import warnings; warnings.filterwarnings("ignore")  # Ignore warnings for cleaner output

# Let us import necessary libraries
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns

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

# Let us plot a simple line chart of the time series
plt.figure(figsize=(10,4))
plt.plot(pd.to_datetime(data["Month"]), data["Passengers"], marker="o")
plt.title("Monthly Airline Passengers Over Time")
plt.xlabel("Month")
plt.ylabel("Number of Passengers")
plt.show()

# Let us start with a histogram
plt.figure(figsize=(8,4))
sns.histplot(data["Passengers"], bins=12, color="skyblue", kde=False)
plt.title("Histogram of Monthly Airline Passengers")
plt.xlabel("Number of Passengers")
plt.ylabel("Count")
plt.show()

# Plotting a KDE (Kernel Density Estimate)
plt.figure(figsize=(8,4))
sns.kdeplot(data["Passengers"], fill=True, color="orange")
plt.title("KDE: Smooth Estimate of Passenger Distribution")
plt.xlabel("Number of Passengers")
plt.ylabel("Density")
plt.show()

# Let us see both histogram and KDE together
plt.figure(figsize=(8,4))
sns.histplot(data["Passengers"], bins=12, color="skyblue", kde=True)
plt.title("Histogram and KDE of Passenger Numbers")
plt.xlabel("Number of Passengers")
plt.ylabel("Count / Density")
plt.show()

# Box plots are useful for spotting outliers
plt.figure(figsize=(6,3))
sns.boxplot(y=data["Passengers"], color="lightgreen")
plt.title("Box Plot of Monthly Airline Passengers")
plt.ylabel("Number of Passengers")
plt.show()

# Violin plots mix KDE and box ideas
plt.figure(figsize=(6,3))
sns.violinplot(y=data["Passengers"], color="violet")
plt.title("Violin Plot of Monthly Airline Passengers")
plt.ylabel("Number of Passengers")
plt.show()

# Compare box and violin plot side by side
fig, axes = plt.subplots(1, 2, figsize=(10,3))
sns.boxplot(y=data["Passengers"], color="lightgreen", ax=axes[0])
axes[0].set_title("Box Plot")
sns.violinplot(y=data["Passengers"], color="violet", ax=axes[1])
axes[1].set_title("Violin Plot")
plt.tight_layout()
plt.show()

# What if there are missing values?
data_missing = data.copy()
data_missing.loc[::12, "Passengers"] = None  # Remove one value per year
print("Missing data count:", data_missing["Passengers"].isnull().sum())

# Plotting with missing values (will skip missing data)
plt.figure(figsize=(8,3))
sns.histplot(data_missing["Passengers"], bins=12, color="coral")
plt.title("Histogram with Missing Values")
plt.xlabel("Number of Passengers")
plt.ylabel("Count")
plt.show()

# You can fill missing values if you want
filled_data = data_missing["Passengers"].fillna(data_missing["Passengers"].mean())
plt.figure(figsize=(8,3))
sns.histplot(filled_data, bins=12, color="navy")
plt.title("Histogram with Filled Missing Values")
plt.xlabel("Number of Passengers")
plt.ylabel("Count")
plt.show()

# Mini-project: Explore temperature data!
temp_url = "https://raw.githubusercontent.com/jbrownlee/Datasets/master/daily-min-temperatures.csv"
temps = pd.read_csv(temp_url)
print("Temperature data shape:", temps.shape)
temps.head()

# Make all four distribution plots for temperatures
plt.figure(figsize=(16,3))
plt.subplot(1,4,1)
sns.histplot(temps["Temp"], bins=15, color="skyblue")
plt.title("Histogram")
plt.subplot(1,4,2)
sns.kdeplot(temps["Temp"], fill=True, color="orange")
plt.title("KDE")
plt.subplot(1,4,3)
sns.boxplot(y=temps["Temp"], color="lightgreen")
plt.title("Box")
plt.subplot(1,4,4)
sns.violinplot(y=temps["Temp"], color="violet")
plt.title("Violin")
plt.tight_layout()
plt.show()

# Best practices
# - Check for missing values
# - Use the right plot for your question
# - Combine plots for deeper insight
# - Always add clear labels and titles

# Troubleshooting: What if a plot looks empty or wrong?
try:
    sns.histplot([], bins=10)
    plt.show()
except Exception as e:
    print("Error:", e)
    

# Extra tip: Plot single value many times
ones_data = [1]*20
plt.figure(figsize=(4,2))
sns.histplot(ones_data, bins=5, color="red")
plt.title("When All Values Are the Same")
plt.show()

# Ready to practice? Make your own customized plot.
user_vals = input("Enter some numbers (comma-separated): ")
my_vals = [float(x.strip()) for x in user_vals.split(",") if x.strip()]
plt.figure(figsize=(5,2))
sns.histplot(my_vals, bins=min(len(my_vals), 10), color="teal")
plt.title("Your Own Data Histogram")
plt.show()