hkjc 0.3.16__tar.gz → 0.3.18__tar.gz

hkjc-0.3.18/.gitignore

@@ -0,0 +1,4 @@
+.venv/
+__pycache__/
+*.pyc
+backend/

{hkjc-0.3.16 → hkjc-0.3.18}/PKG-INFO

@@ -1,12 +1,12 @@
 Metadata-Version: 2.4
 Name: hkjc
-Version: 0.3.16
+Version: 0.3.18
 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: flask>=3.1.2
 Requires-Dist: numba>=0.62.1
 Requires-Dist: numpy>=2.3.3
 Requires-Dist: polars>=1.33.1

hkjc-0.3.18/process.py

@@ -0,0 +1,4 @@
+from hkjc import generate_historical_data
+
+df = generate_historical_data('2024-09-01', '2025-10-06')
+df.write_parquet('hkjc2425.parquet')

{hkjc-0.3.16 → hkjc-0.3.18}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "hkjc"
-version = "0.3.16"
+version = "0.3.18"
 description = "Library for scrapping HKJC data and perform basic analysis"
 readme = "README.md"
 requires-python = ">=3.11"
@@ -8,7 +8,7 @@ dependencies = [
     "beautifulsoup4>=4.14.2",
     "cachetools>=6.2.0",
     "fastexcel>=0.16.0",
-    "joblib>=1.5.2",
+    "flask>=3.1.2",
     "numba>=0.62.1",
     "numpy>=2.3.3",
     "polars>=1.33.1",

{hkjc-0.3.16 → hkjc-0.3.18}/src/hkjc/__init__.py

@@ -4,7 +4,7 @@ This module re-exports commonly used symbols from the submodules.
 """
 from importlib.metadata import version as _version
 
-__all__ = ["live_odds", "qpbanker",
+__all__ = ["live", "qpbanker",
            "generate_all_qp_trades", "generate_all_pla_trades", "pareto_filter",
                         "speedpro_energy", "speedmap", "harveille_model",
                         "generate_historical_data"]
@@ -14,8 +14,7 @@ try:
 except Exception:  # pragma: no cover - best-effort version resolution
     __version__ = "0.0.0"
 
-from .live_odds import live_odds
 from .processing import generate_all_qp_trades, generate_all_pla_trades, generate_historical_data
 from .utils import pareto_filter
 from .speedpro import speedmap, speedpro_energy
-from . import harville_model
+from . import harville_model, live

{hkjc-0.3.16 → hkjc-0.3.18}/src/hkjc/historical.py

@@ -12,6 +12,9 @@ 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?HorseNo={horse_no}"
 
+incidents = ['DISQ', 'DNF', 'FE', 'ML', 'PU', 'TNP', 'TO',
+             'UR', 'VOID', 'WR', 'WV', 'WV-A', 'WX', 'WX-A', 'WXNR']
+
 
 @ttl_cache(maxsize=100, ttl=3600)
 def _soupify(url: str) -> BeautifulSoup:
@@ -37,7 +40,6 @@ def _soupify_horse_page(horse_no: str) -> BeautifulSoup:
     return _soupify(url)
 
 
-
 def _classify_running_style(df: pl.DataFrame, running_pos_col="RunningPosition") -> pl.DataFrame:
     """Classify running style based on RunningPosition column
     """
@@ -50,14 +52,13 @@ def _classify_running_style(df: pl.DataFrame, running_pos_col="RunningPosition")
         .alias("split_data").cast(pl.Int64, strict=False)
     ).unnest("split_data")
 
-    df.with_columns(pl.col('FinishPosition').fill_null(pl.col('Position3')))
+    df = df.with_columns(pl.col('FinishPosition').fill_null(pl.col('Position3')))
 
     df = df.with_columns([
         (pl.col("StartPosition")-pl.col("FinishPosition")).alias("PositionChange"),
-        pl.mean_horizontal("StartPosition", "Position2",
-                           "Position3", "FinishPosition").alias("AvgPosition"),
+        pl.mean_horizontal("StartPosition", "Position2").alias("AvgStartPosition"),
     ]).with_columns(pl.when(pl.col("StartPosition").is_null()).then(pl.lit("--"))
-                    .when((pl.col("PositionChange") <= 0) & pl.col("StartPosition") <= 3).then(pl.lit("FrontRunner"))
+                    .when((pl.col("AvgStartPosition") <= 3) & (pl.col("StartPosition") <= 3)).then(pl.lit("FrontRunner"))
                     .when((pl.col("PositionChange") >= 1) & (pl.col("StartPosition") >= 6)).then(pl.lit("Closer"))
                     .otherwise(pl.lit("Pacer")).alias("RunningStyle"))
 
@@ -67,7 +68,7 @@ def _classify_running_style(df: pl.DataFrame, running_pos_col="RunningPosition")
     return df
 
 
-def get_horse_data(horse_no: str) -> pl.DataFrame:
+def _extract_horse_data(horse_no: str) -> pl.DataFrame:
     """Extract horse info and history from horse page
     """
     soup = _soupify_horse_page(horse_no)
@@ -82,13 +83,16 @@ def get_horse_data(horse_no: str) -> pl.DataFrame:
     profile_data = _parse_html_table(table[1], skip_header=True)
 
     try:
-        current_rating = int(profile_data.filter(pl.col("column_0").str.starts_with("Current Rating"))['column_2'].item(0))
-        season_start_rating = int(profile_data.filter(pl.col("column_0").str.starts_with("Start of Season Rating"))['column_2'].item(0))
+        current_rating = int(profile_data.filter(
+            pl.col("column_0").str.starts_with("Current Rating"))['column_2'].item(0))
+        season_start_rating = int(profile_data.filter(pl.col(
+            "column_0").str.starts_with("Start of Season Rating"))['column_2'].item(0))
     except:
         current_rating, season_start_rating = 0, 0
-    
+
     try:
-        last_rating = int(profile_data.filter(pl.col("column_0").str.starts_with("Last Rating"))['column_2'].item(0))
+        last_rating = int(profile_data.filter(
+            pl.col("column_0").str.starts_with("Last Rating"))['column_2'].item(0))
     except:
         last_rating = 0
 
@@ -96,47 +100,85 @@ def get_horse_data(horse_no: str) -> pl.DataFrame:
         'HorseID': horse_no,
         'CurrentRating': current_rating,
         'SeasonStartRating': season_start_rating,
-        'LastRating' : last_rating if current_rating==0 else current_rating
+        'LastRating': last_rating if current_rating == 0 else current_rating
     }
     horse_data = (horse_data.with_columns([
         pl.lit(value).alias(key) for key, value in horse_info.items()
     ])
     )
 
-    horse_data = horse_data.with_columns([
+    return horse_data
+
+
+def _clean_horse_data(df: pl.DataFrame) -> pl.DataFrame:
+    """ Clean and convert horse data to suitable data types
+    """
+    df = df.with_columns(
+        pl.col('Pla').str.split(' ').list.first().alias('Pla')
+    ).filter(~pl.col('Pla').is_in(incidents))
+
+    df = df.with_columns([
         pl.col('Pla').cast(pl.Int64, strict=False),
-        pl.col('WinOdds').cast(pl.Int64, strict=False),
         pl.col('ActWt').cast(pl.Int64, strict=False),
         pl.col('DeclarHorseWt').cast(pl.Int64, strict=False),
         pl.col('Dr').cast(pl.Int64, strict=False),
         pl.col('Rtg').cast(pl.Int64, strict=False),
-        pl.col('RaceIndex').cast(pl.Int64, strict=False),
-        pl.col('Dist').cast(pl.Int64, strict=False)
+        pl.col('Dist').cast(pl.Int64, strict=False),
+        pl.col('WinOdds').cast(pl.Float64, strict=False),
+        pl.col('RaceIndex').cast(pl.Int64, strict=False)
     ])
 
-    horse_data = horse_data.with_columns(
+    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)
+            pl.col("FinishTime").str.split_exact(".", 1).struct.field("field_0").cast(pl.Int64) * 60 +
+            pl.col("FinishTime").str.split_exact(".", 1).struct.field("field_1").cast(pl.Int64)
         ).cast(pl.Float64).alias("FinishTime")
     )
 
-    horse_data = horse_data.with_columns(
+    df = df.with_columns(
         pl.col('RCTrackCourse').str.split_exact(' / ', 2)
         .struct.rename_fields(['Venue', 'Track', 'Course'])
         .alias('RCTrackCourse')
     ).unnest('RCTrackCourse')
 
-    return horse_data
+    return df
 
+def get_horse_data(horse_no: str) -> pl.DataFrame:
+    df = _extract_horse_data(horse_no)
+    return _clean_horse_data(df)
 
-def get_race_data(date: str, venue_code: str, race_number: int) -> pl.DataFrame:
+def _clean_race_data(df: pl.DataFrame) -> pl.DataFrame:
+    """ Clean and convert horse data to suitable data types
+    """
+    df = df.with_columns(
+        pl.col('Pla').str.split(' ').list.first().alias('Pla')
+    ).filter(~pl.col('Pla').is_in(incidents))
+
+    df = df.with_columns([
+        pl.col('Pla').cast(pl.Int64, strict=False),
+        pl.col('HorseNo').cast(pl.Int64, strict=False),
+        pl.col('ActWt').cast(pl.Int64, strict=False),
+        pl.col('DeclarHorseWt').cast(pl.Int64, strict=False),
+        pl.col('Dr').cast(pl.Int64, strict=False),
+        pl.col('WinOdds').cast(pl.Float64, strict=False)
+    ])
+
+    df = df.with_columns(
+        (
+            pl.col("FinishTime").str.split_exact(":", 1).struct.field("field_0").cast(pl.Int64) * 60 +
+            pl.col("FinishTime").str.split_exact(":", 1).struct.field("field_1").cast(pl.Int64)
+        ).cast(pl.Float64).alias("FinishTime")
+    )
+
+    return df
+
+def _extract_race_data(date: str, venue_code: str, race_number: int) -> pl.DataFrame:
     soup = _soupify_race_page(date, venue_code, race_number)
     table = soup.find('div', class_='race_tab').find('table')
     race_data = _parse_html_table(table)
 
     # Extract the relevant race information
-    race_id = race_data.columns[0].replace(f'RACE{race_number}','')
+    race_id = race_data.columns[0].replace(f'RACE{race_number}', '')
     race_class = race_data.item(1, 0).split('-')[0].strip()
     race_dist = race_data.item(1, 0).split('-')[1].strip().rstrip('M')
     race_name = race_data.item(2, 0).strip()
@@ -162,7 +204,12 @@ def get_race_data(date: str, venue_code: str, race_number: int) -> pl.DataFrame:
                  .with_columns(
                      pl.col("Horse").str.extract(r"\((.*?)\)")
                      .alias("HorseID")
-                 )
-                 )
+    )
+    )
+
+    return race_data
 
-    return race_data
+
+def get_race_data(date: str, venue_code: str, race_number: int) -> pl.DataFrame:
+    df = _extract_race_data(date,venue_code,race_number)
+    return _clean_race_data(df)

hkjc-0.3.18/src/hkjc/live.py

@@ -0,0 +1,375 @@
+"""Functions to fetch and process data from HKJC
+"""
+from __future__ import annotations
+from typing import Tuple, List
+
+import requests
+from cachetools.func import ttl_cache
+import numpy as np
+
+from .utils import _validate_date, _validate_venue_code
+
+HKJC_LIVEODDS_ENDPOINT = "https://info.cld.hkjc.com/graphql/base/"
+
+RACEMTG_PAYLOAD = {
+    "operationName": "raceMeetings",
+    "variables": {"date": None, "venueCode": None},
+    "query": """
+    fragment raceFragment on Race {
+    id
+    no
+    status
+    raceName_en
+    raceName_ch
+    postTime
+    country_en
+    country_ch
+    distance
+    wageringFieldSize
+    go_en
+    go_ch
+    ratingType
+    raceTrack {
+        description_en
+        description_ch
+    }
+    raceCourse {
+        description_en
+        description_ch
+        displayCode
+    }
+    claCode
+    raceClass_en
+    raceClass_ch
+    judgeSigns {
+        value_en
+    }
+    }
+
+    fragment racingBlockFragment on RaceMeeting {
+    jpEsts: pmPools(
+        oddsTypes: [WIN, PLA, TCE, TRI, FF, QTT, DT, TT, SixUP]
+        filters: ["jackpot", "estimatedDividend"]
+    ) {
+        leg {
+        number
+        races
+        }
+        oddsType
+        jackpot
+        estimatedDividend
+        mergedPoolId
+    }
+    poolInvs: pmPools(
+        oddsTypes: [WIN, PLA, QIN, QPL, CWA, CWB, CWC, IWN, FCT, TCE, TRI, FF, QTT, DBL, TBL, DT, TT, SixUP]
+    ) {
+        id
+        leg {
+        races
+        }
+    }
+    penetrometerReadings(filters: ["first"]) {
+        reading
+        readingTime
+    }
+    hammerReadings(filters: ["first"]) {
+        reading
+        readingTime
+    }
+    changeHistories(filters: ["top3"]) {
+        type
+        time
+        raceNo
+        runnerNo
+        horseName_ch
+        horseName_en
+        jockeyName_ch
+        jockeyName_en
+        scratchHorseName_ch
+        scratchHorseName_en
+        handicapWeight
+        scrResvIndicator
+    }
+    }
+
+    query raceMeetings($date: String, $venueCode: String) {
+    timeOffset {
+        rc
+    }
+    activeMeetings: raceMeetings {
+        id
+        venueCode
+        date
+        status
+        races {
+        no
+        postTime
+        status
+        wageringFieldSize
+        }
+    }
+    raceMeetings(date: $date, venueCode: $venueCode) {
+        id
+        status
+        venueCode
+        date
+        totalNumberOfRace
+        currentNumberOfRace
+        dateOfWeek
+        meetingType
+        totalInvestment
+        country {
+        code
+        namech
+        nameen
+        seq
+        }
+        races {
+        ...raceFragment
+        runners {
+            id
+            no
+            standbyNo
+            status
+            name_ch
+            name_en
+            horse {
+            id
+            code
+            }
+            color
+            barrierDrawNumber
+            handicapWeight
+            currentWeight
+            currentRating
+            internationalRating
+            gearInfo
+            racingColorFileName
+            allowance
+            trainerPreference
+            last6run
+            saddleClothNo
+            trumpCard
+            priority
+            finalPosition
+            deadHeat
+            winOdds
+            jockey {
+            code
+            name_en
+            name_ch
+            }
+            trainer {
+            code
+            name_en
+            name_ch
+            }
+        }
+        }
+        obSt: pmPools(oddsTypes: [WIN, PLA]) {
+        leg {
+            races
+        }
+        oddsType
+        comingleStatus
+        }
+        poolInvs: pmPools(
+        oddsTypes: [WIN, PLA, QIN, QPL, CWA, CWB, CWC, IWN, FCT, TCE, TRI, FF, QTT, DBL, TBL, DT, TT, SixUP]
+        ) {
+        id
+        leg {
+            number
+            races
+        }
+        status
+        sellStatus
+        oddsType
+        investment
+        mergedPoolId
+        lastUpdateTime
+        }
+        ...racingBlockFragment
+        pmPools(oddsTypes: []) {
+        id
+        }
+        jkcInstNo: foPools(oddsTypes: [JKC], filters: ["top"]) {
+        instNo
+        }
+        tncInstNo: foPools(oddsTypes: [TNC], filters: ["top"]) {
+        instNo
+        }
+    }
+    }
+"""}
+
+LIVEODDS_PAYLOAD = {
+    "operationName": "racing",
+    "variables": {"date": None, "venueCode": None, "raceNo": None, "oddsTypes": None},
+    "query": """
+query racing($date: String, $venueCode: String, $oddsTypes: [OddsType], $raceNo: Int) {
+    raceMeetings(date: $date, venueCode: $venueCode) {
+        pmPools(oddsTypes: $oddsTypes, raceNo: $raceNo) {
+            id
+            status
+            sellStatus
+            oddsType
+            lastUpdateTime
+            guarantee
+            minTicketCost
+            name_en
+            name_ch
+            leg {
+                number
+                races
+            }
+            cWinSelections {
+                composite
+                name_ch
+                name_en
+                starters
+            }
+            oddsNodes {
+                combString
+                oddsValue
+                hotFavourite
+                oddsDropValue
+                bankerOdds {
+                    combString
+                    oddsValue
+                }
+            }
+        }
+    }
+}""",
+}
+
+
+@ttl_cache(maxsize=12, ttl=1000)
+def _fetch_live_races(date: str, venue_code: str) -> dict:
+    """Fetch live race data from HKJC GraphQL endpoint."""
+    payload = RACEMTG_PAYLOAD.copy()
+    payload["variables"] = payload["variables"].copy()
+    payload["variables"]["date"] = date
+    payload["variables"]["venueCode"] = venue_code
+
+    headers = {
+        "Origin": "https://bet.hkjc.com",
+        "Referer": "https://bet.hkjc.com",
+        "Content-Type": "application/json",
+        "Accept": "application/json",
+        "User-Agent": "python-hkjc-fetch/0.1",
+    }
+
+    r = requests.post(HKJC_LIVEODDS_ENDPOINT, json=payload,
+                      headers=headers, timeout=10)
+    if r.status_code != 200:
+        raise RuntimeError(f"Request failed: {r.status_code} - {r.text}")
+
+    races = r.json()['data']['raceMeetings'][0]['races']
+
+    race_info = {}
+    for race in races:
+        race_num = race['no']
+        race_name = race['raceName_en']
+        race_dist = race['distance']
+        race_going = race['go_en']
+        race_track = race['raceTrack']['description_en']
+        race_class = race['raceClass_en']
+        race_course = race['raceCourse']['displayCode']
+
+        runners = [{'Dr': runner['barrierDrawNumber'],
+                    'Rtg' : int(runner['currentRating']),
+                    'Wt' : int(runner['currentWeight']),
+                    'HorseNo': runner['horse']['code']
+                    } for runner in race['runners']]
+        race_info[race_num]={
+            'No': race_num,
+            'Name': race_name,
+            'Class': race_class,
+            'Course': race_course,
+            'Dist': race_dist,
+            'Going': race_going,
+            'Track': race_track,
+            'Runners': runners            
+        }
+    return race_info
+
+
+@ttl_cache(maxsize=12, ttl=30)
+def _fetch_live_odds(date: str, venue_code: str, race_number: int, odds_type: Tuple[str] = ('PLA', 'QPL')) -> List[dict]:
+    """Fetch live odds data from HKJC GraphQL endpoint."""
+    payload = LIVEODDS_PAYLOAD.copy()
+    payload["variables"] = payload["variables"].copy()
+    payload["variables"]["date"] = date
+    payload["variables"]["venueCode"] = venue_code
+    payload["variables"]["raceNo"] = race_number
+    payload["variables"]["oddsTypes"] = odds_type
+
+    headers = {
+        "Origin": "https://bet.hkjc.com",
+        "Referer": "https://bet.hkjc.com",
+        "Content-Type": "application/json",
+        "Accept": "application/json",
+        "User-Agent": "python-hkjc-fetch/0.1",
+    }
+
+    r = requests.post(HKJC_LIVEODDS_ENDPOINT, json=payload,
+                      headers=headers, timeout=10)
+    if r.status_code != 200:
+        raise RuntimeError(f"Request failed: {r.status_code} - {r.text}")
+
+    meetings = r.json().get("data", {}).get("raceMeetings", [])
+
+    return [
+        {"HorseID": node["combString"], "Type": pool.get(
+            "oddsType"), "Odds": float(node["oddsValue"])}
+        for meeting in meetings
+        for pool in meeting.get("pmPools", [])
+        for node in pool.get("oddsNodes", [])
+    ]
+
+
+def live_odds(date: str, venue_code: str, race_number: int, odds_type: List[str] = ['PLA', 'QPL']) -> dict:
+    """Fetch live odds as numpy arrays.
+
+    Args:
+        date (str): Date in 'YYYY-MM-DD' format.
+        venue_code (str): Venue code, e.g., 'ST' for Shatin, 'HV' for Happy Valley.
+        race_number (int): Race number.
+        odds_type (List[str]): Types of odds to fetch. Default is ['PLA', 'QPL']. Currently the following types are supported:
+            - 'WIN': Win odds
+            - 'PLA': Place odds
+            - 'QIN': Quinella odds
+            - 'QPL': Quinella Place odds
+        fit_harville (bool): Whether to fit the odds using Harville model. Default is False.
+
+    Returns:
+        dict: Dictionary with keys as odds types and values as numpy arrays containing the odds.
+            If odds_type is 'WIN','PLA', returns a 1D array of place odds.
+            If odds_type is 'QIN','QPL', returns a 2D array of quinella place odds. 
+    """
+    _validate_date(date)
+    _validate_venue_code(venue_code)
+
+    race_info = _fetch_live_races(date, venue_code)
+    N = len(race_info[race_number]['Runners'])
+
+    data = _fetch_live_odds(date, venue_code, race_number,
+                            odds_type=tuple(odds_type))
+
+    odds = {'WIN': np.full(N, np.nan, dtype=float),
+            'PLA': np.full(N, np.nan, dtype=float),
+            'QIN': np.full((N, N), np.nan, dtype=float),
+            'QPL': np.full((N, N), np.nan, dtype=float)}
+
+    for entry in data:
+        if entry["Type"] in ["QIN", "QPL"]:
+            horse_ids = list(map(int, entry["HorseID"].split(",")))
+            odds[entry["Type"]][horse_ids[0] - 1,
+                                horse_ids[1] - 1] = entry["Odds"]
+            odds[entry["Type"]][horse_ids[1] - 1,
+                                horse_ids[0] - 1] = entry["Odds"]
+        elif entry["Type"] in ["PLA", "WIN"]:
+            odds[entry["Type"]][int(entry["HorseID"]) - 1] = entry["Odds"]
+
+    return {t: odds[t] for t in odds_type}

