Python Interview Questions

# Example 1: Mutability difference
my_list = [1, 2, 3]
my_list[0] = 99        # Works fine — lists are mutable
print(my_list)
# Output: [99, 2, 3]

my_tuple = (1, 2, 3)
# my_tuple[0] = 99     # Raises: TypeError: 'tuple' object does not support item assignment
print(my_tuple)
# Output: (1, 2, 3)

# Example 2: Tuples as dictionary keys (lists cannot do this)
# Tuples are hashable because they are immutable
coords = {(10, 20): "New York", (40, 50): "London"}
print(coords[(10, 20)])
# Output: New York

# Lists are NOT hashable — this would fail:
# bad_dict = {[10, 20]: "New York"}
# Raises: TypeError: unhashable type: 'list'

120 bytes
print(f"Tuple size: {sys.getsizeof(my_tuple)} bytes")
# Output: Tuple size: 80 bytes
# Tuples use less memory because they don't need resize overhead"># Example 3: Memory and performance comparison
import sys

my_list = [1, 2, 3, 4, 5]
my_tuple = (1, 2, 3, 4, 5)

print(f"List size:  {sys.getsizeof(my_list)} bytes")
# Output: List size:  120 bytes
print(f"Tuple size: {sys.getsizeof(my_tuple)} bytes")
# Output: Tuple size: 80 bytes
# Tuples use less memory because they don't need resize overhead

# Example 1: Immutable strings — "modification" creates a new object
a = "hello"
b = a                # b points to the same object as a
print(id(a) == id(b))
# Output: True

a = a + " world"     # a now points to a NEW string object
print(a)
# Output: hello world
print(b)
# Output: hello
print(id(a) == id(b))
# Output: False
# b still points to the original "hello" — it was never modified

# Example 2: Mutable lists — modification changes the SAME object
x = [1, 2, 3]
y = x                # y points to the same list object
x.append(4)          # Modifies the list in place
print(x)
# Output: [1, 2, 3, 4]
print(y)
# Output: [1, 2, 3, 4]
# Both x and y see the change because they share the same object
print(id(x) == id(y))
# Output: True

# Example 3: Immutable integers — reassignment creates a new object
a = 10
print(id(a))
# Output: 4344024144  (some memory address)
a = a + 5            # Creates a brand new int object 15
print(a)
# Output: 15
# The integer 10 still exists (until garbage collected)
# Python caches small integers (-5 to 256), so id() for those may be reused

# Example 1: List comprehension — entire list stored in memory
squares_list = [x ** 2 for x in range(6)]
print(squares_list)
# Output: [0, 1, 4, 9, 16, 25]
print(type(squares_list))
# Output: <class 'list'>

# Example 2: Generator expression — lazy, one value at a time
squares_gen = (x ** 2 for x in range(6))
print(type(squares_gen))
# Output: <class 'generator'>

# Must iterate or convert to see values
print(next(squares_gen))
# Output: 0
print(next(squares_gen))
# Output: 1
print(list(squares_gen))   # Remaining values
# Output: [4, 9, 16, 25]

87624 bytes
print(f"Generator memory: {sys.getsizeof(gen_expr)} bytes")
# Output: Generator memory: 200 bytes
# Generator uses constant memory regardless of data size"># Example 3: Memory comparison — generators win for large data
import sys

list_comp = [x for x in range(10000)]
gen_expr = (x for x in range(10000))

print(f"List memory:      {sys.getsizeof(list_comp)} bytes")
# Output: List memory:      87624 bytes
print(f"Generator memory: {sys.getsizeof(gen_expr)} bytes")
# Output: Generator memory: 200 bytes
# Generator uses constant memory regardless of data size

# Example 1: Shallow copy — inner lists are shared
import copy

a = [[1, 2], [3, 4]]
b = copy.copy(a)       # Shallow copy
a[0].append(999)       # Modify an inner list

print(a)
# Output: [[1, 2, 999], [3, 4]]
print(b)
# Output: [[1, 2, 999], [3, 4]]
# BUG: b was affected because inner lists are shared references

# Example 2: Deep copy — completely independent
import copy

a = [[1, 2], [3, 4]]
c = copy.deepcopy(a)   # Deep copy — all nested objects are cloned
a[0].append(999)

print(a)
# Output: [[1, 2, 999], [3, 4]]
print(c)
# Output: [[1, 2], [3, 4]]
# c is fully independent — no shared references

# Example 3: Multiple ways to shallow copy a list
original = [1, 2, 3]

# Method 1: copy module
copy1 = copy.copy(original)

# Method 2: list slicing
copy2 = original[:]

# Method 3: list() constructor
copy3 = list(original)

# All produce independent shallow copies for flat lists
original.append(4)
print(original)
# Output: [1, 2, 3, 4]
print(copy1)
# Output: [1, 2, 3]
print(copy2)
# Output: [1, 2, 3]
print(copy3)
# Output: [1, 2, 3]
# For flat lists (no nesting), shallow copy is safe and sufficient

# Example 1: Basic usage in a module file
# File: utils.py
def helper():
    return "I'm a helper function"

def add(a, b):
    return a + b

if __name__ == '__main__':
    # Only runs when: python utils.py
    # Does NOT run when: from utils import helper
    print(helper())
    # Output: I'm a helper function
    print(add(3, 4))
    # Output: 7

# Example 2: Understanding __name__ value
# When run directly:  __name__ == '__main__'
# When imported:      __name__ == 'utils' (the module name)

# File: demo.py
print(f"__name__ is: {__name__}")

# Running: python demo.py
# Output: __name__ is: __main__

# Importing: import demo
# Output: __name__ is: demo

# Example 3: Real-world pattern — ETL script with reusable functions
# File: etl_pipeline.py
def extract(source):
    """Extract data from source — reusable when imported"""
    return [{"id": 1, "name": "Alice"}, {"id": 2, "name": "Bob"}]

def transform(data):
    """Transform data — reusable when imported"""
    return [row for row in data if row["id"] > 0]

def load(data):
    """Load data — reusable when imported"""
    print(f"Loaded {len(data)} rows")

if __name__ == '__main__':
    # Orchestration only runs when script is executed directly
    raw = extract("db://source")
    clean = transform(raw)
    load(clean)
    # Output: Loaded 2 rows

# Example 1: Basic *args — collects positional arguments into a tuple
def add_all(*args):
    # args is a tuple of all positional arguments
    print(f"args = {args}")
    return sum(args)

result = add_all(1, 2, 3, 4, 5)
# Output: args = (1, 2, 3, 4, 5)
print(result)
# Output: 15

# Example 2: Basic **kwargs — collects keyword arguments into a dict
def create_user(**kwargs):
    # kwargs is a dict of all keyword arguments
    for key in sorted(kwargs.keys()):    # sorted for deterministic output
        print(f"  {key}: {kwargs[key]}")

create_user(name="Alice", age=30, role="engineer")
# Output:   age: 30
# Output:   name: Alice
# Output:   role: engineer

# Example 3: Combined usage with correct ordering
def func(required, *args, **kwargs):
    print(f"required: {required}")
    print(f"args: {args}")
    # Sort kwargs keys for deterministic output
    print(f"kwargs: {dict(sorted(kwargs.items()))}")

func(1, 2, 3, x=4, y=5)
# Output: required: 1
# Output: args: (2, 3)
# Output: kwargs: {'x': 4, 'y': 5}

# Real-world use: wrapper functions, decorators, flexible APIs
def log_call(func_name, *args, **kwargs):
    """Log function calls in a data pipeline"""
    sorted_kw = dict(sorted(kwargs.items()))
    print(f"Calling {func_name} with args={args}, kwargs={sorted_kw}")

log_call("extract", "table_a", limit=100, format="parquet")
# Output: Calling extract with args=('table_a',), kwargs={'format': 'parquet', 'limit': 100}

# Example 1: Simple decorator — timing function execution
import time

def timer(func):
    """Decorator that measures execution time"""
    def wrapper(*args, **kwargs):
        start = time.time()
        result = func(*args, **kwargs)           # Call the original function
        elapsed = time.time() - start
        print(f"{func.__name__} took {elapsed:.4f}s")
        return result                             # Return the original result
    return wrapper

