annofabcli 1.102.1__py3-none-any.whl → 1.103.0__py3-none-any.whl

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)
 

annofabcli/statistics/visualization/dataframe/task.py

@@ -71,10 +71,7 @@ class Task:
             logger.warning("引数`df`に重複したキー（project_id, task_id）が含まれています。")
 
         if not self.required_columns_exist(df):
-            raise ValueError(
-                f"引数'df'の'columns'に次の列が存在していません。 {self.missing_required_columns(df)} :: "
-                f"次の列が必須です。{self.required_columns} の列が必要です。"
-            )
+            raise ValueError(f"引数'df'の'columns'に次の列が存在していません。 {self.missing_required_columns(df)} :: 次の列が必須です。{self.required_columns} の列が必要です。")
 
         self.df = df
 
@@ -409,7 +406,7 @@ class Task:
 
             # タイムゾーンを指定している理由::
             # すべてがNaNのseriesをdatetimeに変換すると、型にタイムゾーンが指定されない。
-            # その状態で加算すると、`TypeError: DatetimeArray subtraction must have the same timezones or no timezones`というエラーが発生するため  # noqa: E501
+            # その状態で加算すると、`TypeError: DatetimeArray subtraction must have the same timezones or no timezones`というエラーが発生するため
             if not isinstance(dt1.dtype, pandas.DatetimeTZDtype):
                 dt1 = dt1.dt.tz_localize(pytz.FixedOffset(540))
             if not isinstance(dt2.dtype, pandas.DatetimeTZDtype):

annofabcli/statistics/visualization/dataframe/task_worktime_by_phase_user.py

@@ -107,9 +107,7 @@ class TaskWorktimeByPhaseUser:
             logger.warning("引数`df`に重複したキー（project_id, task_id, phase, phase_stage, account_id）が含まれています。")
 
         if not self.required_columns_exist(df):
-            raise ValueError(
-                f"引数'df'の'columns'に次の列が存在していません。 {self.missing_columns(df)} :: 次の列が必須です。{self.columns}の列が必要です。"
-            )
+            raise ValueError(f"引数'df'の'columns'に次の列が存在していません。 {self.missing_columns(df)} :: 次の列が必須です。{self.columns}の列が必要です。")
 
         self.df = df
 
@@ -141,9 +139,7 @@ class TaskWorktimeByPhaseUser:
             project_id
         """
         df_task = task.df
-        df_worktime_ratio = cls._create_annotation_count_ratio_df(
-            task_history.df, task.df, custom_production_volume_columns=[e.value for e in task.custom_production_volume_list]
-        )
+        df_worktime_ratio = cls._create_annotation_count_ratio_df(task_history.df, task.df, custom_production_volume_columns=[e.value for e in task.custom_production_volume_list])
         if len(df_worktime_ratio) == 0:
             return cls.empty()
 
@@ -239,9 +235,7 @@ class TaskWorktimeByPhaseUser:
         return TaskWorktimeByPhaseUser(df, custom_production_volume_list=self.custom_production_volume_list)
 
     @staticmethod
-    def _create_annotation_count_ratio_df(
-        task_history_df: pandas.DataFrame, task_df: pandas.DataFrame, *, custom_production_volume_columns: Optional[list[str]]
-    ) -> pandas.DataFrame:
+    def _create_annotation_count_ratio_df(task_history_df: pandas.DataFrame, task_df: pandas.DataFrame, *, custom_production_volume_columns: Optional[list[str]]) -> pandas.DataFrame:
         """
         task_id, phase, (phase_index), user_idの作業時間比から、アノテーション数などの生産量を求める
 
@@ -273,11 +267,7 @@ class TaskWorktimeByPhaseUser:
 
         task_history_df = task_history_df[task_history_df["task_id"].isin(set(task_df["task_id"]))]
 
-        group_obj = (
-            task_history_df.sort_values("started_datetime")
-            .groupby(["task_id", "phase", "phase_stage", "account_id"])
-            .agg({"worktime_hour": "sum", "started_datetime": "first"})
-        )
+        group_obj = task_history_df.sort_values("started_datetime").groupby(["task_id", "phase", "phase_stage", "account_id"]).agg({"worktime_hour": "sum", "started_datetime": "first"})
         # 担当者だけ変更して作業していないケースを除外する
         group_obj = group_obj[group_obj["worktime_hour"] > 0]
 
@@ -285,9 +275,7 @@ class TaskWorktimeByPhaseUser:
             logger.warning("タスク履歴情報に作業しているタスクがありませんでした。タスク履歴全件ファイルが更新されていない可能性があります。")
             return pandas.DataFrame()
 
-        group_obj["task_count"] = group_obj.groupby(level=["task_id", "phase", "phase_stage"], group_keys=False)[["worktime_hour"]].apply(
-            lambda e: e / e["worktime_hour"].sum()
-        )
+        group_obj["task_count"] = group_obj.groupby(level=["task_id", "phase", "phase_stage"], group_keys=False)[["worktime_hour"]].apply(lambda e: e / e["worktime_hour"].sum())
 
         quantity_columns = [
             "annotation_count",
@@ -302,9 +290,7 @@ class TaskWorktimeByPhaseUser:
             group_obj[col] = group_obj.apply(sub_get_quantity_value, axis="columns")
 
         new_df = group_obj.reset_index()
-        new_df["pointed_out_inspection_comment_count"] = new_df["pointed_out_inspection_comment_count"] * new_df["phase"].apply(
-            lambda e: 1 if e == TaskPhase.ANNOTATION.value else 0
-        )
+        new_df["pointed_out_inspection_comment_count"] = new_df["pointed_out_inspection_comment_count"] * new_df["phase"].apply(lambda e: 1 if e == TaskPhase.ANNOTATION.value else 0)
         new_df["rejected_count"] = new_df["rejected_count"] * new_df["phase"].apply(lambda e: 1 if e == TaskPhase.ANNOTATION.value else 0)
 
         return new_df