hkjc 0.3.13__tar.gz → 0.3.15__tar.gz

{hkjc-0.3.13 → hkjc-0.3.15}/PKG-INFO

@@ -1,11 +1,12 @@
 Metadata-Version: 2.4
 Name: hkjc
-Version: 0.3.13
+Version: 0.3.15
 Summary: Library for scrapping HKJC data and perform basic analysis
 Requires-Python: >=3.11
 Requires-Dist: beautifulsoup4>=4.14.2
 Requires-Dist: cachetools>=6.2.0
 Requires-Dist: fastexcel>=0.16.0
+Requires-Dist: joblib>=1.5.2
 Requires-Dist: numba>=0.62.1
 Requires-Dist: numpy>=2.3.3
 Requires-Dist: polars>=1.33.1

{hkjc-0.3.13 → hkjc-0.3.15}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "hkjc"
-version = "0.3.13"
+version = "0.3.15"
 description = "Library for scrapping HKJC data and perform basic analysis"
 readme = "README.md"
 requires-python = ">=3.11"
@@ -8,6 +8,7 @@ dependencies = [
     "beautifulsoup4>=4.14.2",
     "cachetools>=6.2.0",
     "fastexcel>=0.16.0",
+    "joblib>=1.5.2",
     "numba>=0.62.1",
     "numpy>=2.3.3",
     "polars>=1.33.1",

{hkjc-0.3.13 → hkjc-0.3.15}/src/hkjc/historical.py

@@ -7,7 +7,7 @@ import polars as pl
 from bs4 import BeautifulSoup
 from cachetools.func import ttl_cache
 
-from .utils import _validate_date, _validate_venue_code, _parse_html_table
+from .utils import _parse_html_table
 
 HKJC_RACE_URL_TEMPLATE = "https://racing.hkjc.com/racing/information/English/Racing/LocalResults.aspx?RaceDate={date}&Racecourse={venue_code}&RaceNo={race_number}"
 HKJC_HORSE_URL_TEMPLATE = "https://racing.hkjc.com/racing/information/English/Horse/Horse.aspx?HorseId={horse_id}"
@@ -77,15 +77,12 @@ def _extract_horse_data(horse_id: str) -> pl.DataFrame:
     # Extract horse profile info
     table = soup.find_all('table', class_='table_eng_text')
     profile_data = _parse_html_table(table[0], skip_header=True)
-    country, age = profile_data.filter(pl.col("column_0").str.starts_with("Country"))['column_2'].item(0).split('/')
     profile_data = _parse_html_table(table[1], skip_header=True)
     current_rating = profile_data.filter(pl.col("column_0").str.starts_with("Current Rating"))['column_2'].item(0)
     season_start_rating = profile_data.filter(pl.col("column_0").str.starts_with("Start of Season Rating"))['column_2'].item(0)
 
     horse_info = {
         'HorseID': horse_id,
-        'OriginCountry': country.strip(),
-        'Age': int(age),
         'CurrentRating': int(current_rating),
         'SeasonStartRating': int(season_start_rating)
     }

{hkjc-0.3.13 → hkjc-0.3.15}/src/hkjc/processing.py

@@ -14,6 +14,7 @@ import numpy as np
 from itertools import combinations
 from tqdm import tqdm
 from datetime import datetime as dt
+from joblib import delayed, Parallel
 
 
 def _all_subsets(lst): return [list(x) for r in range(
@@ -27,13 +28,18 @@ incidents = ['DISQ', 'DNF', 'FE', 'ML', 'PU', 'TNP', 'TO',
              'UR', 'VOID', 'WR', 'WV', 'WV-A', 'WX', 'WX-A', 'WXNR']
 
 
-def _historical_process_single_date_venue(date: str, venue_code: str) -> Union[pl.DataFrame, None]:
-    for race_number in range(1, 12):
+def _historical_process_single_date_venue(date: str, venue_code: str) -> List[pl.DataFrame]:
+    dfs = []
+    iter_date = tqdm(range(1, 12), desc=f"Processing {date} {venue_code} ...", leave=False)
+    for race_number in iter_date:
         try:
-            _extract_race_data(date.strftime('%Y/%m/%d'),
-                               venue_code, race_number)
+            dfs.append(_extract_race_data(date.strftime('%Y/%m/%d'),
+                                          venue_code, race_number))
         except:
-            return None
+            if race_number == 1:
+                iter_date.close()
+                return []
+    return dfs
 
 
 def generate_historical_data(start_date: str, end_date: str) -> pl.DataFrame:
@@ -45,12 +51,12 @@ def generate_historical_data(start_date: str, end_date: str) -> pl.DataFrame:
 
     dfs = []
 
