.ipynb .pdf

repository

Binder

Contents

Week 3 Videos

Lists and related data types in Python

In this video we’ll discuss some similarities and differences between:

• lists

• tuples

• sets

• ranges

• NumPy arrays

range(1,100,3)

range(1, 100, 3)

r = range(1,100,3)

list(r)

[1,
 4,
 7,
 10,
 13,
 16,
 19,
 22,
 25,
 28,
 31,
 34,
 37,
 40,
 43,
 46,
 49,
 52,
 55,
 58,
 61,
 64,
 67,
 70,
 73,
 76,
 79,
 82,
 85,
 88,
 91,
 94,
 97]

type(r)

range

import sys

sys.getsizeof(r)

48

sys.getsizeof(list(r))

416

r2 = range(10**7)

l2 = list(r2)

sys.getsizeof(r2)

48

sys.getsizeof(l2)

90000120

my_list = [3,1,4,1,5]

type(my_list)

list

range(my_list)

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
/var/folders/8j/gshrlmtn7dg4qtztj4d4t_w40000gn/T/ipykernel_43435/890806220.py in <module>
----> 1 range(my_list)

TypeError: 'list' object cannot be interpreted as an integer

my_list.append(13)

my_list

[3, 1, 4, 1, 5, 13]

r

range(1, 100, 3)

r.append(13)

---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
/var/folders/8j/gshrlmtn7dg4qtztj4d4t_w40000gn/T/ipykernel_43435/2895788540.py in <module>
----> 1 r.append(13)

AttributeError: 'range' object has no attribute 'append'

set(r)

{1,
 4,
 7,
 10,
 13,
 16,
 19,
 22,
 25,
 28,
 31,
 34,
 37,
 40,
 43,
 46,
 49,
 52,
 55,
 58,
 61,
 64,
 67,
 70,
 73,
 76,
 79,
 82,
 85,
 88,
 91,
 94,
 97}

my_list

[3, 1, 4, 1, 5, 13]

my_set = set(my_list)

my_set

{1, 3, 4, 5, 13}

my_set[0]

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
/var/folders/8j/gshrlmtn7dg4qtztj4d4t_w40000gn/T/ipykernel_43435/2063814584.py in <module>
----> 1 my_set[0]

TypeError: 'set' object is not subscriptable

my_list[0]

3

3 in my_list

True

3 in my_set

True

3 in range(1,100,2)

True

import pandas as pd

df = pd.DataFrame({"A":range(5),"B":range(6)})

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
/var/folders/8j/gshrlmtn7dg4qtztj4d4t_w40000gn/T/ipykernel_43435/270674517.py in <module>
----> 1 df = pd.DataFrame({"A":range(5),"B":range(6)})

~/miniconda3/envs/math10s22/lib/python3.7/site-packages/pandas/core/frame.py in __init__(self, data, index, columns, dtype, copy)
    612         elif isinstance(data, dict):
    613             # GH#38939 de facto copy defaults to False only in non-dict cases
--> 614             mgr = dict_to_mgr(data, index, columns, dtype=dtype, copy=copy, typ=manager)
    615         elif isinstance(data, ma.MaskedArray):
    616             import numpy.ma.mrecords as mrecords

~/miniconda3/envs/math10s22/lib/python3.7/site-packages/pandas/core/internals/construction.py in dict_to_mgr(data, index, columns, dtype, typ, copy)
    463 
    464     return arrays_to_mgr(
--> 465         arrays, data_names, index, columns, dtype=dtype, typ=typ, consolidate=copy
    466     )
    467 

~/miniconda3/envs/math10s22/lib/python3.7/site-packages/pandas/core/internals/construction.py in arrays_to_mgr(arrays, arr_names, index, columns, dtype, verify_integrity, typ, consolidate)
    117         # figure out the index, if necessary
    118         if index is None:
--> 119             index = _extract_index(arrays)
    120         else:
    121             index = ensure_index(index)

~/miniconda3/envs/math10s22/lib/python3.7/site-packages/pandas/core/internals/construction.py in _extract_index(data)
    633             lengths = list(set(raw_lengths))
    634             if len(lengths) > 1:
--> 635                 raise ValueError("All arrays must be of the same length")
    636 
    637             if have_dicts:

ValueError: All arrays must be of the same length

df = pd.DataFrame({"A":range(5),"B":range(0,10,2)})

df

	A	B
0	0	0
1	1	2
2	2	4
3	3	6
4	4	8

s = df.shape

s

(5, 2)

type(s)

tuple

list(s)

[5, 2]

s

(5, 2)

new_list = list(s)

new_list

[5, 2]

{3,5,new_list}

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
/var/folders/8j/gshrlmtn7dg4qtztj4d4t_w40000gn/T/ipykernel_43435/563774803.py in <module>
----> 1 {3,5,new_list}

TypeError: unhashable type: 'list'

{3,5,s}

{(5, 2), 3, 5}

import numpy as np

my_list

[3, 1, 4, 1, 5, 13]

my_array = np.array(my_list)

my_array

array([ 3,  1,  4,  1,  5, 13])

3 in my_array

True

2 in my_array

False

my_array[2]

4

my_array.shape

(6,)

my_list.shape

---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
/var/folders/8j/gshrlmtn7dg4qtztj4d4t_w40000gn/T/ipykernel_43435/2003403714.py in <module>
----> 1 my_list.shape

AttributeError: 'list' object has no attribute 'shape'

Timing using %%timeit

Some common abbreviations:

• ms means \(10^{-3}\) seconds

• µs means \(10^{-6}\) seconds

• ns means \(10^{-9}\) seconds

import numpy as np

my_array = np.arange(1,10**7)

type(my_array)

numpy.ndarray

my_list = list(my_array)

my_set = set(my_array)

-2 in my_array

False

-2 in my_list

False

-2 in my_set

False

%%timeit
-2 in my_array

3.06 ms ± 3.84 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)

%%timeit
-2 in my_list

955 ms ± 2.31 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)

%%timeit
-2 in my_set

29 ns ± 0.195 ns per loop (mean ± std. dev. of 7 runs, 10000000 loops each)

1/my_array[:10]

array([1.        , 0.5       , 0.33333333, 0.25      , 0.2       ,
       0.16666667, 0.14285714, 0.125     , 0.11111111, 0.1       ])

%%timeit
new_list = []
for x in my_list:
    new_list.append(1/x)

1.34 s ± 14.5 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)

%%timeit
[1/x for x in my_list]

1.17 s ± 13.6 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)

%%timeit
1/my_array

6.24 ms ± 21.7 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)

Created in Deepnote

previous

Working with dates in pandas

next

Homework 3