Data Types

import math

print(0.1 + 0.2)                  # 0.30000000000000004 — binary floats
print(0.1 + 0.2 == 0.3)           # False!
print(math.isclose(0.1 + 0.2, 0.3))   # True — compare floats this way
print(round(2.675, 2))            # 2.67, not 2.68 — same reason

from decimal import Decimal
print(Decimal("0.1") + Decimal("0.2"))   # 0.3 — exact, for money

print(math.sqrt(16), math.pi, math.floor(3.7), math.ceil(3.2))
print(abs(-4), max(3, 9, 1), min([4, 2, 8]), sum([1, 2, 3]))
print(divmod(17, 5))              # (3, 2): quotient and remainder at once
print(10 ** 20)                   # ints never overflow
print(7 / 2, 7 // 2, int(7 / 2))  # 3.5 3 3

s = "Hello, World"

# Indexing and slicing: s[start:stop:step], stop is exclusive, negatives count from the end
print(s[0], s[-1], s[0:5], s[7:], s[::-1])

# Common methods — each returns a NEW string
print(s.upper(), s.lower(), s.title())
print(s.replace("World", "Python"))
print(s.find("World"), s.find("xyz"))     # index or -1
print("World" in s, s.startswith("Hell"), s.endswith("!"))
print("  padded  ".strip() + "|")
print(len(s), s.count("l"))

# split and join — the two you use daily
words = "data engineering is fun".split()
print(words)
print("-".join(words))
print("2026-09-20".split("-"))

# characters ↔ numbers
print(ord("A"), chr(66))

nums = [4, 1, 3]
nums.append(9)          # add to the end
nums.insert(0, 7)       # insert at index
nums.extend([2, 8])     # add several
print(nums)

print(nums.pop())       # remove & return last → 8
nums.remove(1)          # remove first occurrence of the VALUE 1
print(nums, len(nums))
print(nums[0], nums[-1], nums[1:3])
print(9 in nums, nums.index(9))

nums.sort()             # in place, returns None
print(nums)
print(sorted(nums, reverse=True))   # a new list; nums unchanged

# sort by a key
people = [("Ada", 36), ("Linus", 28), ("Grace", 45)]
print(sorted(people, key=lambda p: p[1]))

# copies vs aliases
a = [1, 2, 3]
b = a          # same list, two names
c = a[:]       # a real copy
b.append(4)
print(a, c)

point = (3, 4)
x, y = point                # unpacking
print(x, y, point[0], len(point))

single = (5,)               # the comma makes the tuple, not the parentheses
not_a_tuple = (5)
print(type(single).__name__, type(not_a_tuple).__name__)

# tuples as dict keys — lists cannot do this
distances = {(0, 0): 0, (3, 4): 5}
print(distances[(3, 4)])

# functions return tuples to return several things
def min_max(values):
    return min(values), max(values)
lo, hi = min_max([7, 2, 9])
print(lo, hi)

# named tuples: readable records
from collections import namedtuple
User = namedtuple("User", "name age")
u = User("Ada", 36)
print(u.name, u.age, u)

tags = {"python", "sql", "python", "spark"}
print(sorted(tags), len(tags))    # duplicates gone; sorted() because set order is not guaranteed

seen = set()
for word in "the cat and the dog and the bird".split():
    if word in seen:
        print("repeat:", word)
    seen.add(word)

a = {1, 2, 3, 4}
b = {3, 4, 5}
print(a | b)     # union
print(a & b)     # intersection
print(a - b)     # difference
print(a ^ b)     # symmetric difference
print({1, 2} <= a)   # subset?

# dedupe a list but keep order: dict.fromkeys trick
print(list(dict.fromkeys([3, 1, 3, 2, 1])))

empty = set()    # NOT {} — that is an empty dict
print(type({}).__name__, type(empty).__name__)

user = {"name": "Ada", "age": 36, "langs": ["python", "sql"]}

print(user["name"])              # lookup
user["email"] = "[email protected]"   # add / overwrite
user["age"] += 1
print(user.get("phone"))         # None instead of an error
print(user.get("phone", "n/a"))  # with a default
print("age" in user, len(user))
del user["email"]

for key, value in user.items():
    print(f"{key:6} {value}")
print(list(user.keys()), list(user.values()))

# counting — the pattern you will write 1,000 times
counts = {}
for word in "a b a c b a".split():
    counts[word] = counts.get(word, 0) + 1
print(counts)

# grouping with setdefault
groups = {}
for name, team in [("Ada", "data"), ("Linus", "infra"), ("Grace", "data")]:
    groups.setdefault(team, []).append(name)
print(groups)

# merging (3.9+) and comprehension
defaults = {"theme": "light", "lang": "en"}
prefs = {"lang": "fr"}
print(defaults | prefs)
print({n: n * n for n in range(4)})

from collections import Counter, deque

words = "the cat saw the other cat".split()
c = Counter(words)
print(c.most_common(2))

q = deque(["a", "b"])
q.append("c")        # right
q.appendleft("z")    # left — O(1); list.insert(0, x) is O(n)
print(q.popleft(), q)