def schedule_df(team_name):
team_obj = Schedule(team_name, year=2019)
df = team_obj.dataframe
df.reset_index(inplace=True)
df.rename(columns={"index": "team_name"},inplace=True)
df['team_name'] = team_name
return df
def setup_method(self, *args, **kwargs):
self.results = {
'game': 2,
'boxscore_index': 'TBA/TBA201704040',
'date': 'Tuesday, Apr 4',
'datetime': datetime(2017, 4, 4),
'game_number_for_day': 1,
'location': AWAY,
'opponent_abbr': 'TBR',
'result': WIN,
'runs_scored': 5,
'runs_allowed': 0,
'innings': 9,
'record': '1-1',
'rank': 3,
'games_behind': 0.5,
'winner': 'Sabathia',
'loser': 'Odorizzi',
'save': None,
'game_duration': '3:07',
'day_or_night': NIGHT,
'attendance': 19366,
'streak': '+'
}
flexmock(Boxscore) \
.should_receive('_parse_game_data') \
.and_return(None)
flexmock(Boxscore) \
.should_receive('dataframe') \
.and_return(pd.DataFrame([{'key': 'value'}]))
flexmock(utils) \
.should_receive('_todays_date') \
.and_return(MockDateTime(YEAR, MONTH))
self.schedule = Schedule('NYY')
def test_empty_page_return_no_games(self):
flexmock(utils) \
.should_receive('_no_data_found') \
.once()
flexmock(utils) \
.should_receive('_get_stats_table') \
.and_return(None)
schedule = Schedule('NYY')
assert len(schedule) == 0
def test_no_dataframes_extended_returns_none(self):
flexmock(Schedule) \
.should_receive('_pull_schedule') \
.and_return(None)
schedule = Schedule('HOU')
fake_game = flexmock(dataframe_extended=None)
fake_games = PropertyMock(return_value=fake_game)
type(schedule).__iter__ = fake_games
assert schedule.dataframe_extended is None
def test_invalid_dataframe_not_included_with_schedule_dataframes(self):
# If a DataFrame is not valid, it should not be included with the
# dataframes property. If no dataframes are present, the DataFrame
# should return the default value of None.
flexmock(Schedule) \
.should_receive('_pull_schedule') \
.and_return(None)
schedule = Schedule('HOU')
fake_game = flexmock(_runs_scored=None, _runs_allowed=None)
fake_games = PropertyMock(return_value=fake_game)
type(schedule).__iter__ = fake_games
assert schedule.dataframe is None
def test_invalid_dataframe_not_included_with_schedule_dataframes(self):
# If a DataFrame is not valid, it should not be included with the
# dataframes property. If no dataframes are present, a ValueError
# should be raised.
flexmock(Schedule) \
.should_receive('_pull_schedule') \
.and_return(None)
schedule = Schedule('HOU')
fake_game = flexmock(_runs_scored=None, _runs_allowed=None)
fake_games = PropertyMock(return_value=fake_game)
type(schedule).__iter__ = fake_games
with pytest.raises(ValueError):
schedule.dataframe
def test_mlb_invalid_default_year_reverts_to_previous_year(self,
*args,
**kwargs):
results = {
'game': 2,
'boxscore_index': 'TBA/TBA201704040',
'date': 'Tuesday, Apr 4',
'datetime': datetime(2017, 4, 4),
'game_number_for_day': 1,
'location': AWAY,
'opponent_abbr': 'TBR',
'result': WIN,
'runs_scored': 5,
'runs_allowed': 0,
'innings': 9,
'record': '1-1',
'rank': 3,
'games_behind': 0.5,
'winner': 'Sabathia',
'loser': 'Odorizzi',
'save': None,
'game_duration': '3:07',
'day_or_night': NIGHT,
'attendance': 19366,
'streak': '+'
}
flexmock(Boxscore) \
.should_receive('_parse_game_data') \
.and_return(None)
flexmock(Boxscore) \
.should_receive('dataframe') \
.and_return(pd.DataFrame([{'key': 'value'}]))
flexmock(utils) \
.should_receive('_find_year_for_season') \
