1)improve target selector 2)add examples

examples/report_utils.py

@@ -3,11 +3,9 @@
 import time
 from typing import Type
 
-from tabulate import tabulate
-
 from examples.utils import add_to_eastmoney
 from zvt import zvt_config
-from zvt.api import get_top_volume_entities, get_top_performance_entities
+from zvt.api import get_top_volume_entities, get_top_performance_entities, TopType
 from zvt.api.kdata import get_latest_kdata_date, get_kdata_schema, default_adjust_type
 from zvt.contract import IntervalLevel
 from zvt.contract.api import get_entities, get_entity_schema, get_entity_ids
@@ -155,19 +153,21 @@ def report_targets(
                 )
 
 
-def report_top_stats(
+def report_top_entites(
     entity_provider,
     data_provider,
-    periods=[7, 30, 365],
+    periods=None,
     ignore_new_stock=True,
     entity_type="stock",
     adjust_type=None,
     top_count=30,
     turnover_threshold=100000000,
     turnover_rate_threshold=0.02,
     em_group_over_write=True,
-    report_stats=False,
+    return_type=TopType.positive,
 ):
+    if periods is None:
+        periods = [7, 30, 365]
     if not adjust_type:
         adjust_type = default_adjust_type(entity_type=entity_type)
     kdata_schema = get_kdata_schema(entity_type=entity_type, adjust_type=adjust_type)
@@ -215,88 +215,52 @@ def report_top_stats(
 
     logger.info(f"{entity_type} filter_entity_ids size: {len(filter_entity_ids)}")
     filters = [kdata_schema.entity_id.in_(filter_entity_ids)]
-
-    stats = []
-    ups = []
-    downs = []
-
-    for period in periods:
+    for i, period in enumerate(periods):
         start = next_date(target_date, -period)
-        df, _ = get_top_performance_entities(
+        positive_df, negative_df = get_top_performance_entities(
             entity_type=entity_type,
             start_timestamp=start,
             filters=filters,
             pct=1,
             show_name=True,
             entity_provider=entity_provider,
             data_provider=data_provider,
+            return_type=return_type,
         )
-        df.rename(columns={"score": f"score_{period}"}, inplace=True)
-
-        if report_stats:
-            ups.append(tabulate(df.iloc[:top_count], headers="keys"))
-            downs.append(tabulate(df.iloc[-top_count:], headers="keys"))
 
-            stats.append(tabulate(df.describe(), headers="keys"))
+        if return_type == TopType.positive:
+            tag = "最靓仔"
+            df = positive_df
+        else:
+            tag = "谁有我惨"
+            df = negative_df
 
-        # 最近一周最靓仔的
-        if period == 7:
+        if i == 0:
             inform(
                 email_action,
                 entity_ids=df.index[:top_count].tolist(),
                 target_date=target_date,
-                title=f"{entity_type} {period}日内 最靓仔",
+                title=f"{entity_type} {period}日内 {tag}",
                 entity_provider=entity_provider,
                 entity_type=entity_type,
-                em_group="最靓仔",
+                em_group=tag,
                 em_group_over_write=em_group_over_write,
             )
-        # 最近一月最靓仔的
-        elif period == 30:
+        else:
             inform(
                 email_action,
                 entity_ids=df.index[:top_count].tolist(),
                 target_date=target_date,
-                title=f"{entity_type} {period}日内 最靓仔",
+                title=f"{entity_type} {period}日内 {tag}",
                 entity_provider=entity_provider,
                 entity_type=entity_type,
-                em_group="最靓仔",
+                em_group=tag,
                 em_group_over_write=False,
             )
 
-        # 一年内跌幅最大的
-        elif period == 365:
-            inform(
-                email_action,
-                entity_ids=df.index[-top_count:].tolist(),
-                target_date=target_date,
-                title=f"{entity_type} {period}日内 谁有我惨",
-                entity_provider=entity_provider,
-                entity_type=entity_type,
-                em_group="谁有我惨",
-                em_group_over_write=em_group_over_write,
-            )
-
-    if report_stats:
-        msg = "\n"
-        for s in stats:
-            msg = msg + s + "\n"
-        email_action.send_message(zvt_config["email_username"], f"{target_date} {entity_type}统计报告", msg)
-
-        msg = "\n"
-        for up in ups:
-            msg = msg + up + "\n"
-        email_action.send_message(zvt_config["email_username"], f"{target_date} {entity_type}涨幅统计报告", msg)
-
-        msg = "\n"
-        for down in downs:
-            msg = msg + down + "\n"
-
-        email_action.send_message(zvt_config["email_username"], f"{target_date} {entity_type}跌幅统计报告", msg)
-
 
 if __name__ == "__main__":
-    report_top_stats(
+    report_top_entites(
         entity_type="stockhk",
         entity_provider="em",
         data_provider="em",
@@ -305,4 +269,4 @@ def report_top_stats(
     )
 
