New version 1.7.4

.pre-commit-config.yaml

@@ -3,7 +3,7 @@ default_language_version:
 
 repos:
   - repo: https://github.com/charliermarsh/ruff-pre-commit
-    rev: v0.6.5
+    rev: v0.6.9
     hooks:
       - id: ruff
         args: [ --fix, --exit-non-zero-on-fix ]
@@ -24,7 +24,7 @@ repos:
       - id: python-check-blanket-noqa
       - id: python-check-blanket-type-ignore
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.6.0
+    rev: v5.0.0
     hooks:
       - id: check-ast
       - id: check-added-large-files

CHANGELOG.md

@@ -1,5 +1,13 @@
 # Changelog
 
+## Version [1.7.4] - 2024-10-06
+
+- Tightened existing checks to not allow mixed series types as methods input. The coverage level of the checks has not been widened.
+- Added pandas .ffill() as precursor to pct_change() to suppress pandas FutureWarnings in dependent projects.
+- Fixed method .resample_to_business_period_ends() so it considers renamed labels.
+- Corrected warning in this changelog for release of version 1.7.0. Added 'NO'.
+- Miscellaneous dependency and lockfile updates.
+
 ## Version [1.7.3] - 2024-09-17
 
 - Consolidated all_properties() method and its string validations.
@@ -30,7 +38,7 @@
 
 ## Version [1.7.0] - 2024-07-27
 
-- Changed code to enforce PEP 604 on typing. This means that the PACKAGE WILL LONGER WORK FOR PYTHON 3.9.
+- Changed code to enforce PEP 604 on typing. This means that the PACKAGE WILL NO LONGER WORK FOR PYTHON 3.9.
 - Limited GitHub workflow build.yaml to no longer run on Python 3.9
 - Adjustments to adhere to ruff TCH type checking imports.
 - Introduced strict requirement that generate_calendar_date_range argument trading_days must be positive.

openseries/_common_model.py

@@ -59,6 +59,7 @@
 )
 
 
+# noinspection PyTypeChecker
 class _CommonModel(BaseModel):
     """Declare _CommonModel."""
 
@@ -680,7 +681,7 @@ def to_json(
                 output.append(dict(itemdata))
 
         with dirpath.joinpath(filename).open(mode="w", encoding="utf-8") as jsonfile:
-            dump(output, jsonfile, indent=2, sort_keys=False)
+            dump(obj=output, fp=jsonfile, indent=2, sort_keys=False)
 
         return output
 
@@ -1027,7 +1028,10 @@ def arithmetic_ret_func(
             time_factor = how_many / fraction
 
         result = (
-            self.tsdf.loc[cast(int, earlier) : cast(int, later)].pct_change().mean()
+            self.tsdf.loc[cast(int, earlier) : cast(int, later)]
+            .ffill()
+            .pct_change()
+            .mean()
             * time_factor
         )
 
@@ -1085,7 +1089,7 @@ def vol_func(
             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]))

openseries/frame.py

@@ -14,7 +14,6 @@
 import statsmodels.api as sm  # type: ignore[import-untyped,unused-ignore]
 from numpy import (
     cov,
-    cumprod,
     divide,
     isinf,
     log,
@@ -336,11 +335,12 @@ def value_to_ret(self: Self) -> Self:
             The returns of the values in the series
 
         """
-        self.tsdf = self.tsdf.pct_change()
-        self.tsdf.iloc[0] = 0
+        returns = self.tsdf.ffill().pct_change()
+        returns.iloc[0] = 0
         new_labels = [ValueType.RTRN] * self.item_count
         arrays = [self.tsdf.columns.get_level_values(0), new_labels]
-        self.tsdf.columns = MultiIndex.from_arrays(arrays)
+        returns.columns = MultiIndex.from_arrays(arrays=arrays)
+        self.tsdf = returns.copy()
         return self
 
     def value_to_diff(self: Self, periods: int = 1) -> Self:
@@ -374,14 +374,20 @@ def to_cumret(self: Self) -> Self:
             An OpenFrame object
 
         """
-        if any(
-            x == ValueType.PRICE
-            for x in self.tsdf.columns.get_level_values(1).to_numpy()
-        ):
-            self.value_to_ret()
+        vtypes = [x == ValueType.RTRN for x in self.tsdf.columns.get_level_values(1)]
+        if not any(vtypes):
+            returns = self.tsdf.ffill().pct_change()
+            returns.iloc[0] = 0
+        elif all(vtypes):
+            returns = self.tsdf.copy()
+            returns.iloc[0] = 0
+        else:
+            msg = "Mix of series types will give inconsistent results"
+            raise ValueError(msg)
+
+        returns = returns.add(1.0)
+        self.tsdf = returns.cumprod(axis=0) / returns.iloc[0]
 
