEEKLY_MOVING_AVERAGE_COLUMN_SUFFIX}"] = get_weekly_sum(df_subset["inspection_comment_count"]) / get_weekly_sum(
+                df_subset[production_volume_column]
+            )
 
             source = ColumnDataSource(data=df_subset)
             color = get_color_from_palette(user_index)
@@ -414,7 +406,7 @@ class InspectorProductivityPerDate(AbstractPhaseProductivityPerDate):
 
         df = self.df.copy()
 
-        if target_user_id_list is not None:
+        if target_user_id_list is not None:  # noqa: SIM108
             user_id_list = target_user_id_list
         else:
             user_id_list = df.sort_values(by="user_id", ascending=False)["user_id"].dropna().unique().tolist()
@@ -475,9 +467,7 @@ class InspectorProductivityPerDate(AbstractPhaseProductivityPerDate):
                 continue
 
             df_subset = self._get_df_sequential_date(df_subset)
-            df_subset[f"inspection_worktime_minute/{production_volume_column}"] = (
-                df_subset["inspection_worktime_hour"] * 60 / df_subset[production_volume_column]
-            )
+            df_subset[f"inspection_worktime_minute/{production_volume_column}"] = df_subset["inspection_worktime_hour"] * 60 / df_subset[production_volume_column]
             df_subset[f"inspection_worktime_minute/{production_volume_column}{WEEKLY_MOVING_AVERAGE_COLUMN_SUFFIX}"] = (
                 get_weekly_sum(df_subset["inspection_worktime_hour"]) * 60 / get_weekly_sum(df_subset[production_volume_column])
             )
@@ -554,7 +544,7 @@ class AcceptorProductivityPerDate(AbstractPhaseProductivityPerDate):
 
         df = self.df.copy()
 
-        if target_user_id_list is not None:
+        if target_user_id_list is not None:  # noqa: SIM108
             user_id_list = target_user_id_list
         else:
             user_id_list = df.sort_values(by="user_id", ascending=False)["user_id"].dropna().unique().tolist()
@@ -616,9 +606,7 @@ class AcceptorProductivityPerDate(AbstractPhaseProductivityPerDate):
                 continue
 
             df_subset = self._get_df_sequential_date(df_subset)
-            df_subset[f"acceptance_worktime_minute/{production_volume_column}"] = (
-                df_subset["acceptance_worktime_hour"] * 60 / df_subset[production_volume_column]
-            )
+            df_subset[f"acceptance_worktime_minute/{production_volume_column}"] = df_subset["acceptance_worktime_hour"] * 60 / df_subset[production_volume_column]
 
             df_subset[f"acceptance_worktime_minute/{production_volume_column}{WEEKLY_MOVING_AVERAGE_COLUMN_SUFFIX}"] = (
                 get_weekly_sum(df_subset["acceptance_worktime_hour"]) * 60 / get_weekly_sum(df_subset[production_volume_column])

annofabcli/statistics/visualization/dataframe/project_performance.py

@@ -89,9 +89,7 @@ class ProjectPerformance:
         return [e.value for e in TaskPhase if e.value in tmp_set]
 
     @classmethod
-    def from_project_dirs(
-        cls, project_dir_list: list[ProjectDir], *, custom_production_volume_list: Optional[list[ProductionVolumeColumn]] = None
-    ) -> ProjectPerformance:
+    def from_project_dirs(cls, project_dir_list: list[ProjectDir], *, custom_production_volume_list: Optional[list[ProductionVolumeColumn]] = None) -> ProjectPerformance:
         row_list: list[pandas.Series] = [cls._get_series_from_project_dir(project_dir) for project_dir in project_dir_list]
         return cls(pandas.DataFrame(row_list), custom_production_volume_list=custom_production_volume_list)