#!/usr/bin/env python3
#
# Copyright (C) 2022 Jonathan A. Poritz
# 
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
# 
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
#
import sys
import warnings
import csv
import numpy as np
import matplotlib.pyplot as plt
import argparse

def pairgraph(first_dataset,first_medianline,ylim,second_dataset,second_medianline,main_title,first_boxtitle,first_medianstr,first_meanstr,first_stdstr,second_boxtitle,second_medianstr,second_meanstr,second_stdstr):
  bins=[5*i for i in range(20)]
  plt.rc('text', usetex=True)
  fig, axs = plt.subplots(2)
  axs[0].hist(np.array(first_dataset),bins,histtype='bar',color='white',alpha=0.8,edgecolor='black')
  if ylim:
    axs[0].set_ylim((0,ylim))
  axs[0].set_xlim((0,100))
  axs[0].axvline(x=first_medianline)
  axs[1].hist(np.array(second_dataset),bins,histtype='bar',color='white',alpha=0.8,edgecolor='black')
  if ylim:
    axs[1].set_ylim((0,ylim))
  axs[1].set_xlim((0,100))
  axs[1].axvline(x=second_medianline)
  fig.text(0.04, 0.5, 'Number of Participants', va='center', rotation='vertical')
  plt.xlabel('Percent Correct')
  fig.text(.5, .9, main_title, ha='center')
  fig.text(.17, .69, first_boxtitle+'\nmedian='+first_medianstr+'\n$\overline{x}='+first_meanstr+'$\n$\sigma='+first_stdstr+'$\n$n='+str(len(first_dataset))+'$', bbox=dict(fc="none"))
  fig.text(.17, .26, second_boxtitle+'\nmedian='+second_medianstr+'\n$\overline{x}='+second_meanstr+'$\n$\sigma='+second_stdstr+'$\n$n='+str(len(second_dataset))+'$', bbox=dict(fc="none"))
  plt.show()
  return


if not sys.warnoptions:
  warnings.simplefilter("ignore")
parser = argparse.ArgumentParser(description='Make graphs associated with pre- and post-test of material in the Creative Commons Certificate coures.')
parser.add_argument("--input_file", help="CSV file that contains test results as produced by Google Forms, based on the test dating 17 Jan 2022, but including a column FW (i.e., column with Python list index 178) put in by hand that indicates P or F or <anything else> depending upon whether that participant eventually passed, failed, or their final status is unknown.  Default is 'results.csv'.", default="results.csv")
group=parser.add_mutually_exclusive_group()
group.add_argument("--up", help="treat participants whose pass/fail status in the course is unknown as if they passed (conflicts with '--uf')", action="store_true")
group.add_argument("--uf", help="treat participants whose pass/fail status in the course is unknown as if they failed (conflicts with '--up')", action="store_true")
parser.add_argument("--prepostpass", help="show paired graphs of pre- and post-scores, for only passing folks", action="store_true")
parser.add_argument("--prepostall", help="show paired graphs of pre- and post-scores, for all students (P&F)", action="store_true")
parser.add_argument("--pretestpassfail", help="show paired graphs of pass vs fail students on pre-tests", action="store_true")
parser.add_argument("--unit",type=int,choices=[1,2,3,4,5],help="consider only the score for parts of test corresponding to the specified unit of the course; when missing, use the entire test score")
parser.add_argument("--ylim",type=int,help="the upper limit of y-axes of the histograms; when absent, picks automatically",default=0)
parser.add_argument("--ed", help="show graphs for educator section participants", action="store_true")
parser.add_argument("--lib", help="show graphs for librarian section participants", action="store_true")
parser.add_argument("--glam", help="show graphs for GLAM section participants", action="store_true")
parser.add_argument("--allsections", help="show graphs which combine participants from all sections (ed, lib, and GLAM)", action="store_true")
args = parser.parse_args()
fdin=open(args.input_file,"r",newline='')
rdr=csv.reader(fdin)
r=next(rdr)
u1=[13,16,18,20,22,25,28]
u2=[31,34,37,40,43,45,47,49,52,55,58,61,64,67,70]
u3=[73,76,79,82,85,88,91,94,97,100,103,106,109]
u4=[112,115,118,121,124,127,130,133,136,138,140,142,144,147]
u5=[150,152,154,156,158,160,163,166,168,170,173]
unit_colnums=[0,u1,u2,u3,u4,u5]
