Create app.py

app.py

@@ -0,0 +1,56 @@
+from fastapi import FastAPI
+from pydantic import BaseModel
+import joblib
+import numpy as np
+
+# 1. Load the trained model
+# Ensure 'iris_model.pkl' is uploaded to the same folder in Hugging Face
+model = joblib.load("iris_model.pkl")
+
+# 2. Define the class mapping based on your notebook encoding
+# In your notebook: Iris-setosa=1, Iris-versicolor=2, Iris-virginica=3
+class_names = {
+    1: "Iris-setosa", 
+    2: "Iris-versicolor", 
+    3: "Iris-virginica"
+}
+
+# 3. Define the input data format using Pydantic
+class IrisInput(BaseModel):
+    SepalLengthCm: float
+    SepalWidthCm: float
+    PetalLengthCm: float
+    PetalWidthCm: float
+
+# 4. Initialize FastAPI
+app = FastAPI()
+
+# 5. Define the Home Route (Health Check)
+@app.get("/")
+def home():
+    return {"message": "Iris Species Prediction API is Live!"}
+
+# 6. Define the Prediction Route
+@app.post("/predict")
+def predict_species(data: IrisInput):
+    # Extract features from the input object
+    features = np.array([[
+        data.SepalLengthCm, 
+        data.SepalWidthCm, 
+        data.PetalLengthCm, 
+        data.PetalWidthCm
+    ]])
+    
+    # Make the prediction using the loaded model
+    prediction = model.predict(features)
+    
+    # The model returns an array (e.g., [1]), so we take the first item
+    predicted_class = int(prediction[0])
+    
+    # Map the number back to the name
+    species_name = class_names.get(predicted_class, "Unknown")
+    
+    return {
+        "predicted_class": predicted_class,
+        "species_name": species_name
+    }