90.0% ≤ sim ≤ 100%

HW5

convert_to_dict,get_medals_by_team,get_top_five,get_medals_trend,get_sports,get_common_sports: 3 clusters, 6 submissions

>> cluster #1(2)
# 6532150421 (point = 100.0%) sim = 99%
def convert_to_dict(data):
    athletes_by_Year_NOC = {}
    a = data[0]
    for e in data[1::1]:
        year = e[9]
        NOC = e[7]
        if year not in athletes_by_Year_NOC:
            athletes_by_Year_NOC[year] = {}
        if NOC not in athletes_by_Year_NOC[year]:
            athletes_by_Year_NOC[year][NOC] = [{a[i]:e[i] for i in range(len(a))}]
        else:
            athletes_by_Year_NOC[year][NOC].append({a[i]:e[i] for i in range(len(a))})
    return athletes_by_Year_NOC
#======================================
def get_medals_by_team(athletes_by_Year_NOC, year):
    medals = {}
    for k,v in athletes_by_Year_NOC[year].items():
        if k not in medals:
            medals[k] = [0, 0, 0]
        for e in v:
            if e["Medal"] == "Gold":
                medals[k][0] += 1
            elif e["Medal"] == "Silver":
                medals[k][1] += 1
            elif e["Medal"] == "Bronze":
                medals[k][2] += 1
    for k,v in medals.items():
        medals[k] = tuple(v)
    return medals
#======================================
def get_top_five(medals):
    topfive = []
    sm = [ ((-medals[e][0], -medals[e][1], -medals[e][2]), e) for e in medals.keys()]
    sm.sort()
    ans = sm[:5]
    for i in range(5,len(sm)):
        if (ans[-1][0] == sm[i][0]):
            ans.append(sm[i])
        else:
            break
    topfive = [(e[1], -e[0][0], -e[0][1], -e[0][2]) for e in ans]
    return topfive
#======================================
def get_medals_trend(athletes_by_Year_NOC, NOC, start, end):
    trend = []
    for y in range(start,end+1):
        y = str(y)
        if y in athletes_by_Year_NOC:
            medals = get_medals_by_team(athletes_by_Year_NOC, y)
            if NOC in medals:
                t = medals[NOC]
                trend.append((y, t[0], t[1], t[2]))
    return trend
#======================================
def get_sports(athletes_by_Year_NOC, NOC, year):
    sports = set()
    if year in athletes_by_Year_NOC and NOC in athletes_by_Year_NOC[year]:
        data = athletes_by_Year_NOC[year][NOC]
        for e in data:
            if not e["Medal"] == "NA":
                sports.add(e["Sport"])
    return sports
#======================================
def get_common_sports(athletes_by_Year_NOC, NOCs, year):
    sports = set()
    first = True
    for noc in NOCs:
        if first:
            sports = get_sports(athletes_by_Year_NOC, noc, year)
            first = False
        else:
            sports &= get_sports(athletes_by_Year_NOC, noc, year)
    return sports
#======================================
# สามารถเขียนฟังก์ชันที่สร้างเองได้ในบริเวณด้านล่างของ cell นี้ เท่านั้น
# 6530290221 (point = 100.0%) sim = 99%
def convert_to_dict(data):
  athletes_by_Year_NOC = {}
  ListHead = data[0]
  for d in data[1:]:
    year = d[9]
    NOC = d[7]
    if year not in athletes_by_Year_NOC:
      athletes_by_Year_NOC[year] = {}
    if NOC not in athletes_by_Year_NOC[year]:
      athletes_by_Year_NOC[year][NOC] = [{ListHead[i]:d[i] for i in range(len(ListHead))}]
    else: athletes_by_Year_NOC[year][NOC].append({ListHead[i]:d[i] for i in range(len(ListHead))})
  return athletes_by_Year_NOC
#======================================
def get_medals_by_team(athletes_by_Year_NOC, year):
  medals = {}
  for key,value in athletes_by_Year_NOC[year].items():
    if key not in medals: medals[key] = [0, 0, 0]
    for elem in value:
