Upload 6 files

imputer.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca769650d144cf1dc143fffc9c368ef47469de6671430be2d594823d424c294d
+size 13713

label_encoder.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32f95b42cdc2676ef36ff0ff99037431b1ba4d2601e88c04568d99b40e9dca48
+size 582

scaler.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:863c08f64c1de60c260b4c92fbccd6891f8987244f9b5c3dff420a93f1975427
+size 807

svc_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f28410514081ad74524f60f8658661427acc3406c8da8c3f0096f14d03017348
+size 146369

water_quality_index.py

@@ -0,0 +1,114 @@
+import streamlit as st
+import pandas as pd
+import numpy as np
+import joblib
+import plotly.express as px
+import base64
+from sklearn.preprocessing import LabelEncoder
+
+def run():
+    # === Load Trained Objects ===
+    svc_model = joblib.load("svc_model.pkl")
+    xgb_model = joblib.load("xgb_model.pkl")
+    imputer = joblib.load("imputer.pkl")
+    scaler = joblib.load("scaler.pkl")
+    label_encoder = joblib.load("label_encoder.pkl")  # already fitted
+
+    # === Expected Columns ===
+    feature_cols = [
+        "pH (Potential Hydrogen)",
+        "BOD (Biological Oxygen Demand) (mg/L)",
+        "COD (Chemical Oxygen Demand) (mg/L)",
+        "TSS (Total Suspended Solid) (mg/L)",
+        "DO (Dissolved Oxygen) (mg/L)",
+        "NO3N (Nitrat) (mg/L)",
+        "Total Phosphat (mg/L)",
+        "Fecal Coliform (MPN/100 mL)"
+    ]
+
+    # === Streamlit Setup ===
+    st.set_page_config(page_title="Water Quality Classifier Dashboard", layout="wide")
+    st.title("💧 Water Quality Prediction and Dashboard")
+
+    # === Model Selector ===
+    model_choice = st.selectbox("Select Model", ["SVC + SMOTETomek", "XGBoost + SMOTETomek"])
+    model = svc_model if model_choice == "SVC + SMOTETomek" else xgb_model
+
+    # === Input Section ===
+    st.header("📥 Input Data")
+    data_option = st.radio("Choose Input Method", ["Upload CSV", "Manual Entry"])
+    input_df = None
+
+    if data_option == "Upload CSV":
+        uploaded_file = st.file_uploader("Upload your CSV file", type=["csv"])
+        if uploaded_file:
+            df = pd.read_csv(uploaded_file)
+            missing_cols = [col for col in feature_cols if col not in df.columns]
+            if missing_cols:
+                st.error(f"Missing required columns: {missing_cols}")
+            else:
+                input_df = df[feature_cols]
+    else:
+        with st.form("manual_form"):
+            ph = st.number_input("pH", min_value=0.0, max_value=14.0, value=7.0)
+            bod = st.number_input("BOD (mg/L)", min_value=0.0, max_value=100.0, value=2.0)
+            cod = st.number_input("COD (mg/L)", min_value=0.0, max_value=500.0, value=10.0)
+            tss = st.number_input("TSS (mg/L)", min_value=0.0, max_value=1000.0, value=20.0)
+            do = st.number_input("DO (mg/L)", min_value=0.0, max_value=20.0, value=5.0)
+            no3 = st.number_input("NO3N (mg/L)", min_value=0.0, max_value=10.0, value=1.0)
+            tp = st.number_input("Total Phosphat (mg/L)", min_value=0.0, max_value=10.0, value=0.1)
+            fecal = st.number_input("Fecal Coliform (MPN/100 mL)", min_value=0.0, max_value=1000000.0, value=500.0)
+            submitted = st.form_submit_button("Predict")
+
+        if submitted:
+            input_df = pd.DataFrame([{
+                "pH (Potential Hydrogen)": ph,
+                "BOD (Biological Oxygen Demand) (mg/L)": bod,
+                "COD (Chemical Oxygen Demand) (mg/L)": cod,
+                "TSS (Total Suspended Solid) (mg/L)": tss,
+                "DO (Dissolved Oxygen) (mg/L)": do,
+                "NO3N (Nitrat) (mg/L)": no3,
+                "Total Phosphat (mg/L)": tp,
+                "Fecal Coliform (MPN/100 mL)": fecal
+            }])
+
+    # === Prediction Section ===
+    if input_df is not None:
+        st.header("🔍 Prediction Results")
+
+        try:
+            # Preprocessing
+            X_imp = imputer.transform(input_df)
+            X_scaled = scaler.transform(X_imp)
+
+            # Prediction
+            y_proba = model.predict_proba(X_scaled)
+            y_pred = model.predict(X_scaled)
+            pred_class = label_encoder.inverse_transform(y_pred)[0]
+
+            st.markdown(f"### 🧪 Predicted Class: `{pred_class}`")
+
+            fig_pie = px.pie(
+                names=label_encoder.classes_,
+                values=y_proba[0],
+                title="Prediction Probability per Class",
+                color_discrete_sequence=px.colors.qualitative.Set3
+            )
+            st.plotly_chart(fig_pie, use_container_width=True)
+
+            # Export
+            st.subheader("📤 Download Prediction")
+            input_df["Predicted Class"] = pred_class
+            input_df[[f"Prob_{cls}" for cls in label_encoder.classes_]] = y_proba
+            csv = input_df.to_csv(index=False)
+            b64 = base64.b64encode(csv.encode()).decode()
+            href = f'<a href="data:file/csv;base64,{b64}" download="prediction_result.csv">Download CSV File</a>'
+            st.markdown(href, unsafe_allow_html=True)
+
+        except Exception as e:
+            st.error(f"Prediction failed: {e}")
+
+    # === Footer ===
+    st.markdown("---")
+    st.caption("Developed with ❤️ for real-time water quality analysis")
+

xgb_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbb9a7b0ad941aad43124b0bc77282a36dad4e2b0baa2a75bebafed1deba3ad5
+size 512625