Rename weighted encoding to EDGE encoding

Author: jrm5100

pandas_genomics/accessors/dataframe_accessor.py

@@ -4,7 +4,7 @@
 import numpy as np
 import pandas as pd
 
-from .utils import generate_weighted_encodings
+from .utils import calculate_edge_alphas
 from pandas_genomics.arrays import GenotypeDtype
 
 
@@ -145,10 +145,10 @@ def encode_codominant(self) -> pd.DataFrame:
             axis=1,
         )
 
-    def encode_weighted(self, encoding_info: pd.DataFrame) -> pd.DataFrame:
-        """Weighted (EDGE) encoding of genotypes.
+    def encode_edge(self, encoding_info: pd.DataFrame) -> pd.DataFrame:
+        """EDGE (weighted) encoding of genotypes.
 
-        See :meth:`GenotypeArray.encode_weighted`
+        See :meth:`GenotypeArray.encode_edge`
 
         Parameters
         ----------
@@ -221,7 +221,7 @@ def encode_weighted(self, encoding_info: pd.DataFrame) -> pd.DataFrame:
                 continue
             else:
                 try:
-                    results.append(s.genomics.encode_weighted(**info))
+                    results.append(s.genomics.encode_edge(**info))
                 except Exception as e:
                     warnings[s.array.variant.id] = str(e)
         # Print Warnings
@@ -232,14 +232,14 @@ def encode_weighted(self, encoding_info: pd.DataFrame) -> pd.DataFrame:
         # Concatenate results
         return pd.concat(results, axis=1)
 
-    def generate_weighted_encodings(
+    def calculate_edge_encoding_values(
         self,
         data: pd.DataFrame,
         outcome_variable: str,
         covariates: Optional[List[str]] = None,
     ):
         """
-        Calculate alpha values to be used in weighted encoding
+        Calculate alpha values to be used in edge encoding
 
         Parameters
         ----------
@@ -261,15 +261,15 @@ def generate_weighted_encodings(
 
         Notes
         -----
-        See [1]_ for more information about weighted encoding.
+        See [1]_ for more information about edge encoding.
 
         References
         ----------
         .. [1] Hall, Molly A., et al.
                "Novel EDGE encoding method enhances ability to identify genetic interactions."
                PLoS genetics 17.6 (2021): e1009534.
         """
-        return generate_weighted_encodings(
+        return calculate_edge_alphas(
             genotypes=self._obj.select_dtypes([GenotypeDtype]),
             data=data,
             outcome_variable=outcome_variable,

pandas_genomics/accessors/series_accessor.py

@@ -2,7 +2,7 @@
 
 import pandas as pd
 
-from .utils import generate_weighted_encodings
+from .utils import calculate_edge_alphas
 from pandas_genomics.arrays import GenotypeDtype
 
 
@@ -156,30 +156,30 @@ def encode_codominant(self) -> pd.Series:
             data=self._array.encode_codominant(), index=self._index, name=self._name
         )
 
-    def encode_weighted(
+    def encode_edge(
         self,
         alpha_value: float,
         ref_allele: str,
         alt_allele: str,
         minor_allele_freq: float,
     ) -> pd.Series:
-        """Weighted (edge) encoding of genotypes.
+        """EDGE (weighted) encoding of genotypes.
 
-        See :meth:`GenotypeArray.encode_weighted`
+        See :meth:`GenotypeArray.encode_edge`
 
         Returns
         -------
         pd.Series
         """
         return pd.Series(
-            data=self._array.encode_weighted(
+            data=self._array.encode_edge(
                 alpha_value, ref_allele, alt_allele, minor_allele_freq
             ),
             index=self._index,
             name=self._name,
         )
 
-    def generate_weighted_encodings(
+    def calculate_edge_encoding_values(
         self,
         data: pd.DataFrame,
         outcome_variable: str,
@@ -216,7 +216,7 @@ def generate_weighted_encodings(
                "Novel EDGE encoding method enhances ability to identify genetic interactions."
                PLoS genetics 17.6 (2021): e1009534.
         """
-        return generate_weighted_encodings(
+        return calculate_edge_alphas(
             genotypes=pd.Series(self._array, name=self._name, index=self._index),
             data=data,
             outcome_variable=outcome_variable,

pandas_genomics/accessors/utils/__init__.py

@@ -1 +1 @@
-from .weighted_encodings import generate_weighted_encodings
+from .edge_encoding import calculate_edge_alphas

pandas_genomics/accessors/utils/weighted_encodings.py renamed to pandas_genomics/accessors/utils/edge_encoding.py