{hkjc-0.3.16 → hkjc-0.3.18}/src/hkjc/processing.py

@@ -3,10 +3,10 @@
 from __future__ import annotations
 from typing import Tuple, List, Union
 
-from .live_odds import live_odds
+from .live import live_odds
 from .strategy import qpbanker, place_only
 from .harville_model import fit_harville_to_odds
-from .historical import get_race_data, get_horse_data
+from .historical import _extract_horse_data, _extract_race_data, _clean_horse_data
 from .utils import _validate_date
 
 import polars as pl
@@ -23,8 +23,7 @@ def _all_subsets(lst): return [list(x) for r in range(
 # ======================================
 # Historical data processing functions
 # ======================================
-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) -> List[pl.DataFrame]:
@@ -33,7 +32,7 @@ def _historical_process_single_date_venue(date: str, venue_code: str) -> List[pl
         range(1, 12), desc=f"Processing {date} {venue_code} ...", leave=False)
     for race_number in iter_date:
         try:
-            dfs.append(get_race_data(date.strftime('%Y/%m/%d'),
+            dfs.append(_extract_race_data(date.strftime('%Y/%m/%d'),
                                      venue_code, race_number))
         except:
             if race_number == 1:
@@ -51,7 +50,7 @@ def generate_historical_data(start_date: str, end_date: str) -> pl.DataFrame:
 
     dfs = []
 
-    for date in tqdm(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), leave=False, desc='Scanning for horse IDs ...'):
         for venue_code in ['ST', 'HV']:
             dfs += _historical_process_single_date_venue(date, venue_code)
 
@@ -62,35 +61,9 @@ def generate_historical_data(start_date: str, end_date: str) -> pl.DataFrame:
     horse_ids = pl.concat(dfs)['HorseID'].unique()
 
     # Use horse track records
-    dfs = [get_horse_data(horse_id) for horse_id in horse_ids]
-    df = (
-        pl.concat(dfs).with_columns(
-            pl.col('Date').str.strptime(pl.Date, '%m/%d/%y')
-        ).filter(pl.col('Date').is_between(start_dt, end_dt))
-        .filter(~pl.col('Pla').is_in(incidents))
-        .with_columns(
-            pl.col('Pla').str.split(' ').list.first().alias('Pla')
-        )
-    )
-
-    df = df.with_columns([
-        pl.col('Pla').cast(pl.Int64, strict=False),
-        pl.col('HorseNo').cast(pl.Int64, strict=False),
-        pl.col('ActWt').cast(pl.Int64, strict=False),
-        pl.col('DeclarHorseWt').cast(pl.Int64, strict=False),
-        pl.col('Dr').cast(pl.Int64, strict=False),
-        pl.col('RaceDistance').cast(pl.Int64, strict=False),
-        pl.col('WinOdds').cast(pl.Float64, strict=False)
-    ])
-
-    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
+    dfs = [_extract_horse_data(horse_id) for horse_id in tqdm(horse_ids, desc='Processing horses ...', leave=False)]
+    df = pl.concat(dfs)
+    return _clean_horse_data(df)
 
