annofabcli 1.102.1__py3-none-any.whl → 1.104.0__py3-none-any.whl

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
 
@@ -259,7 +253,7 @@ class AnnotatorProductivityPerDate(AbstractPhaseProductivityPerDate):
 
         df = self.df.copy()
 
-        if target_user_id_list is not None:  # noqa: SIM108
+        if target_user_id_list is not None:
             user_id_list = target_user_id_list
         else:
             user_id_list = df.sort_values(by="user_id")["user_id"].dropna().unique().tolist()
@@ -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)
@@ -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])
             )
@@ -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_history.py

@@ -67,7 +67,7 @@ class TaskHistory:
                 new_task_history["worktime_hour"] = isoduration_to_hour(task_history["accumulated_labor_time_milliseconds"])
                 all_task_history_list.append(new_task_history)
 
-        if len(all_task_history_list) > 0:  # noqa: SIM108
+        if len(all_task_history_list) > 0:
             df = pandas.DataFrame(all_task_history_list)
         else:
             df = cls.empty()

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

annofabcli/statistics/visualization/dataframe/user_performance.py

@@ -100,9 +100,7 @@ class UserPerformance:
         self.custom_production_volume_list = custom_production_volume_list if custom_production_volume_list is not None else []
         self.phase_list = phase_list
         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
 
@@ -116,18 +114,14 @@ class UserPerformance:
         return len(self.df) == 0
 
     @staticmethod
-    def _add_ratio_column_for_productivity_per_user(
-        df: pandas.DataFrame, phase_list: Sequence[TaskPhaseString], production_volume_columns: list[str]
-    ) -> None:
+    def _add_ratio_column_for_productivity_per_user(df: pandas.DataFrame, phase_list: Sequence[TaskPhaseString], production_volume_columns: list[str]) -> None:
         """
         ユーザーの生産性に関する列を、DataFrameに追加します。
         """
 
         # 集計対象タスクから算出した計測作業時間（`monitored_worktime_hour`）に対応する実績作業時間を推定で算出する
         # 具体的には、実際の計測作業時間と十先作業時間の比（`real_monitored_worktime_hour/real_actual_worktime_hour`）になるように按分する
-        df[("actual_worktime_hour", "sum")] = (
-            df[("monitored_worktime_hour", "sum")] / df[("real_monitored_worktime_hour/real_actual_worktime_hour", "sum")]
-        )
+        df[("actual_worktime_hour", "sum")] = df[("monitored_worktime_hour", "sum")] / df[("real_monitored_worktime_hour/real_actual_worktime_hour", "sum")]
 
         for phase in phase_list:
 
@@ -156,23 +150,15 @@ class UserPerformance:
             # 生産性を算出
             ratio__actual_vs_monitored_worktime = df[("actual_worktime_hour", phase)] / df[("monitored_worktime_hour", phase)]
             for production_volume_column in production_volume_columns:
-                df[(f"monitored_worktime_hour/{production_volume_column}", phase)] = (
-                    df[("monitored_worktime_hour", phase)] / df[(production_volume_column, phase)]
-                )
-                df[(f"actual_worktime_hour/{production_volume_column}", phase)] = (
-                    df[("actual_worktime_hour", phase)] / df[(production_volume_column, phase)]
-                )
+                df[(f"monitored_worktime_hour/{production_volume_column}", phase)] = df[("monitored_worktime_hour", phase)] / df[(production_volume_column, phase)]
+                df[(f"actual_worktime_hour/{production_volume_column}", phase)] = df[("actual_worktime_hour", phase)] / df[(production_volume_column, phase)]
 
-                df[(f"stdev__actual_worktime_hour/{production_volume_column}", phase)] = (
-                    df[(f"stdev__monitored_worktime_hour/{production_volume_column}", phase)] * ratio__actual_vs_monitored_worktime
-                )
+                df[(f"stdev__actual_worktime_hour/{production_volume_column}", phase)] = df[(f"stdev__monitored_worktime_hour/{production_volume_column}", phase)] * ratio__actual_vs_monitored_worktime
 