@timer
def process_data():
    total = sum(range(1000000))    # Some computation
    return total

result = process_data()
# Output: process_data took 0.0312s  (approximate)
print(result)
# Output: 499999500000

# Example 2: Decorator with arguments — retry logic
import time

def retry(max_attempts=3):
    """Decorator factory — returns a decorator configured with max_attempts"""
    def decorator(func):
        def wrapper(*args, **kwargs):
            for attempt in range(1, max_attempts + 1):
                try:
                    return func(*args, **kwargs)
                except Exception as e:
                    print(f"Attempt {attempt} failed: {e}")
                    if attempt == max_attempts:
                        raise
            return None
        return wrapper
    return decorator

@retry(max_attempts=2)
def fetch_data():
    print("Fetching...")
    return {"status": "ok"}

result = fetch_data()
# Output: Fetching...
print(result)
# Output: {'status': 'ok'}

# Example 3: Understanding decorator syntax — @ is syntactic sugar
def shout(func):
    def wrapper():
        result = func()
        return result.upper()
    return wrapper

# These two are IDENTICAL:
@shout
def greet():
    return "hello world"

# Same as: greet = shout(greet)

print(greet())
# Output: HELLO WORLD

# Example 1: Threading for I/O-bound work (GIL is released during I/O)
import threading
import time

results = []
lock = threading.Lock()

def fetch_url(url, delay):
    """Simulate an I/O-bound task (API call)"""
    time.sleep(delay)          # GIL is released during sleep/I/O
    with lock:
        results.append(f"Done: {url}")

threads = [
    threading.Thread(target=fetch_url, args=("api/users", 0.1)),
    threading.Thread(target=fetch_url, args=("api/orders", 0.1)),
]

start = time.time()
for t in threads:
    t.start()
for t in threads:
    t.join()

elapsed = time.time() - start
print(sorted(results))
# Output: ['Done: api/orders', 'Done: api/users']
print(f"Time: {elapsed:.1f}s (parallel, not 0.2s)")
# Output: Time: 0.1s (parallel, not 0.2s)

# Example 2: Multiprocessing for CPU-bound work (bypasses GIL)
from multiprocessing import Pool

def square(n):
    """CPU-bound computation"""
    return n * n

# Each process has its own Python interpreter and GIL
with Pool(processes=2) as pool:
    results = pool.map(square, [1, 2, 3, 4, 5])

print(results)
# Output: [1, 4, 9, 16, 25]

# Example 3: When to use what — quick reference
# I/O-bound (network, disk, DB) --> threading or asyncio
#   - API calls, file reads, database queries
#   - GIL is released during I/O operations

# CPU-bound (math, data processing) --> multiprocessing
#   - Number crunching, image processing, data transformation
#   - Each process has its own GIL

# Data engineering --> PySpark / Dask
#   - Distributed computing across machines
#   - Each executor runs a separate Python process

print("Threading:       best for I/O-bound tasks")
print("Multiprocessing: best for CPU-bound tasks")
print("PySpark/Dask:    best for distributed big data")
# Output: Threading:       best for I/O-bound tasks
# Output: Multiprocessing: best for CPU-bound tasks
# Output: PySpark/Dask:    best for distributed big data

# Example 1: Value equality vs identity
a = [1, 2, 3]
b = [1, 2, 3]    # Same values, different object

print(a == b)
# Output: True    (same values)
print(a is b)
# Output: False   (different objects in memory)

c = a             # c points to the SAME object as a
print(a is c)
# Output: True    (same object)

# Example 2: The correct way to check for None
value = None

# CORRECT — use 'is' for None checks
if value is None:
    print("Value is None")
# Output: Value is None

# ALSO CORRECT — 'is not' for the opposite
value = 42
if value is not None:
    print(f"Value is {value}")
# Output: Value is 42

