summaryrefslogtreecommitdiff
path: root/megapixels/notebooks/msc
diff options
context:
space:
mode:
authorjules@lens <julescarbon@gmail.com>2019-10-10 13:33:31 +0200
committerjules@lens <julescarbon@gmail.com>2019-10-10 13:33:31 +0200
commit7d72cbb935ec53ce66c6a0c5cdc68f157be1d35f (patch)
treea44049683c3c5e44449fe2698bb080329ecf7e61 /megapixels/notebooks/msc
parent488a65aa5caba91c1384e7bcb2023056e913fc22 (diff)
parentcdc0c7ad21eb764cfe36d7583e126660d87fe02d (diff)
Merge branch 'master' of asdf.us:megapixels_dev
Diffstat (limited to 'megapixels/notebooks/msc')
-rw-r--r--megapixels/notebooks/msc/sort_embassy_flickr_images.ipynb94
1 files changed, 94 insertions, 0 deletions
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
+}