Project Analisis Data COVID-19 untuk Pemula dengan Python

pip install pandas matplotlib seaborn numpy

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from datetime import datetime

# URL dataset COVID-19
confirmed_url = "https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_time_series/time_series_covid19_confirmed_global.csv"
deaths_url = "https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_time_series/time_series_covid19_deaths_global.csv"
recovered_url = "https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_time_series/time_series_covid19_recovered_global.csv"

# Load data
confirmed = pd.read_csv(confirmed_url)
deaths = pd.read_csv(deaths_url)
recovered = pd.read_csv(recovered_url)

print("Confirmed Cases Data:")
print(confirmed.head())
print("\nDeaths Data:")
print(deaths.head())
print("\nRecovered Data:")
print(recovered.head())

print("\nConfirmed Data Shape:", confirmed.shape)
print("Deaths Data Shape:", deaths.shape)
print("Recovered Data Shape:", recovered.shape)

print("Missing Values in Confirmed Data:")
print(confirmed.isnull().sum())

print("\nMissing Values in Deaths Data:")
print(deaths.isnull().sum())

print("\nMissing Values in Recovered Data:")
print(recovered.isnull().sum())

# Isi missing values untuk Province/State dengan 'Unknown'
confirmed['Province/State'] = confirmed['Province/State'].fillna('Unknown')
deaths['Province/State'] = deaths['Province/State'].fillna('Unknown')
recovered['Province/State'] = recovered['Province/State'].fillna('Unknown')

# Isi missing values untuk Lat/Long dengan mean
confirmed['Lat'] = confirmed['Lat'].fillna(confirmed['Lat'].mean())
confirmed['Long'] = confirmed['Long'].fillna(confirmed['Long'].mean())

# Mengubah format data dari wide ke long
def melt_data(df, value_name):
    melted = df.melt(
        id_vars=['Province/State', 'Country/Region', 'Lat', 'Long'],
        var_name='Date',
        value_name=value_name
    )
    melted['Date'] = pd.to_datetime(melted['Date'])
    return melted

confirmed_long = melt_data(confirmed, 'Confirmed')
deaths_long = melt_data(deaths, 'Deaths')
recovered_long = melt_data(recovered, 'Recovered')

# Hitung total kasus global per hari
global_confirmed = confirmed_long.groupby('Date')['Confirmed'].sum()
global_deaths = deaths_long.groupby('Date')['Deaths'].sum()
global_recovered = recovered_long.groupby('Date')['Recovered'].sum()

# Plot perkembangan global
plt.figure(figsize=(14, 7))
plt.plot(global_confirmed.index, global_confirmed.values, label='Confirmed', color='blue')
plt.plot(global_deaths.index, global_deaths.values, label='Deaths', color='red')
plt.plot(global_recovered.index, global_recovered.values, label='Recovered', color='green')
plt.title('Global COVID-19 Cases Over Time')
plt.xlabel('Date')
plt.ylabel('Number of Cases')
plt.legend()
plt.grid()
plt.show()

# Pilih 10 negara dengan kasus tertinggi
top_countries = confirmed_long.groupby('Country/Region')['Confirmed'].max().nlargest(10)

plt.figure(figsize=(12, 6))
top_countries.plot(kind='bar', color='orange')
plt.title('Top 10 Countries by Confirmed Cases')
plt.xlabel('Country')
plt.ylabel('Confirmed Cases')
plt.xticks(rotation=45)
plt.show()

# Hitung rasio kematian dan kesembuhan
latest_date = confirmed_long['Date'].max()
latest_data = confirmed_long[confirmed_long['Date'] == latest_date].merge(
    deaths_long[deaths_long['Date'] == latest_date], 
    on=['Province/State', 'Country/Region', 'Date']
).merge(
    recovered_long[recovered_long['Date'] == latest_date],
    on=['Province/State', 'Country/Region', 'Date']
)

latest_data['Death Rate'] = (latest_data['Deaths'] / latest_data['Confirmed']) * 100
latest_data['Recovery Rate'] = (latest_data['Recovered'] / latest_data['Confirmed']) * 100

