def get_stats_data(sort_by_date=False, options=None):
"""
Get Pandas DataFrame of all league stats in the top 5 leagues, over time.
Parameters:
- sort_by_date (bool): Sort data by league names if False. Sort data by dates if True. Default: False
- options (dict): options to filter out data to extract
NOTE: Can be used for time-series analysis.
"""
json_data = extract.get_stats(options=options)
list_of_stats = transform.parse_json(json_data=json_data)
data_stats = transform.wrangle_list_to_dataframe(list_data=list_of_stats)
data_stats['year'] = data_stats['year'].astype(int)
data_stats['month'] = data_stats['month'].astype(int)
data_stats = data_stats.sort_values(by=['league', 'year', 'month'], ascending=[True, True, True])\
.reset_index(drop=True)
data_stats['datetime'] = data_stats['year'].astype(
str) + '-' + data_stats['month'].astype(str) + '-' + '28'
data_stats['datetime'] = pd.to_datetime(arg=data_stats['datetime'],
format="%Y-%m-%d")
if sort_by_date:
data_stats = data_stats.sort_values(
by='datetime', ascending=True).reset_index(drop=True)
return data_stats
def get_player_shots_data(player_id, options=None):
"""
Get Pandas DataFrame of shots-data of particular player in all matches he's played, by ['player_id']
"""
json_data = extract.get_player_shots(player_id=player_id, options=options)
list_of_matches = transform.parse_json(json_data=json_data)
data_player_shots = transform.wrangle_list_to_dataframe(
list_data=list_of_matches)
return data_player_shots
def get_team_players_data(team_name, season, options=None):
"""
Get Pandas DataFrame of stats of players for a particular team, by ['team_name', 'season']
"""
json_data = extract.get_team_players(team_name=team_name,
season=season,
options=options)
list_of_players = transform.parse_json(json_data=json_data)
data_team_players = transform.wrangle_list_to_dataframe(
list_data=list_of_players)
data_team_players['season'] = season
return data_team_players
def get_player_matches_data(player_id, options=None):
"""
Get Pandas DataFrame of stats of particular player in all matches he's played, by ['player_id']
"""
json_data = extract.get_player_matches(player_id=player_id,
options=options)
list_of_matches = transform.parse_json(json_data=json_data)
data_player_matches = transform.wrangle_list_to_dataframe(
list_data=list_of_matches)
player_ids_all = utils.pickle_load(filename='ids_of_players.pkl')
player_name = player_ids_all[str(player_id)]
data_player_matches['PlayerName'] = player_name
return data_player_matches
def get_player_stats_data(player_id, positions=None):
"""
Get Pandas DataFrame of max, min, avg stats of player over the seasons, by ['player_id']
"""
json_data = extract.get_player_stats(player_id=player_id,
positions=positions)
list_of_matches = transform.parse_json(json_data=json_data)
data_player_stats = transform.wrangle_list_to_dataframe(
list_data=list_of_matches)
data_player_stats = transform.wrangle_max_min_avg(
dataframe=data_player_stats)
player_ids_all = utils.pickle_load(filename='ids_of_players.pkl')
player_name = player_ids_all[str(player_id)]
data_player_stats['PlayerName'] = player_name
return data_player_stats
def get_team_results_data(team_name, season, options=None):
"""
Get Pandas DataFrame of stats of results for a particular team, by ['team_name', 'season']
"""
data_team_results = pd.DataFrame()
json_data = extract.get_team_results(team_name=team_name,
season=season,
options=options)
list_of_matches = transform.parse_json(json_data=json_data)
data = transform.wrangle_list_to_dataframe(list_data=list_of_matches)
data_team_results = transform.wrangle_results(dataframe=data)
data_team_results['h_a'] = data['side']
data_team_results['result'] = data['result'].map({
'w': 'Win',
'l': 'Loss',
'd': 'Draw'
})
data_team_results['TeamOfInterest'] = team_name
data_team_results['season'] = season
data_team_results.sort_values(by='datetime', ascending=True, inplace=True)
return data_team_results
def get_team_fixtures_data(team_name, season):
"""
Get Pandas DataFrame of upcoming league fixtures for a particular team, by ['team_name', 'season']
"""
data_new = pd.DataFrame()
json_upcoming_fixtures_home = extract.get_team_fixtures(
team_name=team_name, season=season, side='h')
json_upcoming_fixtures_away = extract.get_team_fixtures(
team_name=team_name, season=season, side='a')
list_of_matches_home = transform.parse_json(
json_data=json_upcoming_fixtures_home)
list_of_matches_away = transform.parse_json(
json_data=json_upcoming_fixtures_away)
list_of_matches = list_of_matches_home + list_of_matches_away
data = transform.wrangle_list_to_dataframe(list_data=list_of_matches)
if data.empty:
return pd.DataFrame()
data_new = transform.wrangle_upcoming_fixtures(dataframe=data)
data_new['h_a'] = data['side']
data_new['TeamOfInterest'] = team_name
return data_new