ddi-fw 0.0.44__tar.gz → 0.0.46__tar.gz

{ddi_fw-0.0.44 → ddi_fw-0.0.46}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ddi_fw
-Version: 0.0.44
+Version: 0.0.46
 Summary: Do not use :)
 Author-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
 Maintainer-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>

{ddi_fw-0.0.44 → ddi_fw-0.0.46}/pyproject.toml

@@ -5,7 +5,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "ddi_fw"
-version = "0.0.44"
+version = "0.0.46"
 description = "Do not use :)"
 readme = "README.md"
 authors = [

{ddi_fw-0.0.44 → ddi_fw-0.0.46}/src/ddi_fw/datasets/core.py

@@ -22,7 +22,14 @@ def stack(df_column):
 
 
 class BaseDataset(ABC):
-    def __init__(self,embedding_size,embedding_dict, embeddings_pooling_strategy:PoolingStrategy, ner_df, chemical_property_columns, embedding_columns, ner_columns,
+    def __init__(self,
+                 embedding_size,
+                 embedding_dict, 
+                 embeddings_pooling_strategy: PoolingStrategy, 
+                 ner_df, 
+                 chemical_property_columns, 
+                 embedding_columns, 
+                 ner_columns,
                  **kwargs):
         self.embedding_size = embedding_size
         self.embedding_dict = embedding_dict
@@ -61,7 +68,7 @@ class BaseDataset(ABC):
                           y_train_label, test_data, y_test_label])
         return items
 
-##remove this function
+# remove this function
     def generate_sim_matrices(self, chemical_properties_df, two_d_dict):
 
         jaccard_sim_dict = {}
@@ -125,7 +132,7 @@ class BaseDataset(ABC):
 
         return two_d_dict
 
-    #todo dictionary içinde ndarray dönsün
+    # todo dictionary içinde ndarray dönsün
     def generate_vectors(self, chemical_properties_df):
         self.stopwatch.reset()
         self.stopwatch.start()
@@ -144,19 +151,23 @@ class BaseDataset(ABC):
         print(f'vector_generation: {self.stopwatch.elapsed}')
 
 
-##remove this function
-    def sim(self,chemical_properties_df):
+# remove this function
+
+
+    def sim(self, chemical_properties_df):
         self.stopwatch.reset()
         self.stopwatch.start()
-        from scipy.spatial.distance import pdist        
+        from scipy.spatial.distance import pdist
         sim_matrix_gen = SimilarityMatrixGenerator()
 
         drugbank_ids = chemical_properties_df['id'].to_list()
         similarity_matrices = {}
         for column in self.__similarity_related_columns__:
-            df = pd.DataFrame(np.stack(chemical_properties_df[f'{column}_vectors'].values), index = drugbank_ids)
+            df = pd.DataFrame(np.stack(
+                chemical_properties_df[f'{column}_vectors'].values), index=drugbank_ids)
         #   similarity_matrices[column] = 1 - pdist(df.to_numpy(), metric='jaccard')
-            similarity_matrices[column] = sim_matrix_gen.create_jaccard_similarity_matrices(df.to_numpy())
+            similarity_matrices[column] = sim_matrix_gen.create_jaccard_similarity_matrices(
+                df.to_numpy())
         self.stopwatch.stop()
         print(f'sim: {self.stopwatch.elapsed}')
         return similarity_matrices
@@ -177,12 +188,14 @@ class BaseDataset(ABC):
         X = self.dataframe.drop('class', axis=1)
         y = self.dataframe['class']
         X_train, X_test, y_train, y_test = train_test_split(
-            X, y, shuffle=shuffle, test_size=test_size, stratify=np.argmax(np.vstack(y.to_numpy()),axis = 1))
+            X, y, shuffle=shuffle, test_size=test_size, stratify=np.argmax(np.vstack(y.to_numpy()), axis=1))
         # k_fold = KFold(n_splits=fold_size, shuffle=shuffle, random_state=1)
         # folds = k_fold.split(X_train)
 
