hotfix on parse_statsbomb_data.py

Hotfix on an edge case where the GSIS Player ID is not available for this player for some reason.
sportsdataverse · Apr 1, 2024 · c3dcefb · c3dcefb
1 parent dfbd25c
commit c3dcefb
Show file tree

Hide file tree

Showing 4 changed files with 10 additions and 7 deletions.
diff --git a/.github/workflows/update_statsbomb_data_csv.yml b/.github/workflows/update_statsbomb_data_csv.yml
@@ -14,7 +14,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.10"]
+        python-version: ["3.12"]
 
     steps:
       - uses: actions/checkout@v3

diff --git a/.github/workflows/update_statsbomb_data_parquet.yml b/.github/workflows/update_statsbomb_data_parquet.yml
@@ -14,7 +14,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.10"]
+        python-version: ["3.12"]
 
     steps:
       - uses: actions/checkout@v3

diff --git a/check_data_advalibility.py b/check_data_advalibility.py
@@ -18,7 +18,7 @@
 )
 
 
-def check_data_advalibility(
+def check_data_availability(
     check_csv: bool = False,
     check_parquet: bool = False,
     check_all_seasons: bool = True
@@ -123,12 +123,12 @@ def check_data_advalibility(
             "files, or the `.parquet` files."
         )
     elif csv_flag is True:
-        check_data_advalibility(
+        check_data_availability(
             check_csv=True,
             check_all_seasons=check_all_seasons
         )
     elif parquet_flag is True:
-        check_data_advalibility(
+        check_data_availability(
             check_parquet=True,
             check_all_seasons=check_all_seasons
         )

diff --git a/parse_statsbomb_data.py b/parse_statsbomb_data.py
@@ -226,7 +226,10 @@ def parse_statsbomb_amf_tracking_data(json_data: dict):
             position_code = player["player"]["position_code"]
             player_name = player["player"]["name"]
             player_jersey_number = player["player"]["jersey_number"]
-            gsis_player_id = player["player"]["gsis_player_id"]
+            try:
+                gsis_player_id = player["player"]["gsis_player_id"]
+            except:
+                gsis_player_id = None
             on_camera_ratio = player["on_camera_ratio"]
 
             row_df = pd.DataFrame(player["steps"])
@@ -410,7 +413,7 @@ def get_statsbomb_tracking_data(season: int):
 
 if __name__ == "__main__":
     print("starting up")
-    for i in range(2018, 2024):
+    for i in range(2016, 2017):
         get_statsbomb_tracking_data(i)
 
     # get_statsbomb_tracking_data(2019)