import warnings
warnings.filterwarnings("ignore")
# Import core modules
import pandas as pd
import matplotlib.pyplot as plt
import plotly.express as px
 
 

# Data setup
url = "https://raw.githubusercontent.com/jbrownlee/Datasets/master/airline-passengers.csv"
df = pd.read_csv(url)
print("Shape:", df.shape)
df.head()

# Convert Month string to datetime, check types
df['Month'] = pd.to_datetime(df['Month'])
print(df.dtypes)

# Simple line plot of passengers over time
plt.figure(figsize=(10,5))
plt.plot(df['Month'], df['Passengers'], marker='.')
plt.title('Monthly Airline Passengers')
plt.xlabel('Month')
plt.ylabel('Number of Passengers')
plt.grid(True)
plt.show()

# Interactive plotly line plot
fig = px.line(df, x='Month', y='Passengers', title='Monthly Airline Passengers (Interactive)')
fig.show()

# Let us highlight the trend with a rolling mean
df['MA12'] = df['Passengers'].rolling(window=12).mean()
plt.figure(figsize=(10,5))
plt.plot(df['Month'], df['Passengers'], alpha=0.5, label='Passengers')
plt.plot(df['Month'], df['MA12'], color='red', label='12-Month Average')
plt.legend()
plt.title('Passengers and 12-Month Trend')
plt.show()

# Handling missing data safely
print('Any missing? ', df.isnull().values.any())
df2 = df.copy()
df2.loc[5, 'Passengers'] = None  # Simulate a missing value
print('Any missing now?', df2.isnull().values.any())
df2['Passengers'].fillna(method='ffill', inplace=True)
print('Missing after fill:', df2['Passengers'].isnull().sum())

# Zoom in on a single year
mask = (df['Month'] >= '1957-01-01') & (df['Month'] < '1958-01-01')
df_1957 = df[mask]
plt.figure(figsize=(8,4))
plt.plot(df_1957['Month'], df_1957['Passengers'], marker='o')
plt.title('Passengers in 1957')
plt.xlabel('Month')
plt.ylabel('Passengers')
plt.show()

# Multiple lines: compare different years
for yr in [1956, 1957, 1958]:
    mask = (df['Month'].dt.year == yr)
    plt.plot(df.loc[mask, 'Month'].dt.month, df.loc[mask, 'Passengers'], label=str(yr))
plt.title('Compare 1956, 1957, and 1958')
plt.xlabel('Month')
plt.ylabel('Passengers')
plt.legend()
plt.show()

# Add customizations: color, style, labels
plt.figure(figsize=(10,5))
plt.plot(df['Month'], df['Passengers'], 'g--', label='Passengers')
plt.title('Styled Time Series Plot')
plt.xlabel('Time')
plt.ylabel('People Flying')
plt.legend()
plt.show()

# Plotly: add range slider and buttons
fig = px.line(df, x='Month', y='Passengers', title='Passengers with Range Slider')
fig.update_layout(xaxis_rangeslider_visible=True,
                  updatemenus=[
                      dict(type='buttons',
                           showactive=False,
                           buttons=[
                               dict(label='Linear',
                                    method='relayout',
                                    args=[{'yaxis.type': 'linear'}]),
                               dict(label='Log',
                                    method='relayout',
                                    args=[{'yaxis.type': 'log'}])
                           ])
                  ])
fig.show()

# Annotate an extreme point
mx_idx = df['Passengers'].idxmax()
mx_month = df.loc[mx_idx, 'Month']
mx_val = df.loc[mx_idx, 'Passengers']
plt.figure(figsize=(10,5))
plt.plot(df['Month'], df['Passengers'])
plt.scatter([mx_month], [mx_val], color='red', zorder=5)
plt.annotate('Peak Passengers', (mx_month, mx_val), xytext=(mx_month, mx_val+50),
             arrowprops={'arrowstyle':'->', 'color':'red'})
plt.title('Annotate Highest Point')
plt.show()

# Save a plot to file for reports
plt.figure(figsize=(10,5))
plt.plot(df['Month'], df['Passengers'])
plt.title('Report Example')
plt.savefig('report_plot.png')
plt.close()