changed format of columns

.gitignore

@@ -8,4 +8,3 @@ __pycache__/
 env/
 venv/
 .machine_learning/
-

app_old.py

@@ -0,0 +1,191 @@
+import streamlit as st
+import pandas as pd
+import joblib
+
+def create_dataframe_from_user_input():
+    """
+    Collects user input for house features using Streamlit and
+    returns a Pandas DataFrame.  The input fields are organized
+    into categorized sections for better usability.
+    """
+
+    # Define the lists of possible values for dropdown selections
+    type_list = ['HOUSE', 'APARTMENT']
+    subtype_list = ['HOUSE', 'APARTMENT', 'VILLA', 'APARTMENT_BLOCK', 'APARTMENT_GROUP',
+                     'MIXED_USE_BUILDING', 'GROUND_FLOOR', 'DUPLEX', 'HOUSE_GROUP',
+                     'FLAT_STUDIO', 'PENTHOUSE', 'EXCEPTIONAL_PROPERTY', 'MANSION',
+                     'TOWN_HOUSE', 'SERVICE_FLAT', 'BUNGALOW', 'KOT', 'COUNTRY_COTTAGE',
+                     'FARMHOUSE', 'LOFT', 'CHALET', 'TRIPLEX', 'CASTLE', 'OTHER_PROPERTY',
+                     'MANOR_HOUSE', 'PAVILION']
+    province_list = ['West Flanders', 'Antwerp', 'East Flanders', 'Brussels', 'Hainaut',
+                     'Liège', 'Flemish Brabant', 'Limburg', 'Walloon Brabant', 'Namur',
+                     'Luxembourg']
+    building_condition_list = ['GOOD', 'AS_NEW', 'TO_RENOVATE', 'TO_BE_DONE_UP',
+                               'JUST_RENOVATED', 'TO_RESTORE']
+    flood_zone_type_list = ['NON_FLOOD_ZONE', 'POSSIBLE_FLOOD_ZONE', 'RECOGNIZED_FLOOD_ZONE',
+                            'RECOGNIZED_N_CIRCUMSCRIBED_FLOOD_ZONE', 'CIRCUMSCRIBED_WATERSIDE_ZONE',
+                            'CIRCUMSCRIBED_FLOOD_ZONE', 'POSSIBLE_N_CIRCUMSCRIBED_FLOOD_ZONE',
+                            'POSSIBLE_N_CIRCUMSCRIBED_WATERSIDE_ZONE', 'RECOGNIZED_N_CIRCUMSCRIBED_WATERSIDE_ZONE']
+    heating_type_list = ['GAS', 'FUELOIL', 'ELECTRIC', 'PELLET', 'WOOD', 'SOLAR', 'CARBON']
+    kitchen_type_list = ['INSTALLED', 'HYPER_EQUIPPED', 'SEMI_EQUIPPED', 'NOT_INSTALLED',
+                         'USA_HYPER_EQUIPPED', 'USA_INSTALLED', 'USA_SEMI_EQUIPPED',
+                         'USA_UNINSTALLED']
+    garden_orientation_list = ['SOUTH', 'SOUTH_WEST', 'SOUTH_EAST', 'WEST', 'EAST',
+                               'NORTH_WEST', 'NORTH_EAST', 'NORTH']
+    terrace_orientation_list = ['SOUTH', 'SOUTH_WEST', 'SOUTH_EAST', 'WEST', 'EAST',
+                               'NORTH_WEST', 'NORTH_EAST', 'NORTH']
+    epc_score_list = ['B', 'C', 'D', 'A', 'F', 'E', 'G', 'A+', 'A++']
+
+    # Create Streamlit input fields
+    st.header("Enter House Information")
+
+    # --- Property Details ---
+    st.subheader("Property Details")
+    col1, col2 = st.columns(2)
+    with col1:
+        property_type = st.selectbox("Property Type", type_list, key='type')
+        property_subtype = st.selectbox("Subtype", subtype_list, key='subtype')
+        province = st.selectbox("Province", province_list, key='province')
+        locality = st.text_input("Locality", key='locality')
+        post_code = st.number_input("Post Code", min_value=1000, max_value=9999, step=1, key='postCode')
+    with col2:
+        building_condition = st.selectbox("Building Condition", building_condition_list, key='buildingCondition')
+        building_construction_year = st.number_input("Building Construction Year", min_value=1000, max_value=2024, step=1, key='buildingConstructionYear')
+        facade_count = st.number_input("Facade Count", min_value=0, step=1, key='facadeCount')
+        floor_count = st.number_input("Floor Count", min_value=0, step=1, key='floorCount')
+        flood_zone_type = st.selectbox("Flood Zone Type", flood_zone_type_list, key='floodZoneType')
+        epc_score = st.selectbox("EPC Score", epc_score_list, key='epcScore')
+
+    # --- Room Information ---
+    st.subheader("Room Information")
+    col3, col4 = st.columns(2)
+    with col3:
+        bedroom_count = st.number_input("Bedroom Count", min_value=0, step=1, key='bedroomCount')
