1 files changed, 315 insertions, 0 deletions
diff --git a/megapixels/notebooks/datasets/megaface/megaface_prepare_flickr_api.ipynb b/megapixels/notebooks/datasets/megaface/megaface_prepare_flickr_api.ipynb
new file mode 100644
index 00000000..48133228
--- /dev/null
+++ b/megapixels/notebooks/datasets/megaface/megaface_prepare_flickr_api.ipynb
@@ -0,0 +1,315 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Prepare Flickr API Batch CSV"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "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 pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create CSV for API"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "| filepath | query |\n",
+    "|:---|:---|\n",
+    "| 12234 | 12234@123|"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 72,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "fp_in_dir_ids = '/data_store_ssd_perrier/datasets/people/megaface/downloads/MegafaceIdentities_VGG_META/'\n",
+    "fp_out_queries = '/data_store_hdd/datasets/people/megaface/research/megaface_flickr_api_queries.csv'\n",
+    "fp_out_queries_full = '/data_store_hdd/datasets/people/megaface/research/megaface_flickr_api_queries_full.csv'"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 59,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "nsid_paths = glob(join(fp_in_dir_ids, '*'))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 74,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "1ab58c3dd0934591b0ea3f2da77003f5",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "HBox(children=(IntProgress(value=0, max=672057), HTML(value='')))"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "items = []\n",
+    "for nsid_path in tqdm(nsid_paths):\n",
+    "  nsid_full = Path(nsid_path).name\n",
+    "  nsid = nsid_full.split('_')[0]\n",
+    "  json_files = glob(join(fp_in_dir_ids, nsid_path, '*.json'))\n",
+    "  for json_file in json_files:\n",
+    "    nsid_id_json = file_utils.load_json(json_file)\n",
+    "    full_image_url = nsid_id_json.get('full_img_url')\n",
+    "    obj = {'nsid': nsid, 'nsid_full': nsid_full, 'full_image_url': full_image_url}\n",
+    "    items.append(obj)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 75,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = pd.DataFrame.from_dict(items)\n",
+    "df.to_csv(fp_out_queries_full, index=False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 76,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "count_lookup = {}\n",
+    "for item in items:\n",
+    "  nsid = item['nsid']\n",
+    "  if not nsid in count_lookup.keys():\n",
+    "    count_lookup[nsid] = 0\n",
+    "  count_lookup[nsid] += 1"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Combine MegaFace Flickr API Meta for User/NSID"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 77,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "fp_in_dir = '/media/adam/ah8tb/data_store/datasets/people/megaface/research/flickr_api_dump'\n",
+    "fp_files = glob(join(fp_in_dir, '*.json'))\n",
+    "fp_files_err = [f for f in fp_files if '.txt' in f]\n",
+    "fp_files = [f for f in fp_files if '.txt' not in f]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 78,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "46906\n",
+      "0\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(len(fp_files))\n",
+    "print(len(fp_files_err))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 44,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# combine files into single CSV"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "```\n",
+    "{\n",
+    "  \"stat\": \"ok\",\n",
+    "  \"user\": {\n",
+    "    \"nsid\": \"7122726@N03\",\n",
+    "    \"url\": \"https://www.flickr.com/people/tdbsca/\"\n",
+    "  }\n",
+    "}\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 99,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "c304096902584115be0c1a86accf2f69",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "HBox(children=(IntProgress(value=0, max=46906), HTML(value='')))"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "meta_records = []\n",
+    "for fp_file in tqdm(fp_files):\n",
+    "  data = file_utils.load_json(fp_file)\n",
+    "  user = data.get('user')\n",
+    "  nsid = user.get('nsid')\n",
+    "  path_alias = Path(user.get('url')).stem\n",
+    "  count = count_lookup.get(nsid)\n",
+    "  obj = {'path_alias': path_alias, 'nsid': nsid, 'count': count}\n",
+    "  meta_records.append(obj)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 100,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "46906\n"
+     ]
+    }
+   ],
+   "source": [
+    "df_meta_records = pd.DataFrame.from_dict(meta_records)\n",
+    "print(len(df_meta_records))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 101,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_meta_records.drop_duplicates(subset='nsid', keep='last', inplace=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 102,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "46906\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(len(df_meta_records))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 103,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "fp_out_combined = '/data_store_hdd/datasets/people/megaface/research/megaface_flickr_meta_count.csv'\n",
+    "df_meta_records.to_csv(fp_out_combined, index=False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 104,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "4627187\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(df_meta_records['count'].sum())"
+   ]
+  },
+  {
+   "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
+}