 # the __all__ is generated
-__all__ = ["report_targets", "report_top_stats"]
+__all__ = ["report_targets", "report_top_entites"]

examples/reports/report_stats.py → examples/reports/report_top_stockhks.py

@@ -3,29 +3,17 @@
 
 from apscheduler.schedulers.background import BackgroundScheduler
 
-from examples.report_utils import report_top_stats
+from examples.report_utils import report_top_entites
 from zvt import init_log
 
 logger = logging.getLogger(__name__)
 
 sched = BackgroundScheduler()
 
 
-@sched.scheduled_job("cron", hour=17, minute=30, day_of_week="mon-fri")
-def report_stats():
-    report_top_stats(
-        entity_type="stock",
-        entity_provider="em",
-        data_provider="em",
-        periods=[7, 30, 365],
-        ignore_new_stock=True,
-        adjust_type=None,
-        top_count=30,
-        turnover_threshold=100000000,
-        turnover_rate_threshold=0.02,
-        em_group_over_write=True,
-    )
-    report_top_stats(
+@sched.scheduled_job("cron", hour=18, minute=30, day_of_week="mon-fri")
+def report_top_stockhks():
+    report_top_entites(
         entity_type="stockhk",
         entity_provider="em",
         data_provider="em",
@@ -40,9 +28,9 @@ def report_stats():
 
 
 if __name__ == "__main__":
-    init_log("report_stats.log")
+    init_log("report_hk_stats.log")
 
-    report_stats()
+    report_top_stockhks()
 
     sched.start()
 

examples/reports/report_top_stocks.py

@@ -0,0 +1,52 @@
+# -*- coding: utf-8 -*-
+import logging
+
+from apscheduler.schedulers.background import BackgroundScheduler
+
+from examples.report_utils import report_top_entites
+from zvt import init_log
+from zvt.api import TopType
+
+logger = logging.getLogger(__name__)
+
+sched = BackgroundScheduler()
+
+
+@sched.scheduled_job("cron", hour=17, minute=0, day_of_week="mon-fri")
+def report_top_stocks():
+    report_top_entites(
+        entity_type="stock",
+        entity_provider="em",
+        data_provider="em",
+        periods=[3, 8, 30],
+        ignore_new_stock=True,
+        adjust_type=None,
+        top_count=20,
+        turnover_threshold=400000000,
+        turnover_rate_threshold=0.02,
+        em_group_over_write=True,
+        return_type=TopType.positive,
+    )
+    report_top_entites(
+        entity_type="stock",
+        entity_provider="em",
+        data_provider="em",
+        periods=[365],
+        ignore_new_stock=True,
+        adjust_type=None,
+        top_count=30,
+        turnover_threshold=200000000,
+        turnover_rate_threshold=0.02,
+        em_group_over_write=True,
+        return_type=TopType.negative,
+    )
+
+
+if __name__ == "__main__":
+    init_log("report_top_stocks.log")
+
+    report_top_stocks()
+
+    sched.start()
+
+    sched._thread.join()

examples/reports/report_vol_up.py

@@ -34,7 +34,7 @@ def report_vol_up():
         windows=[120, 250],
         over_mode="or",
         up_intervals=60,
-        turnover_threshold=200000000,
+        turnover_threshold=300000000,
         turnover_rate_threshold=0.02,
         entity_ids=entity_ids,
     )

