brlib 0.6.0__tar.gz → 0.7.0__tar.gz

{brlib-0.6.0 → brlib-0.7.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: brlib
-Version: 0.6.0
+Version: 0.7.0
 Summary: A library for collecting baseball statistics from Baseball Reference
 Project-URL: Documentation, https://github.com/john-bieren/brlib/wiki
 Project-URL: GitHub, https://github.com/john-bieren/brlib

{brlib-0.6.0 → brlib-0.7.0}/scripts/refresh_tests.py

@@ -35,6 +35,7 @@ def main() -> None:
 
 def refresh_games(games_dir: Path) -> None:
     """Refreshes expected data for games in `games_dir`."""
+    games_list = []
     for game_id in tqdm(game_test_cases, unit="game"):
         # locate, create target directories
         (original_dir := games_dir / "original" / game_id).mkdir(exist_ok=True)
@@ -57,12 +58,14 @@ def refresh_games(games_dir: Path) -> None:
         game.update_team_names()
         game.update_venue_names()
         game.info.to_csv(updated_dir / "info.csv", index=False)
-        game.batting.to_csv(updated_dir / "batting.csv", index=False)
         game.pitching.to_csv(updated_dir / "pitching.csv", index=False)
-        game.fielding.to_csv(updated_dir / "fielding.csv", index=False)
         game.team_info.to_csv(updated_dir / "team_info.csv", index=False)
         game.linescore.to_csv(updated_dir / "linescore.csv", index=False)
 
+        games_list.append(game)
+    game_set = br.GameSet(games_list)
+    game_set.records.to_csv(games_dir / "records.csv", index=False)
+
 
 def refresh_players(players_dir: Path) -> None:
     """Refreshes expected data for players in `players_dir`."""
@@ -87,7 +90,6 @@ def refresh_players(players_dir: Path) -> None:
         player.update_team_names()
         player.info.to_csv(updated_dir / "info.csv", index=False)
         player.pitching.to_csv(updated_dir / "pitching.csv", index=False)
-        player.salaries.to_csv(updated_dir / "salaries.csv", index=False)
 
 
 def refresh_teams(teams_dir: Path) -> None:
@@ -112,10 +114,7 @@ def refresh_teams(teams_dir: Path) -> None:
         team.update_team_names()
         team.update_venue_names()
         team.info.to_csv(updated_dir / "info.csv", index=False)
-        team.bling.to_csv(updated_dir / "bling.csv", index=False)
-        team.batting.to_csv(updated_dir / "batting.csv", index=False)
         team.pitching.to_csv(updated_dir / "pitching.csv", index=False)
-        team.fielding.to_csv(updated_dir / "fielding.csv", index=False)
 
         teams_list.append(team)
     team_set = br.TeamSet(teams_list)

{brlib-0.6.0 → brlib-0.7.0}/src/brlib/__init__.py

@@ -21,7 +21,7 @@ from .team import Team
 from .team_set import TeamSet
 from .test_connection import test_connection
 
-__version__ = "0.6.0"
+__version__ = "0.7.0"
 
 __all__ = [
     "all_players",

{brlib-0.6.0 → brlib-0.7.0}/src/brlib/_helpers/abbreviations_manager.py

@@ -26,7 +26,7 @@ from .singleton import Singleton
 
 class AbbreviationsManager(Singleton):
     """
-    A wrapper for a DataFrame which contains information on all historical team and
+    A wrapper for a DataFrame that contains information on all historical team and
     franchise abbreviations used by Baseball Reference. Has methods for working with these
     abbreviations. Manages retrieval and caching of the data, loads data on import of brlib.
     """
@@ -146,13 +146,16 @@ class AbbreviationsManager(Singleton):
         """
         abv_rows = self.df.loc[self.df["Team"] == abbreviation]
 
