Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,40 +1,118 @@
-import altair as alt
-import numpy as np
-import pandas as pd
 import streamlit as st
+import pandas as pd
+import numpy as np
+import joblib
+
+# --- PAGE CONFIGURATION ---
+st.set_page_config(
+    page_title="Steel Plate Defect Prediction",
+    page_icon="🏗️",
+    layout="wide")
+
+@st.cache_resource
+def load_artifacts():
+    artifacts = joblib.load('src/steel_defect_model.pkl')
+    return artifacts
+
+try:
+    artifacts = load_artifacts()
+    models = artifacts['models']
+    scaler = artifacts['scaler']
+    feature_names = artifacts['features']
+    targets = artifacts['targets']
+except FileNotFoundError:
+    st.error("Model file 'steel_defect_model.pkl' not found.")
+    st.stop()
+
+st.title("🏗️ Steel Plate Defect Prediction AI")
+st.markdown("""
+This AI model predicts the probability of **7 different types of defects** in steel plates based on their geometric and radiometric properties.
+""")
+
+st.sidebar.header("Input Parameters")
+st.sidebar.info("Adjust the sliders to simulate different steel plate properties.")
+
+def user_input_features():
+    data = {}
+    
+    st.sidebar.subheader("1. Geometry")
+    data['X_Minimum'] = st.sidebar.number_input('X Minimum', 0, 1700, 0)
+    data['X_Maximum'] = st.sidebar.number_input('X Maximum', 0, 1700, 50)
+    data['Y_Minimum'] = st.sidebar.number_input('Y Minimum', 0, 13000000, 600000)
+    data['Y_Maximum'] = st.sidebar.number_input('Y Maximum', 0, 13000000, 600050)
+    data['Pixels_Areas'] = st.sidebar.number_input('Pixels Areas', 0, 20000, 200)
+    data['Steel_Plate_Thickness'] = st.sidebar.slider('Steel Plate Thickness', 40, 300, 80)
+    
+    st.sidebar.subheader("2. Luminosity")
+    data['Sum_of_Luminosity'] = st.sidebar.number_input('Sum of Luminosity', 0, 12000000, 20000)
+    data['Minimum_of_Luminosity'] = st.sidebar.slider('Minimum Luminosity', 0, 200, 80)
+    data['Maximum_of_Luminosity'] = st.sidebar.slider('Maximum Luminosity', 0, 260, 130)
+    
+    data['Length_of_Conveyer'] = 1459  
+    data['TypeOfSteel_A300'] = st.sidebar.selectbox('Type of Steel A300', [0, 1], index=0)
+    data['Edges_Index'] = 0.35
+    data['Empty_Index'] = 0.4
+    data['Square_Index'] = 0.57
+    data['Outside_X_Index'] = 0.03
+    data['Edges_X_Index'] = 0.61
+    data['Edges_Y_Index'] = 0.83
+    data['Outside_Global_Index'] = 0.5
+    data['LogOfAreas'] = np.log(data['Pixels_Areas']) if data['Pixels_Areas'] > 0 else 0 
+    data['Log_X_Index'] = 0 
+    data['Log_Y_Index'] = 0 
+    data['Orientation_Index'] = 0.1
+    data['Luminosity_Index'] = -0.13
+    data['SigmoidOfAreas'] = 0.5
+    
+    df = pd.DataFrame(data, index=[0])
+    return df
+
+input_df = user_input_features()
+
+def preprocess_input(df):
+    df = df.copy()
+    
+    df['X_Range'] = df['X_Maximum'] - df['X_Minimum']
+    df['Y_Range'] = df['Y_Maximum'] - df['Y_Minimum']
+    
+    x_range = df['X_Range'].replace(0, 1)
+    y_range = df['Y_Range'].replace(0, 1)
+    
+    df['Density'] = df['Pixels_Areas'] / (x_range * y_range)
+    df['Aspect_Ratio'] = df['X_Range'] / y_range
+    df['Luminosity_Range'] = df['Maximum_of_Luminosity'] - df['Minimum_of_Luminosity']
+    
+    skewed_features = ['Pixels_Areas', 'Sum_of_Luminosity', 
+                       'X_Range', 'Y_Range', 'Aspect_Ratio']
+        
+    for col in feature_names:
+        if col not in df.columns:
+            df[col] = 0 
+            
+    for feature in skewed_features:
+        if feature in df.columns:
+            df[feature] = np.log1p(df[feature].abs())
+            
+    df = df[feature_names]
+    return df
 
-"""
-# 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])),
-    ))
+if st.button('🔎 Analyze Steel Plate'):
+    processed_df = preprocess_input(input_df)
+    scaled_array = scaler.transform(processed_df)
+    scaled_df = pd.DataFrame(scaled_array, columns=feature_names)
+    results = {}
+    for target in targets:
+        model = models[target]
+        prob = model.predict_proba(scaled_df)[0][1]
+        results[target] = prob
+    st.subheader("Analysis Results")
+    results_df = pd.DataFrame(list(results.items()), columns=['Defect Type', 'Probability'])
+    results_df = results_df.sort_values(by='Probability', ascending=False)
+    top_defect = results_df.iloc[0]
+    if top_defect['Probability'] > 0.5:
+        st.error(f"⚠️ High Risk Detected: **{top_defect['Defect Type']}** ({top_defect['Probability']:.1%})")
+    else:
+        st.success("✅ No severe defects detected (All probabilities < 50%)")
+    st.bar_chart(results_df.set_index('Defect Type'))
+    with st.expander("See Detailed Probabilities"):
+        st.dataframe(results_df.style.format({'Probability': '{:.2%}'}))