From a4ea2852f4b46566a61f988342aa04e4059ccef9 Mon Sep 17 00:00:00 2001 From: adamhrv Date: Tue, 8 Oct 2019 16:02:33 +0200 Subject: add notebooks --- .../notebooks/msc/sort_embassy_flickr_images.ipynb | 94 ++++++++++++++++++++++ 1 file changed, 94 insertions(+) create mode 100644 megapixels/notebooks/msc/sort_embassy_flickr_images.ipynb (limited to 'megapixels/notebooks/msc') diff --git a/megapixels/notebooks/msc/sort_embassy_flickr_images.ipynb b/megapixels/notebooks/msc/sort_embassy_flickr_images.ipynb new file mode 100644 index 00000000..4e898785 --- /dev/null +++ b/megapixels/notebooks/msc/sort_embassy_flickr_images.ipynb @@ -0,0 +1,94 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Sort Embassy Flickr Images" + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "metadata": {}, + "outputs": [], + "source": [ + "import pandas as pd\n", + "from pathlib import Path\n", + "import shutil\n" + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "metadata": {}, + "outputs": [], + "source": [ + "fp_files = '/data_store/datasets/msc/embassies/embassy_counts_images.csv'\n", + "fp_dir_dst = '/data_store/datasets/msc/images_sorted/'\n", + "fp_dir_src = '/data_store/datasets/msc/images/'" + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "metadata": {}, + "outputs": [], + "source": [ + "df_flickr = pd.read_csv(fp_files)" + ] + }, + { + "cell_type": "code", + "execution_count": 19, + "metadata": {}, + "outputs": [], + "source": [ + "groups_username = df_flickr.groupby('path_alias')" + ] + }, + { + "cell_type": "code", + "execution_count": 23, + "metadata": {}, + "outputs": [], + "source": [ + "for group_username, df_group in groups_username:\n", + " for idx, df in df_group.iterrows():\n", + " fp_dst = Path(fp_dir_dst) / group_username / df.dataset_key\n", + " fp_src = Path(fp_dir_src) / df.filepath\n", + " if fp_src.exists():\n", + " fp_dst.mkdir(exist_ok=True, parents=True)\n", + " shutil.copy(fp_src, fp_dst)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "megapixels", + "language": "python", + "name": "megapixels" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.6.8" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +} -- cgit v1.2.3-70-g09d2