brlib 0.1.0__tar.gz → 0.2.0__tar.gz

{brlib-0.1.0 → brlib-0.2.0}/.github/workflows/test.yml

@@ -2,10 +2,11 @@ name: Tests
 
 on: 
   push:
-    branches: '**'
+    branches:
+      - '**'
   schedule:
     # run at 12 UTC, hopefully after BR's daily in-season updates
-    # run weekly because any more would be overkill
+    # run weekly, because anything more would be overkill
     - cron: '0 12 * * 6'
 
 jobs:

{brlib-0.1.0 → brlib-0.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: brlib
-Version: 0.1.0
+Version: 0.2.0
 Summary: A library for collecting baseball statistics from Baseball Reference
 Project-URL: Homepage, https://github.com/john-bieren/brlib
 Project-URL: Documentation, https://github.com/john-bieren/brlib/wiki

{brlib-0.1.0 → brlib-0.2.0}/src/brlib/__init__.py

@@ -13,7 +13,7 @@ from .player_set import PlayerSet
 from .team import Team
 from .team_set import TeamSet
 
-__version__ = "0.1.0"
+__version__ = "0.2.0"
 
 __all__ = [
     "all_major_leaguers",

{brlib-0.1.0 → brlib-0.2.0}/src/brlib/_helpers/abbreviations_manager.py

@@ -121,7 +121,7 @@ class AbbreviationsManager(Singleton):
         Can return an empty DataFrame if there is no match.
 
         If `era_adjustment` is True, the return DataFrame will contain the row associated with
-        `abbrevation`'s franchise during `season` even if the abbreviation is not correct.
+        `abbreviation`'s franchise during `season` even if the abbreviation is not correct.
         For example, `self._find_correct_teams("FLA", 2025, True)` returns the `MIA` team row.
         There can be multiple rows in the return DataFrame if an abbreviation, e.g. `BAL`,
         is valid during a season, e.g. 1915, and is also associated with a franchise that

{brlib-0.1.0 → brlib-0.2.0}/src/brlib/_helpers/constants.py

@@ -58,11 +58,11 @@ DATE_REGEX = re.compile("^[0-1]?[0-9][0-3][0-9]$")
 DATE_RANGE_REGEX = re.compile("^[0-1]?[0-9][0-3][0-9]-[0-1]?[0-9][0-3][0-9]$")
 PLAYER_ID_REGEX = re.compile("^[a-z.'_]{3,7}[0-9]{2}$")
 SCHEDULE_TAG_REGEX = re.compile("^all_[0-9]")
-GAME_URL_REGEX = re.compile(r"https:\/\/www\.baseball-reference\.com\/boxes\/[A-Z1-2]{2,3}\/[A-Z1-2]{2,3}[0-9]{4}[0-1][0-9][0-3][0-9][0-3]\.shtml")
-ALLSTAR_GAME_URL_REGEX = re.compile(r"https:\/\/www\.baseball-reference\.com\/allstar\/[1-2][0-9]{3}-allstar-game-?[1-2]?\.shtml")
-PLAYER_URL_REGEX = re.compile(r"https:\/\/www\.baseball-reference\.com\/players\/[a-z]\/[a-z.'_]{3,7}[0-9]{2}\.shtml")
-TEAM_URL_REGEX = re.compile(r"https:\/\/www\.baseball-reference\.com\/teams\/[A-Z1-4]{2,3}\/[1-2][0-9]{3}\.shtml")
-SB_ATTEMPT_REGEX = re.compile(r"^(?P<base>2nd base|3rd base|Home) (?:off|by) (?P<pitcher>\D+)\/(?P<catcher>\D+)(?P<times>[0-9]?)$")
+GAME_URL_REGEX = re.compile(r"https://www\.baseball-reference\.com/boxes/[A-Z1-2]{2,3}/[A-Z1-2]{2,3}[0-9]{4}[0-1][0-9][0-3][0-9][0-3]\.shtml")
+ALLSTAR_GAME_URL_REGEX = re.compile(r"https://www\.baseball-reference\.com/allstar/[1-2][0-9]{3}-allstar-game-?[1-2]?\.shtml")
+PLAYER_URL_REGEX = re.compile(r"https://www\.baseball-reference\.com/players/[a-z]/[a-z.'_]{3,7}[0-9]{2}\.shtml")
+TEAM_URL_REGEX = re.compile(r"https://www\.baseball-reference\.com/teams/[A-Z1-4]{2,3}/[1-2][0-9]{3}\.shtml")
+SB_ATTEMPT_REGEX = re.compile(r"^(?P<base>2nd base|3rd base|Home) (?:off|by) (?P<pitcher>\D+)/(?P<catcher>\D+)(?P<times>[0-9]?)$")
 PICKOFF_REGEX = re.compile(r"^(?P<base>1st base|2nd base|3rd base|Home) by (?P<pitcher>\D+)(?P<times>[0-9]?)$")
 
