Update app.py

app.py

@@ -1,53 +1,36 @@
-import streamlit as st
-import cv2
+import gradio as gr
+import pandas as pd
 import numpy as np
-from PIL import Image
-import pytesseract
-from deep_translator import GoogleTranslator
-
-st.set_page_config(page_title="Image Translator App", layout="centered")
-st.title("📄 Image Translator")
-st.write("Upload an image with text and get it translated directly on the image.")
-
-uploaded_file = st.file_uploader("Choose an image...", type=["jpg", "jpeg", "png"])
-
-if uploaded_file is not None:
-    image = Image.open(uploaded_file)
-    image_np = np.array(image)
-
-    st.image(image, caption="Original Image", use_column_width=True)
-
-    # Convert image to RGB (OpenCV uses BGR by default)
-    image_rgb = cv2.cvtColor(image_np, cv2.COLOR_RGB2BGR)
-
-    # OCR - get data with bounding boxes
-    data = pytesseract.image_to_data(image_rgb, output_type=pytesseract.Output.DICT)
-
-    translator = GoogleTranslator(source='auto', target='hi')
-
-    n_boxes = len(data['text'])
-    for i in range(n_boxes):
-        if int(data['conf'][i]) > 60:  # confidence threshold
-            x, y, w, h = data['left'][i], data['top'][i], data['width'][i], data['height'][i]
-            text = data['text'][i]
-            if text.strip() != "":
-                try:
-                    translated_text = translator.translate(text)
-
-                    # Draw white rectangle as background for text
-                    cv2.rectangle(image_rgb, (x, y), (x + w, y + h), (255, 255, 255), -1)
-
-                    # Adjust font scale based on box height
-                    font_scale = h / 35
-                    font_thickness = 1
-
-                    # Overlay translated text, vertically aligned inside the box
-                    cv2.putText(image_rgb, translated_text, (x, y + h - 5),
-                                cv2.FONT_HERSHEY_SIMPLEX, font_scale, (0, 0, 0),
-                                font_thickness, cv2.LINE_AA)
-                except Exception as e:
-                    print(f"Translation error for '{text}': {e}")
-
-    # Convert back to RGB for PIL display
-    result_image = cv2.cvtColor(image_rgb, cv2.COLOR_BGR2RGB)
-    st.image(result_image, caption="Translated Image", use_column_width=True)
+import pickle
+
+def predict_diabetes(pregnancies, glucose, blood_pressure, skin_thickness, insulin, bmi, diabetes_pedigree_function, age):
+    # Load the model
+    with open("model.pkl", "rb") as f:
+        model = pickle.load(f)
+
+    input_data = np.array([[pregnancies, glucose, blood_pressure, skin_thickness, insulin, bmi, diabetes_pedigree_function, age]])
+    prediction = model.predict(input_data)
+    result = "Diabetic" if prediction[0] == 1 else "Not Diabetic"
+    return result
+
+# Gradio Interface
+description = "Diabetes Prediction Model - Enter your values below"
+
+demo = gr.Interface(
+    fn=predict_diabetes,
+    inputs=[
+        gr.Number(label="Pregnancies"),
+        gr.Number(label="Glucose"),
+        gr.Number(label="Blood Pressure"),
+        gr.Number(label="Skin Thickness"),
+        gr.Number(label="Insulin"),
+        gr.Number(label="BMI"),
+        gr.Number(label="Diabetes Pedigree Function"),
+        gr.Number(label="Age")
+    ],
+    outputs=gr.Text(label="Prediction"),
+    title="Diabetes Prediction",
+    description=description
+)
+
+demo.launch()