         # 品質に関する情報
         phase = TaskPhase.ANNOTATION.value
         for production_volume_column in production_volume_columns:
-            df[(f"pointed_out_inspection_comment_count/{production_volume_column}", phase)] = (
-                df[("pointed_out_inspection_comment_count", phase)] / df[(production_volume_column, phase)]
-            )
+            df[(f"pointed_out_inspection_comment_count/{production_volume_column}", phase)] = df[("pointed_out_inspection_comment_count", phase)] / df[(production_volume_column, phase)]
 
         df[("rejected_count/task_count", phase)] = df[("rejected_count", phase)] / df[("task_count", phase)]
 
@@ -204,9 +190,7 @@ class UserPerformance:
         return cls(df, task_completion_criteria, custom_production_volume_list=custom_production_volume_list)
 
     @classmethod
-    def empty(
-        cls, task_completion_criteria: TaskCompletionCriteria, *, custom_production_volume_list: Optional[list[ProductionVolumeColumn]] = None
-    ) -> UserPerformance:
+    def empty(cls, task_completion_criteria: TaskCompletionCriteria, *, custom_production_volume_list: Optional[list[ProductionVolumeColumn]] = None) -> UserPerformance:
         """空のデータフレームを持つインスタンスを生成します。"""
         production_volume_columns = ["input_data_count", "annotation_count"]
         if custom_production_volume_list is not None:
@@ -321,10 +305,7 @@ class UserPerformance:
             # `to_csv()`で出力したときにKeyErrorが発生内容にするため、事前に列を追加しておく
             phase = TaskPhase.ANNOTATION.value
             columns = pandas.MultiIndex.from_tuples(
-                [
-                    (f"stdev__monitored_worktime_hour/{production_volume_column}", phase)
-                    for production_volume_column in task_worktime_by_phase_user.production_volume_columns
-                ]
+                [(f"stdev__monitored_worktime_hour/{production_volume_column}", phase) for production_volume_column in task_worktime_by_phase_user.production_volume_columns]
             )
             df_empty = pandas.DataFrame(columns=columns, index=pandas.Index([], name="account_id"), dtype="float64")
             return df_empty
@@ -340,9 +321,7 @@ class UserPerformance:
         df_stdev_per_volume_count_list = []
         for production_volume_column in task_worktime_by_phase_user.production_volume_columns:
             df_stdev_per_input_data_count = (
-                df2[df2[f"worktime_hour/{production_volume_column}"] != float("inf")]
-                .groupby(["account_id", "phase"])[[f"worktime_hour/{production_volume_column}"]]
-                .std(ddof=0)
+                df2[df2[f"worktime_hour/{production_volume_column}"] != float("inf")].groupby(["account_id", "phase"])[[f"worktime_hour/{production_volume_column}"]].std(ddof=0)
             )
             df_stdev_per_volume_count_list.append(df_stdev_per_input_data_count)
         df_stdev = pandas.concat(df_stdev_per_volume_count_list, axis=1)
@@ -351,9 +330,7 @@ class UserPerformance:
         # 前述の処理でinfを除外しているので、NaNが含まれることはないはず
         df_stdev2 = pandas.pivot_table(
             df_stdev,
-            values=[
-                f"worktime_hour/{production_volume_column}" for production_volume_column in task_worktime_by_phase_user.production_volume_columns
-            ],
+            values=[f"worktime_hour/{production_volume_column}" for production_volume_column in task_worktime_by_phase_user.production_volume_columns],
             index="account_id",
             columns="phase",
             dropna=False,
@@ -501,10 +478,7 @@ class UserPerformance:
 
         df = worktime_per_date.df
 
-        df4_list = [
-            _create_df_first_last_working_date(phase)
-            for phase in [None, TaskPhase.ANNOTATION.value, TaskPhase.INSPECTION.value, TaskPhase.ACCEPTANCE.value]
-        ]
+        df4_list = [_create_df_first_last_working_date(phase) for phase in [None, TaskPhase.ANNOTATION.value, TaskPhase.INSPECTION.value, TaskPhase.ACCEPTANCE.value]]
 
         # joinしない理由: レベル1の列名が空文字のDataFrameをjoinすると、Python3.12のpandas2.2.0で、列名が期待通りにならないため
         # https://github.com/pandas-dev/pandas/issues/57500
@@ -546,7 +520,7 @@ class UserPerformance:
             task_worktime_by_phase_user: タスク、フェーズ、ユーザーごとの作業時間や生産量が格納されたオブジェクト。生産量やタスクにかかった作業時間の取得に利用します。
 
