import warnings
warnings.filterwarnings("ignore")

# This is a comment. It will not run.

print("Hello, data world!")

name = input("What is your name? ")
print("Welcome, " + name + "!")

import pandas as pd
import matplotlib.pyplot as plt

# Data setup

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

plt.figure(figsize=(10,5))
plt.plot(df["Month"], df["Passengers"])
plt.title("Airline Passengers Over Time")
plt.xlabel("Month")
plt.ylabel("Number of Passengers")
plt.xticks(rotation=45)
plt.tight_layout()
plt.show()

# What if you want just one column?

months = df["Month"]
months.head()

# Checking for missing values

missing = df.isnull().sum()
print("Missing values per column:")
print(missing)

# Quick column stats

print(df["Passengers"].describe())

# Adding a new column

df["Year"] = df["Month"].apply(lambda x: x.split("-")[0])
df.head()

# Group by year

yearly = df.groupby("Year")["Passengers"].sum()
print(yearly)

# Bar chart of total passengers per year

yearly.plot(kind="bar", figsize=(8,4), color="skyblue")
plt.title("Total Passengers Each Year")
plt.ylabel("Passengers")
plt.xlabel("Year")
plt.show()

# Safe access: What if column does not exist?

try:
    print(df["NotARealColumn"])
except KeyError:
    print("Column not found!")
    

# Mini-project: Find the month with most passengers

max_row = df.loc[df["Passengers"].idxmax()]
print("Month with most passengers:")
print(max_row)

# Extra: Save a plot as a file

plt.figure(figsize=(6,3))
plt.plot(df["Month"], df["Passengers"], color="green")
plt.title("Monthly Air Passengers")
plt.tight_layout()
plt.savefig("airline_passengers_plot.png")
print("Plot saved as airline_passengers_plot.png")

# Practice: Try your own data

custom_url = input("Enter a CSV URL for another time series dataset, or press Enter to use the same one: ")
if not custom_url:
    custom_url = "https://raw.githubusercontent.com/jbrownlee/Datasets/master/shampoo.csv"
custom_df = pd.read_csv(custom_url)
print("Preview of your chosen dataset:")
print(custom_df.head())