# WHY? None is a singleton — there's only ONE None object in Python
# So 'is' is both correct and faster than ==

# Example 3: Python's integer caching — a common gotcha
# Python caches small integers from -5 to 256
a = 256
b = 256
print(a is b)
# Output: True    (cached — same object)

a = 257
b = 257
print(a is b)
# Output: False   (not cached — different objects)

# LESSON: Never use 'is' to compare integers or strings
# Always use == for value comparison
print(a == b)
# Output: True    (correct way to compare values)

# Example 1: Reference counting in action
import sys

a = [1, 2, 3]
print(sys.getrefcount(a))
# Output: 2   (one for 'a', one for the getrefcount argument)

b = a                        # Another reference to the same list
print(sys.getrefcount(a))
# Output: 3   (a + b + getrefcount arg)

del b                        # Remove one reference
print(sys.getrefcount(a))
# Output: 2   (back to a + getrefcount arg)

# Example 2: Circular references — garbage collector handles these
import gc

class Node:
    def __init__(self, name):
        self.name = name
        self.ref = None        # Will create circular reference

# Create circular reference
a = Node("A")
b = Node("B")
a.ref = b                     # A points to B
b.ref = a                     # B points to A (circular!)

# Delete external references
del a
del b
# Reference count for both is still 1 (they point to each other)
# But Python's garbage collector detects and cleans circular references

collected = gc.collect()       # Force garbage collection
print(f"Garbage collector cleaned up {collected} objects")
# Output: Garbage collector cleaned up 0 objects
# (may vary; objects might already be collected)

28 bytes
print(f"int(1):      {sys.getsizeof(1)} bytes")
# Output: int(1):      28 bytes
print(f"str(''):     {sys.getsizeof('')} bytes")
# Output: str(''):     49 bytes
print(f"str('hello'):{sys.getsizeof('hello')} bytes")
# Output: str('hello'):54 bytes
print(f"list([]):    {sys.getsizeof([])} bytes")
# Output: list([]):    56 bytes
print(f"dict({{}}):    {sys.getsizeof({})} bytes")
# Output: dict({}):    64 bytes"># Example 3: Checking memory usage of objects
import sys

# Different types use different amounts of memory
print(f"int(0):      {sys.getsizeof(0)} bytes")
# Output: int(0):      28 bytes
print(f"int(1):      {sys.getsizeof(1)} bytes")
# Output: int(1):      28 bytes
print(f"str(''):     {sys.getsizeof('')} bytes")
# Output: str(''):     49 bytes
print(f"str('hello'):{sys.getsizeof('hello')} bytes")
# Output: str('hello'):54 bytes
print(f"list([]):    {sys.getsizeof([])} bytes")
# Output: list([]):    56 bytes
print(f"dict({{}}):    {sys.getsizeof({})} bytes")
# Output: dict({}):    64 bytes

# Example 1: Lambda vs regular function — equivalent code
# Lambda version
square = lambda x: x ** 2
print(square(5))
# Output: 25

# Equivalent regular function
def square_func(x):
    return x ** 2

print(square_func(5))
# Output: 25

# Example 2: Lambda with sorted() — most common real-world use
# Sort list of dicts by a specific key
employees = [
    {"name": "Charlie", "salary": 75000},
    {"name": "Alice", "salary": 90000},
    {"name": "Bob", "salary": 60000},
]

# Sort by salary ascending
by_salary = sorted(employees, key=lambda emp: emp["salary"])
for emp in by_salary:
    print(f"{emp['name']}: {emp['salary']}")
# Output: Bob: 60000
# Output: Charlie: 75000
# Output: Alice: 90000

# Sort by name descending
by_name_desc = sorted(employees, key=lambda emp: emp["name"], reverse=True)
for emp in by_name_desc:
    print(emp["name"])
# Output: Charlie
# Output: Bob
# Output: Alice

# Example 3: Lambda with map() and filter()
numbers = [1, 2, 3, 4, 5, 6, 7, 8]

# filter: keep only even numbers
evens = list(filter(lambda x: x % 2 == 0, numbers))
print(evens)
# Output: [2, 4, 6, 8]

# map: double each number
doubled = list(map(lambda x: x * 2, numbers))
print(doubled)
# Output: [2, 4, 6, 8, 10, 12, 14, 16]

