Qubx 0.1.6__cp311-cp311-manylinux_2_35_x86_64.whl → 0.1.8__cp311-cp311-manylinux_2_35_x86_64.whl

qubx/data/readers.py

@@ -29,6 +29,13 @@ def _recognize_t(t: Union[int, str], defaultvalue, timeunit) -> int:
     return defaultvalue
 
 
+def _time(t, timestamp_units: str) -> int:
+    t = int(t) if isinstance(t, float) else t
+    if timestamp_units == 'ns':
+        return np.datetime64(t, 'ns').item() 
+    return np.datetime64(t, timestamp_units).astype('datetime64[ns]').item()
+
+
 def _find_column_index_in_list(xs, *args):
     xs = [x.lower() for x in xs]
     for a in args:
@@ -38,6 +45,9 @@ def _find_column_index_in_list(xs, *args):
     raise IndexError(f"Can't find any from {args} in list: {xs}")
 
 
+_FIND_TIME_COL_IDX = lambda column_names: _find_column_index_in_list(column_names, 'time', 'timestamp', 'datetime', 'date', 'open_time')
+
+
 class DataTransformer:
 
     def __init__(self) -> None:
@@ -121,9 +131,9 @@ class CsvStorageDataReader(DataReader):
         # - try to find range to load  
         start_idx, stop_idx = 0, table.num_rows
         try:
-            _time_field_idx = _find_column_index_in_list(fieldnames, 'time', 'timestamp', 'datetime', 'date')
+            _time_field_idx = _FIND_TIME_COL_IDX(fieldnames)
             _time_type = table.field(_time_field_idx).type
-            _time_unit = _time_type.unit if hasattr(_time_type, 'unit') else 's'
+            _time_unit = _time_type.unit if hasattr(_time_type, 'unit') else 'ms'
             _time_data = table[_time_field_idx]
 
             # - check if need convert time to primitive types (i.e. Date32 -> timestamp[x])
@@ -181,9 +191,11 @@ class AsPandasFrame(DataTransformer):
     """
     List of records to pandas dataframe transformer
     """
+    def __init__(self, timestamp_units=None) -> None:
+        self.timestamp_units = timestamp_units
 
     def start_transform(self, name: str, column_names: List[str]):
-        self._time_idx = _find_column_index_in_list(column_names, 'time', 'timestamp', 'datetime', 'date')
+        self._time_idx = _FIND_TIME_COL_IDX(column_names)
         self._column_names = column_names
         self._frame = pd.DataFrame()
     
@@ -191,6 +203,8 @@ class AsPandasFrame(DataTransformer):
         self._frame
         p = pd.DataFrame.from_records(rows_data, columns=self._column_names)
         p.set_index(self._column_names[self._time_idx], drop=True, inplace=True)
+        p.index = pd.to_datetime(p.index, unit=self.timestamp_units) if self.timestamp_units else p.index
+        p.index.rename('timestamp', inplace=True)
         p.sort_index(inplace=True)
         self._frame = pd.concat((self._frame, p), axis=0, sort=True)
         return p
@@ -200,6 +214,17 @@ class AsPandasFrame(DataTransformer):
 
 
 class AsOhlcvSeries(DataTransformer):
+    """
+    Convert incoming data into OHLCV series.
+
+    Incoming data may have one of the following structures: 
+
+        ```
+        ohlcv:        time,open,high,low,close,volume|quote_volume,(buy_volume)
+        quotes:       time,bid,ask,bidsize,asksize
+        trades (TAS): time,price,size,(is_taker)
+        ```
+    """
 
     def __init__(self, timeframe: str | None = None, timestamp_units='ns') -> None:
         super().__init__()
@@ -209,7 +234,7 @@ class AsOhlcvSeries(DataTransformer):
         self.timestamp_units = timestamp_units
 
     def start_transform(self, name: str, column_names: List[str]):
-        self._time_idx = _find_column_index_in_list(column_names, 'time', 'timestamp', 'datetime', 'date')
+        self._time_idx = _FIND_TIME_COL_IDX(column_names)
         self._volume_idx = None
         self._b_volume_idx = None
         try:
@@ -251,15 +276,10 @@ class AsOhlcvSeries(DataTransformer):
         if self.timeframe:
             self._series = OHLCV(self._name, self.timeframe)
 
