Operators, Strings, Indexing, Slicing & String Methods

print(7 / 2, 7 // 2, -7 // 2, 7 % 2, -7 % 3, 2 ** 10, 9 ** 0.5)
print(divmod(17, 5))                  # (quotient, remainder) in one call
hours = 135; print(f"{hours // 60} h {hours % 60} min")       # split minutes into hours and minutes
print(10 % 3 == 1, 12 % 2 == 0)      # test odd/even and divisibility

x = 15
print(x > 10, x == 15, x != 15, 10 < x <= 20)        # chained comparison: 10 < x and x <= 20
print(x > 10 and x < 20, x < 5 or x > 12, not x > 10)
print("apple" < "banana", "Zebra" < "apple")         # strings compare by character codes: uppercase before lowercase

print(0 or "default", "" or "n/a", "x" and "y", None and 1)
name = ""; print(name or "Anonymous")          # a common idiom for default values
print(5 > 3 and print("evaluated") is None)     # right side runs only when needed

count = 10; count += 5; count *= 2; count -= 1; count //= 4; count **= 2
print(count)
print(3 in [1, 2, 3], "py" in "python", "z" not in "python", "a" in {"a": 1})     # membership
a = [1, 2]; b = [1, 2]; c = a
print(a == b, a is b, a is c, None is None)                                          # equality vs identity

print(5 & 3, 5 | 3, 5 ^ 3, 5 << 1, 5 >> 1, bin(5))

print(2 + 3 * 4 ** 2, (2 + 3) * 4 ** 2, -2 ** 2, (-2) ** 2, not 1 == 2 or False)

city = "Bengaluru"
quote = 'She said "hello"'
multi = """Line 1
Line 2"""
hindi = "नमस्ते"                      # Unicode works everywhere
print(len(city), len(hindi), multi.splitlines(), city.upper())
print("Ha" * 3, "data" + " " + "science", "-" * 20)

w = "BENGALURU"
print(w[0], w[3], w[-1], w[-3])
try: print(w[20])
except IndexError as e: print("IndexError:", e)

w = "BENGALURU"
print(w[0:3], w[:3], w[3:], w[3:6], w[-4:], w[:-1])
print(w[::2], w[::-1], w[1::3], w[8:2:-2])
print(w[2:100], repr(w[5:2]))             # out-of-range slices are safe; an empty slice is ''

order_id = "IN-2025-00042"
country, year, number = order_id[:2], int(order_id[3:7]), int(order_id[-5:])
print(country, year, number)                      # same as LEFT/MID/RIGHT in Excel and SQL

s = "  new DELHI  "
print(repr(s.strip()), repr(s.lstrip()), repr(s.rstrip()))
print(s.strip().lower(), s.strip().upper(), s.strip().title(), s.strip().capitalize(), s.strip().swapcase())
print("xxHixx".strip("x"), "2025-04-27".replace("-", "/"), "a,b,,c".replace(",,", ","))
print("Bengaluru".casefold() == "BENGALURU".casefold())         # robust case-insensitive comparison

t = "Delhi, Mumbai, Delhi, Pune"
print(t.find("Delhi"), t.rfind("Delhi"), t.find("Goa"), t.count("Delhi"), t.index("Mumbai"))
print(t.startswith("Delhi"), t.endswith("Pune"), "Mumbai" in t)
print("12345".isdigit(), "12.5".isdigit(), "abc".isalpha(), "abc123".isalnum(), "  ".isspace(), "Abc".istitle(), "abc".islower())

csv_line = "E101,Kavya Iyer,HR,97000"
parts = csv_line.split(",")
print(parts, len(parts))
print("one  two   three".split(), "a-b-c".split("-", 1), "line1\nline2".splitlines(), "path/to/file.csv".rsplit("/", 1))
print(", ".join(["Pune", "Delhi", "Goa"]), "".join(["a", "b"]), " | ".join(str(n) for n in [1, 2, 3]))
print("abc".partition("b"), "IN-2025-00042".partition("-"))

print("42".zfill(6), "7".rjust(4, "0"), "ab".ljust(5, ".") + "|", "ab".center(8, "*"))
print("Total".ljust(10) + "1,500".rjust(10))
print("{:>8} {:<8} {:^8}".format("right", "left", "mid"))
print("tab\tseparated", "new\\nline stays literal", "unicode: \u20b9 \u2713")

table = str.maketrans({"₹": "Rs ", ",": ""})
print("₹1,25,000".translate(table))
print("naïve café".encode("utf-8"), "abc".encode("ascii"), b"abc".decode())
print(ord("A"), chr(97), "é".encode("utf-8"), len("é".encode("utf-8")))

import pandas as pd
cust = pd.read_csv("customers.csv")
raw = ["  asha RAO ", "ravi   verma", "MEERA\tIYER", "kabir  singh "]          # messy examples
def clean_name(name):
    parts = name.split()                         # split() collapses all whitespace
    return " ".join(p.capitalize() for p in parts)
print([clean_name(n) for n in raw])
print(cust.customer_name.head(5).tolist())
first_names = [n.split()[0] for n in cust.customer_name]
print(len(first_names), "names; most common first names:", pd.Series(first_names).value_counts().head(5).to_dict())

def initials(name): return "".join(w[0].upper() for w in name.split())
def mask_email(email):
    user, _, domain = email.partition("@")
    return user[0] + "*" * (len(user) - 2) + user[-1] + "@" + domain
print(initials("kavya iyer"), mask_email("[email protected]"))
print("palindrome" if (s := "Level").lower() == s.lower()[::-1] else "not")

text = "data science is fun and data engineering is fun too"
words = text.split()
freq = {}
for w in words: freq[w] = freq.get(w, 0) + 1
print(freq)
print(max(freq, key=freq.get), len(words), len(set(words)))