tutorial 1 | Python Fiddle

print("Tutorial 4")
print# Insert information to define the following objects 
Last         = ""
First        = ""
Month        = 1
Day          = 1
Year         = 1
CourseName   = ""
CourseNumber = 1
print("")
print("Name:   " + Last + ", " + First)
print("Course: " + CourseName + "-" + str(CourseNumber))
print("Date:   " + str(Month) + "/" + str(Day) + "/" + str(Year))
print("")
print("")
#    THIS PROGRAM SHOULD RUN WITHOUT ERROR--Change the values of variables LAST, FIRST, 
#     COURSE, and DATE. Next make THREE changes to the  code:
#      (1) round "Correlation of Height and Weight" to 2 decimal places
#      (2) round "Median height of relief pitchers" to 2 decimal places
#      (3) round "Mean height of relief pitchers" to 2 decimal places
#      Do not worry about rounding the correlation values in the correlation matrix
# Webscrape the data from U of Michigan's wiki page using the following libraries

from bs4 import BeautifulSoup
import numpy as np
from urllib.request import urlopen
# Get the data (soup) from the HTML table (bowl) and store it in the output file, but first we have to define a row
# of empty values to stack the baseball rows to, which gets delated when the rows of baseball data have been scrapped
baseball = np.array(["","","","","",""])
html= BeautifulSoup(urlopen('http://wiki.socr.umich.edu/index.php/SOCR_Data_MLB_HeightsWeights').read(), "html.parser")
bowls = html.find("table", {"class" : "wikitable"})
print(baseball)
'''
for row in bowls.findAll('tr')[1:]:
    soup = row.findAll('td')
    rowK = np.array([soup[0].text,soup[1].text,soup[2].text,soup[3].text,soup[4].text,soup[5].text])
    baseball = np.vstack((baseball,rowK))
baseball = np.delete(baseball, (0), axis=0)        # This deletes that row of missing observations

# Convert the last three columns of numbers from strings to floats (age) or integers (height and weight)
name     = baseball[:,0]
team     = baseball[:,1]
position = baseball[:,2]
height   = baseball[:,3].astype(int)
weight   = baseball[:,4].astype(int)
age      = baseball[:,5].astype(float)

# Convert height to metric meters
height_m = height*0.0254
print("The metric heights of the players are")
print(height_m)
print("")

# Create a Numpy array from weight, and then convert it to metric KG
weight_m = weight*0.453592
print("The metric weights of the players are")
print(weight_m)
print("")

# Calculate the BMI
bmi = np.round(weight_m/height_m**2,1)
print("The BMI for each players is")
print(weight)
print(height)
print(bmi)
print("")

# Print the name of the 314th player, his team, his position, and his BMI
i = 313
print("The " + str(i+1) + "th player in the list is " + name[i] + ". He plays for " + team[i] + ". He is a "
print(position[i] + "and his BMI is " + str(bmi[i]))
print("")
      
# Create the really light BMI array
light = bmi < 20.5
print("List the values of LIGHT BMI:")
print(light)
print("")

# Print out BMIs of all baseball players whose BMI is below 21
print("List the BMIs of the players who have a BMI less than 21:")
print(bmi[light])
print("")

# Select the entire fourth column of baseball: weight
print("The weights of the players on the list are given below. Why is the first a set of integers, and the")
print("second a set of strings?")
print(weight)
print(baseball[:,4])
print("")

# Print out the mean of height
Havg = np.mean(height)
print("The average height of the players: " + str(round(Havg,1)))
print("")

# Print out the median of height
Hmed = np.median(height)
print("The median height of the players: " + str(Hmed))
print("")

# Print out the standard deviation on height. Replace 'None'
Hstd = np.std(height)
print("Standard Deviation of player height is " + str(Hstd))
print("")

# Print out correlation between player height and weight
HWcorr = np.corrcoef(height,weight)
print("Correlation of Height and Weight is")
print(HWcorr)
print("")
print("Correlation of Height and Weight is " + str(HWcorr[0,1]))
print("")
      
# Heights of relief pitchers
heights_rp = np.array(height[position == 'Relief_Pitcher'])
print("Median height of relief pitchers: " + str(np.median(heights_rp)))
print("Mean height of relief pitchers: " + str(np.mean(heights_rp)))
print("")

# Heights of the other players
heights_op = np.array(height[position != 'Relief_Pitcher'])
print("Median height of other players: " + str(np.median(heights_op)))
print("Mean height of other players: " + str(np.mean(heights_op)))
print("")

# Heights of starting pitchers
heights_sp = np.array(height[position == 'Starting_Pitcher'])
print("Median height of starting pitchers: " + str(np.median(heights_sp)))
print("Mean height of starting pitchers: " + str(np.mean(heights_sp)))
print("")

# Heights of the other players
heights_op = np.array(height[position != 'Relief_Pitcher'])
position_op = np.array(position[position != 'Relief_Pitcher'])
heights_op = np.array(heights_op[position_op != 'Starting_Pitcher'])
print("Median height of other players: " + str(np.median(heights_op)))
print("Mean height of other players: " + str(np.mean(heights_op)))

color = position
for i in range(len(color)): 
    if color[i] == 'Relief_Pitcher':    color[i] = 'red'     
    if color[i] == 'Starting_Pitcher':  color[i] = 'red'
    if color[i] == 'Designated_Hitter': color[i] = 'blue'
    if color[i] == 'First_Baseman':     color[i] = 'green'
    if color[i] == 'Outfielder':        color[i] = 'green'
    if color[i] == 'Catcher':           color[i] = 'green'
    if color[i] == 'Second_Baseman':    color[i] = 'green'
    if color[i] == 'Third_Baseman':     color[i] = 'green'
    if color[i] == 'Shortstop':         color[i] = 'green'
      
import statsmodels.api as sm 
import matplotlib.pyplot as plt

m = age**5/250000
title = "Fig 1--MLB Players (age=size) (F=green,P=red,DH=blue)"
xlab = 'height'
ylab = 'weight'
F1 = sm.OLS(weight,sm.add_constant(height)).fit() # estimate a line of best fit
X_plot = np.linspace(np.min(height),np.max(height)) # create the line for the graph
plt.plot(X_plot, X_plot*F1.params[1] + F1.params[0], c ='black') # plots the line in the graph
plt.scatter(height, weight, s = m, c = color, alpha = .4)
plt.title(title)
plt.xlabel(xlab) 
plt.ylabel(ylab) 
plt.show()

title = "Fig 2--MLB Players (F=green,P=red,DH=blue)"
xlab = 'age'
ylab = 'BMI'
F2 = sm.OLS(bmi,sm.add_constant(age)).fit() # estimate a line of best fit
X_plot = np.linspace(np.min(age),np.max(age)) # create the line for the graph
plt.plot(X_plot, X_plot*F2.params[1] + F2.params[0], c ='black') # plots the line in the graph
plt.scatter(age, bmi, c = color, alpha = .4)
plt.title(title)
plt.xlabel(xlab) 
plt.ylabel(ylab) 
plt.show()      '''

Python Fiddle

Python Cloud IDE