Application Iris Dataset

README.md

@@ -1,10 +1,10 @@
 ---
-title: App Iris
-emoji: 🔥
+title: Info7390 Deploy
+emoji: 🌖
 colorFrom: yellow
-colorTo: green
+colorTo: blue
 sdk: streamlit
-sdk_version: 1.27.2
+sdk_version: 1.25.0
 app_file: app.py
 pinned: false
 ---

app.py

@@ -0,0 +1,24 @@
+# app_iris.py
+
+import streamlit as st
+import onnxruntime as rt
+import numpy as np
+
+# Load the trained ONNX model
+sess = rt.InferenceSession("random_forest_iris.onnx")
+
+st.title("Iris Prediction with Random Forest")
+
+# Input features
+sepal_length = st.slider("Sepal Length", 0.0, 10.0, 5.0)
+sepal_width = st.slider("Sepal Width", 0.0, 10.0, 3.5)
+petal_length = st.slider("Petal Length", 0.0, 10.0, 2.5)
+petal_width = st.slider("Petal Width", 0.0, 10.0, 1.0)
+
+input_features = [sepal_length, sepal_width, petal_length, petal_width]
+
+# Predict
+if st.button("Predict"):
+    input_array = np.array([input_features], dtype=np.float32)
+    pred_onnx = sess.run(None, {'float_input': input_array})
+    st.write(f"Predicted class: {pred_onnx[0][0]}")

random_forest_iris.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7850ccd707ca0c8fabf5ab3c287a8cda49b4e8c268c52c9cd4784eeef5c35c86
+size 80984

requirements.txt

@@ -0,0 +1,5 @@
+streamlit
+onnx
+onnxruntime
+skl2onnx
+numpy