Skip to content

SoccerExtendedPandas

SoccerExtendedPandas dataclass

Bases: SportradarAPI

Parser to transform the SoccerExtended API response to Pandas DataFrame

Source code in sportradar_api/soccer_extended/soccer_extended_pandas.py 
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
@dataclass
class SoccerExtendedPandas(SportradarAPI):
    """Parser to transform the SoccerExtended API response to Pandas DataFrame"""

    api: str = "soccer-extended"

    def __post_init__(self):
        self.soccer_extended = SoccerExtended(api_key=self.api_key, verbose=self.verbose)

    def get_competitions(self) -> pd.DataFrame:
        """Get all available Soccer competitions.

        Returns:
            Pandas DataFrame
        """
        competitions = self.soccer_extended.get_competitions()
        competitions = pd.json_normalize(competitions["competitions"])

        return competitions

    def get_seasons(self) -> pd.DataFrame:
        """Get historical season information for all competitions.

        Returns:
            Pandas DataFrame
        """
        seasons = self.soccer_extended.get_seasons()
        seasons = pd.json_normalize(seasons["seasons"])

        return seasons

    def get_season_matches(self, season_urn: str):
        """Get the information of all matches from a given season.

        Args:
            season_urn: URN of a given season

        Returns:
            Pandas DataFrame
        """
        cols = [
            "sport_event.id",
            "sport_event.start_time",
            "sport_event.start_time_confirmed",
            "sport_event.sport_event_context.sport.id",
            "sport_event.sport_event_context.category.id",
            "sport_event.sport_event_context.competition.id",
            "sport_event.sport_event_context.season.id",
            "sport_event.coverage.sport_event_properties.lineups",
            "sport_event.coverage.sport_event_properties.venue",
            "sport_event.coverage.sport_event_properties.extended_player_stats",
            "sport_event.coverage.sport_event_properties.extended_team_stats",
            "sport_event.coverage.sport_event_properties.basic_play_by_play",
            "sport_event.coverage.sport_event_properties.basic_player_stats",
            "sport_event.coverage.sport_event_properties.basic_team_stats",
            "sport_event.competitor_home_id",
            "sport_event.competitor_away_id",
            "sport_event.venue.id",
            "sport_event.sport_event_conditions.ground.neutral",
            "sport_event_status.status",
            "sport_event_status.match_status",
            "sport_event.replaced_by",
            "sport_event_status.home_score",
            "sport_event_status.away_score",
            "sport_event_status.match_tie",
            "sport_event_status.winner_id",
        ]
        season_summaries = self.soccer_extended.get_season_summaries(season_urn=season_urn)
        season_matches = pd.json_normalize(season_summaries["summaries"])

        competitors = pd.DataFrame(season_matches.pop("sport_event.competitors").to_list())
        competitors.columns = ["sport_event.competitor_home_id", "sport_event.competitor_away_id"]
        competitors["sport_event.competitor_home_id"] = competitors["sport_event.competitor_home_id"].apply(
            lambda x: x.get("id")
        )
        competitors["sport_event.competitor_away_id"] = competitors["sport_event.competitor_away_id"].apply(
            lambda x: x.get("id")
        )

        cols_select = [col for col in cols if col in season_matches.columns]

        season_matches = (
            season_matches.join(competitors)
            .loc[:, cols_select]
            .pipe(
                remove_cols_str,
                [
                    "sport_event.",
                    "sport_event_context.",
                    "coverage.sport_event_properties.",
                    "sport_event_conditions.",
                    "sport_event_status.",
                ],
            )
            .pipe(replace_cols_str, {".": "_"})
        )

        return season_matches

    def get_season_matches_statistics(self, season_urn: str) -> pd.DataFrame:
        """Get the players statistics of all matches from a given season.

        Args:
            season_urn: URN of a given season

        Returns:
            Pandas DataFrame
        """
        season_summaries = self.soccer_extended.get_season_summaries(season_urn=season_urn)

        matches_statistics = (
            pd.json_normalize(season_summaries, "summaries")
            .pipe(explode_column, "statistics.totals.competitors", ["sport_event.id", "sport_event.start_time"])
            .pipe(
                explode_column,
                "statistics.totals.competitors.players",
                [
                    "sport_event.id",
                    "sport_event.start_time",
                    "statistics.totals.competitors.id",
                    "statistics.totals.competitors.qualifier",
                ],
            )
            .pipe(
                lambda x: x.set_axis(
                    [remove_str("_".join(col.split(".")[-2:]), ["sport_event_", "statistics_"]) for col in x.columns],
                    axis=1,
                )
            )
        )

        return matches_statistics

    def get_season_competitors(self, season_urn: str) -> pd.DataFrame:
        """Get all teams participating for a given season.

