Update app.py

app.py

@@ -15,8 +15,6 @@ model = SetFitModel.from_pretrained(
 )
 
 # Dummy reference categories (replace with your real categories or load CSV)
-import pandas as pd
-
 ref_data = pd.DataFrame({
     "Cat1EN": [
         "Purchase of goods","Purchase of goods","Purchase of goods","Purchase of goods",
@@ -30,14 +28,28 @@ ref_data = pd.DataFrame({
         "Food & beverages","Food & beverages","Food & beverages","Food & beverages",
         "Food & beverages","Food & beverages","Food & beverages","Food & beverages",
         "Heating and air conditioning","Heating and air conditioning","Fuels","Fuels","Fuels","Fuels",
-        "Fuels","Fuels","Mobility (freight)","Mobility (freight)","Mobility (freight)","Mobility (freight)",
-        "Mobility (freight)","Mobility (passengers)","Mobility (passengers)","Mobility (passengers)",
+        "Fuels","Fuels",
+        
+        "Mobility (freight)","Mobility (freight)","Mobility (freight)","Mobility (freight)",
+        "Mobility (freight)",
+        
+        "Mobility (passengers)","Mobility (passengers)","Mobility (passengers)",
         "Mobility (passengers)","Mobility (passengers)","Mobility (passengers)","Mobility (passengers)",
         "Mobility (passengers)","Mobility (passengers)","Mobility (passengers)","Mobility (passengers)",
-        "Mobility (passengers)","Process and fugitive emissions","Process and fugitive emissions",
-        "Process and fugitive emissions","Waste treatment","Waste treatment","Waste treatment",
-        "Waste treatment","Waste treatment","Waste treatment","Waste treatment","Waste treatment",
+
+        
+       
+        
+        "Process and fugitive emissions","Process and fugitive emissions",
+        "Process and fugitive emissions",
+        
+        "Waste treatment","Waste treatment","Waste treatment",
         "Waste treatment","Waste treatment","Waste treatment","Waste treatment","Waste treatment",
+        "Waste treatment","Waste treatment","Waste treatment","Waste treatment",
+        
+     
+
+        
         "Use of electricity","Use of electricity","Use of electricity"
     ],
     "Cat2EN": [
@@ -52,19 +64,28 @@ ref_data = pd.DataFrame({
         "Condiments","Desserts","Fruits and vegetables","Fats and oils","Prepared / cooked meals",
         "Animal products","Cereal products","Dairy products","Heat and steam","Air conditioning and refrigeration",
         "Fossil fuels","Mobile fossil fuels","Organic fuels","Gaseous fossil fuels","Liquid fossil fuels",
-        "Solid fossil fuels","Air transport","Ship transport","Truck transport","Combined transport",
-        "Train transport","Air transport","Coach / Urban bus","Ship transport","Combined transport",
+        "Solid fossil fuels",
+        
+        "Air transport","Ship transport","Truck transport","Combined transport",
+        "Train transport",
+        
+        "Air transport","Coach / Urban bus","Ship transport","Combined transport",
         "E-Bike","Accommodation / Events","Soft mobility","Motorcycle / Scooter","Train transport",
-        "Public transport","Car","Agriculture","Global warming potential","Industrial processes",
+        "Public transport","Car",
+        
+        "Agriculture","Global warming potential","Industrial processes",
+        
         "Commercial and industrial","Wastewater","Electrical equipment","Households and similar",
         "Metal","Organic materials","Paper and cardboard","Batteries and accumulators","Plastics",
-        "Fugitive process emissions","Textiles","Glass","Electricity for electric vehicles","Renewables","Standard"
+        "Fugitive process emissions","Textiles","Glass",
+        
+        "Electricity for electric vehicles","Renewables","Standard"
     ],
     "DescriptionCat2EN": [
         "Goods purchase - sports","Goods purchase - buildings","Goods purchase - office items","Goods purchase - water",
         "Goods purchase - appliances","Goods purchase - electricals","Goods purchase - machinery","Goods purchase - furniture",
         "Goods purchase - textiles","Goods purchase - vehicles","Material purchase - construction","Material purchase - organic",
-        "Material purchase - paper","Material purchase - plastics","Material purchase - chemicals","Material purchase - refrigerants & others",
+        "Material purchase - paper","Material purchase - plastics","Material purchase - chemicals","Material purchase - refrigerants",
         "Service - equipment rental","Service - building rental","Service - furniture rental","Service - vehicles",
         "Service - info/culture","Service - catering","Service - healthcare","Service - crafts",
         "Service - admin/consulting","Service - cleaning","Service - IT","Service - logistics",
@@ -72,19 +93,28 @@ ref_data = pd.DataFrame({
         "Food condiments","Food desserts","Food fruits & vegetables","Food fats & oils","Prepared meals",
         "Animal-based food","Cereal-based food","Dairy products","Heating - heat & steam","Heating - cooling/refrigeration",
         "Fuel - fossil","Fuel - mobile fossil","Fuel - organic","Fuel - gaseous","Fuel - liquid","Fuel - solid",
+        
         "Freight transport - air","Freight transport - ship","Freight transport - truck","Freight transport - combined",
-        "Freight transport - train","Passenger transport - air","Passenger transport - bus","Passenger transport - ship",
+        "Freight transport - train",
+        
+        "Passenger transport - air","Passenger transport - bus","Passenger transport - ship",
         "Passenger transport - combined","Passenger transport - e-bike","Passenger transport - accommodation/events",
         "Passenger transport - soft mobility","Passenger transport - scooter/motorbike","Passenger transport - train",
-        "Passenger transport - public","Passenger transport - car","Emissions - agriculture","Emissions - warming potential",
-        "Emissions - industry","Waste - commercial/industrial","Waste - wastewater","Waste - electricals",
+        "Passenger transport - public","Passenger transport - car",
+        
+        "Emissions - agriculture","Emissions - warming potential",
+        "Emissions - industry",
+        
+        "Waste - commercial/industrial","Waste - wastewater","Waste - electricals",
         "Waste - households","Waste - metals","Waste - organics","Waste - paper","Waste - batteries",
         "Waste - plastics","Waste - fugitive","Waste - textiles","Waste - glass",
+        
         "Electricity - EVs","Electricity - renewables","Electricity - standard"
     ]
 })
 
 
+
 ref_data["combined"] = ref_data[["Cat1EN", "Cat2EN", "DescriptionCat2EN"]].agg(" ".join, axis=1)
 ref_embeddings = model.encode(ref_data["combined"].tolist())