'''
    DS2500
    Spring 2025
    Sample code from lecture - normalizing adm rate and tuition

    Goals:
    - draw lineplot of time vs tuition & time vs admission rate
    - normalize both datasets
    - draw lineplots again, and compute euclidean distance
    - compute std dev of each dataset
'''


import statistics
from scipy import stats
import matplotlib.pyplot as plt
import seaborn as sns
from utils import *

ADM_FILE = "data/admission_rate.csv"
TUITION_FILE = "data/tuition.csv"
DATA_COL = 1
YEAR_COL = 0

def plot_comparison(x_vals, y_vals, title, xlabel):
    ''' given a list of x values and a 2d list of y vals,
        plot all the y-val lists against the x-val list
    '''
    for label, yval in y_vals.items():
        sns.lineplot(x = x_vals, y = yval, label = label)
    plt.xlabel(xlabel)
    plt.title(title)
    plt.legend()
    plt.show()

def main():
    # gather data - read in admissions and tuition data, pull out important columns
    adm_data = read_csv(ADM_FILE)
    tuition_data = read_csv(TUITION_FILE)
    adm_lst = col_to_lst(adm_data, DATA_COL)
    tuition_lst = col_to_lst(tuition_data, DATA_COL)
    year_lst = col_to_lst(tuition_data, YEAR_COL)

    # convert our lists of strings into floats
    adm_lst = [float(adm) for adm in adm_lst]
    tuition_lst = [clean_currency(tuition) for tuition in tuition_lst]
    year_lst = [int(year) for year in year_lst]

    # Plot year vs tuition, year vs admin rate
    # omg it looks terrible and misleading! Like adm rates have stayed flat this whole time...
    plot_comparison(year_lst, {"Admission" : adm_lst, "Tuition" : tuition_lst},
                    "Admission Rate, Tuition at Northeastern 2013-2021", xlabel = "Year")

    # normalize our tuition and adm rate data, and plot again
    norm_tuition = normalize(tuition_lst)
    norm_adm = normalize(adm_lst)
    plot_comparison(year_lst, {"Admission" : norm_adm, "Tuition" : norm_tuition},
                    "Admission Rate, Tuition at Northeastern 2013-2021", xlabel = "Year")

    # std dev of tuition?
    var = statistics.variance(tuition_lst)
    print(f"The std deviation of tuition 2013-2021 is {round(var ** .5, 3)}")

if __name__ == "__main__":
    main()