Upload 4 files

Logistic_Regression_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e15a031bd903126b88722cbcf4516dd8ce5fc80eb391b129cd921f999680cfbb
+size 886

Random_Forest_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c31e65ba7d64634fe23d82094b153405892ebba4efdeec0f60831292ff12e9d8
+size 507816

app.py

@@ -0,0 +1,50 @@
+import streamlit as st
+import pandas as pd
+import pickle
+
+# Load pre-trained models
+models = {}
+with open('Logistic_Regression_model.pkl', 'rb') as f:
+    models['Logistic Regression'] = pickle.load(f)
+
+with open('Random_Forest_model.pkl', 'rb') as f:
+    models['Random Forest'] = pickle.load(f)
+
+def predict_kidney_stone(gravity, ph, osmo, cond, urea, calc):
+    data = {'gravity': [gravity], 'ph': [ph], 'osmo': [osmo], 'cond': [cond], 'urea': [urea], 'calc': [calc]}  # Include 'calc' in the data
+    test_df = pd.DataFrame(data)
+    
+    # Predict using the combined models
+    y_pred_lr = models['Logistic Regression'].predict_proba(test_df)[:, 1]
+    y_pred_rf = models['Random Forest'].predict_proba(test_df)[:, 1]
+
+    combined_prediction = (y_pred_lr + y_pred_rf) / 2
+    
+    return combined_prediction[0]
+
+# Streamlit app
+import streamlit as st
+
+st.title('Kidney Stone Detection 🧪')
+st.write('This app predicts whether a tabular kidney stone is present or not based on input values.')
+st.image('https://www.health.com/thmb/vU7eqqoH-LmfHlX4WlPu9t-LyN8=/2000x0/filters:no_upscale():max_bytes(150000):strip_icc()/kindney-disease-causes-GettyImages-1257900987-03002a7b6e244dfaaecfacf4bae2f707.jpg', use_column_width=True)
+st.write('Gravity: Indicates urine concentration; higher values increase stone risk.(1 - 1.1)')
+st.write('pH: Measures urine acidity; extremes can promote specific stone types. (0-14)')
+st.write('Osmo: Reflects urine solute concentration; higher values raise stone risk.(0-2000)')
+st.write('Cond: Indicates urine ion concentration; higher values suggest increased stone risk.(0-50)')
+st.write('Urea: Waste product from protein metabolism; high levels can raise stone risk.(0-1000)')
+st.write('Calc: Essential mineral; excessive levels can increase certain stone types risk.(0-50)')
+
+
+# Input form
+gravity = st.number_input('Gravity', min_value=0.0, max_value=2.0, step=0.001, value=1.021)
+ph = st.number_input('pH', min_value=0.0, max_value=14.0, step=0.1, value=4.91)
+osmo = st.number_input('Osmo', min_value=0, max_value=2000, step=1, value=442)
+cond = st.number_input('Cond', min_value=0.0, max_value=50.0, step=0.1, value=20.8)
+urea = st.number_input('Urea', min_value=0, max_value=1000, step=1, value=398)
+calc = st.number_input('Calc', min_value=0.0, max_value=50.0, step=1.0, value=6.63)
+
+# Predict
+if st.button('Predict'):
+    prediction = predict_kidney_stone(gravity, ph, osmo, cond, urea, calc)
+    st.write(f'Predicted Probability of Kidney Stone is: {prediction:.4f}%')

requirements.txt

@@ -0,0 +1,3 @@
+pandas
+pickle
+scikit-learn