saving work

imports.py

@@ -74,6 +74,9 @@ geneL_ppi2      = ['alr', 'embb', 'katg']
 #%% get cols
 mycols = my_df.columns
 
+my_df['active_aa_pos'].dtype
+my_df['active_aa_pos'] = my_df['active_aa_pos'].astype(object)
+
 #%%============================================================================
 # GET Y
 

my_data9.py

@@ -59,9 +59,9 @@ f2 = preprocessor.transform(numerical_features_df)
 f3 = preprocessor.fit_transform(numerical_features_df)
 (f3==f2).all()
 
-f4 = preprocessor.fit_transform(all_features_df)
-f4
-reprocessor.fit_transform(numerical_features_df)
+preprocessor.fit_transform(numerical_features_df)
+
+#preprocessor.fit_transform(all_features_df)
 
 #%%
 model_log = Pipeline(steps = [
@@ -108,8 +108,6 @@ pd.DataFrame(output).mean()
 t1_res = MultClassPipeline2(X_trainN, X_testN, y_trainN, y_testN, input_df = all_features_df)
 t1_res
 
-t2_res = MultClassPipeline2(X_train, X_test, y_train, y_test, input_df = all_features_df)
-t2_res
 #%%
 # https://machinelearningmastery.com/columntransformer-for-numerical-and-categorical-data/
 #Each transformer is a three-element tuple that defines the name of the transformer, the transform to apply, and the column indices to apply it to. For example:
@@ -129,4 +127,8 @@ col_transform = ColumnTransformer(transformers=t
 # create pipeline (unlike example above where the col transfer was a preprocess step and it was fit_transformed)             
 
 pipeline = Pipeline(steps=[('prep', col_transform)
-                                   , ('classifier', clf)])
+                                   , ('classifier', LogisticRegression())])
+#%% Added this to the MultClassPipeline
+
+t2_res = MultClassPipeline2(X_train, X_test, y_train, y_test, input_df = all_features_df)
+t2_res