refactor(read_dataset): blacken

438bf321 · Björn Ludwig · e55f5cdb · 438bf321
Verified Commit 438bf321 authored 2 years ago by Björn Ludwig
--- a/src/zema_emc_annotated/examples/read_dataset.ipynb
+++ b/src/zema_emc_annotated/examples/read_dataset.ipynb
@@ -36,7 +36,7 @@
   "outputs": [],
   "source": [
    "def local_path_to_dataset_after_download_if_required():\n",
-    "    LOCAL_ZEMA_DATASET_PATH = Path(os.path.abspath('')).parent.joinpath(\"datasets\")\n",
+    "    LOCAL_ZEMA_DATASET_PATH = Path(os.path.abspath(\"\")).parent.joinpath(\"datasets\")\n",
    "    ZEMA_DATASET_HASH = (\n",
    "        \"sha256:fb0e80de4e8928ae8b859ad9668a1b6ea6310028a6690bb8d4c1abee31cb8833\"\n",
    "    )\n",

 %% Cell type:markdown id: tags:
 # Read ZeMA dataset and preprocess data
 %% Cell type:code id: tags:
 ``` python
 import json
 import os
 from os.path import dirname
 from pathlib import Path
 import h5py
 import numpy as np
 from h5py import Dataset, File, Group
 from numpy import ndarray
 from pooch import retrieve
 ```
 %% Cell type:code id: tags:
 ``` python
 def local_path_to_dataset_after_download_if_required():
-    LOCAL_ZEMA_DATASET_PATH = Path(os.path.abspath('')).parent.joinpath("datasets")
+    LOCAL_ZEMA_DATASET_PATH = Path(os.path.abspath("")).parent.joinpath("datasets")
    ZEMA_DATASET_HASH = (
        "sha256:fb0e80de4e8928ae8b859ad9668a1b6ea6310028a6690bb8d4c1abee31cb8833"
    )
    ZEMA_DATASET_URL = (
        "https://zenodo.org/record/5185953/files/axis11_2kHz_ZeMA_PTB_SI.h5"
    )
    return retrieve(
        url=ZEMA_DATASET_URL,
        known_hash=ZEMA_DATASET_HASH,
        path=LOCAL_ZEMA_DATASET_PATH,
        progressbar=True,
    )
 ```
 %% Cell type:code id: tags:
 ``` python
 def print_attrs(h5py_dataset_or_group):
    for key in h5py_dataset_or_group.attrs:
        print(key)
        val = json.loads(h5py_dataset_or_group.attrs[key])
        if isinstance(val, dict):
            for subkey, subval in val.items():
                print(f"   {subkey}  : {subval}")
        else:
            print(f"   {val}")
 ```
 %% Cell type:code id: tags:
 ``` python
 with h5py.File(local_path_to_dataset_after_download_if_required(), "r") as h5f:
    print_attrs(h5f)
 ```
 %% Output
    Experiment
       date  : 2021-03-29/2021-04-15
       DUT  : Festo ESBF cylinder
       identifier  : axis11
       label  : Electromechanical cylinder no. 11
    Person
       dc:author  : ['Tanja Dorst', 'Maximilian Gruber', 'Anupam Prasad Vedurmudi']
       e-mail  : ['t.dorst@zema.de', 'maximilian.gruber@ptb.de', 'anupam.vedurmudi@ptb.de']
       affiliation  : ['ZeMA gGmbH', 'Physikalisch-Technische Bundesanstalt', 'Physikalisch-Technische Bundesanstalt']
    Project
       fullTitle  : Metrology for the Factory of the Future
       acronym  : Met4FoF
       websiteLink  : www.met4fof.eu
       fundingSource  : European Commission (EC)
       fundingAdministrator  : EURAMET
       funding programme  : EMPIR
       fundingNumber  : 17IND12
       acknowledgementText  : This work has received funding within the project 17IND12 Met4FoF from the EMPIR program co-financed by the Participating States and from the European Union's Horizon 2020 research and innovation program. The authors want to thank Clifford Brown, Daniel Hutzschenreuter, Holger Israel, Giacomo Lanza, Björn Ludwig, and Julia Neumann fromPhysikalisch-Technische Bundesanstalt (PTB) for their helpful suggestions and support.
