def game_filter(csv_file):
# Takes in a csv filepath of one of the EightThirtyFour data sets
# and filters the data to games with a 10 or less point lead in
# the last 6 minutes of the game.
pbp = Table().read_table(csv_file)
unique_games = pbp.group('GAME_ID').column(0)
print(unique_games)
last_quarter = pbp.where('PERIOD', predicates.are.equal_to(4))
transformed_minutes = last_quarter.apply(time_string_to_number,
'PCTIMESTRING')
last_quarter_and_minutes = last_quarter.with_column(
'TIME', transformed_minutes)
between_six_and_seven = last_quarter_and_minutes.where(
'TIME', predicates.are.below_or_equal_to(6.5))
close_games = make_array()
for game in unique_games:
game_scores_only = between_six_and_seven.where(
'GAME_ID',
predicates.are.equal_to(game)).select('TIME', 'SCORE').where(
'SCORE', predicates.are.not_equal_to('nan'))
score = game_scores_only.row(0).item(1)
t1, t2 = score.split('-')
if abs(int(t1) - int(t2)) <= 10:
close_games = np.append(close_games, game)
return close_games
new_full_names = [] # from last,first to first,last
for name in full_names:
if ',' in name:
first_name = name.split(',')[1].strip()
last_name = name.split(',')[0].strip()
new_full_names.append(first_name + " " + last_name)
else:
new_full_names.append(name)
# compile into a table
books = Table().with_columns("SEMESTER", semesters, "SECTIONS", section,
"CLASS NAME", class_name, "BOOK TITLES",
book_names, "AUTHOR", new_full_names)
grouped = books.group(["SEMESTER", "AUTHOR"])
print(grouped)
# "calculate" genders from Wikipedia articles
gender = []
seen = {} # memoization: author -> gender
wiki = WikiApi()
for author in grouped.column("AUTHOR"):
if author.lower() in seen:
print(author, "already found previously")
gender.append(seen[author.lower()])
continue
try:
try:
print("trying to find " + author + " in wikipedia")
