add utils for analyzing identities

2 files changed, 248 insertions, 1 deletions

diff --git a/megapixels/notebooks/datasets/lfw/count_images.ipynb b/megapixels/notebooks/datasets/lfw/count_images.ipynb
new file mode 100644
index 00000000..26682f8b
--- /dev/null
+++ b/megapixels/notebooks/datasets/lfw/count_images.ipynb
@@ -0,0 +1,247 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Count Images for LFW\n",
+    "\n",
+    "- use sub-directory as `identity_key`"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%reload_ext autoreload\n",
+    "%autoreload 2\n",
+    "\n",
+    "import os\n",
+    "from os.path import join\n",
+    "from glob import glob\n",
+    "from pathlib import Path\n",
+    "from pprint import pprint\n",
+    "\n",
+    "from tqdm import tqdm_notebook as tqdm\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "from slugify import slugify\n",
+    "\n",
+    "import sys\n",
+    "sys.path.append('/work/megapixels_dev/megapixels')\n",
+    "from app.utils import file_utils\n",
+    "from app.settings import types, app_cfg\n",
+    "from app.models.data_store import DataStore"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Get image counts"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "opt_dataset = types.Dataset.LFW\n",
+    "opt_data_store = types.DataStore.HDD\n",
+    "data_store = DataStore(opt_data_store, opt_dataset)\n",
+    "# get filepath out\n",
+    "fp_records = data_store.metadata(types.Metadata.FILE_RECORD)\n",
+    "fp_img_counts = data_store.metadata(types.Metadata.IMAGE_COUNT)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 42,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_records = pd.read_csv(fp_records).set_index('index')\n",
+    "records = df_records.to_dict('records')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# paths\n",
+    "fp_dirs = '/data_store_hdd/datasets/people/lfw/media/original/'\n",
+    "\n",
+    "fp_out = '/data_store_hdd/datasets/people/lfw/metadata/image_counts.csv'\n",
+    "\n",
+    "# glob\n",
+    "dirs = glob(join(fp_dirs,'*'))\n",
+    "\n",
+    "# count images\n",
+    "image_counts = []\n",
+    "\n",
+    "for d in tqdm(dirs):\n",
+    "  # get number of images\n",
+    "  files = file_utils.glob_multi(d, ['jpg', 'png'], recursive=False)\n",
+    "  count = len(files)\n",
+    "  name = Path(d).stem\n",
+    "  image_counts.append({'identity_key': name, 'count': count})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_counts = pd.DataFrame.from_dict(image_counts)\n",
+    "df_counts.index.name = 'index'\n",
+    "df_counts.to_csv(fp_out)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>count</th>\n",
+       "      <th>identity_key</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>index</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>14</td>\n",
+       "      <td>Kim_Clijsters</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>1</td>\n",
+       "      <td>William_Rosenberg</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>2</td>\n",
+       "      <td>John_Brady</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>3</td>\n",
+       "      <td>Juan_Ignacio_Chela</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>1</td>\n",
+       "      <td>Floyd_Keith</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "       count        identity_key\n",
+       "index                           \n",
+       "0         14       Kim_Clijsters\n",
+       "1          1   William_Rosenberg\n",
+       "2          2          John_Brady\n",
+       "3          3  Juan_Ignacio_Chela\n",
+       "4          1         Floyd_Keith"
+      ]
+     },
+     "execution_count": 24,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df_counts.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python [conda env:megapixels]",
+   "language": "python",
+   "name": "conda-env-megapixels-py"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/megapixels/notebooks/datasets/lfw/lfw_names.ipynb b/megapixels/notebooks/datasets/lfw/lfw_names.ipynb
index 37a1bd8f..8c474dd7 100644
--- a/megapixels/notebooks/datasets/lfw/lfw_names.ipynb
+++ b/megapixels/notebooks/datasets/lfw/lfw_names.ipynb
@@ -218,7 +218,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.7"
+   "version": "3.6.6"
   }
  },
  "nbformat": 4,