+        # find the row(s) to which the arguments correspond
         if era_adjustment:
             # handle potential overlap of abbreviations (e.g., BAL, 1915)
             potential_franchises = abv_rows["Franchise"].to_numpy()
-            franchise_rows = self.df.loc[self.df["Franchise"].isin(potential_franchises)]
-            matching_franchises = franchise_rows.loc[
-                (franchise_rows["First Year"] <= season) & (franchise_rows["Last Year"] >= season)
-            ]["Franchise"]
+            matching_franchises = self.df.loc[
+                (self.df["Franchise"].isin(potential_franchises))
+                & (self.df["First Year"] <= season)
+                & (self.df["Last Year"] >= season),
+                "Franchise",
+            ]
             correct_rows = abv_rows.loc[abv_rows["Franchise"].isin(matching_franchises)]
             # handle the special case of the 1939 Toledo Crawfords, who changed leagues mid-season
             # these are treated as separate teams and have different abbreviations (TC and TC2)
@@ -162,26 +165,32 @@ class AbbreviationsManager(Singleton):
                 correct_rows = pd.concat([correct_rows, tc_rows], ignore_index=True)
         else:
             # check whether abbreviation is valid for season, if so, pass that row forward
-            mask = (abv_rows["First Year"] <= season) & (abv_rows["Last Year"] >= season)
-            correct_rows = abv_rows.loc[mask]
+            correct_rows = abv_rows.loc[
+                (abv_rows["First Year"] <= season) & (abv_rows["Last Year"] >= season)
+            ]
             assert len(correct_rows) <= 1
 
-        # For each row in correct_rows, find the team row with the shortest year range that
-        # includes season within the same franchise.
+        # For each row in correct_rows, find which team row within the same franchise has the
+        # shortest year range that includes season.
         # This corrects abbreviations for era (if applicable) and also fixes discontinuities.
         # For example, LAA is listed as 1961-present, but CAL and ANA were also used during
         # parts of that time. The rows returned should reflect the abbreviations used during season.
         correct_rows = correct_rows.reset_index(drop=True)
         for i, franchise in enumerate(correct_rows["Franchise"].to_numpy()):
-            franchise_rows = self.df.loc[self.df["Franchise"] == franchise]
-            franchise_rows = franchise_rows.loc[
-                (franchise_rows["First Year"] <= season) & (franchise_rows["Last Year"] >= season)
-            ]
             # for the 1939 Crawfords, skip the normal process to enable the prior workaround
-            if not (season == 1939 and franchise == "PC"):
+            if season == 1939 and franchise == "PC":
+                continue
+            franchise_rows = self.df.loc[
+                (self.df["Franchise"] == franchise)
+                & (self.df["First Year"] <= season)
+                & (self.df["Last Year"] >= season)
+            ]
+            if len(franchise_rows) > 1:  # a discontinuity
                 years_col = franchise_rows["Last Year"] - franchise_rows["First Year"]
                 correct_row = franchise_rows.loc[years_col == years_col.min()]
-                correct_rows.iloc[i] = correct_row.reset_index(drop=True).iloc[0]
+            else:
+                correct_row = franchise_rows
+            correct_rows.iloc[i] = correct_row.reset_index(drop=True).iloc[0]
         return correct_rows
 
     def correct_abvs(self, abbreviation: str, season: int, era_adjustment: bool) -> list[str]:
@@ -198,7 +207,7 @@ class AbbreviationsManager(Singleton):
 
     def all_team_abvs(self, abbreviation: str, season: int) -> list[str]:
         """
-        Returns all team abbreviations used by the franchise which is associated with the team at
+        Returns all team abbreviations used by the franchise that is associated with the team at
         `abbreviation` and `season`, e.g., `("ATH", 2025)` returns `["PHA", "KCA", "OAK", "ATH"]`.
         """
         franchise_abv = self.franchise_abv(abbreviation, season)

{brlib-0.6.0 → brlib-0.7.0}/src/brlib/_helpers/constants.py

@@ -591,7 +591,6 @@ GAME_INFO_DTYPES = {
 }
 
 GAME_BATTING_DTYPES = {
-    "Game": "string",
     "Player": "string",
     "Position": "string",
     "AB": "Int64",
@@ -638,8 +637,6 @@ GAME_BATTING_DTYPES = {
     "2-Out RBI": "Int64",
     "LOB": "Int64",
     "RISP": "string",
-    "Team": "string",
-    "Opponent": "string",
     "Game ID": "string",
     "Player ID": "string",
     "Team ID": "string",
@@ -647,7 +644,6 @@ GAME_BATTING_DTYPES = {
 }
 