# Note: List comprehensions are usually more Pythonic
evens_lc = [x for x in numbers if x % 2 == 0]
doubled_lc = [x * 2 for x in numbers]
print(evens_lc)
# Output: [2, 4, 6, 8]
print(doubled_lc)
# Output: [2, 4, 6, 8, 10, 12, 14, 16]

# Example 1: append() adds ONE item — even if that item is a list
a = [1, 2]
a.append([3, 4])       # Adds the entire list as a single element
print(a)
# Output: [1, 2, [3, 4]]
print(len(a))
# Output: 3             (the inner list counts as one element)

# Example 2: extend() unpacks the iterable and adds each element
b = [1, 2]
b.extend([3, 4])       # Adds 3 and 4 individually
print(b)
# Output: [1, 2, 3, 4]
print(len(b))
# Output: 4

# extend works with any iterable, not just lists
c = [1, 2]
c.extend("abc")        # Strings are iterable — adds each character
print(c)
# Output: [1, 2, 'a', 'b', 'c']

# Example 3: += is equivalent to extend() (not append!)
d = [1, 2]
d += [3, 4]             # Same as d.extend([3, 4])
print(d)
# Output: [1, 2, 3, 4]

# Comparison side by side
append_result = [1, 2]
extend_result = [1, 2]
pluseq_result = [1, 2]

append_result.append([3, 4])
extend_result.extend([3, 4])
pluseq_result += [3, 4]

print(f"append: {append_result}")
# Output: append: [1, 2, [3, 4]]
print(f"extend: {extend_result}")
# Output: extend: [1, 2, 3, 4]
print(f"+=:     {pluseq_result}")
# Output: +=:     [1, 2, 3, 4]

# Example 1: Simple generator with yield
def count_up_to(n):
    """Generator that yields numbers from 1 to n"""
    i = 1
    while i <= n:
        yield i          # Pause here, return value, resume on next call
        i += 1

gen = count_up_to(5)
print(next(gen))
# Output: 1
print(next(gen))
# Output: 2
print(list(gen))        # Remaining values
# Output: [3, 4, 5]

# Example 2: Generator for processing data in chunks
def chunked_range(start, end, chunk_size):
    """Yield data in chunks — simulates batch processing"""
    for i in range(start, end, chunk_size):
        chunk = list(range(i, min(i + chunk_size, end)))
        yield chunk       # Only one chunk in memory at a time

for batch in chunked_range(0, 10, 3):
    print(f"Processing batch: {batch}")
# Output: Processing batch: [0, 1, 2]
# Output: Processing batch: [3, 4, 5]
# Output: Processing batch: [6, 7, 8]
# Output: Processing batch: [9]

# Example 3: Generator pipeline — chaining generators for ETL
def generate_rows():
    """Extract: produce raw rows"""
    data = [
        {"name": "Alice", "score": 85},
        {"name": "Bob", "score": 45},
        {"name": "Charlie", "score": 92},
    ]
    for row in data:
        yield row

def filter_passing(rows, threshold=60):
    """Transform: keep only passing scores"""
    for row in rows:
        if row["score"] >= threshold:
            yield row

def format_output(rows):
    """Transform: format for display"""
    for row in rows:
        yield f"{row['name']}: {row['score']}"

# Chain generators — no intermediate lists created
pipeline = format_output(filter_passing(generate_rows()))
for record in pipeline:
    print(record)
# Output: Alice: 85
# Output: Charlie: 92

# Example 1: All three method types compared
class DataProcessor:
    default_format = "csv"          # Class variable

    def __init__(self, name):
        self.name = name            # Instance variable

    def process(self):
        """Regular method — has access to instance (self)"""
        return f"{self.name} processing as {self.default_format}"

    @classmethod
    def set_format(cls, fmt):
        """Class method — has access to class (cls), not instance"""
        cls.default_format = fmt
        return f"Format set to {fmt}"

    @staticmethod
    def validate_extension(filename):
        """Static method — no access to class or instance"""
        return filename.endswith((".csv", ".json", ".parquet"))

