import pandas as pd
import numpy as np
from scipy import stats

df = pd.read_csv('superstore_sales.csv')
sales = df['Sales']
print(sales.describe())

mean_sales = sales.mean()
median_sales = sales.median()
mode_sales = sales.mode()[0]
print(f'Mean: {mean_sales:.2f}, Median: {median_sales:.2f}, Mode: {mode_sales:.2f}')

variance = sales.var()
std_dev = sales.std()
data_range = sales.max() - sales.min()
print(f'Variance: {variance:.2f}')
print(f'Std Dev: {std_dev:.2f}')
print(f'Range: {data_range:.2f}')

q1 = sales.quantile(0.25)
q3 = sales.quantile(0.75)
iqr = q3 - q1
print(f'Q1: {q1:.2f}, Q3: {q3:.2f}, IQR: {iqr:.2f}')

skewness = stats.skew(sales)
kurt = stats.kurtosis(sales)
print(f'Skewness: {skewness:.2f}')
print(f'Kurtosis: {kurt:.2f}')

z_scores = stats.zscore(sales)
df['sales_zscore'] = z_scores
outliers = df[df['sales_zscore'].abs() > 3]
print(f'{len(outliers)} real orders beyond 3 standard deviations')
print(outliers[['Category', 'Sales', 'sales_zscore']].sort_values('sales_zscore', ascending=False).head(5))

import matplotlib.pyplot as plt

log_sales = np.log(sales[sales > 0])
plt.hist(log_sales, bins=40, density=True, color='steelblue', edgecolor='white', alpha=0.7)
x = np.linspace(log_sales.min(), log_sales.max(), 100)
plt.plot(x, stats.norm.pdf(x, log_sales.mean(), log_sales.std()), color='darkred', linewidth=2)
plt.title('Real Log-Transformed Sales vs. a Fitted Normal Curve')
plt.xlabel('log(Sales)')
plt.show()