Merge pull request #155 from crowdcent/feature/era-col-from-dates

Feature/era col from dates

numerblox/numerframe.py

@@ -203,6 +203,13 @@ def get_dates_from_era_col(self) -> pd.Series:
             "Era col is not 'era'. Please make sure to have a valid 'era' column to use for converting to dates."
         return self[self.meta.era_col].astype(int).apply(self.get_date_from_era)
 
+    @property
+    def get_eras_from_date_col(self) -> pd.Series:
+        """ Column of all eras from date column. """
+        assert self.meta.era_col == "date" or self.meta.era_col == "friday_date", \
+            "Era col is not 'date' or 'friday_date'. Please make sure to have a valid 'date' or 'friday_date column to use for converting to eras."
+        return self[self.meta.era_col].apply(self.get_era_from_date)
+
     def get_era_range(self, start_era: int, end_era: int) -> "NumerFrame":
         """ 
         Get all eras between two era numbers. 

numerblox/preprocessing/signals.py

@@ -288,6 +288,10 @@ def transform(
             output_df[f"{feature}_quantile{self.num_quantiles}"] = group_data
         return output_df.to_numpy()
 
+    def fit_transform(self, X: Union[np.array, pd.DataFrame], eras: pd.Series):
+        self.fit(X=X, eras=eras)
+        return self.transform(X=X, eras=eras)
+
     def get_feature_names_out(self, input_features=None) -> List[str]:
         """Return feature names."""
         if not input_features:
@@ -374,6 +378,10 @@ def transform(self, X: Union[np.array, pd.DataFrame], tickers: pd.Series) -> np.
         self.output_features = output_features
         return X[output_features].to_numpy()
 
+    def fit_transform(self, X: Union[np.array, pd.DataFrame], tickers: pd.Series):
+        self.fit(X=X, tickers=tickers)
+        return self.transform(X=X, tickers=tickers)
+
     def get_feature_names_out(self, input_features=None) -> List[str]:
         """Return feature names."""
         return self.output_features if not input_features else input_features

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "numerblox"
-version = "1.1.10"
+version = "1.1.11"
 description = "Solid Numerai Pipelines"
 authors = ["CrowdCent <[email protected]>"]
 license = "MIT License"

tests/test_numerframe.py

@@ -175,6 +175,16 @@ def test_get_dates_from_era_col():
     assert all(result.index == nf.index[:5])
     assert result.tolist() == [pd.Timestamp(ERA_ONE_START)] * len(result)
 
+def test_get_eras_from_date_col():
+    dataset_copy = dataset.copy()
+    dataset_copy['date'] = [pd.Timestamp(ERA_ONE_START) + pd.Timedelta(days=i*7) for i in range(0, len(dataset_copy))]
+    dataset_copy = dataset_copy.drop(columns="era")
+    nf = NumerFrame(dataset_copy.iloc[:5])
+    result = nf.get_eras_from_date_col
+    assert isinstance(result, pd.Series)
+    assert all(result.index == nf.index[:5])
+    assert result.tolist() == [i+1 for i in range(0, len(result))]
+
 def test_get_era_range():
     nf = NumerFrame(dataset)
     result = nf.get_era_range(start_era=1, end_era=3)