examples/research/top_dragon_tiger.py

@@ -0,0 +1,122 @@
+# -*- coding: utf-8 -*-
+from typing import Optional, Type, List, Union
+
+import pandas as pd
+
+from zvt.api import get_top_performance_by_month
+from zvt.api.selector import get_players
+from zvt.contract import TradableEntity, IntervalLevel, AdjustType
+from zvt.contract.factor import Transformer, Accumulator
+from zvt.domain import Stock
+from zvt.factors import TechnicalFactor
+from zvt.utils import pd_is_not_null, pre_month_start_date, next_date
+
+
+def top_dragon_and_tiger(data_provider="em", start_timestamp="2021-01-01", end_timestamp="2022-01-01"):
+    dfs = []
+    for start_date, end_date, df in get_top_performance_by_month(
+        start_timestamp=start_timestamp, end_timestamp=end_timestamp, list_days=250, data_provider=data_provider
+    ):
+        pre_month_start = pre_month_start_date(start_date)
+        for entity_id in df.index[:30]:
+            players = get_players(
+                entity_id=entity_id,
+                start_timestamp=next_date(start_date, 15),
+                end_timestamp=end_timestamp,
+                provider=data_provider,
+                direction="in",
+            )
+            print(players)
+            dfs.append(players)
+
+    player_df = pd.concat(dfs, sort=True)
+    return player_df.sort_index(level=[0, 1])
+
+
+class DragonTigerFactor(TechnicalFactor):
+    def __init__(
+        self,
+        entity_id: str,
+        entity_schema: Type[TradableEntity] = Stock,
+        provider: str = "em",
+        entity_provider: str = "em",
+        exchanges: List[str] = None,
+        codes: List[str] = None,
+        start_timestamp: Union[str, pd.Timestamp] = None,
+        end_timestamp: Union[str, pd.Timestamp] = None,
+        columns: List = None,
+        filters: List = None,
+        order: object = None,
+        limit: int = None,
+        level: Union[str, IntervalLevel] = IntervalLevel.LEVEL_1DAY,
+        category_field: str = "entity_id",
+        time_field: str = "timestamp",
+        computing_window: int = None,
+        keep_all_timestamp: bool = False,
+        fill_method: str = "ffill",
+        effective_number: int = None,
+        transformer: Transformer = None,
+        accumulator: Accumulator = None,
+        need_persist: bool = False,
+        only_compute_factor: bool = False,
+        factor_name: str = None,
+        clear_state: bool = False,
+        only_load_factor: bool = False,
+        adjust_type: Union[AdjustType, str] = None,
+    ) -> None:
+        super().__init__(
+            entity_schema,
+            provider,
+            entity_provider,
+            [entity_id],
+            exchanges,
+            codes,
+            start_timestamp,
+            end_timestamp,
+            columns,
+            filters,
+            order,
+            limit,
+            level,
+            category_field,
+            time_field,
+            computing_window,
+            keep_all_timestamp,
+            fill_method,
+            effective_number,
+            transformer,
+            accumulator,
+            need_persist,
+            only_compute_factor,
+            factor_name,
+            clear_state,
+            only_load_factor,
+            adjust_type,
+        )
+        self.player_df = get_players(
+            entity_id=entity_id,
+            start_timestamp=start_timestamp,
+            end_timestamp=end_timestamp,
+            provider="em",
+            direction="in",
+        )
+
+    def drawer_annotation_df(self) -> Optional[pd.DataFrame]:
+        def order_type_flag(df):
+            return "<br>".join(df.tolist())
+
+        if pd_is_not_null(self.player_df):
+            annotation_df = self.player_df.copy()
+            annotation_df["value"] = self.factor_df.loc[annotation_df.index]["close"]
+            annotation_df["flag"] = annotation_df[["dep1", "dep2", "dep3", "dep4", "dep5"]].apply(
+                lambda x: order_type_flag(x), axis=1
+            )
+            annotation_df["color"] = "#ff7f0e"
+            return annotation_df
+
+
+if __name__ == "__main__":
+    top_dragon_and_tiger()
+    # Stock1dHfqKdata.record_data(entity_id="stock_sz_002561", provider="em")
+    # f = DragonTigerFactor(entity_id="stock_sz_002561", provider="em")
+    # f.draw(show=True)

examples/research/top_tags.py

@@ -3,12 +3,13 @@
 from zvt.domain import Stock1dHfqKdata
 from zvt.utils import next_date, month_end_date, is_same_date
 
+
 # 每月涨幅前30，市值90%分布在100亿以下
 # 重复上榜的有1/4左右
 # 连续两个月上榜的1/10左右
 def top_tags(data_provider="em", start_timestamp="2010-01-01"):
     records = []
-    for timestamp, df in get_top_performance_by_month(
+    for _, timestamp, df in get_top_performance_by_month(
         start_timestamp=start_timestamp, list_days=250, data_provider=data_provider
     ):
         for entity_id in df.index[:30]: