Alternative Lahman DB route

pybaseball/__init__.py

@@ -7,31 +7,31 @@
 from .teamid_lookup import team_ids
 from .statcast import statcast, statcast_single_game
 from .statcast_pitcher import (
-	statcast_pitcher,
-	statcast_pitcher_exitvelo_barrels,
-	statcast_pitcher_expected_stats,
-	statcast_pitcher_pitch_arsenal,
-	statcast_pitcher_arsenal_stats,
-	statcast_pitcher_percentile_ranks,
-	statcast_pitcher_spin_dir_comp
+    statcast_pitcher,
+    statcast_pitcher_exitvelo_barrels,
+    statcast_pitcher_expected_stats,
+    statcast_pitcher_pitch_arsenal,
+    statcast_pitcher_arsenal_stats,
+    statcast_pitcher_percentile_ranks,
+    statcast_pitcher_spin_dir_comp,
 )
 from .statcast_batter import (
-	statcast_batter,
-	statcast_batter_exitvelo_barrels,
-	statcast_batter_expected_stats,
-	statcast_batter_percentile_ranks,
-	statcast_batter_pitch_arsenal,
-    statcast_batter_bat_tracking
+    statcast_batter,
+    statcast_batter_exitvelo_barrels,
+    statcast_batter_expected_stats,
+    statcast_batter_percentile_ranks,
+    statcast_batter_pitch_arsenal,
+    statcast_batter_bat_tracking,
 )
 from .statcast_running import statcast_sprint_speed, statcast_running_splits
 from .statcast_fielding import (
-	statcast_outs_above_average,
-	statcast_outfield_directional_oaa,
-	statcast_outfield_catch_prob,
-	statcast_outfielder_jump,
-	statcast_catcher_poptime,
-	statcast_catcher_framing,
-	statcast_fielding_run_value
+    statcast_outs_above_average,
+    statcast_outfield_directional_oaa,
+    statcast_outfield_catch_prob,
+    statcast_outfielder_jump,
+    statcast_catcher_poptime,
+    statcast_catcher_framing,
+    statcast_fielding_run_value,
 )
 from .league_batting_stats import batting_stats_bref
 from .league_batting_stats import batting_stats_range
@@ -78,8 +78,9 @@
 from .lahman import salaries
 from .lahman import schools
 from .lahman import series_post
-from .lahman import teams_core
-from .lahman import teams_upstream
+from .lahman import teams
+
+# from .lahman import teams_upstream  Not part of Lahman
 from .lahman import teams_franchises
 from .lahman import teams_half
 from .lahman import download_lahman
@@ -98,7 +99,12 @@
 from .plotting import spraychart
 from .plotting import plot_teams
 from .plotting import plot_strike_zone
-from .datasources.fangraphs import (fg_batting_data, fg_pitching_data, fg_team_batting_data, fg_team_fielding_data,
-                                    fg_team_pitching_data)
+from .datasources.fangraphs import (
+    fg_batting_data,
+    fg_pitching_data,
+    fg_team_batting_data,
+    fg_team_fielding_data,
+    fg_team_pitching_data,
+)
 from .split_stats import get_splits
 from .version import __version__

pybaseball/lahman.py

@@ -8,11 +8,12 @@
 
 from . import cache
 
-url = "https://github.com/chadwickbureau/baseballdatabank/archive/master.zip"
-base_string = "baseballdatabank-master"
+url = "https://github.com/jmaslek/LahmanDatabase/archive/refs/heads/main/baseballdb.zip"
+base_string = "LahmanDatabase-main/baseballdb"
 
 _handle = None
 
+
 def get_lahman_zip() -> Optional[ZipFile]:
     # Retrieve the Lahman database zip file, returns None if file already exists in cwd.
     # If we already have the zip file, keep re-using that.
@@ -25,6 +26,7 @@ def get_lahman_zip() -> Optional[ZipFile]:
         _handle = ZipFile(BytesIO(s.content))
     return _handle
 
+
 def download_lahman():
     # download entire lahman db to present working directory
     z = get_lahman_zip()
@@ -34,103 +36,135 @@ def download_lahman():
         # this way we'll now start using the extracted zip directory
         # instead of the session ZipFile object
 
-def _get_file(tablename: str, quotechar: str = "'") -> pd.DataFrame:
+
+def _get_file(tablename: str, quotechar: str = "'", encoding="latin1") -> pd.DataFrame:
     z = get_lahman_zip()
-    f = f'{base_string}/{tablename}'
+    f = f"{base_string}/{tablename}"
     data = pd.read_csv(
         f"{path.join(cache.config.cache_directory, f)}" if z is None else z.open(f),
         header=0,
-        sep=',',
-        quotechar=quotechar
+        sep=",",
+        quotechar=quotechar,
+        encoding=encoding,
     )
     return data
 
