Upload app.py
Browse files
app.py
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
#+--------------------------------------------------------------------------------------------+
|
2 |
+
# Breast Cancer Prediction
|
3 |
+
# Using Neural Networks and Tensorflow
|
4 |
+
# Prediction using Gradio on Hugging Face
|
5 |
+
# Written by: Prakash R. Kota
|
6 |
+
# Written on: 12 Feb 2025
|
7 |
+
# Last update: 12 Feb 2025
|
8 |
+
|
9 |
+
# Data Set from
|
10 |
+
# Original:
|
11 |
+
# https://archive.ics.uci.edu/dataset/17/breast+cancer+wisconsin+diagnostic
|
12 |
+
# With Header:
|
13 |
+
# https://www.kaggle.com/code/nancyalaswad90/analysis-breast-cancer-prediction-dataset
|
14 |
+
#
|
15 |
+
# Input Data Format for Gradio must be in the above header format with 30 features
|
16 |
+
# The header has 32 features listed, but ignore the first 2 header columns
|
17 |
+
#+--------------------------------------------------------------------------------------------+
|
18 |
+
|
19 |
+
import tensorflow as tf
|
20 |
+
import numpy as np
|
21 |
+
import gradio as gr
|
22 |
+
import joblib
|
23 |
+
|
24 |
+
|
25 |
+
# Load the trained model
|
26 |
+
model = tf.keras.models.load_model("PRK_BC_NN_Model.keras")
|
27 |
+
|
28 |
+
# Load the saved Scaler
|
29 |
+
scaler = joblib.load("PRK_BC_NN_Scaler.pkl")
|
30 |
+
|
31 |
+
# Function to process input and make predictions
|
32 |
+
def predict(input_text):
|
33 |
+
# Convert input string into a NumPy array of shape (1, 30)
|
34 |
+
input_data = np.array([list(map(float, input_text.split(",")))])
|
35 |
+
|
36 |
+
# Ensure the input shape is correct
|
37 |
+
if input_data.shape != (1, 30):
|
38 |
+
return "Error: Please enter exactly 30 numerical values separated by commas."
|
39 |
+
|
40 |
+
# Transform the input data using the loded scaler
|
41 |
+
input_data_scaled = scaler.transform(input_data)
|
42 |
+
|
43 |
+
# Make a prediction
|
44 |
+
prediction = model.predict(input_data_scaled)
|
45 |
+
|
46 |
+
# Convert prediction to a binary outcome (assuming classification)
|
47 |
+
result = "Malignant" if prediction[0][0] > 0.5 else "Benign"
|
48 |
+
|
49 |
+
return f"Prediction: {result} (Confidence: {prediction[0][0]:.2f})"
|
50 |
+
|
51 |
+
|
52 |
+
import gradio as gr
|
53 |
+
|
54 |
+
# Create the Gradio interface
|
55 |
+
interface = gr.Interface(
|
56 |
+
fn=predict,
|
57 |
+
inputs=gr.Textbox(label="Enter 30 feature values, comma-separated"),
|
58 |
+
outputs="text",
|
59 |
+
title="Breast Cancer Prediction",
|
60 |
+
description="Enter 30 numerical feature values separated by commas to predict whether the biopsy is Malignant or Benign."
|
61 |
+
)
|
62 |
+
|
63 |
+
# Launch the Gradio app
|
64 |
+
interface.launch()
|
65 |
+
|