Lecture 4 – Comparisons and Boolean Operators

Data 6, Summer 2021

Review exercise – growth rates

$$\text{FV} = \text{PV} (1 + i)^t$$

PV = 1e4            # Scientific notation for 10000
FV = 47123
t = 10

i = (FV / PV) ** (1 / 10) - 1
i

0.16767852509215087

NoneType and bool

NoneType

my_var = None

type(my_var)

NoneType

# Nothing is displayed!
my_var

# But it can be printed.
print(my_var)

None

Pay attention to what happens here.

strange = print(15)

15

strange

print(strange)

None

bool

# Can display multiple values in one line
True, False

(True, False)

type(True), type(False)

(bool, bool)

int(True), int(False)

(1, 0)

# Equivalent to 3 + 1 - 0
3 + True - False

4

Keywords

# Doesn't work
3 = 4

  File "/tmp/ipykernel_113/679380462.py", line 2
    3 = 4
    ^
SyntaxError: cannot assign to literal

# Similarly, doesn't work
True = 14

  File "/tmp/ipykernel_113/2825449733.py", line 2
    True = 14
    ^
SyntaxError: cannot assign to True

# Works, but don't do it!
# Don't uncomment this, because it will ruin the demos later on.
# bool = "breaking the rules"
# bool

Quick Check 1

A = str('None') + str('00')

B = True * 8 - float(False) * 15

C = int(None) - 1

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
/tmp/ipykernel_113/3143381484.py in <module>
----> 1 C = int(None) - 1

TypeError: int() argument must be a string, a bytes-like object or a number, not 'NoneType'

Comparisons

# is age at least age_limit?
age_limit = 21
age = 17

age >= age_limit

False

# is password_guess equal to true_password?
true_password = 'qwerty1093x!'
password_guess = 'QWERTY1093x!'

password_guess == true_password

False

3 == 3

True

'hello' != 'howdy'

True

-3 > -2

False

-3 < -2

True

'alpha' >= 'beta'

False

x = 5         # set x equal to 5

x == 5        # is x equal to 5?

True

y = x == 5
y

True

Comparing different types

17 == '17'

False

'zebra' != True

True

True == 1.0

True

5 > True

True

'alpha' >= 'beta'

False

'alpha' >= 5

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
/tmp/ipykernel_113/1172788117.py in <module>
----> 1 'alpha' >= 5

TypeError: '>=' not supported between instances of 'str' and 'int'

Floating point issues, revisited

0.1 * 2 == 0.2

True

0.1 * 6

0.6000000000000001

0.1 * 6 == 0.6

False

abs(0.1 * 6 - 0.6) < 0.0001

True

String containment

'berkeley' in 'uc berkeley'

True

'stanford' in 'uc berkeley'

False

'berkeley' in 'UC BERKELEY'

False

Quick Check 2

passed = .5 * 30 + .5 * 100 >= 65
#passed

not_passed = passed == False
not_passed

False

Boolean operators

year = 'junior'
units = 125

year_check = year == 'senior'
year_check

False

units_check = units >= 120
units_check

True

ready_to_grad = year_check and units_check
almost_ready = year_check or units_check

ready_to_grad

False

units_check

True

n = 12
(n % 2 == 0) and (n % 4 == 0)

True

(n % 2 == 0) and not (n % 5 == 0)

True

(n % 3 != 0) and (n % 4 != 0)

False

True and False and True and True

False

True or False or True or True

True

3 < 4 <= 5

True

3 < 4 > 2 < 11 > -1

True

3 < 4 < 2 > 11 > -1

False

Quick Check 3

temp = 67
raining = bool(0)
wear_socks = (not not raining) and (temp < 60)
wear_jacket = (not wear_socks) or (temp > 65)
wear_jacket = wear_jacket and wear_socks

wear_socks

False

wear_jacket

False

Demo

The first cell contains code that's mostly copied from last lecture. Ignore it once again!

from datascience import *
import matplotlib.pyplot as plt
%matplotlib inline
import seaborn as sns
import numpy as np

data = Table.read_table('data/countries.csv')
data = data.relabeled('Country(or dependent territory)', 'Country') \
           .relabeled('% of world', '%') \
           .relabeled('Source(official or UN)', 'Source')
data = data.with_columns(
    'Country', data.apply(lambda s: s[:s.index('[')].lower() if '[' in s else s.lower(), 'Country'),
    'Population', data.apply(lambda i: int(i.replace(',', '')), 'Population'),
    '%', data.apply(lambda f: float(f.replace('%', '')), '%')
)

def first_letter(s):
    return s[0]

def last_letter(s):
    return s[-1]

data

Rank	Country	Population	%	Date	Source
1	china	1405936040	17.9	27 Dec 2020	National population clock[3]
2	india	1371366679	17.5	27 Dec 2020	National population clock[4]
3	united states	330888778	4.22	27 Dec 2020	National population clock[5]
4	indonesia	269603400	3.44	1 Jul 2020	National annual projection[6]
5	pakistan	220892331	2.82	1 Jul 2020	UN Projection[2]
6	brazil	212523810	2.71	27 Dec 2020	National population clock[7]
7	nigeria	206139587	2.63	1 Jul 2020	UN Projection[2]
8	bangladesh	169885314	2.17	27 Dec 2020	National population clock[8]
9	russia	146748590	1.87	1 Jan 2020	National annual estimate[9]
10	mexico	127792286	1.63	1 Jul 2020	National annual projection[10]

... (232 rows omitted)

Below, assign first_or_last to a string containing a single lowercase letter. We'll look at the distribution of populations of countries whose names either begin or end with first_or_last.

first_or_last = 'a'

relevant_countries = data.where(data.apply(
    
              # Focus on this part!
    lambda name: first_letter(name) == first_or_last and last_letter(name) == first_or_last
    
    
, 'Country')).sort('Population', descending = True)

relevant_countries

Rank	Country	Population	%	Date	Source
31	argentina	45376763	0.579	1 Jul 2020	National annual projection[31]
32	algeria	43900000	0.56	1 Jan 2020	National annual projection[32]
45	angola	31127674	0.397	30 Jun 2020	National annual projection[45]
53	australia	25720882	0.328	27 Dec 2020	National population clock[51]
97	austria	8935112	0.114	1 Oct 2020	National quarterly estimate[94]
134	armenia	2967900	0.0379	30 Sep 2020	National quarterly estimate[129]
135	albania	2845955	0.0363	1 Jan 2020	National annual estimate[130]
–	abkhazia	245424	0.00313	1 Jan 2020	National annual estimate[174]
184	antigua and barbuda	97895	0.00125	1 Jul 2020	National annual projection[186]
185	andorra	77543	0.000989	31 Dec 2019	National annual estimate[188]

# Ignore everything except the last line!
plt.figure(figsize = (10, 7))
names = relevant_countries.column('Country')
pops = relevant_countries.column('Population')

if relevant_countries.num_rows > 15:
    names = names[:15]
    pops = pops[:15]

sns.barplot(x = pops, y = names, orient = 'h')

# Focus on this part!
plt.title('Populations of countries starting or ending with ' + first_or_last);