Water_Quality_Central_Java / water_quality_index.py
darly9991's picture
Update water_quality_index.py
36ec84c verified
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
# === Thresholds for Rule-Based Classification ===
thresholds = {
'pH_min': 6.0, 'pH_max': 9.0,
'BOD': 3.0,
'COD': 25.0,
'TSS': 50.0,
'DO': 4.0,
'Nitrate': 10.0,
'Phosphate': 0.2,
'FecalColiform': 1000
}
def categorize_sample(row):
pH = row['pH (Potential Hydrogen)']
BOD = row['BOD (Biological Oxygen Demand) (mg/L)']
COD = row['COD (Chemical Oxygen Demand) (mg/L)']
DO = row['DO (Dissolved Oxygen) (mg/L)']
nitrate = row['NO3N (Nitrat) (mg/L)']
phosphate = row['Total Phosphat (mg/L)']
fecal = row['Fecal Coliform (MPN/100 mL)']
TSS = row['TSS (Total Suspended Solid) (mg/L)']
if (
thresholds['pH_min'] <= pH <= thresholds['pH_max'] and
BOD <= thresholds['BOD'] and
COD <= thresholds['COD'] and
DO >= thresholds['DO'] and
nitrate <= thresholds['Nitrate'] and
phosphate <= thresholds['Phosphate'] and
fecal <= thresholds['FecalColiform'] and
TSS <= thresholds['TSS']
):
return "Safe", "Safe"
categories = []
if COD > thresholds['COD'] * 1.5 or pH < thresholds['pH_min'] or pH > thresholds['pH_max'] or TSS > thresholds['TSS']:
categories.append("Chemical")
if BOD > thresholds['BOD'] or DO < thresholds['DO'] or fecal > thresholds['FecalColiform'] or TSS > thresholds['TSS']:
categories.append("Biological")
if nitrate > thresholds['Nitrate'] or phosphate > thresholds['Phosphate'] or TSS > thresholds['TSS']:
categories.append("Eutrophication")
priority_order = ["Chemical", "Biological", "Eutrophication"]
for cat in priority_order:
if cat in categories:
return ", ".join(categories), cat
return "Safe", "Safe"
# === Streamlit App ===
def run():
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")
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)"
]
st.set_page_config(page_title="Water Quality Classifier Dashboard", layout="wide")
st.title("πŸ’§ Water Quality Prediction and Rule-Based Evaluation")
model_choice = st.selectbox("Select Model", ["SVC + SMOTETomek", "XGBoost + SMOTETomek"])
model = svc_model if model_choice == "SVC + SMOTETomek" else xgb_model
st.header("πŸ“₯ 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
}])
if input_df is not None:
st.header("πŸ” Prediction Results")
try:
X_imp = imputer.transform(input_df)
X_scaled = scaler.transform(X_imp)
y_proba = model.predict_proba(X_scaled)
y_pred = model.predict(X_scaled)
pred_class = label_encoder.inverse_transform(y_pred)[0]
# Rule-Based Evaluation
rule_violations, rule_label = categorize_sample(input_df.iloc[0])
# Display results
st.markdown(f"### πŸ§ͺ ML Predicted Class: `{pred_class}`")
st.markdown(f"### πŸ“ Rule-Based Class: `{rule_label}`")
st.markdown(f"**Violations Detected:** {rule_violations}")
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 Results
input_df["Predicted Class (ML)"] = pred_class
input_df["Rule-Based Class"] = rule_label
input_df["Rule-Based Violations"] = rule_violations
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.subheader("πŸ“€ Download Result")
st.markdown(href, unsafe_allow_html=True)
except Exception as e:
st.error(f"Prediction failed: {e}")
st.markdown("---")
st.caption("Developed with ❀️ for integrated ML + expert rule water quality system")