-        k_fold = StratifiedKFold(n_splits=fold_size, shuffle=shuffle, random_state=1)
-        folds = k_fold.split(X_train, np.argmax(np.vstack(y_train.to_numpy()),axis = 1))
+        k_fold = StratifiedKFold(
+            n_splits=fold_size, shuffle=shuffle, random_state=1)
+        folds = k_fold.split(X_train, np.argmax(
+            np.vstack(y_train.to_numpy()), axis=1))
         train_idx_arr = []
         val_idx_arr = []
         for i, (train_index, val_index) in enumerate(folds):
@@ -269,7 +282,7 @@ class BaseDataset(ABC):
         #         lambda x: {x.id: x[f'{embedding_column}_embedding']}, axis=1)
         #     x = {k: v for l in d.values.tolist() for k, v in l.items()}
         #     embedding_dict[embedding_column] = x
- 
+
         # self.ner_df = CTakesNER().load()
         drug_names = self.drugs_df['name'].to_list()
         drug_ids = self.drugs_df['id'].to_list()
@@ -354,7 +367,7 @@ class BaseDataset(ABC):
         # def similarity_lambda_fnc(row, value):
         #     if row['id1'] in value and row['id2'] in value:
         #         return value[row['id1']][row['id2']]
-            
+
         def similarity_lambda_fnc(row, value):
             if row['id1'] in value:
                 return value[row['id1']]
@@ -366,7 +379,7 @@ class BaseDataset(ABC):
                 # return np.hstack(
                 #     (value[row['id1']], value[row['id2']]), dtype=np.float16)
 
-        def x_fnc(row, embedding_column,embeddings_after_pooling):
+        def x_fnc(row, embedding_column, embeddings_after_pooling):
             if row['id1'] in self.embedding_dict[embedding_column]:
                 v1 = embeddings_after_pooling[embedding_column][row['id1']]
             else:
@@ -387,10 +400,11 @@ class BaseDataset(ABC):
 
         for embedding_column in self.embedding_columns:
             print(f"concat {embedding_column} embeddings")
-            embeddings_after_pooling = {k: self.embeddings_pooling_strategy.apply(v) for k,v in self.embedding_dict[embedding_column].items()}
+            embeddings_after_pooling = {k: self.embeddings_pooling_strategy.apply(
+                v) for k, v in self.embedding_dict[embedding_column].items()}
             # column_embeddings_dict = embedding_values[embedding_column]
             self.ddis_df[embedding_column+'_embedding'] = self.ddis_df.apply(
-                x_fnc, args=(embedding_column,embeddings_after_pooling), axis=1)
+                x_fnc, args=(embedding_column, embeddings_after_pooling), axis=1)
 
         self.dataframe = self.ddis_df.copy()
         self.dataframe['class'] = list(classes)

{ddi_fw-0.0.44 → ddi_fw-0.0.46}/src/ddi_fw/datasets/ddi_mdl/base.py

@@ -1,6 +1,8 @@
 import pathlib
 
 import pandas as pd
+
+from ddi_fw.datasets.embedding_generator_new import PoolingStrategy
 from .. import BaseDataset
 from ..db_utils import create_connection
 
@@ -8,7 +10,7 @@ HERE = pathlib.Path(__file__).resolve().parent
 
 
 class DDIMDLDataset(BaseDataset):
-    def __init__(self, embedding_size, embedding_dict, ner_df, chemical_property_columns=['enzyme',
+    def __init__(self, embedding_size, embedding_dict,embeddings_pooling_strategy:PoolingStrategy, ner_df, chemical_property_columns=['enzyme',
                                                    'target',
                                                    'pathway',
                                                    'smile'],
@@ -16,7 +18,7 @@ class DDIMDLDataset(BaseDataset):
                  ner_columns=[],
                  **kwargs):
 
-        super().__init__(embedding_size, embedding_dict,ner_df, chemical_property_columns, embedding_columns,
+        super().__init__(embedding_size, embedding_dict,ner_df,embeddings_pooling_strategy, chemical_property_columns, embedding_columns,
                          ner_columns, **kwargs)
 
         # kwargs = {'index_path': str(HERE.joinpath('indexes'))}

{ddi_fw-0.0.44 → ddi_fw-0.0.46}/src/ddi_fw.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ddi_fw
-Version: 0.0.44
+Version: 0.0.46
 Summary: Do not use :)
 Author-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
 Maintainer-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>