openseries 1.9.3__py3-none-any.whl → 1.9.5__py3-none-any.whl

openseries/_common_model.py

@@ -7,7 +7,6 @@ https://github.com/CaptorAB/openseries/blob/master/LICENSE.md
 SPDX-License-Identifier: BSD-3-Clause
 """
 
-# mypy: disable-error-code="no-any-return"
 from __future__ import annotations
 
 import datetime as dt
@@ -25,7 +24,9 @@ from .owntypes import (
     DateAlignmentError,
     InitialValueZeroError,
     NumberOfItemsAndLabelsNotSameError,
+    ResampleDataLossError,
     Self,
+    ValueType,
 )
 
 if TYPE_CHECKING:  # pragma: no cover
@@ -47,7 +48,6 @@ if TYPE_CHECKING:  # pragma: no cover
         LiteralPlotlyJSlib,
         LiteralPlotlyOutput,
         LiteralQuantileInterp,
-        ValueType,
     )
 from openpyxl.utils.dataframe import dataframe_to_rows
 from openpyxl.workbook.workbook import Workbook
@@ -66,7 +66,7 @@ from plotly.graph_objs import Figure  # type: ignore[import-untyped]
 from plotly.io import to_html  # type: ignore[import-untyped]
 from plotly.offline import plot  # type: ignore[import-untyped]
 from pydantic import BaseModel, ConfigDict, DirectoryPath, ValidationError
-from scipy.stats import (  # type: ignore[import-untyped]
+from scipy.stats import (
     kurtosis,
     norm,
     skew,
@@ -432,7 +432,17 @@ class _CommonModel(BaseModel):  # type: ignore[misc]
 
         wmdf = wmdf.reindex(index=[deyt.date() for deyt in dates], method=method)
         wmdf.index = DatetimeIndex(wmdf.index)
-        result = wmdf.pct_change().min()
+
+        vtypes = [x == ValueType.RTRN for x in wmdf.columns.get_level_values(1)]
+        if any(vtypes):
+            msg = (
+                "Do not run worst_month on return series. The operation will "
+                "pick the last data point in the sparser series. It will not sum "
+                "returns and therefore data will be lost and result will be wrong."
+            )
+            raise ResampleDataLossError(msg)
+
+        result = wmdf.ffill().pct_change().min()
 
         if self.tsdf.shape[1] == 1:
             return float(result.iloc[0])
@@ -1305,6 +1315,7 @@ class _CommonModel(BaseModel):  # type: ignore[misc]
 
         result = (
             self.tsdf.loc[cast("int", earlier) : cast("int", later)]
+            .ffill()
             .pct_change()
             .mean()
             * time_factor
@@ -1366,7 +1377,7 @@ class _CommonModel(BaseModel):  # type: ignore[misc]
             time_factor = how_many / fraction
 
         data = self.tsdf.loc[cast("int", earlier) : cast("int", later)]
-        result = data.pct_change().std().mul(sqrt(time_factor))
+        result = data.ffill().pct_change().std().mul(sqrt(time_factor))
 
