added MultClassPipe2 that has one hot encoder step to the pipeline

my_data9.py

@@ -7,7 +7,12 @@ Created on Sat Mar  5 12:57:32 2022
 """
 #%%
 # data, etc for now  comes from my_data6.py and/or my_data5.py
+#%%
+homedir = os.path.expanduser("~")
+os.chdir(homedir + "/git/ML_AI_training/")
 
+# my function
+from MultClassPipe2 import MultClassPipeline2 
 #%% try combinations
 #import sys, os
 #os.system("imports.py")
@@ -45,11 +50,19 @@ X_train, X_test, y_train, y_test = train_test_split(all_features_df,
 preprocessor = ColumnTransformer(
     transformers=[
         ('num', MinMaxScaler()  , numerical_features_names)
-        #,('cat', OneHotEncoder(), categorical_features_names)
-        ])
+        ,('cat', OneHotEncoder(), categorical_features_names)
+        ], remainder = 'passthrough')
+
+f = preprocessor.fit(numerical_features_df)
+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(numerical_features_df)
-preprocessor.transform(numerical_features_df)
 #%%
 model_log = Pipeline(steps = [
     ('preprocess', preprocessor)
@@ -90,21 +103,30 @@ output = cross_validate(model, X_trainN, y_trainN
                         , cv = 10
                         , return_train_score = False)
 pd.DataFrame(output).mean()
+#%% Run multiple models using MultClassPipeline
+# only good for numerical features as categ features is not supported yet!
+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:
+# (Name, Object, Columns)
 
-selector_logistic = RFECV(estimator = model
-                       , cv = 10
-                       , step = 1)
+# Determine categorical and numerical features
+numerical_ix = all_features_df.select_dtypes(include=['int64', 'float64']).columns
+numerical_ix
+categorical_ix = all_features_df.select_dtypes(include=['object', 'bool']).columns
+categorical_ix
 
-X_trainN, X_testN, y_trainN, y_testN = train_test_split(numerical_features_df 
-                                                    , target1 
-                                                    , test_size = 0.33
-                                                    , random_state = 42)
+# Define the data preparation for the columns
+t = [('cat', OneHotEncoder(), categorical_ix)
+     , ('num', MinMaxScaler(), numerical_ix)]
+col_transform = ColumnTransformer(transformers=t
+                                  , remainder='passthrough')
+# create pipeline (unlike example above where the col transfer was a preprocess step and it was fit_transformed)             
 
-selector_logistic_xtrain = selector_logistic.fit_transform(X_trainN, y_trainN)
-print(sel_rfe_logistic.get_support())
-X_trainN.columns
-
-print(sel_rfe_logistic.ranking_)
+pipeline = Pipeline(steps=[('prep', col_transform)
+                                   , ('classifier', clf)])