      if elem["Medal"] == "Gold":
        medals[key][0] += 1
      elif elem["Medal"] == "Silver":
        medals[key][1] += 1
      elif elem["Medal"] == "Bronze":
        medals[key][2] += 1
  for key, value in medals.items():
    medals[key] = tuple(value)
  return medals
#======================================
def get_top_five(medals):
  topfive = []
  sortedMedals = [ ((-medals[e][0], -medals[e][1], -medals[e][2]), e) for e in medals.keys()]
  sortedMedals.sort()
  ans = sortedMedals[:5]
  for i in range(5, len(sortedMedals)):
    if (ans[-1][0] == sortedMedals[i][0]):
      ans.append(sortedMedals[i])
    else: break
  topfive = [(e[1], -e[0][0], -e[0][1], -e[0][2]) for e in ans]
  return topfive
#======================================
def get_medals_trend(athletes_by_Year_NOC, NOC, start, end):
  trend = []
  for year in range(start, end+1):
    year = str(year)
    if year in athletes_by_Year_NOC:
      medals = get_medals_by_team(athletes_by_Year_NOC, year)
      if NOC in medals:
        medalsOfTeam = medals[NOC]
        trend.append((year, medalsOfTeam[0], medalsOfTeam[1], medalsOfTeam[2]))
  return trend
#======================================
def get_sports(athletes_by_Year_NOC, NOC, year):
  sports = set()
  if year in athletes_by_Year_NOC and NOC in athletes_by_Year_NOC[year]:
    data = athletes_by_Year_NOC[year][NOC]
    for d in data:
      if d["Medal"] != "NA":
        sports.add(d["Sport"])
  return sports
#======================================
def get_common_sports(athletes_by_Year_NOC, NOCs, year):
  sports = set()
  isFirst = True
  for noc in NOCs:
    if isFirst:
      sports = get_sports(athletes_by_Year_NOC, noc, year)
      isFirst = False
    else:
      sports &= get_sports(athletes_by_Year_NOC, noc, year)
  return sports
#======================================
# สามารถเขียนฟังก์ชันที่สร้างเองได้ในบริเวณด้านล่างของ cell นี้ เท่านั้น 
# Part 1
# d = convert_to_dict(data)
# print(len(d['2000']['THA']))
# for i in range(5):
#   print(d['2000']['THA'][i])
# Part 2
# d = convert_to_dict(data)
# m = get_medals_by_team(d, '2000')
# print(len(m))
# print(m)
# # Part 3
# d = convert_to_dict(data)
# m = get_medals_by_team(d, '2000')
# print(get_top_five(m))
# d_mock = convert_to_dict(data_mock)
# m_mock = get_medals_by_team(d_mock, '2010')
# print(get_top_five(m_mock))
# # Part 4
# d = convert_to_dict(data)
# print('USA')
# print(get_medals_trend(d, 'USA', 2001, 2015))
# print('THA')
# print(get_medals_trend(d, 'THA', 2000, 2016))
# # Part 5
# d = convert_to_dict(data)
# print(get_sports(d, 'THA', '2000'))
# print(get_sports(d, 'THA', '2010'))
# print(get_sports(d, 'THA', '2020'))
# print(get_sports(d, 'SOM', '2000'))
# print(get_sports(d, 'THA', '2008'))
# print(get_sports(d, 'VIE', '2008'))
# print(get_sports(d, 'DEN', '2008'))
# print(get_sports(d, 'XXX', '2000'))
# # Part 6
# d = convert_to_dict(data)
# print(get_common_sports(d, {'THA','VIE'}, '2008'))
# print(get_common_sports(d, {'THA','VIE','DEN'}, '2008'))
# print(get_common_sports(d, {'THA','XXX'}, '2008'))

>> cluster #2(2)
# 6530418321 (point = 87.5%) sim = 96%
def convert_to_dict(data):
  athletes_by_Year_NOC = {}
  data_collect = data[0]
  for i in range(1, len(data)) :
    f = {}
    for j in range(len(data_collect)) :
      f[data_collect[j]] = data[i][j]
    if data[i][9] not in athletes_by_Year_NOC :
      athletes_by_Year_NOC[data[i][9]] = {data[i][7] : []}
    else :
      if data[i][7] not in athletes_by_Year_NOC[data[i][9]] :
        athletes_by_Year_NOC[data[i][9]][data[i][7]] = []
    athletes_by_Year_NOC[data[i][9]][data[i][7]].append(f)
  return athletes_by_Year_NOC