@@ -9,14 +9,14 @@
 from pandas_genomics.arrays import GenotypeDtype
 
 
-def generate_weighted_encodings(
+def calculate_edge_alphas(
     genotypes: Union[pd.Series, pd.DataFrame],
     data: pd.DataFrame,
     outcome_variable: str,
     covariates: Optional[List[str]] = None,
 ):
     """
-    Calculate alpha values to be used in weighted encoding
+    Calculate alpha values to be used in EDGE encoding
 
     Parameters
     ----------
@@ -40,7 +40,7 @@ def generate_weighted_encodings(
 
     Notes
     -----
-    See [1]_ for more information about weighted encoding.
+    See [1]_ for more information about EDGE encoding.
 
     References
     ----------

pandas_genomics/arrays/encoding_mixin.py

@@ -86,14 +86,14 @@ def encode_codominant(self) -> pd.arrays.Categorical:
         result[(self.allele_idxs == MISSING_IDX).any(axis=1)] = None
         return result
 
-    def encode_weighted(
+    def encode_edge(
         self,
         alpha_value: float,
         ref_allele: str,
         alt_allele: str,
         minor_allele_freq: float,
     ) -> pd.DataFrame:
-        """Perform weighted (edge) encoding.
+        """Perform EDGE (weighted) encoding.
 
         Parameters
         ----------
@@ -116,7 +116,7 @@ def encode_weighted(
 
         Notes
         -----
-        See [1]_ for more information about weighted encoding.
+        See [1]_ for more information about edge encoding.
         Encoding will be based on the provided ref and alt alleles, since the alpha value would be specific to them.
         In the future, if the existing minor allele frequency differs greatly from the provided value, a warning will be issued.
 

tests/genotype_array/test_GenotypeArrayEncoding.py

@@ -177,7 +177,7 @@ def test_encoding_codominant(data_for_encoding):
 def test_encoding_weighted(
     data_for_encoding, alpha_value, ref_allele, alt_allele, minor_allele_freq, expected
 ):
-    result = data_for_encoding().encode_weighted(
+    result = data_for_encoding().encode_edge(
         alpha_value, ref_allele, alt_allele, minor_allele_freq
     )
     assert_array_equal(expected, result)
@@ -233,7 +233,7 @@ def test_encoding_weighted(
 def test_encoding_weighted_df(encoding_df, encoding_info, expected):
     df = encoding_df.copy()
     df["num"] = pd.Series(np.ones(len(df)))
-    result = df.genomics.encode_weighted(encoding_info)
+    result = df.genomics.encode_edge(encoding_info)
     assert_frame_equal(expected, result)
 
 
@@ -242,12 +242,12 @@ def test_generated_encodings_plink(genotypearray_df):
         {"phenotype": genotypearray_df.index.get_level_values("phenotype")},
         index=genotypearray_df.index,
     )
-    result_df = genotypearray_df.genomics.generate_weighted_encodings(
+    result_df = genotypearray_df.genomics.calculate_edge_encoding_values(
         data, outcome_variable="phenotype"
     )
     result_series = genotypearray_df[
         "18_nullA_18"
-    ].genomics.generate_weighted_encodings(data, outcome_variable="phenotype")
+    ].genomics.calculate_edge_encoding_values(data, outcome_variable="phenotype")
     expected = pd.DataFrame(
         {
             "Variant ID": ["nullA_18"],
@@ -320,7 +320,7 @@ def test_generated_encodings_bams(bam, expected_alphas):
     genotypes = bam.generate_case_control()
     data = genotypes["Outcome"]
     genotypes = genotypes.drop(columns="Outcome")
-    result = genotypes.genomics.generate_weighted_encodings(
+    result = genotypes.genomics.calculate_edge_encoding_values(
         data, outcome_variable="Outcome"
     )
     assert np.isclose(result["Alpha Value"], expected_alphas).all()