# Get ready! Import core libraries.
import warnings; warnings.filterwarnings("ignore")
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from scipy import stats

# Simulate random dice rolls using a probability distribution
dice_rolls = np.random.choice([1, 2, 3, 4, 5, 6], size=10)
print("Ten random dice rolls:", dice_rolls)

# Data setup: real-world time series for later analysis
url = "https://raw.githubusercontent.com/jbrownlee/Datasets/master/shampoo.csv"
df = pd.read_csv(url)
print("Data shape:", df.shape)
print("First few rows:")
print(df.head())

# Plot the shampoo sales data to explore it visually
plt.figure(figsize=(8, 4))
plt.plot(df["Sales"], marker="o")
plt.title("Monthly Shampoo Sales (Time Series)")
plt.xlabel("Month")
plt.ylabel("Sales")
plt.show()

# Plotting a normal distribution (bell curve)
x = np.linspace(-4, 4, 100)
pdf = stats.norm.pdf(x, loc=0, scale=1)
plt.plot(x, pdf, label="Standard Normal PDF")
plt.title("Normal Distribution (Bell Curve)")
plt.xlabel("Value")
plt.ylabel("Probability Density")
plt.legend()
plt.show()

# Generate random heights with a normal distribution
np.random.seed(42)
heights = np.random.normal(loc=170, scale=10, size=1000)
plt.hist(heights, bins=30, color="skyblue", edgecolor="black")
plt.title("Simulated Heights (cm)")
plt.xlabel("Height (cm)")
plt.ylabel("Count")
plt.show()

# Find probability of a value under the normal curve
mean = 170
std = 10
prob = stats.norm.cdf(180, loc=mean, scale=std)
print(f"Chance a person is shorter than 180 cm: {prob:.2f}")

# Compute and plot binomial probabilities
n = 10  # Number of flips
p = 0.5  # Chance of heads
x = np.arange(0, n+1)
pmf = stats.binom.pmf(x, n, p)
plt.bar(x, pmf, color="lightcoral", edgecolor="black")
plt.title("Coin Flips: Probability of Getting Heads")
plt.xlabel("Number of Heads")
plt.ylabel("Probability")
plt.show()

# What is the probability of getting exactly five heads?
prob_5 = stats.binom.pmf(5, n, p)
print(f"Probability of exactly 5 heads: {prob_5:.2f}")

# Practice: Simulate a person's answer to a question using input()
answer = input("What is your favorite random number between 1 and 6? ")
print("Thank you! Your random number is:", answer)

# Use the Poisson distribution: rare events in sales (mini-project setup)
monthly_average = df["Sales"].mean()
poisson_sample = stats.poisson.rvs(monthly_average, size=12)
plt.bar(np.arange(1, 13), poisson_sample, color="goldenrod")
plt.title("Simulated Monthly Sales Events (Poisson)")
plt.xlabel("Month")
plt.ylabel("Simulated Sales Counts")
plt.show()

# Mini-project: Bootstrap confidence intervals for the mean (advanced!)
np.random.seed(42)
sample_means = [np.mean(np.random.choice(df["Sales"], size=20, replace=True)) for _ in range(1000)]
lower, upper = np.percentile(sample_means, [2.5, 97.5])
print(f"95% bootstrap confidence interval: ({lower:.2f}, {upper:.2f})")

# Best practices: Always check your data before modeling
print(df.isnull().sum())
print(df.dtypes)

# Troubleshooting: What if your values are not numbers?
try:
    numbers = pd.to_numeric(df["Sales"])
except Exception as e:
    print("Could not convert to numbers:", e)
    

# Extra tip: Compare two distributions side by side
group_a = np.random.normal(170, 10, 200)
group_b = np.random.normal(160, 8, 200)
plt.hist(group_a, bins=25, alpha=0.6, label="Group A")
plt.hist(group_b, bins=25, alpha=0.6, label="Group B")
plt.legend()
plt.title("Comparing Two Groups (Heights)")
plt.xlabel("Height (cm)")
plt.ylabel("Count")
plt.show()