#======================================
def get_medals_by_team(athletes_by_Year_NOC, year):
  medals = {}
  for data in athletes_by_Year_NOC[year] :
    if data not in medals :
      medals[data] = [0,0,0]
    for i in range(len(athletes_by_Year_NOC[year][data])) :
      if athletes_by_Year_NOC[year][data][i]["Medal"] == "Bronze" :
        medals[data][2] += 1
      elif athletes_by_Year_NOC[year][data][i]["Medal"] == "Silver" :
        medals[data][1] += 1
      elif athletes_by_Year_NOC[year][data][i]["Medal"] == "Gold" :
        medals[data][0] += 1
    medals[data] = tuple(medals[data])
  return medals
#======================================
def get_top_five(medals):
  topfive = []
  new_d = []
  f = set()
  for k,v in medals.items() :
    if v not in f :
      new_d.append([v, [k]])
      f.add(v)
    else :
      for i in range(len(new_d)) :
        if new_d[i][0] == v :
          new_d[i][1].append(k)
  new_d.sort(reverse = True)
  n = 5
  for i in range(len(new_d)) :
    new_d[i][1].sort()
    for e in new_d[i][1] :
      topfive.append((e, new_d[i][0][0], new_d[i][0][1], new_d[i][0][2]))
      n -= 1
    if n <= 0: break
  return topfive
#======================================
def get_medals_trend(athletes_by_Year_NOC, NOC, start, end):
  trend = []
  for i in range(start, end + 1) :
    if str(i) in athletes_by_Year_NOC :
      for e in get_medals_by_team(d, str(i)) :
        if e == NOC :
          g,s,b = get_medals_by_team(d, str(i))[e]
          trend.append((str(i), g, s, b))
  return trend
#======================================
def get_sports(athletes_by_Year_NOC, NOC, year):
  sports = set()
  if year in athletes_by_Year_NOC :
    if NOC in athletes_by_Year_NOC[year] :
      for e in athletes_by_Year_NOC[year][NOC] :
        if e["Medal"] != "NA" :
          sports.add(e["Sport"])
  return sports
#======================================
def get_common_sports(athletes_by_Year_NOC, NOCs, year):
  sports = set()
  i = True
  for NOC in NOCs :
    if i :
      sports = get_sports(athletes_by_Year_NOC, NOC, year)
      i = False
    sports &= get_sports(athletes_by_Year_NOC, NOC, year)
  return sports
#======================================
# สามารถเขียนฟังก์ชันที่สร้างเองได้ในบริเวณด้านล่างของ cell นี้ เท่านั้น
# 6530266221 (point = 100.0%) sim = 96%
def convert_to_dict(data):
  athletes_by_Year_NOC = {}
  data_collect = data[0]
  for i in range(1, len(data)) :
    f = {}
    for j in range(len(data_collect)) :
      f[data_collect[j]] = data[i][j]
    if data[i][9] not in athletes_by_Year_NOC :
      athletes_by_Year_NOC[data[i][9]] = {data[i][7] : []}
    else :
      if data[i][7] not in athletes_by_Year_NOC[data[i][9]] :
        athletes_by_Year_NOC[data[i][9]][data[i][7]] = []
    athletes_by_Year_NOC[data[i][9]][data[i][7]].append(f)
  return athletes_by_Year_NOC
#======================================
def get_medals_by_team(athletes_by_Year_NOC, year):
  medals = {}
  for data in athletes_by_Year_NOC[year] :
    if data not in medals :
      medals[data] = [0,0,0]
    for i in range(len(athletes_by_Year_NOC[year][data])) :
      if athletes_by_Year_NOC[year][data][i]["Medal"] == "Bronze" :
        medals[data][2] += 1
      elif athletes_by_Year_NOC[year][data][i]["Medal"] == "Silver" :
        medals[data][1] += 1
      elif athletes_by_Year_NOC[year][data][i]["Medal"] == "Gold" :
        medals[data][0] += 1
    medals[data] = tuple(medals[data])
  return medals
#======================================
def get_top_five(medals):
  topfive = []
  new_d = []
  f = set()
  for k,v in medals.items() :
    if v not in f :
