from datascience import *
import numpy as np

Tables¶

A table is given a name (such as nba) in our programming environment so that we can perform operations on the whole table.

# From https://github.com/erikgregorywebb/datasets/blob/master/nba-salaries.csv
nba = Table.read_table('nba_salaries.csv')
nba

Manipulating the table creates a new table, but doesn’t change/lose the original.

nba.select('name')

nba.drop('rank', 'position').sort('name')

nba.sort('name')

'nba'

Because each operation creates a new table, multiple operations can be applied.

nba.where('position', 'PG')

nba.where('name', "Shaquille O'Neal")

The result of applying operations is a table, which can also be given a name (e.g., point_guards) in our programming environment.

point_guards = nba.where('position', 'PG').drop('rank', 'position')
point_guards

point_guards.where('season', 2020).sort('name').sort('team')

nba

Sorting can be performed in descending order as well.

point_guards.where('season', 2020).sort('salary').show(10)

point_guards.where('season', 2020).sort('salary', descending=True).show(10)

Numbers¶

30

10 * 3    # int

30

10 / 3    # float

3.3333333333333335

10 / 2

5.0

10 ** 3

1000

10 ** 0.5

3.1622776601683795

1234567 ** 89

139574185988226216352411677967079384654819840770263154148901015711434587555916221871855053939370772085656915237689603767083349991793713346471091572628494106076146419389211087459209170823939332677859093756734470172351895079430772488109105692648444480028380122417140932569432824316430008740958025053716735421344729410520681559715479472541631321425013768978692403188995380725532383634472359562908542469547971146457062422356845701571795811721146126639734809904577967012608961528997012178537266420111446716001493476975934877110973383995456863730247

10 / 3

3.3333333333333335

75892745.215489247589274985712

75892745.21548925

75892745.215489247589274985712 - 75892745.21548925

0.0

(13 ** 0.5) ** 2

12.999999999999998

3.605551275463989 * 3.605551275463989

12.999999999999998

int(10 / 5)

2

int(10 / 4)

2

float(3)

3.0

6 / 4

1.5

6 / 4000

0.0015

6 / 400000000000000000000000000000000000000000000000000000000

1.5e-56

400000000000000000000000000000000000000000000000000000000 * 1.5e-56

6.0

1.5e-56

1.5e-56

x = 5

5

x + 1

6

2x

  Cell In[64], line 1
    2x
    ^
SyntaxError: invalid decimal literal

2 * x

10

Strings¶

'Flavor'

'Flavor'

flavor = 2

flavor

2

# The line below causes a name error
# Flavor

"Flavor"

'Flavor'

'Don't always use single quotes'

  Cell In[72], line 1
    'Don't always use single quotes'
                                   ^
SyntaxError: unterminated string literal (detected at line 1)

"Don't always use single quotes"

"Don't always use single quotes"

'straw' 'berry' # concatenation

'strawberry'

'straw' + 'berry' # concatenation

'strawberry'

'Chris' + 'Paul' # spaces aren't added for you

'ChrisPaul'

'Chris' + ' ' + 'Paul'

'Chris Paul'

x = 'straw'
y = 'berry'
x + y

'strawberry'

x y

  Cell In[80], line 1
    x y
      ^
SyntaxError: invalid syntax

'ha' * 100

'hahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahahaha'

'lo' * 5.5

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
Cell In[82], line 1
----> 1 'lo' * 5.5

TypeError: can't multiply sequence by non-int of type 'float'

'ha' + 10

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
Cell In[83], line 1
----> 1 'ha' + 10

TypeError: can only concatenate str (not "int") to str

'ha' + str(10)

'ha10'

'ha' + '10'

'ha10'

'3' + 5

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
Cell In[87], line 1
----> 1 '3' + 5

TypeError: can only concatenate str (not "int") to str

int('3') + 5

8

int('3.0')

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
Cell In[90], line 1
----> 1 int('3.0')

ValueError: invalid literal for int() with base 10: '3.0'

'3.0'

'3.0'

float('3.0')

3.0

int(3.0)

3

int(float('3.0'))

3

dot_oh = '.0'
float('3' + dot_oh)

3.0

float('3' + dot_oh) * 7

21.0

Types¶

type(10)

int

a = 10

10

type(a)

int

type(4.5)

float

type('abc')

str

type(nba)

datascience.tables.Table

type(Table.read_table('nba_salaries.csv'))

datascience.tables.Table

type(True)

bool

type(abs(-5))

int

type(abs)

builtin_function_or_method

Arrays¶

first_four = make_array(1, 2, 3, 4)

first_four

array([1, 2, 3, 4])

array([1, 2, 3, 4])

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[116], line 1
----> 1 array([1, 2, 3, 4])

NameError: name 'array' is not defined

from numpy import array

array([1, 2, 3, 4])

array([1, 2, 3, 4])

first_four

array([1, 2, 3, 4])

first_four * 2

array([2, 4, 6, 8])

first_four ** 2

array([ 1, 4, 9, 16])

(first_four + 1) ** 2

array([ 4, 9, 16, 25])

first_four # array is unchanged, just like when we call show/select/drop on Table

array([1, 2, 3, 4])

next_four = make_array(5, 6, 7, 8)

next_four

array([5, 6, 7, 8])

first_four + next_four

array([ 6, 8, 10, 12])

only_three = make_array(5, 6, 7)

# This line will cause an error 
first_four + only_three

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
Cell In[129], line 2
      1 # This line will cause an error 
----> 2 first_four + only_three

ValueError: operands could not be broadcast together with shapes (4,) (3,)

str_array = make_array('ha', 'he', 'ho')

str_array

array(['ha', 'he', 'ho'],
      dtype='<U2')

str_array * 4

---------------------------------------------------------------------------
UFuncTypeError                            Traceback (most recent call last)
Cell In[132], line 1
----> 1 str_array * 4

UFuncTypeError: ufunc 'multiply' did not contain a loop with signature matching types (dtype('<U2'), dtype('int64')) -> None

next_four

array([5, 6, 7, 8])

next_four.item(0)

5

next_four.item(4)

---------------------------------------------------------------------------
IndexError                                Traceback (most recent call last)
Cell In[138], line 1
----> 1 next_four.item(4)

IndexError: index 4 is out of bounds for axis 0 with size 4

sum(next_four)

np.average(next_four)

len(next_four)