 
-        """  # noqa: E501
+        """
 
         def drop_unnecessary_columns(df: pandas.DataFrame) -> pandas.DataFrame:
             """
@@ -593,9 +567,7 @@ class UserPerformance:
         df = df.join(cls._create_df_stdev_monitored_worktime(task_worktime_by_phase_user))
 
         # 比例関係の列を計算して追加する
-        cls._add_ratio_column_for_productivity_per_user(
-            df, phase_list=phase_list, production_volume_columns=task_worktime_by_phase_user.production_volume_columns
-        )
+        cls._add_ratio_column_for_productivity_per_user(df, phase_list=phase_list, production_volume_columns=task_worktime_by_phase_user.production_volume_columns)
 
         # 出力に不要な列を削除する
         df = drop_unnecessary_columns(df)
@@ -611,9 +583,7 @@ class UserPerformance:
 
         df = df.sort_values(["user_id"])
         # `df.reset_index()`を実行する理由：indexである`account_id`を列にするため
-        return cls(
-            df.reset_index(), task_completion_criteria, custom_production_volume_list=task_worktime_by_phase_user.custom_production_volume_list
-        )
+        return cls(df.reset_index(), task_completion_criteria, custom_production_volume_list=task_worktime_by_phase_user.custom_production_volume_list)
 
     @classmethod
     def _convert_column_dtypes(cls, df: pandas.DataFrame) -> pandas.DataFrame:
@@ -663,11 +633,7 @@ class UserPerformance:
             ("real_monitored_worktime_hour", "acceptance"),
         ]
 
-        monitored_worktime_columns = (
-            [("monitored_worktime_hour", "sum")]
-            + [("monitored_worktime_hour", phase) for phase in phase_list]
-            + [("monitored_worktime_ratio", phase) for phase in phase_list]
-        )
+        monitored_worktime_columns = [("monitored_worktime_hour", "sum")] + [("monitored_worktime_hour", phase) for phase in phase_list] + [("monitored_worktime_ratio", phase) for phase in phase_list]
         production_columns = [("task_count", phase) for phase in phase_list]
         for production_volume_column in production_volume_columns:
             production_columns.extend([(production_volume_column, phase) for phase in phase_list])
@@ -685,10 +651,7 @@ class UserPerformance:
 
         inspection_comment_columns = [
             ("pointed_out_inspection_comment_count", TaskPhase.ANNOTATION.value),
-            *[
-                (f"pointed_out_inspection_comment_count/{production_volume_column}", TaskPhase.ANNOTATION.value)
-                for production_volume_column in production_volume_columns
-            ],
+            *[(f"pointed_out_inspection_comment_count/{production_volume_column}", TaskPhase.ANNOTATION.value) for production_volume_column in production_volume_columns],
         ]
 
         rejected_count_columns = [
@@ -815,48 +778,32 @@ class UserPerformance:
         """
         # ゼロ割の警告を無視する
         with numpy.errstate(divide="ignore", invalid="ignore"):
-            series[("real_monitored_worktime_hour/real_actual_worktime_hour", "sum")] = (
-                series[("real_monitored_worktime_hour", "sum")] / series[("real_actual_worktime_hour", "sum")]
-            )
+            series[("real_monitored_worktime_hour/real_actual_worktime_hour", "sum")] = series[("real_monitored_worktime_hour", "sum")] / series[("real_actual_worktime_hour", "sum")]
 
             for phase in phase_list:
                 # Annofab時間の比率を算出
-                # 計測作業時間の合計値が0により、monitored_worktime_ratioはnanになる場合は、教師付の実績作業時間を実績作業時間の合計値になるようなmonitored_worktime_ratioに変更する  # noqa: E501
+                # 計測作業時間の合計値が0により、monitored_worktime_ratioはnanになる場合は、教師付の実績作業時間を実績作業時間の合計値になるようなmonitored_worktime_ratioに変更する
                 if series[("monitored_worktime_hour", "sum")] == 0:
                     if phase == TaskPhase.ANNOTATION.value:
                         series[("monitored_worktime_ratio", phase)] = 1
                     else:
                         series[("monitored_worktime_ratio", phase)] = 0
                 else:
-                    series[("monitored_worktime_ratio", phase)] = (
-                        series[("monitored_worktime_hour", phase)] / series[("monitored_worktime_hour", "sum")]
-                    )
+                    series[("monitored_worktime_ratio", phase)] = series[("monitored_worktime_hour", phase)] / series[("monitored_worktime_hour", "sum")]
 
