I am new to the machine learning area. below mention my dataset.
Dataset

I did the prepossessing part and data visualization part. Below mention my coding.

    import math
    import pandas as pd
    import numpy as np
    import matplotlib.pyplot as plt
    from sklearn.preprocessing import MinMaxScaler
    from sklearn.metrics import mean_squared_error
    from keras.models import Sequential
    from keras.layers import Dense, LSTM, Dropout

    df = pd.read_csv('sample_data/covid19_full_data.csv')
    df

    df.isnull().sum()

    print('Dataset length before drop null values')
    len(df)

    df['date'] = pd.to_datetime(df['date'])

    aggregated_data = df.groupby('date').agg({
    'new_cases': 'sum',
    'new_deaths': 'sum',
    'total_cases': 'sum',
    'total_deaths': 'sum'
    }).reset_index()
    aggregated_data

    # Plotting new_cases over time
    plt.figure(figsize=(14, 7))
    plt.plot(aggregated_data['date'], aggregated_data['new_cases'], label="New Cases")
    plt.title('New COVID-19 Cases Over Time')
    plt.xlabel('Date')
    plt.ylabel('Number of New Cases')
    plt.legend()
    plt.show()

    plt.figure(figsize=(14, 7))
    plt.plot(aggregated_data['date'], aggregated_data['new_deaths'], label="New Deaths",       color="red")
    plt.title('New COVID-19 Deaths Over Time')
    plt.xlabel('Date')
    plt.ylabel('Number of New Deaths')
    plt.legend()
    plt.show()

    plt.figure(figsize=(14, 7))
    plt.plot(aggregated_data['date'], aggregated_data['total_cases'], label="Total Cases",      color="green")
    plt.title('Total COVID-19 Cases Over Time')
    plt.xlabel('Date')
    plt.ylabel('Total Number of Cases')
    plt.legend()
    plt.show()

    plt.figure(figsize=(14, 7))
    plt.plot(aggregated_data['date'], aggregated_data['total_deaths'], label="Total Deaths",    color="black")
    plt.title('Total COVID-19 Deaths Over Time')
    plt.xlabel('Date')
    plt.ylabel('Total Number of Deaths')
    plt.legend()
    plt.show()

how to do the feature extraction part to my approach. Please write the code for the feature extraction part and explain each step.