 
 # ==========================

{hkjc-0.3.16 → hkjc-0.3.18}/uv.lock

@@ -15,6 +15,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/94/fe/3aed5d0be4d404d12d36ab97e2f1791424d9ca39c2f754a6285d59a3b01d/beautifulsoup4-4.14.2-py3-none-any.whl", hash = "sha256:5ef6fa3a8cbece8488d66985560f97ed091e22bbc4e9c2338508a9d5de6d4515", size = 106392, upload-time = "2025-09-29T10:05:43.771Z" },
 ]
 
+[[package]]
+name = "blinker"
+version = "1.9.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/21/28/9b3f50ce0e048515135495f198351908d99540d69bfdc8c1d15b73dc55ce/blinker-1.9.0.tar.gz", hash = "sha256:b4ce2265a7abece45e7cc896e98dbebe6cead56bcf805a3d23136d145f5445bf", size = 22460, upload-time = "2024-11-08T17:25:47.436Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/10/cb/f2ad4230dc2eb1a74edf38f1a38b9b52277f75bef262d8908e60d957e13c/blinker-1.9.0-py3-none-any.whl", hash = "sha256:ba0efaa9080b619ff2f3459d1d500c57bddea4a6b424b60a91141db6fd2f08bc", size = 8458, upload-time = "2024-11-08T17:25:46.184Z" },
+]
+
 [[package]]
 name = "cachetools"
 version = "6.2.0"
@@ -86,6 +95,18 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/8a/1f/f041989e93b001bc4e44bb1669ccdcf54d3f00e628229a85b08d330615c5/charset_normalizer-3.4.3-py3-none-any.whl", hash = "sha256:ce571ab16d890d23b5c278547ba694193a45011ff86a9162a71307ed9f86759a", size = 53175, upload-time = "2025-08-09T07:57:26.864Z" },
 ]
 
+[[package]]
+name = "click"
+version = "8.3.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "colorama", marker = "sys_platform == 'win32'" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/46/61/de6cd827efad202d7057d93e0fed9294b96952e188f7384832791c7b2254/click-8.3.0.tar.gz", hash = "sha256:e7b8232224eba16f4ebe410c25ced9f7875cb5f3263ffc93cc3e8da705e229c4", size = 276943, upload-time = "2025-09-18T17:32:23.696Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/db/d3/9dcc0f5797f070ec8edf30fbadfb200e71d9db6b84d211e3b2085a7589a0/click-8.3.0-py3-none-any.whl", hash = "sha256:9b9f285302c6e3064f4330c05f05b81945b2a39544279343e6e7c5f27a9baddc", size = 107295, upload-time = "2025-09-18T17:32:22.42Z" },
+]
+
 [[package]]
 name = "colorama"
 version = "0.4.6"
@@ -108,15 +129,32 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/9c/2e/805c2d0e799710e4937d084d9c37821bafa129eda1de62c3279a042ca56d/fastexcel-0.16.0-cp39-abi3-win_amd64.whl", hash = "sha256:04c2b6fea7292e26d76a458f9095f4ec260c864c90be7a7161d20ca81cf77fd8", size = 2819876, upload-time = "2025-09-22T12:34:38.716Z" },
 ]
 
+[[package]]
+name = "flask"
+version = "3.1.2"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "blinker" },
+    { name = "click" },
+    { name = "itsdangerous" },
+    { name = "jinja2" },
+    { name = "markupsafe" },
+    { name = "werkzeug" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/dc/6d/cfe3c0fcc5e477df242b98bfe186a4c34357b4847e87ecaef04507332dab/flask-3.1.2.tar.gz", hash = "sha256:bf656c15c80190ed628ad08cdfd3aaa35beb087855e2f494910aa3774cc4fd87", size = 720160, upload-time = "2025-08-19T21:03:21.205Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/ec/f9/7f9263c5695f4bd0023734af91bedb2ff8209e8de6ead162f35d8dc762fd/flask-3.1.2-py3-none-any.whl", hash = "sha256:ca1d8112ec8a6158cc29ea4858963350011b5c846a414cdb7a954aa9e967d03c", size = 103308, upload-time = "2025-08-19T21:03:19.499Z" },
+]
+
 [[package]]
 name = "hkjc"
-version = "0.3.16"
+version = "0.3.18"
 source = { editable = "." }
 dependencies = [
     { name = "beautifulsoup4" },
     { name = "cachetools" },
     { name = "fastexcel" },
-    { name = "joblib" },
+    { name = "flask" },
     { name = "numba" },
     { name = "numpy" },
     { name = "polars" },
@@ -131,7 +169,7 @@ 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 = "flask", specifier = ">=3.1.2" },
     { name = "numba", specifier = ">=0.62.1" },
     { name = "numpy", specifier = ">=2.3.3" },
     { name = "polars", specifier = ">=1.33.1" },
@@ -151,12 +189,24 @@ wheels = [
 ]
 
 [[package]]
-name = "joblib"
-version = "1.5.2"
+name = "itsdangerous"
+version = "2.2.0"
 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" }
+sdist = { url = "https://files.pythonhosted.org/packages/9c/cb/8ac0172223afbccb63986cc25049b154ecfb5e85932587206f42317be31d/itsdangerous-2.2.0.tar.gz", hash = "sha256:e0050c0b7da1eea53ffaf149c0cfbb5c6e2e2b69c4bef22c81fa6eb73e5f6173", size = 54410, upload-time = "2024-04-16T21:28:15.614Z" }
 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" },
+    { url = "https://files.pythonhosted.org/packages/04/96/92447566d16df59b2a776c0fb82dbc4d9e07cd95062562af01e408583fc4/itsdangerous-2.2.0-py3-none-any.whl", hash = "sha256:c6242fc49e35958c8b15141343aa660db5fc54d4f13a1db01a3f5891b98700ef", size = 16234, upload-time = "2024-04-16T21:28:14.499Z" },
+]
+
+[[package]]
+name = "jinja2"
+version = "3.1.6"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "markupsafe" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/df/bf/f7da0350254c0ed7c72f3e33cef02e048281fec7ecec5f032d4aac52226b/jinja2-3.1.6.tar.gz", hash = "sha256:0137fb05990d35f1275a587e9aee6d56da821fc83491a0fb838183be43f66d6d", size = 245115, upload-time = "2025-03-05T20:05:02.478Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/62/a1/3d680cbfd5f4b8f15abc1d571870c5fc3e594bb582bc3b64ea099db13e56/jinja2-3.1.6-py3-none-any.whl", hash = "sha256:85ece4451f492d0c13c5dd7c13a64681a86afae63a5f347908daf103ce6d2f67", size = 134899, upload-time = "2025-03-05T20:05:00.369Z" },
 ]
 
 [[package]]
@@ -182,6 +232,80 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/09/56/ed35668130e32dbfad2eb37356793b0a95f23494ab5be7d9bf5cb75850ee/llvmlite-0.45.1-cp313-cp313-win_amd64.whl", hash = "sha256:080e6f8d0778a8239cd47686d402cb66eb165e421efa9391366a9b7e5810a38b", size = 38132232, upload-time = "2025-10-01T18:05:14.477Z" },
 ]
 