+        bathroom_count = st.number_input("Bathroom Count", min_value=0, step=1, key='bathroomCount')
+        room_count = st.number_input("Room Count", min_value=0, step=1, key='roomCount')
+        has_attic = st.selectbox("Has Attic", ['Yes', 'No'], key='hasAttic')
+        has_basement = st.selectbox("Has Basement", ['Yes', 'No'], key='hasBasement')
+        has_dressing_room = st.selectbox("Has Dressing Room", ['Yes', 'No'], key='hasDressingRoom')
+        has_dining_room = st.selectbox("Has Dining Room", ['Yes', 'No'], key='hasDiningRoom')
+        dining_room_surface = st.number_input("Dining Room Surface (sqm)", min_value=0.0, key='diningRoomSurface')
+    with col4:
+        has_living_room = st.selectbox("Has Living Room", ['Yes', 'No'], key='hasLivingRoom')
+        living_room_surface = st.number_input("Living Room Surface (sqm)", min_value=0.0, key='livingRoomSurface')
+        kitchen_surface = st.number_input("Kitchen Surface (sqm)", min_value=0.0, key='kitchenSurface')
+        kitchen_type = st.selectbox("Kitchen Type", kitchen_type_list, key='kitchenType')
+        toilet_count = st.number_input("Toilet Count", min_value=0, step=1, key='toiletCount')
+        has_office = st.selectbox("Has Office", ['Yes', 'No'], key='hasOffice')
+        has_lift = st.selectbox("Has Lift", ['Yes', 'No'], key='hasLift')
+
+    # --- Surface Areas ---
+    st.subheader("Surface Areas")
+    col5, col6 = st.columns(2)
+    with col5:
+        habitable_surface = st.number_input("Habitable Surface (sqm)", min_value=0.0, key='habitableSurface')
+        land_surface = st.number_input("Land Surface (sqm)", min_value=0.0, key='landSurface')
+        garden_surface = st.number_input("Garden Surface (sqm)", min_value=0.0, key='gardenSurface')
+    with col6:
+        terrace_surface = st.number_input("Terrace Surface (sqm)", min_value=0.0, key='terraceSurface')
+        street_facade_width = st.number_input("Street Facade Width (m)", min_value=0.0, key='streetFacadeWidth')
+        monthly_cost = st.number_input("Monthly Cost (€)", min_value=0.0, key='monthlyCost')
+
+    # --- Outdoor Features ---
+    st.subheader("Outdoor Features")
+    col7, col8 = st.columns(2)
+    with col7:
+        has_garden = st.selectbox("Has Garden", ['Yes', 'No'], key='hasGarden')
+        garden_orientation = st.selectbox("Garden Orientation", garden_orientation_list, key='gardenOrientation')
+        has_balcony = st.selectbox("Has Balcony", ['Yes', 'No'], key='hasBalcony')
+        has_terrace = st.selectbox("Has Terrace", ['Yes', 'No'], key='hasTerrace')
+        terrace_orientation = st.selectbox("Terrace Orientation", terrace_orientation_list, key='terraceOrientation')
+    with col8:
+        parking_count_indoor = st.number_input("Indoor Parking Count", min_value=0, step=1, key='parkingCountIndoor')
+        parking_count_outdoor = st.number_input("Outdoor Parking Count", min_value=0, step=1, key='parkingCountOutdoor')
+        has_swimming_pool = st.selectbox("Has Swimming Pool", ['Yes', 'No'], key='hasSwimmingPool')
+
+    # --- Additional Features ---
+    st.subheader("Additional Features")
+    col9, col10 = st.columns(2)
+    with col9:
+        heating_type = st.selectbox("Heating Type", heating_type_list, key='heatingType')
+        has_heat_pump = st.selectbox("Has Heat Pump", ['Yes', 'No'], key='hasHeatPump')
+        has_photovoltaic_panels = st.selectbox("Has Photovoltaic Panels", ['Yes', 'No'], key='hasPhotovoltaicPanels')
+        has_thermic_panels = st.selectbox("Has Thermic Panels", ['Yes', 'No'], key='hasThermicPanels')
+    with col10:
+        has_air_conditioning = st.selectbox("Has Air Conditioning", ['Yes', 'No'], key='hasAirConditioning')
+        has_armored_door = st.selectbox("Has Armored Door", ['Yes', 'No'], key='hasArmoredDoor')
+        has_visiophone = st.selectbox("Has Visiophone", ['Yes', 'No'], key='hasVisiophone')
