app_test.py

import tensorflow as tf
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from pathlib import Path
from keras.models import model_from_json
import tensorflow as tf
import matplotlib.pyplot as plt
import joblib
import requests
import json
from datetime import datetime

def load_model(name):
    # Load JSON and create model
    json_file = open("%s.json" % name, "r")
    loaded_model_json = json_file.read()
    json_file.close()
    loaded_model = model_from_json(loaded_model_json)

    # Check if the weights file exists before loading
    weights_file = f"{name}.weights.h5"
    if not Path(weights_file).is_file():
        raise FileNotFoundError(f"Weight file {weights_file} not found.")
    
    # Load weights into the new model
    loaded_model.load_weights(weights_file)
    print("Loaded model from disk")
    return loaded_model

model = load_model("3_day_forecast_AQI_v5")

####################################

# Load the scalers
scaler_X = joblib.load('scaler_X_AQI.pkl')
scaler_y = joblib.load('scaler_y_AQI.pkl')

import requests
import pandas as pd
import joblib
import os
from datetime import datetime
# delhi  28.639638713652012, 77.19002000205269
# bhopal 23.23731292701139, 77.44433463788636
# ahemdabad 23.0364012974141, 72.58238347964425
# ankleshwar 21.62880896774956, 73.0043990197163
# jamnagar 22.3033564155508, 70.8012921707898
# 21.22050672027795  72.83355967457062#  
# 21.236796371788703, 72.8665479925569

# Define API parameters
api_key = "26daca1b78f44099a755b921be4bfcf1"  # Your WeatherAPI key
latitude = 21.236796371788703  # Example latitude
longitude = 72.8665479925569  #  # Example longitude
base_url = f"https://api.weatherbit.io/v2.0/current/airquality?lat={latitude}&lon={longitude}&key={api_key}"

# Make the API request
response = requests.get(base_url)
if response.status_code == 200:
    data = response.json()

# Extract forecast data
dx = [data['data'][0]]
test = pd.DataFrame(dx)

# Add time-based features
now = datetime.now()
current_time = now.strftime("%Y-%m-%d %H:%M:%S")
test = test[['pm25', 'pm10', 'no2', 'so2', 'co', 'aqi']]
test['Date'] = pd.to_datetime(current_time)
test['Day'] = test['Date'].dt.day
test['Month'] = test['Date'].dt.month
test['Hour'] = test['Date'].dt.hour
test = test[['pm25', 'pm10', 'no2', 'so2', 'co', 'aqi', 'Day', 'Month', 'Hour']]
test.columns = ['PM2.5', 'PM10', 'NO2', 'SO2', 'CO', 'AQI', 'Day', 'Month', 'Hour']

# Load scalers
scaler_X = joblib.load('scaler_X_AQI.pkl')
scaler_y = joblib.load('scaler_y_AQI.pkl')

# Standardize data and make predictions
data_normalized = scaler_X.transform(test)
prediction_Test = model.predict(data_normalized)
predictions_actual = scaler_y.inverse_transform(prediction_Test)
test['lat']= latitude
test['lon']= longitude
# Create a DataFrame for predictions
pred = pd.DataFrame(predictions_actual, columns=['AQI_step_1', 'AQI_step_2', 'AQI_step_3'])
df = pd.concat([test, pred], axis=1)

# Define the CSV file path
csv_file_path = "aqi_data.csv"

# Create the CSV file with headers if it doesn't exist
if not os.path.exists(csv_file_path):
    columns = ['PM2.5', 'PM10', 'NO2', 'SO2', 'CO', 'AQI', 'Day', 'Month', 'Hour', 'lat', 'lon', 'AQI_step_1', 'AQI_step_2', 'AQI_step_3']
    df_empty = pd.DataFrame(columns=columns)
    df_empty.to_csv(csv_file_path, index=False)

# Append new data to the existing CSV
df.to_csv(csv_file_path, mode='a', index=False, header=False)

print(f"Data appended to {csv_file_path}")