 GAME_PITCHING_DTYPES = {
-    "Game": "string",
     "Player": "string",
     "Position": "string",
     "IP": "Float64",
@@ -692,8 +688,6 @@ GAME_PITCHING_DTYPES = {
     "NH": "Int64",
     "PG": "Int64",
     "CNH": "Int64",
-    "Team": "string",
-    "Opponent": "string",
     "Game ID": "string",
     "Player ID": "string",
     "Team ID": "string",
@@ -701,7 +695,6 @@ GAME_PITCHING_DTYPES = {
 }
 
 GAME_FIELDING_DTYPES = {
-    "Game": "string",
     "Player": "string",
     "Position": "string",
     "PO": "Int64",
@@ -723,8 +716,6 @@ GAME_FIELDING_DTYPES = {
     "1B Pick": "Int64",
     "2B Pick": "Int64",
     "3B Pick": "Int64",
-    "Team": "string",
-    "Opponent": "string",
     "Game ID": "string",
     "Player ID": "string",
     "Team ID": "string",
@@ -732,7 +723,6 @@ GAME_FIELDING_DTYPES = {
 }
 
 GAME_TEAM_INFO_DTYPES = {
-    "Game": "string",
     "Team": "string",
     "Score": "Int64",
     "Record": "string",
@@ -745,7 +735,6 @@ GAME_TEAM_INFO_DTYPES = {
 }
 
 GAME_UMP_INFO_DTYPES = {
-    "Game": "string",
     "Umpire": "string",
     "Position": "string",
     "Game ID": "string",
@@ -797,7 +786,6 @@ PLAYER_INFO_DTYPES = {
 }
 
 PLAYER_BLING_DTYPES = {
-    "Player": "string",
     "Season": "string",
     "AS": "Int64",
     "SS": "Int64",
@@ -828,9 +816,7 @@ PLAYER_BLING_DTYPES = {
 }
 
 PLAYER_BATTING_DTYPES = {
-    "Player": "string",
     "Season": "string",
-    "Game Type": "string",
     "Age": "string",
     "Team": "string",
     "League": "string",
@@ -896,14 +882,13 @@ PLAYER_BATTING_DTYPES = {
     "RS%": "Float64",
     "SB%": "Float64",
     "XBT%": "Float64",
+    "Game Type": "string",
     "Player ID": "string",
     "Team ID": "string",
 }
 
 PLAYER_PITCHING_DTYPES = {
-    "Player": "string",
     "Season": "string",
-    "Game Type": "string",
     "Age": "string",
     "Team": "string",
     "League": "string",
@@ -972,14 +957,13 @@ PLAYER_PITCHING_DTYPES = {
     "NH": "Int64",
     "PG": "Int64",
     "CNH": "Int64",
+    "Game Type": "string",
     "Player ID": "string",
     "Team ID": "string",
 }
 
 PLAYER_FIELDING_DTYPES = {
-    "Player": "string",
     "Season": "string",
-    "Game Type": "string",
     "Age": "string",
     "Team": "string",
     "League": "string",
@@ -1010,12 +994,12 @@ PLAYER_FIELDING_DTYPES = {
     "CS%": "Float64",
     "lgCS%": "Float64",
     "Pick": "Int64",
+    "Game Type": "string",
     "Player ID": "string",
     "Team ID": "string",
 }
 
 PLAYER_SALARIES_DTYPES = {
-    "Player": "string",
     "Year": "string",
     "Age": "string",
     "Team": "string",
@@ -1064,8 +1048,6 @@ TEAM_INFO_DTYPES = {
 }
 
 TEAM_BLING_DTYPES = {
-    "Team": "string",
-    "Season": "Int64",
     "Player": "string",
     "AS": "Int64",
     "GG": "Int64",
@@ -1086,9 +1068,6 @@ TEAM_BLING_DTYPES = {
 }
 
 TEAM_BATTING_DTYPES = {
-    "Team": "string",
-    "Season": "Int64",
-    "Game Type": "string",
     "Player": "string",
     "Age": "string",
     "Position": "string",
@@ -1134,14 +1113,12 @@ TEAM_BATTING_DTYPES = {
     "oWAR": "Float64",
     "dWAR": "Float64",
     "oRAR": "Int64",
+    "Game Type": "string",
     "Team ID": "string",
     "Player ID": "string",
 }
 
