From 18be7018f7d797293f58d1383760949175343b81 Mon Sep 17 00:00:00 2001
From: Bjoern Ludwig <bjoern.ludwig@ptb.de>
Date: Mon, 16 Jan 2023 18:22:24 +0100
Subject: [PATCH] docs(notebook): adapt read_dataset.ipynb to new
implementation without manual cache location spec
---
.../examples/read_dataset.ipynb | 167 +-----------------
1 file changed, 4 insertions(+), 163 deletions(-)
diff --git a/src/zema_emc_annotated/examples/read_dataset.ipynb b/src/zema_emc_annotated/examples/read_dataset.ipynb
index 8561a47..847a21f 100644
--- a/src/zema_emc_annotated/examples/read_dataset.ipynb
+++ b/src/zema_emc_annotated/examples/read_dataset.ipynb
@@ -9,44 +9,29 @@
},
{
"cell_type": "code",
- "execution_count": 10,
- "metadata": {
- "pycharm": {
- "is_executing": true
- }
- },
+ "execution_count": 13,
+ "metadata": {},
"outputs": [],
"source": [
"import json\n",
- "import os\n",
- "from os.path import dirname\n",
- "from pathlib import Path\n",
"\n",
"import h5py\n",
- "import numpy as np\n",
- "from h5py import Dataset, File, Group\n",
- "from numpy import ndarray\n",
"from pooch import retrieve"
]
},
{
"cell_type": "code",
- "execution_count": 16,
+ "execution_count": 14,
"metadata": {},
"outputs": [],
"source": [
"def local_path_to_dataset_after_download_if_required():\n",
- " LOCAL_ZEMA_DATASET_PATH = Path(os.path.abspath(\"\")).parent.joinpath(\"datasets\")\n",
- " ZEMA_DATASET_HASH = (\n",
- " \"sha256:fb0e80de4e8928ae8b859ad9668a1b6ea6310028a6690bb8d4c1abee31cb8833\"\n",
- " )\n",
" ZEMA_DATASET_URL = (\n",
" \"https://zenodo.org/record/5185953/files/axis11_2kHz_ZeMA_PTB_SI.h5\"\n",
" )\n",
" return retrieve(\n",
" url=ZEMA_DATASET_URL,\n",
- " known_hash=ZEMA_DATASET_HASH,\n",
- " path=LOCAL_ZEMA_DATASET_PATH,\n",
+ " known_hash=None,\n",
" progressbar=True,\n",
" )"
]
@@ -140,150 +125,6 @@
" print(my_uncertainty)\n",
" print(list(h5f[\"PTB_SUU\"]))"
]
- },
- {
- "cell_type": "code",
- "execution_count": 5,
- "metadata": {},
- "outputs": [],
- "source": [
- "def extract_data(n_samples: int, verbose: bool = False) -> ndarray:\n",
- " extracted_data = np.empty((n_samples, 0))\n",
- " indices = np.s_[0:5, 0]\n",
- " with h5py.File(local_path_to_dataset_after_download_if_required(), \"r\") as h5f:\n",
- " daq_identifier = \"ZeMA_DAQ\"\n",
- " if verbose:\n",
- " print(\n",
- " f\"\\nShow data for sensor set {daq_identifier}:\\n{'-'*(26 + len(daq_identifier))}\"\n",
- " )\n",
- " for quantity in conditional_first_level_element(h5f, daq_identifier):\n",
- " if verbose:\n",
- " print(\n",
- " f\"\\n Show data for quantity {quantity}:\\n {'-'*(24 + len(quantity))}\"\n",
- " )\n",
- " for dataset in hdf5_part(h5f, (daq_identifier, quantity)):\n",
- " if verbose:\n",
- " print(f\" {hdf5_part(h5f, (daq_identifier, quantity, dataset))}\")\n",
- " if (\n",
- " \"qudt:standardUncertainty\"\n",
- " in hdf5_part(h5f, (daq_identifier, quantity, dataset)).name\n",
- " ):\n",
- " if (\n",
- " len(hdf5_part(h5f, (daq_identifier, quantity, dataset)).shape)\n",
- " == 3\n",
- " ):\n",
- " for sensor in hdf5_part(\n",
- " h5f, (daq_identifier, quantity, dataset)\n",
- " ):\n",
- " extracted_data = append_to_extraction(\n",
- " extracted_data,\n",
- " extract_sample_from_dataset(sensor, indices),\n",
- " )\n",
- " else:\n",
- " extracted_data = append_to_extraction(\n",
- " extracted_data,\n",
- " extract_sample_from_dataset(\n",
- " hdf5_part(h5f, (daq_identifier, quantity, dataset)),\n",
- " indices,\n",
- " ),\n",
- " )\n",
- " return extracted_data\n",
- "\n",
- "\n",
- "def conditional_first_level_element(hdf5_file: File, identifier: str) -> Group:\n",
- " for sensor_set_descriptor in hdf5_file:\n",
- " if identifier in sensor_set_descriptor:\n",
