diff --git a/EDA/login.yaml b/EDA/login.yaml new file mode 100644 index 0000000..9286751 --- /dev/null +++ b/EDA/login.yaml @@ -0,0 +1,2 @@ +- url: # enter url +- password: # enter passwort \ No newline at end of file diff --git a/EDA/owncloud.ipynb b/EDA/owncloud.ipynb deleted file mode 100644 index 68572b0..0000000 --- a/EDA/owncloud.ipynb +++ /dev/null @@ -1,157 +0,0 @@ -{ - "cells": [ - { - "cell_type": "code", - "execution_count": null, - "id": "aab6b326-a583-47ad-8bb7-723c2fddcc63", - "metadata": { - "scrolled": true - }, - "outputs": [], - "source": [ - "# %pip install pyocclient\n", - "import yaml\n", - "import owncloud\n", - "import pandas as pd\n", - "import time" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "id": "4f42846c-27c3-4394-a40a-e22d73c2902e", - "metadata": {}, - "outputs": [], - "source": [ - "start = time.time()\n", - "\n", - "with open(\"../login.yaml\") as f:\n", - " cfg = yaml.safe_load(f)\n", - "url, password = cfg[0][\"url\"], cfg[1][\"password\"]\n", - "file = \"adabase-public-0022-v_0_0_2.h5py\"\n", - "oc = owncloud.Client.from_public_link(url, folder_password=password)\n", - "\n", - "\n", - "oc.get_file(file, \"tmp22.h5\")\n", - "\n", - "end = time.time()\n", - "print(end - start)\n" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "id": "3714dec2-85d0-4f76-af46-ea45ebec2fa3", - "metadata": {}, - "outputs": [], - "source": [ - "start = time.time()\n", - "df_performance = pd.read_hdf(\"tmp22.h5\", \"PERFORMANCE\")\n", - "end = time.time()\n", - "print(end - start)" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "id": "f50e97d0", - "metadata": {}, - "outputs": [], - "source": [ - "print(22)" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "id": "c131c816", - "metadata": {}, - "outputs": [], - "source": [ - "df_performance" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "id": "6ae47e52-ad86-4f8d-b929-0080dc99f646", - "metadata": {}, - "outputs": [], - "source": [ - "start = time.time()\n", - "df_4_col = pd.read_hdf(\"tmp.h5\", \"SIGNALS\", mode=\"r\", columns=[\"STUDY\"], start=0, stop=1)\n", - "end = time.time()\n", - "print(end - start)" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "id": "7c139f3a-ede8-4530-957d-d1bb939f6cb5", - "metadata": {}, - "outputs": [], - "source": [ - "df_4_col.head()" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "id": "a68d58ea-65f2-46c4-a2b2-8c3447c715d7", - "metadata": {}, - "outputs": [], - "source": [ - "df_4_col.shape" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "id": "95aa4523-3784-4ab6-bf92-0227ce60e863", - "metadata": {}, - "outputs": [], - "source": [ - "df_4_col.info()" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "id": "defbcaf4-ad1b-453f-9b48-ab0ecfc4b5d5", - "metadata": {}, - "outputs": [], - "source": [ - "df_4_col.isna().sum()" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "id": "72313895-c478-44a5-9108-00b0bec01bb8", - "metadata": {}, - "outputs": [], - "source": [] - } - ], - "metadata": { - "kernelspec": { - "display_name": "base", - "language": "python", - "name": "python3" - }, - "language_info": { - "codemirror_mode": { - "name": "ipython", - "version": 3 - }, - "file_extension": ".py", - "mimetype": "text/x-python", - "name": "python", - "nbconvert_exporter": "python", - "pygments_lexer": "ipython3", - "version": "3.11.5" - } - }, - "nbformat": 4, - "nbformat_minor": 5 -} diff --git a/EDA/owncloud_file_access.ipynb b/EDA/owncloud_file_access.ipynb new file mode 100644 index 0000000..46927dd --- /dev/null +++ b/EDA/owncloud_file_access.ipynb @@ -0,0 +1,112 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "id": "457e7807", + "metadata": {}, + "source": [ + "# Get data from owncloud" + ] + }, + { + "cell_type": "markdown", + "id": "dc9ed3f8", + "metadata": {}, + "source": [ + "Imports" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# %pip install pyocclient\n", + "import os\n", + "import time\n", + "import yaml\n", + "import owncloud\n", + "import pandas as pd\n" + ] + }, + { + "cell_type": "markdown", + "id": "68e34abc", + "metadata": {}, + "source": [ + "Download and save" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "start = time.time()\n", + "\n", + "# TODO: User input: directory where downloaded files should be saved\n", + "save_dir = r\"./downloads\"\n", + "\n", + "\n", + "os.makedirs(save_dir, exist_ok=True)\n", + "\n", + "# Load credentials\n", + "with open(\"login.yaml\", \"r\") as f:\n", + " cfg = yaml.safe_load(f)\n", + "\n", + "url = cfg[0][\"url\"]\n", + "password = cfg[1][\"password\"]\n", + "\n", + "# Connect to OwnCloud public link\n", + "oc = owncloud.Client.from_public_link(url, folder_password=password)\n", + "\n", + "# List all available files in the shared folder\n", + "remote_files = oc.list(\".\")\n", + "\n", + "# Keep only HDF5 files and sort them by name\n", + "hdf5_files = sorted([f.get_name() for f in remote_files if f.get_name().endswith(\".hdf5\")])\n", + "\n", + "print(f\"Found {len(hdf5_files)} .hdf5 files in OwnCloud\")\n", + "\n", + "if not hdf5_files:\n", + " print(\"No .hdf5 files found.\")\n", + "else:\n", + " for i, remote_name in enumerate(hdf5_files):\n", + " local_name = f\"tmp_{i:04d}.h5\"\n", + " local_path = os.path.join(save_dir, local_name)\n", + "\n", + " try:\n", + " oc.get_file(remote_name, local_path)\n", + " print(f\"Downloaded: {remote_name} -> {local_path}\")\n", + " except Exception as e:\n", + " print(f\"Failed to download {remote_name}: {e}\")\n", + "\n", + "end = time.time()\n", + "print(f\"Finished in {end - start:.2f} seconds\")\n" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "base", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.11.5" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +}