# Always suppress warnings for a beginner-friendly experience
import warnings
warnings.filterwarnings('ignore')

# Let us import our basic analysis tools
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
np.random.seed(42)

# Data setup (COVID-19 Global Cases)
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_covid = pd.read_csv(url)
print(df_covid.shape)
print(df_covid.head(3))

# Look at the first few column names and check for missing values
print('Columns:', df_covid.columns[:10].tolist())
print('Any missing:', df_covid.isnull().any().any())
 
 

# See all unique country names
print(sorted(df_covid['Country/Region'].unique())[:10])
print('Total countries:', df_covid['Country/Region'].nunique())

# Convert date columns from text to useable format (pandas DateTime)
date_cols = df_covid.columns[4:]
df_long = df_covid.melt(id_vars=['Province/State', 'Country/Region', 'Lat', 'Long'], var_name='Date', value_name='Confirmed')
df_long['Date'] = pd.to_datetime(df_long['Date'])

# Plot line chart of confirmed cases in Italy
country = 'Italy'
country_data = df_long[df_long['Country/Region'] == country].groupby('Date')['Confirmed'].sum()
plt.figure(figsize=(10,5))
plt.plot(country_data.index, country_data.values)
plt.title(f'COVID-19 Confirmed Cases in {country}')
plt.xlabel('Date')
plt.ylabel('Confirmed Cases')
plt.grid(True)
plt.show()

# Practice: Let the user pick a country to plot COVID-19 trends interactively
chosen_country = input('Enter a country to visualize: ')
country_data2 = df_long[df_long['Country/Region'] == chosen_country].groupby('Date')['Confirmed'].sum()
plt.figure(figsize=(10,5))
plt.plot(country_data2.index, country_data2.values, color='orange')
plt.title(f'COVID-19 Confirmed Cases in {chosen_country}')
plt.xlabel('Date')
plt.ylabel('Confirmed Cases')
plt.grid(True)
plt.show()

# Visualize monthly new COVID-19 cases for Italy
monthly = country_data.diff().resample('M').sum()
plt.figure(figsize=(10,5))
plt.bar(monthly.index.strftime('%Y-%m'), monthly.values)
plt.title('Italy Monthly New COVID-19 Cases')
plt.xlabel('Month')
plt.ylabel('New Cases')
plt.xticks(rotation=45)
plt.grid(True, axis='y')
plt.tight_layout()
plt.show()

# Compare two countries side by side for 2020
country1 = 'Italy'
country2 = 'India'
data1 = df_long[(df_long['Country/Region']==country1) & (df_long['Date']<'2021-01-01')].groupby('Date')['Confirmed'].sum()
data2 = df_long[(df_long['Country/Region']==country2) & (df_long['Date']<'2021-01-01')].groupby('Date')['Confirmed'].sum()
plt.figure(figsize=(10,5))
plt.plot(data1.index, data1.values, label=country1, color='red')
plt.plot(data2.index, data2.values, label=country2, color='blue')
plt.title('COVID-19: Italy vs India (2020)')
plt.xlabel('Date')
plt.ylabel('Confirmed Cases')
plt.legend()
plt.show()

# Export cleaned tidy COVID data to CSV for future use
df_long.to_csv('tidy_covid_data.csv', index=False)
print('Saved as tidy_covid_data.csv')

# Data setup (Titanic Dataset)
import pandas as pd
url = 'https://raw.githubusercontent.com/datasciencedojo/datasets/master/titanic.csv'
df_titanic = pd.read_csv(url)
print(df_titanic.shape)
print(df_titanic.head(3))

# Practice: Find number of missing entries in Age column
missing_age = df_titanic['Age'].isnull().sum()
print('Missing Age values:', missing_age)