From 008f3147a5e5cfae5a38c79461661bc3e4ebd216 Mon Sep 17 00:00:00 2001 From: Stefan Karner Date: Wed, 24 Apr 2019 10:18:01 +0200 Subject: [PATCH] Add Notebooks, script and requirements.txt --- LOC Colors - Data Management.ipynb | 1509 ++++++++++++++++++++++++++++ LOC Colors - Production.ipynb | 787 +++++++++++++++ create_swatches.py | 166 +++ requirements.txt | 5 + 4 files changed, 2467 insertions(+) create mode 100644 LOC Colors - Data Management.ipynb create mode 100644 LOC Colors - Production.ipynb create mode 100644 create_swatches.py create mode 100644 requirements.txt diff --git a/LOC Colors - Data Management.ipynb b/LOC Colors - Data Management.ipynb new file mode 100644 index 0000000..c4ba067 --- /dev/null +++ b/LOC Colors - Data Management.ipynb @@ -0,0 +1,1509 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# LOC Colors - Data Management" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "*Export data as minimal JSON files - only the essentials to create the swatches in the browser*" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "To use the created swatches for [https://labs.onb.ac.at/en/topic/akon-swatches/](https://labs.onb.ac.at/en/topic/akon-swatches/), I have to create a JSON file looking like this:\n", + "\n", + "```json\n", + "[[\"AK111_461\", [\"#f4e6cd\", \"#cac4b2\", \"#7e8077\", \"#3e4139\", \"#2f3431\", \"#000304\"], \"Nonza\", \"gelaufen 1903\"],\n", + "[\"AK111_072\", [\"#e2d7c1\", \"#a19c8f\", \"#504e42\", \"#494a44\", \"#010500\", \"#393c39\"], \"Kirchberg am Walde\", \"gelaufen 1914\"],\n", + "[\"AK111_077\", [\"#454234\", \"#3e3b1f\", \"#7f7e77\", \"#a9b8be\", \"#3b4347\", \"#425a6b\"], \"Kirchberg am Wechsel\", \"gelaufen 1913\"]]\n", + "```" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "The first part (the id and the colors) are part of the created swatches, the second part (a name and an approximate date) are part of the metadata to download here: [https://labs.onb.ac.at/gitlab/labs-team/raw-metadata/raw/master/akon_postcards_public_domain.csv.bz2?inline=false](https://labs.onb.ac.at/gitlab/labs-team/raw-metadata/raw/master/akon_postcards_public_domain.csv.bz2?inline=false)." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Read created swatches" + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "metadata": {}, + "outputs": [], + "source": [ + "import pandas as pd" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": {}, + "outputs": [], + "source": [ + "df = pd.read_csv('historic_postcards_color_swatches.csv.bz2', compression='bz2')" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "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", + "
Unnamed: 0akon_idimage_linkhex_colorshtml
2191421914AK036_405https://iiif.onb.ac.at/images/AKON/AK036_405/4...['#f2e3c1', '#e6dec6', '#8e8a7a', '#7b7864', '...<a href=\"https://iiif.onb.ac.at/images/AKON/AK...
\n", + "
" + ], + "text/plain": [ + " Unnamed: 0 akon_id \\\n", + "21914 21914 AK036_405 \n", + "\n", + " image_link \\\n", + "21914 https://iiif.onb.ac.at/images/AKON/AK036_405/4... \n", + "\n", + " hex_colors \\\n", + "21914 ['#f2e3c1', '#e6dec6', '#8e8a7a', '#7b7864', '... \n", + "\n", + " html \n", + "21914 \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", + "
akon_idhex_colors
14980AK010_595['#cfbfa4', '#62583b', '#c8c7b6', '#4f5144', '...
7474AK084_243['#aca693', '#414028', '#444537', '#5c5f57', '...
23730AK043_578['#4e502c', '#444735', '#51554a', '#dae1d1', '...
30352AK085_096['#b5aa9d', '#f3e7d7', '#756d62', '#211a0f', '...
22389AK038_067['#f2e9cb', '#989384', '#545245', '#fcf7db', '...
\n", + "" + ], + "text/plain": [ + " akon_id hex_colors\n", + "14980 AK010_595 ['#cfbfa4', '#62583b', '#c8c7b6', '#4f5144', '...\n", + "7474 AK084_243 ['#aca693', '#414028', '#444537', '#5c5f57', '...\n", + "23730 AK043_578 ['#4e502c', '#444735', '#51554a', '#dae1d1', '...\n", + "30352 AK085_096 ['#b5aa9d', '#f3e7d7', '#756d62', '#211a0f', '...\n", + "22389 AK038_067 ['#f2e9cb', '#989384', '#545245', '#fcf7db', '..." + ] + }, + "execution_count": 5, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "id_and_hex_colors.sample(5)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Parse Color Array" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "In order to properly export the color array as a JSON array later, convert the data representation slightly." + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": {}, + "outputs": [], + "source": [ + "import json" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": {}, + "outputs": [], + "source": [ + "id_and_hex_colors['colors'] = id_and_hex_colors['hex_colors'].apply(\n", + " lambda c: json.loads(c.replace(\"'\", '\"'))\n", + ")" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
akon_idhex_colorscolors
1291AK116_455['#f4ece0', '#d4d2ce', '#716d5c', '#65665e', '...[#f4ece0, #d4d2ce, #716d5c, #65665e, #b2b4bb, ...
