app.py

import streamlit as st
import pandas as pd

# Load the cleaned data
df = pd.read_csv('cleaned_farmer_data.csv')

# Set the page configuration for better layout and dark theme
st.set_page_config(
    page_title="Agroforestry Program Dashboard",
    page_icon="🌱",
    layout="wide",
)

# Custom CSS for dark theme and background color adjustments
st.markdown("""
    <style>
        body {
            background-color: #121212;  /* Dark background color */
            color: white;  /* Text color set to white */
        }
        .sidebar .sidebar-content {
            background-color: #1e1e1e;  /* Dark sidebar background */
            color: white;  /* Sidebar text color */
        }
        .stButton>button {
            background-color: #4CAF50;  /* Green button color */
            color: white;  /* Button text color */
        }
        .title {
            text-align: center;
            font-size: 40px;
            color: #4CAF50;
        }
        .stMarkdown {
            background-color: #1e1e1e;  /* Dark background for markdown blocks */
        }
        .stTable {
            background-color: #1e1e1e;  /* Dark background for table blocks */
        }
        .stDataFrame {
            background-color: #1e1e1e;  /* Dark background for dataframe */
        }
    </style>
""", unsafe_allow_html=True)

# Title and header for the dashboard
st.markdown('<div class="title">Real-Time Insights for Farmers</div>', unsafe_allow_html=True)

# Sidebar for navigation with a cleaner layout
st.sidebar.header("Dashboard Navigation")
section = st.sidebar.radio(
    "Select a Section:",
    ['Overview', 'Data Quality Issues', 'Plantation Progress', 'Location Insights']
)

# Overview Section
if section == 'Overview':
    st.subheader("📊 Overall Statistics")
    
    # Display key metrics in a clean, organized way
    total_area = df['total_land_area_acre'].sum()  # Corrected column name
    total_plantation_area = df['area_f4f_acre'].sum()  # Assuming 'area_f4f_acre' represents plantation area
    
    # Calculate the number of rows with missing or erroneous data
    missing_data_count = df.isnull().sum().sum()  # Total missing values in the dataset
    
    st.markdown(f"""
        <div style="display: flex; justify-content: space-around; margin-top: 20px;">
            <div style="padding: 10px; background-color: #333333; border-radius: 8px; width: 30%; text-align: center;">
                <h3>Total Area (Acres)</h3>
                <p style="font-size: 30px; color: #4CAF50;">{total_area}</p>
            </div>
            <div style="padding: 10px; background-color: #333333; border-radius: 8px; width: 30%; text-align: center;">
                <h3>Total Plantation Area (Acres)</h3>
                <p style="font-size: 30px; color: #4CAF50;">{total_plantation_area}</p>
            </div>
            <div style="padding: 10px; background-color: #333333; border-radius: 8px; width: 30%; text-align: center;">
                <h3>Missing Data Entries</h3>
                <p style="font-size: 30px; color: #f44336;">{missing_data_count}</p>
            </div>
        </div>
    """, unsafe_allow_html=True)

# Data Quality Issues Section
elif section == 'Data Quality Issues':
    st.subheader("⚠️ Data Quality Issues")
    
    # Check for missing or erroneous data
    missing_data = df[df.isnull().any(axis=1)]  # Rows with missing values
    
    # Search functionality to filter results by farmer name
    search_term = st.text_input("🔍 Search by Farmer Name", "").strip().lower()
    if search_term:
        missing_data = missing_data[missing_data['farmer_name'].str.lower().str.contains(search_term)]
    
    if not missing_data.empty:
        st.write(f"**Displaying {len(missing_data)} records with data quality issues:**")
        st.dataframe(missing_data)
    else:
        st.write("🎉 No data quality issues found!")

# Plantation Progress Section
elif section == 'Plantation Progress':
    st.subheader("🌿 Plantation Progress")
    
    # Check if plantation area percentage data exists
    if 'area_f4f_acre' in df.columns and 'total_land_area_acre' in df.columns:
        df['plantation_area_percentage'] = (df['area_f4f_acre'] / df['total_land_area_acre']) * 100
        st.bar_chart(df['plantation_area_percentage'])
    else:
        st.warning("⚠️ No plantation progress data available!")

# Location Insights Section
elif section == 'Location Insights':
    st.subheader("📍 Plantation Area by Location")
    
    # Display the plantation area by district or location
    if 'District' in df.columns and 'area_f4f_acre' in df.columns:
        location_distribution = df.groupby('District')['area_f4f_acre'].sum().reset_index()
        st.bar_chart(location_distribution.set_index('District')['area_f4f_acre'])
    else:
        st.warning("⚠️ Location or plantation area data is missing!")

# Footer with contact info
st.markdown("""
    ---
    **Developed by:** [Satyam Kumar](https://github.com/Satyam0775) 
    **📧 Contact:** Satyamrishav0013@gmail.com   
""")