add MSC nbs and cli cmds

1 files changed, 162 insertions, 0 deletions

diff --git a/megapixels/notebooks/datasets/helen/prepare_flickr_api.ipynb b/megapixels/notebooks/datasets/helen/prepare_flickr_api.ipynb
new file mode 100644
index 00000000..311d3462
--- /dev/null
+++ b/megapixels/notebooks/datasets/helen/prepare_flickr_api.ipynb
@@ -0,0 +1,162 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# HELEN Prepare Flickr API"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%reload_ext autoreload\n",
+    "%autoreload 2\n",
+    "\n",
+    "import os\n",
+    "from os.path import join\n",
+    "from glob import glob, iglob\n",
+    "from pathlib import Path\n",
+    "from tqdm import tqdm_notebook as tqdm\n",
+    "\n",
+    "import h5py\n",
+    "from scipy import misc\n",
+    "from io import BytesIO\n",
+    "from base64 import b64decode\n",
+    "\n",
+    "from PIL import Image, ImageDraw\n",
+    "%matplotlib inline\n",
+    "import matplotlib.pyplot as plt\n",
+    "import scipy.io as sio\n",
+    "import h5py\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "import sys\n",
+    "sys.path.append('/work/megapixels_dev/megapixels/')\n",
+    "from app.utils import file_utils"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "fp_in = '/data_store/datasets/people/helen/research/flickr_photo_ids.txt'\n",
+    "fp_out = '/data_store/datasets/people/helen/research/helen_flickr_meta.csv'"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "photo_id_list = file_utils.load_text(fp_in)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "items = [{'photo_id': x.split('_')[0]} for x in photo_id_list]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = pd.DataFrame.from_dict(items)\n",
+    "df.to_csv(fp_out, index=False)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Load Flickr API Dump\n",
+    "\n",
+    "- and create Flickr meta"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "fp_api_dump = '/data_store/datasets/people/helen/research/helen_flickr_api_dump.csv'\n",
+    "df = pd.read_csv(fp_api_dump)\n",
+    "#records = df.to_dict('records')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "groups = df.groupby('nsid')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "results = []\n",
+    "for nsid, group in groups:\n",
+    "  obj = {\n",
+    "    'nsid': nsid,\n",
+    "    'count': len(group)\n",
+    "  }\n",
+    "  results.append(obj)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "pd.DataFrame.from_dict(results).to_csv(fp_out, index=False)"
+   ]
+  },
+  {
+   "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
+}