# Regular method — needs an instance
dp = DataProcessor("Pipeline-1")
print(dp.process())
# Output: Pipeline-1 processing as csv

# Class method — can be called on the class itself
print(DataProcessor.set_format("parquet"))
# Output: Format set to parquet

# Static method — utility function, no class/instance needed
print(DataProcessor.validate_extension("data.csv"))
# Output: True
print(DataProcessor.validate_extension("data.exe"))
# Output: False

# Example 2: @classmethod as alternative constructor
class Config:
    def __init__(self, host, port, db):
        self.host = host
        self.port = port
        self.db = db

    @classmethod
    def from_string(cls, config_str):
        """Alternative constructor — parses a config string"""
        host, port, db = config_str.split(":")
        return cls(host, int(port), db)   # cls() creates a new instance

    def __repr__(self):
        return f"Config({self.host}:{self.port}/{self.db})"

# Standard constructor
c1 = Config("localhost", 5432, "mydb")
print(c1)
# Output: Config(localhost:5432/mydb)

# Alternative constructor via classmethod
c2 = Config.from_string("prod-server:5432:analytics")
print(c2)
# Output: Config(prod-server:5432/analytics)

# Example 3: When to use which — decision guide
class DateUtils:
    date_format = "%Y-%m-%d"

    @staticmethod
    def is_weekend(day_number):
        """No class or instance data needed — pure utility"""
        return day_number >= 5     # 5=Sat, 6=Sun

    @classmethod
    def get_format(cls):
        """Needs access to class-level configuration"""
        return cls.date_format

print(DateUtils.is_weekend(6))
# Output: True
print(DateUtils.get_format())
# Output: %Y-%m-%d

# Example 1: Reading a file with context manager
import json

# CORRECT — 'with' ensures file is closed even if an exception occurs
data = '{"name": "Alice", "role": "engineer"}'

# Simulating file read with json.loads (no external file needed)
config = json.loads(data)
print(config["name"])
# Output: Alice
print(config["role"])
# Output: engineer

# Pattern for real file reading:
# with open("config.json") as f:
#     config = json.load(f)

# BAD — file may not be closed if an exception occurs
# f = open("config.json")
# config = json.load(f)
# f.close()              # Skipped if exception happens above!

# Example 2: Reading large files — line by line (memory efficient)
import io

# Simulate a large CSV file
csv_content = "id,name,score\n1,Alice,85\n2,Bob,92\n3,Charlie,78\n"
fake_file = io.StringIO(csv_content)

# Line-by-line reading — only ONE line in memory at a time
row_count = 0
for line in fake_file:
    row_count += 1
    print(line.strip())
# Output: id,name,score
# Output: 1,Alice,85
# Output: 2,Bob,92
# Output: 3,Charlie,78
print(f"Total lines: {row_count}")
# Output: Total lines: 4

# Example 3: Reading in chunks — for binary or very large files
import io

# Simulate a large file
large_content = "A" * 100    # 100 characters

fake_file = io.StringIO(large_content)
chunk_size = 30
chunks_read = 0

while True:
    chunk = fake_file.read(chunk_size)
    if not chunk:
        break
    chunks_read += 1
    print(f"Chunk {chunks_read}: {len(chunk)} chars")
# Output: Chunk 1: 30 chars
# Output: Chunk 2: 30 chars
# Output: Chunk 3: 30 chars
# Output: Chunk 4: 10 chars
print(f"Total chunks: {chunks_read}")
# Output: Total chunks: 4

# Example 1: Basic dict comprehension — creating a mapping
# Square mapping
squares = {x: x ** 2 for x in range(6)}
print(squares)
# Output: {0: 0, 1: 1, 2: 4, 3: 9, 4: 16, 5: 25}

# Equivalent loop (more verbose)
squares_loop = {}
for x in range(6):
    squares_loop[x] = x ** 2
print(squares_loop)
# Output: {0: 0, 1: 1, 2: 4, 3: 9, 4: 16, 5: 25}

# Example 2: Filtering with dict comprehension
scores = {"Alice": 85, "Bob": 55, "Charlie": 92, "Diana": 48}

# Keep only passing scores (>= 60)
passed = {k: v for k, v in sorted(scores.items()) if v >= 60}
print(passed)
# Output: {'Alice': 85, 'Charlie': 92}

# Invert a dictionary (swap keys and values)
inverted = {v: k for k, v in sorted(scores.items())}
print(inverted)
# Output: {48: 'Diana', 55: 'Bob', 85: 'Alice', 92: 'Charlie'}

# Example 3: Real-world use — transforming data structures
# Convert list of tuples to dict
raw_data = [("host", "localhost"), ("port", "5432"), ("db", "analytics")]
config = {k: v for k, v in raw_data}
print(config)
# Output: {'host': 'localhost', 'port': '5432', 'db': 'analytics'}

# Create a lookup table from a list of records
employees = [
    {"id": 101, "name": "Alice"},
    {"id": 102, "name": "Bob"},
    {"id": 103, "name": "Charlie"},
]
lookup = {emp["id"]: emp["name"] for emp in employees}
print(lookup)
# Output: {101: 'Alice', 102: 'Bob', 103: 'Charlie'}
print(lookup[102])
# Output: Bob

# Example 1: Bad vs Good — manual index vs enumerate
names = ["Alice", "Bob", "Charlie"]

# BAD — manual indexing with range(len(...))
for i in range(len(names)):
    print(f"{i}: {names[i]}")
# Output: 0: Alice
# Output: 1: Bob
# Output: 2: Charlie

# GOOD — enumerate is cleaner and more Pythonic
for i, name in enumerate(names):
    print(f"{i}: {name}")
# Output: 0: Alice
# Output: 1: Bob
# Output: 2: Charlie

# Example 2: Custom start index
tasks = ["Extract", "Transform", "Load"]

# Start counting from 1 instead of 0
for step, task in enumerate(tasks, start=1):
    print(f"Step {step}: {task}")
# Output: Step 1: Extract
# Output: Step 2: Transform
# Output: Step 3: Load

# Example 3: Practical use — finding positions of matching elements
scores = [72, 85, 91, 45, 88, 55, 93]
threshold = 80

# Find indices of scores above threshold
high_scorers = [(i, score) for i, score in enumerate(scores) if score > threshold]
print(high_scorers)
# Output: [(1, 85), (2, 91), (4, 88), (6, 93)]

# Convert enumerate to a dict
index_map = dict(enumerate(["zero", "one", "two", "three"]))
print(index_map)
# Output: {0: 'zero', 1: 'one', 2: 'two', 3: 'three'}

# Example 1: Structure visualization
# myproject/                    <- Project root
#   main.py                     <- Script
#   mypackage/                  <- Package (directory with __init__.py)
#     __init__.py               <- Makes this directory a package
#     utils.py                  <- Module (single .py file)
#     models.py                 <- Module
#     subpackage/               <- Sub-package
#       __init__.py
#       helpers.py              <- Module

# Import a module from a package
# from mypackage import utils
# from mypackage.subpackage import helpers

# Example 2: Creating and using a simple module
# Simulating what a module looks like

# --- File: math_utils.py (this would be a module) ---
def add(a, b):
    return a + b

def multiply(a, b):
    return a * b

PI = 3.14159

# --- File: main.py (importing the module) ---
# import math_utils
# result = math_utils.add(3, 4)

# Or selective import:
# from math_utils import add, PI
# result = add(3, 4)

# Demonstrating the concept inline
print(add(3, 4))
# Output: 7
print(f"PI = {PI}")
# Output: PI = 3.14159

# Example 3: __init__.py controls what gets exported
# --- File: mypackage/__init__.py ---
# This file runs when you do: import mypackage

# You can expose specific items at the package level:
# from .utils import helper_function
# from .models import DataModel

# Then users can do:
# from mypackage import helper_function   (clean import)
# Instead of:
# from mypackage.utils import helper_function   (longer path)

# Check if something is a module, package, or built-in
import json
import os

print(type(json))
# Output: <class 'module'>
print(hasattr(json, '__path__'))
# Output: False   (json is a module, not a package in this context)
print(hasattr(os, '__path__'))
# Output: True    (os is a package — it's a directory with __init__.py)