 TEAM_PITCHING_DTYPES = {
-    "Team": "string",
-    "Season": "Int64",
-    "Game Type": "string",
     "Player": "string",
     "Age": "string",
     "Position": "string",
@@ -1193,14 +1170,12 @@ TEAM_PITCHING_DTYPES = {
     "NH": "Int64",
     "PG": "Int64",
     "CNH": "Int64",
+    "Game Type": "string",
     "Team ID": "string",
     "Player ID": "string",
 }
 
 TEAM_FIELDING_DTYPES = {
-    "Team": "string",
-    "Season": "Int64",
-    "Game Type": "string",
     "Player": "string",
     "Age": "string",
     "G": "Int64",
@@ -1228,6 +1203,7 @@ TEAM_FIELDING_DTYPES = {
     "CS%": "Float64",
     "Pick": "Int64",
     "Pos": "string",
+    "Game Type": "string",
     "Team ID": "string",
     "Player ID": "string",
 }

{brlib-0.6.0 → brlib-0.7.0}/src/brlib/_helpers/inputs.py

@@ -137,7 +137,7 @@ def validate_team_list(team_list: list[str]) -> list[str]:
             write(f'cannot get "{team_id}": {message}')
             continue
 
-        # check home team abbreviation
+        # check abbreviation
         correct_abvs = abv_mgr.correct_abvs(abv, int(season), era_adjustment=False)
         if len(correct_abvs) == 0:  # correct_abvs is a list of length 0 or 1
             write(f'cannot get "{team_id}": {abv} did not play in {season}')

{brlib-0.6.0 → brlib-0.7.0}/src/brlib/_helpers/no_hitter_dicts.py

@@ -26,7 +26,7 @@ from .utils import soup_from_comment, str_between
 
 class NoHitterDicts(Singleton):
     """
-    A wrapper for several dictionaries which contain information about no-hitters.
+    A wrapper for several dictionaries that contain information about no-hitters.
     Contains dictionaries for individual no-hitters, perfect games, or combined no-hitters
     oriented by game, player, or team. Manages retrieval and caching of the data upon use of the
     `populate` method. Until this method is called, the dictionaries are empty.
@@ -125,7 +125,7 @@ class NoHitterDicts(Singleton):
             records,
             columns=("Rk", "Name", "Perfect", "Gcar", "Gtm", "Year", "Date", "Team", "Home/Away"),
         )
-        # remove the header rows which appear every 25 rows
+        # remove the header rows, which appear every 25 rows
         individual_df = individual_df.loc[individual_df["Name"] != "Name"].reset_index(drop=True)
         individual_df["Game Type"] = "R"
         postseason_mask = (
@@ -176,7 +176,7 @@ class NoHitterDicts(Singleton):
             records,
             columns=("Rk", "Year", "Date", "Team", "Home/Away", "Opp", "Rslt", "Name", "Gcar"),
         )
-        # remove the header rows which appear every 25 rows
+        # remove the header rows, which appear every 25 rows
         combined_df = combined_df.loc[combined_df["Name"] != "Name"].reset_index(drop=True)
         combined_df["Game Type"] = "R"
         postseason_mask = (

{brlib-0.6.0 → brlib-0.7.0}/src/brlib/_helpers/utils.py

@@ -11,7 +11,7 @@ from .constants import TEAM_REPLACEMENTS
 
 def str_between(string: str, start: str, end: str, anchor: str = "start") -> str:
     """
-    Returns the substring of `string` which appears between `start` and `end`.
+    Returns the substring of `string` that appears between `start` and `end`.
     `string` must contain `start` and `end`.
 
     If `anchor` is `"start"`, the substring between the first occurrence of `start`
@@ -108,7 +108,7 @@ def convert_numeric_cols(df: pd.DataFrame) -> pd.DataFrame:
             ValueError,  # includes a non-convertable value of a compatible type (e.g., "a")
             TypeError,  # includes a value of an incompatible type (e.g., a list)
         ):
-            # skip columns which cannot be converted
+            # skip columns that cannot be converted
             pass
     return df
 

{brlib-0.6.0 → brlib-0.7.0}/src/brlib/find_asg.py

@@ -18,7 +18,7 @@ from .options import write
 @runtime_typecheck
 def find_asg(seasons: str | list[str] = "ALL") -> list[str]:
     """
-    Returns a list of All-Star Game IDs which can be an input to
+    Returns a list of All-Star Game IDs, which can be an input to
     [`get_games`](https://github.com/john-bieren/brlib/wiki/get_games).
 