+        has_fireplace = st.selectbox("Has Fireplace", ['Yes', 'No'], key='hasFireplace')
+        accessible_disabled_people = st.selectbox("Accessible Disabled People", ['True', 'False'], key='accessibleDisabledPeople')
+
+    # Create a button to trigger DataFrame creation
+    if st.button("Predict"):
+        # Create the DataFrame
+        data = {
+            'type': property_type,
+            'subtype': property_subtype,
+            'bedroomCount': bedroom_count,
+            'bathroomCount': bathroom_count,
+            'province': province,
+            'locality': locality,
+            'postCode': post_code,
+            'habitableSurface': habitable_surface,
+            'roomCount': room_count,
+            'monthlyCost': monthly_cost,
+            'hasAttic': has_attic == 'Yes',
+            'hasBasement': has_basement == 'Yes',
+            'hasDressingRoom': has_dressing_room == 'Yes',
+            'diningRoomSurface': dining_room_surface,
+            'hasDiningRoom': has_dining_room == 'Yes',
+            'buildingCondition': building_condition,
+            'buildingConstructionYear': building_construction_year,
+            'facadeCount': facade_count,
+            'floorCount': floor_count,
+            'streetFacadeWidth': street_facade_width,
+            'hasLift': has_lift == 'Yes',
+            'floodZoneType': flood_zone_type,
+            'heatingType': heating_type,
+            'hasHeatPump': has_heat_pump == 'Yes',
+            'hasPhotovoltaicPanels': has_photovoltaic_panels == 'Yes',
+            'hasThermicPanels': has_thermic_panels == 'Yes',
+            'kitchenSurface': kitchen_surface,
+            'kitchenType': kitchen_type,
+            'landSurface': land_surface,
+            'hasLivingRoom': has_living_room == 'Yes',
+            'livingRoomSurface': living_room_surface,
+            'hasBalcony': has_balcony == 'Yes',
+            'hasGarden': has_garden == 'Yes',
+            'gardenSurface': garden_surface,
+            'gardenOrientation': garden_orientation,
+            'parkingCountIndoor': parking_count_indoor,
+            'parkingCountOutdoor': parking_count_outdoor,
+            'hasAirConditioning': has_air_conditioning == 'Yes',
+            'hasArmoredDoor': has_armored_door == 'Yes',
+            'hasVisiophone': has_visiophone == 'Yes',
+            'hasOffice': has_office == 'Yes',
+            'toiletCount': toilet_count,
+            'hasSwimmingPool': has_swimming_pool == 'Yes',
+            'hasFireplace': has_fireplace == 'Yes',
+            'hasTerrace': has_terrace == 'Yes',
+            'terraceSurface': terrace_surface,
+            'terraceOrientation': terrace_orientation,
+            'accessibleDisabledPeople': accessible_disabled_people == 'True',
+            'epcScore': epc_score
+        }
+        df = pd.DataFrame(data, index=[0])
+        pipeline = joblib.load('saved/pipeline.pkl')
+        model = joblib.load('saved/model.pkl')
+        expected_columns = joblib.load('saved/columns.pkl')
+        df_test = pipeline.transform(df)
+        for col in expected_columns:
+            if col not in df_test.columns:
+                df_test[col] = 0
+
+        df_test = df_test[expected_columns]
+        preds = model.predict(df_test)
+        st.subheader("Price prediction")
+        st.markdown(f"<h1 style='text-align: center; color: red;'>{preds[0]:.2f} €</h1>", unsafe_allow_html=True)
+        return df
+
+if __name__ == "__main__":
+    create_dataframe_from_user_input()

preprocessing/pipeline_components.py

@@ -26,8 +26,10 @@ class DataCleaner(BaseEstimator, TransformerMixin):
             'hasTerrace': 'int', 'terraceSurface': 'float', 'terraceOrientation': 'str', 
             'epcScore': 'str', 'facadeCount': 'int'
         }
+        self.kitchenType_mode = None
         
     def fit(self, X, y=None):
+        #self.kitchenType_mode = X['kitchenType'].mode()[0]
         return self
         
     def transform(self, X):