# Suppress warnings for a clean experience
import warnings; warnings.filterwarnings("ignore")

# Import useful packages
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns

# Data setup: Load the Airline Passengers dataset
url = "https://raw.githubusercontent.com/jbrownlee/Datasets/master/airline-passengers.csv"
data = pd.read_csv(url)
print('Shape:', data.shape)
data.head()

# First visualization: see the trend over time
plt.figure(figsize=(10,5))
plt.plot(data['Month'], data['Passengers'], marker='o')
plt.title("Monthly Airline Passengers Over Time")
plt.xlabel("Month")
plt.ylabel("Number of Passengers")
plt.xticks(rotation=45)
plt.tight_layout()
plt.show()

# Prepare data for scatter: extract year and month number
data['Year'] = data['Month'].str[:4].astype(int)
data['Month_num'] = data['Month'].str[5:].astype(int)

# Simple scatter plot: Passengers vs Year
plt.figure(figsize=(8,5))
plt.scatter(data['Year'], data['Passengers'])
plt.title("Passengers vs Year")
plt.xlabel("Year")
plt.ylabel("Number of Passengers")
plt.show()

# Scatter plot with color: Passengers by Month
plt.figure(figsize=(8,5))
sns.scatterplot(x='Month_num', y='Passengers', hue='Year', data=data, palette='viridis')
plt.title("Monthly Passengers Colored by Year")
plt.xlabel("Month Number")
plt.ylabel("Number of Passengers")
plt.legend(title="Year", bbox_to_anchor=(1.05,1), loc='upper left')
plt.tight_layout()
plt.show()

# Regression plot: Passengers vs Year
plt.figure(figsize=(8,5))
sns.regplot(x='Year', y='Passengers', data=data, scatter_kws={'color':'blue'}, line_kws={'color':'red'})
plt.title("Passengers Over Years (With Regression)")
plt.xlabel("Year")
plt.ylabel("Number of Passengers")
plt.show()

# Regression without dots: just show the trend
plt.figure(figsize=(8,5))
sns.regplot(x='Year', y='Passengers', data=data, scatter=False, color='green')
plt.title("Trend Line Only: Year vs Passengers")
plt.xlabel("Year")
plt.ylabel("Number of Passengers")
plt.show()

# Create a mini-dataset with passengers by year, month, count
df = data[['Year','Month_num','Passengers']]
# Show a sample
df.head()

# Basic pairplot
sns.pairplot(df)
plt.suptitle("Pairplot: Year, Month, Passengers", y=1.02)
plt.show()

# Highlight pairplot by color (hue)
df['Decade'] = (df['Year']//10)*10
sns.pairplot(df, hue='Decade', palette='mako')
plt.suptitle("Pairplot Colored by Decade", y=1.02)
plt.show()

# Load the daily minimum temperatures dataset
temp_url = "https://raw.githubusercontent.com/jbrownlee/Datasets/master/daily-min-temperatures.csv"
temp = pd.read_csv(temp_url)
print('Shape:', temp.shape)
temp.head()

# Plot: Temperature over time
plt.figure(figsize=(12,5))
plt.plot(temp['Date'], temp['Temp'], color='orange')
plt.xlabel('Date')
plt.ylabel('Temperature (C)')
plt.title('Daily Minimum Temperatures Over Time')
plt.xticks(rotation=45)
plt.tight_layout()
plt.show()

# Regression plot: Temperature by Day-of-Year
temp['Date'] = pd.to_datetime(temp['Date'])
temp['DayOfYear'] = temp['Date'].dt.dayofyear
plt.figure(figsize=(8,5))
sns.regplot(x='DayOfYear', y='Temp', data=temp, scatter_kws={'s':1}, line_kws={'color':'red'})
plt.title('Temperature Trend Within the Year')
plt.xlabel('Day of Year (1-366)')
plt.ylabel('Minimum Temperature (C)')
plt.show()

# Input your two lists of numbers
x_vals = input("Enter at least 5 numbers, separated by commas, for X: ")
y_vals = input("Enter at least 5 numbers, separated by commas, for Y: ")
x = [float(x) for x in x_vals.split(',')]
y = [float(y) for y in y_vals.split(',')]
plt.scatter(x, y)
plt.title("Your Custom Scatter Plot")
plt.xlabel("X Values")
plt.ylabel("Y Values")
plt.show()

# Troubleshooting: what if your plot does not show?
print("Troubleshooting tips:")
print("- Check that you included plt.show()")
print("- Make sure your input data is numeric")
print("- Look for typos in column names")
print("- Run code cells in order, from top to bottom")
print("- If you see blank, try rerunning that cell or restarting the runtime")