app.py

import streamlit as st
import pandas as pd
import numpy as np
from sklearn.neighbors import KNeighborsRegressor
from geopy.distance import geodesic
import googlemaps
from geopy.exc import GeocoderTimedOut

# Function to calculate distance in meters between two coordinates
def calculate_distance(lat1, lon1, lat2, lon2):
    coords_1 = (lat1, lon1)
    coords_2 = (lat2, lon2)
    return geodesic(coords_1, coords_2).meters

# Function to apply KNN and return V_oferta values
def knn_predict(df, target_column, features_columns, k=5):
    # Separate features and target variable
    X = df[features_columns]
    y = df[target_column]

    # Create KNN regressor
    knn = KNeighborsRegressor(n_neighbors=k)

    # Fit the model
    knn.fit(X, y)

    # Use the model to predict V_oferta for the filtered_data
    predictions = knn.predict(df[features_columns])

    return predictions

# Set wide mode
st.set_page_config(layout="wide")

# Set dark theme
st.markdown(
    """
    <style>
        @font-face {font-family: 'Quicksand';
        src: url('font/Quicksand-VariableFont_wght.ttf') format('truetype');

        }
        body {
            color: white;
            background-color: #1e1e1e;
            font-family: 'Quicksand', sans-serif;
        }
        .st-df-header, .st-df-body, .st-df-caption {
            color: #f8f9fa;  /* Bootstrap table header text color */
        }
        .st-eb {
            background-color: #343a40;  /* Streamlit exception box background color */
        }
    </style>
    """,
    unsafe_allow_html=True
)


# Create a DataFrame with sample data
data = pd.read_excel('ven_fim_PEDÓ_nov_23.xlsx')

# Initialize variables to avoid NameError
selected_coords = 'Direcionada'
radius_visible = True
custom_address_initial = 'Centro, Lajeado - RS, Brazil'  # Initial custom address
custom_lat = data['latitude'].median()
custom_lon = data['longitude'].median()
radius_in_meters = 1500
filtered_data = data  # Initialize with the entire dataset

# Find the maximum distance between coordinates
max_distance = 0
for index, row in data.iterrows():
    distance = calculate_distance(row['latitude'], row['longitude'], data['latitude'].mean(), data['longitude'].mean())
    if distance > max_distance:
        max_distance = distance

# Calculate a zoom level based on the maximum distance
zoom_level = round(17 - np.log10(max_distance))

# Set font to 'Quicksand' for title_html
title_html = """
        <style>
        @font-face {font-family: 'Quicksand';
        src: url('font/Quicksand-VariableFont_wght.ttf') format('truetype');
        }
        body {{
            font-family: 'Quicksand', sans-serif;
        }}
    </style>
    <span style='color: gray; font-size: 50px;'>aval</span>
    <span style='color: white; font-size: 50px;'>ia</span>
    <span style='color: gray; font-size: 50px;'>.NEXUS</span>
    """

# Set font to 'Quicksand' for factor_html
factor_html = """
    <style>
        @font-face {font-family: 'Quicksand';
        src: url('font/Quicksand-VariableFont_wght.ttf') format('truetype');
        }
        body {{
            font-family: 'Quicksand', sans-serif;
        }}
    </style>
    <a href='https://huggingface.co/spaces/DavidSB/avaliaFACTOR' target='_blank' style='text-decoration: none; color: inherit;'>
    <span style='color: gray; font-size: 20px;'>aval</span>
    <span style='color: white; font-size: 20px;'>ia</span>
    <span style='color: gray; font-size: 20px;'>.FACTOR</span>
"""

# Set font to 'Quicksand' for evo_html
evo_html = """
    <style>
        @font-face {font-family: 'Quicksand';
        src: url('font/Quicksand-VariableFont_wght.ttf') format('truetype');
        }
        body {{
            font-family: 'Quicksand', sans-serif;
        }}
    </style>
    <a href='https://huggingface.co/spaces/DavidSB/avalia.EVO' target='_blank' style='text-decoration: none; color: inherit;'>
    <span style='color: gray; font-size: 20px;'>aval</span>
    <span style='color: white; font-size: 20px;'>ia</span>
    <span style='color: gray; font-size: 20px;'>.EVO</span>
"""


# Create a sidebar for controls
with st.sidebar:
    #st.title('avalia.se')

    st.sidebar.markdown(title_html, unsafe_allow_html=True)

    # Add a dropdown for filtering "Tipo"
    selected_tipo = st.selectbox('Filtrar por Tipo', data['Tipo'].unique())

    data = data[data['Tipo'] == selected_tipo]
    
    selected_coords = st.selectbox('Selecione o tipo de pesquisa', ['Ampla', 'Direcionada'])

    if selected_coords == 'Direcionada':
        custom_address = st.text_input('Informe o endereço', custom_address_initial)
        radius_visible = True  # Show radius slider for custom coordinates
        # No need to initialize max_distance_all here
    else:
        custom_address = "Lajeado, Rio Grande do Sul, Brazil"  # Default address
        radius_visible = False  # Hide radius slider for random coordinates
        max_distance_all = 0  # Initialize max_distance_all here

        max_distance_all = 0  # Initialize max_distance_all here

    # Geocode the custom address using the Google Maps API
    gmaps = googlemaps.Client(key='AIzaSyDoJ6C7NE2CHqFcaHTnhreOfgJeTk4uSH0')  # Replace with your API key

    try:
        location = gmaps.geocode(custom_address)[0]['geometry']['location']
        custom_lat, custom_lon = location['lat'], location['lng']
    except (IndexError, GeocoderTimedOut):
        st.error("Erro: Não foi possível geocodificar o endereço fornecido. Por favor, verifique e tente novamente.")