+[[package]]
+name = "markupsafe"
+version = "3.0.3"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/7e/99/7690b6d4034fffd95959cbe0c02de8deb3098cc577c67bb6a24fe5d7caa7/markupsafe-3.0.3.tar.gz", hash = "sha256:722695808f4b6457b320fdc131280796bdceb04ab50fe1795cd540799ebe1698", size = 80313, upload-time = "2025-09-27T18:37:40.426Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/08/db/fefacb2136439fc8dd20e797950e749aa1f4997ed584c62cfb8ef7c2be0e/markupsafe-3.0.3-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:1cc7ea17a6824959616c525620e387f6dd30fec8cb44f649e31712db02123dad", size = 11631, upload-time = "2025-09-27T18:36:18.185Z" },
+    { url = "https://files.pythonhosted.org/packages/e1/2e/5898933336b61975ce9dc04decbc0a7f2fee78c30353c5efba7f2d6ff27a/markupsafe-3.0.3-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:4bd4cd07944443f5a265608cc6aab442e4f74dff8088b0dfc8238647b8f6ae9a", size = 12058, upload-time = "2025-09-27T18:36:19.444Z" },
+    { url = "https://files.pythonhosted.org/packages/1d/09/adf2df3699d87d1d8184038df46a9c80d78c0148492323f4693df54e17bb/markupsafe-3.0.3-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:6b5420a1d9450023228968e7e6a9ce57f65d148ab56d2313fcd589eee96a7a50", size = 24287, upload-time = "2025-09-27T18:36:20.768Z" },
+    { url = "https://files.pythonhosted.org/packages/30/ac/0273f6fcb5f42e314c6d8cd99effae6a5354604d461b8d392b5ec9530a54/markupsafe-3.0.3-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:0bf2a864d67e76e5c9a34dc26ec616a66b9888e25e7b9460e1c76d3293bd9dbf", size = 22940, upload-time = "2025-09-27T18:36:22.249Z" },
+    { url = "https://files.pythonhosted.org/packages/19/ae/31c1be199ef767124c042c6c3e904da327a2f7f0cd63a0337e1eca2967a8/markupsafe-3.0.3-cp311-cp311-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:bc51efed119bc9cfdf792cdeaa4d67e8f6fcccab66ed4bfdd6bde3e59bfcbb2f", size = 21887, upload-time = "2025-09-27T18:36:23.535Z" },
+    { url = "https://files.pythonhosted.org/packages/b2/76/7edcab99d5349a4532a459e1fe64f0b0467a3365056ae550d3bcf3f79e1e/markupsafe-3.0.3-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:068f375c472b3e7acbe2d5318dea141359e6900156b5b2ba06a30b169086b91a", size = 23692, upload-time = "2025-09-27T18:36:24.823Z" },
+    { url = "https://files.pythonhosted.org/packages/a4/28/6e74cdd26d7514849143d69f0bf2399f929c37dc2b31e6829fd2045b2765/markupsafe-3.0.3-cp311-cp311-musllinux_1_2_riscv64.whl", hash = "sha256:7be7b61bb172e1ed687f1754f8e7484f1c8019780f6f6b0786e76bb01c2ae115", size = 21471, upload-time = "2025-09-27T18:36:25.95Z" },
+    { url = "https://files.pythonhosted.org/packages/62/7e/a145f36a5c2945673e590850a6f8014318d5577ed7e5920a4b3448e0865d/markupsafe-3.0.3-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:f9e130248f4462aaa8e2552d547f36ddadbeaa573879158d721bbd33dfe4743a", size = 22923, upload-time = "2025-09-27T18:36:27.109Z" },
+    { url = "https://files.pythonhosted.org/packages/0f/62/d9c46a7f5c9adbeeeda52f5b8d802e1094e9717705a645efc71b0913a0a8/markupsafe-3.0.3-cp311-cp311-win32.whl", hash = "sha256:0db14f5dafddbb6d9208827849fad01f1a2609380add406671a26386cdf15a19", size = 14572, upload-time = "2025-09-27T18:36:28.045Z" },
+    { url = "https://files.pythonhosted.org/packages/83/8a/4414c03d3f891739326e1783338e48fb49781cc915b2e0ee052aa490d586/markupsafe-3.0.3-cp311-cp311-win_amd64.whl", hash = "sha256:de8a88e63464af587c950061a5e6a67d3632e36df62b986892331d4620a35c01", size = 15077, upload-time = "2025-09-27T18:36:29.025Z" },
+    { url = "https://files.pythonhosted.org/packages/35/73/893072b42e6862f319b5207adc9ae06070f095b358655f077f69a35601f0/markupsafe-3.0.3-cp311-cp311-win_arm64.whl", hash = "sha256:3b562dd9e9ea93f13d53989d23a7e775fdfd1066c33494ff43f5418bc8c58a5c", size = 13876, upload-time = "2025-09-27T18:36:29.954Z" },
+    { url = "https://files.pythonhosted.org/packages/5a/72/147da192e38635ada20e0a2e1a51cf8823d2119ce8883f7053879c2199b5/markupsafe-3.0.3-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:d53197da72cc091b024dd97249dfc7794d6a56530370992a5e1a08983ad9230e", size = 11615, upload-time = "2025-09-27T18:36:30.854Z" },
+    { url = "https://files.pythonhosted.org/packages/9a/81/7e4e08678a1f98521201c3079f77db69fb552acd56067661f8c2f534a718/markupsafe-3.0.3-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:1872df69a4de6aead3491198eaf13810b565bdbeec3ae2dc8780f14458ec73ce", size = 12020, upload-time = "2025-09-27T18:36:31.971Z" },
+    { url = "https://files.pythonhosted.org/packages/1e/2c/799f4742efc39633a1b54a92eec4082e4f815314869865d876824c257c1e/markupsafe-3.0.3-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:3a7e8ae81ae39e62a41ec302f972ba6ae23a5c5396c8e60113e9066ef893da0d", size = 24332, upload-time = "2025-09-27T18:36:32.813Z" },
+    { url = "https://files.pythonhosted.org/packages/3c/2e/8d0c2ab90a8c1d9a24f0399058ab8519a3279d1bd4289511d74e909f060e/markupsafe-3.0.3-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:d6dd0be5b5b189d31db7cda48b91d7e0a9795f31430b7f271219ab30f1d3ac9d", size = 22947, upload-time = "2025-09-27T18:36:33.86Z" },
+    { url = "https://files.pythonhosted.org/packages/2c/54/887f3092a85238093a0b2154bd629c89444f395618842e8b0c41783898ea/markupsafe-3.0.3-cp312-cp312-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:94c6f0bb423f739146aec64595853541634bde58b2135f27f61c1ffd1cd4d16a", size = 21962, upload-time = "2025-09-27T18:36:35.099Z" },
+    { url = "https://files.pythonhosted.org/packages/c9/2f/336b8c7b6f4a4d95e91119dc8521402461b74a485558d8f238a68312f11c/markupsafe-3.0.3-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:be8813b57049a7dc738189df53d69395eba14fb99345e0a5994914a3864c8a4b", size = 23760, upload-time = "2025-09-27T18:36:36.001Z" },
+    { url = "https://files.pythonhosted.org/packages/32/43/67935f2b7e4982ffb50a4d169b724d74b62a3964bc1a9a527f5ac4f1ee2b/markupsafe-3.0.3-cp312-cp312-musllinux_1_2_riscv64.whl", hash = "sha256:83891d0e9fb81a825d9a6d61e3f07550ca70a076484292a70fde82c4b807286f", size = 21529, upload-time = "2025-09-27T18:36:36.906Z" },
+    { url = "https://files.pythonhosted.org/packages/89/e0/4486f11e51bbba8b0c041098859e869e304d1c261e59244baa3d295d47b7/markupsafe-3.0.3-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:77f0643abe7495da77fb436f50f8dab76dbc6e5fd25d39589a0f1fe6548bfa2b", size = 23015, upload-time = "2025-09-27T18:36:37.868Z" },
+    { url = "https://files.pythonhosted.org/packages/2f/e1/78ee7a023dac597a5825441ebd17170785a9dab23de95d2c7508ade94e0e/markupsafe-3.0.3-cp312-cp312-win32.whl", hash = "sha256:d88b440e37a16e651bda4c7c2b930eb586fd15ca7406cb39e211fcff3bf3017d", size = 14540, upload-time = "2025-09-27T18:36:38.761Z" },
+    { url = "https://files.pythonhosted.org/packages/aa/5b/bec5aa9bbbb2c946ca2733ef9c4ca91c91b6a24580193e891b5f7dbe8e1e/markupsafe-3.0.3-cp312-cp312-win_amd64.whl", hash = "sha256:26a5784ded40c9e318cfc2bdb30fe164bdb8665ded9cd64d500a34fb42067b1c", size = 15105, upload-time = "2025-09-27T18:36:39.701Z" },
+    { url = "https://files.pythonhosted.org/packages/e5/f1/216fc1bbfd74011693a4fd837e7026152e89c4bcf3e77b6692fba9923123/markupsafe-3.0.3-cp312-cp312-win_arm64.whl", hash = "sha256:35add3b638a5d900e807944a078b51922212fb3dedb01633a8defc4b01a3c85f", size = 13906, upload-time = "2025-09-27T18:36:40.689Z" },
+    { url = "https://files.pythonhosted.org/packages/38/2f/907b9c7bbba283e68f20259574b13d005c121a0fa4c175f9bed27c4597ff/markupsafe-3.0.3-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:e1cf1972137e83c5d4c136c43ced9ac51d0e124706ee1c8aa8532c1287fa8795", size = 11622, upload-time = "2025-09-27T18:36:41.777Z" },
