Update app.py

app.py

@@ -1,20 +1,19 @@
-# app.py
-from fastapi import FastAPI
-from pydantic import BaseModel
-from typing import List
+import streamlit as st
 import pandas as pd
 from setfit import SetFitModel
 from sentence_transformers import util
 import torch
 
-app = FastAPI()
+# Load model once
+@st.cache_resource
+def load_model():
+    return SetFitModel.from_pretrained(
+        "HEN10/setfit-particular-transaction-solon-embeddings-labels-large-kaggle-automatisation-v1"
+    )
 
-# Load your trained model once at startup
-model = SetFitModel.from_pretrained(
-    "HEN10/setfit-particular-transaction-solon-embeddings-labels-large-kaggle-automatisation-v1"
-)
+model = load_model()
 
-# Dummy reference categories (replace with your real categories or load CSV)
+# Load reference categories
 ref_data = pd.DataFrame({
     "Cat1EN": [
         "Purchase of goods","Purchase of goods","Purchase of goods","Purchase of goods",
@@ -28,28 +27,14 @@ 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)",
-
-        
-       
-        
-        "Process and fugitive emissions","Process and fugitive emissions",
-        "Process and fugitive emissions",
-        
-        "Waste treatment","Waste treatment","Waste treatment",
+        "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",
         "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": [
@@ -64,22 +49,13 @@ 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",
@@ -93,51 +69,56 @@ 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"
     ]
 })
 
-
-
+# Precompute embeddings
 ref_data["combined"] = ref_data[["Cat1EN", "Cat2EN", "DescriptionCat2EN"]].agg(" ".join, axis=1)
 ref_embeddings = model.encode(ref_data["combined"].tolist())
 
-# ✅ Root endpoint so Hugging Face doesn’t show "Not Found"
-@app.get("/")
-def read_root():
-    return {"status": "ok", "message": "Category mapping API is running. Use POST /map_categories"}
+# Streamlit UI
+st.title("📊 Transaction Category Mapper")
+st.write("Upload a CSV file with a column of transactions, and the app will map them to categories.")
+
+uploaded_file = st.file_uploader("Upload your CSV file", type=["csv"])
+
+if uploaded_file:
+    df = pd.read_csv(uploaded_file)
+
+    # Let user choose which column to map
+    col_to_use = st.selectbox("Select the column containing transactions:", df.columns)
 
-# ✅ Define request schema
-class TransactionsRequest(BaseModel):
-    transactions: List[str]
+    if st.button("Run Mapping"):
+        results = []
+        for text in df[col_to_use].dropna().tolist():
+            trans_emb = model.encode([text])[0]
+            scores = util.pytorch_cos_sim(torch.tensor(trans_emb), torch.tensor(ref_embeddings)).flatten()
+            best_idx = scores.argmax().item()
+            results.append({
+                "input_text": text,
+                "best_Cat1": ref_data.iloc[best_idx]["Cat1EN"],
+                "best_Cat2": ref_data.iloc[best_idx]["Cat2EN"],
+                "similarity": float(scores[best_idx])
+            })
+        
+        results_df = pd.DataFrame(results)
+        st.success("✅ Mapping completed!")
+        st.dataframe(results_df)
 
-@app.post("/map_categories")
-def map_categories(request: TransactionsRequest):
-    results = []
-    for text in request.transactions:
-        trans_emb = model.encode([text])[0]
-        scores = util.pytorch_cos_sim(torch.tensor(trans_emb), torch.tensor(ref_embeddings)).flatten()
-        best_idx = scores.argmax().item()
-        results.append({
-            "input_text": text,
-            "best_Cat1": ref_data.iloc[best_idx]["Cat1EN"],
-            "best_Cat2": ref_data.iloc[best_idx]["Cat2EN"],
-            "similarity": float(scores[best_idx])
-        })
-    return {"matches": results}
+        # Option to download
+        csv = results_df.to_csv(index=False).encode("utf-8")
+        st.download_button(
+            label="📥 Download results as CSV",
+            data=csv,
+            file_name="mapped_transactions.csv",
+            mime="text/csv"
+        )