import streamlit as st
import random
import numpy as np
from deap import base, creator, tools, algorithms
import folium
from streamlit_folium import folium_static

st.title('UAV Genetic Algorithm (Evolutionary Algorithm) X-Shaped Flight Pattern')
st.image('UAV_GA_Path_4.jpeg', caption='UAV Genetic Algorithm Path 4')
st.write('一。 Nico Maulen B2B Lean Gatti - Techengue Vol 1 - Tech & Latin House')
st.write('二。 GUAY [TECH HOUSE REMIX] Ozuna, Bad Gyal')
st.write('三。 KAROL G, Feid, DFZM ft. Ovy On The Drums, J Balvin, Maluma, Ryan Castro, Blessd - +57')
st.write('四。 Dei V - Quickie (Official Video)')
st.image('UAV_GA_Path_2.webp', caption='UAV Genetic Algorithm Path 2')

# Define the target M-shape pattern in Miami
#target_pattern = np.array([
   # [25.7743, -80.1937],   # Top left of M
   # [25.76815, -80.1868],  # Bottom left of M
   # [25.765, -80.183],     # Middle top of M
   # [25.762, -80.18],      # Bottom middle of M
   #  [25.765, -80.177],     # Middle top of M (right side)
   #  [25.768, -80.18],      # Bottom right of M
   #  [25.7743, -80.1868]    # Top right of M
# ])
# Target Pattern set of coordinates does not form the letter M shape

# Define the target M-shape pattern in Miami
#target_pattern = np.array([
   # [25.76815, -80.1868],  # Top left of M
   # [25.762, -80.18],      # Bottom left of M
   # [25.765, -80.183],     # Middle of M
   # [25.768, -80.18],      # Bottom right of M
   # [25.7743, -80.1868]    # Top right of M
# ])
# Target Pattern set of coordinates does not form the letter M shape

# Define the target pattern [Flying in the shape of an X-Pattern]
target_pattern = np.array([
    [25.76815, -80.1868],
    [25.7743, -80.1937],
    [25.762, -80.18],
    [25.76815, -80.1868],
    [25.7743, -80.18],
    [25.762, -80.1937]
])

# Define the target pattern [Flying in the shape of an ∞-Pattern]
#target_pattern = np.array([
    #[25.76815, -80.1868],  # Start of the figure-eight
    #[25.765, -80.183],     # Top of the left loop
    #[25.762, -80.18],      # Bottom of the left loop
    #[25.765, -80.183],     # Middle of the figure-eight
    #[25.768, -80.18],      # Bottom of the right loop
    #[25.7743, -80.1868],   # Top of the right loop
    #[25.76815, -80.1868]   # End of the figure-eight
#])



# Define the number of points in the optimized pattern
num_points = len(target_pattern)

# Define the range for latitude and longitude
lat_range = (25.76, 25.78)
lon_range = (-80.20, -80.17)

# Create the fitness function and individual
creator.create("FitnessMin", base.Fitness, weights=(-1.0,))
creator.create("Individual", list, fitness=creator.FitnessMin)

toolbox = base.Toolbox()

# Attribute generator
toolbox.register("attr_lat", random.uniform, lat_range[0], lat_range[1])
toolbox.register("attr_lon", random.uniform, lon_range[0], lon_range[1])

# Structure initializers
toolbox.register("individual", tools.initCycle, creator.Individual,
                 (toolbox.attr_lat, toolbox.attr_lon), n=num_points)
toolbox.register("population", tools.initRepeat, list, toolbox.individual)

# Define the objective function
def objective_function(optimized_pattern, target_pattern):
    return np.sum((np.array(optimized_pattern) - np.array(target_pattern)) ** 2)

def eval_pattern(individual):
    optimized_pattern = np.array(individual).reshape(-1, 2)
    return objective_function(optimized_pattern, target_pattern),

toolbox.register("evaluate", eval_pattern)
toolbox.register("mate", tools.cxBlend, alpha=0.5)
toolbox.register("mutate", tools.mutGaussian, mu=0, sigma=0.1, indpb=0.2)
toolbox.register("select", tools.selTournament, tournsize=3)

# Genetic Algorithm Parameters
pop_size = 100
ngen = 500
cxpb = 0.7
mutpb = 0.2

# Initialize population
pop = toolbox.population(n=pop_size)

# Capture fitness values over generations
stats = tools.Statistics(lambda ind: ind.fitness.values)
stats.register("avg", np.mean)
stats.register("min", np.min)
logbook = tools.Logbook()

# Run the genetic algorithm
algorithms.eaSimple(pop, toolbox, cxpb, mutpb, ngen, stats=stats, halloffame=None, verbose=True)

# Get the best individual
best_individual = tools.selBest(pop, k=1)[0]
best_pattern = np.array(best_individual).reshape(-1, 2)

# Print the original target pattern
st.write("Original Target Pattern:")
st.write(target_pattern)
st.image('UAV_GA_Path_3.jpeg', caption='UAV Genetic Algorithm Path 3')

# Print the optimized pattern
st.write("Optimized Pattern:")
st.write(best_pattern)
st.write("Objective Function Value:", objective_function(best_pattern, target_pattern))
st.image('UAV_GA_Path_1.jpeg', caption='UAV Genetic Algorithm Path 1')

# Create a Folium map centered around the target pattern
m = folium.Map(location=[25.76815, -80.1868], zoom_start=13)

# Create feature groups for the target pattern and optimized pattern
target_group = folium.FeatureGroup(name='Target Pattern')
optimized_group = folium.FeatureGroup(name='Optimized Pattern')

# Add markers for the target pattern to the target group
for point in target_pattern:
    folium.Marker(location=point, icon=folium.Icon(color='red', icon='info-sign')).add_to(target_group)

# Add markers for the optimized pattern to the optimized group
for point in best_pattern:
    folium.Marker(location=point, icon=folium.Icon(color='blue', icon='info-sign')).add_to(optimized_group)

# Add a Polyline for the optimized pattern to the optimized group
folium.PolyLine(locations=best_pattern, color='blue', weight=3, opacity=1).add_to(optimized_group)

# Add labels for the target pattern and optimized pattern
folium.Marker(
    location=[25.76815, -80.1868],
    icon=folium.DivIcon(
        icon_size=(150,36),
        icon_anchor=(0, -30),  # Shift south by 30 pixels
        html='<div style="font-size: 18pt; color: red;">Target Pattern</div>',
    )
).add_to(target_group)

folium.Marker(
    location=[25.7743, -80.18],
    icon=folium.DivIcon(
        icon_size=(150,36),
        icon_anchor=(30, 0),  # Shift right by 30 pixels
        html='<div style="font-size: 18pt; color: blue;">Optimized Pattern</div>',
    )
).add_to(optimized_group)

# Add the feature groups to the map
target_group.add_to(m)
optimized_group.add_to(m)

# Add layer control to the map
folium.LayerControl().add_to(m)

st.image('UAV_GA_Path_6.jpeg', caption='UAV Genetic Algorithm Path 6')
# Display the Folium map in Streamlit
st.write("Map of Target and Optimized Patterns:")
folium_static(m)
st.image('UAV_GA_Path_5.jpeg', caption='UAV Genetic Algorithm Path 5')