         if self.tsdf.shape[1] == 1:
             return float(cast("SupportsFloat", result.iloc[0]))
@@ -1564,21 +1575,24 @@ class _CommonModel(BaseModel):  # type: ignore[misc]
         if drift_adjust:
             imp_vol = (-sqrt(time_factor) / norm.ppf(level)) * (
                 self.tsdf.loc[cast("int", earlier) : cast("int", later)]
+                .ffill()
                 .pct_change()
                 .quantile(1 - level, interpolation=interpolation)
                 - self.tsdf.loc[cast("int", earlier) : cast("int", later)]
+                .ffill()
                 .pct_change()
                 .sum()
                 / len(
-                    self.tsdf.loc[
-                        cast("int", earlier) : cast("int", later)
-                    ].pct_change(),
+                    self.tsdf.loc[cast("int", earlier) : cast("int", later)]
+                    .ffill()
+                    .pct_change(),
                 )
             )
         else:
             imp_vol = (
                 -sqrt(time_factor)
                 * self.tsdf.loc[cast("int", earlier) : cast("int", later)]
+                .ffill()
                 .pct_change()
                 .quantile(1 - level, interpolation=interpolation)
                 / norm.ppf(level)
@@ -1643,15 +1657,16 @@ class _CommonModel(BaseModel):  # type: ignore[misc]
             deep=True
         )
         result = [
-            cvar_df.loc[:, x]  # type: ignore[call-overload,index]
+            cvar_df.loc[:, x]  # type: ignore[call-overload]
+            .ffill()
             .pct_change()
             .sort_values()
             .iloc[
                 : ceil(
-                    (1 - level)
-                    * cvar_df.loc[:, x]  # type: ignore[index]
-                    .pct_change()
-                    .count(),
+                    cast(
+                        "int",
+                        (1 - level) * cvar_df.loc[:, x].ffill().pct_change().count(),
+                    )
                 ),
             ]
             .mean()
@@ -1718,6 +1733,7 @@ class _CommonModel(BaseModel):  # type: ignore[misc]
 
         how_many = (
             self.tsdf.loc[cast("int", earlier) : cast("int", later)]
+            .ffill()
             .pct_change()
             .count(numeric_only=True)
         )
@@ -1734,6 +1750,7 @@ class _CommonModel(BaseModel):  # type: ignore[misc]
         per_period_mar = min_accepted_return / time_factor
         diff = (
             self.tsdf.loc[cast("int", earlier) : cast("int", later)]
+            .ffill()
             .pct_change()
             .sub(per_period_mar)
         )
@@ -1788,12 +1805,7 @@ class _CommonModel(BaseModel):  # type: ignore[misc]
         )
         fraction = (later - earlier).days / 365.25
 
-        any_below_zero = any(
-            self.tsdf.loc[[earlier, later]]  # type: ignore[index]
-            .lt(0.0)
-            .any()
-            .to_numpy()
-        )
+        any_below_zero = any(self.tsdf.loc[[earlier, later]].lt(0.0).any().to_numpy())
         if zero in self.tsdf.loc[earlier].to_numpy() or any_below_zero:
             msg = (
                 "Geometric return cannot be calculated due to "
@@ -1845,6 +1857,7 @@ class _CommonModel(BaseModel):  # type: ignore[misc]
         )
         result: NDArray[float64] = skew(
             a=self.tsdf.loc[cast("int", earlier) : cast("int", later)]
+            .ffill()
             .pct_change()
             .to_numpy(),
             bias=True,
@@ -1892,7 +1905,11 @@ class _CommonModel(BaseModel):  # type: ignore[misc]
             to_dt=to_date,
         )
         result: NDArray[float64] = kurtosis(
-            a=(self.tsdf.loc[cast("int", earlier) : cast("int", later)].pct_change()),
+            a=(
+                self.tsdf.loc[cast("int", earlier) : cast("int", later)]
+                .ffill()
+                .pct_change()
+            ),
             fisher=True,
             bias=True,
             nan_policy="omit",
@@ -1988,16 +2005,18 @@ class _CommonModel(BaseModel):  # type: ignore[misc]
         )
         pos = (
             self.tsdf.loc[cast("int", earlier) : cast("int", later)]
+            .ffill()
             .pct_change()[1:][
-                self.tsdf.loc[cast("int", earlier) : cast("int", later)].pct_change()[
-                    1:
-                ]
+                self.tsdf.loc[cast("int", earlier) : cast("int", later)]
+                .ffill()
+                .pct_change()[1:]
                 > zero
             ]
             .count()
         )
         tot = (
             self.tsdf.loc[cast("int", earlier) : cast("int", later)]
+            .ffill()
             .pct_change()
             .count()
         )
@@ -2184,7 +2203,11 @@ class _CommonModel(BaseModel):  # type: ignore[misc]
             from_dt=from_date,
             to_dt=to_date,
         )
-        retdf = self.tsdf.loc[cast("int", earlier) : cast("int", later)].pct_change()
+        retdf = (
+            self.tsdf.loc[cast("int", earlier) : cast("int", later)]
+            .ffill()
+            .pct_change()
+        )
         pos = retdf[retdf > min_accepted_return].sub(min_accepted_return).sum()
         neg = retdf[retdf < min_accepted_return].sub(min_accepted_return).sum()
         ratio = pos / -neg
@@ -2272,7 +2295,7 @@ class _CommonModel(BaseModel):  # type: ignore[misc]
             period = "-".join([str(year), str(month).zfill(2)])
         vrdf = self.tsdf.copy()
         vrdf.index = DatetimeIndex(vrdf.index)
-        resultdf = DataFrame(vrdf.pct_change())
+        resultdf = DataFrame(vrdf.ffill().pct_change())
         result = resultdf.loc[period] + 1
         cal_period = result.cumprod(axis="index").iloc[-1] - 1
         if self.tsdf.shape[1] == 1:
@@ -2324,6 +2347,7 @@ class _CommonModel(BaseModel):  # type: ignore[misc]
         )
         result = (
             self.tsdf.loc[cast("int", earlier) : cast("int", later)]
+            .ffill()
             .pct_change()
             .quantile(1 - level, interpolation=interpolation)
         )
@@ -2372,6 +2396,7 @@ class _CommonModel(BaseModel):  # type: ignore[misc]
         )
         result = (
             self.tsdf.loc[cast("int", earlier) : cast("int", later)]
+            .ffill()
             .pct_change()
             .rolling(observations, min_periods=observations)
             .sum()
@@ -2418,9 +2443,11 @@ class _CommonModel(BaseModel):  # type: ignore[misc]
             from_dt=from_date,
             to_dt=to_date,
         )
-        zscframe = self.tsdf.loc[
-            cast("int", earlier) : cast("int", later)
-        ].pct_change()
+        zscframe = (
+            self.tsdf.loc[cast("int", earlier) : cast("int", later)]
+            .ffill()
+            .pct_change()
+        )
         result = (zscframe.iloc[-1] - zscframe.mean()) / zscframe.std()
 