-    def _time(self, t) -> int:
-        if self.timestamp_units == 'ns':
-            return np.datetime64(t, 'ns').item() 
-        return np.datetime64(t, self.timestamp_units).astype('datetime64[ns]').item()
-
     def _proc_ohlc(self, rows_data: List[List]):
         for d in rows_data:
             self._series.update_by_bar(
-                self._time(d[self._time_idx]),
+                _time(d[self._time_idx], self.timestamp_units),
                 d[self._open_idx], d[self._high_idx], d[self._low_idx], d[self._close_idx], 
                 d[self._volume_idx] if self._volume_idx else 0,
                 d[self._b_volume_idx] if self._b_volume_idx else 0
@@ -268,7 +288,7 @@ class AsOhlcvSeries(DataTransformer):
     def _proc_quotes(self, rows_data: List[List]):
         for d in rows_data:
             self._series.update(
-                self._time(d[self._time_idx]),
+                _time(d[self._time_idx], self.timestamp_units),
                 (d[self._ask_idx] + d[self._bid_idx])/2
             )
 
@@ -277,7 +297,7 @@ class AsOhlcvSeries(DataTransformer):
             a = d[self._taker_idx] if self._taker_idx else 0
             s = d[self._size_idx]
             b = s if a else 0 
-            self._series.update(self._time(d[self._time_idx]), d[self._price_idx], s, b)
+            self._series.update(_time(d[self._time_idx], self.timestamp_units), d[self._price_idx], s, b)
 
     def process_data(self, rows_data: List[List]) -> Any:
         if self._series is None:
@@ -302,10 +322,14 @@ class AsOhlcvSeries(DataTransformer):
 
 
 class AsQuotes(DataTransformer):
+    """
+    Tries to convert incoming data to list of Quote's
+    Data must have appropriate structure: bid, ask, bidsize, asksize and time
+    """
 
