4 built-in data types

In Python, lists, sets, tuples, and dictionaries are used to store collections of data. Each has different properties and use cases.

• list

# create a list
my_list = [1, 2, 3, "hello", 4.5]  # Mixed data types allowed

type(my_list) # list

dir(my_list) # .....
             # 'append',
             # 'clear',
             # 'copy',
             # 'count',
             # 'extend',
             # 'index',
             # 'insert',
             # 'pop',
             # 'remove',
             # 'reverse',
             # 'sort'

# accessing elements
x = [1, 4, 9, 16, 25]
print(x[0]) # 1
print(x[-1]) # 25
# indexing and slicing
print(x[1:3]) # [4, 9]
print(x[:3]) # [1, 4, 9]
print(x[3:]) # [16, 25]
print(x[-3:]) # [9, 16, 25]
print(x[:2]) # [1, 4]
print(x[::2]) # [1, 9, 25]
print(x[0::]) # [1, 4, 9, 16, 25]
print(x[::-1]) # [25, 16, 9, 4, 1]

# modify / update
x[0] = 0 # [0, 4, 9, 16, 25]

# add / append
x.append(36) # [0, 4, 9, 16, 25, 36]

# extend the list to the back
x.extend([40, 45]) # [0, 4, 9, 16, 25, 36, 40, 45]

or:

# extend the list to the back
x = x + [40, 45] # [0, 4, 9, 16, 25, 36, 40, 45]

# extend the list to the front
x = [1, 4, 9] + x # [1, 4, 9, 0, 4, 9, 16, 25, 36, 40, 45]

# remove by value
x.remove(0) # [1, 4, 9, 4, 9, 16, 25, 36, 40, 45]

# remove by index using "del"
del x[2] # [1, 4, 4, 9, 16, 25, 36, 40, 45]

# remove duplicate values
x = list(set(x)) # [1, 4, 36, 40, 9, 45, 16, 25]

# remove the last value
x.pop() # [1, 4, 36, 40, 9, 45, 16]

# remove two biggest values
x = sorted(x)[:-2] # [1, 4, 9, 16, 36]

# remove the first element
x.pop(0) # [4, 9, 16, 36]

#sort
x = [1, 9, 25, 16, 4]
print(sorted(x)) # [1, 4, 9, 16, 25]
print(sorted(x, reverse=True)) # [25, 16, 9, 4, 1]

# insert by index
x.insert(2, 7) # [1, 9, 7, 25, 16, 4]

# creat a list with the split method
fruits = 'apple,banana,pear'.split(',')

# use f-string to concatenate
for fruit in fruits:
  print(f'I like {fruit}s') # I like apples
                            # I like bananas
                            # I like pears

# duplicate data
basket = ['apple', 'orange', 'apple', 'pear', 'orange', 'banana']
basket.count('apple') # 2

# find duplicate data
from collections import Counter

counter = Counter(basket)

duplicates = {item: count for item, count in counter.items() if count > 1}

print(counter) # Counter({'apple': 2, 'orange': 2, 'pear': 1, 'banana': 1})
print(duplicates) # {'apple': 2, 'orange': 2}

# show indices of duplicate data
from collections import defaultdict

# Create a dictionary to store indices of each item
indices = defaultdict(list)

# Populate the dictionary with item indices
for index, item in enumerate(basket):
    indices[item].append(index)

# Filter out only the duplicates (items appearing more than once)
duplicates_with_indices = {item: idx_list for item, idx_list in indices.items() if len(idx_list) > 1}

print(duplicates_with_indices) # {'apple': [0, 2], 'orange': [1, 4]}

# sort and remove duplicate values
for i in sorted(basket):
    print(i) # apple
             # apple
             # banana
             # orange
             # orange
             # pear
for i in sorted(basket, reverse=True):
    print(i) # pear
             # orange
             # orange
             # banana
             # apple
             # apple
# remove duplicate values using set()
for i in sorted(set(basket)):
  print(i) # apple
           # banana
           # orange
           # pear
# save the sorted, unduplicated list to new_list
new_list = []
for i in sorted(set(basket)):
  new_list.append(i)
  print(new_list) # ['apple', 'banana', 'orange', 'pear']

or:

new_list = sorted(set(basket)) # ['apple', 'banana', 'orange', 'pear']

# squaring with "for" loop
y = [1, 2, 3]
for a in y:
  print(f'{a} square is {a**2}.') # 1 square is 1.
                                  # 2 square is 4.
                                  # 3 square is 9.

# squaring for even numbers
for a in y:
  if a % 2 == 0:
    print(f'{a} square is {a**2} for even numbers.') # 2 square is 4 for even numbers.

# squaring with odd numbers
for a in y:
  if a % 2 != 0:
    print(f'{a} square is {a**2} for odd numbers.') # 1 square is 1 for odd numbers.
                                                    # 3 square is 9 for odd numbers.

# squaring for both even and odd numbers
for a in y:
  if a % 2 == 0:
    print(f'{a} square is {a**2} for even numbers.')
  else:
    print(f'{a} square is {a**2} for odd numbers.') # 1 square is 1 for odd numbers.
                                                    # 2 square is 4 for even numbers.
                                                    # 3 square is 9 for odd numbers.

# squaring numbers created with "range"
for i in range(5):
  print(i*i) # 0
             # 1
             # 4
             # 9
             # 16

# make a list from a to g
letters = [chr(i) for i in range(ord('a'), ord('g') + 1)] # ['a', 'b', 'c', 'd', 'e', 'f', 'g']

# replace some values
letters[2:5] = ['C', 'D', 'E'] # ['a', 'b', 'C', 'D', 'E', 'f', 'g']

# remove some values
letters[2:5] = [] # ['a', 'b', 'f', 'g']
len(letters) # 4

# clear the list
letters = [] # []

# removing NaNs

import math

data = [10, float('nan'), 25, 30, math.nan, 40, None, "apple", True, 3.5]
cleaned_data = [x for x in data if not (isinstance(x, float) and math.isnan(x))]
print(cleaned_data) # [10, 25, 30, 40, None, 'apple', True, 3.5]

# isinstance(x, float): Checks if x is a float data type.
# math.isnan(x): Checks if x is "Not a Number" (NaN).

# removing NaNs and strings
cleaned_data = [x for x in data if isinstance(x, (int, float)) and not math.isnan(x)]
print(cleaned_data) # [10, 25, 30, 40, True, 3.5]

# isinstance(x, (int, float)): Ensures only numbers (int or float) are considered.
# not math.isnan(x): Removes NaN values.

# removing NaNs, strings and boolean values
cleaned_data = [x for x in data if isinstance(x, (int, float)) and not isinstance(x, bool) and not math.isnan(x)]
print(cleaned_data) # [10, 25, 30, 40, 3.5]

# not isinstance(x, bool): Excludes boolean values (True and False).