 
 # do this for every table in the lahman db so they can exist as separate functions
 def parks() -> pd.DataFrame:
-    return _get_file('core/Parks.csv')
+    return _get_file("Parks.csv")
+
 
 def all_star_full() -> pd.DataFrame:
-    return _get_file("core/AllstarFull.csv")
+    return _get_file("AllstarFull.csv")
+
 
 def appearances() -> pd.DataFrame:
-    return _get_file("core/Appearances.csv")
+    return _get_file("Appearances.csv")
+
 
 def awards_managers() -> pd.DataFrame:
-    return _get_file("contrib/AwardsManagers.csv")
+    return _get_file("AwardsManagers.csv")
+
 
 def awards_players() -> pd.DataFrame:
-    return _get_file("contrib/AwardsPlayers.csv")
+    return _get_file("AwardsPlayers.csv")
+
 
 def awards_share_managers() -> pd.DataFrame:
-    return _get_file("contrib/AwardsShareManagers.csv")
+    return _get_file("AwardsShareManagers.csv")
+
 
 def awards_share_players() -> pd.DataFrame:
-    return _get_file("contrib/AwardsSharePlayers.csv")
+    return _get_file("AwardsSharePlayers.csv")
+
 
 def batting() -> pd.DataFrame:
-    return _get_file("core/Batting.csv")
+    return _get_file("Batting.csv")
+
 
 def batting_post() -> pd.DataFrame:
-    return _get_file("core/BattingPost.csv")
+    return _get_file("BattingPost.csv")
+
 
 def college_playing() -> pd.DataFrame:
-    return _get_file("contrib/CollegePlaying.csv")
+    return _get_file("CollegePlaying.csv")
+
 
 def fielding() -> pd.DataFrame:
-    return _get_file("core/Fielding.csv")
+    return _get_file("Fielding.csv")
+
 
 def fielding_of() -> pd.DataFrame:
-    return _get_file("core/FieldingOF.csv")
+    return _get_file("FieldingOF.csv")
+
 
 def fielding_of_split() -> pd.DataFrame:
-    return _get_file("core/FieldingOFsplit.csv")
+    return _get_file("FieldingOFsplit.csv")
+
 
 def fielding_post() -> pd.DataFrame:
-    return _get_file("core/FieldingPost.csv")
+    return _get_file("FieldingPost.csv")
+
 
 def hall_of_fame() -> pd.DataFrame:
-    return _get_file("contrib/HallOfFame.csv")
+    return _get_file("HallOfFame.csv")
+
 
 def home_games() -> pd.DataFrame:
-    return _get_file("core/HomeGames.csv")
+    return _get_file("HomeGames.csv")
+
 
 def managers() -> pd.DataFrame:
-    return _get_file("core/Managers.csv")
+    return _get_file("Managers.csv")
+
 
 def managers_half() -> pd.DataFrame:
-    return _get_file("core/ManagersHalf.csv")
+    return _get_file("ManagersHalf.csv")
+
 
 def master() -> pd.DataFrame:
     # Alias for people -- the new name for master
     return people()
 
+
 def people() -> pd.DataFrame:
-    return _get_file("core/People.csv")
+    return _get_file("People.csv")
+
 
 def pitching() -> pd.DataFrame:
-    return _get_file("core/Pitching.csv")
+    return _get_file("Pitching.csv")
+
 
 def pitching_post() -> pd.DataFrame:
-    return _get_file("core/PitchingPost.csv")
+    return _get_file("PitchingPost.csv")
+
 
 def salaries() -> pd.DataFrame:
-    return _get_file("contrib/Salaries.csv")
+    return _get_file("Salaries.csv")
+
 
 def schools() -> pd.DataFrame:
-    return _get_file("contrib/Schools.csv", quotechar='"')  # different here bc of doublequotes used in some school names
+    return _get_file(
+        "Schools.csv", quotechar='"'
+    )  # different here bc of doublequotes used in some school names
+
 
 def series_post() -> pd.DataFrame:
-    return _get_file("core/SeriesPost.csv")
+    return _get_file("SeriesPost.csv")
+
 
-def teams_core() -> pd.DataFrame:
-    return _get_file("core/Teams.csv")
+def teams() -> pd.DataFrame:
+    return _get_file("Teams.csv")
+
+
+# def teams_upstream() -> pd.DataFrame:
+#     return _get_file("Teams.csv") # manually maintained file
 
-def teams_upstream() -> pd.DataFrame:
-    return _get_file("upstream/Teams.csv") # manually maintained file
 
 def teams_franchises() -> pd.DataFrame:
-    return _get_file("core/TeamsFranchises.csv")
+    return _get_file("TeamsFranchises.csv")
+
 
 def teams_half() -> pd.DataFrame:
-    return _get_file("core/TeamsHalf.csv")
+    return _get_file("TeamsHalf.csv")