        Args:
            season_urn: URN of a given season

        Returns:
            Pandas DataFrame
        """
        season_competitors = self.soccer_extended.get_season_competitors(season_urn=season_urn)
        season_competitors = pd.json_normalize(season_competitors["season_competitors"])

        return season_competitors.assign(season_urn=season_urn)

    def get_season_competitor_player(self, season_urn: str) -> pd.DataFrame:
        """Get all players profile for a given season

        Args:
            season_urn: URN of a given season

        Returns:
            Pandas DataFrame
        """
        season_competitor_players = self.soccer_extended.get_season_competitor_players(season_urn=season_urn)
        season_competitor_players = (
            pd.json_normalize(season_competitor_players["season_competitor_players"])
            .explode("players")
            .players.apply(pd.Series)
        )

        return season_competitor_players

    def get_player_profile_info(self, player_urn: str) -> pd.DataFrame:
        """Get the basic information from a player profile

        Args:
            player_urn: URN of a given player

        Returns:
            Pandas DataFrame
        """
        player_profile = self.soccer_extended.get_player_profile(player_urn=player_urn)
        player_profile_info = pd.json_normalize(player_profile["player"])

        return player_profile_info

    def get_player_profile_competitors(self, player_urn: str) -> pd.DataFrame:
        """Get the competitors from a player profile

        Args:
            player_urn: URN of a given player

        Returns:
            Pandas DataFrame
        """
        player_profile = self.soccer_extended.get_player_profile(player_urn=player_urn)
        player_profile_competitors = pd.json_normalize(player_profile["competitors"])

        return player_profile_competitors.assign(player_id=player_urn)

    def get_player_profile_roles(self, player_urn: str) -> pd.DataFrame:
        """Get the roles from a player profile

        Args:
            player_urn: URN of a given player

        Returns:
            Pandas DataFrame
        """
        player_profile = self.soccer_extended.get_player_profile(player_urn=player_urn)
        player_profile_roles = pd.json_normalize([flatten(role, separator=".") for role in player_profile["roles"]])

        return player_profile_roles.assign(player_urn=player_urn)

    def get_sport_event_statistics(self, sport_event_urn: str) -> pd.DataFrame:
        """Get the statistics from a sport event

        Args:
            sport_event_urn: URN of a given sport event

        Returns:
            Pandas DataFrame
        """
        sport_event_summary = self.soccer_extended.get_sport_event_summary(sport_event_urn=sport_event_urn)

        sport_event_statistics = (
            pd.json_normalize(sport_event_summary)
            .pipe(explode_column, "statistics.totals.competitors", ["sport_event.id", "sport_event.start_time"])
            .pipe(
                explode_column,
                "statistics.totals.competitors.players",
                [
                    "sport_event.id",
                    "sport_event.start_time",
                    "statistics.totals.competitors.id",
                    "statistics.totals.competitors.qualifier",
                ],
            )
            .pipe(
                lambda x: x.set_axis(
                    [remove_str("_".join(col.split(".")[-2:]), ["sport_event_", "statistics_"]) for col in x.columns],
                    axis=1,
                )
            )
        )

        return sport_event_statistics

get_competitions()

Get all available Soccer competitions.

Returns:

Type Description
pd.DataFrame

Pandas DataFrame
Source code in sportradar_api/soccer_extended/soccer_extended_pandas.py 
25
26
27
28
29
30
31
32
33
34
def get_competitions(self) -> pd.DataFrame:
    """Get all available Soccer competitions.

    Returns:
        Pandas DataFrame
    """
    competitions = self.soccer_extended.get_competitions()
    competitions = pd.json_normalize(competitions["competitions"])

    return competitions

get_player_profile_competitors(player_urn)

Get the competitors from a player profile

Parameters:

Name Type Description Default
player_urn str

URN of a given player

 required

Returns:

Type Description
pd.DataFrame

Pandas DataFrame
Source code in sportradar_api/soccer_extended/soccer_extended_pandas.py 
195
196
197
198
199
200
201
202
203
204
205
206
207
def get_player_profile_competitors(self, player_urn: str) -> pd.DataFrame:
    """Get the competitors from a player profile

    Args:
        player_urn: URN of a given player

    Returns:
        Pandas DataFrame
    """
    player_profile = self.soccer_extended.get_player_profile(player_urn=player_urn)
    player_profile_competitors = pd.json_normalize(player_profile["competitors"])

    return player_profile_competitors.assign(player_id=player_urn)

get_player_profile_info(player_urn)

