.

1 files changed, 510 insertions, 0 deletions

diff --git a/megapixels/notebooks/datasets/lfw/lfw_make_identity_csv.ipynb b/megapixels/notebooks/datasets/lfw/lfw_make_identity_csv.ipynb
new file mode 100644
index 00000000..039614f0
--- /dev/null
+++ b/megapixels/notebooks/datasets/lfw/lfw_make_identity_csv.ipynb
@@ -0,0 +1,510 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Add identity ID to index"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from os.path import join\n",
+    "from pathlib import Path\n",
+    "import difflib\n",
+    "\n",
+    "from tqdm import tqdm_notebook as tqdm\n",
+    "import pandas as pd\n",
+    "import numpy as np"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# names\n",
+    "DATA_STORE = '/data_store_ssd/'\n",
+    "dir_dataset = 'datasets/people/lfw/metadata'"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# split records into index and uuids\n",
+    "fp_identity_in = join(DATA_STORE, dir_dataset, 'identities_old.csv')\n",
+    "fp_identity_out = join(DATA_STORE, dir_dataset, 'identity_lookup.csv')\n",
+    "\n",
+    "df_identity = pd.read_csv(fp_identity_in).set_index('index')"
+   ]
+  },
+  {
+   "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>name</th>\n",
+       "      <th>name_orig</th>\n",
+       "      <th>description</th>\n",
+       "      <th>gender</th>\n",
+       "      <th>images</th>\n",
+       "      <th>image_index</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>index</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>A. J. Cook</td>\n",
+       "      <td>AJ Cook</td>\n",
+       "      <td>Canadian actress</td>\n",
+       "      <td>f</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>AJ Lamas</td>\n",
+       "      <td>AJ Lamas</td>\n",
+       "      <td>American actor</td>\n",
+       "      <td>m</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>Aaron Eckhart</td>\n",
+       "      <td>Aaron Eckhart</td>\n",
+       "      <td>American actor</td>\n",
+       "      <td>m</td>\n",
+       "      <td>1</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>Aaron Guiel</td>\n",
+       "      <td>Aaron Guiel</td>\n",
+       "      <td>Professional baseball player</td>\n",
+       "      <td>m</td>\n",
+       "      <td>1</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>Aaron Patterson</td>\n",
+       "      <td>Aaron Patterson</td>\n",
+       "      <td>Author</td>\n",
+       "      <td>m</td>\n",
+       "      <td>1</td>\n",
+       "      <td>4</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                  name        name_orig                   description gender  \\\n",
+       "index                                                                          \n",
+       "0           A. J. Cook          AJ Cook              Canadian actress      f   \n",
+       "1             AJ Lamas         AJ Lamas                American actor      m   \n",
+       "2        Aaron Eckhart    Aaron Eckhart                American actor      m   \n",
+       "3          Aaron Guiel      Aaron Guiel  Professional baseball player      m   \n",
+       "4      Aaron Patterson  Aaron Patterson                        Author      m   \n",
+       "\n",
+       "       images  image_index  \n",
+       "index                       \n",
+       "0           1            0  \n",
+       "1           1            1  \n",
+       "2           1            2  \n",
+       "3           1            3  \n",
+       "4           1            4  "
+      ]
+     },
+     "execution_count": 24,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df_identity.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "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>name</th>\n",
+       "      <th>name_orig</th>\n",
+       "      <th>description</th>\n",
+       "      <th>gender</th>\n",
+       "      <th>images</th>\n",
+       "      <th>image_index</th>\n",
+       "      <th>subdir</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>index</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>A. J. Cook</td>\n",
+       "      <td>AJ Cook</td>\n",
+       "      <td>Canadian actress</td>\n",
+       "      <td>f</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td></td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>AJ Lamas</td>\n",
+       "      <td>AJ Lamas</td>\n",
+       "      <td>American actor</td>\n",
+       "      <td>m</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td></td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "             name name_orig       description gender  images  image_index  \\\n",
+       "index                                                                       \n",