 # old names for teams (which have box scores) that didn't relocate
@@ -106,54 +106,52 @@ RANGE_TEAM_REPLACEMENTS = (
     (1901, 1960, "Washington Senators", "Washington Nationals (1901-1960)")
 )
 
-# old names for stadiums
+# map all names of a venue to its best known name, or current name, if applicable
 VENUE_REPLACEMENTS = {
-    "Angel Stadium of Anaheim": "Anaheim Stadium",
-    "Edison Field": "Anaheim Stadium",
+    "Miller Park": "American Family Field",
+    "Anaheim Stadium": "Angel Stadium of Anaheim",
+    "Edison Field": "Angel Stadium of Anaheim",
     "BB&T Park": "Bowman Field",
     "Muncy Bank Ballpark": "Bowman Field",
     "Journey Bank Ballpark": "Bowman Field",
+    "3Com Park": "Candlestick Park",
     "Bank One Ballpark": "Chase Field",
     "White Sox Park": "Comiskey Park I",
-    "U.S. Cellular Field": "Comiskey Park II",
-    "Guaranteed Rate Field": "Comiskey Park II",
-    "Rate Field": "Comiskey Park II",
     "Mile High Stadium": "Coors Field",
     "Redland Field": "Crosley Field",
     "Enron Field": "Daikin Park",
     "Minute Maid Park": "Daikin Park",
-    "The Ballpark in Arlington": "Globe Life Park",
-    "Ameriquest Field": "Globe Life Park",
-    "Rangers Ballpark in Arlington": "Globe Life Park",
-    "Globe Life Park in Arlington": "Globe Life Park",
-    "Sun Life Stadium": "Hard Rock Stadium",
-    "Land Shark Stadium": "Hard Rock Stadium",
-    "Dolphin Stadium": "Hard Rock Stadium",
-    "Dolphins Stadium": "Hard Rock Stadium",
-    "Pro Player Stadium": "Hard Rock Stadium",
+    "The Ballpark in Arlington": "Globe Life Park in Arlington",
+    "Ameriquest Field": "Globe Life Park in Arlington",
+    "Rangers Ballpark in Arlington": "Globe Life Park in Arlington",
+    "Comiskey Park II": "Rate Field",
+    "U.S. Cellular Field": "Rate Field",
+    "Guaranteed Rate Field": "Rate Field",
     "Joe Robbie Stadium": "Hard Rock Stadium",
+    "Pro Player Stadium": "Hard Rock Stadium",
+    "Dolphins Stadium": "Hard Rock Stadium",
+    "Dolphin Stadium": "Hard Rock Stadium",
+    "Land Shark Stadium": "Hard Rock Stadium",
+    "Sun Life Stadium": "Hard Rock Stadium",
     "Royals Stadium": "Kauffman Stadium",
-    "loanDepot park": "Marlins Park",
-    "American Family Field": "Miller Park",
-    "Municipal Stadium": "Oakland Coliseum",
-    "Oakland-Alameda County Coliseum": "Oakland Coliseum",
-    "Network Associates Coliseum": "Oakland Coliseum",
-    "McAfee Coliseum": "Oakland Coliseum",
-    "O.co Coliseum": "Oakland Coliseum",
-    "RingCentral Coliseum": "Oakland Coliseum",
-    "AT&T Park": "Oracle Park",
-    "SBC Park": "Oracle Park",
+    "Marlins Park": "loanDepot park",
+    "Oakland Coliseum": "Oakland-Alameda County Coliseum",
+    "Network Associates Coliseum": "Oakland-Alameda County Coliseum",
+    "McAfee Coliseum": "Oakland-Alameda County Coliseum",
+    "O.co Coliseum": "Oakland-Alameda County Coliseum",
+    "RingCentral Coliseum": "Oakland-Alameda County Coliseum",
     "Pacific Bell Park": "Oracle Park",
-    "3Com Park": "Oracle Park",
+    "SBC Park": "Oracle Park",
+    "AT&T Park": "Oracle Park",
     "Jacobs Field": "Progressive Field",
     "Cinergy Field": "Riverfront Stadium",
     "SkyDome": "Rogers Centre",
-    "Jack Murphy Stadium": "San Diego Stadium",
-    "Qualcomm Stadium": "San Diego Stadium",
+    "San Diego Stadium": "Jack Murphy Stadium",
+    "Qualcomm Stadium": "Jack Murphy Stadium",
     "Connie Mack Stadium": "Shibe Park",
+    "Safeco Field": "T-Mobile Park",
     "Navin Field": "Tiger Stadium",
     "Briggs Stadium": "Tiger Stadium",
-    "Safeco Field": "T-Mobile Park",
     "SunTrust Park": "Truist Park",
     "Weeghman Park": "Wrigley Field",
     "Cubs Park": "Wrigley Field",
@@ -234,7 +232,24 @@ MISSING_SEASONS_DICT = {
     1940: {"JRC"}
 }
 