\n", + "
" + ], + "text/plain": [ + " akon_id hex_colors \\\n", + "1291 AK116_455 ['#f4ece0', '#d4d2ce', '#716d5c', '#65665e', '... \n", + "\n", + " colors \n", + "1291 [#f4ece0, #d4d2ce, #716d5c, #65665e, #b2b4bb, ... " + ] + }, + "execution_count": 8, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "id_and_hex_colors.sample()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Do you see the subtle difference? The entry in the colors column is now an array with strings _without_ the single quotes `'`." + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": {}, + "outputs": [], + "source": [ + "id_and_colors = id_and_hex_colors[['akon_id', 'colors']].copy()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Add Metadata From Original Records" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Next up: Combining the id and the color array with names and dates. Read the metadata dump directly from the link found on [https://labs.onb.ac.at/en/dataset/akon/](https://labs.onb.ac.at/en/dataset/akon/):" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/opt/conda/lib/python3.6/site-packages/IPython/core/interactiveshell.py:2785: DtypeWarning: Columns (13) have mixed types. Specify dtype option on import or set low_memory=False.\n", + " interactivity=interactivity, compiler=compiler, result=result)\n" + ] + } + ], + "source": [ + "original = pd.read_csv('https://labs.onb.ac.at/gitlab/labs-team/raw-metadata/raw/master/akon_postcards_public_domain.csv.bz2?inline=false', compression='bz2')" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
akon_idnamedate
16251AK016_087Neulengbachvor 1907
23864AK044_401Gloriette1907
33292AK085_517Milanovor 1905
13875AK008_070Schloß Schönbrunn1906
12223AK004_040Pürgg1909
4129AK125_097Altausseegelaufen 1901
23756AK044_080Radstädter Tauern1907
26479AK069_067Attersee1906
14251AK109_329Josefsthalvor 1907
28518AK063_083Gaußig1908
\n", + "
" + ], + "text/plain": [ + " akon_id name date\n", + "16251 AK016_087 Neulengbach vor 1907\n", + "23864 AK044_401 Gloriette 1907\n", + "33292 AK085_517 Milano vor 1905\n", + "13875 AK008_070 Schloß Schönbrunn 1906\n", + "12223 AK004_040 Pürgg 1909\n", + "4129 AK125_097 Altaussee gelaufen 1901\n", + "23756 AK044_080 Radstädter Tauern 1907\n", + "26479 AK069_067 Attersee 1906\n", + "14251 AK109_329 Josefsthal vor 1907\n", + "28518 AK063_083 Gaußig 1908" + ] + }, + "execution_count": 11, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "original[['akon_id', 'name', 'date']].sample(10)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "These are the columns needed." + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "metadata": {}, + "outputs": [], + "source": [ + "original_info = original[['akon_id', 'name', 'date']].copy()" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "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", + "
akon_idnamedate
24871AK048_377Reichenau an der Rax1925
4191AK054_543Aflenz Kurortvor 1905
\n", + "
" + ], + "text/plain": [ + " akon_id name date\n", + "24871 AK048_377 Reichenau an der Rax 1925\n", + "4191 AK054_543 Aflenz Kurort vor 1905" + ] + }, + "execution_count": 13, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "original_info.sample(2)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Pandas offers a handy function for merging two dataframes _not on the index_, but on a shared column:" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "metadata": {}, + "outputs": [], + "source": [ + "colors_and_info = pd.merge(id_and_colors, original_info, on='akon_id')" + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "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", + "
akon_idcolorsnamedate
16356AK016_310[#5f5a57, #9c938c, #4d453f, #cabbab, #3c3b39, ...Kapellen1908
1117AK116_129[#dcc9ab, #cec0a7, #a8a290, #48473a, #6c6c62, ...Garstengelaufen 1902
\n", + "