scores={'ed':{'pre':{'p':[],'f':[],'u':[],'pf':[]},'post':{'p':[],'f':[],'u':[],'pf':[]}},'lib':{'pre':{'p':[],'f':[],'u':[],'pf':[]},'post':{'p':[],'f':[],'u':[],'pf':[]}},'glam':{'pre':{'p':[],'f':[],'u':[],'pf':[]},'post':{'p':[],'f':[],'u':[],'pf':[]}},'all':{'pre':{'p':[],'f':[],'u':[],'pf':[]},'post':{'p':[],'f':[],'u':[],'pf':[]}}}
for r in rdr:
  if args.unit:
    points=0
    for i in unit_colnums[args.unit]:
      if len(r[i])>0:
        points += int(r[i][:r[i].index('.00')])
    score = 100*points/len(unit_colnums[args.unit])
    title_frag="Unit "+str(args.unit)
  else:
    score = int(r[2][:r[2].index('.00')])/.6
    title_frag="Over-all"
  if r[3]=='Will take in the future':
    time='pre'
  elif r[3]=='Already taken':
    time='post'
  else:
    raise ValueError("pre/post error: "+r[3])
  if r[6]=='CC Certificate for Educators':
    version='ed'
  elif r[6]=='CC Certificate for Librarians':
    version='lib'
  elif r[6]=='CC Certificate for GLAM':
    version='glam'
  else:
    raise ValueError("ed/lib/glam error: "+r[6])
  if len(r)<179:
    if args.up:
      success='p'
    elif args.uf:
      success='f'
    else:
      success='u'
  elif r[178]=='P':
    success='p'
  elif r[178]=='F':
    success='f'
  else:
    if args.up:
      success='p'
    elif args.uf:
      success='f'
    else:
      success='u'
  scores[version][time][success].append(score)
  scores[version][time]['pf'].append(score)
  scores['all'][time][success].append(score)
  scores['all'][time]['pf'].append(score)
means={}
medians={}
medianv={}
stdevs={}
for ve in ['ed','lib','glam','all']:
  means[ve]={}
  medianv[ve]={}
  medians[ve]={}
  stdevs[ve]={}
  for ti in ['pre','post']:
    means[ve][ti]={}
    medianv[ve][ti]={}
    medians[ve][ti]={}
    stdevs[ve][ti]={}
    for su in ['p','f','u','pf']:
      data = scores[ve][ti][su]
      if len(data):
        means[ve][ti][su]=str(round(np.mean(data),2))
        medval=np.median(data)
        medianv[ve][ti][su]=medval
        medians[ve][ti][su]=str(round(medval,1))
        stdevs[ve][ti][su]=str(round(np.std(data),2))
      else:
        means[ve][ti][su]='undef'
        medianv[ve][ti][su]=-1
        medians[ve][ti][su]='undef'
        stdevs[ve][ti][su]='undef'
sections_to_graph=[]
if args.ed:
  sections_to_graph.append('ed')
if args.lib:
  sections_to_graph.append('lib')
if args.glam:
  sections_to_graph.append('glam')
if args.allsections:
  sections_to_graph.append('all')
if args.prepostpass:
  if args.ed:
    pairgraph(first_dataset=scores['ed']['pre']['p'],
              ylim=args.ylim,
              first_medianline=medianv['ed']['pre']['p'],
              second_dataset=scores['ed']['post']['p'],
              second_medianline=medianv['ed']['post']['p'],
              main_title='Histograms of '+title_frag+' Score\nBefore and After Cert Course\nEducator Section (only passing students)',
              first_boxtitle='Before Course',
              first_medianstr=medians['ed']['pre']['p'],
              first_meanstr=means['ed']['pre']['p'],
              first_stdstr=stdevs['ed']['pre']['p'],
              second_boxtitle='After Course',
              second_medianstr=medians['ed']['post']['p'],
              second_meanstr=means['ed']['post']['p'],
              second_stdstr=stdevs['ed']['post']['p'])
  if args.lib:
    pairgraph(first_dataset=scores['lib']['pre']['p'],
              ylim=args.ylim,
              first_medianline=medianv['lib']['pre']['p'],
              second_dataset=scores['lib']['post']['p'],
              second_medianline=medianv['lib']['post']['p'],
              main_title='Histograms of '+title_frag+' Score\nBefore and After Cert Course\nLibrarian Section (only passing students)',
              first_boxtitle='Before Course',
              first_medianstr=medians['lib']['pre']['p'],
              first_meanstr=means['lib']['pre']['p'],
              first_stdstr=stdevs['lib']['pre']['p'],
              second_boxtitle='After Course',
              second_medianstr=medians['lib']['post']['p'],
              second_meanstr=means['lib']['post']['p'],
              second_stdstr=stdevs['lib']['post']['p'])
  if args.glam:
    pairgraph(first_dataset=scores['glam']['pre']['p'],
              ylim=args.ylim,