      new_d.append([v, [k]])
      f.add(v)
    else :
      for i in range(len(new_d)) :
        if new_d[i][0] == v :
          new_d[i][1].append(k)
  new_d.sort(reverse = True)
  n = 5
  for i in range(len(new_d)) :
    new_d[i][1].sort()
    for e in new_d[i][1] :
      topfive.append((e, new_d[i][0][0], new_d[i][0][1], new_d[i][0][2]))
      n -= 1
    if n <= 0: break
  return topfive
#======================================
def get_medals_trend(athletes_by_Year_NOC, NOC, start, end):
  trend = []
  for i in range(start, end + 1) :
    if str(i) in athletes_by_Year_NOC :
      for e in get_medals_by_team(athletes_by_Year_NOC, str(i)) :
        if e == NOC :
          g,s,b = get_medals_by_team(athletes_by_Year_NOC, str(i))[e]
          trend.append((str(i), g, s, b))
  return trend
#======================================
def get_sports(athletes_by_Year_NOC, NOC, year):
  sports = set()
  if year in athletes_by_Year_NOC :
    if NOC in athletes_by_Year_NOC[year] :
      for e in athletes_by_Year_NOC[year][NOC] :
        if e["Medal"] != "NA" :
          sports.add(e["Sport"])
  return sports
#======================================
def get_common_sports(athletes_by_Year_NOC, NOCs, year):
  sports = set()
  i = True
  for NOC in NOCs :
    if i :
      sports = get_sports(athletes_by_Year_NOC, NOC, year)
      i = False
    sports &= get_sports(athletes_by_Year_NOC, NOC, year)
  return sports
#======================================
# สามารถเขียนฟังก์ชันที่สร้างเองได้ในบริเวณด้านล่างของ cell นี้ เท่านั้น

>> cluster #3(2)
# 6530403921 (point = 100.0%) sim = 90%
def convert_to_dict(data):
  athletes_by_Year_NOC = {}
  for i in data[1:]:
    if i[9] in athletes_by_Year_NOC:
      if i[7] in athletes_by_Year_NOC[i[9]]:
        athletes_by_Year_NOC[i[9]][i[7]].append(dict(zip(data[0], i)))
      else:
        athletes_by_Year_NOC[i[9]][i[7]] = [dict(zip(data[0], i))]
    else:
      athletes_by_Year_NOC[i[9]] = {i[7]:[dict(zip(data[0], i))]}
  return athletes_by_Year_NOC
#======================================
def get_medals_by_team(athletes_by_Year_NOC, year):
  medals = {}
  for i in athletes_by_Year_NOC[year]: 
    medals[i] = {'Gold': 0, 'Silver': 0, 'Bronze': 0}
    for j in athletes_by_Year_NOC[year][i]: 
      if j['Medal'] == 'Gold':
        medals[i]['Gold'] += 1
      elif j['Medal'] == 'Silver':
        medals[i]['Silver'] += 1
      elif j['Medal'] == 'Bronze':
        medals[i]['Bronze'] += 1
    medals[i] = (medals[i]['Gold'], medals[i]['Silver'], medals[i]['Bronze'])
  return medals
#======================================
def get_top_five(medals):
  topfive = []
  sortedmedals = []
  for i in medals:
    sortedmedals.append([-medals[i][0],-medals[i][1],-medals[i][2],i])
  sortedmedals.sort()
  prev = [sortedmedals[0][0], sortedmedals[0][1], sortedmedals[0][2]]
  topfive.append((sortedmedals[0][3],-sortedmedals[0][0], -sortedmedals[0][1], -sortedmedals[0][2]))
  count = 1
  for i in sortedmedals[1:]:
    if count == 4:
      prev = [i[0],i[1],i[2]]
    if count >=5 and not (i[0] == prev[0] and i[1] == prev[1] and i[2] == prev[2]):
      break
    topfive.append((i[3],-i[0],-i[1],-i[2]))
    count += 1
  return topfive
#======================================
def get_medals_trend(athletes_by_Year_NOC, NOC, start, end):
  trend = []
  for i in athletes_by_Year_NOC:
    if start<= int(i) <=end: 
      x=get_medals_by_team(athletes_by_Year_NOC, i)
      if NOC in x:
        trend.append((i, x[NOC][0],x[NOC][1],x[NOC][2]))
  trend.sort()
  return trend
#======================================
def get_sports(athletes_by_Year_NOC, NOC, year):
  sports = set()