-    for date in pl.date_range(start_dt, end_dt, interval='1d', eager=True):
+    for date in tqdm(pl.date_range(start_dt, end_dt, interval='1d', eager=True)):
         for venue_code in ['ST', 'HV']:
-            df = _historical_process_single_date_venue(date, venue_code)
-            if df is None:
-                continue
-            dfs.append(df)
+            dfs += _historical_process_single_date_venue(date, venue_code)
+
+    if dfs == []:
+        raise ValueError("Failed to obtain any race data. This could be due to invalid date range, or server requests limit. Please try again later.")
 
     df = (pl.concat(dfs)
           .filter(~pl.col('Pla').is_in(incidents))
@@ -69,10 +75,11 @@ def generate_historical_data(start_date: str, end_date: str) -> pl.DataFrame:
         pl.col('WinOdds').cast(pl.Float64, strict=False)
     ])
 
-    df = df.with_columns(pl.col('Finish Time')
-        .str.strptime(pl.Duration, format='%M:%S.%f', strict=False)
-        .dt.total_seconds()
-        .alias('Finish Time')
+    df = df.with_columns(
+        (
+            pl.col("FinishTime").str.split(":").list.get(0).cast(pl.Int64) * 60 +
+            pl.col("FinishTime").str.split(":").list.get(1).cast(pl.Float64)
+        ).cast(pl.Float64).alias("FinishTime")
     )
 
     return df

{hkjc-0.3.13 → hkjc-0.3.15}/uv.lock

@@ -110,12 +110,13 @@ wheels = [
 
 [[package]]
 name = "hkjc"
-version = "0.3.13"
+version = "0.3.15"
 source = { editable = "." }
 dependencies = [
     { name = "beautifulsoup4" },
     { name = "cachetools" },
     { name = "fastexcel" },
+    { name = "joblib" },
     { name = "numba" },
     { name = "numpy" },
     { name = "polars" },
@@ -130,6 +131,7 @@ requires-dist = [
     { name = "beautifulsoup4", specifier = ">=4.14.2" },
     { name = "cachetools", specifier = ">=6.2.0" },
     { name = "fastexcel", specifier = ">=0.16.0" },
+    { name = "joblib", specifier = ">=1.5.2" },
     { name = "numba", specifier = ">=0.62.1" },
     { name = "numpy", specifier = ">=2.3.3" },
     { name = "polars", specifier = ">=1.33.1" },
@@ -148,6 +150,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/76/c6/c88e154df9c4e1a2a66ccf0005a88dfb2650c1dffb6f5ce603dfbd452ce3/idna-3.10-py3-none-any.whl", hash = "sha256:946d195a0d259cbba61165e88e65941f16e9b36ea6ddb97f00452bae8b1287d3", size = 70442, upload-time = "2024-09-15T18:07:37.964Z" },
 ]
 
+[[package]]
+name = "joblib"
+version = "1.5.2"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/e8/5d/447af5ea094b9e4c4054f82e223ada074c552335b9b4b2d14bd9b35a67c4/joblib-1.5.2.tar.gz", hash = "sha256:3faa5c39054b2f03ca547da9b2f52fde67c06240c31853f306aea97f13647b55", size = 331077, upload-time = "2025-08-27T12:15:46.575Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/1e/e8/685f47e0d754320684db4425a0967f7d3fa70126bffd76110b7009a0090f/joblib-1.5.2-py3-none-any.whl", hash = "sha256:4e1f0bdbb987e6d843c70cf43714cb276623def372df3c22fe5266b2670bc241", size = 308396, upload-time = "2025-08-27T12:15:45.188Z" },
+]
+
 [[package]]
 name = "llvmlite"
 version = "0.45.1"