+       "0      A. J. Cook   AJ Cook  Canadian actress      f       1            0   \n",
+       "1        AJ Lamas  AJ Lamas    American actor      m       1            1   \n",
+       "\n",
+       "      subdir  \n",
+       "index         \n",
+       "0             \n",
+       "1             "
+      ]
+     },
+     "execution_count": 25,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# associate each file with an identity\n",
+    "df_identity['subdir'] = [''] * len(df_identity)\n",
+    "df_identity.head(2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "ece5c11b90954b25b1f1e28fc2fe6b55",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "HBox(children=(IntProgress(value=0, max=5749), HTML(value='')))"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "for row in tqdm(df_identity.itertuples(), total=len(df_identity)):\n",
+    "  name = row.name_orig\n",
+    "  subdir = name.replace(' ','_')\n",
+    "  df_identity.at[row.Index, 'subdir'] = subdir"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "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>name</th>\n",
+       "      <th>name_orig</th>\n",
+       "      <th>description</th>\n",
+       "      <th>gender</th>\n",
+       "      <th>images</th>\n",
+       "      <th>image_index</th>\n",
+       "      <th>subdir</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>index</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>A. J. Cook</td>\n",
+       "      <td>AJ Cook</td>\n",
+       "      <td>Canadian actress</td>\n",
+       "      <td>f</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>AJ_Cook</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>AJ Lamas</td>\n",
+       "      <td>AJ Lamas</td>\n",
+       "      <td>American actor</td>\n",
+       "      <td>m</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>AJ_Lamas</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>Aaron Eckhart</td>\n",
+       "      <td>Aaron Eckhart</td>\n",
+       "      <td>American actor</td>\n",
+       "      <td>m</td>\n",
+       "      <td>1</td>\n",
+       "      <td>2</td>\n",
+       "      <td>Aaron_Eckhart</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>Aaron Guiel</td>\n",
+       "      <td>Aaron Guiel</td>\n",
+       "      <td>Professional baseball player</td>\n",
+       "      <td>m</td>\n",
+       "      <td>1</td>\n",
+       "      <td>3</td>\n",
+       "      <td>Aaron_Guiel</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>Aaron Patterson</td>\n",
+       "      <td>Aaron Patterson</td>\n",
+       "      <td>Author</td>\n",
+       "      <td>m</td>\n",
+       "      <td>1</td>\n",
+       "      <td>4</td>\n",
+       "      <td>Aaron_Patterson</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                  name        name_orig                   description gender  \\\n",
+       "index                                                                          \n",
+       "0           A. J. Cook          AJ Cook              Canadian actress      f   \n",
+       "1             AJ Lamas         AJ Lamas                American actor      m   \n",
+       "2        Aaron Eckhart    Aaron Eckhart                American actor      m   \n",
+       "3          Aaron Guiel      Aaron Guiel  Professional baseball player      m   \n",
+       "4      Aaron Patterson  Aaron Patterson                        Author      m   \n",
+       "\n",
+       "       images  image_index           subdir  \n",
+       "index                                        \n",
+       "0           1            0          AJ_Cook  \n",
+       "1           1            1         AJ_Lamas  \n",
+       "2           1            2    Aaron_Eckhart  \n",
+       "3           1            3      Aaron_Guiel  \n",
+       "4           1            4  Aaron_Patterson  "
+      ]
+     },
+     "execution_count": 27,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df_identity.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_identity.to_csv(fp_identity_out)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 138,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# make a clean index separate from files"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 145,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'AJ Lamas'"
+      ]
+     },
+     "execution_count": 145,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#df_identies = pd.read_csv('identities.csv')\n",
+    "df_identities.iloc[1]['name']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 149,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "1 2 3 4\n"
+     ]
+    }
+   ],
+   "source": [
+    "a = [1,2,3,4]\n",
+    "\n",
+    "print(*a)"
+   ]
+  },
+  {
+   "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
+}