####################################


import requests
import json
from datetime import datetime

# Define API parameters
api_key = "26daca1b78f44099a755b921be4bfcf1"  # Your WeatherAPI key
# 21.195069775800516,72.79324648126439
# 21.22050672027795, 72.83355967457062
# 28.639638713652012,77.19002000205269
# 23.23731292701139,77.44433463788636,
# 23.0364012974141,72.58238347964425,
# 21.62880896774956,73.0043990197163,
# jamnagar 22.3033564155508, 70.8012921707898
# new delhi 28.619913380208967, 77.20633325621425

latitude = 21.236796371788703  # Example latitude
longitude = 72.8665479925569  #  # Example longitude

base_url = f"https://api.weatherbit.io/v2.0/forecast/airquality?lat={latitude}&lon={longitude}&key={api_key}"

# Make the API request
response = requests.get(base_url)

if response.status_code == 200:
    # Parse the returned JSON data
    data = response.json()
    
data

data=data['data']

from collections import defaultdict

# Group AQI values by date (ignoring the hour)
grouped_aqi = defaultdict(list)

for entry in data:
    # Extract date part only from the datetime (before the colon)
    date = entry['datetime'].split(':')[0]
    aqi = entry['aqi']
    grouped_aqi[date].append(aqi)

# Convert defaultdict to a regular dictionary
grouped_aqi = dict(grouped_aqi)

# Display the result
print(grouped_aqi)
index=11
key= grouped_aqi.keys()
samp={}
samp.clear()
for i in key:
    print(i)
    ls=grouped_aqi[i]
    if index<len(ls):
        print(ls[11])
        samp[i]=ls[11]
    else:
        print(ls[-1])
        samp[i]=ls[-1]
print(samp)
df = pd.DataFrame([samp])
df.columns=['AQI_currrent','AQI_step_1', 'AQI_step_2', 'AQI_step_3']
print(df)
# Define the CSV file path
csv_file_path = "aqi_data_actual_api.csv"

# Create the CSV file with headers if it doesn't exist
if not os.path.exists(csv_file_path):
    columns = ['AQI_currrent_API','AQI_step_1_API', 'AQI_step_2_API', 'AQI_step_3_API']
    df_empty = pd.DataFrame(columns=columns)
    df_empty.to_csv(csv_file_path, index=False)
    
# Append new data to the existing CSV
df.to_csv(csv_file_path, mode='a', index=False, header=False)


##########################################################


import folium
import matplotlib.pyplot as plt
from io import BytesIO
import base64
import pandas as pd


df1= pd.read_csv('aqi_data.csv')
df2= pd.read_csv('aqi_data_actual_api.csv')
data = pd.concat([df1,df2],axis=1)
data = data.head(3)
# Create the Folium map
map_center = [data['lat'].mean(), data['lon'].mean()]
m = folium.Map(location=map_center, zoom_start=10)

# AQI Color Legend
legend_html = """
<div style="
    position: fixed; 
    bottom: 20px; left: 20px; width: 350px; height: 225px; 
    background-color: white; 
    z-index:9999; font-size:14px; border:2px solid grey; 
    padding: 10px; overflow-y: auto;">
    <b>AQI Color Legend</b>
    <table style="width: 100%; border-collapse: collapse; text-align: left;">
        <thead>
            <tr style="border-bottom: 2px solid grey;">
                <th style="padding: 5px;">Color</th>
                <th style="padding: 5px;">Remark</th>
                <th style="padding: 5px;">Range</th>
            </tr>
        </thead>
        <tbody>
            <tr>
                <td><i style="background:green; width:15px; height:15px; display:inline-block; border:1px solid black;"></i></td>
                <td>Good</td>
                <td>0-50</td>
            </tr>
            <tr>
                <td><i style="background:yellow; width:15px; height:15px; display:inline-block; border:1px solid black;"></i></td>
                <td>Moderate</td>
                <td>51-100</td>
            </tr>
            <tr>
                <td><i style="background:orange; width:15px; height:15px; display:inline-block; border:1px solid black;"></i></td>
                <td>Unhealthy for Sensitive Groups</td>
                <td>101-150</td>
            </tr>
            <tr>
                <td><i style="background:red; width:15px; height:15px; display:inline-block; border:1px solid black;"></i></td>
                <td>Unhealthy</td>
                <td>151-200</td>
            </tr>
            <tr>
                <td><i style="background:purple; width:15px; height:15px; display:inline-block; border:1px solid black;"></i></td>
                <td>Very Unhealthy</td>
                <td>201-300</td>
            </tr>
            <tr>
                <td><i style="background:maroon; width:15px; height:15px; display:inline-block; border:1px solid black;"></i></td>
                <td>Hazardous</td>
                <td>301+</td>
            </tr>
        </tbody>
    </table>
</div>
"""
# Add the legend to the map
legend = folium.Element(legend_html)
m.get_root().html.add_child(legend)

