Merge pull request #37 from legend-exp/pydataobj-update

Support the latest legend-pydataobj version

docs/source/notebooks/DSPTutorial.ipynb

@@ -46,14 +46,14 @@
     "import matplotlib.pyplot as plt\n",
     "import numpy as np\n",
     "\n",
-    "import lgdo.lh5_store as lh5\n",
+    "from lgdo import lh5\n",
     "from legendtestdata import LegendTestData\n",
     "\n",
     "# Get some sample waveforms from LEGEND test data\n",
     "ldata = LegendTestData()\n",
     "raw_file = ldata.get_path(\"lh5/LDQTA_r117_20200110T105115Z_cal_geds_raw.lh5\")\n",
     "st = lh5.LH5Store()\n",
-    "tab = st.read_object(\"geds/raw\", raw_file)[0]\n",
+    "tab = st.read(\"geds/raw\", raw_file)[0]\n",
     "wfs = tab[\"waveform\"].values.nda.astype(\"float32\")\n",
     "t = tab[\"waveform\"].dt.nda.reshape((100, 1)) * np.arange(wfs.shape[1])\n",
     "baselines = tab[\"baseline\"].nda\n",
@@ -731,7 +731,7 @@
     "\n",
     "lh5.show(\"test_dsp.lh5\")\n",
     "print()\n",
-    "print(st.read_object(\"geds/dsp\", \"test_dsp.lh5\")[0].get_dataframe())"
+    "print(st.read(\"geds/dsp\", \"test_dsp.lh5\")[0].get_dataframe())"
    ]
   },
   {

docs/source/notebooks/IntroToDSP.ipynb

@@ -21,7 +21,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from lgdo import LH5Store, ls, show, load_dfs\n",
+    "from lgdo.lh5 import LH5Store, ls, show, load_dfs\n",
     "from dspeed.vis import WaveformBrowser\n",
     "from dspeed import units\n",
     "from dspeed import build_dsp\n",
@@ -510,7 +510,7 @@
    "outputs": [],
    "source": [
     "store = LH5Store()\n",
-    "obj, nrows = store.read_object(\"geds/dsp\", \"./example_dsp_file.lh5\")\n",
+    "obj, nrows = store.read(\"geds/dsp\", \"./example_dsp_file.lh5\")\n",
     "print(\n",
     "    f\"We have saved the following list of outputs from our DSP routine: {list(obj.keys())}\"\n",
     ")\n",

docs/source/notebooks/WaveformBrowser.ipynb

@@ -29,7 +29,7 @@
     "\n",
     "u = pint.get_application_registry()\n",
     "\n",
-    "import lgdo.lh5_store as lh5\n",
+    "from lgdo import lh5\n",
     "from dspeed.vis.waveform_browser import WaveformBrowser\n",
     "from legendtestdata import LegendTestData\n",
     "\n",
@@ -132,7 +132,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from lgdo import load_dfs\n",
+    "from lgdo.lh5 import load_dfs\n",
     "\n",
     "df = load_dfs(dsp_file, [\"trapEmax\", \"AoE\"], \"geds/dsp\")"
    ]

setup.cfg

@@ -35,7 +35,7 @@ install_requires =
     colorlog
     h5py>=3.2
     iminuit
-    legend-pydataobj~=1.0
+    legend-pydataobj>=1.5.0a1
     matplotlib
     numba!=0.53.*,!=0.54.*
     parse

src/dspeed/build_dsp.py

@@ -9,9 +9,8 @@
 import os
 
 import h5py
-import lgdo.lh5_store as lh5
 import numpy as np
-from lgdo.lgdo_utils import expand_path
+from lgdo import lh5
 from tqdm.auto import tqdm
 
 from .errors import DSPFatal
@@ -133,7 +132,7 @@ def build_dsp(
     # get the database parameters. For now, this will just be a dict in a json
     # file, but eventually we will want to interface with the metadata repo
     if isinstance(database, str):
-        with open(expand_path(database)) as db_file:
+        with open(lh5.utils.expand_path(database)) as db_file:
             database = json.load(db_file)
 
     if database and not isinstance(database, dict):
@@ -190,7 +189,7 @@ def build_dsp(
                 e.wf_range = f"{e.wf_range[0]+start_row}-{e.wf_range[1]+start_row}"
                 raise e
 
