From a4ea2852f4b46566a61f988342aa04e4059ccef9 Mon Sep 17 00:00:00 2001 From: adamhrv Date: Tue, 8 Oct 2019 16:02:33 +0200 Subject: add notebooks --- .../datasets/megaface/megapixels_age_nyt.ipynb | 214 +++++++++++++++++++++ 1 file changed, 214 insertions(+) create mode 100644 megapixels/notebooks/datasets/megaface/megapixels_age_nyt.ipynb (limited to 'megapixels/notebooks/datasets/megaface/megapixels_age_nyt.ipynb') diff --git a/megapixels/notebooks/datasets/megaface/megapixels_age_nyt.ipynb b/megapixels/notebooks/datasets/megaface/megapixels_age_nyt.ipynb new file mode 100644 index 00000000..b49bcc42 --- /dev/null +++ b/megapixels/notebooks/datasets/megaface/megapixels_age_nyt.ipynb @@ -0,0 +1,214 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "metadata": {}, + "outputs": [], + "source": [ + "import os\n", + "from os.path import join\n", + "import sys\n", + "from pathlib import Path\n", + "\n", + "import numpy as np\n", + "import pandas as pd\n", + "\n", + "from PIL import Image\n", + "import cv2 as cv" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": {}, + "outputs": [], + "source": [ + "fp_attr = '/data_store_hdd/datasets/people/megaface/metadata/face_attributes.csv'" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": {}, + "outputs": [], + "source": [ + "df = pd.read_csv(fp_attr)" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
indexage_apparentage_realfmroi_index
0011.0518.630.81550.18450
1128.5926.640.02190.97811
2212.0919.080.68080.31922
3339.3651.360.99430.00573
4441.8452.250.82260.17744
\n", + "
" + ], + "text/plain": [ + " index age_apparent age_real f m roi_index\n", + "0 0 11.05 18.63 0.8155 0.1845 0\n", + "1 1 28.59 26.64 0.0219 0.9781 1\n", + "2 2 12.09 19.08 0.6808 0.3192 2\n", + "3 3 39.36 51.36 0.9943 0.0057 3\n", + "4 4 41.84 52.25 0.8226 0.1774 4" + ] + }, + "execution_count": 4, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 21, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Less than 21yr: 311,973 (apparent), 168,619 (real)\n", + "Less than 18yr: 175,628 (apparent), 53,602 (real)\n", + "Less than 12yr: 35,235 (apparent), 773 (real)\n", + "Less than 8yr: 1,488 (apparent), 0 (real)\n" + ] + } + ], + "source": [ + "brackets = [21, 18, 12, 8]\n", + "for b in brackets:\n", + " age_ap = len(df[df['age_apparent'] < b])\n", + " age_real = len(df[df['age_real'] < b])\n", + " print(f\"Less than {b}yr: {age_ap:,} (apparent), {age_real:,} (real)\")" + ] + }, + { + "cell_type": "code", + "execution_count": 22, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "1559780" + ] + }, + "execution_count": 22, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "len(df)" + ] + }, + { + "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 +} -- cgit v1.2.3-70-g09d2