              first_medianline=medianv['glam']['pre']['p'],
              second_dataset=scores['glam']['post']['p'],
              second_medianline=medianv['glam']['post']['p'],
              main_title='Histograms of '+title_frag+' Score\nBefore and After Cert Course\nGLAM Section (only passing students)',
              first_boxtitle='Before Course',
              first_medianstr=medians['glam']['pre']['p'],
              first_meanstr=means['glam']['pre']['p'],
              first_stdstr=stdevs['glam']['pre']['p'],
              second_boxtitle='After Course',
              second_medianstr=medians['glam']['post']['p'],
              second_meanstr=means['glam']['post']['p'],
              second_stdstr=stdevs['glam']['post']['p'])
  if args.allsections:
    pairgraph(first_dataset=scores['all']['pre']['p'],
              ylim=args.ylim,
              first_medianline=medianv['all']['pre']['p'],
              second_dataset=scores['all']['post']['p'],
              second_medianline=medianv['all']['post']['p'],
              main_title='Histograms of '+title_frag+' Score\nBefore and After Cert Course\nEducator, Librarian, and GLAM Sections (only passing students)',
              first_boxtitle='Before Course',
              first_medianstr=medians['all']['pre']['p'],
              first_meanstr=means['all']['pre']['p'],
              first_stdstr=stdevs['all']['pre']['p'],
              second_boxtitle='After Course',
              second_medianstr=medians['all']['post']['p'],
              second_meanstr=means['all']['post']['p'],
              second_stdstr=stdevs['all']['post']['p'])
if args.prepostall:
  if args.ed:
    pairgraph(first_dataset=scores['ed']['pre']['pf'],
              ylim=args.ylim,
              first_medianline=medianv['ed']['pre']['pf'],
              second_dataset=scores['ed']['post']['pf'],
              second_medianline=medianv['ed']['post']['pf'],
              main_title='Histograms of '+title_frag+' Score\nBefore and After Cert Course\nEducator Section',
              first_boxtitle='Before Course',
              first_medianstr=medians['ed']['pre']['pf'],
              first_meanstr=means['ed']['pre']['pf'],
              first_stdstr=stdevs['ed']['pre']['pf'],
              second_boxtitle='After Course',
              second_medianstr=medians['ed']['post']['pf'],
              second_meanstr=means['ed']['post']['pf'],
              second_stdstr=stdevs['ed']['post']['pf'])
  if args.lib:
    pairgraph(first_dataset=scores['lib']['pre']['pf'],
              ylim=args.ylim,
              first_medianline=medianv['lib']['pre']['pf'],
              second_dataset=scores['lib']['post']['pf'],
              second_medianline=medianv['lib']['post']['pf'],
              main_title='Histograms of '+title_frag+' Score\nBefore and After Cert Course\nLibrarian Section',
              first_boxtitle='Before Course',
              first_medianstr=medians['lib']['pre']['pf'],
              first_meanstr=means['lib']['pre']['pf'],
              first_stdstr=stdevs['lib']['pre']['pf'],
              second_boxtitle='After Course',
              second_medianstr=medians['lib']['post']['pf'],
              second_meanstr=means['lib']['post']['pf'],
              second_stdstr=stdevs['lib']['post']['pf'])
  if args.glam:
    pairgraph(first_dataset=scores['glam']['pre']['pf'],
              ylim=args.ylim,
              first_medianline=medianv['glam']['pre']['pf'],
              second_dataset=scores['glam']['post']['pf'],
              second_medianline=medianv['glam']['post']['pf'],
              main_title='Histograms of '+title_frag+' Score\nBefore and After Cert Course\nGLAM Section',
              first_boxtitle='Before Course',
              first_medianstr=medians['glam']['pre']['pf'],
              first_meanstr=means['glam']['pre']['pf'],
              first_stdstr=stdevs['glam']['pre']['pf'],
              second_boxtitle='After Course',
              second_medianstr=medians['glam']['post']['pf'],
              second_meanstr=means['glam']['post']['pf'],
              second_stdstr=stdevs['glam']['post']['pf'])
  if args.allsections:
    pairgraph(first_dataset=scores['all']['pre']['pf'],
