numpy lab(11/03/2024)

# -*- coding: utf-8 -*-
"""
Created on Mon Mar 11 09:30:09 2024

@author: lab
"""

import numpy as np
import pandas as pd
import seaborn as sns
# Example dataset
diamonds = sns.load_dataset("diamonds")
diamond_prices = diamonds["price"]
mean_price = diamond_prices.mean()
median_price = diamond_prices.median()
std = diamond_prices.std()
skewness = (3 * (mean_price - median_price)) / std
print(f"The Pierson's second skewness score of diamond prices distribution is {skewness:.5f}")
#The Pierson's second skewness score of diamond prices distribution is 1.15189
def moment_based_skew(distribution):
 n = len(distribution)
 mean = np.mean(distribution)
 std = np.std(distribution)

 # Divide the formula into two parts
 first_part = n / ((n - 1) * (n - 2))
 second_part = np.sum(((distribution - mean) / std) ** 3)

 skewness = first_part * second_part
 return skewness
skew = moment_based_skew(diamond_prices)
print("The moment_based skewness score of diamond prices distribution is ", skew)
# Using Libraries
# Pandas version
print("The moment_based skewness skewness score of diamond prices distribution is ",
diamond_prices.skew())
# SciPy version
from scipy.stats import skew
print("The moment_based skewness skewness score of diamond prices distribution is ",
skew(diamond_prices))
# Visualization
import matplotlib.pyplot as plt
sns.kdeplot(diamond_prices)
plt.title("Plot of diamond prices")
plt.xlabel("Price ($)")