Upload 4 files

README.md

@@ -1,13 +1,11 @@
 ---
-title: TabNet Kerato V2
-emoji: 💻
-colorFrom: yellow
-colorTo: yellow
+title: TabNet_Kerato_v2
+emoji: 📊
+colorFrom: blue
+colorTo: indigo
 sdk: gradio
 sdk_version: 5.12.0
 app_file: app.py
 pinned: false
-short_description: 4 way classification
 ---
-
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,34 @@
+import gradio as gr
+import joblib
+from pytorch_tabnet.tab_model import TabNetClassifier
+import sklearn
+import numpy as np
+
+file_name = 'TabNet_model_4.sav'
+model_3 = joblib.load(file_name)
+
+def TabNet(Z_00, Z_1M1, Z_1P1, Z_2M2, Z_20, 
+           Z_2P2, Z_3M3, Z_3M1, Z_3P1, Z_3P3,
+           Z_4M4, Z_4M2, Z_40, Z_4P2, Z_4P4):
+    
+    outcome_decoded = {0:"Normal", 1:"TBN", 2:"TBF", 3:"Keratoconic"}
+    
+    X = [[Z_00, Z_1M1, Z_1P1, Z_2M2, Z_20, 
+        Z_2P2, Z_3M3, Z_3M1, Z_3P1, Z_3P3,
+        Z_4M4, Z_4M2, Z_40, Z_4P2, Z_4P4]]
+    X = np.array(X)
+
+    result_4way = model_3.predict(X)
+    return 'The patient is ' + outcome_decoded[int(result_4way)] + '.'
+
+iface = gr.Interface(
+    fn=TabNet, 
+    title='TabNet Predictor',
+    description='This TabNet model is capable of detecting Keratoconus and Keratoconic suspects with high accuracy. It takes in all of the Zernike Polynomials with values 4 and below. This is the 4-way classification.\
+                The parameter Z_00 refers to z(0,0); Z_2P2 refers to z(2, +2); where P represents the Plus "+" and M represents the Minus "-"\
+                This version further subdivides the suspects into 2 groups.',
+    inputs=["number", "number", "number", "number", "number",
+            "number", "number", "number", "number", "number",
+            "number", "number", "number", "number", "number"],
+    outputs="text")
+iface.launch()

requirements.txt

@@ -0,0 +1,5 @@
+gradio==5.12.0
+scikit-learn
+pytorch_tabnet
+joblib==1.2.0
+numpy