Get the basic information from a player profile

Parameters:

Name Type Description Default
player_urn str

URN of a given player

 required

Returns:

Type Description
pd.DataFrame

Pandas DataFrame
Source code in sportradar_api/soccer_extended/soccer_extended_pandas.py 
181
182
183
184
185
186
187
188
189
190
191
192
193
def get_player_profile_info(self, player_urn: str) -> pd.DataFrame:
    """Get the basic information from a player profile

    Args:
        player_urn: URN of a given player

    Returns:
        Pandas DataFrame
    """
    player_profile = self.soccer_extended.get_player_profile(player_urn=player_urn)
    player_profile_info = pd.json_normalize(player_profile["player"])

    return player_profile_info

get_player_profile_roles(player_urn)

Get the roles from a player profile

Parameters:

Name Type Description Default
player_urn str

URN of a given player

 required

Returns:

Type Description
pd.DataFrame

Pandas DataFrame
Source code in sportradar_api/soccer_extended/soccer_extended_pandas.py 
209
210
211
212
213
214
215
216
217
218
219
220
221
def get_player_profile_roles(self, player_urn: str) -> pd.DataFrame:
    """Get the roles from a player profile

    Args:
        player_urn: URN of a given player

    Returns:
        Pandas DataFrame
    """
    player_profile = self.soccer_extended.get_player_profile(player_urn=player_urn)
    player_profile_roles = pd.json_normalize([flatten(role, separator=".") for role in player_profile["roles"]])

    return player_profile_roles.assign(player_urn=player_urn)

get_season_competitor_player(season_urn)

Get all players profile for a given season

Parameters:

Name Type Description Default
season_urn str

URN of a given season

 required

Returns:

Type Description
pd.DataFrame

Pandas DataFrame
Source code in sportradar_api/soccer_extended/soccer_extended_pandas.py 
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
def get_season_competitor_player(self, season_urn: str) -> pd.DataFrame:
    """Get all players profile for a given season

    Args:
        season_urn: URN of a given season

    Returns:
        Pandas DataFrame
    """
    season_competitor_players = self.soccer_extended.get_season_competitor_players(season_urn=season_urn)
    season_competitor_players = (
        pd.json_normalize(season_competitor_players["season_competitor_players"])
        .explode("players")
        .players.apply(pd.Series)
    )

    return season_competitor_players

get_season_competitors(season_urn)

Get all teams participating for a given season.

Parameters:

Name Type Description Default
season_urn str

URN of a given season

 required

Returns:

Type Description
pd.DataFrame

Pandas DataFrame
Source code in sportradar_api/soccer_extended/soccer_extended_pandas.py 
149
150
151
152
153
154
155
156
157
158
159
160
161
def get_season_competitors(self, season_urn: str) -> pd.DataFrame:
    """Get all teams participating for a given season.

    Args:
        season_urn: URN of a given season

    Returns:
        Pandas DataFrame
    """
    season_competitors = self.soccer_extended.get_season_competitors(season_urn=season_urn)
    season_competitors = pd.json_normalize(season_competitors["season_competitors"])

    return season_competitors.assign(season_urn=season_urn)

get_season_matches(season_urn)

Get the information of all matches from a given season.

Parameters:

Name Type Description Default
season_urn str

URN of a given season

 required

Returns:

Type Description

Pandas DataFrame
Source code in sportradar_api/soccer_extended/soccer_extended_pandas.py 
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
def get_season_matches(self, season_urn: str):
    """Get the information of all matches from a given season.

    Args:
        season_urn: URN of a given season

    Returns:
        Pandas DataFrame
    """
    cols = [
        "sport_event.id",
        "sport_event.start_time",
        "sport_event.start_time_confirmed",
        "sport_event.sport_event_context.sport.id",
        "sport_event.sport_event_context.category.id",
        "sport_event.sport_event_context.competition.id",
        "sport_event.sport_event_context.season.id",
        "sport_event.coverage.sport_event_properties.lineups",
        "sport_event.coverage.sport_event_properties.venue",
        "sport_event.coverage.sport_event_properties.extended_player_stats",
        "sport_event.coverage.sport_event_properties.extended_team_stats",
        "sport_event.coverage.sport_event_properties.basic_play_by_play",
        "sport_event.coverage.sport_event_properties.basic_player_stats",
        "sport_event.coverage.sport_event_properties.basic_team_stats",
        "sport_event.competitor_home_id",
        "sport_event.competitor_away_id",
        "sport_event.venue.id",
        "sport_event.sport_event_conditions.ground.neutral",
        "sport_event_status.status",
        "sport_event_status.match_status",
        "sport_event.replaced_by",
        "sport_event_status.home_score",
        "sport_event_status.away_score",
        "sport_event_status.match_tie",
        "sport_event_status.winner_id",
    ]
    season_summaries = self.soccer_extended.get_season_summaries(season_urn=season_urn)
    season_matches = pd.json_normalize(season_summaries["summaries"])

