79 add fifa country name to several functions

impectPy/iteration_averages.py

@@ -49,7 +49,12 @@ def getPlayerIterationAveragesFromHost(
         method="GET"
     ).process_response(
         endpoint="Players"
-    )[["id", "commonname", "firstname", "lastname", "birthdate", "birthplace", "leg", "idMappings"]]
+    )[["id", "commonname", "firstname", "lastname", "birthdate", "birthplace", "leg", "countryIds", "idMappings"]]
+
+    # only keep first country id for each player
+    country_series = players["countryIds"].explode().groupby(level=0).first()
+    players["countryIds"] = players.index.to_series().map(country_series).astype("float").astype("Int64")
+    players = players.rename(columns={"countryIds": "countryId"})
 
     # unnest mappings
     players = unnest_mappings_df(players, "idMappings").drop(["idMappings"], axis=1).drop_duplicates()
@@ -65,6 +70,14 @@ def getPlayerIterationAveragesFromHost(
     # get iterations
     iterations = getIterationsFromHost(connection=connection, host=host)
 
+    # get country data
+    countries = connection.make_api_request_limited(
+        url=f"{host}/v5/customerapi/countries",
+        method="GET"
+    ).process_response(
+        endpoint="KPIs"
+    )
+
     # create empty df to store averages
     averages = pd.DataFrame()
 
@@ -162,14 +175,20 @@ def getPlayerIterationAveragesFromHost(
     ).merge(
         players[[
             "id", "wyscoutId", "heimSpielId", "skillCornerId", "commonname",
-            "firstname", "lastname", "birthdate", "birthplace", "leg"
+            "firstname", "lastname", "birthdate", "birthplace", "countryId", "leg"
         ]].rename(
             columns={"commonname": "playerName"}
         ),
         left_on="playerId",
         right_on="id",
         how="left",
         suffixes=("", "_right")
+    ).merge(
+        countries.rename(columns={"fifaName": "playerCountry"}),
+        left_on="countryId",
+        right_on="id",
+        how="left",
+        suffixes=("", "_right")
     )
 
     # remove NA rows
@@ -199,6 +218,7 @@ def getPlayerIterationAveragesFromHost(
         "lastname",
         "birthdate",
         "birthplace",
+        "playerCountry",
         "leg",
         "position",
         "matchShare",

impectPy/iterations.py

@@ -50,8 +50,44 @@ def getIterationsFromHost(connection: RateLimitedAPI, host: str) -> pd.DataFrame
     df.heimSpielId = df.heimSpielId.apply(lambda x: x[0] if x else None)
     df.wyscoutId = df.wyscoutId.apply(lambda x: x[0] if x else None)
 
+    # get country data
+    countries = connection.make_api_request_limited(
+        url=f"{host}/v5/customerapi/countries",
+        method="GET"
+    ).process_response(
+        endpoint="KPIs"
+    )
+
+    df = df.merge(
+        countries[["id", "fifaName"]].rename(
+            columns={"id": "competitionCountryId", "fifaName": "competitionCountryName"}
+        ),
+        how="left",
+        on="competitionCountryId"
+    )
+
     # sort iterations
     df = df.sort_values(by="id")
 
+    # define column order
+    order = [
+        "id",
+        "competitionId",
+        "competitionName",
+        "season",
+        "competitionType",
+        "competitionCountryId",
+        "competitionCountryName",
+        "competitionGender",
+        "dataVersion",
+        "lastChangeTimestamp",
+        "wyscoutId",
+        "heimSpielId",
+        "skillCornerId",
+    ]
+
+    # select columns
+    df = df[order]
+
     # return dataframe
     return df

impectPy/matchsums.py

@@ -80,7 +80,12 @@ def getPlayerMatchsumsFromHost(matches: list, connection: RateLimitedAPI, host:
             ),
             iterations),
         ignore_index=True
-    )[["id", "commonname", "firstname", "lastname", "birthdate", "birthplace", "leg", "idMappings"]]
+    )[["id", "commonname", "firstname", "lastname", "birthdate", "birthplace", "leg", "countryIds", "idMappings"]]
+
+    # only keep first country id for each player
+    country_series = players["countryIds"].explode().groupby(level=0).first()
+    players["countryIds"] = players.index.to_series().map(country_series).astype("float").astype("Int64")
+    players = players.rename(columns={"countryIds": "countryId"})
 