-# for distniguishing between league and team abbreviations when processing player career totals
+# some games need their winners altered due to forfeits (https://www.retrosheet.org/forfeits.htm)
+FORFEITED_GAME_WINNERS = {
+    "NY1190105130": "New York Giants",
+    "DET190105310": "Detroit Tigers",
+    "CLE190107230": "Washington Senators",
+    "PIT190508050": "Pittsburgh Pirates",
+    "NYA190609032": "New York Highlanders",
+    "SLN190710051": "St. Louis Cardinals",
+    "NY1190910042": "New York Giants",
+    "CHN191607180": "Brooklyn Robins",
+    "CHA191709090": "Chicago White Sox",
+    "WS1194108150": "Boston Red Sox",
+    "NY1194209262": "Boston Braves",
+    "WS2197109300": "New York Yankees",
+    "CLE197406040": "Texas Rangers"
+}
+
+# for distinguishing between league and team abbreviations when processing player career totals
 LEAGUE_ABVS = {
     "WS", "NL", "AL", "NNL", "NN2", "NAL", "ECL", "ANL",
     "EWL", "NSL", "FL", "AA", "PL", "UA", "NA"
@@ -316,12 +331,11 @@ GAME_INFO_COLS = (
     "Innings",
     "Field Condition",
     "Temperature",
-    "Windspeed",
+    "Wind Speed",
     "Wind Direction",
     "Weather",
     "Precipitation",
-    "Game Type",
-    "Doubleheader"
+    "Game Type"
 )
 
 GAME_BATTING_COLS = (
@@ -483,12 +497,6 @@ GAME_TEAM_INFO_COLS = (
     "Game ID"
 )
 
-GAME_UMP_INFO_COLS = (
-    "Game ID",
-    "Position",
-    "Umpire"
-)
-
 PLAYER_INFO_COLS = (
     "Player",
     "Player ID",
@@ -764,6 +772,7 @@ PLAYER_FIELDING_COLS = (
     "CS%",
     "lgCS%",
     "Pick",
+    "Salary",
     "AS",
     "GG",
     "SS",
@@ -789,7 +798,7 @@ TEAM_INFO_COLS = (
     "General Manager",
     "Farm Director",
     "Scouting Director",
-    "Ballpark",
+    "Venue",
     "Attendance",
     "Attendance Rank",
     "Multi-Year Batting Park Factor",

{brlib-0.1.0 → brlib-0.2.0}/src/brlib/_helpers/no_hitter_dicts.py

@@ -199,12 +199,12 @@ class NoHitterDicts(Singleton):
                 player_id_column.append(player_id)
             elif href.startswith("/boxes"):
                 game_id = str_between(href, "/", ".", anchor="end")
-                # filter out links to non-existant pages
+                # filter out links to non-existent pages
                 if game_id[:-9] not in BML_TEAM_ABVS:
                     game_id_column.append(game_id)
 
         combined_df["Player ID"] = player_id_column
-        combined_df["Game ID"] = combined_df["Game ID"].astype("object")
+        combined_df["Game ID"] = combined_df["Game ID"].astype("object") # cast to nullable dtype
         combined_df.loc[
             (~combined_df["Team"].isin(BML_TEAM_ABVS)) &
             (combined_df["Year"].astype(int) >= FIRST_GAMES_YEAR),

{brlib-0.1.0 → brlib-0.2.0}/src/brlib/_helpers/utils.py

@@ -3,10 +3,11 @@
 """Defines utility functions used throughout the codebase."""
 
 import functools
+import typing
 from collections.abc import Callable
 from datetime import datetime
 from types import UnionType
-from typing import Any, get_args, get_origin, get_type_hints
+from typing import Any
 
 import pandas as pd
 from bs4 import BeautifulSoup as bs
@@ -18,7 +19,7 @@ from tqdm import tqdm
 def report_on_exc(resp_index: int = 1) -> Callable[..., Any]:
     """
     Prints the URL of a page which causes an exception.
-    `resp_index` is the index of the decorated function's Response arugment which
+    `resp_index` is the index of the decorated function's Response argument which
     corresponds to the offending page.
     """
     def decorator(func: Callable[..., Any]) -> Callable[..., Any]:
@@ -40,7 +41,7 @@ def runtime_typecheck(func: Callable[..., Any]) -> Callable[..., Any]:
     Raises a TypeError at runtime if values passed to the function
     do not match its type annotations.
     """
-    hints = get_type_hints(func)
+    hints = typing.get_type_hints(func)
 