    Publication
       dc:identifier  : 10.5281/zenodo.5185953
       dc:license  : Creative Commons Attribution 4.0 International (CC-BY-4.0)
       dc:title  : Sensor data set of one electromechanical cylinder at ZeMA testbed (ZeMA DAQ and Smart-Up Unit)
       dc:description  : The data set was generated with two different measurement systems at the ZeMA testbed. The ZeMA DAQ unit consists of 11 sensors and the SmartUp-Unit has 13 differentsignals. A typical working cycle lasts 2.8s and consists of a forward stroke, a waiting time and a return stroke of the electromechanical cylinder. The data set does not consist of the entire working cycles. Only one second of the return stroke of every 100rd working cycle is included. The dataset consists of 4776 cycles. One row represents one second of the return stroke of one working cycle.
       dc:subject  : ['dynamic measurement', 'measurement uncertainty', 'sensor network', 'digital sensors', 'MEMS', 'machine learning', 'European Union (EU)', 'Horizon 2020', 'EMPIR']
       dc:SizeOrDuration  : 24 sensors, 4776 cycles and 2000 datapoints each
       dc:type  : Dataset
       dc:issued  : 2021-09-10
       dc:bibliographicCitation  : T. Dorst, M. Gruber and A. P. Vedurmudi : Sensor data set of one electromechanical cylinder at ZeMA testbed (ZeMA DAQ and Smart-Up Unit), Zenodo [data set], https://doi.org/10.5281/zenodo.5185953, 2021.
 %% Cell type:code id: tags:
 ``` python
 with h5py.File(local_path_to_dataset_after_download_if_required(), "r") as h5f:
    my_uncertainty = h5f["PTB_SUU"]["MPU_9250"]["Acceleration"][
        "qudt:standardUncertainty"
    ]
    print("qudt:standardUncertainty" in my_uncertainty.name)
    print_attrs(my_uncertainty)
    print(my_uncertainty)
    print(list(h5f["PTB_SUU"]))
 ```
 %% Output
    True
    si:label
       ['X acceleration uncertainty', 'Y acceleration uncertainty', 'Z acceleration uncertainty']
    <HDF5 dataset "qudt:standardUncertainty": shape (3, 1000, 4766), type "<f8">
    ['BMA_280', 'MPU_9250']
 %% Cell type:code id: tags:
 ``` python
 def extract_data(n_samples: int, verbose: bool = False) -> ndarray:
    extracted_data = np.empty((n_samples, 0))
    indices = np.s_[0:5, 0]
    with h5py.File(local_path_to_dataset_after_download_if_required(), "r") as h5f:
        daq_identifier = "ZeMA_DAQ"
        if verbose:
            print(
                f"\nShow data for sensor set {daq_identifier}:\n{'-'*(26 + len(daq_identifier))}"
            )
        for quantity in conditional_first_level_element(h5f, daq_identifier):
            if verbose:
                print(
                    f"\n    Show data for quantity {quantity}:\n    {'-'*(24 + len(quantity))}"
                )
            for dataset in hdf5_part(h5f, (daq_identifier, quantity)):
                if verbose:
                    print(f"    {hdf5_part(h5f, (daq_identifier, quantity, dataset))}")
                if (
                    "qudt:standardUncertainty"
                    in hdf5_part(h5f, (daq_identifier, quantity, dataset)).name
                ):
                    if (
                        len(hdf5_part(h5f, (daq_identifier, quantity, dataset)).shape)
                        == 3
                    ):
                        for sensor in hdf5_part(
                            h5f, (daq_identifier, quantity, dataset)
                        ):
                            extracted_data = append_to_extraction(
                                extracted_data,
                                extract_sample_from_dataset(sensor, indices),
                            )
                    else:
                        extracted_data = append_to_extraction(
                            extracted_data,