+    { url = "https://files.pythonhosted.org/packages/9c/d9/5f7756922cdd676869eca1c4e3c0cd0df60ed30199ffd775e319089cb3ed/markupsafe-3.0.3-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:116bb52f642a37c115f517494ea5feb03889e04df47eeff5b130b1808ce7c219", size = 12029, upload-time = "2025-09-27T18:36:43.257Z" },
+    { url = "https://files.pythonhosted.org/packages/00/07/575a68c754943058c78f30db02ee03a64b3c638586fba6a6dd56830b30a3/markupsafe-3.0.3-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:133a43e73a802c5562be9bbcd03d090aa5a1fe899db609c29e8c8d815c5f6de6", size = 24374, upload-time = "2025-09-27T18:36:44.508Z" },
+    { url = "https://files.pythonhosted.org/packages/a9/21/9b05698b46f218fc0e118e1f8168395c65c8a2c750ae2bab54fc4bd4e0e8/markupsafe-3.0.3-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:ccfcd093f13f0f0b7fdd0f198b90053bf7b2f02a3927a30e63f3ccc9df56b676", size = 22980, upload-time = "2025-09-27T18:36:45.385Z" },
+    { url = "https://files.pythonhosted.org/packages/7f/71/544260864f893f18b6827315b988c146b559391e6e7e8f7252839b1b846a/markupsafe-3.0.3-cp313-cp313-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:509fa21c6deb7a7a273d629cf5ec029bc209d1a51178615ddf718f5918992ab9", size = 21990, upload-time = "2025-09-27T18:36:46.916Z" },
+    { url = "https://files.pythonhosted.org/packages/c2/28/b50fc2f74d1ad761af2f5dcce7492648b983d00a65b8c0e0cb457c82ebbe/markupsafe-3.0.3-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:a4afe79fb3de0b7097d81da19090f4df4f8d3a2b3adaa8764138aac2e44f3af1", size = 23784, upload-time = "2025-09-27T18:36:47.884Z" },
+    { url = "https://files.pythonhosted.org/packages/ed/76/104b2aa106a208da8b17a2fb72e033a5a9d7073c68f7e508b94916ed47a9/markupsafe-3.0.3-cp313-cp313-musllinux_1_2_riscv64.whl", hash = "sha256:795e7751525cae078558e679d646ae45574b47ed6e7771863fcc079a6171a0fc", size = 21588, upload-time = "2025-09-27T18:36:48.82Z" },
+    { url = "https://files.pythonhosted.org/packages/b5/99/16a5eb2d140087ebd97180d95249b00a03aa87e29cc224056274f2e45fd6/markupsafe-3.0.3-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:8485f406a96febb5140bfeca44a73e3ce5116b2501ac54fe953e488fb1d03b12", size = 23041, upload-time = "2025-09-27T18:36:49.797Z" },
+    { url = "https://files.pythonhosted.org/packages/19/bc/e7140ed90c5d61d77cea142eed9f9c303f4c4806f60a1044c13e3f1471d0/markupsafe-3.0.3-cp313-cp313-win32.whl", hash = "sha256:bdd37121970bfd8be76c5fb069c7751683bdf373db1ed6c010162b2a130248ed", size = 14543, upload-time = "2025-09-27T18:36:51.584Z" },
+    { url = "https://files.pythonhosted.org/packages/05/73/c4abe620b841b6b791f2edc248f556900667a5a1cf023a6646967ae98335/markupsafe-3.0.3-cp313-cp313-win_amd64.whl", hash = "sha256:9a1abfdc021a164803f4d485104931fb8f8c1efd55bc6b748d2f5774e78b62c5", size = 15113, upload-time = "2025-09-27T18:36:52.537Z" },
+    { url = "https://files.pythonhosted.org/packages/f0/3a/fa34a0f7cfef23cf9500d68cb7c32dd64ffd58a12b09225fb03dd37d5b80/markupsafe-3.0.3-cp313-cp313-win_arm64.whl", hash = "sha256:7e68f88e5b8799aa49c85cd116c932a1ac15caaa3f5db09087854d218359e485", size = 13911, upload-time = "2025-09-27T18:36:53.513Z" },
+    { url = "https://files.pythonhosted.org/packages/e4/d7/e05cd7efe43a88a17a37b3ae96e79a19e846f3f456fe79c57ca61356ef01/markupsafe-3.0.3-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:218551f6df4868a8d527e3062d0fb968682fe92054e89978594c28e642c43a73", size = 11658, upload-time = "2025-09-27T18:36:54.819Z" },
+    { url = "https://files.pythonhosted.org/packages/99/9e/e412117548182ce2148bdeacdda3bb494260c0b0184360fe0d56389b523b/markupsafe-3.0.3-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:3524b778fe5cfb3452a09d31e7b5adefeea8c5be1d43c4f810ba09f2ceb29d37", size = 12066, upload-time = "2025-09-27T18:36:55.714Z" },
+    { url = "https://files.pythonhosted.org/packages/bc/e6/fa0ffcda717ef64a5108eaa7b4f5ed28d56122c9a6d70ab8b72f9f715c80/markupsafe-3.0.3-cp313-cp313t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:4e885a3d1efa2eadc93c894a21770e4bc67899e3543680313b09f139e149ab19", size = 25639, upload-time = "2025-09-27T18:36:56.908Z" },
+    { url = "https://files.pythonhosted.org/packages/96/ec/2102e881fe9d25fc16cb4b25d5f5cde50970967ffa5dddafdb771237062d/markupsafe-3.0.3-cp313-cp313t-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:8709b08f4a89aa7586de0aadc8da56180242ee0ada3999749b183aa23df95025", size = 23569, upload-time = "2025-09-27T18:36:57.913Z" },
+    { url = "https://files.pythonhosted.org/packages/4b/30/6f2fce1f1f205fc9323255b216ca8a235b15860c34b6798f810f05828e32/markupsafe-3.0.3-cp313-cp313t-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:b8512a91625c9b3da6f127803b166b629725e68af71f8184ae7e7d54686a56d6", size = 23284, upload-time = "2025-09-27T18:36:58.833Z" },
+    { url = "https://files.pythonhosted.org/packages/58/47/4a0ccea4ab9f5dcb6f79c0236d954acb382202721e704223a8aafa38b5c8/markupsafe-3.0.3-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:9b79b7a16f7fedff2495d684f2b59b0457c3b493778c9eed31111be64d58279f", size = 24801, upload-time = "2025-09-27T18:36:59.739Z" },
+    { url = "https://files.pythonhosted.org/packages/6a/70/3780e9b72180b6fecb83a4814d84c3bf4b4ae4bf0b19c27196104149734c/markupsafe-3.0.3-cp313-cp313t-musllinux_1_2_riscv64.whl", hash = "sha256:12c63dfb4a98206f045aa9563db46507995f7ef6d83b2f68eda65c307c6829eb", size = 22769, upload-time = "2025-09-27T18:37:00.719Z" },
+    { url = "https://files.pythonhosted.org/packages/98/c5/c03c7f4125180fc215220c035beac6b9cb684bc7a067c84fc69414d315f5/markupsafe-3.0.3-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:8f71bc33915be5186016f675cd83a1e08523649b0e33efdb898db577ef5bb009", size = 23642, upload-time = "2025-09-27T18:37:01.673Z" },
+    { url = "https://files.pythonhosted.org/packages/80/d6/2d1b89f6ca4bff1036499b1e29a1d02d282259f3681540e16563f27ebc23/markupsafe-3.0.3-cp313-cp313t-win32.whl", hash = "sha256:69c0b73548bc525c8cb9a251cddf1931d1db4d2258e9599c28c07ef3580ef354", size = 14612, upload-time = "2025-09-27T18:37:02.639Z" },
+    { url = "https://files.pythonhosted.org/packages/2b/98/e48a4bfba0a0ffcf9925fe2d69240bfaa19c6f7507b8cd09c70684a53c1e/markupsafe-3.0.3-cp313-cp313t-win_amd64.whl", hash = "sha256:1b4b79e8ebf6b55351f0d91fe80f893b4743f104bff22e90697db1590e47a218", size = 15200, upload-time = "2025-09-27T18:37:03.582Z" },
+    { url = "https://files.pythonhosted.org/packages/0e/72/e3cc540f351f316e9ed0f092757459afbc595824ca724cbc5a5d4263713f/markupsafe-3.0.3-cp313-cp313t-win_arm64.whl", hash = "sha256:ad2cf8aa28b8c020ab2fc8287b0f823d0a7d8630784c31e9ee5edea20f406287", size = 13973, upload-time = "2025-09-27T18:37:04.929Z" },
+    { url = "https://files.pythonhosted.org/packages/33/8a/8e42d4838cd89b7dde187011e97fe6c3af66d8c044997d2183fbd6d31352/markupsafe-3.0.3-cp314-cp314-macosx_10_13_x86_64.whl", hash = "sha256:eaa9599de571d72e2daf60164784109f19978b327a3910d3e9de8c97b5b70cfe", size = 11619, upload-time = "2025-09-27T18:37:06.342Z" },
+    { url = "https://files.pythonhosted.org/packages/b5/64/7660f8a4a8e53c924d0fa05dc3a55c9cee10bbd82b11c5afb27d44b096ce/markupsafe-3.0.3-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:c47a551199eb8eb2121d4f0f15ae0f923d31350ab9280078d1e5f12b249e0026", size = 12029, upload-time = "2025-09-27T18:37:07.213Z" },