.and_return(2018)
schedule = Schedule('NYY')
for attribute, value in results.items():
assert getattr(schedule[1], attribute) == value
def get_day(str):
return datetime.strptime(str, " %B %d, %Y").day
def to_duration(str):
t1 = datetime.strptime(str, '%H:%M')
t2 = datetime(1900, 1, 1)
return (t1 - t2).total_seconds() / 60.0
today = date.today()
teams = Teams()
for team in teams:
abr = team.abbreviation
sched = Schedule(abr)
#open csv
#get the last row month and day
fname = abr + '.csv'
old_df = pd.read_csv(fname)
new_rows = []
last_month = int(old_df.tail(1)['month'])
last_day = int(old_df.tail(1)['day'])
last_date = datetime(today.year, last_month, last_day)
for game in sched:
if game.datetime > last_date and len(game.boxscore_index) == 16:
new_rows.append(Boxscore(game.boxscore_index).dataframe)
from sportsreference.mlb.teams import Teams
from sportsreference.mlb.boxscore import Boxscore
from sportsreference.mlb.schedule import Schedule
import pandas as pd
##### Single Team Work ######
# Clean up date format
sea_df = Schedule('SEA').dataframe_extended
sea_df['date'] = pd.to_datetime(sea_df.date)
sea_df['date'] = sea_df['date'].dt.strftime('%m/%d/%Y')
# Add Home and Away Team fields
home_team = []
away_team = []
for ind in sea_df.index:
if sea_df['winner'][ind] == 'Home':
home_team.append(sea_df['winning_abbr'][ind])
else:
home_team.append(sea_df['losing_abbr'][ind])
if sea_df['winner'][ind] == 'Away':
away_team.append(sea_df['winning_abbr'][ind])
else:
away_team.append(sea_df['losing_abbr'][ind])
sea_df.insert(81, 'home_team', home_team, True)
sea_df.insert(82, 'away_team', away_team, True)
sea_df['team'] = 'SEA'
# already integrated with pandas
# print datafram for each team
for team in Teams():
print(team.name)
print(team.dataframe)
# use .loc[] to access a single ron
for team in Teams():
print(team.name)
schedule = team.schedule # Request the current team's schedule
for game in schedule:
print(game.date, game.points_scored, game.points_allowed)
# different way to access schedule
houston_schedule = Schedule('HOU')
for game in houston_schedule:
print(game.date, game.points_scored, game.points_allowed)
# get boxscores
game_data = Boxscore('BOS/BOS201808020')
print(game_data.away_runs, game_data.home_runs)
print(game_data.dataframe)
# different way to get boxscores
houston_schedule = Schedule('HOU')
for game in houston_schedule:
print(game.boxscore_index) # Prints the boxscore URI for each game
# Returns an instance of the Boxscore class for this specific game
elif re.search(sPattern2, tLinkText):
teams.append(tLinkText)
else:
for tLink in tLinks:
tLinkText = tLink.text
if re.search(sPattern1, tLinkText):
teams.append(tLinkText)
#removing duplicates
teams = list(dict.fromkeys(teams))
baseBall.append(teams)
#loop through each baseball team, if any, and see if they are playing at home today
if len(teams) > 0:
for team in teams:
sch = Schedule(mlbAbbr[team])
for game in sch:
if game.date == today and game.location == 'Home':
isPlaying.append(team)
whosePlaying.append(isPlaying)
#creating the data frame
df = pd.DataFrame(list(
zip(Names, States, Lat, Long, TZ, Pops, Area, Demonyms, featColl, baseBall,
whosePlaying, weather)),
columns=[
'City Name', 'State', 'Latitude', 'Longitude',
'Time Zone', 'Population', 'Area', 'Demonyms',
'Notable Educational Insitiutiions', 'Baseball Team(s)',
'What team is playing at home today', 'the weather'
])