     def start_transform(self, name: str, column_names: List[str]):
         self.buffer = list()
-        self._time_idx = _find_column_index_in_list(column_names, 'time', 'timestamp', 'datetime')
+        self._time_idx = _FIND_TIME_COL_IDX(column_names)
         self._bid_idx = _find_column_index_in_list(column_names, 'bid')
         self._ask_idx = _find_column_index_in_list(column_names, 'ask')
         self._bidvol_idx = _find_column_index_in_list(column_names, 'bidvol', 'bid_vol', 'bidsize', 'bid_size')
@@ -320,6 +344,48 @@ class AsQuotes(DataTransformer):
                 bv = d[self._bidvol_idx]
                 av = d[self._askvol_idx]
                 self.buffer.append(Quote(t.as_unit('ns').asm8.item(), b, a, bv, av))
+                
+
+class AsTimestampedRecords(DataTransformer):
+    """
+    Convert incoming data to list or dictionaries with preprocessed timestamps ('timestamp_ns' and 'timestamp')
+    ```
+    [
+        {
+            'open_time': 1711944240000.0,
+            'open': 203.219,
+            'high': 203.33,
+            'low': 203.134,
+            'close': 203.175,
+            'volume': 10060.0,
+            ....
+            'timestamp_ns': 1711944240000000000,
+            'timestamp': Timestamp('2024-04-01 04:04:00')
+        },
+        ...
+    ] ```
+    """
+
+    def __init__(self, timestamp_units: str | None=None) -> None:
+        self.timestamp_units = timestamp_units
+
+    def start_transform(self, name: str, column_names: List[str]):
+        self.buffer = list()
+        self._time_idx = _FIND_TIME_COL_IDX(column_names)
+        self._column_names = column_names
+
+    def process_data(self, rows_data: Iterable) -> Any:
+        self.buffer.extend(rows_data)
+
+    def collect(self) -> Any:
+        res = []
+        for r in self.buffer:
+            t = r[self._time_idx]
+            if self.timestamp_units:
+                t = _time(t, self.timestamp_units)
+            di = dict(zip(self._column_names, r)) | { 'timestamp_ns': t, 'timestamp': pd.Timestamp(t) }
+            res.append(di)
+        return res
 
 
 class RestoreTicksFromOHLC(DataTransformer):
@@ -344,7 +410,7 @@ class RestoreTicksFromOHLC(DataTransformer):
     def start_transform(self, name: str, column_names: List[str]):
         self.buffer = []
         # - it will fail if receive data doesn't look as ohlcv 
-        self._time_idx = _find_column_index_in_list(column_names, 'time', 'timestamp', 'datetime', 'date')
+        self._time_idx = _FIND_TIME_COL_IDX(column_names)
         self._open_idx = _find_column_index_in_list(column_names, 'open')
         self._high_idx = _find_column_index_in_list(column_names, 'high')
         self._low_idx = _find_column_index_in_list(column_names, 'low')
@@ -441,23 +507,25 @@ class QuestDBConnector(DataReader):
     """
     Very first version of QuestDB connector
 
-    # Connect to an existing QuestDB instance
-    >>> db = QuestDBConnector('user=admin password=quest host=localhost port=8812', OhlcvPandasDataProcessor())
-    >>> db.read('BINANCEF.ETHUSDT', '2024-01-01')
+    ### Connect to an existing QuestDB instance
+    >>> db = QuestDBConnector()
+    >>> db.read('BINANCE.UM:ETHUSDT', '2024-01-01', transform=AsPandasFrame())
     """
     _reconnect_tries = 5
     _reconnect_idle = 0.1  # wait seconds before retying
 
-    def __init__(self, connection_url: str) -> None:
