import matplotlib.pyplot as plt
from scipy import stats
import numpy as np


def main():
    """
    [1] H. Schuman, E. Walsh, C. Olson, and B. Etheridge, “Effort and Reward:
        The Assumption that College Grades Are Affected by Quantity of Study*,”
        Social Forces, vol. 63, no. 4, pp. 945–966, June 1985.
    """
    # [1, p. 950]
    hours_studied = np.array([1, 2.5, 3.5, 4.5, 5.5, 6.5])
    gpa = np.array([2.94, 2.91, 2.97, 2.86, 3.25, 3.18])

    slope, intercept, r, p, std_err = stats.linregress(hours_studied, gpa)

    print(f"GPA/hour (slope) of best fit line: {slope}")

    plt.plot(hours_studied, gpa, label="Plot from publication")
    plt.plot(hours_studied, slope * hours_studied + intercept, label="Best fit")
    plt.xlabel("Hours studied")
    plt.ylabel("GPA")
    plt.legend()
    plt.show()


if __name__ == "__main__":
    main()