Create data_transformer.py

projects/DAPIO/data-processing/preprocessing/data_transformer.py

@@ -0,0 +1,33 @@
+import pandas as pd
+from sklearn.compose import ColumnTransformer
+from sklearn.pipeline import Pipeline
+from sklearn.impute import SimpleImputer
+from sklearn.preprocessing import OneHotEncoder
+
+class DataTransformer:
+    def __init__(self, data: pd.DataFrame):
+        self.data = data
+
+    def create_pipeline(self) -> Pipeline:
+        numeric_features = self.data.select_dtypes(include=['int64', 'float64']).columns
+        categorical_features = self.data.select_dtypes(include=['object']).columns
+
+        numeric_transformer = Pipeline(steps=[
+            ('imputer', SimpleImputer(strategy='median')),
+            ('scaler', StandardScaler())])
+
+        categorical_transformer = Pipeline(steps=[
+            ('imputer', SimpleImputer(strategy='constant', fill_value='missing')),
+            ('onehot', OneHotEncoder(handle_unknown='ignore'))])
+
+        preprocessor = ColumnTransformer(
+            transformers=[
+                ('num', numeric_transformer, numeric_features),
+                ('cat', categorical_transformer, categorical_features)])
+
+        return preprocessor
+
+    def transform_data(self) -> pd.DataFrame:
+        preprocessor = self.create_pipeline()
+        self.data = preprocessor.fit_transform(self.data)
+        return self.data