     ## Parameters
@@ -26,7 +26,7 @@ def find_asg(seasons: str | list[str] = "ALL") -> list[str]:
     * `seasons`: `str` or `list[str]`, default `"ALL"`
 
         A year, inclusive range of years (e.g., `"2017-2019"`), `"ALL"`, or a list of multiple such
-        inputs which specify the seasons from which to find All-Star Games.
+        inputs that specify the seasons from which to find All-Star Games.
 
     ## Returns
 
@@ -34,7 +34,7 @@ def find_asg(seasons: str | list[str] = "ALL") -> list[str]:
 
     ## Examples
 
-    Seasons which did not have All-Star Games are taken into account:
+    Seasons that did not have All-Star Games are taken into account:
 
     ```
     >>> br.find_asg("2019-2022")

{brlib-0.6.0 → brlib-0.7.0}/src/brlib/find_games.py

@@ -48,22 +48,22 @@ def find_games(
     * `seasons`: `str` or `list[str]`, default `"ALL"`
 
         A year, inclusive range of years (e.g., `"2017-2019"`), `"ALL"`, or a list of multiple such
-        inputs which specify the seasons from which to find games.
+        inputs that specify the seasons from which to find games.
 
     * `opponents`: `str` or `list[str]`, default `"ALL"`
 
-        A valid `teams` input specifying the opponents which `teams` must be facing in returned
+        A valid `teams` input specifying the opponents that `teams` must be facing in returned
         games.
 
     * `dates`: `str` or `list[str]`, default `"ALL"`
 
         A string representing a date in MMDD format as a number (e.g., `"1005"` or `"704"`), an
         inclusive range of such numbers (e.g., `"927-1002"`), `"ALL"`, or a list of multiple such
-        inputs which specify the dates from which games should be found.
+        inputs that specify the dates from which games should be found.
 
     * `home_away`: `str`, default `"ALL"`
 
-        `"HOME"`, `"AWAY"`, or `"ALL"` to specify the role which `teams` should have in returned
+        `"HOME"`, `"AWAY"`, or `"ALL"` to specify the role that `teams` should have in returned
         games.
 
     * `game_type`: `str`, default `"ALL"`
@@ -91,7 +91,8 @@ def find_games(
     ['SEA201907020', 'SEA201907030', 'SEA201907040']
     ```
 
-    Abbreviations can match multiple teams due to era adjustment:
+    Abbreviations can match multiple teams due to [era
+    adjustment](https://github.com/john-bieren/brlib/wiki/Team-Abbreviation-Handling):
 
     ```
     >>> br.find_games(teams="BAL", seasons="1915", dates="825", home_away="home")
@@ -232,7 +233,7 @@ def _find_year_list(
     if game_type == "POST":
         year_set = {y for y in year_set if y not in NO_POSTSEASON_YEARS}
 
-    # filter years to those which could possibly contain a matchup of the teams and opponents
+    # filter years to those that could possibly contain a matchup of the teams and opponents
     if teams != ["ALL"] or opponents != ["ALL"]:
         valid_years = set(all_game_years)
         if teams != ["ALL"]:
@@ -270,8 +271,8 @@ def _find_season_games(
     game_type: str,
 ) -> list[str]:
     """
-    Scrapes an MLB schedule page, and returns the games from that season which
-    match all the other input parameters. Inputs must be uppercase.
+    Scrapes an MLB schedule page and returns the games from that season that match all the other
+    input parameters. Inputs must be uppercase.
     """
     team_set = set(teams)
     opponent_set = set(opponents)
@@ -312,7 +313,7 @@ def _find_season_games(
             links = game.find_all("a", href=True)
             # there should be links to the pages of the away team, home team, and box score
             if len(links) != 3:
-                # skip games which lack box scores
+                # skip games that lack box scores
                 continue
             away_link, home_link, endpoint = [a["href"] for a in links]
             if "previews" in endpoint:

{brlib-0.6.0 → brlib-0.7.0}/src/brlib/find_teams.py

@@ -40,7 +40,7 @@ def find_teams(
     * `seasons`: `str` or `list[str]`, default `"ALL"`
 
         A year, inclusive range of years (e.g., `"2017-2019"`), `"ALL"`, or a list of multiple such
-        inputs which specify the years from which to find teams.
+        inputs that specify the years from which to find teams.
 