-            raw_store.write_object(
+            raw_store.write(
                 obj=tb_out,
                 name=tb_name,
                 lh5_file=f_dsp,

src/dspeed/processing_chain.py

@@ -16,10 +16,8 @@
 from typing import Any
 
 import lgdo
-import lgdo.lh5_store as lh5
 import numpy as np
-from lgdo import LGDO
-from lgdo.lgdo_utils import expand_path
+from lgdo import LGDO, lh5
 from numba import vectorize
 from pint import Quantity, Unit
 
@@ -1111,7 +1109,7 @@ def _loadlh5(path_to_file, path_in_file: str) -> np.array:  # noqa: N805
         """
 
         try:
-            loaded_data = sto.read_object(path_in_file, path_to_file)[0].nda
+            loaded_data = sto.read(path_in_file, path_to_file)[0].nda
         except ValueError:
             raise ProcessingChainError(f"LH5 file not found: {path_to_file}")
 
@@ -1780,8 +1778,8 @@ def build_processing_chain(
     block_width: int = 16,
 ) -> tuple[ProcessingChain, list[str], lgdo.Table]:
     """Produces a :class:`ProcessingChain` object and an LH5
-    :class:`~lgdo.table.Table` for output parameters from an input LH5
-    :class:`~lgdo.table.Table` and a JSON recipe.
+    :class:`~lgdo.types.table.Table` for output parameters from an input LH5
+    :class:`~lgdo.types.table.Table` and a JSON recipe.
 
     Parameters
     ----------
@@ -1863,7 +1861,7 @@ def build_processing_chain(
     proc_chain = ProcessingChain(block_width, lh5_in.size)
 
     if isinstance(dsp_config, str):
-        with open(expand_path(dsp_config)) as f:
+        with open(lh5.utils.expand_path(dsp_config)) as f:
             dsp_config = json.load(f)
     elif dsp_config is None:
         dsp_config = {"outputs": [], "processors": {}}

src/dspeed/processors/wiener_filter.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
-import lgdo.lh5_store as lh5
 import numpy as np
+from lgdo import lh5
 from numba import guvectorize
 
 from ..errors import DSPFatal
@@ -65,10 +65,10 @@ def wiener_filter(file_name_array: list[str]) -> np.ndarray:
 
     # Read in the data
 
-    superpulse, _ = sto.read_object("spms/processed/superpulse", file_name)
+    superpulse, _ = sto.read("spms/processed/superpulse", file_name)
     superpulse = superpulse.nda
 
-    noise_wf, _ = sto.read_object("spms/processed/noise_wf", file_name)
+    noise_wf, _ = sto.read("spms/processed/noise_wf", file_name)
     noise_wf = noise_wf.nda
 
     # Now check that the data are valid

src/dspeed/vis/waveform_browser.py

@@ -5,12 +5,13 @@
 import string
 import sys
 
-import lgdo.lh5_store as lh5
+import lgdo
 import matplotlib.pyplot as plt
 import numpy as np
 import pandas
 import pint
 from cycler import cycler
+from lgdo import lh5
 from matplotlib.lines import Line2D
 
 from ..processing_chain import build_processing_chain
@@ -28,7 +29,7 @@ class WaveformBrowser:
 
     def __init__(
         self,
-        files_in: str | list[str] | lgdo.LH5Iterator,  # noqa: F821
+        files_in: str | list[str] | lh5.LH5Iterator,  # noqa: F821
         lh5_group: str | list[str] = "",
         base_path: str = "",
         entry_list: list[int] | list[list[int]] = None,
@@ -61,7 +62,7 @@ def __init__(
             and group, they must be the same size. If a file is wild-carded,
             the same group will be assigned to each file found
         base_path
-            base path for file. See :class:`~lgdo.lh5_store.LH5Store`.
+            base path for file. See :class:`~lgdo.lh5.LH5Store`.
 