# Example 1: Full try/except/else/finally structure
def divide(a, b):
    try:
        result = a / b                    # Risky operation
    except ZeroDivisionError:
        print("Error: Cannot divide by zero!")
        return None
    except TypeError as e:
        print(f"Error: Wrong types — {e}")
        return None
    else:
        print(f"Success: {a} / {b} = {result}")   # Only if NO exception
        return result
    finally:
        print("Cleanup: division attempt complete")  # ALWAYS runs

print(divide(10, 3))
# Output: Success: 10 / 3 = 3.3333333333333335
# Output: Cleanup: division attempt complete
# Output: 3.3333333333333335

print(divide(10, 0))
# Output: Error: Cannot divide by zero!
# Output: Cleanup: division attempt complete
# Output: None

# Example 2: Catching multiple exception types
def parse_config(value):
    """Parse a config value — handle various errors"""
    try:
        # Try converting to int
        result = int(value)
        return result
    except ValueError:
        print(f"'{value}' is not a valid integer")
        return None
    except TypeError:
        print(f"Expected string or number, got {type(value).__name__}")
        return None

print(parse_config("42"))
# Output: 42
print(parse_config("abc"))
# Output: 'abc' is not a valid integer
# Output: None
print(parse_config(None))
# Output: Expected string or number, got NoneType
# Output: None

# Example 3: Custom exceptions for data pipelines
class DataValidationError(Exception):
    """Custom exception for data quality issues"""
    def __init__(self, column, message):
        self.column = column
        self.message = message
        super().__init__(f"Column '{column}': {message}")

def validate_row(row):
    if row.get("age") is not None and row["age"] < 0:
        raise DataValidationError("age", "negative value not allowed")
    if not row.get("name"):
        raise DataValidationError("name", "cannot be empty")
    return True

# Test validation
test_rows = [
    {"name": "Alice", "age": 30},
    {"name": "Bob", "age": -5},
    {"name": "", "age": 25},
]

for row in test_rows:
    try:
        validate_row(row)
        print(f"Valid: {row}")
    except DataValidationError as e:
        print(f"Invalid: {e}")
# Output: Valid: {'name': 'Alice', 'age': 30}
# Output: Invalid: Column 'age': negative value not allowed
# Output: Invalid: Column 'name': cannot be empty

# Example 1: Basic zip — pairing two lists
names = ["Alice", "Bob", "Charlie"]
scores = [85, 92, 78]

paired = list(zip(names, scores))
print(paired)
# Output: [('Alice', 85), ('Bob', 92), ('Charlie', 78)]

# Create a dict from two lists
score_map = dict(zip(names, scores))
print(score_map)
# Output: {'Alice': 85, 'Bob': 92, 'Charlie': 78}

# Example 2: Unzipping with zip(*)
pairs = [("Alice", 85), ("Bob", 92), ("Charlie", 78)]

# Unzip — separate back into individual tuples
names_back, scores_back = zip(*pairs)
print(names_back)
# Output: ('Alice', 'Bob', 'Charlie')
print(scores_back)
# Output: (85, 92, 78)

# Convert back to lists if needed
print(list(names_back))
# Output: ['Alice', 'Bob', 'Charlie']

# Example 3: Unequal lengths and zip_longest
from itertools import zip_longest

names = ["Alice", "Bob", "Charlie"]
scores = [85, 92]                      # Shorter!

# Regular zip — stops at shortest
print(list(zip(names, scores)))
# Output: [('Alice', 85), ('Bob', 92)]
# Charlie is DROPPED silently!

# zip_longest — fills missing values with a default
print(list(zip_longest(names, scores, fillvalue=0)))
# Output: [('Alice', 85), ('Bob', 92), ('Charlie', 0)]

# Practical use: iterate multiple lists in parallel
columns = ["id", "name", "score"]
values = [101, "Alice", 85]

for col, val in zip(columns, values):
    print(f"  {col} = {val}")
# Output:   id = 101
# Output:   name = Alice
# Output:   score = 85