     ## Returns
 
@@ -62,7 +62,8 @@ def find_teams(
     ['BBB1948', 'BEG1948', 'CAG1948', 'CBE1948', ...]
     ```
 
-    Abbreviations can match multiple teams due to era adjustment:
+    Abbreviations can match multiple teams due to [era
+    adjustment](https://github.com/john-bieren/brlib/wiki/Team-Abbreviation-Handling):
 
     ```
     >>> br.find_teams("BAL", "1914")

{brlib-0.6.0 → brlib-0.7.0}/src/brlib/game.py

@@ -120,7 +120,7 @@ class Game:
 
     * `linescore`: `pandas.DataFrame`
 
-        Contains the game's linescore, a box score fixture which displays the teams' run totals by
+        Contains the game's linescore, a box score fixture that displays the teams' run totals by
         inning, as well as their total runs, hits, and errors. [See DataFrame
         info](https://github.com/john-bieren/brlib/wiki/DataFrames-Info#gamelinescore)
 
@@ -397,14 +397,13 @@ class Game:
         self.pitching = convert_numeric_cols(self.pitching)
         self.players = list(dict.fromkeys(self.players))
 
-        self.info[["Game", "Game ID", "Home Team ID", "Away Team ID"]] = (
+        self.info[["Game", "Home Team ID", "Away Team ID"]] = (
             self.name,
-            self.id,
             self._home_team_id,
             self._away_team_id,
         )
-        self.batting[["Game", "Game ID"]] = self.name, self.id
-        self.pitching[["Game", "Game ID"]] = self.name, self.id
+        self.batting["Game ID"] = self.id
+        self.pitching["Game ID"] = self.id
         self.batting = self.batting.reset_index(drop=True)
         self.pitching = self.pitching.reset_index(drop=True)
 
@@ -428,7 +427,7 @@ class Game:
 
     def _scrape_info(self, content: Tag, other_info: Tag) -> None:
         """Populates `self.info` with data from `content` and `other_info`."""
-        self.info = pd.DataFrame([self.name], columns=["Game"])
+        self.info = pd.DataFrame([self.id], columns=["Game ID"])
         self.team_info = pd.DataFrame(
             {"Home/Away": ["Away", "Home"], "Game ID": [self.id, self.id]}
         )
@@ -591,17 +590,16 @@ class Game:
 
     def _gather_team_info(self) -> None:
         """Generates `self.team_info`."""
-        self.team_info["Game"] = self.name
-        self.team_info.loc[:, "Team"] = [self._away_team, self._home_team]
-        self.team_info.loc[:, "Team ID"] = [self._away_team_id, self._home_team_id]
-        self.team_info.loc[:, "Score"] = [self._away_score, self._home_score]
+        self.team_info["Team"] = [self._away_team, self._home_team]
+        self.team_info["Team ID"] = [self._away_team_id, self._home_team_id]
+        self.team_info["Score"] = [self._away_score, self._home_score]
 
         if self._winning_team == self._home_team:
-            self.team_info.loc[:, "Result"] = ["Loss", "Win"]
+            self.team_info["Result"] = ["Loss", "Win"]
         elif self._winning_team == self._away_team:
-            self.team_info.loc[:, "Result"] = ["Win", "Loss"]
+            self.team_info["Result"] = ["Win", "Loss"]
         else:
-            self.team_info.loc[:, "Result"] = "Tie"
+            self.team_info["Result"] = "Tie"
 
     def _scrape_other_info(self, other_info: Tag) -> None:
         """Scrapes weather and umpire info from `other_info`."""
@@ -746,12 +744,14 @@ class Game:
         dp_tp = ["DP", "TP"]
         h_df[list(player_stats.values())] = 0
         h_df[dp_tp] = 0
+        # find players with hyphenated names before parsing hyphen-delimited DP/TP player lists
+        hyphenated_names = h_df.loc[h_df["Player"].str.contains("-"), "Player"].to_numpy()
 