  if year in athletes_by_Year_NOC:
   if NOC in athletes_by_Year_NOC[year]:
    for i  in athletes_by_Year_NOC[year][NOC]:
      if i['Medal'] != 'NA':
       sports.add(i['Sport'])
  return sports
#======================================
def get_common_sports(athletes_by_Year_NOC, NOCs, year):
  sports = set()
  if year in athletes_by_Year_NOC:
    x =0
    for i in NOCs:
      if i in athletes_by_Year_NOC[year]:
        NOCSport = set()
        for i  in athletes_by_Year_NOC[year][i]:
          if i['Medal'] != 'NA':
            NOCSport.add(i['Sport'])
        if x == 0:
          sports = sports.union(NOCSport)
        else:
          sports = sports.intersection(NOCSport)
      x+=1
  return sports
#======================================
# สามารถเขียนฟังก์ชันที่สร้างเองได้ในบริเวณด้านล่างของ cell นี้ เท่านั้น
# 6530334221 (point = 100.0%) sim = 90%
def convert_to_dict(data):
  athletes_by_Year_NOC = {}
  for i in data[1:]:
    if i[9] in athletes_by_Year_NOC:
      if i[7] in athletes_by_Year_NOC[i[9]]:
        athletes_by_Year_NOC[i[9]][i[7]].append(dict(zip(data[0], i)))
      else:
        athletes_by_Year_NOC[i[9]][i[7]] = [dict(zip(data[0], i))]
    else:
      athletes_by_Year_NOC[i[9]] = {i[7]: [dict(zip(data[0], i))]}
  return athletes_by_Year_NOC
#======================================
def get_medals_by_team(athletes_by_Year_NOC, year):
  medals = {}
  for i in athletes_by_Year_NOC[year]: 
    medals[i] = [0,0,0]
    for k in athletes_by_Year_NOC[year][i]: 
      if k['Medal'] == 'Gold':
        medals[i][0] += 1
      elif k['Medal'] == 'Silver':
        medals[i][1] += 1
      elif k['Medal'] == 'Bronze':
        medals[i][2] += 1
    medals[i]=tuple(medals[i])
  return medals
#======================================
def get_top_five(medals):
  topfive = []
  sortedmedals = []
  for i in medals:
    sortedmedals.append([-medals[i][0],-medals[i][1],-medals[i][2],i])
  sortedmedals.sort()
  prev = [sortedmedals[0][0], sortedmedals[0][1], sortedmedals[0][2]]
  topfive.append((sortedmedals[0][3],-sortedmedals[0][0], -sortedmedals[0][1], -sortedmedals[0][2]))
  count = 1
  for i in sortedmedals[1:]:
    if count == 4:
      prev = [i[0],i[1],i[2]]
    if count >=5 and not (i[0] == prev[0] and i[1] == prev[1] and i[2] == prev[2]):
      break
    topfive.append((i[3],-i[0],-i[1],-i[2]))
    count += 1
  return topfive
#======================================
def get_medals_trend(athletes_by_Year_NOC, NOC, start, end):
  trend = []
  for i in athletes_by_Year_NOC:
    if int(i) >= start and int(i) <= end:
      g=get_medals_by_team(athletes_by_Year_NOC, i)
      if NOC in g:
        trend.append((i, g[NOC][0],g[NOC][1],g[NOC][2]))
  trend.sort()
  return trend
#======================================
def get_sports(athletes_by_Year_NOC, NOC, year):
  sports = set()
  if year in athletes_by_Year_NOC:
    if NOC in athletes_by_Year_NOC[year]:
     for i  in athletes_by_Year_NOC[year][NOC]:
       if i['Medal'] != 'NA':
        sports.add(i['Sport'])
  return sports
#======================================
def get_common_sports(athletes_by_Year_NOC, NOCs, year):
  sports = set()
  j =0
  if year in athletes_by_Year_NOC:
    for i in NOCs:
      if i in athletes_by_Year_NOC[year]:
        NOCSport = set()
        for i  in athletes_by_Year_NOC[year][i]:
          if i['Medal'] != 'NA':
            NOCSport.add(i['Sport'])
        if j == 0:
          sports = NOCSport
        else:
          sports = sports.intersection(NOCSport)
      j+=1
  return sports
#======================================
# สามารถเขียนฟังก์ชันที่สร้างเองได้ในบริเวณด้านล่างของ cell นี้ เท่านั้น