+    { url = "https://files.pythonhosted.org/packages/da/ef/e648bfd021127bef5fa12e1720ffed0c6cbb8310c8d9bea7266337ff06de/markupsafe-3.0.3-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:f34c41761022dd093b4b6896d4810782ffbabe30f2d443ff5f083e0cbbb8c737", size = 24408, upload-time = "2025-09-27T18:37:09.572Z" },
+    { url = "https://files.pythonhosted.org/packages/41/3c/a36c2450754618e62008bf7435ccb0f88053e07592e6028a34776213d877/markupsafe-3.0.3-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:457a69a9577064c05a97c41f4e65148652db078a3a509039e64d3467b9e7ef97", size = 23005, upload-time = "2025-09-27T18:37:10.58Z" },
+    { url = "https://files.pythonhosted.org/packages/bc/20/b7fdf89a8456b099837cd1dc21974632a02a999ec9bf7ca3e490aacd98e7/markupsafe-3.0.3-cp314-cp314-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:e8afc3f2ccfa24215f8cb28dcf43f0113ac3c37c2f0f0806d8c70e4228c5cf4d", size = 22048, upload-time = "2025-09-27T18:37:11.547Z" },
+    { url = "https://files.pythonhosted.org/packages/9a/a7/591f592afdc734f47db08a75793a55d7fbcc6902a723ae4cfbab61010cc5/markupsafe-3.0.3-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:ec15a59cf5af7be74194f7ab02d0f59a62bdcf1a537677ce67a2537c9b87fcda", size = 23821, upload-time = "2025-09-27T18:37:12.48Z" },
+    { url = "https://files.pythonhosted.org/packages/7d/33/45b24e4f44195b26521bc6f1a82197118f74df348556594bd2262bda1038/markupsafe-3.0.3-cp314-cp314-musllinux_1_2_riscv64.whl", hash = "sha256:0eb9ff8191e8498cca014656ae6b8d61f39da5f95b488805da4bb029cccbfbaf", size = 21606, upload-time = "2025-09-27T18:37:13.485Z" },
+    { url = "https://files.pythonhosted.org/packages/ff/0e/53dfaca23a69fbfbbf17a4b64072090e70717344c52eaaaa9c5ddff1e5f0/markupsafe-3.0.3-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:2713baf880df847f2bece4230d4d094280f4e67b1e813eec43b4c0e144a34ffe", size = 23043, upload-time = "2025-09-27T18:37:14.408Z" },
+    { url = "https://files.pythonhosted.org/packages/46/11/f333a06fc16236d5238bfe74daccbca41459dcd8d1fa952e8fbd5dccfb70/markupsafe-3.0.3-cp314-cp314-win32.whl", hash = "sha256:729586769a26dbceff69f7a7dbbf59ab6572b99d94576a5592625d5b411576b9", size = 14747, upload-time = "2025-09-27T18:37:15.36Z" },
+    { url = "https://files.pythonhosted.org/packages/28/52/182836104b33b444e400b14f797212f720cbc9ed6ba34c800639d154e821/markupsafe-3.0.3-cp314-cp314-win_amd64.whl", hash = "sha256:bdc919ead48f234740ad807933cdf545180bfbe9342c2bb451556db2ed958581", size = 15341, upload-time = "2025-09-27T18:37:16.496Z" },
+    { url = "https://files.pythonhosted.org/packages/6f/18/acf23e91bd94fd7b3031558b1f013adfa21a8e407a3fdb32745538730382/markupsafe-3.0.3-cp314-cp314-win_arm64.whl", hash = "sha256:5a7d5dc5140555cf21a6fefbdbf8723f06fcd2f63ef108f2854de715e4422cb4", size = 14073, upload-time = "2025-09-27T18:37:17.476Z" },
+    { url = "https://files.pythonhosted.org/packages/3c/f0/57689aa4076e1b43b15fdfa646b04653969d50cf30c32a102762be2485da/markupsafe-3.0.3-cp314-cp314t-macosx_10_13_x86_64.whl", hash = "sha256:1353ef0c1b138e1907ae78e2f6c63ff67501122006b0f9abad68fda5f4ffc6ab", size = 11661, upload-time = "2025-09-27T18:37:18.453Z" },
+    { url = "https://files.pythonhosted.org/packages/89/c3/2e67a7ca217c6912985ec766c6393b636fb0c2344443ff9d91404dc4c79f/markupsafe-3.0.3-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:1085e7fbddd3be5f89cc898938f42c0b3c711fdcb37d75221de2666af647c175", size = 12069, upload-time = "2025-09-27T18:37:19.332Z" },
+    { url = "https://files.pythonhosted.org/packages/f0/00/be561dce4e6ca66b15276e184ce4b8aec61fe83662cce2f7d72bd3249d28/markupsafe-3.0.3-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:1b52b4fb9df4eb9ae465f8d0c228a00624de2334f216f178a995ccdcf82c4634", size = 25670, upload-time = "2025-09-27T18:37:20.245Z" },
+    { url = "https://files.pythonhosted.org/packages/50/09/c419f6f5a92e5fadde27efd190eca90f05e1261b10dbd8cbcb39cd8ea1dc/markupsafe-3.0.3-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:fed51ac40f757d41b7c48425901843666a6677e3e8eb0abcff09e4ba6e664f50", size = 23598, upload-time = "2025-09-27T18:37:21.177Z" },
+    { url = "https://files.pythonhosted.org/packages/22/44/a0681611106e0b2921b3033fc19bc53323e0b50bc70cffdd19f7d679bb66/markupsafe-3.0.3-cp314-cp314t-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:f190daf01f13c72eac4efd5c430a8de82489d9cff23c364c3ea822545032993e", size = 23261, upload-time = "2025-09-27T18:37:22.167Z" },
+    { url = "https://files.pythonhosted.org/packages/5f/57/1b0b3f100259dc9fffe780cfb60d4be71375510e435efec3d116b6436d43/markupsafe-3.0.3-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:e56b7d45a839a697b5eb268c82a71bd8c7f6c94d6fd50c3d577fa39a9f1409f5", size = 24835, upload-time = "2025-09-27T18:37:23.296Z" },
+    { url = "https://files.pythonhosted.org/packages/26/6a/4bf6d0c97c4920f1597cc14dd720705eca0bf7c787aebc6bb4d1bead5388/markupsafe-3.0.3-cp314-cp314t-musllinux_1_2_riscv64.whl", hash = "sha256:f3e98bb3798ead92273dc0e5fd0f31ade220f59a266ffd8a4f6065e0a3ce0523", size = 22733, upload-time = "2025-09-27T18:37:24.237Z" },
+    { url = "https://files.pythonhosted.org/packages/14/c7/ca723101509b518797fedc2fdf79ba57f886b4aca8a7d31857ba3ee8281f/markupsafe-3.0.3-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:5678211cb9333a6468fb8d8be0305520aa073f50d17f089b5b4b477ea6e67fdc", size = 23672, upload-time = "2025-09-27T18:37:25.271Z" },
+    { url = "https://files.pythonhosted.org/packages/fb/df/5bd7a48c256faecd1d36edc13133e51397e41b73bb77e1a69deab746ebac/markupsafe-3.0.3-cp314-cp314t-win32.whl", hash = "sha256:915c04ba3851909ce68ccc2b8e2cd691618c4dc4c4232fb7982bca3f41fd8c3d", size = 14819, upload-time = "2025-09-27T18:37:26.285Z" },
+    { url = "https://files.pythonhosted.org/packages/1a/8a/0402ba61a2f16038b48b39bccca271134be00c5c9f0f623208399333c448/markupsafe-3.0.3-cp314-cp314t-win_amd64.whl", hash = "sha256:4faffd047e07c38848ce017e8725090413cd80cbc23d86e55c587bf979e579c9", size = 15426, upload-time = "2025-09-27T18:37:27.316Z" },
+    { url = "https://files.pythonhosted.org/packages/70/bc/6f1c2f612465f5fa89b95bead1f44dcb607670fd42891d8fdcd5d039f4f4/markupsafe-3.0.3-cp314-cp314t-win_arm64.whl", hash = "sha256:32001d6a8fc98c8cb5c947787c5d08b0a50663d139f1305bac5885d98d9b40fa", size = 14146, upload-time = "2025-09-27T18:37:28.327Z" },
+]
+
 [[package]]
 name = "numba"
 version = "0.62.1"
@@ -464,3 +588,15 @@ sdist = { url = "https://files.pythonhosted.org/packages/15/22/9ee70a2574a4f4599
 wheels = [
     { url = "https://files.pythonhosted.org/packages/a7/c2/fe1e52489ae3122415c51f387e221dd0773709bad6c6cdaa599e8a2c5185/urllib3-2.5.0-py3-none-any.whl", hash = "sha256:e6b01673c0fa6a13e374b50871808eb3bf7046c4b125b216f6bf1cc604cff0dc", size = 129795, upload-time = "2025-06-18T14:07:40.39Z" },
 ]
+
+[[package]]
+name = "werkzeug"
+version = "3.1.3"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "markupsafe" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/9f/69/83029f1f6300c5fb2471d621ab06f6ec6b3324685a2ce0f9777fd4a8b71e/werkzeug-3.1.3.tar.gz", hash = "sha256:60723ce945c19328679790e3282cc758aa4a6040e4bb330f53d30fa546d44746", size = 806925, upload-time = "2024-11-08T15:52:18.093Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/52/24/ab44c871b0f07f491e5d2ad12c9bd7358e527510618cb1b803a88e986db1/werkzeug-3.1.3-py3-none-any.whl", hash = "sha256:54b78bf3716d19a65be4fceccc0d1d7b89e608834989dfae50ea87564639213e", size = 224498, upload-time = "2024-11-08T15:52:16.132Z" },
+]

