Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,40 +1,98 @@
-import altair as alt
-import numpy as np
-import pandas as pd
+# Libraries 
 import streamlit as st
+import pandas as pd
+from sklearn.model_selection import train_test_split
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.metrics import accuracy_score
+
+# Title
+st.title("Diabetes Prediction System")
+st.write("A Machine Learning model trained on the PIMA Indians Diabetes Dataset.")
+
+# Load data and Train Data
+@st.cache_resource
+def train_model():
+    try:
+        df = pd.read_csv("diabetes.csv")
+    except FileNotFoundError:
+        # We create a tiny dummy dataset.
+        # This prevents the app from crashing.
+        st.warning("'diabetes.csv' not found. Using dummy data for demonstration.")
+        data = {
+            'Pregnancies': [6, 1, 8, 1, 0, 5, 3, 10],
+            'Glucose': [148, 85, 183, 89, 137, 116, 78, 115],
+            'BloodPressure': [72, 66, 64, 66, 40, 74, 50, 0],
+            'SkinThickness': [35, 29, 0, 23, 35, 0, 32, 0],
+            'Insulin': [0, 0, 0, 94, 168, 0, 88, 0],
+            'BMI': [33.6, 26.6, 23.3, 28.1, 43.1, 25.6, 31.0, 35.3],
+            'DiabetesPedigreeFunction': [0.627, 0.351, 0.672, 0.167, 2.288, 0.201, 0.248, 0.134],
+            'Age': [50, 31, 32, 21, 33, 30, 26, 29],
+            'Outcome': [1, 0, 1, 0, 1, 0, 1, 0]
+        }
+        df = pd.DataFrame(data)
+
+    # Data Split
+    X = df.drop(columns=['Outcome'])
+    y = df['Outcome']
+    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+
+    # Train Model
+    model = RandomForestClassifier(random_state=42)
+    model.fit(X_train, y_train)
+    
+    # Calculate accuracy
+    acc = accuracy_score(y_test, model.predict(X_test))
+    
+    return model, acc
+
+# Loading the Model
+model, accuracy = train_model()
+
+# Display Model Accuracy
+st.write(f"**Model Accuracy:** {accuracy * 100:.2f}%")
+st.markdown("---")
+
+# UI
+st.sidebar.header("Patient Data")
+
+def user_input_features():
+    pregnancies = st.sidebar.slider('Pregnancies', 0, 17, 3)
+    glucose = st.sidebar.slider('Glucose', 0, 199, 117)
+    bp = st.sidebar.slider('Blood Pressure', 0, 122, 72)
+    skin = st.sidebar.slider('Skin Thickness', 0, 99, 23)
+    insulin = st.sidebar.slider('Insulin', 0, 846, 30)
+    bmi = st.sidebar.slider('BMI', 0.0, 67.1, 32.0)
+    dpf = st.sidebar.slider('Diabetes Pedigree Function', 0.078, 2.42, 0.3725)
+    age = st.sidebar.slider('Age', 21, 81, 29)
+    
+    data = {
+        'Pregnancies': pregnancies,
+        'Glucose': glucose,
+        'BloodPressure': bp,
+        'SkinThickness': skin,
+        'Insulin': insulin,
+        'BMI': bmi,
+        'DiabetesPedigreeFunction': dpf,
+        'Age': age
+    }
+    features = pd.DataFrame(data, index=[0])
+    return features
+
+input_df = user_input_features()
+
+# Display User Input
+st.subheader('User Input parameters')
+st.write(input_df)
+
+# Prediction
+if st.button('Predict Diabetes Risk'):
+    prediction = model.predict(input_df)
+    prediction_proba = model.predict_proba(input_df)
+
+    st.subheader('Prediction Result')
+    if prediction[0] == 1:
+        st.error('Positive (High Risk of Diabetes)')
+    else:
+        st.success('Negative (Low Risk of Diabetes)')
 
-"""
-# Welcome to Streamlit!
-
-Edit `/streamlit_app.py` to customize this app to your heart's desire :heart:.
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
-
-In the meantime, below is an example of what you can do with just a few lines of code:
-"""
-
-num_points = st.slider("Number of points in spiral", 1, 10000, 1100)
-num_turns = st.slider("Number of turns in spiral", 1, 300, 31)
-
-indices = np.linspace(0, 1, num_points)
-theta = 2 * np.pi * num_turns * indices
-radius = indices
-
-x = radius * np.cos(theta)
-y = radius * np.sin(theta)
-
-df = pd.DataFrame({
-    "x": x,
-    "y": y,
-    "idx": indices,
-    "rand": np.random.randn(num_points),
-})
-
-st.altair_chart(alt.Chart(df, height=700, width=700)
-    .mark_point(filled=True)
-    .encode(
-        x=alt.X("x", axis=None),
-        y=alt.Y("y", axis=None),
-        color=alt.Color("idx", legend=None, scale=alt.Scale()),
-        size=alt.Size("rand", legend=None, scale=alt.Scale(range=[1, 150])),
-    ))
+    st.write(f"Probability: {prediction_proba[0][prediction[0]] * 100:.2f}%")