-        self.tsdf = self.tsdf.add(1.0)
-        self.tsdf = self.tsdf.apply(cumprod, axis="index") / self.tsdf.iloc[0]
         new_labels = [ValueType.PRICE] * self.item_count
         arrays = [self.tsdf.columns.get_level_values(0), new_labels]
         self.tsdf.columns = MultiIndex.from_arrays(arrays)
@@ -453,8 +459,15 @@ def resample_to_business_period_ends(
                 method=method,
             )
 
+        arrays = [
+            self.tsdf.columns.get_level_values(0),
+            self.tsdf.columns.get_level_values(1),
+        ]
+
         self._set_tsdf()
 
+        self.tsdf.columns = MultiIndex.from_arrays(arrays)
+
         return self
 
     def ewma_risk(
@@ -1284,30 +1297,8 @@ def jensen_alpha(  # noqa: C901
 
         """
         full_year = 1.0
-        if all(
-            x == ValueType.RTRN
-            for x in self.tsdf.columns.get_level_values(1).to_numpy()
-        ):
-            msg = "asset should be a tuple[str, ValueType] or an integer."
-            if isinstance(asset, tuple):
-                asset_log = self.tsdf.loc[:, asset]
-                asset_cagr = asset_log.mean()
-            elif isinstance(asset, int):
-                asset_log = self.tsdf.iloc[:, asset]
-                asset_cagr = asset_log.mean()
-            else:
-                raise TypeError(msg)
-
-            msg = "market should be a tuple[str, ValueType] or an integer."
-            if isinstance(market, tuple):
-                market_log = self.tsdf.loc[:, market]
-                market_cagr = market_log.mean()
-            elif isinstance(market, int):
-                market_log = self.tsdf.iloc[:, market]
-                market_cagr = market_log.mean()
-            else:
-                raise TypeError(msg)
-        else:
+        vtypes = [x == ValueType.RTRN for x in self.tsdf.columns.get_level_values(1)]
+        if not any(vtypes):
             msg = "asset should be a tuple[str, ValueType] or an integer."
             if isinstance(asset, tuple):
                 asset_log = log(
@@ -1375,6 +1366,29 @@ def jensen_alpha(  # noqa: C901
                     )
             else:
                 raise TypeError(msg)
+        elif all(vtypes):
+            msg = "asset should be a tuple[str, ValueType] or an integer."
+            if isinstance(asset, tuple):
+                asset_log = self.tsdf.loc[:, asset]
+                asset_cagr = asset_log.mean()
+            elif isinstance(asset, int):
+                asset_log = self.tsdf.iloc[:, asset]
+                asset_cagr = asset_log.mean()
+            else:
+                raise TypeError(msg)
+
+            msg = "market should be a tuple[str, ValueType] or an integer."
+            if isinstance(market, tuple):
+                market_log = self.tsdf.loc[:, market]
+                market_cagr = market_log.mean()
+            elif isinstance(market, int):
+                market_log = self.tsdf.iloc[:, market]
+                market_cagr = market_log.mean()
+            else:
+                raise TypeError(msg)
+        else:
+            msg = "Mix of series types will give inconsistent results"
+            raise ValueError(msg)
 
         covariance = cov(asset_log, market_log, ddof=dlta_degr_freedms)
         beta = covariance[0, 1] / covariance[1, 1]
@@ -1407,27 +1421,30 @@ def make_portfolio(
                 "to run the make_portfolio method."
             )
             raise ValueError(msg)
-        dframe = self.tsdf.copy()
-        if not any(
-            x == ValueType.RTRN
-            for x in self.tsdf.columns.get_level_values(1).to_numpy()
-        ):
-            dframe = dframe.pct_change()
-            dframe.iloc[0] = 0
+
+        vtypes = [x == ValueType.RTRN for x in self.tsdf.columns.get_level_values(1)]
+        if not any(vtypes):
+            returns = self.tsdf.ffill().pct_change()
+            returns.iloc[0] = 0
+        elif all(vtypes):
+            returns = self.tsdf.copy()
+        else:
+            msg = "Mix of series types will give inconsistent results"
+            raise ValueError(msg)
 
         msg = "Weight strategy not implemented"
         if weight_strat:
             if weight_strat == "eq_weights":
                 self.weights = [1.0 / self.item_count] * self.item_count
             elif weight_strat == "inv_vol":
-                vol = divide(1.0, std(dframe, axis=0, ddof=1))
+                vol = divide(1.0, std(returns, axis=0, ddof=1))
                 vol[isinf(vol)] = nan
                 self.weights = list(divide(vol, vol.sum()))
             else:
                 raise NotImplementedError(msg)
 
         return DataFrame(
-            data=(dframe @ self.weights).add(1.0).cumprod(),
+            data=(returns @ self.weights).add(1.0).cumprod(),
             index=self.tsdf.index,
             columns=[[name], [ValueType.PRICE]],
             dtype="float64",

openseries/portfoliotools.py

@@ -83,13 +83,15 @@ def simulate_portfolios(
     """
     copi = simframe.from_deepcopy()
 