hkjc-0.3.16/process.py

@@ -1,4 +0,0 @@
-from hkjc import generate_historical_data
-
-df = generate_historical_data('2024-09-08', '2025-10-06')
-df.write_parquet('2024-2025-hkjc.parquet')

hkjc-0.3.16/src/hkjc/live_odds.py

@@ -1,136 +0,0 @@
-"""Functions to fetch and process data from HKJC
-"""
-from __future__ import annotations
-from typing import Tuple, List
-
-import requests
-from cachetools.func import ttl_cache
-import numpy as np
-
-from .utils import _validate_date, _validate_venue_code
-
-HKJC_LIVEODDS_ENDPOINT = "https://info.cld.hkjc.com/graphql/base/"
-
-LIVEODDS_PAYLOAD = {
-    "operationName": "racing",
-    "variables": {"date": None, "venueCode": None, "raceNo": None, "oddsTypes": None},
-    "query": """
-query racing($date: String, $venueCode: String, $oddsTypes: [OddsType], $raceNo: Int) {
-    raceMeetings(date: $date, venueCode: $venueCode) {
-        pmPools(oddsTypes: $oddsTypes, raceNo: $raceNo) {
-            id
-            status
-            sellStatus
-            oddsType
-            lastUpdateTime
-            guarantee
-            minTicketCost
-            name_en
-            name_ch
-            leg {
-                number
-                races
-            }
-            cWinSelections {
-                composite
-                name_ch
-                name_en
-                starters
-            }
-            oddsNodes {
-                combString
-                oddsValue
-                hotFavourite
-                oddsDropValue
-                bankerOdds {
-                    combString
-                    oddsValue
-                }
-            }
-        }
-    }
-}""",
-}
-
-
-@ttl_cache(maxsize=12, ttl=30)
-def _fetch_live_odds(date: str, venue_code: str, race_number: int, odds_type: Tuple[str] = ('PLA', 'QPL')) -> Tuple[dict]:
-    """Fetch live odds data from HKJC GraphQL endpoint."""
-    payload = LIVEODDS_PAYLOAD.copy()
-    payload["variables"] = payload["variables"].copy()
-    payload["variables"]["date"] = date
-    payload["variables"]["venueCode"] = venue_code
-    payload["variables"]["raceNo"] = race_number
-    payload["variables"]["oddsTypes"] = odds_type
-
-    headers = {
-        "Origin": "https://bet.hkjc.com",
-        "Referer": "https://bet.hkjc.com",
-        "Content-Type": "application/json",
-        "Accept": "application/json",
-        "User-Agent": "python-hkjc-fetch/0.1",
-    }
-
-    r = requests.post(HKJC_LIVEODDS_ENDPOINT, json=payload,
-                      headers=headers, timeout=10)
-    if r.status_code != 200:
-        raise RuntimeError(f"Request failed: {r.status_code} - {r.text}")
-
-    meetings = r.json().get("data", {}).get("raceMeetings", [])
-
-    return [
-        {"HorseID": node["combString"], "Type": pool.get(
-            "oddsType"), "Odds": float(node["oddsValue"])}
-        for meeting in meetings
-        for pool in meeting.get("pmPools", [])
-        for node in pool.get("oddsNodes", [])
-    ]
-
-
-def live_odds(date: str, venue_code: str, race_number: int, odds_type: List[str] = ['PLA', 'QPL']) -> dict:
-    """Fetch live odds as numpy arrays.
-
-    Args:
-        date (str): Date in 'YYYY-MM-DD' format.
-        venue_code (str): Venue code, e.g., 'ST' for Shatin, 'HV' for Happy Valley.
-        race_number (int): Race number.
-        odds_type (List[str]): Types of odds to fetch. Default is ['PLA', 'QPL']. Currently the following types are supported:
-            - 'WIN': Win odds
-            - 'PLA': Place odds
-            - 'QIN': Quinella odds
-            - 'QPL': Quinella Place odds
-        fit_harville (bool): Whether to fit the odds using Harville model. Default is False.
-
-    Returns:
-        dict: Dictionary with keys as odds types and values as numpy arrays containing the odds.
-            If odds_type is 'WIN','PLA', returns a 1D array of place odds.
-            If odds_type is 'QIN','QPL', returns a 2D array of quinella place odds. 
-    """
-    _validate_date(date)
-    _validate_venue_code(venue_code)
-
-    mandatory_types = ['PLA']
-
-    data = _fetch_live_odds(date, venue_code, race_number,
-                            odds_type=tuple(set(mandatory_types+odds_type)))
-
-    # use place odds to determine number of horses
-    pla_data = [entry for entry in data if entry["Type"] == "PLA"]
-    N = len(pla_data)
-
-    odds = {'WIN': np.full(N, np.nan, dtype=float),
-            'PLA': np.full(N, np.nan, dtype=float),
-            'QIN': np.full((N, N), np.nan, dtype=float),
-            'QPL': np.full((N, N), np.nan, dtype=float)}
-
-    for entry in data:
-        if entry["Type"] in ["QIN", "QPL"]:
-            horse_ids = list(map(int, entry["HorseID"].split(",")))
-            odds[entry["Type"]][horse_ids[0] - 1,
-                                horse_ids[1] - 1] = entry["Odds"]
-            odds[entry["Type"]][horse_ids[1] - 1,
-                                horse_ids[0] - 1] = entry["Odds"]
-        elif entry["Type"] in ["PLA", "WIN"]:
-            odds[entry["Type"]][int(entry["HorseID"]) - 1] = entry["Odds"]
-
-    return {t: odds[t] for t in odds_type}