hkjc 0.3.14__py3-none-any.whl → 0.3.15__py3-none-any.whl

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/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:
@@ -47,10 +53,10 @@ def generate_historical_data(start_date: str, end_date: str) -> pl.DataFrame:
 
     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-0.3.14.dist-info → hkjc-0.3.15.dist-info}/METADATA

@@ -1,11 +1,12 @@
 Metadata-Version: 2.4
 Name: hkjc
-Version: 0.3.14
+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-0.3.14.dist-info → hkjc-0.3.15.dist-info}/RECORD

@@ -1,13 +1,13 @@
 hkjc/__init__.py,sha256=TI7PVhmoWSvYX-xdTEdaT3jfY99LiYQFRQZaIwBhJd8,785
 hkjc/harville_model.py,sha256=MZjPLS-1nbEhp1d4Syuq13DtraKnd7TlNqBmOOCwxgc,15976
-hkjc/historical.py,sha256=HRsy8O2NqJQ5Ljcs1ySppngL7kO0rqC49vkIKIDp1Do,6027
+hkjc/historical.py,sha256=FRECc4pmozjFKkFeWN0vTzECF9QOS7URyJoCfTt5hlw,5805
 hkjc/live_odds.py,sha256=G4ELBBp1d2prxye9kKzu2pwtS4vSfRPOmEuT7-Nd-3A,4741
-hkjc/processing.py,sha256=K3mlPiGaE5PlVcbjLpn0QWNpMNOFiaLXFqWGdIBe2xw,7082
+hkjc/processing.py,sha256=XeVrF5KKkU3Oy-vqPvMgM22QHVTCVCuml2IsIGdRbYw,7483
 hkjc/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 hkjc/speedpro.py,sha256=Y2Z3GYGeePc4sM-ZnCHXCI1N7L-_j9nrMqS3CC5BBSo,2031
 hkjc/utils.py,sha256=4CA_FPf_U3GvzoLkqBX0qDPZgrSvKJKvbP7VWqd5FiA,6323
 hkjc/strategy/place_only.py,sha256=lHPjTSj8PzghxncNBg8FI4T4HJigekB9a3bV7l7VtPA,2079
 hkjc/strategy/qpbanker.py,sha256=MQxjwsfhllKZroKS8w8Q3bi3HMjGc1DAyBIjNZAp3yQ,4805
-hkjc-0.3.14.dist-info/METADATA,sha256=u-6OgmWRvNgS_RySOBRWzowDULmKE7Q0TNPzAQCIPg8,452
-hkjc-0.3.14.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-hkjc-0.3.14.dist-info/RECORD,,
+hkjc-0.3.15.dist-info/METADATA,sha256=2nQL1EImJ0hXnWFdGnpORIknMdaaFham-Pw9cgjUiO4,481
+hkjc-0.3.15.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+hkjc-0.3.15.dist-info/RECORD,,