                 # Annofab時間の比率から、Annowork時間を予測する
                 series[("actual_worktime_hour", phase)] = series[("actual_worktime_hour", "sum")] * series[("monitored_worktime_ratio", phase)]
 
                 # 生産性を算出
-                series[("monitored_worktime_hour/input_data_count", phase)] = (
-                    series[("monitored_worktime_hour", phase)] / series[("input_data_count", phase)]
-                )
-                series[("actual_worktime_hour/input_data_count", phase)] = (
-                    series[("actual_worktime_hour", phase)] / series[("input_data_count", phase)]
-                )
+                series[("monitored_worktime_hour/input_data_count", phase)] = series[("monitored_worktime_hour", phase)] / series[("input_data_count", phase)]
+                series[("actual_worktime_hour/input_data_count", phase)] = series[("actual_worktime_hour", phase)] / series[("input_data_count", phase)]
 
-                series[("monitored_worktime_hour/annotation_count", phase)] = (
-                    series[("monitored_worktime_hour", phase)] / series[("annotation_count", phase)]
-                )
-                series[("actual_worktime_hour/annotation_count", phase)] = (
-                    series[("actual_worktime_hour", phase)] / series[("annotation_count", phase)]
-                )
+                series[("monitored_worktime_hour/annotation_count", phase)] = series[("monitored_worktime_hour", phase)] / series[("annotation_count", phase)]
+                series[("actual_worktime_hour/annotation_count", phase)] = series[("actual_worktime_hour", phase)] / series[("annotation_count", phase)]
 
             phase = TaskPhase.ANNOTATION.value
-            series[("pointed_out_inspection_comment_count/annotation_count", phase)] = (
-                series[("pointed_out_inspection_comment_count", phase)] / series[("annotation_count", phase)]
-            )
-            series[("pointed_out_inspection_comment_count/input_data_count", phase)] = (
-                series[("pointed_out_inspection_comment_count", phase)] / series[("input_data_count", phase)]
-            )
+            series[("pointed_out_inspection_comment_count/annotation_count", phase)] = series[("pointed_out_inspection_comment_count", phase)] / series[("annotation_count", phase)]
+            series[("pointed_out_inspection_comment_count/input_data_count", phase)] = series[("pointed_out_inspection_comment_count", phase)] / series[("input_data_count", phase)]
             series[("rejected_count/task_count", phase)] = series[("rejected_count", phase)] / series[("task_count", phase)]
 
     def get_production_volume_name(self, production_volume_column: str) -> str:
@@ -929,9 +876,7 @@ class UserPerformance:
         y_column = f"{worktime_type.value}_worktime_minute/{production_volume_column}"
         # 分単位の生産性を算出する
         for phase in self.phase_list:
-            df[(f"{worktime_type.value}_worktime_minute/{production_volume_column}", phase)] = (
-                df[(f"{worktime_type.value}_worktime_hour/{production_volume_column}", phase)] * 60
-            )
+            df[(f"{worktime_type.value}_worktime_minute/{production_volume_column}", phase)] = df[(f"{worktime_type.value}_worktime_hour/{production_volume_column}", phase)] * 60
 
         for biography_index, biography in enumerate(sorted(set(df["biography"]))):
             for scatter_obj, phase in zip(scatter_obj_list, self.phase_list):
@@ -1074,9 +1019,7 @@ class UserPerformance:
 
         write_bokeh_graph(bokeh.layouts.column(element_list), output_file)
 
-    def plot_quality_and_productivity(
-        self, output_file: Path, worktime_type: WorktimeType, production_volume_column: str, *, metadata: Optional[dict[str, Any]] = None
-    ) -> None:
+    def plot_quality_and_productivity(self, output_file: Path, worktime_type: WorktimeType, production_volume_column: str, *, metadata: Optional[dict[str, Any]] = None) -> None:
         """
         作業時間を元に算出した生産性と品質の関係を、メンバごとにプロットする
         """
@@ -1157,9 +1100,7 @@ class UserPerformance:
         df = self.convert_df_suitable_for_bokeh(self.df)
         PHASE = TaskPhase.ANNOTATION.value  # noqa: N806
 
