# Import key libraries
import warnings; warnings.filterwarnings("ignore")
import pandas as pd
import matplotlib.pyplot as plt

# Our dashboard will use pandas for data and matplotlib for charts

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

# First look at the data
df.info()
print("\nMissing values per column:")
print(df.isnull().sum())

# Preview a simple time series plot
plt.figure(figsize=(10,5))
plt.plot(df["Month"], df["Passengers"])
plt.title("Monthly Airline Passengers Over Time")
plt.xlabel("Month")
plt.ylabel("Passengers")
plt.xticks(rotation=45)
plt.tight_layout()
plt.show()

# Basic summary statistics
df["Passengers"].describe()

# Convert Month to a real date
df["Month"] = pd.to_datetime(df["Month"])
df = df.set_index("Month")
df.head(3)

# Drill down: Which months have the highest sales?
top_months = df.sort_values("Passengers", ascending=False).head(5)
print(top_months)

# What if we look for a month that is not there?
try:
    print(df.loc["2050-01"])
except KeyError:
    print("Month not found!")
    

# Let us fill missing data, just in case
df_fixed = df.copy()
df_fixed["Passengers"] = df_fixed["Passengers"].fillna(method="ffill")

# Editing a passenger total
df_copy = df.copy()
the_month = df_copy.index[0]
df_copy.at[the_month, "Passengers"] = 999
df_copy.head(1)

# Add a new summary row for all data
summary = pd.DataFrame({"Passengers": [df_copy["Passengers"].sum()]}, index=["Total"])
df_summary = pd.concat([df_copy, summary])
df_summary.tail()

# Remove the last row in the summary table
df_summary = df_summary.iloc[:-1]
df_summary.tail()

# Find yearly totals
df["Year"] = df.index.year
yearly = df.groupby("Year")["Passengers"].sum().reset_index()
print(yearly)

# Quick bar chart - yearly totals
plt.bar(yearly["Year"], yearly["Passengers"])
plt.title("Yearly Total Passengers")
plt.xlabel("Year")
plt.ylabel("Passengers")
plt.show()

# Find all months above the average
avg = df["Passengers"].mean()
busy_months = df[df["Passengers"] > avg]
print(f"Busiest months (>{avg:.2f} passengers): {len(busy_months)} found.")
busy_months.head(3)

# Mini-Project: Simple Sales Dashboard Function
def sales_dashboard(df):
    print("Latest month:", df.index.max().strftime("%b %Y"))
    print("Total passengers:", df["Passengers"].sum())
    print("Mean passengers per month:", int(df["Passengers"].mean()))
    print("Best month:", df["Passengers"].idxmax().strftime("%b %Y"), "with", df["Passengers"].max())

sales_dashboard(df)

# Mini-Project Part 2: Year-on-Year Growth Calculation
yearly["Growth"] = yearly["Passengers"].pct_change().fillna(0) * 100
for i, row in yearly.iterrows():
    print(f"Year {int(row['Year'])}: {int(row['Passengers'])} passengers, {row['Growth']:.1f}% growth")