Let’s explore some basic data analysis using pandas.

import pandas as pd
import numpy as np

# Create a sample dataset
np.random.seed(42)
data = {
    'date': pd.date_range('2026-01-01', periods=30, freq='D'),
    'sales': np.random.randint(100, 500, 30),
    'customers': np.random.randint(20, 100, 30)
}
df = pd.DataFrame(data)

# Display basic statistics
print("Dataset Summary:")
print(df.describe())

# Show first few rows
df.head()
Dataset Summary:
                      date       sales  customers
count                   30   30.000000  30.000000
mean   2026-01-15 12:00:00  308.433333  60.500000
min    2026-01-01 00:00:00  120.000000  21.000000
25%    2026-01-08 06:00:00  209.750000  34.750000
50%    2026-01-15 12:00:00  302.500000  69.000000
75%    2026-01-22 18:00:00  404.250000  79.000000
max    2026-01-30 00:00:00  485.000000  99.000000
std                    NaN  109.450881  24.415583
date sales customers
0 2026-01-01 202 68
1 2026-01-02 448 78
2 2026-01-03 370 61
3 2026-01-04 206 79
4 2026-01-05 171 99 
# Calculate rolling average
df['sales_rolling_avg'] = df['sales'].rolling(window=7).mean()

# Plot the data
import matplotlib.pyplot as plt

plt.figure(figsize=(12, 6))
plt.plot(df['date'], df['sales'], label='Daily Sales', alpha=0.7, marker='o')
plt.plot(df['date'], df['sales_rolling_avg'], label='7-Day Moving Average', linewidth=2)
plt.xlabel('Date')
plt.ylabel('Sales')
plt.title('Sales Trend Analysis')
plt.legend()
plt.grid(True, alpha=0.3)
plt.xticks(rotation=45)
plt.tight_layout()
plt.show()