Skip to content

Introduction to Python

Run the hidden code cell below to import the data used in this course.

# Importing course packages; you can add more too!
import numpy as np
import math

# Import columns as numpy arrays
baseball_names = np.genfromtxt(
    fname="baseball.csv",  # This is the filename
    delimiter=",",  # The file is comma-separated
    usecols=0,  # Use the first column
    skip_header=1,  # Skip the first line
    dtype=str,  # This column contains strings
)
baseball_heights = np.genfromtxt(
    fname="baseball.csv", delimiter=",", usecols=3, skip_header=1
)
baseball_weights = np.genfromtxt(
    fname="baseball.csv", delimiter=",", usecols=4, skip_header=1
)
baseball_ages = np.genfromtxt(
    fname="baseball.csv", delimiter=",", usecols=5, skip_header=1
)

soccer_names = np.genfromtxt(
    fname="soccer.csv",
    delimiter=",",
    usecols=1,
    skip_header=1,
    dtype=str,
    encoding="utf", 
)
soccer_ratings = np.genfromtxt(
    fname="soccer.csv",
    delimiter=",",
    usecols=2,
    skip_header=1,
    encoding="utf", 
)
soccer_positions = np.genfromtxt(
    fname="soccer.csv",
    delimiter=",",
    usecols=3,
    skip_header=1,
    encoding="utf", 
    dtype=str,
)
soccer_heights = np.genfromtxt(
    fname="soccer.csv",
    delimiter=",",
    usecols=4,
    skip_header=1,
    encoding="utf", 
)
soccer_shooting = np.genfromtxt(
    fname="soccer.csv",
    delimiter=",",
    usecols=8,
    skip_header=1,
    encoding="utf", 
)

Take Notes

Add notes about the concepts you've learned and code cells with code you want to keep.

Add your notes here

# Add your code snippets here

# area variables (in square meters)
hall = 11.25
kit = 18.0
liv = 20.0
bed = 10.75
bath = 9.50

# Adapt list areas
areas = ["hallway", hall, "kitchen", kit, "living room", liv, "bedroom", bed, "bathroom", bath]

# Print areas
print(areas)

Explore Datasets

Use the arrays imported in the first cell to explore the data and practice your skills!

  • Print out the weight of the first ten baseball players.
  • What is the median weight of all baseball players in the data?
  • Print out the names of all players with a height greater than 80 (heights are in inches).
  • Who is taller on average? Baseball players or soccer players? Keep in mind that baseball heights are stored in inches!
  • The values in soccer_shooting are decimals. Convert them to whole numbers (e.g., 0.98 becomes 98).
  • Do taller players get higher ratings? Calculate the correlation between soccer_ratings and soccer_heights to find out!
  • What is the average rating for attacking players ('A')?
# Create list areas
areas = [11.25, 18.0, 20.0, 10.75, 9.50]

# Create areas_copy
## areas_copy = areas
### areas_copy = list(areas)

areas_copy = areas[:]

# Change areas_copy
areas_copy[0] = 5.0

# Print areas
print(areas)

on inner workings of list. you can use list() or [:]

# string to experiment with: place
place = "poolhouse"

# Use upper() on place: place_up
place_up = place.upper() #capitalize all letters, changing to all caps

# Print out place and place_up
print(place)
print(place_up)

# Print out the number of o's in place
print(place.count('o'))

methods

# Create list areas
areas = [11.25, 18.0, 20.0, 10.75, 9.50]

# Use append twice to add poolhouse and garage size
areas.append("poolhouse")
areas.append("garage size")


# Print out areas
print(areas)

# Reverse the orders of the elements in areas
areas.reverse() #note: always add ()

# Print out areas
print(areas)
# Definition of radius
r = 0.43

# Import the math package
import math 

# Calculate C
C = 2 * math.pi * r

# Calculate A
A = math.pi * (r ** 2)

# Build printout
print("Circumference: " + str(C))
print("Area: " + str(A))

from scipy.linalg import inv as my_inv <-- creating a local name for a function from a package

# height_in and weight_lb 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])
# 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)
‌
‌
‌