Merge pull request #673 from realpython/python-namedtuple

Sample code for the article on namedtuple

Author: brendaweles

python-namedtuple/README.md

@@ -0,0 +1,3 @@
+# Write Pythonic and Clean Code With namedtuple
+
+This folder provides the code examples for the Real Python tutorial [Write Pythonic and Clean Code With namedtuple](https://realpython.com/python-namedtuple/).

python-namedtuple/employees.csv

@@ -0,0 +1,6 @@
+name,job,email
+"Linda","Technical Lead","[email protected]"
+"Joe","Senior Web Developer","[email protected]"
+"Lara","Project Manager","[email protected]"
+"David","Data Analyst","[email protected]"
+"Jane","Senior Python Developer","[email protected]"

python-namedtuple/employees.py

@@ -0,0 +1,9 @@
+import csv
+from collections import namedtuple
+
+with open("employees.csv", "r", encoding="utf-8") as csv_file:
+    reader = csv.reader(csv_file)
+    Employee = namedtuple("Employee", next(reader), rename=True)
+    for row in reader:
+        employee = Employee(*row)
+        print(employee.name, employee.job, employee.email)

python-namedtuple/namedtuple_dataclass_memory.py

@@ -0,0 +1,21 @@
+from collections import namedtuple
+from dataclasses import dataclass
+
+from pympler import asizeof
+
+PointNamedTuple = namedtuple("PointNamedTuple", "x y z")
+
+
+@dataclass
+class PointDataClass:
+    x: int
+    y: int
+    z: int
+
+
+namedtuple_memory = asizeof.asizeof(PointNamedTuple(x=1, y=2, z=3))
+dataclass_memory = asizeof.asizeof(PointDataClass(x=1, y=2, z=3))
+gain = 100 - namedtuple_memory / dataclass_memory * 100
+
+print(f"namedtuple: {namedtuple_memory} bytes ({gain:.2f}% lower)")
+print(f"data class: {dataclass_memory} bytes")

python-namedtuple/namedtuple_dataclass_time.py

@@ -0,0 +1,36 @@
+from collections import namedtuple
+from dataclasses import dataclass
+from time import perf_counter
+
+
+def average_time(structure, test_func):
+    time_measurements = []
+    for _ in range(1_000_000):
+        start = perf_counter()
+        test_func(structure)
+        end = perf_counter()
+        time_measurements.append(end - start)
+    return sum(time_measurements) / len(time_measurements) * int(1e9)
+
+
+def time_structure(structure):
+    structure.x
+    structure.y
+    structure.z
+
+
+PointNamedTuple = namedtuple("PointNamedTuple", "x y z", defaults=[3])
+
+
+@dataclass
+class PointDataClass:
+    x: int
+    y: int
+    z: int
+
+
+namedtuple_time = average_time(PointNamedTuple(x=1, y=2, z=3), time_structure)
+dataclass_time = average_time(PointDataClass(x=1, y=2, z=3), time_structure)
+
+print(f"namedtuple: {namedtuple_time:.2f} ns")
+print(f"data class: {dataclass_time:.2f} ns")

python-namedtuple/namedtuple_dict_memory.py

@@ -0,0 +1,13 @@
+from collections import namedtuple
+
+from pympler import asizeof
+
+Point = namedtuple("Point", "x y z")
+point = Point(1, 2, 3)
+
+namedtuple_size = asizeof.asizeof(point)
+dict_size = asizeof.asizeof(point._asdict())
+gain = 100 - namedtuple_size / dict_size * 100
+
+print(f"namedtuple: {namedtuple_size} bytes ({gain:.2f}% smaller)")
+print(f"dict:       {dict_size} bytes")

python-namedtuple/namedtuple_dict_time.py

@@ -0,0 +1,39 @@
+from collections import namedtuple
+from time import perf_counter
+
+
+def average_time(structure, test_func):
+    time_measurements = []
+    for _ in range(1_000_000):
+        start = perf_counter()
+        test_func(structure)
+        end = perf_counter()
+        time_measurements.append(end - start)
+    return sum(time_measurements) / len(time_measurements) * int(1e9)
+
+
+def time_dict(dictionary):
+    "x" in dictionary
+    "missing_key" in dictionary
+    2 in dictionary.values()
+    "missing_value" in dictionary.values()
+    dictionary["y"]
+
+
+def time_namedtuple(named_tuple):
+    "x" in named_tuple._fields
+    "missing_field" in named_tuple._fields
+    2 in named_tuple
+    "missing_value" in named_tuple
+    named_tuple.y
+
+
+Point = namedtuple("Point", "x y z")
+point = Point(x=1, y=2, z=3)
+
+namedtuple_time = average_time(point, time_namedtuple)
+dict_time = average_time(point._asdict(), time_dict)
+gain = dict_time / namedtuple_time
+
+print(f"namedtuple: {namedtuple_time:.2f} ns ({gain:.2f}x faster)")
+print(f"dict:       {dict_time:.2f} ns")

python-namedtuple/performance.py

@@ -0,0 +1,51 @@
+from collections import namedtuple
+
+STest = namedtuple("TEST", "a b c")
+a = STest(a=1, b=2, c=3)
+
+
+class Test(object):
+    __slots__ = ["a", "b", "c"]
+
+    def __init__(self) -> None:
+        self.a = 1
+        self.b = 2
+        self.c = 3
+
+
+b = Test()
+
+c = {"a": 1, "b": 2, "c": 3}
+
+d = (1, 2, 3)
+e = [1, 2, 3]
+f = (1, 2, 3)
+g = [1, 2, 3]
+key = 2
+
+if __name__ == "__main__":
+    from timeit import timeit
+
+    print("Named tuple with a, b, c:")
+    print(timeit("z = a.c", "from __main__ import a"))
+
+    print("Named tuple, using index:")
+    print(timeit("z = a[2]", "from __main__ import a"))
+
+    print("Class using __slots__, with a, b, c:")
+    print(timeit("z = b.c", "from __main__ import b"))
+
+    print("Dictionary with keys a, b, c:")
+    print(timeit("z = c['c']", "from __main__ import c"))
+
+    print("Tuple with three values, using a constant key:")
+    print(timeit("z = d[2]", "from __main__ import d"))
+
+    print("List with three values, using a constant key:")
+    print(timeit("z = e[2]", "from __main__ import e"))
+
+    print("Tuple with three values, using a local key:")
+    print(timeit("z = d[key]", "from __main__ import d, key"))
+
+    print("List with three values, using a local key:")
+    print(timeit("z = e[key]", "from __main__ import e, key"))

python-namedtuple/person_dataclass.py

@@ -0,0 +1,13 @@
+from dataclasses import astuple, dataclass
+
+
+@dataclass
+class Person:
+    name: str
+    age: int
+    height: float
+    weight: float
+    country: str = "Canada"
+
+    def __iter__(self):
+        return iter(astuple(self))

python-namedtuple/subclass.py

@@ -0,0 +1,26 @@
+from collections import namedtuple
+from datetime import date
+
+BasePerson = namedtuple(
+    "BasePerson", "name birthdate country", defaults=["Canada"]
+)
+
+
+class Person(BasePerson):
+    """A namedtuple subclass to hold a person's data."""
+
+    __slots__ = ()
+
+    def __repr__(self):
+        return f"Name: {self.name}, age: {self.age} years old."
+
+    @property
+    def age(self):
+        return (date.today() - self.birthdate).days // 365
+
+
+Person.__doc__
+
+jane = Person("Jane", date(1996, 3, 5))
+print(jane.age)
+print(jane)