# Import required libraries and suppress warnings
import warnings
from statsmodels.tools.sm_exceptions import ConvergenceWarning, ValueWarning
warnings.filterwarnings("ignore", category=ValueWarning)
warnings.filterwarnings("ignore", category=ConvergenceWarning)
warnings.filterwarnings("ignore", category=RuntimeWarning)  # e.g., from log/exp on edge values
import warnings; warnings.filterwarnings('ignore')
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt

# Data setup: download and load with pandas
url = 'https://raw.githubusercontent.com/jbrownlee/Datasets/master/airline-passengers.csv'
df = pd.read_csv(url)

# Show shape and first 5 rows
print('Shape of table:', df.shape)
df.head()

# Quick line plot to visualize time series data
plt.figure(figsize=(8,4))
plt.plot(df['Month'], df['Passengers'], marker='o')
plt.title('Passengers Over Time')
plt.xlabel('Month')
plt.ylabel('Number of Passengers')
plt.xticks(rotation=45)
plt.tight_layout()
plt.show()

# Make up a tiny grid of numbers to illustrate heatmap basics
import numpy as np
data = np.array([[1, 4, 3],
                 [2, 0, 8],
                 [6, 3, 5]])
sns.heatmap(data, annot=True, cmap='YlGnBu')
plt.title('Toy Example: Heatmap of Numbers')
plt.show()

# Create a small DataFrame with random numbers for demo
np.random.seed(0)
mini_df = pd.DataFrame({
    'A': np.random.rand(8),
    'B': np.random.rand(8),
    'C': np.random.rand(8)*2 + 1
})
mini_corr = mini_df.corr()
print('Small correlation matrix:')
print(mini_corr.round(2))

# Draw a heatmap of the correlation matrix
sns.heatmap(mini_corr, annot=True, cmap='coolwarm', center=0)
plt.title('Correlation Matrix Heatmap (Mini Example)')
plt.show()

# Extract year and month columns
df['Year'] = df['Month'].str[:4]
df['MonthNum'] = df['Month'].str[5:7]

# Group by year and month, get mean passenger count
pivot = df.pivot_table(values='Passengers', index='Year', columns='MonthNum', aggfunc='mean')
pivot.head()

# Heatmap of passenger numbers by month and year
plt.figure(figsize=(10,6))
sns.heatmap(pivot, annot=True, fmt='.0f', cmap='YlOrRd')
plt.title('Passengers by Year and Month: Heatmap')
plt.xlabel('Month')
plt.ylabel('Year')
plt.show()

# Calculate correlation matrix for all numeric columns
# Ensure only numeric columns are included for correlation
numeric_cols = df.select_dtypes(include='number')
corr = numeric_cols.corr()
print('Correlation matrix for passengers data:')
print(corr.round(2))

# Heatmap for the dataset's correlation matrix
sns.heatmap(corr, annot=True, cmap='vlag', center=0)
plt.title('Passengers Dataset Correlation Heatmap')
plt.show()

# Get month averages across all years
month_means = df.groupby('MonthNum')['Passengers'].mean()
print('Average passengers by month:')
print(month_means.sort_values(ascending=False))

# Visualize with a bar heatmap
plt.figure(figsize=(8,2))
sns.heatmap([month_means.values], annot=True, cmap='YlOrBr', cbar=True)
plt.yticks([])
plt.xticks(ticks=np.arange(12)+.5, labels=month_means.index, rotation=0)
plt.title('Average Passengers by Month: Heatmap')
plt.xlabel('Month (MM)')
plt.show()

# Check for missing values
print('Has missing data?')
print(df.isnull().any())