【Python】辞書内包表記/セット内包表記に入門する

# 辞書: 数値nに対して n: n*n のマップを作る
squares = {n: n * n for n in range(5)}
print(squares)

# セット: 文字列の長さの集合(重複は自動で排除)
lengths = {len(s) for s in ["a", "bb", "ccc", "bb", "a"]}
print(lengths)

# forループ版: 偶数だけを2乗にして辞書化
result = {}
for n in range(10):
    if n % 2 == 0:
        result[n] = n * n
print(result)

# 内包表記版
result2 = {n: n * n for n in range(10) if n % 2 == 0}
print(result2)

names = ["Alice", "Bob", "Charlie"]

# enumerateで(インデックス, 要素)を取り出し、キーと値を作る
name_lengths = {i: len(name) for i, name in enumerate(names, start=1)}
print(name_lengths)

prices = {"apple": "100", "banana": "80", "orange": "120"}

# 文字列の数字をintに変換し、税抜→税込(10%)へ
with_tax = {item: int(price) * 1.10 for item, price in prices.items()}
print(with_tax)

from decimal import Decimal, ROUND_HALF_UP

with_tax_decimal = {
    item: (Decimal(price) * Decimal("1.10")).quantize(Decimal("1"), rounding=ROUND_HALF_UP)
    for item, price in prices.items()
}
print(with_tax_decimal)

scores = {"Alice": 82, "Bob": 59, "Charlie": 91, "Dana": 74}

# 合格(>= 70)だけを抽出
passed = {name: s for name, s in scores.items() if s >= 70}
print(passed)

# 合否を値にする
result = {name: ("PASS" if s >= 70 else "FAIL") for name, s in scores.items()}
print(result)

# 0,1,2 のキーに対して繰り返し代入が起こる例
d = {n % 3: n for n in range(6)}  # n = 0..5
print(d)                          # 値は「後勝ち」
print(list(d.items()))            # 挿入順は最初の出現位置のまま

words = ["Apple", "banana", "APPLE", "Banana", "orange"]

# 小文字化してユニーク化
unique_lower = {w.lower() for w in words}
print(unique_lower)

raw_emails = [" ALICE@example.com ", "bob@EXAMPLE.com", "", "carol@example.com", " "]

# 前後の空白を取り、空文字を捨て、ドメインを小文字化してユニーク化
cleaned = {
    e.strip().lower()
    for e in raw_emails
    if e and e.strip()  # 空や空白のみを除外
}
print(cleaned)

print(sorted(cleaned))  # アルファベット順にソート

pref_to_capital = {"Hokkaido": "Sapporo", "Aomori": "Aomori", "Iwate": "Morioka"}

# 値がユニークな場合
capital_to_pref = {capital: pref for pref, capital in pref_to_capital.items()}
print(capital_to_pref)

# 値ごとに、元のキーの集合を作る(やや重い・全探索)
d = {"a": 1, "b": 2, "c": 1}
inv_to_keys = {
    v: {k for k, vv in d.items() if vv == v}
    for v in set(d.values())
}
print(inv_to_keys)

raw = {"A": "10", "B": "x", "C": "003"}

# 数字のみならint、それ以外はNone
normalized = {k: (int(v) if v.isdigit() else None) for k, v in raw.items()}
print(normalized)

def to_int_or_none(s: str) -> int | None:
    # 先頭の0は許容し、空文字や負数、混在は除外する簡易例
    return int(s) if s.isdigit() else None

normalized2 = {k: to_int_or_none(v) for k, v in raw.items()}
print(normalized2)

tags = ["Python", "python", "AI", "ai", "AI ", " Data ", "data"]

unique_tags = {t.strip().lower() for t in tags}
print(unique_tags)
print(sorted(unique_tags))  # 表示は並べ替えると安定

import timeit

setup = "data = list(range(10000))"
stmt_loop = """
d = {}
for x in data:
    if x % 2 == 0:
        d[x] = x * x
"""
stmt_comp = "{x: x*x for x in data if x % 2 == 0}"

t_loop = timeit.timeit(stmt_loop, setup=setup, number=200)
t_comp = timeit.timeit(stmt_comp, setup=setup, number=200)
print(f"forループ: {t_loop:.3f}s, 内包表記: {t_comp:.3f}s, 倍率: {t_loop/t_comp:.2f}x")

# 悪例: ネストと条件が増えて読みにくい
pairs = [(i, j) for i in range(5) for j in range(5) if (i + j) % 3 == 0 if i != j]

# 良例: 条件を名前付きで分け、段階的に書く
pairs2 = []
for i in range(5):
    for j in range(5):
        valid_sum = (i + j) % 3 == 0
        different = i != j
        if valid_sum and different:
            pairs2.append((i, j))

print(len(pairs), len(pairs2), set(pairs) == set(pairs2))