         entry_list
             list of event indices to draw. If it is a nested list, use local
@@ -293,7 +294,7 @@ def __init__(
         # If we still have no x_unit get it from the first waveform we can find
         if self.x_unit is None:
             for wf in self.lh5_out.values():
-                if not isinstance(wf, lh5.WaveformTable):
+                if not isinstance(wf, lgdo.WaveformTable):
                     continue
                 self.x_unit = ureg(wf.dt_units)
 
@@ -390,7 +391,7 @@ def find_entry(
             ref_time = 0
         elif isinstance(self.align_par, str):
             data = self.lh5_out.get(self.align_par, None)
-            if isinstance(data, lh5.Array):
+            if isinstance(data, lgdo.Array):
                 ref_time = data.nda[i_tb]
                 unit = data.attrs.get("units", None)
                 if unit and unit in ureg and ureg.is_compatible_with(unit, self.x_unit):
@@ -405,7 +406,7 @@ def find_entry(
         for name, lines in self.lines.items():
             # Get the data; note this is implicitly copying it!
             data = self.lh5_out.get(name, None)
-            if isinstance(data, lh5.WaveformTable):
+            if isinstance(data, lgdo.WaveformTable):
                 y = data.values.nda[i_tb, :] / norm
                 dt = data.dt.nda[i_tb] * float(ureg(data.dt_units) / self.x_unit)
                 t0 = (
@@ -416,13 +417,13 @@ def find_entry(
                 lines.append(Line2D(x, y))
                 self._update_auto_limit(x, y)
 
-            elif isinstance(data, lh5.ArrayOfEqualSizedArrays):
+            elif isinstance(data, lgdo.ArrayOfEqualSizedArrays):
                 y = data.nda[i_tb, :] / norm
                 x = np.arange(len(y), dtype="float")
                 lines.append(Line2D(x, y))
                 self._update_auto_limit(x, y)
 
-            elif isinstance(data, lh5.Array):
+            elif isinstance(data, lgdo.Array):
                 val = data.nda[i_tb]
                 unit = data.attrs.get("units", None)
                 if unit and unit in ureg and ureg.is_compatible_with(unit, self.x_unit):
@@ -453,7 +454,7 @@ def find_entry(
 
             if not data:
                 data = ureg.Quantity(self.aux_vals[name][entry])
-            elif isinstance(data, lh5.Array):
+            elif isinstance(data, lgdo.Array):
                 unit = data.attrs.get("units", None)
                 if unit and unit in ureg:
                     data = data.nda[i_tb] * ureg(unit)

tests/conftest.py

@@ -11,7 +11,7 @@
 import numpy as np
 import pytest
 from legendtestdata import LegendTestData
-from lgdo import LH5Store
+from lgdo.lh5 import LH5Store
 
 import dspeed.processors  # noqa: F401
 
@@ -42,7 +42,7 @@ def lgnd_test_data():
 @pytest.fixture(scope="session")
 def geds_raw_tbl(lgnd_test_data):
     store = LH5Store()
-    obj, _ = store.read_object(
+    obj, _ = store.read(
         "/geds/raw",
         lgnd_test_data.get_path("lh5/LDQTA_r117_20200110T105115Z_cal_geds_raw.lh5"),
         n_rows=10,
@@ -53,7 +53,7 @@ def geds_raw_tbl(lgnd_test_data):
 @pytest.fixture(scope="session")
 def spms_raw_tbl(lgnd_test_data):
     store = LH5Store()
-    obj, _ = store.read_object(
+    obj, _ = store.read(
         "/ch0/raw",
         lgnd_test_data.get_path("lh5/L200-comm-20211130-phy-spms.lh5"),
         n_rows=10,

tests/processors/test_histogram.py

@@ -1,6 +1,6 @@
 import os
 
-import lgdo.lh5_store as store
+from lgdo import lh5
 
 from dspeed import build_dsp
 
@@ -28,7 +28,7 @@ def test_histogram_fixed_width(lgnd_test_data, tmptestdir):
     )
     assert os.path.exists(dsp_file)
 
-    df = store.load_nda(dsp_file, ["hist_weights", "hist_borders"], "geds/dsp/")
+    df = lh5.load_nda(dsp_file, ["hist_weights", "hist_borders"], "geds/dsp/")
 
     assert len(df["hist_weights"][0]) + 1 == len(df["hist_borders"][0])
     for i in range(2, len(df["hist_borders"][0])):

tests/test_build_dsp.py

@@ -3,7 +3,7 @@
 
 import lgdo
 import pytest
-from lgdo.lh5_store import LH5Store, ls
+from lgdo.lh5 import LH5Store, ls
 
 from dspeed import build_dsp
 
@@ -72,7 +72,7 @@ def test_build_dsp_spms_channelwise(dsp_test_file_spm):
     ]
 
     store = LH5Store()
-    lh5_obj, n_rows = store.read_object("/ch0/dsp/energies", dsp_test_file_spm)
+    lh5_obj, n_rows = store.read("/ch0/dsp/energies", dsp_test_file_spm)
     assert isinstance(lh5_obj, lgdo.ArrayOfEqualSizedArrays)
     assert len(lh5_obj) == 5
     assert len(lh5_obj.nda[0]) == 20

tests/test_list_parsing.py

@@ -1,8 +1,8 @@
 import os
 from pathlib import Path
 
-import lgdo.lh5_store as store
 import numpy as np
+from lgdo import lh5
 
 from dspeed import build_dsp
 
@@ -33,6 +33,6 @@ def test_list_parisng(lgnd_test_data, tmptestdir):
     )
     assert os.path.exists(dsp_file)
 
-    df = store.load_nda(dsp_file, ["wf_out"], "geds/dsp/")
+    df = lh5.load_nda(dsp_file, ["wf_out"], "geds/dsp/")
 
     assert np.all(df["wf_out"][:] == np.array([7, 9, 11, 13, 15]))

tests/test_numpy_constants_parsing.py

@@ -1,8 +1,8 @@
 import os
 from pathlib import Path
 
-import lgdo.lh5_store as store
 import numpy as np
+from lgdo import lh5
 
 from dspeed import build_dsp
 
@@ -24,7 +24,7 @@ def test_build_dsp(lgnd_test_data, tmptestdir):
 
 def test_numpy_math_constants_dsp(tmptestdir):
     dsp_file = f"{tmptestdir}/LDQTA_r117_20200110T105115Z_cal_geds__numpy_test_dsp.lh5"
-    df = store.load_nda(dsp_file, ["timestamp", "calc1", "calc2", "calc3"], "geds/dsp/")
+    df = lh5.load_nda(dsp_file, ["timestamp", "calc1", "calc2", "calc3"], "geds/dsp/")
 
     a1 = df["timestamp"] - df["timestamp"] - np.pi * df["timestamp"]
     a2 = df["timestamp"] - df["timestamp"] - np.pi
@@ -41,7 +41,7 @@ def test_numpy_math_constants_dsp(tmptestdir):
 
 def test_numpy_infinity_and_nan_dsp(tmptestdir):
     dsp_file = f"{tmptestdir}/LDQTA_r117_20200110T105115Z_cal_geds__numpy_test_dsp.lh5"
-    df = store.load_nda(dsp_file, ["calc4", "calc5", "calc6"], "geds/dsp/")
+    df = lh5.load_nda(dsp_file, ["calc4", "calc5", "calc6"], "geds/dsp/")
 
     assert (np.isnan(df["calc4"])).all()
     assert (np.isneginf(df["calc5"])).all()