         team_totals_mask = h_df["Player"] == "Team Totals"
         footer = table.find("div", {"class": "footer no_hide_long"})
         # [1:] because the first tag is the parent of the others
         for line in footer.find_all("div")[1:]:
-            # skip the divs which contain the fielding and baserunning divs
+            # skip the divs that contain the fielding and baserunning divs
             if "\n" in line.text:
                 continue
             line_str = line.text.replace("\xa0", " ")
@@ -779,6 +779,9 @@ class Game:
             elif stat in dp_tp:
                 total, player_list = players.split(". ", maxsplit=1)
                 h_df.loc[team_totals_mask, stat] = int(total)
+                # distinguish between hyphenated names and delimiters
+                for name in hyphenated_names:
+                    player_list = player_list.replace(name, name.replace("-", "&"))
 
                 for dp_players in player_list.split("; "):
                     if dp_players.rsplit(maxsplit=1)[1].isnumeric():
@@ -787,7 +790,8 @@ class Game:
                     else:
                         number = 1
                     for player in set(dp_players.split("-")):
-                        h_df.loc[h_df["Player"] == player, stat] += number
+                        # revert to hyphenated name
+                        h_df.loc[h_df["Player"] == player.replace("&", "-"), stat] += number
 
         # convert cWPA from percentage to a float
         if "cWPA" in h_df.columns:
@@ -902,23 +906,13 @@ class Game:
             or self._home_team == "Houston Colt .45s"
             and "HoustonColts" in table_id
         ):
-            df[["Team", "Opponent", "Team ID", "Opponent Team ID"]] = (
-                self._home_team,
-                self._away_team,
-                self._home_team_id,
-                self._away_team_id,
-            )
+            df[["Team ID", "Opponent Team ID"]] = self._home_team_id, self._away_team_id
         elif (
             str_remove(self._away_team, " ", "-", ".") in table_id
             or self._away_team == "Houston Colt .45s"
             and "HoustonColts" in table_id
         ):
-            df[["Team", "Opponent", "Team ID", "Opponent Team ID"]] = (
-                self._away_team,
-                self._home_team,
-                self._away_team_id,
-                self._home_team_id,
-            )
+            df[["Team ID", "Opponent Team ID"]] = self._away_team_id, self._home_team_id
         else:
             raise ValueError("home and away teams cannot be found from batting tables")
         return df
@@ -927,7 +921,6 @@ class Game:
         """Copies info and moves fielding stats from `self.batting` to `self.fielding`."""
         self.fielding = self.batting[
             [
-                "Game",
                 "Player",
                 "Player ID",
                 "Position",
@@ -940,8 +933,6 @@ class Game:
                 "PB",
                 "SB",
                 "CS",
-                "Team",
-                "Opponent",
                 "Team ID",
                 "Opponent Team ID",
                 "Game ID",
@@ -958,7 +949,7 @@ class Game:
         self.fielding = self.fielding[played_defense_mask]
         self.fielding = self.fielding.reset_index(drop=True)
 
-        # some old games have an asterisk in PO team total rows (e.g., SLN190106150)
+        # some old games have an asterisk in PO team total rows (e.g., SLN190106150, BSN191107122)
         self.fielding.loc[self.fielding["PO"] == "*", "PO"] = pd.NA
 
         # remove pitchers who did not hit
@@ -1064,9 +1055,9 @@ class Game:
         """Populates `self.ump_info`."""
         self.ump_info = pd.melt(
             self.info,
-            id_vars=["Game", "Game ID"],
+            id_vars=["Game ID"],
             value_vars=["HP Ump", "1B Ump", "2B Ump", "3B Ump", "LF Ump", "RF Ump"],
         )
         self.ump_info = self.ump_info.rename(columns={"variable": "Position", "value": "Umpire"})
-        self.ump_info = self.ump_info.loc[~self.ump_info["Umpire"].isnull()]
+        self.ump_info = self.ump_info[~self.ump_info["Umpire"].isnull()].reset_index(drop=True)
         self.ump_info["Position"] = self.ump_info["Position"].str.replace(" Ump", "")