- " return hdf5_file[sensor_set_descriptor]\n",
- "\n",
- "\n",
- "def hdf5_part(hdf5_file: File, keys: tuple[str, ...]) -> Group | Dataset:\n",
- " part = hdf5_file\n",
- " for key in keys:\n",
- " part = part[key]\n",
- " return part\n",
- "\n",
- "\n",
- "def extract_sample_from_dataset(\n",
- " data_set: Dataset, ns_samples: tuple[int | slice]\n",
- ") -> ndarray[float]:\n",
- " return np.expand_dims(np.array(data_set[ns_samples]), 1)\n",
- "\n",
- "\n",
- "def append_to_extraction(append_to: ndarray, appendix: ndarray) -> ndarray:\n",
- " return np.append(append_to, appendix, axis=1)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 6,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "\n",
- "Show data for sensor set ZeMA_DAQ:\n",
- "----------------------------------\n",
- "\n",
- " Show data for quantity Acceleration:\n",
- " ------------------------------------\n",
- " <HDF5 dataset \"qudt:standardUncertainty\": shape (3, 2000, 4766), type \"<f8\">\n",
- " <HDF5 dataset \"qudt:value\": shape (3, 2000, 4766), type \"<f8\">\n",
- "\n",
- " Show data for quantity Active_Current:\n",
- " --------------------------------------\n",
- " <HDF5 dataset \"qudt:standardUncertainty\": shape (2000, 4766), type \"<f8\">\n",
- " <HDF5 dataset \"qudt:value\": shape (2000, 4766), type \"<f8\">\n",
- "\n",
- " Show data for quantity Force:\n",
- " -----------------------------\n",
- " <HDF5 dataset \"qudt:standardUncertainty\": shape (2000, 4766), type \"<f8\">\n",
- " <HDF5 dataset \"qudt:value\": shape (2000, 4766), type \"<f8\">\n",
- "\n",
- " Show data for quantity Motor_Current:\n",
- " -------------------------------------\n",
- " <HDF5 dataset \"qudt:standardUncertainty\": shape (3, 2000, 4766), type \"<f8\">\n",
- " <HDF5 dataset \"qudt:value\": shape (3, 2000, 4766), type \"<f8\">\n",
- "\n",
- " Show data for quantity Pressure:\n",
- " --------------------------------\n",
- " <HDF5 dataset \"qudt:standardUncertainty\": shape (2000, 4766), type \"<f8\">\n",
- " <HDF5 dataset \"qudt:value\": shape (2000, 4766), type \"<f8\">\n",
- "\n",
- " Show data for quantity Sound_Pressure:\n",
- " --------------------------------------\n",
- " <HDF5 dataset \"qudt:standardUncertainty\": shape (2000, 4766), type \"<f8\">\n",
- " <HDF5 dataset \"qudt:value\": shape (2000, 4766), type \"<f8\">\n",
- "\n",
- " Show data for quantity Velocity:\n",
- " --------------------------------\n",
- " <HDF5 dataset \"qudt:standardUncertainty\": shape (2000, 4766), type \"<f8\">\n",
- " <HDF5 dataset \"qudt:value\": shape (2000, 4766), type \"<f8\">\n",
- "[[2.83190307e+00 2.83190307e+00 2.83190307e+00 1.64743668e-02\n",
- " 1.24365050e-02 1.16511079e-02 2.13708300e-02 3.66123419e-02\n",
- " 1.68325082e+04 2.78848019e-05 1.20545254e+00]\n",
- " [2.83190307e+00 2.83190307e+00 2.83190307e+00 3.01910282e-02\n",
- " 1.24365050e-02 5.74690879e-02 1.12427249e-02 6.80918703e-02\n",
- " 1.68325082e+04 2.78848019e-05 2.17917358e+00]\n",
- " [2.83190307e+00 2.83190307e+00 2.83190307e+00 2.61650718e-02\n",
- " 1.24365050e-02 6.31271288e-02 4.34207110e-02 1.82414959e-02\n",
- " 1.68325082e+04 2.78848019e-05 1.92350168e+00]\n",
- " [2.83190307e+00 2.83190307e+00 2.83190307e+00 2.82367380e-02\n",
- " 1.24365050e-02 3.59956144e-02 5.92208475e-02 2.20117766e-02\n",
- " 1.68325082e+04 2.78848019e-05 2.06234912e+00]\n",
- " [2.83190307e+00 2.83190307e+00 2.83190307e+00 2.92119176e-02\n",
- " 1.24365050e-02 8.26010663e-03 4.94686133e-02 5.76812843e-02\n",
- " 1.68325082e+04 2.78848019e-05 1.97239442e+00]]\n",
- "(5, 11)\n"
- ]
- }
- ],
- "source": [
- "uncertainties = extract_data(1, verbose=True)\n",
- "print(uncertainties)\n",
- "print(uncertainties.shape)"
- ]
}
],
"metadata": {
--
GitLab