import warnings; warnings.filterwarnings('ignore')

# This line tells Python to suppress warning messages.
# Warnings often show up when using data science tools.
# Keeping them hidden makes things less distracting for new users.

# Let us start with a simple variable.
city = "London"
print(city)

# Python stores text inside quote marks.

# You can also store numbers.
passengers = 250
print(passengers)

# Lists help us group many items. Let us list some major cities.
cities = ["London", "Paris", "New York", "Tokyo"]
print(cities)

# Access an item from a list using its position (starting from 0).
print(cities[1])

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

# Plot airline passenger counts to see patterns over time.
import matplotlib.pyplot as plt
df.plot(x="Month", y="Passengers", legend=False, title="Airline Passengers Over Time")
plt.ylabel("Passengers")
plt.show()

# Let us print the month with the highest passenger number.
max_row = df[df["Passengers"] == df["Passengers"].max()]
print("Busiest month:", max_row["Month"].values[0])

# Create a list of all months.
months = df["Month"].tolist()
print(months[:5])  # Show the first five months

# Calculate how many months had more than 400 passengers.
over_400 = df[df["Passengers"] > 400]
print("Months with over 400 passengers:", over_400.shape[0])

# Safe access: What if a month is missing in the data?
search_month = input("Enter a month (like 1950-08): ")
if search_month in months:
    print("Yes,", search_month, "is in the airline data.")
else:
    print("Sorry,", search_month, "is not in our list.")
    

# Add a new column to categorize each month as High or Low traffic.
df["TrafficLevel"] = ["High" if p > 400 else "Low" for p in df["Passengers"]]
print(df[["Month", "Passengers", "TrafficLevel"]].head())

# Remove a column if it is not needed anymore.
df = df.drop(columns=["TrafficLevel"])
print(df.head())

# Find and print basic statistics about the passenger numbers.
print("Average:", df["Passengers"].mean())
print("Minimum:", df["Passengers"].min())
print("Maximum:", df["Passengers"].max())

# Loop through each month and print when passengers were above 450.
for idx, row in df.iterrows():
    if row['Passengers'] > 450:
        print(row['Month'], 'had over 450 passengers.')
        

# Create a list of months that had less than 350 passengers.
low_months = [row['Month'] for idx, row in df.iterrows() if row['Passengers'] < 350]
print(low_months)

# Sort the data so busiest months appear first.
sorted_df = df.sort_values("Passengers", ascending=False)
print(sorted_df.head())

# Add together all passenger counts from 1955 onward.
from datetime import datetime
recent_mask = df["Month"].apply(lambda x: int(x.split('-')[0]) >= 1955)
recent_sum = df[recent_mask]["Passengers"].sum()
print("Total passengers from 1955 onward:", recent_sum)

# Mini-project Part 1: Rough map of monthly traffic ups and downs.
import numpy as np
plt.figure(figsize=(12,5))
plt.plot(df["Month"], df["Passengers"], label="Monthly Traffic", color="steelblue")
plt.scatter(df["Month"][::12], df["Passengers"][::12], color="firebrick", label="Year starts")
plt.xlabel("Month")
plt.ylabel("Passengers")
plt.xticks(df["Month"][::12], rotation=45)
plt.legend()
plt.title("Airline Traffic Seasonality (Year Starts Highlighted)")
plt.tight_layout()
plt.show()

# Mini-project Part 2: Map busiest months using world cities and simple coordinates.
world_cities = {
    "London": (51.5074, -0.1278),
    "Paris": (48.8566, 2.3522),
    "New York": (40.7128, -74.0060),
    "Tokyo": (35.6895, 139.6917),
}
busiest = sorted_df.iloc[0:4]["Month"].tolist()
print("Busiest months:", busiest)

# In a real map, we would plot world city coordinates!
for city, coords in world_cities.items():
    print(f"{city}: Latitude {coords[0]}, Longitude {coords[1]}")
    

# Best practices: Always check for missing or strange numbers.
print("Any missing data?", df.isna().any().any())
print("Example data types:", df.dtypes.to_dict())

# Troubleshooting: Code sometimes gives an error.
try:
    print(df["NonexistentColumn"].head())
except KeyError:
    print('Oops! That column does not exist in this data.')
    

# Tips: Use the .info() and .describe() functions for a quick overview.
print(df.info())
print(df.describe())

# Challenge: Find the first month with fewer than 150 passengers.
for idx, row in df.iterrows():
    if row['Passengers'] < 150:
        print('First month with under 150 passengers:', row['Month'])
        break