Python for Data Science

# Lists, Dicts, and Sets
numbers = [1, 2, 3, 4, 5]
person = {"name": "Alice", "age": 30}
unique = {1, 2, 3, 3, 2}  # {1, 2, 3}

# List operations
numbers.append(6)
squared = [x**2 for x in numbers if x > 2]
print(squared)  # [9, 16, 25, 36]

# Dict comprehension
squares = {x: x**2 for x in range(5)}
print(squares)  # {0: 0, 1: 1, 2: 4, 3: 9, 4: 16}

# Set operations
A, B = {1, 2, 3}, {3, 4, 5}
print(A & B)  # {3} intersection
print(A | B)  # {1, 2, 3, 4, 5} union

# List comprehension vs loop
squares = [x**2 for x in range(10)]
# Same as: squares = []
#          for x in range(10): squares.append(x**2)

# Generator expression (lazy)
gen = (x**2 for x in range(10**6))
print(next(gen))  # 0 — no memory blowup

# Generator function
def fibonacci(limit):
    a, b = 0, 1
    while a < limit:
        yield a
        a, b = b, a + b

fib = list(fibonacci(100))
print(fib)  # [0, 1, 1, 2, 3, 5, 8, 13, 21, 34, 55, 89]

import numpy as np
import pandas as pd

# NumPy array
arr = np.array([[1, 2, 3], [4, 5, 6]])
print(arr.shape)     # (2, 3)
print(arr.mean())    # 3.5
print(arr.sum(axis=0))  # [5, 7, 9]

# Pandas DataFrame
df = pd.DataFrame({
    "name": ["Alice", "Bob", "Charlie"],
    "score": [85, 92, 78]
})
print(df.describe())
print(df[df["score"] > 80])