-    if any(
-        x == ValueType.PRICE for x in copi.tsdf.columns.get_level_values(1).to_numpy()
-    ):
+    vtypes = [x == ValueType.RTRN for x in copi.tsdf.columns.get_level_values(1)]
+    if not any(vtypes):
         copi.value_to_ret()
         log_ret = copi.tsdf.copy()[1:]
-    else:
+    elif all(vtypes):
         log_ret = copi.tsdf.copy()
+    else:
+        msg = "Mix of series types will give inconsistent results"
+        raise ValueError(msg)
 
     log_ret.columns = log_ret.columns.droplevel(level=1)
 
@@ -165,13 +167,15 @@ def efficient_frontier(  # noqa: C901
 
     copi = eframe.from_deepcopy()
 
-    if any(
-        x == ValueType.PRICE for x in copi.tsdf.columns.get_level_values(1).to_numpy()
-    ):
+    vtypes = [x == ValueType.RTRN for x in copi.tsdf.columns.get_level_values(1)]
+    if not any(vtypes):
         copi.value_to_ret()
         log_ret = copi.tsdf.copy()[1:]
-    else:
+    elif all(vtypes):
         log_ret = copi.tsdf.copy()
+    else:
+        msg = "Mix of series types will give inconsistent results"
+        raise ValueError(msg)
 
     log_ret.columns = log_ret.columns.droplevel(level=1)
 

openseries/series.py

@@ -346,6 +346,7 @@ def from_fixed_rate(
                 - cast(DatetimeIndex, d_range)[:-1]
             ],
         )
+        # noinspection PyTypeChecker
         arr = list(cumprod(insert(1 + deltas * rate / 365, 0, 1.0)))
         dates = [d.strftime("%Y-%m-%d") for d in cast(DatetimeIndex, d_range)]
 
@@ -434,15 +435,12 @@ def value_to_ret(self: Self) -> Self:
             The returns of the values in the series
 
         """
-        self.tsdf = self.tsdf.pct_change()
-        self.tsdf.iloc[0] = 0
+        returns = self.tsdf.ffill().pct_change()
+        returns.iloc[0] = 0
         self.valuetype = ValueType.RTRN
-        self.tsdf.columns = MultiIndex.from_arrays(
-            [
-                [self.label],
-                [self.valuetype],
-            ],
-        )
+        arrays = [[self.label], [self.valuetype]]
+        returns.columns = MultiIndex.from_arrays(arrays=arrays)
+        self.tsdf = returns.copy()
         return self
 
     def value_to_diff(self: Self, periods: int = 1) -> Self:
@@ -480,14 +478,12 @@ def to_cumret(self: Self) -> Self:
             An OpenTimeSeries object
 
         """
-        if not any(
-            x == ValueType.RTRN
-            for x in cast(MultiIndex, self.tsdf.columns).get_level_values(1).to_numpy()
-        ):
+        if self.valuetype == ValueType.PRICE:
             self.value_to_ret()
 
         self.tsdf = self.tsdf.add(1.0)
         self.tsdf = self.tsdf.cumprod(axis=0) / self.tsdf.iloc[0]
+
         self.valuetype = ValueType.PRICE
         self.tsdf.columns = MultiIndex.from_arrays(
             [
@@ -520,6 +516,7 @@ def from_1d_rate_to_cumret(
         arr = array(self.values) / divider
 
         deltas = array([i.days for i in self.tsdf.index[1:] - self.tsdf.index[:-1]])
+        # noinspection PyTypeChecker
         arr = cumprod(insert(1.0 + deltas * arr[:-1] / days_in_year, 0, 1.0))
 
         self.dates = [d.strftime("%Y-%m-%d") for d in self.tsdf.index]
@@ -684,11 +681,7 @@ def running_adjustment(
             An OpenTimeSeries object
 
         """
-        values: list[float]
-        if any(
-            x == ValueType.RTRN
-            for x in cast(MultiIndex, self.tsdf.columns).get_level_values(1).to_numpy()
-        ):
+        if self.valuetype == ValueType.RTRN:
             ra_df = self.tsdf.copy()
             values = [1.0]
             returns_input = True
@@ -818,6 +811,7 @@ def timeseries_chain(
 
     dates.extend([x.strftime("%Y-%m-%d") for x in new.tsdf.index])
 
+    # noinspection PyUnresolvedReferences
     if back.__class__.__subclasscheck__(
         OpenTimeSeries,
     ):