Psych GPA vs work hours faux study

study.py

import random

import matplotlib.pyplot as plt
import numpy as np

respondents = 23

random.seed()

gpa = []
hours_worked = []

for point in range(respondents / 3):
    gpa_point = random.triangular(1.0, 4.5, 3.5)
    worked_point = gpa_point * 10 * random.uniform(0.5, 1.5)

    gpa_point = round(gpa_point / .1) * .1
    worked_point = round(worked_point / 5) * 5

    hours_worked.append(worked_point)
    gpa.append(gpa_point)

    gpa.append(round(random.triangular(0.0, 4.5, 2.0) / .1) * .1)
    hours_worked.append(round(random.triangular(1, 50) / 5) * 5)

    gpa.append(round(random.triangular(0.0, 4.8, 4.8) / .1) * .1)
    hours_worked.append(round(random.triangular(1, 50) / 5) * 5)

gpa = np.clip(np.array(gpa), 0.0, 4.0)
hours_worked = np.array(hours_worked)

with open('C:\Users\mike_000\Desktop\psych_data.txt', 'w') as outfile:
    for index in range(len(gpa)):
        outfile.write(hours_worked[index].astype(str) + '-' + gpa[index].astype(str) + '\n')



# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

# Lists of gpa/work hour data
gpa = []
hours_worked = []

# Read data from text file
with open('C:\Users\mike_000\Desktop\psych_data.txt') as infile:
    lines = infile.readlines()
    print(lines)
    for line in lines:
        # Split each entry into work hours and gpa via dash delimiter
        work_hours_point, gpa_point = line.split('-')
        hours_worked.append(work_hours_point)
        gpa.append(gpa_point)

# Convert to numpy arrays
hours_worked = np.array(hours_worked).astype(np.float16)
gpa = np.array(gpa).astype(np.float16)

print(np.corrcoef(gpa, hours_worked))

# Labels
plt.title('GPA vs Work Hours')
plt.ylabel("Grade Point Average")
plt.xlabel("Hours Worked")

# Scale axis
plt.axis((0, np.amax(hours_worked), 1.0, 4.0))

# Render plot with data lists on x and y axes
plt.scatter(hours_worked, gpa)
plt.show()