app.py

import cv2
import numpy as np
import pandas as pd
import streamlit as st
from keras.models import load_model
from sklearn.preprocessing import OneHotEncoder, StandardScaler

# Load the pre-trained model
loaded_model = load_model('solar_irradiance_model.keras')

# Load the dataset for encoder and scaler setup
data = pd.read_csv('Solar_Irradiance.csv')
data['Latitude'] = data['Latitude'].str.rstrip('°').astype(float)
data['Longitude'] = data['Longitude'].str.rstrip('°').astype(float)

# Features and encoder/scaler setup
features = data[['Month', 'Hour', 'Latitude', 'Longitude', 'Panel_Capacity(W)', 'Panel_Efficiency', 'Wind_Speed(km/h)', 'Cloud_Cover(%)', 'temperature (°f)']]

encoder = OneHotEncoder(sparse_output=False, categories='auto')
categorical_features = features[['Month', 'Hour']]
encoder.fit(categorical_features)

scaler = StandardScaler()
numerical_features = features[['Latitude', 'Longitude', 'Panel_Capacity(W)', 'Panel_Efficiency', 'Wind_Speed(km/h)', 'Cloud_Cover(%)', 'temperature (°f)']]
scaler.fit(numerical_features)

# Shadow Removal Function
def remove_shadows(image):
    """Removes shadows using illumination normalization."""
    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
    blurred = cv2.GaussianBlur(gray, (21, 21), 0)
    normalized = cv2.divide(gray, blurred, scale=255)
    result = cv2.cvtColor(normalized, cv2.COLOR_GRAY2BGR)
    return result

# Preprocess Image with Canny Edge Detection
def apply_canny_edge(image):
    # Step 1: Remove shadows
    shadow_free_image = remove_shadows(image)
    
    # Step 2: Convert to grayscale
    gray = cv2.cvtColor(shadow_free_image, cv2.COLOR_BGR2GRAY)
    
    # Step 3: Apply Canny edge detection
    edges = cv2.Canny(gray, 100, 200)
    
    # Step 4: Dilate the edges to make them more prominent
    kernel = np.ones((5, 5), np.uint8)
    dilated_edges = cv2.dilate(edges, kernel, iterations=2)
    
    return dilated_edges

# Predict Irradiance Function
def predict_irradiance(month, hour, latitude, longitude, panel_capacity, panel_efficiency, wind_speed, cloud_cover, temperature):
    # Ensure the month is passed as a string (e.g., "January", "February")
    # Encode the month and hour using the same encoder fitted during training
    encoded_month_hour = encoder.transform([[month, hour]])
    
    # Scale the numerical features
    scaled_features = scaler.transform([[latitude, longitude, panel_capacity, panel_efficiency, wind_speed, cloud_cover, temperature]])
    
    # Combine the encoded categorical features with the scaled numerical features
    processed_features = np.concatenate((encoded_month_hour, scaled_features), axis=1)
    
    # Reshape features to match LSTM input
    reshaped_features = np.reshape(processed_features, (1, 1, processed_features.shape[1]))
    
    # Predict the irradiance using the trained model
    predicted_irradiance = loaded_model.predict(reshaped_features)
    
    # Ensure the result is not negative
    return max(predicted_irradiance[0][0], 0.0)

# Streamlit Interface Setup
st.title("Solar Irradiance Predictor")

# Upload image
uploaded_image = st.file_uploader("Upload Rooftop Image", type=["jpg", "jpeg", "png"])

if uploaded_image is not None:
    image = np.array(cv2.imdecode(np.frombuffer(uploaded_image.read(), np.uint8), 1))

    # User inputs
    month = st.selectbox("Month", ['January', 'february', 'march', 'april', 'may', 'june', 'july', 'august', 'september', 'october', 'november', 'december'])
    hour = st.slider("Hour", 0, 23, step=1)
    latitude = st.number_input("Latitude", value=28.57)
    longitude = st.number_input("Longitude", value=77.33)
    panel_capacity = st.number_input("Panel Capacity (W)", value=500.0)
    panel_efficiency = st.number_input("Panel Efficiency (0-1)", value=0.15)
    wind_speed = st.number_input("Wind Speed (km/h)", value=6.44)
    cloud_cover = st.number_input("Cloud Cover (%)", value=17.7)
    temperature = st.number_input("Temperature (°F)", value=55.0)

    # Predict Button
    if st.button("Predict Irradiance"):
        irradiance = predict_irradiance(month, hour, latitude, longitude, panel_capacity, panel_efficiency, wind_speed, cloud_cover, temperature)

        # Display results
        st.subheader("Results")
        st.text(f"Predicted Irradiance: {irradiance:.2f} W/m²")