# Always suppress warnings for a smooth experience
import warnings; warnings.filterwarnings("ignore")
import numpy as np
np.random.seed(42)

# Data setup
import pandas as pd
url = 'https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_time_series/time_series_covid19_confirmed_global.csv'
df = pd.read_csv(url)
print(df.shape)
print(df.head(3))

# See basic info about the table and columns
df.info()
 

# Check for any missing values
print(df.isnull().sum().head())

# Get global daily total confirmed cases
date_cols = df.columns[4:]
global_total = df[date_cols].sum()
print(global_total.head())

# Plot global cases over time
import matplotlib.pyplot as plt
 
plt.figure(figsize=(10,5))
plt.plot(global_total.index, global_total.values)
plt.title("Worldwide Covid 19 Confirmed Cases Over Time")
plt.xlabel("Date")
plt.ylabel("Total Cases")
plt.xticks(rotation=45)
plt.tight_layout()
plt.show()

# Show first 10 days and last 10 days in the global total
print("First 10 days:")
print(global_total.head(10))
print("\nLast 10 days:")
print(global_total.tail(10))

# Pick a country to explore (for example, India)
india = df[df['Country/Region'] == 'India']
india_total = india[date_cols].sum()
 
plt.figure(figsize=(10,5))
plt.plot(india_total.index, india_total.values, color='orange')
plt.title("Covid 19 Confirmed Cases in India Over Time")
plt.xlabel("Date")
plt.ylabel("Total Cases")
plt.xticks(rotation=45)
plt.tight_layout()
plt.show()

# Let the user choose a country to plot
country_name = input("Type a country name, for example 'Italy': ")
country_data = df[df['Country/Region'] == country_name]
country_total = country_data[date_cols].sum()
 
plt.figure(figsize=(10,5))
plt.plot(country_total.index, country_total.values, color='green')
plt.title(f"Covid 19 Confirmed Cases in {country_name} Over Time")
plt.xlabel("Date")
plt.ylabel("Total Cases")
plt.xticks(rotation=45)
plt.tight_layout()
plt.show()

# Compare top 5 affected countries
top5 = df.groupby('Country/Region')[date_cols[-1]].sum().sort_values(ascending=False).head(5)
print("Top 5 countries by total confirmed cases:")
print(top5)

# Bar chart of top 5 countries
import seaborn as sns
 
plt.figure(figsize=(8,6))
sns.barplot(x=top5.values, y=top5.index, palette='Reds_r')
plt.xlabel("Total Confirmed Cases")
plt.ylabel("Country")
plt.title("Top 5 Countries by Confirmed Covid 19 Cases")
plt.tight_layout()
plt.show()

# Calculate new global cases per day
new_cases = global_total.diff().fillna(0).astype(int)
print(new_cases.head(10))

# Plot new global daily cases
plt.figure(figsize=(10,5))
plt.bar(new_cases.index, new_cases.values, color='blue')
plt.title("New Confirmed Covid 19 Cases Each Day (World)")
plt.xlabel("Date")
plt.ylabel("New Cases")
plt.xticks(rotation=45)
plt.tight_layout()
plt.show()