              ylim=args.ylim,
              first_medianline=medianv['all']['pre']['pf'],
              second_dataset=scores['all']['post']['pf'],
              second_medianline=medianv['all']['post']['pf'],
              main_title='Histograms of '+title_frag+' Score\nBefore and After Cert Course\nEducator, Librarian, and GLAM Sections',
              first_boxtitle='Before Course',
              first_medianstr=medians['all']['pre']['pf'],
              first_meanstr=means['all']['pre']['pf'],
              first_stdstr=stdevs['all']['pre']['pf'],
              second_boxtitle='After Course',
              second_medianstr=medians['all']['post']['pf'],
              second_meanstr=means['all']['post']['pf'],
              second_stdstr=stdevs['all']['post']['pf'])
if args.pretestpassfail:
  if args.ed:
    pairgraph(first_dataset=scores['ed']['pre']['f'],
              ylim=args.ylim,
              first_medianline=medianv['ed']['pre']['f'],
              second_dataset=scores['ed']['pre']['p'],
              second_medianline=medianv['ed']['pre']['p'],
              main_title='Histograms of '+title_frag+' Pre-Test Score\nAmong Students Who Eventually Fail or Pass Course\nEducator Section',
              first_boxtitle='Eventual Fail',
              first_medianstr=medians['ed']['pre']['f'],
              first_meanstr=means['ed']['pre']['f'],
              first_stdstr=stdevs['ed']['pre']['f'],
              second_boxtitle='Eventual Pass',
              second_medianstr=medians['ed']['pre']['p'],
              second_meanstr=means['ed']['pre']['p'],
              second_stdstr=stdevs['ed']['pre']['p'])
  if args.lib:
    pairgraph(first_dataset=scores['lib']['pre']['f'],
              ylim=args.ylim,
              first_medianline=medianv['lib']['pre']['f'],
              second_dataset=scores['lib']['pre']['p'],
              second_medianline=medianv['lib']['pre']['p'],
              main_title='Histograms of '+title_frag+' Pre-Test Score\nAmong Students Who Eventually Fail or Pass Course\nLibrarian Section',
              first_boxtitle='Eventual Fail',
              first_medianstr=medians['lib']['pre']['f'],
              first_meanstr=means['lib']['pre']['f'],
              first_stdstr=stdevs['lib']['pre']['f'],
              second_boxtitle='Eventual Pass',
              second_medianstr=medians['lib']['pre']['p'],
              second_meanstr=means['lib']['pre']['p'],
              second_stdstr=stdevs['lib']['pre']['p'])
  if args.glam:
    pairgraph(first_dataset=scores['glam']['pre']['f'],
              ylim=args.ylim,
              first_medianline=medianv['glam']['pre']['f'],
              second_dataset=scores['glam']['pre']['p'],
              second_medianline=medianv['glam']['pre']['p'],
              main_title='Histograms of '+title_frag+' Pre-Test Score\nAmong Students Who Eventually Fail or Pass Course\nGLAM Section',
              first_boxtitle='Eventual Fail',
              first_medianstr=medians['glam']['pre']['f'],
              first_meanstr=means['glam']['pre']['f'],
              first_stdstr=stdevs['glam']['pre']['f'],
              second_boxtitle='Eventual Pass',
              second_medianstr=medians['glam']['pre']['p'],
              second_meanstr=means['glam']['pre']['p'],
              second_stdstr=stdevs['glam']['pre']['p'])
  if args.allsections:
    pairgraph(first_dataset=scores['all']['pre']['f'],
              ylim=args.ylim,
              first_medianline=medianv['all']['pre']['f'],
              second_dataset=scores['all']['pre']['p'],
              second_medianline=medianv['all']['pre']['p'],
              main_title='Histograms of '+title_frag+' Pre-Test Score\nAmong Students Who Eventually Fail or Pass Course\nEducator, Librarian, and GLAM Sections',
              first_boxtitle='Eventual Fail',
              first_medianstr=medians['all']['pre']['f'],
              first_meanstr=means['all']['pre']['f'],
              first_stdstr=stdevs['all']['pre']['f'],
              second_boxtitle='Eventual Pass',
              second_medianstr=medians['all']['pre']['p'],
              second_meanstr=means['all']['pre']['p'],
              second_stdstr=stdevs['all']['pre']['p'])