# Let us import needed libraries and suppress warnings
import warnings
warnings.filterwarnings("ignore")
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
 
 

# A coin flip: Let's simulate it
flip = np.random.choice(["Heads", "Tails"])
print("You flipped:", flip)

# Let us list the sample space for a simple coin toss
sample_space = ["Heads", "Tails"]
print("Sample space:", sample_space)

# Calculate probability for fair coin
p_heads = 1 / 2
p_tails = 1 / 2
print("Probability of Heads:", p_heads)
print("Probability of Tails:", p_tails)

# Let us list the sample space for rolling a six-sided die
die_sample_space = [1, 2, 3, 4, 5, 6]
print("Sample space for a die:", die_sample_space)

# Probability of rolling a "3" with a fair die
p_three = 1 / len(die_sample_space)
print("Probability of rolling a 3:", p_three)

# Now, let us simulate 20 rolls of a die and count how many times we see a 6
rolls = np.random.choice(die_sample_space, size=20, replace=True)
num_sixes = np.sum(rolls == 6)
print("Rolls:", rolls)
print("Number of sixes:", num_sixes)

# Use your list of die rolls above. Find mean, median, and mode.
mean_roll = np.mean(rolls)
median_roll = np.median(rolls)
mode_roll = pd.Series(rolls).mode()[0]
print("Mean:", mean_roll)
print("Median:", median_roll)
print("Mode:", mode_roll)

# What if data is missing? Let us create a new list with missing values.
rolls_missing = np.append(rolls, [np.nan, np.nan])
print("Rolls (with missing):", rolls_missing)
# Safe mean excluding missing data
mean_safe = np.nanmean(rolls_missing)
print("Mean (safe):", mean_safe)

# Simulate 100 coin flips
n_flips = 100
coin_results = np.random.choice(["Heads", "Tails"], size=n_flips, replace=True)
heads_count = np.sum(coin_results == "Heads")
tails_count = np.sum(coin_results == "Tails")
print("Heads:", heads_count, "Tails:", tails_count)
print("Fraction Heads:", heads_count/n_flips)

# Plot the results of our 100 coin flips
sns.countplot(x=coin_results, palette="pastel");
plt.title("Coin Flip Results (100 Flips)");
plt.xlabel("Outcome"); plt.ylabel("Count");
plt.show()

# [Mini-Project Part 2] Explore a real dataset: Titanic sample
titanic = sns.load_dataset("titanic")
print("Titanic shape:", titanic.shape)
titanic.head()

# What fraction of Titanic passengers survived?
survived_rate = titanic["survived"].mean()
print("Survival rate:", survived_rate)

# Practice: Try flipping a coin as many times as you want!
times = int(input("How many times would you like to flip the coin? "))
results = np.random.choice(["Heads", "Tails"], size=times)
print("Flip results:", results)

# Challenge: What is the probability of getting at least one six in three dice rolls?
tries = 10000
success = 0
for _ in range(tries):
    rolls = np.random.choice([1,2,3,4,5,6], size=3)
    if 6 in rolls:
        success += 1
print("Simulated probability:", success / tries)