# Function to generate a horizontal bar plot
def create_aqi_comparison_plot(data):
    fig, ax = plt.subplots(figsize=(5, 2))
    categories = ['DAY 1', 'DAY 2', 'DAY 3']
    actual_values = [data['AQI_step_1'], data['AQI_step_2'], data['AQI_step_3']]
    api_values = [data['AQI_step_1_API'], data['AQI_step_2_API'], data['AQI_step_3_API']]

    bar_width = 0.35
    index = range(len(categories))

    # Plot horizontal bars
    bars_actual = ax.barh(index, actual_values, bar_width, label="Model AQI", color='blue')
    bars_api = ax.barh([i + bar_width for i in index], api_values, bar_width, label="API AQI", color='green')

    # Add values to each bar
    max_value = 0  # Track the maximum value for axis limit adjustment
    for bar in bars_actual:
        value = bar.get_width()
        ax.text(value + 2, bar.get_y() + bar.get_height() / 2, 
                f'{value:.1f}', va='center', fontsize=10)
        max_value = max(max_value, value)
    for bar in bars_api:
        value = bar.get_width()
        ax.text(value + 2, bar.get_y() + bar.get_height() / 2, 
                f'{value:.1f}', va='center', fontsize=10)
        max_value = max(max_value, value)

    # Adjust x-axis limits to accommodate annotations
    ax.set_xlim(0, max_value * 1.2)

    # Customize y-ticks and labels
    ax.set_yticks([i + bar_width / 2 for i in index])
    ax.set_yticklabels(categories)
    ax.set_xlabel('AQI')
    ax.set_title('AQI Comparison')

    # Place legend outside the plot area
    ax.legend(loc='center left', bbox_to_anchor=(1, 0.5), frameon=False)

    plt.tight_layout()

    # Save the plot to a PNG image in memory
    buffer = BytesIO()
    plt.savefig(buffer, format="png", bbox_inches='tight')
    plt.close(fig)
    buffer.seek(0)

    # Encode the image to base64 to embed it in the HTML
    image_base64 = base64.b64encode(buffer.read()).decode()
    return f'<img src="data:image/png;base64,{image_base64}">'

# Function to determine AQI marker color
def get_color_for_aqi(aqi_value):
    if aqi_value <= 50:
        return 'green'
    elif aqi_value <= 100:
        return 'yellow'
    elif aqi_value <= 150:
        return 'orange'
    elif aqi_value <= 200:
        return 'red'
    elif aqi_value <= 300:
        return 'purple'
    else:
        return 'maroon'

# Add markers with AQI comparison plot
for _, row in data.iterrows():
    color = get_color_for_aqi(row['AQI_step_1'])
    popup_html = create_aqi_comparison_plot(row)
    folium.Marker(
        location=[row["lat"], row["lon"]],
        popup=folium.Popup(html=popup_html, max_width=500),
        #tooltip=row["name"],
        icon=folium.Icon(color=color)
    ).add_to(m)

# Save the map
m.save("aqi_forecast_with_legend.html")
m