# Filter negara dengan lebih dari 1000 kasus
significant_countries = latest_data[latest_data['Confirmed'] > 1000]

# Plot 10 negara dengan death rate tertinggi
top_death_rates = significant_countries.nlargest(10, 'Death Rate')

plt.figure(figsize=(12, 6))
plt.bar(top_death_rates['Country/Region'], top_death_rates['Death Rate'], color='red')
plt.title('Top 10 Countries by Death Rate (Confirmed Cases > 1000)')
plt.xlabel('Country')
plt.ylabel('Death Rate (%)')
plt.xticks(rotation=45)
plt.show()

# Buat pivot table untuk heatmap
heatmap_data = confirmed_long.pivot_table(
    index='Country/Region',
    columns='Date',
    values='Confirmed',
    aggfunc='sum'
)

# Ambil 20 negara dengan kasus tertinggi
top_20 = heatmap_data.max(axis=1).nlargest(20).index
heatmap_data = heatmap_data.loc[top_20]

# Plot heatmap
plt.figure(figsize=(16, 10))
sns.heatmap(
    np.log1p(heatmap_data),  # Gunakan log untuk visualisasi yang lebih baik
    cmap='YlOrRd',
    linewidths=0.1
)
plt.title('COVID-19 Confirmed Cases Heatmap (Top 20 Countries)')
plt.xlabel('Date')
plt.ylabel('Country')
plt.show()

# Hitung kasus baru harian
global_confirmed_daily = global_confirmed.diff().fillna(0)
global_deaths_daily = global_deaths.diff().fillna(0)
global_recovered_daily = global_recovered.diff().fillna(0)

# Plot kasus baru harian dengan moving average 7 hari
plt.figure(figsize=(14, 7))
plt.plot(global_confirmed_daily.index, global_confirmed_daily.values, 
         label='Daily New Cases', color='blue', alpha=0.3)
plt.plot(global_confirmed_daily.index, global_confirmed_daily.rolling(7).mean(), 
         label='7-Day Moving Average', color='blue', linewidth=2)
plt.title('Global Daily New COVID-19 Cases')
plt.xlabel('Date')
plt.ylabel('New Cases')
plt.legend()
plt.grid()
plt.show()

pip install folium

import folium

# Buat peta dunia
world_map = folium.Map(location=[20, 0], zoom_start=2)

# Tambahkan data ke peta
for idx, row in latest_data.iterrows():
    if row['Confirmed'] > 1000:  # Hanya tampilkan negara dengan >1000 kasus
        folium.CircleMarker(
            location=[row['Lat'], row['Long']],
            radius=np.log(row['Confirmed'])*2,  # Ukuran berdasarkan log kasus
            popup=f"{row['Country/Region']}<br>Confirmed: {row['Confirmed']:,}<br>Deaths: {row['Deaths']:,}",
            color='red',
            fill=True,
            fill_color='red'
        ).add_to(world_map)

# Simpan peta
world_map.save('covid19_map.html')

print("=== COVID-19 ANALYSIS REPORT ===")
print(f"Last Update: {latest_date.strftime('%Y-%m-%d')}")
print(f"Total Global Cases: {global_confirmed.max():,}")
print(f"Total Global Deaths: {global_deaths.max():,}")
print(f"Total Global Recovered: {global_recovered.max():,}")
print(f"\nGlobal Death Rate: {(global_deaths.max()/global_confirmed.max())*100:.2f}%")
print(f"Global Recovery Rate: {(global_recovered.max()/global_confirmed.max())*100:.2f}%")

print("\nTop 5 Countries by Confirmed Cases:")
print(confirmed_long.groupby('Country/Region')['Confirmed'].max().nlargest(5))