+    def __init__(self, host='localhost', user='admin', password='quest', port=8812) -> None:
         self._connection = None
         self._cursor = None
-        self.connection_url = connection_url
+        self._host = host
+        self._port = port
+        self.connection_url = f'user={user} password={password} host={host} port={port}'
         self._connect()
 
     def _connect(self):
-        logger.info("Connecting to QuestDB ...")
         self._connection = pg.connect(self.connection_url, autocommit=True)
         self._cursor = self._connection.cursor()
+        logger.debug(f"Connected to QuestDB at {self._host}:{self._port}")
 
     @_retry
     def read(self, data_id: str, start: str|None=None, stop: str|None=None, 
@@ -476,14 +544,49 @@ class QuestDBConnector(DataReader):
         transform.process_data(records)
         return transform.collect()
 
-    def _prepare_data_sql(self, data_id: str, start: str|None, end: str|None, resample: str) -> str:
-        # just a temp hack - actually we need to discuss symbology etc
-        symbol = data_id#.split('.')[-1]
+    @staticmethod
+    def _convert_time_delta_to_qdb_resample_format(c_tf: str):
+        if c_tf:
+            _t = re.match(r'(\d+)(\w+)', c_tf)
+            if _t and len(_t.groups()) > 1:
+                c_tf = f"{_t[1]}{_t[2][0].lower()}"
+        return c_tf 
+
+    def _get_table_name(self, data_id: str, sfx: str='') -> str:
+        """
+        Get table name for data_id
+        data_id can have format <exchange>.<type>:<symbol>
+        for example: 
+            BINANCE.UM:BTCUSDT or BINANCE:BTCUSDT for spot 
+        """
+        _aliases = {'um': 'umfutures', 'cm': 'cmfutures', 'f': 'futures'}
+        table_name = data_id
+        _ss = data_id.split(':')
+        if len(_ss) > 1:
+            _exch, symb = _ss
+            _mktype = 'spot'
+            _ss = _exch.split('.')
+            if len(_ss) > 1:
+                _exch = _ss[0]
+                _mktype = _ss[1]
+            _mktype = _mktype.lower()
+            table_name = '.'.join(filter(lambda x: x, [_exch.lower(), _aliases.get(_mktype, _mktype), symb.lower(), sfx]))
+        return table_name
 
+    def _prepare_data_sql(self, data_id: str, start: str|None, end: str|None, resample: str) -> str:
+        where = ''
         w0 = f"timestamp >= '{start}'" if start else ''
         w1 = f"timestamp <= '{end}'" if end else ''
-        where = f'where {w0} and {w1}' if (w0 and w1) else f"where {(w0 or w1)}"
 
+        # - fix: when no data ranges are provided we must skip empy where keyword
+        if w0 or w1: 
+            where = f'where {w0} and {w1}' if (w0 and w1) else f"where {(w0 or w1)}"
+
+        # - check resample format
+        resample = QuestDBConnector._convert_time_delta_to_qdb_resample_format(resample) if resample else resample
+        _rsmpl = f"SAMPLE by {resample}" if resample else ''
+
+        table_name = self._get_table_name(data_id, 'candles_1m')
         return f"""
                 select timestamp, 
                 first(open) as open, 
@@ -495,8 +598,7 @@ class QuestDBConnector(DataReader):
                 sum(count) as count,
                 sum(taker_buy_volume) as taker_buy_volume,
                 sum(taker_buy_quote_volume) as taker_buy_quote_volume
-                from "{symbol.upper()}" {where}
-                SAMPLE by {resample};