     # unnest mappings
     players = unnest_mappings_df(players, "idMappings").drop(["idMappings"], axis=1).drop_duplicates()
@@ -117,6 +122,14 @@ def getPlayerMatchsumsFromHost(matches: list, connection: RateLimitedAPI, host:
     # get iterations
     iterations = getIterationsFromHost(connection=connection, host=host)
 
+    # get country data
+    countries = connection.make_api_request_limited(
+        url=f"{host}/v5/customerapi/countries",
+        method="GET"
+    ).process_response(
+        endpoint="KPIs"
+    )
+
     # create empty df to store matchsums
     matchsums = pd.DataFrame()
 
@@ -181,7 +194,7 @@ def getPlayerMatchsumsFromHost(matches: list, connection: RateLimitedAPI, host:
 
             # append to matchsums
             matchsums = pd.concat([matchsums, temp])
-    
+
     # merge with other data
     matchsums = matchsums.merge(
         matchplan[["id", "scheduledDate", "matchDayIndex", "matchDayName", "iterationId"]],
@@ -206,14 +219,20 @@ def getPlayerMatchsumsFromHost(matches: list, connection: RateLimitedAPI, host:
     ).merge(
         players[[
             "id", "wyscoutId", "heimSpielId", "skillCornerId", "commonname",
-            "firstname", "lastname", "birthdate", "birthplace", "leg"
+            "firstname", "lastname", "birthdate", "birthplace", "countryId", "leg"
         ]].rename(
             columns={"commonname": "playerName"}
         ),
         left_on="id",
         right_on="id",
         how="left",
         suffixes=("", "_right")
+    ).merge(
+        countries.rename(columns={"fifaName": "playerCountry"}),
+        left_on="countryId",
+        right_on="id",
+        how="left",
+        suffixes=("", "_right")
     )
 
     # rename some columns
@@ -244,6 +263,7 @@ def getPlayerMatchsumsFromHost(matches: list, connection: RateLimitedAPI, host:
         "lastname",
         "birthdate",
         "birthplace",
+        "playerCountry",
         "leg",
         "position",
         "matchShare",

impectPy/player_profile_scores.py

@@ -41,37 +41,37 @@ def getPlayerProfileScores(
 def getPlayerProfileScoresFromHost(
         iteration: int, positions: list, connection: RateLimitedAPI, host: str
 ) -> pd.DataFrame:
-    
+
     # check input for iteration argument
     if not isinstance(iteration, int):
         raise Exception("Input for iteration argument must be an integer")
-        
+
     # check input for positions argument
     if not isinstance(positions, list):
         raise Exception("Input for positions argument must be a list")
-    
+
     # check if the input positions are valid
     invalid_positions = [position for position in positions if position not in allowed_positions]
     if len(invalid_positions) > 0:
         raise Exception(
             f"Invalid position(s): {', '.join(invalid_positions)}."
             f"\nChoose one or more of: {', '.join(allowed_positions)}"
         )
-    
+
     # get squads
     squads = connection.make_api_request_limited(
         url=f"{host}/v5/customerapi/iterations/{iteration}/squads",
         method="GET"
     ).process_response(
         endpoint="Squads"
     )
-    
+
     # get squadIds
     squad_ids = squads[squads.access].id.to_list()
-    
+
     # compile position string
     position_string = ",".join(positions)
-    
+
     # get player profile scores per squad
     profile_scores_raw = pd.concat(
         map(lambda squadId: connection.make_api_request_limited(
@@ -97,38 +97,51 @@ def getPlayerProfileScoresFromHost(
     error_list = [str(squadId) for squadId in squad_ids if squadId not in profile_scores_raw.squadId.to_list()]
     if len(error_list) > 0:
         print(f"No players played at positions {positions} for iteration {iteration} for following squads:\n\t{', '.join(error_list)}")
-    
+
     # get players
     players = connection.make_api_request_limited(
         url=f"{host}/v5/customerapi/iterations/{iteration}/players",
         method="GET"
     ).process_response(
         endpoint="Players"
-    )[["id", "commonname", "firstname", "lastname", "birthdate", "birthplace", "leg", "idMappings"]]
+    )[["id", "commonname", "firstname", "lastname", "birthdate", "birthplace", "leg", "countryIds", "idMappings"]]
+
+    # only keep first country id for each player
+    country_series = players["countryIds"].explode().groupby(level=0).first()
+    players["countryIds"] = players.index.to_series().map(country_series).astype("float").astype("Int64")
+    players = players.rename(columns={"countryIds": "countryId"})
 