                            extract_sample_from_dataset(
                                hdf5_part(h5f, (daq_identifier, quantity, dataset)),
                                indices,
                            ),
                        )
    return extracted_data
 def conditional_first_level_element(hdf5_file: File, identifier: str) -> Group:
    for sensor_set_descriptor in hdf5_file:
        if identifier in sensor_set_descriptor:
            return hdf5_file[sensor_set_descriptor]
 def hdf5_part(hdf5_file: File, keys: tuple[str, ...]) -> Group | Dataset:
    part = hdf5_file
    for key in keys:
        part = part[key]
    return part
 def extract_sample_from_dataset(
    data_set: Dataset, ns_samples: tuple[int | slice]
 ) -> ndarray[float]:
    return np.expand_dims(np.array(data_set[ns_samples]), 1)
 def append_to_extraction(append_to: ndarray, appendix: ndarray) -> ndarray:
    return np.append(append_to, appendix, axis=1)
 ```
 %% Cell type:code id: tags:
 ``` python
 uncertainties = extract_data(1, verbose=True)
 print(uncertainties)
 print(uncertainties.shape)
 ```
 %% Output
    Show data for sensor set ZeMA_DAQ:
    ----------------------------------
        Show data for quantity Acceleration:
        ------------------------------------
        <HDF5 dataset "qudt:standardUncertainty": shape (3, 2000, 4766), type "<f8">
        <HDF5 dataset "qudt:value": shape (3, 2000, 4766), type "<f8">
        Show data for quantity Active_Current:
        --------------------------------------
        <HDF5 dataset "qudt:standardUncertainty": shape (2000, 4766), type "<f8">
        <HDF5 dataset "qudt:value": shape (2000, 4766), type "<f8">
        Show data for quantity Force:
        -----------------------------
        <HDF5 dataset "qudt:standardUncertainty": shape (2000, 4766), type "<f8">
        <HDF5 dataset "qudt:value": shape (2000, 4766), type "<f8">
        Show data for quantity Motor_Current:
        -------------------------------------
        <HDF5 dataset "qudt:standardUncertainty": shape (3, 2000, 4766), type "<f8">
        <HDF5 dataset "qudt:value": shape (3, 2000, 4766), type "<f8">
        Show data for quantity Pressure:
        --------------------------------
        <HDF5 dataset "qudt:standardUncertainty": shape (2000, 4766), type "<f8">
        <HDF5 dataset "qudt:value": shape (2000, 4766), type "<f8">
        Show data for quantity Sound_Pressure:
        --------------------------------------
        <HDF5 dataset "qudt:standardUncertainty": shape (2000, 4766), type "<f8">
        <HDF5 dataset "qudt:value": shape (2000, 4766), type "<f8">
        Show data for quantity Velocity:
        --------------------------------
        <HDF5 dataset "qudt:standardUncertainty": shape (2000, 4766), type "<f8">
        <HDF5 dataset "qudt:value": shape (2000, 4766), type "<f8">
    [[2.83190307e+00 2.83190307e+00 2.83190307e+00 1.64743668e-02
      1.24365050e-02 1.16511079e-02 2.13708300e-02 3.66123419e-02
      1.68325082e+04 2.78848019e-05 1.20545254e+00]
     [2.83190307e+00 2.83190307e+00 2.83190307e+00 3.01910282e-02
      1.24365050e-02 5.74690879e-02 1.12427249e-02 6.80918703e-02
      1.68325082e+04 2.78848019e-05 2.17917358e+00]
     [2.83190307e+00 2.83190307e+00 2.83190307e+00 2.61650718e-02
      1.24365050e-02 6.31271288e-02 4.34207110e-02 1.82414959e-02
      1.68325082e+04 2.78848019e-05 1.92350168e+00]
     [2.83190307e+00 2.83190307e+00 2.83190307e+00 2.82367380e-02
      1.24365050e-02 3.59956144e-02 5.92208475e-02 2.20117766e-02
      1.68325082e+04 2.78848019e-05 2.06234912e+00]
     [2.83190307e+00 2.83190307e+00 2.83190307e+00 2.92119176e-02
      1.24365050e-02 8.26010663e-03 4.94686133e-02 5.76812843e-02
      1.68325082e+04 2.78848019e-05 1.97239442e+00]]
    (5, 11)