Python Basics for Data Science

year_of_birth = 1994 height_cm = 170.50 subject = "Data Science" is_success = True print(type(year_of_birth), type(height_cm), type(subject), type(is_success))

fruits = ["pineapple", "apple", "lemon", "strawberry", "orange", "kiwi"] fruits[1] # apple fruits[0] # "pineapple" fruits[-1] # "kiwi" fruits[5] # "kiwi" fruits[-3] # "strawberry" # List slicing fruits[::] # ["pineapple", "apple", "lemon", "strawberry", "orange", "kiwi"] fruits[0:2] # ["pineapple", "apple"] fruits[-2:-1] # ["orange"] fruits[3:] # ["strawberry", "orange", "kiwi"] fruits[:4] # ["pineapple", "apple", "lemon", "strawberry"] fruits[:] # ["pineapple", "apple", "lemon", "strawberry", "orange", "kiwi"] fruits[::-1] # ["kiwi", "orange", "strawberry", "lemon", "apple", "pineapple"] fruits[::-2] # ["kiwi", "strawberry", "apple"] fruits[::2] # ["pineapple", "lemon", "orange"]

# Add values to a list fruits.append("peach") fruits # ["pineapple", "apple", "lemon", "strawberry", "orange", "kiwi", "peach"] fruits = fruits + ["fig", "melon"] fruits # ["pineapple", "apple", "lemon", "strawberry", "orange", "kiwi", "peach", "fig", "melon"] # Change values from a list fruits[0:2] = ["grape", "mango"] fruits # ["grape", "mango", "lemon", "strawberry", "orange", "kiwi", "peach", "fig", "melon"] # Delete values from a list fruits.remove("mango") fruits # ["grape", "lemon", "strawberry", "orange", "kiwi", "peach", "fig", "melon"]

numbers = [10, 42, 28, 420] numbers_copy = numbers numbers_copy[2] = 100 numbers # [10, 42, 100, 420] numbers_copy # [10, 42, 100, 420] ratings = [4.5, 5.0, 3.5, 4.75, 4.00] ratings_copy = ratings[:] ratings_copy[0] = 2.0 ratings # [4.5, 5.0, 3.5, 4.75, 4.0] ratings_copy # [2.0, 5.0, 3.5, 4.75, 4.0] characters = ["A", "B", "C"] characters_copy = list(characters) characters_copy[-1] = "D" characters # ["A", "B", "C"] characters_copy # ["A", "B", "D"]

movies = ["Ex Machina", "Mad Max: Fury Road", "1408"] ratings = [7.7, 8.1, 6.8] movie_choice_index = movies.index("Ex Machina") print(ratings[movie_choice_index]) # 7.7

ratings = { "Ex Machina": 7.7, "Mad Max: Fury Road": 8.1, "1408" : 6.8 } print(ratings["Ex Machina"]) # 7.7

ratings["Deadpool"] = 8.0 print(ratings) # {'Ex Machina': 7.7, 'Mad Max: Fury Road': 8.1, '1408': 6.8, 'Deadpool': 8.0} ratings["Ex Machina"] = 7.8 print(ratings) # {'Ex Machina': 7.8, 'Mad Max: Fury Road': 8.1, '1408': 6.8, 'Deadpool': 8.0} del(ratings["1408"]) print(ratings) # {'Ex Machina': 7.8, 'Mad Max: Fury Road': 8.1, 'Deadpool': 8.0}

print("Ex Machina" in ratings) # True

def is_prime(n): if n <= 1: return False elif n <= 3: return True elif n % 2 == 0 or n % 3 == 0: return False current_number = 5 while current_number * current_number <= n: if n % current_number == 0 or n % (current_number + 2) == 0: return False current_number = current_number + 6 return True

# String methods text = "Data Science" text.upper() # "DATA SCIENCE" text.lower() # "data science" text.capitalize() # "Data science" # Lists methods numbers = [1, 4, 0, 2, 9, 9, 10] numbers.reverse() print(numbers) # [10, 9, 9, 2, 0, 4, 1] numbers.sort() print(numbers) # [0, 1, 2, 4, 9, 9, 10] # Dictionaris methods ratings = { "Ex Machina": 7.7, "Mad Max: Fury Road": 8.1, "1408" : 6.8 } print(ratings.keys()) # dict_keys(['Ex Machina', 'Mad Max: Fury Road', '1408']) print(ratings.values()) # dict_values([7.7, 8.1, 6.8]) print(ratings.items()) # dict_items([('Ex Machina', 7.7), ('Mad Max: Fury Road', 8.1), ('1408', 6.8)])

numbers = [10, 30, 55, 40, 8, 30] text = "Data Science" numbers.index(8) # 4 text.index("a") # 1 numbers.count(30) # 2 text.count("i") # 1dd

import numpy numbers = numpy.array([3, 4, 20, 15, 7, 19, 0])

import numpy as np # np is an alias for the numpy package numbers = np.array([3, 4, 20, 15, 7, 19, 0]) # works fine numbers = numpy.array([3, 4, 20, 15, 7, 19, 0]) # NameError: name 'numpy' is not defined

# import the "pyplot" submodule from the "matplotlib" package with alias "plt" import matplotlib.pyplot as plt

from numpy import array numbers = array([3, 4, 20, 15, 7, 19, 0]) # works fine numbers = numpy.array([3, 4, 20, 15, 7, 19, 0]) # NameError: name 'numpy' is not defined type(numbers) # numpy.ndarray

np.array([37, 48, 50]) + 1 # array([38, 49, 51]) np.array([20, 30, 40]) * 2 # array([40, 60, 80]) np.array([42, 10, 60]) / 2 # array([ 21., 5., 30.]) np.array([1, 2, 3]) * np.array([10, 20, 30]) # array([10, 40, 90]) np.array([1, 2, 3]) - np.array([10, 20, 30]) # array([ -9, -18, -27])

numbers = np.array([ [1, 2, 3], [4, 5, 6], [7, 8, 9], [10, 11, 12] ]) numbers[2, 1] # 8 numbers[-1, 0] # 10 numbers[0] # array([1, 2, 3]) numbers[:, 0] # array([ 1, 4, 7, 10]) numbers[0:3, 2] # array([3, 6, 9]) numbers[1:3, 1:3] # array([[5, 6],[8, 9]])

numbers = np.array([ [1, 2, 3], [4, 5, 6], [7, 8, 9], [10, 11, 12], [13, 14, 15] ]) numbers.shape # (5, 3)

learning_hours = [1, 2, 6, 4, 10] grades = [3, 4, 6, 5, 6] np.mean(learning_hours) # 4.6 np.median(learning_hours) # 4.0 np.std(learning_hours) # 3.2 np.corrcoef(learning_hours, grades) # [[ 1. 0.88964891][ 0.88964891 1. ]]