     # unnest mappings
     players = unnest_mappings_df(players, "idMappings").drop(["idMappings"], axis=1).drop_duplicates()
-    
+
     # get scores
     scores = connection.make_api_request_limited(
         url=f"{host}/v5/customerapi/player-profiles",
         method="GET"
     ).process_response(
         endpoint="playerProfiles"
     )[["name"]]
-    
+
     # get iterations
     iterations = getIterationsFromHost(connection=connection, host=host)
-
+
+    # get country data
+    countries = connection.make_api_request_limited(
+        url=f"{host}/v5/customerapi/countries",
+        method="GET"
+    ).process_response(
+        endpoint="KPIs"
+    )
+
     # unnest scorings
     profile_scores = profile_scores_raw.explode("profileScores").reset_index(drop=True)
-    
+
     # unnest dictionary in kpis column
     profile_scores = pd.concat(
         [profile_scores.drop(["profileScores"], axis=1), pd.json_normalize(profile_scores["profileScores"])],
         axis=1
     )
-    
+
     # merge with player scores to ensure all kpis are present
     profile_scores = profile_scores.merge(
         scores,
@@ -137,15 +150,15 @@ def getPlayerProfileScoresFromHost(
         how="outer",
         suffixes=("", "_right")
     )
-    
+
     # get matchShares
     match_shares = profile_scores[
         ["iterationId", "squadId", "playerId", "positions", "playDuration", "matchShare"]].drop_duplicates()
-    
+
     # fill missing values in the "name" column with a default value to ensure players without scorings don't get lost
     if len(profile_scores["name"][profile_scores["name"].isnull()]) > 0:
         profile_scores["name"] = profile_scores["name"].fillna("-1")
-    
+
     # pivot kpi values
     profile_scores = pd.pivot_table(
         profile_scores,
@@ -156,11 +169,11 @@ def getPlayerProfileScoresFromHost(
         fill_value=0,
         dropna=False
     ).reset_index()
-    
+
     # drop "-1" column
     if "-1" in profile_scores.columns:
         profile_scores.drop(["-1"], inplace=True, axis=1)
-    
+
     # merge with playDuration and matchShare
     profile_scores = profile_scores.merge(
         match_shares,
@@ -187,27 +200,33 @@ def getPlayerProfileScoresFromHost(
     ).merge(
         players[[
             "id", "wyscoutId", "heimSpielId", "skillCornerId", "commonname",
-            "firstname", "lastname", "birthdate", "birthplace", "leg"
+            "firstname", "lastname", "birthdate", "birthplace", "countryId", "leg"
         ]].rename(
             columns={"commonname": "playerName"}
         ),
         left_on="playerId",
         right_on="id",
         how="left",
         suffixes=("", "_right")
+    ).merge(
+        countries.rename(columns={"fifaName": "playerCountry"}),
+        left_on="countryId",
+        right_on="id",
+        how="left",
+        suffixes=("", "_right")
     )
-    
+
     # remove NA rows
     profile_scores = profile_scores[profile_scores.iterationId.notnull()]
-    
+
     # fix column types
     profile_scores["squadId"] = profile_scores["squadId"].astype("Int64")
     profile_scores["playerId"] = profile_scores["playerId"].astype("Int64")
     profile_scores["iterationId"] = profile_scores["iterationId"].astype("Int64")
     profile_scores["wyscoutId"] = profile_scores["wyscoutId"].astype("Int64")
     profile_scores["heimSpielId"] = profile_scores["heimSpielId"].astype("Int64")
     profile_scores["skillCornerId"] = profile_scores["skillCornerId"].astype("Int64")
-    
+
     # define column order
     order = [
         "iterationId",
@@ -224,17 +243,18 @@ def getPlayerProfileScoresFromHost(
         "lastname",
         "birthdate",
         "birthplace",
+        "playerCountry",
         "leg",
         "positions",
         "matchShare",
         "playDuration"
     ]
-    
+
     # add kpiNames to order
     order = order + scores.name.to_list()
-    
+
     # select columns
     profile_scores = profile_scores[order]
-    
+
     # return result
     return profile_scores