     @functools.wraps(func)
     def wrapper(*args: Any, **kwargs: Any) -> Any:
@@ -61,11 +62,11 @@ def is_type(value: Any, expected_type: type) -> bool:
     if expected_type == Any:
         return True
 
-    origin = get_origin(expected_type)
+    origin = typing.get_origin(expected_type)
     if origin is None:
         return isinstance(value, expected_type)
 
-    args = get_args(expected_type)
+    args = typing.get_args(expected_type)
     if origin is UnionType:
         return any(is_type(value, arg) for arg in args)
 
@@ -97,10 +98,10 @@ def str_between(string: str, start: str, end: str, anchor: str = "start") -> str
     Returns the substring of `string` which appears between `start` and `end`.
     `string` must contain `start` and `end`.
 
-    If `anchor` == "start", the substring between the first occurrence of `start`
+    If `anchor` == `"start"`, the substring between the first occurrence of `start`
     and the first subsequent occurrence of `end` will be returned.
 
-    If `anchor` == "end", the substring between the final occurrence of `end`
+    If `anchor` == `"end"`, the substring between the final occurrence of `end`
     and the final prior occurrence of `start` will be returned.
     """
     if start not in string:
@@ -126,7 +127,7 @@ def clean_spaces(string: str) -> str:
 
 def reformat_date(string_date: str) -> str:
     """
-    Converts `string_date` of "MM DD, YYYY" to "YY-MM-DD" for formatting consistency.
+    Converts `string_date` of "Month DD, YYYY" to "YY-MM-DD" for formatting consistency.
     If `string_date` does not match this format, an empty string will be returned.
     """
     try:
@@ -139,7 +140,7 @@ def reformat_date(string_date: str) -> str:
     day = f"0{day}" if day < 10 else day
     return f"{date.year}-{month}-{day}"
 
-def soup_from_comment(tag: Tag, only_if_table: bool = False) -> bs | Tag:
+def soup_from_comment(tag: Tag, only_if_table: bool) -> bs | Tag:
     """
     Returns contents from the first comment within `tag`.
     If `tag` does not include a table and `only_if_table` == True, returns `tag`.
@@ -153,7 +154,7 @@ def soup_from_comment(tag: Tag, only_if_table: bool = False) -> bs | Tag:
     except (IndexError, ValueError):
         return tag
 
-def scrape_player_ids(table: bs) -> list[str]:
+def scrape_player_ids(table: bs | Tag) -> list[str]:
     """Returns player IDs from anchor tags in `table`."""
     player_id_column = []
     for row in table.find_all("a", href=True):

{brlib-0.1.0 → brlib-0.2.0}/src/brlib/all_major_leaguers.py

@@ -16,7 +16,7 @@ def all_major_leaguers() -> pd.DataFrame:
 
     ## Parameters
 
-    None.
+    None
 
     ## Returns
 
@@ -67,6 +67,6 @@ def all_major_leaguers() -> pd.DataFrame:
     # convert active column from 0/1 to boolean
     players_df["Active"] = players_df["Active"].astype(bool)
 
-    columns=["Player ID", "Name", "Career Start", "Career End", "Active"]
+    columns = ["Player ID", "Name", "Career Start", "Career End", "Active"]
     players_df = players_df.reindex(columns=columns)
     return players_df

{brlib-0.1.0 → brlib-0.2.0}/src/brlib/find_games.py

@@ -253,7 +253,7 @@ def _find_season_games(
         ) -> list[tuple[str, str, str]]:
     """
     Scrapes an MLB schedule page, and returns the games from that season which
-    match all of the other input parameters. Inputs must be uppercase.
+    match all the other input parameters. Inputs must be uppercase.
     """
     team_set = set(teams)
     opponent_set = set(opponents)

{brlib-0.1.0 → brlib-0.2.0}/src/brlib/find_teams.py

@@ -170,7 +170,7 @@ def _find_season_teams(year: int, year_teams: list[str]) -> list[tuple[str, str]
         else:
             team_mask = abv_man.df["Team"] == team
 
-        match_rows = abv_man.df[(year_mask) & (team_mask)]
+        match_rows = abv_man.df[year_mask & team_mask]
         teams = match_rows["Team"].values
         results = [(abv, str(year)) for abv in teams if abv not in missing_seasons]
         results.sort(key=lambda x: x[0]) # sort by team abv instead of franchise abv