add interface to raw jsons

Philip-A7 · Sep 10, 2020 · de32c70 · de32c70
1 parent b11440f
commit de32c70
Show file tree

Hide file tree

Showing 17 changed files with 30 additions and 18 deletions.
diff --git a/README.md b/README.md
@@ -4,7 +4,7 @@
 
 #### Support: [email protected]
 
-#### Updated January 15, 2020.
+#### Updated September 10, 2020.
 
 This repository is a Python package to easily stream StatsBomb data into Python using your log in credentials for the API or free data from our GitHub page. **API access is for paying customers only**
 
@@ -491,7 +491,6 @@ grouped_events["dribbles"]
 </table>
 
 ```
-
 # if you want to store all events in a given competition on a single non tidy dataframe
 events = sb.competition_events(
     country="Germany",
@@ -648,3 +647,22 @@ grouped_events["dribbles"]
 </table>
 
 
+```
+# alternatively, entities can be accessed as python dictionaries serving as an interface to raw jsons and without performing any preprocessing
+
+sb.competitions(fmt="dict")
+
+sb.matches(competition_id=9, season_id=42, fmt="dict")
+
+sb.lineups(match_id=303299, fmt="dict")
+
+sb.events(303299, fmt="dict")
+
+sb.competition_events(
+    country="Germany",
+    division= "1. Bundesliga",
+    season="2019/2020",
+    gender="male",
+    fmt="dict"
+)
+```
diff --git a/doc/LICENSE.pdf b/doc/LICENSE.pdf
diff --git a/doc/Open Data Competitions v2.0.0.pdf b/doc/Open Data Competitions v2.0.0.pdf
diff --git a/doc/Open Data Events v4.0.0.pdf b/doc/Open Data Events v4.0.0.pdf
diff --git a/doc/Open Data Lineups v2.0.0.pdf b/doc/Open Data Lineups v2.0.0.pdf
diff --git a/doc/Open Data Matches v3.0.0.pdf b/doc/Open Data Matches v3.0.0.pdf
diff --git a/doc/StatsBomb Open Data Specification v1.1.pdf b/doc/StatsBomb Open Data Specification v1.1.pdf
diff --git a/setup.py b/setup.py
diff --git a/statsbombpy/__init__.py b/statsbombpy/__init__.py
diff --git a/statsbombpy/api_client.py b/statsbombpy/api_client.py
diff --git a/statsbombpy/config.py b/statsbombpy/config.py
diff --git a/statsbombpy/entities.py b/statsbombpy/entities.py
diff --git a/statsbombpy/helpers.py b/statsbombpy/helpers.py
diff --git a/statsbombpy/public.py b/statsbombpy/public.py
diff --git a/statsbombpy/sb.py b/statsbombpy/sb.py
@@ -74,9 +74,9 @@ def events(
         events = api_client.events(match_id, creds)
     else:
         events = public.events(match_id)
-    events = filter_and_group_events(events, filters, fmt, flatten)
 
     if fmt == "dataframe":
+        events = filter_and_group_events(events, filters, fmt, flatten)
         for ev_type, evs in events.items():
             events[ev_type] = pd.DataFrame(evs)
         if split is False:
@@ -97,18 +97,18 @@ def competition_events(
 
     c = competitions(creds)[country, division, season, gender]
 
-    events_call = partial(
-        events,
-        split=True,
-        filters=filters,
-        fmt="json",
-        flatten=fmt == "dataframe",
-        creds=creds,
-    )
+    events_call = partial(events, fmt="json", creds=creds,)
     with Pool(PARALLELL_CALLS_NUM) as p:
         matches_events = p.map(
             events_call, matches(c["competition_id"], c["season_id"], creds)
         )
+        matches_events = map(
+            lambda events: filter_and_group_events(
+                events, filters, fmt, fmt == "dataframe"
+            ),
+            matches_events,
+        )
+
     competition_events = reduce_events(matches_events, fmt)
     if fmt == "dataframe" and split is False:
         competition_events = pd.concat(

diff --git a/tests/__init__.py b/tests/__init__.py
diff --git a/tests/statsbombpy_test/test_sb.py b/tests/statsbombpy_test/test_sb.py
@@ -50,11 +50,7 @@ def test_events(self):
         self.assertIsInstance(events["shots"], pd.DataFrame)
 
         events = sb.events(match_id=7562, fmt="json")
-        self.assertIsInstance(events["shots"], list)
-        self.assertIsInstance(events["shots"][0], dict)
-
-        shots = sb.events(match_id=7562, filters={"type": "Shot"}, fmt="json")["shots"]
-        self.assertSetEqual({"Shot"}, set(map(lambda s: s["type"]["name"], shots)))
+        self.assertIsInstance(events, dict)
 
         events = sb.events(match_id=7562, creds={})
         self.assertIsInstance(events, pd.DataFrame)
@@ -79,8 +75,6 @@ def test_competition_events(self):
             season="2019/2020",
             fmt="json",
         )
-        self.assertIsInstance(events["shots"], list)
-        self.assertIsInstance(events["shots"][0], dict)
 
 
 if __name__ == "__main__":