Lecture 13 – Dictionaries, File Formats, and Modules

Data 6, Summer 2021

names = ['bill', 'sarah', 'cal', 'nina']

names[2]

'cal'

dog = {'name': 'Junior', 
       'age': 11, 
       4: ['kibble', 'treat']}

dog['name']

'Junior'

dog['age']

11

dog[4]

['kibble', 'treat']

dog[0]

---------------------------------------------------------------------------
KeyError                                  Traceback (most recent call last)
/tmp/ipykernel_23/2067700495.py in <module>
----> 1 dog[0]

KeyError: 0

Quick Check 1

bears = {
    'polar': {
        'color': 'white',
        'weight_range': [175, 700],
        'hungry': True
    },
    'grizzly': {
        'color': 'brown',
        'weight_range': [130, 360],
        'endangered': False
    },
    None: ['koala', 'panda']
}

bears['polar']['hungry']

True

bears[None][1]

'panda'

bears['weight_range']

---------------------------------------------------------------------------
KeyError                                  Traceback (most recent call last)
/tmp/ipykernel_23/995406303.py in <module>
----> 1 bears['weight_range']

KeyError: 'weight_range'

Modification

# {} creates a new empty dictionary
slang = {}
slang

{}

slang['btw'] = 'by the way'
slang

{'btw': 'by the way'}

slang['nw'] = 'no worries'
slang

{'btw': 'by the way', 'nw': 'no worries'}

slang

{'btw': 'by the way', 'nw': 'no worries'}

slang['btw'] = 'bring the windex'
slang

{'btw': 'bring the windex', 'nw': 'no worries'}

slang['nw'] += ", it's cool"
slang

{'btw': 'bring the windex', 'nw': "no worries, it's cool"}

Quick Check 2

two = 1
numbers = {'1': 2}
numbers['five'] = 5
numbers[two] = numbers['1']
numbers[2] = numbers[1] + numbers['five']

numbers['1']

2

numbers['five']

5

numbers[1]

2

numbers[2]

7

Iteration

more_slang = {
    'haha': 'that was not funny',
    'smh': 'shake my head',
    'lol': 'laugh out loud',
    'GOAT': 'greatest of all time'
}

# Number of key-value pairs
len(more_slang)

4

# We will do this often!
list(more_slang.keys())

['haha', 'smh', 'lol', 'GOAT']

# We will not do this often
list(more_slang.values())

['that was not funny',
 'shake my head',
 'laugh out loud',
 'greatest of all time']

# Checks if 'smh' is a key
'smh' in more_slang

True

# Checks if 'shake my head' is a key
# It is not – it is a value
'shake my head' in more_slang

False

more_slang

{'haha': 'that was not funny',
 'smh': 'shake my head',
 'lol': 'laugh out loud',
 'GOAT': 'greatest of all time'}

for abb in more_slang.keys():
    print(more_slang[abb])

that was not funny
shake my head
laugh out loud
greatest of all time

for abb in more_slang.keys():
    print(abb, more_slang[abb])

haha that was not funny
smh shake my head
lol laugh out loud
GOAT greatest of all time

Example: replace slang

# Replaces all abbreviations in text
# that are defined in more_slang
# with their full forms

def replace_slang(text):
    for abb in more_slang.keys():
        if abb in text:
            text = text.replace(abb, more_slang[abb])
    return text

replace_slang('smh, I did not lol')

'shake my head, I did not laugh out loud'

replace_slang('serena is the GOAT')

'serena is the greatest of all time'

Data formats

grandma_tree = {
    "name": "Grandma",
    "children": [
        {"name": "Dad",
         "children": [
            {"name": "Me"},
            {"name": "Brother"}
             ]
            },
        {"name": "my aunt",
         "children": [
            {"name": "Cousin 1"},
            {"name": "Cousin 2",
             "children": [
                 {"name": "Cousin 2 Jr."}
                 ]
              }
            ]
        }
    ]
}

Modules

np.pi

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
/tmp/ipykernel_23/4136878702.py in <module>
----> 1 np.pi

NameError: name 'np' is not defined

import numpy as np

np.pi

3.141592653589793

pi

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
/tmp/ipykernel_23/3440806613.py in <module>
----> 1 pi

NameError: name 'pi' is not defined

np.array([1, 2, 3]) + np.array([4, 5, -3])

array([5, 7, 0])

Table.read_table('data/pups.csv')

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
/tmp/ipykernel_23/1703717253.py in <module>
----> 1 Table.read_table('data/pups.csv')

NameError: name 'Table' is not defined

from datascience import *

pups = Table.read_table('data/pups.csv')

pups

name	age	breed
Junior Smith	11	cockapoo
Rex Rogers	7	labradoodle
Flash Heat	3	labrador
Reese Bo	4	boston terrier
Polo Cash	2	shih tzu

Table.read_table('covid.csv')

state	cases
california	100
texas	120

import json
def read_json(path):
    return json.load(open(path, 'r'))

read_json('data/family.json')

{'name': 'Grandma',
 'children': [{'name': 'Dad',
   'children': [{'name': 'Me'}, {'name': 'Brother'}]},
  {'name': 'my aunt',
   'children': [{'name': 'Cousin 1'},
    {'name': 'Cousin 2', 'children': [{'name': 'Cousin 2 Jr.'}]}]}]}