    # Slider for setting the zoom level
    if selected_coords == 'Direcionada':
        zoom_level = st.slider('Nível de zoom', min_value=1, max_value=15, value=zoom_level)
    else:
        for index, row in data.iterrows():
            distance_all = calculate_distance(row['latitude'], row['longitude'], data['latitude'].mean(), data['longitude'].mean())
            if distance_all > max_distance_all:
                max_distance_all = distance_all

        # Calculate a zoom level based on the maximum distance of the entire dataset
        zoom_level_all = round(15 - np.log10(max_distance_all))

        # Slider for setting the zoom level based on the entire dataset
        zoom_level = st.slider('Nível de zoom', min_value=1, max_value=15, value=zoom_level_all)

    # Conditionally render the radius slider
    if radius_visible:
        radius_in_meters = st.slider('Selecione raio (em metros)', min_value=100, max_value=5000, value=1000)

    # Add sliders to filter data based
    atotal_range = st.slider('Área Total', float(data['Atotal'].min()), float(data['Atotal'].max()), (float(data['Atotal'].min()), float(data['Atotal'].max())))
    apriv_range = st.slider('Área Privativa', float(data['Apriv'].min()), float(data['Apriv'].max()), (float(data['Apriv'].min()), float(data['Apriv'].max())))
    dorm_range = st.slider('Dormitórios', float(data['Dorm'].min()), float(data['Dorm'].max()), (float(data['Dorm'].min()), float(data['Dorm'].max())))
    banho_range = st.slider('Banheiros', float(data['Banheiro'].min()), float(data['Banheiro'].max()), (float(data['Banheiro'].min()), float(data['Banheiro'].max())))
    vaga_range = st.slider('Vaga de estacionamento', float(data['Vaga'].min()), float(data['Vaga'].max()), (float(data['Vaga'].min()), float(data['Vaga'].max())))

    # Add checkboxes for dummy features
    elev_checkbox = st.checkbox('Elevador')
    churr_checkbox = st.checkbox('Churrasqueira')
    esq_checkbox = st.checkbox('Duas ou mais frentes')

    # Transform checkbox values into 1s and 0s
    elev_value = 1 if elev_checkbox else 0
    churr_value = 1 if churr_checkbox else 0
    esq_value = 1 if esq_checkbox else 0

    data = data[(data['Tipo'] == selected_tipo) &
            (data['Atotal'] == atotal_range) &
            (data['Apriv'] == apriv_range) &
            (data['Dorm'] == dorm_range) &
            (data['Banheiro'] == banho_range) &
            (data['Vaga'] == vaga_range) &  
            (data['Elevador'] == elev_value) &
            (data['Churrasq'] == churr_value) &
            (data['Lot_pos'] == esq_value)]


    # Links to other apps at the bottom of the sidebar
    st.sidebar.markdown(factor_html, unsafe_allow_html=True)
    st.sidebar.markdown(evo_html, unsafe_allow_html=True)


# Filter data based on the radius
if selected_coords == 'Direcionada':
    filtered_data = data[data.apply(lambda x: calculate_distance(x['latitude'], x['longitude'], custom_lat, custom_lon), axis=1) <= radius_in_meters]
    filtered_data = filtered_data.dropna()  # Drop rows with NaN values

# Add a custom CSS class to the map container
st.markdown(f"""<style>
.map {{
  width: 100%;
  height: 100vh;
}}
</style>""", unsafe_allow_html=True)

# Determine which area feature to use for prediction
filtered_data['area_feature'] = np.where(filtered_data['Apriv'] != 0, filtered_data['Apriv'], filtered_data['Atotal'])

# Check if KNN should be applied
if selected_coords == 'Direcionada' and radius_visible:
    # Apply KNN and get predicted V_oferta values
    predicted_V_oferta = knn_predict(filtered_data, 'V_oferta', ['latitude', 'longitude', 'area_feature'])  # Update with your features
    # Add predicted V_oferta values to filtered_data
    filtered_data['Predicted_V_oferta'] = predicted_V_oferta

# Display the map and filtered_data
with st.container():
    if selected_coords == 'Direcionada':
        st.map(filtered_data, zoom=zoom_level, use_container_width=True)
    elif selected_coords == 'Ampla':
        st.map(data, zoom=zoom_level, use_container_width=True)

# Display the predicted V_oferta values if applicable
if 'Predicted_V_oferta' in filtered_data.columns:
    st.write("Valores (R$/m²) previstos com algoritmo KNN:")
    st.write(filtered_data[['latitude', 'longitude', 'V_oferta', 'Predicted_V_oferta']])