    competitors = pd.DataFrame(season_matches.pop("sport_event.competitors").to_list())
    competitors.columns = ["sport_event.competitor_home_id", "sport_event.competitor_away_id"]
    competitors["sport_event.competitor_home_id"] = competitors["sport_event.competitor_home_id"].apply(
        lambda x: x.get("id")
    )
    competitors["sport_event.competitor_away_id"] = competitors["sport_event.competitor_away_id"].apply(
        lambda x: x.get("id")
    )

    cols_select = [col for col in cols if col in season_matches.columns]

    season_matches = (
        season_matches.join(competitors)
        .loc[:, cols_select]
        .pipe(
            remove_cols_str,
            [
                "sport_event.",
                "sport_event_context.",
                "coverage.sport_event_properties.",
                "sport_event_conditions.",
                "sport_event_status.",
            ],
        )
        .pipe(replace_cols_str, {".": "_"})
    )

    return season_matches

get_season_matches_statistics(season_urn)

Get the players statistics of all matches from a given season.

Parameters:

Name Type Description Default
season_urn str

URN of a given season

 required

Returns:

Type Description
pd.DataFrame

Pandas DataFrame
Source code in sportradar_api/soccer_extended/soccer_extended_pandas.py 
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
def get_season_matches_statistics(self, season_urn: str) -> pd.DataFrame:
    """Get the players statistics of all matches from a given season.

    Args:
        season_urn: URN of a given season

    Returns:
        Pandas DataFrame
    """
    season_summaries = self.soccer_extended.get_season_summaries(season_urn=season_urn)

    matches_statistics = (
        pd.json_normalize(season_summaries, "summaries")
        .pipe(explode_column, "statistics.totals.competitors", ["sport_event.id", "sport_event.start_time"])
        .pipe(
            explode_column,
            "statistics.totals.competitors.players",
            [
                "sport_event.id",
                "sport_event.start_time",
                "statistics.totals.competitors.id",
                "statistics.totals.competitors.qualifier",
            ],
        )
        .pipe(
            lambda x: x.set_axis(
                [remove_str("_".join(col.split(".")[-2:]), ["sport_event_", "statistics_"]) for col in x.columns],
                axis=1,
            )
        )
    )

    return matches_statistics

get_seasons()

Get historical season information for all competitions.

Returns:

Type Description
pd.DataFrame

Pandas DataFrame
Source code in sportradar_api/soccer_extended/soccer_extended_pandas.py 
36
37
38
39
40
41
42
43
44
45
def get_seasons(self) -> pd.DataFrame:
    """Get historical season information for all competitions.

    Returns:
        Pandas DataFrame
    """
    seasons = self.soccer_extended.get_seasons()
    seasons = pd.json_normalize(seasons["seasons"])

    return seasons

get_sport_event_statistics(sport_event_urn)

Get the statistics from a sport event

Parameters:

Name Type Description Default
sport_event_urn str

URN of a given sport event

 required

Returns:

Type Description
pd.DataFrame

Pandas DataFrame
Source code in sportradar_api/soccer_extended/soccer_extended_pandas.py 
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
def get_sport_event_statistics(self, sport_event_urn: str) -> pd.DataFrame:
    """Get the statistics from a sport event

    Args:
        sport_event_urn: URN of a given sport event

    Returns:
        Pandas DataFrame
    """
    sport_event_summary = self.soccer_extended.get_sport_event_summary(sport_event_urn=sport_event_urn)

    sport_event_statistics = (
        pd.json_normalize(sport_event_summary)
        .pipe(explode_column, "statistics.totals.competitors", ["sport_event.id", "sport_event.start_time"])
        .pipe(
            explode_column,
            "statistics.totals.competitors.players",
            [
                "sport_event.id",
                "sport_event.start_time",
                "statistics.totals.competitors.id",
                "statistics.totals.competitors.qualifier",
            ],
        )
        .pipe(
            lambda x: x.set_axis(
                [remove_str("_".join(col.split(".")[-2:]), ["sport_event_", "statistics_"]) for col in x.columns],
                axis=1,
            )
        )
    )

    return sport_event_statistics
Last update: 2023-06-08