         if self.tsdf.shape[1] == 1:
@@ -2489,6 +2516,7 @@ class _CommonModel(BaseModel):  # type: ignore[misc]
         ret_label = cast("tuple[str]", self.tsdf.iloc[:, column].name)[0]
         retseries = (
             Series(self.tsdf.iloc[:, column])
+            .ffill()
             .pct_change()
             .rolling(observations, min_periods=observations)
             .sum()

openseries/datefixer.py

@@ -12,7 +12,7 @@ from __future__ import annotations
 import datetime as dt
 from typing import TYPE_CHECKING, cast
 
-import exchange_calendars as exchcal
+import exchange_calendars as exchcal  # type: ignore[import-untyped]
 from dateutil.relativedelta import relativedelta
 from holidays import (
     country_holidays,
@@ -163,7 +163,7 @@ def holiday_calendar(
         custom_list = (
             [custom_holidays]
             if isinstance(custom_holidays, str)
-            else list(custom_holidays)  # type: ignore[arg-type]
+            else list(custom_holidays)
         )
         hols.extend([date_fix(fixerdate=ddate) for ddate in custom_list])
 
@@ -255,7 +255,7 @@ def date_offset_foll(
         while not is_busday(dates=new_date, busdaycal=calendar):
             new_date += day_delta
 
-    return new_date  # type: ignore[no-any-return]
+    return new_date
 
 
 def get_previous_business_day_before_today(
@@ -505,7 +505,7 @@ def _do_resample_to_business_period_ends(
     dates = DatetimeIndex(
         [copydata.index[0]]
         + [
-            date_offset_foll(  # type: ignore[misc]
+            date_offset_foll(
                 raw_date=dt.date(d.year, d.month, 1)
                 + relativedelta(months=1)
                 - dt.timedelta(days=1),