hkjc 0.3.16__py3-none-any.whl → 0.3.18__py3-none-any.whl

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/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/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/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.dist-info → hkjc-0.3.18.dist-info}/METADATA

@@ -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-0.3.16.dist-info → hkjc-0.3.18.dist-info}/RECORD

@@ -1,14 +1,14 @@
-hkjc/__init__.py,sha256=TI7PVhmoWSvYX-xdTEdaT3jfY99LiYQFRQZaIwBhJd8,785
+hkjc/__init__.py,sha256=5A9MzcITYJDcA2UbIBpkimZBYSqS4pgRuQJhTagOfpE,753
 hkjc/analysis.py,sha256=0042_NMIkQCl0J6B0P4TFfrBDCnm2B6jsCZKOEO30yI,108
 hkjc/harville_model.py,sha256=MZjPLS-1nbEhp1d4Syuq13DtraKnd7TlNqBmOOCwxgc,15976
-hkjc/historical.py,sha256=R_7z0yqLDj57G5JgvuPYDxKLBoqlhfpRnpTER6aeluM,6678
-hkjc/live_odds.py,sha256=G4ELBBp1d2prxye9kKzu2pwtS4vSfRPOmEuT7-Nd-3A,4741
-hkjc/processing.py,sha256=KZFrGuCdCEJ5OI54PnrWhy-c9qx7mcWm12chc3HuDO8,7764
+hkjc/historical.py,sha256=v9k_R47Na5en5ftrocjIHofkNAUthE_lp4CyLaCTsQE,8280
+hkjc/live.py,sha256=GqctH-BVdIL6Vi1g8XHe3p8fZBopCQf5KACLAR0meP0,10249
+hkjc/processing.py,sha256=H0chtW_FBMMhK3IzcjYjrryd3fAPYimanc2fWuGiB0M,6807
 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-0.3.16.dist-info/METADATA,sha256=yusLSNb82ebKoie5iUxlO5XE9mBBfPiIBHmRepLXA9c,481
-hkjc-0.3.16.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-hkjc-0.3.16.dist-info/RECORD,,
+hkjc-0.3.18.dist-info/METADATA,sha256=aoXp6Fvn3EkuXyv6p5LClSbZa5XS_bfcUxMKBJXcNvw,480
+hkjc-0.3.18.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+hkjc-0.3.18.dist-info/RECORD,,

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}