import pandas as pd
import numpy as np

data_1 = {
    'id': ['1011231', '2201031', '0882541', '3452211'],
    'Name': ['John Sawyer', 'Alice Johnson', 'Lee Tran', 'Bobby Jones'],
    'major': ['CS', 'CIS', 'CS', 'MATH']
}

df1 = pd.DataFrame(data_1)
print(f"df1:\n{df1}")
print()

data_2 = {
    'CIS': [110,151,138,145,120,114],
    'CS': [132,153,128,160,130,126],
    'ITEC': [80,99,110,115,121,115]
}

year = [2021,2022,2023,2024,2025,2026]
df2 = pd.DataFrame(data_2, index=year)
print(f"df2:\n{df2}")
print()

#   sum
print(f"df2.sum(axis=0):\n{df2.sum(axis=0)}") 
print()
print(f"df2.sum(axis=1):\n{df2.sum(axis=1)}") 
print()

print("Descriptive statistics for all columns in df2 (df2.describe()):")
print(df2.describe())
print()

print(f"df2.head(3):\n{df2.head(3)}")
print()
print(f"df2.tail(3):\n{df2.tail(3)}")
print()
print(f"df2.loc[2023]:\n{df2.loc[2023]}")
print()
print(f"df2.loc[2025]:\n{df2.loc[2025]}")
print()