Python-Basics-DataCamp/NumPy.py at main · farzeenshahid/Python-Basics-DataCamp · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
# Import the numpy package as np
import numpy as np

# Create list baseball
baseball = [180, 215, 210, 210, 188, 176, 209, 200]

# Create a numpy array from baseball: np_baseball
np_baseball = np.array(baseball)

# Print out type of np_baseball
print(type(np_baseball))

#Baseball players' height
# Create a numpy array from height_in: np_height_in
np_height_in = np.array(height_in)

# Print out np_height_in
print(np_height_in)

# Convert np_height_in to m: np_height_m
np_height_m = np_height_in * 0.0254

# Print np_height_m
print(np_height_m)

# Store weight and height lists as numpy arrays
np_weight_lb = np.array(weight_lb)
np_height_in = np.array(height_in)

# Print out the weight at index 50
print(np_weight_lb[50])

# Print out sub-array of np_height_in: index 100 up to and including index 110
print(np_height_in[100:111])

#2D Numpy Array
# Create baseball, a list of lists
baseball = [[180, 78.4],
            [215, 102.7],
            [210, 98.5],
            [188, 75.2]]

# Create a 2D numpy array from baseball: np_baseball
np_baseball = np.array(baseball)

# Print out the type of np_baseball
print(type(np_baseball))

# Print out the shape of np_baseball
print(np_baseball.shape)

# Create a 2D numpy array from baseball: np_baseball
np_baseball = np.array(baseball)

# Print out the shape of np_baseball
print(np_baseball.shape)

#Subsetting 2D NumPy Arrays
# Print out the 50th row of np_baseball
print(np_baseball[49,:])

# Select the entire second column of np_baseball: np_weight_lb
np_weight_lb = np_baseball[:,1]

# Print out height of 124th player
print(np_baseball[123,0])

#2D Arithmetic
# Print out addition of np_baseball and updated
print(np_baseball + updated)

# Create numpy array: conversion
conversion = np.array([0.0254,0.453592,1])

# Print out product of np_baseball and conversion
print(np_baseball*conversion)

#Avg Vs Median
# Create np_height_in from np_baseball
np_height_in = np.array(np_baseball[:,0])

# Print out the mean of np_height_in
print(np.mean(np_height_in))

# Print out the median of np_height_in
print(np.median(np_height_in))

#Explore Baseball data
# Print mean height (first column)
avg = np.mean(np_baseball[:,0])
print("Average: " + str(avg))

# Print median height. Replace 'None'
med = np.median(np_baseball[:,0])
print("Median: " + str(med))

# Print out the standard deviation on height. Replace 'None'
stddev = np.std(np_baseball[:,0])
print("Standard Deviation: " + str(stddev))

# Print out correlation between first and second column. Replace 'None'
corr = np.corrcoef(np_baseball[:,0], np_baseball[:,1])
print("Correlation: " + str(corr))


netflix_subset[(netflix_subset["release_year"] >= 1990) & (netflix_subset["release_year"] < 2000)]