+                from "{table_name}" {where} {_rsmpl};
             """ 
 
     def _prepare_names_sql(self) -> str:

{qubx-0.1.6.dist-info → qubx-0.1.8.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: Qubx
-Version: 0.1.6
+Version: 0.1.8
 Summary: Qubx - quantitative trading framework
 Home-page: https://github.com/dmarienko/Qubx
 Author: Dmitry Marienko

{qubx-0.1.6.dist-info → qubx-0.1.8.dist-info}/RECORD

@@ -6,13 +6,13 @@ qubx/core/basics.py,sha256=2u7WV5KX-RbTmzoKfi1yT4HNLDPfQcFMCUZ1pVsM_VE,14777
 qubx/core/helpers.py,sha256=gPE78dO718NBY0-JbfqNGCzIvr4BVatFntNIy2RUrEY,11559
 qubx/core/loggers.py,sha256=HpgavBZegoDv9ssihtqX0pitXKULVAPHUpoE_volJw0,11910
 qubx/core/lookups.py,sha256=4aEC7b2AyEXFqHHGDenex3Z1FZGrpDSb8IwzBZrSqIA,13688
-qubx/core/series.cpython-311-x86_64-linux-gnu.so,sha256=48xXevH8u0RzK6uWFve0vgd6cCFBQcUqyXWRzOww198,698952
+qubx/core/series.cpython-311-x86_64-linux-gnu.so,sha256=ltVxtoC4f0B4skXk6yRtoryDzon6gwLX_3NuX7gb5io,698952
 qubx/core/series.pxd,sha256=IS89NQ5FYp3T0YIHe1lELKZIAKrNvX8K6WlLyac44I4,2847
 qubx/core/series.pyx,sha256=WEAjn4j3zn540Cxx68X5gRXilvwa7NGdbki6myzZbIM,28108
 qubx/core/strategy.py,sha256=Fs4fFyHaEGYuz7mBeQHBWFu3Ipg0yFzcxXhskgsPxJE,30330
-qubx/core/utils.cpython-311-x86_64-linux-gnu.so,sha256=bNoo-8OPy-YeF0AgPNPhBkcWjHuMWSIke-WiAKlA6wU,74216
+qubx/core/utils.cpython-311-x86_64-linux-gnu.so,sha256=5ddzSg68VpiWMCEtase_w0XhyEb4DUjP7xWxL55XQ4k,74216
 qubx/core/utils.pyx,sha256=6dQ8R02bl8V3f-W3Wk9-e86D9OvDz-5-4NA_dlF_xwc,1368
-qubx/data/readers.py,sha256=i_QbRaCXc5Lf4G22XIsl86YZBS0OrFSJq4wDuo3k-5w,21310
+qubx/data/readers.py,sha256=EuYLt7mmf4TPtVzlbbxGvgw-luR7oDPwdLJQe37iU6c,24786
 qubx/impl/ccxt_connector.py,sha256=NqF-tgxfTATnmVqKUonNXCAzECrDU8YrgqM3Nq06fw8,9150
 qubx/impl/ccxt_customizations.py,sha256=kK_4KmOyKvDVgd4MTkVg4CyqdjE-6r41siZIvLj-A-Q,3488
 qubx/impl/ccxt_trading.py,sha256=cmg4P-zd78w-V8j3-IGS2LFxikGhxFPgmCvz3sr065Q,9097
@@ -23,7 +23,7 @@ qubx/pandaz/__init__.py,sha256=Iw5uzicYGSC3FEKZ-W1O5-7cXq_P0kH11-EcXV0zZhs,175
 qubx/pandaz/ta.py,sha256=TUvjrvmk4EQvDcXoRp6Os08-HUap-ZvpSDGawhViOgg,85271
 qubx/pandaz/utils.py,sha256=FyLKQy8spkqxhBij_nPFC_ZzI_L3-IgB9O53MqWKmq0,19109
 qubx/ta/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-qubx/ta/indicators.cpython-311-x86_64-linux-gnu.so,sha256=ktYA1gKh1Lo-rNWs7LkeVcBu_6r4duK_Ju9hyzlKgQ8,284552
+qubx/ta/indicators.cpython-311-x86_64-linux-gnu.so,sha256=JDkaQwaNS6-J9ICrxJsATcSxaZKvURf0jtQ-09vhUGg,284552
 qubx/ta/indicators.pyx,sha256=P-GEYUks2lSHo6hbtUFAB7TWE1AunjLR4jIjwqPHrwU,7708
 qubx/trackers/__init__.py,sha256=1y_yvIy0OQwBqfhAW_EY33NxFzFSWvI0qNAPU6zchYc,60
 qubx/trackers/rebalancers.py,sha256=QCzANCooZBi2VMCBjjCPMq_Dt1h1zrBelATnfmVve74,5522
@@ -34,6 +34,6 @@ qubx/utils/marketdata/binance.py,sha256=36dl4rxOAGTeY3uoONmiPanj8BkP0oBdDiH-URJJ
 qubx/utils/misc.py,sha256=z5rdz5hbRu9-F2QgF47OCkMvhfIkRKs-PHR8L5DWkBM,9831
 qubx/utils/runner.py,sha256=OY7SoRfxHwzn0rKTGB_lbg5zNASEL_49hQXWqs-LiMk,9306
 qubx/utils/time.py,sha256=_DjCdQditzZwMy_8rvPdWyw5tjw__2p24LMPgXdZ8i0,4911
-qubx-0.1.6.dist-info/METADATA,sha256=y_DcaF5WFk44CtZCJVQWfsON1wEAa1iSvz5cZjshGA8,2490
-qubx-0.1.6.dist-info/WHEEL,sha256=MLOa6LysROdjgj4FVxsHitAnIh8Be2D_c9ZSBHKrz2M,110
-qubx-0.1.6.dist-info/RECORD,,
+qubx-0.1.8.dist-info/METADATA,sha256=W62rM-gCLkzeF0GQ087NFox6vZ6wQBouO_aSfRaDoV8,2490
+qubx-0.1.8.dist-info/WHEEL,sha256=MLOa6LysROdjgj4FVxsHitAnIh8Be2D_c9ZSBHKrz2M,110
+qubx-0.1.8.dist-info/RECORD,,