01 01 Introduction to Python Numpy - HannaAA17/Data-Scientist-With-Python-datacamp GitHub Wiki

This is the note for Numpy section of the course #introduction to python#.

  • Numpy stands for: Numeric Python
  • Alternative to Python List: Numpy Array
  • Calculations over entire arrays.
  • Numpy arrays: contain only one type.
# Create list baseball
baseball = [180, 215, 210, 210, 188, 176, 209, 200]

# Import the numpy package as np
import numpy as np

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

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

01 use Numpy to do calculation with an array

# height is available as a regular list

# Import numpy
import numpy as np

# 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)

02 create boolean Numpy Array to find certain elements

# height and weight are available as a regular lists

# Import numpy
import numpy as np

# Calculate the BMI: bmi
np_height_m = np.array(height_in) * 0.0254
np_weight_kg = np.array(weight_lb) * 0.453592
bmi = np_weight_kg / np_height_m ** 2

# Create the light array
light = bmi < 21

# Print out light
print(light)

# Print out BMIs of all baseball players whose BMI is below 21
print(bmi[light])

03 Subsetting Numpy Arrays

Subsetting (using the square bracket notation on lists or arrays) works exactly the same. np_weight[50]

04 2D NumPy Array

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

# Import numpy
import numpy as np

# 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)

Output

<script.py> output:
    <class 'numpy.ndarray'>
    (4, 2)

subsetting 2D Numpy Array

# baseball is available as a regular list of lists

# Import numpy package
import numpy as np

# Create np_baseball (2 cols)
np_baseball = np.array(baseball)

# 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])

Arithmetic

# baseball is available as a regular list of lists
# updated is available as 2D numpy array

# Import numpy package
import numpy as np

# Create np_baseball (3 cols)
np_baseball = np.array(baseball)

# 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)

04 Basic Statistics

# np_baseball is available

# Import numpy
import numpy as np

# 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))

Exercise: prove ' the median height of goalkeepers is higher than other player on the soccer field '

# heights and positions are available as lists

# Import numpy
import numpy as np

# Convert positions and heights to numpy arrays: np_positions, np_heights
np_positions = np.array(positions)
np_heights = np.array(heights)


# Heights of the goalkeepers: gk_heights
gk_heights = np_heights[np_positions == 'GK']

# Heights of the other players: other_heights
other_heights = np_heights[np_positions != 'GK']

# Print out the median height of goalkeepers. Replace 'None'
print("Median height of goalkeepers: " + str(np.median(gk_heights)))

# Print out the median height of other players. Replace 'None'
print("Median height of other players: " + str(np.median(other_heights)))
⚠️ **GitHub.com Fallback** ⚠️