-        df[(f"{worktime_type.value}_worktime_minute/{production_volume_column}", PHASE)] = (
-            df[(f"{worktime_type.value}_worktime_hour/{production_volume_column}", PHASE)] * 60
-        )
+        df[(f"{worktime_type.value}_worktime_minute/{production_volume_column}", PHASE)] = df[(f"{worktime_type.value}_worktime_hour/{production_volume_column}", PHASE)] * 60
         logger.debug(f"{output_file} を出力します。")
 
         production_volume_name = self.get_production_volume_name(production_volume_column)

annofabcli/statistics/visualization/dataframe/whole_performance.py

@@ -84,9 +84,7 @@ class WholePerformance:
         df_task = df_task_worktime_by_phase_user[["project_id", "task_id", "status"]].drop_duplicates()
 
         unique_keys_for_worktime = ["project_id", "task_id", "phase", "phase_stage"]
-        addable_columns_for_task = list(
-            set(df_task_worktime_by_phase_user.columns) - set(user_info_columns) - set(unique_keys_for_worktime) - {"status"}
-        )
+        addable_columns_for_task = list(set(df_task_worktime_by_phase_user.columns) - set(user_info_columns) - set(unique_keys_for_worktime) - {"status"})
         df_task_worktime_by_phase_user = df_task_worktime_by_phase_user.groupby(unique_keys_for_worktime)[addable_columns_for_task].sum()
         df_task_worktime_by_phase_user[user_info_columns] = PSEUDO_VALUE
         df_task_worktime_by_phase_user = df_task_worktime_by_phase_user.reset_index()
@@ -95,9 +93,7 @@ class WholePerformance:
 
         return UserPerformance.from_df_wrapper(
             worktime_per_date=WorktimePerDate(df_worktime_per_date),
-            task_worktime_by_phase_user=TaskWorktimeByPhaseUser(
-                df_task_worktime_by_phase_user, custom_production_volume_list=task_worktime_by_phase_user.custom_production_volume_list
-            ),
+            task_worktime_by_phase_user=TaskWorktimeByPhaseUser(df_task_worktime_by_phase_user, custom_production_volume_list=task_worktime_by_phase_user.custom_production_volume_list),
             task_completion_criteria=task_completion_criteria,
         )
 
@@ -115,7 +111,7 @@ class WholePerformance:
             worktime_per_date: 日ごとの作業時間が記載されたDataFrameを格納したオブジェクト。ユーザー情報の取得や、実際の作業時間（集計タスクに影響しない）の算出に利用します。
             task_worktime_by_phase_user: タスク、フェーズ、ユーザーごとの作業時間や生産量が格納されたオブジェクト。生産量やタスクにかかった作業時間の取得に利用します。
 
-        """  # noqa: E501
+        """
         # 1人が作業した場合のパフォーマンス情報を生成する
         all_user_performance = cls._create_all_user_performance(worktime_per_date, task_worktime_by_phase_user, task_completion_criteria)
 
@@ -142,9 +138,7 @@ class WholePerformance:
         return cls(df_all.iloc[0], task_completion_criteria, custom_production_volume_list=task_worktime_by_phase_user.custom_production_volume_list)
 
     @classmethod
-    def empty(
-        cls, task_completion_criteria: TaskCompletionCriteria, *, custom_production_volume_list: Optional[list[ProductionVolumeColumn]] = None
-    ) -> WholePerformance:
+    def empty(cls, task_completion_criteria: TaskCompletionCriteria, *, custom_production_volume_list: Optional[list[ProductionVolumeColumn]] = None) -> WholePerformance:
         """空のデータフレームを持つインスタンスを生成します。"""
 
         production_volume_columns = ["input_data_count", "annotation_count"]
@@ -219,12 +213,12 @@ class WholePerformance:
         # CSVファイル読み込み直後では、数値も文字列として格納されているので、文字列情報以外は数値に変換する
         for key, value in series.items():
             # `first_working_date`など2列目が空欄の場合は、key[1]がnumpy.nanになるため、keyを変換する
-            if isinstance(key[1], float) and numpy.isnan(key[1]):  # noqa: SIM108
+            if isinstance(key[1], float) and numpy.isnan(key[1]):
                 key2 = (key[0], "")
             else:
                 key2 = key
 
-            if key2 in cls.STRING_KEYS:  # noqa: SIM108
+            if key2 in cls.STRING_KEYS:
                 value2 = value
             else:
                 value2 = float(value)