" + ], + "text/plain": [ + " akon_id colors name \\\n", + "16356 AK016_310 [#5f5a57, #9c938c, #4d453f, #cabbab, #3c3b39, ... Kapellen \n", + "1117 AK116_129 [#dcc9ab, #cec0a7, #a8a290, #48473a, #6c6c62, ... Garsten \n", + "\n", + " date \n", + "16356 1908 \n", + "1117 gelaufen 1902 " + ] + }, + "execution_count": 16, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "colors_and_info.sample(2)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "That's exactly what's needed." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Save to JSON-File" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Pandas can export the data exactly in the target format:" + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "metadata": {}, + "outputs": [], + "source": [ + "colors_and_info.to_json('historic_postcards__id_colors_name_date.json', orient='values')" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Extract Subset" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "That's almost all. For the preview on [https://labs.onb.ac.at/en/dataset/akon/](https://labs.onb.ac.at/en/dataset/akon/) I need a subset of 100 swatches and save them:" + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "metadata": {}, + "outputs": [], + "source": [ + "id_and_colors_100 = colors_and_info.iloc[:100]" + ] + }, + { + "cell_type": "code", + "execution_count": 19, + "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", + "
akon_idcolorsnamedate
99AK111_207[#403e2c, #f9f8eb, #7e7f6b, #35362d, #32342f, ...Klosterneuburggelaufen 1908
34AK111_293[#e6d8bf, #c7c1b1, #4a4c3c, #aeafa5, #464740, ...Komotauvor 1905
86AK111_184[#f7edd6, #d1cbb8, #f6f0db, #2d2a1b, #9e9f93, ...Klausenburggelaufen 1904
3AK111_026[#e2cba6, #9e8e73, #574c39, #3c311a, #4c473b, ...Kierling1922
39AK111_072[#e5d9c2, #c0baac, #928e81, #4c493e, #484943, ...Kirchberg am Waldegelaufen 1914
\n", + "
" + ], + "text/plain": [ + " akon_id colors \\\n", + "99 AK111_207 [#403e2c, #f9f8eb, #7e7f6b, #35362d, #32342f, ... \n", + "34 AK111_293 [#e6d8bf, #c7c1b1, #4a4c3c, #aeafa5, #464740, ... \n", + "86 AK111_184 [#f7edd6, #d1cbb8, #f6f0db, #2d2a1b, #9e9f93, ... \n", + "3 AK111_026 [#e2cba6, #9e8e73, #574c39, #3c311a, #4c473b, ... \n", + "39 AK111_072 [#e5d9c2, #c0baac, #928e81, #4c493e, #484943, ... \n", + "\n", + " name date \n", + "99 Klosterneuburg gelaufen 1908 \n", + "34 Komotau vor 1905 \n", + "86 Klausenburg gelaufen 1904 \n", + "3 Kierling 1922 \n", + "39 Kirchberg am Walde gelaufen 1914 " + ] + }, + "execution_count": 19, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "id_and_colors_100.sample(5)" + ] + }, + { + "cell_type": "code", + "execution_count": 20, + "metadata": {}, + "outputs": [], + "source": [ + "id_and_colors_100.to_json('historic_postcards__id_colors_name_date__100.json', orient='values')" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "And done!" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Below there's a fast-forward, compact version of what's been done above. No need to do all this again." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Compact (with other data source)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Load Data" + ] + }, + { + "cell_type": "code", + "execution_count": 65, + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/opt/conda/lib/python3.6/site-packages/IPython/core/interactiveshell.py:2785: DtypeWarning: Columns (13) have mixed types. Specify dtype option on import or set low_memory=False.\n", + " interactivity=interactivity, compiler=compiler, result=result)\n" + ] + } + ], + "source": [ + "colors_hsv_clip = pd.read_csv('akon_with_hsv_clip50_color_swatches.csv.bz2', compression='bz2')\n", + "raw_data = pd.read_csv('akon_postcards_public_domain_1925.csv.bz2', compression='bz2')" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## View Data Format" + ] + }, + { + "cell_type": "code", + "execution_count": 66, + "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", + "
Unnamed: 0akon_idimage_linkhex_colorshtml
1191411914AK003_285https://iiif.onb.ac.at/images/AKON/AK003_285/2...['#050300', '#eee2c9', '#b6af9e', '#fdf7da', '...<a href=\"https://iiif.onb.ac.at/images/AKON/AK...
\n", + "
" + ], + "text/plain": [ + " Unnamed: 0 akon_id \\\n", + "11914 11914 AK003_285 \n", + "\n", + " image_link \\\n", + "11914 https://iiif.onb.ac.at/images/AKON/AK003_285/2... \n", + "\n", + " hex_colors \\\n", + "11914 ['#050300', '#eee2c9', '#b6af9e', '#fdf7da', '... \n", + "\n", + " html \n", + "11914 \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", + "
Unnamed: 0akon_ididaltitudebuildingcitycolorcommentmountainother...feature_classfeature_codegeoname_idlatitudelongitudenamecountry_idadmin_name_1admin_code_1geo
2343523435AK042_53325265434.0NaNFrohnleitenFalseNaNNaNNaN...PPPLA32779202.047.2666715.31667FrohnleitenATNaNNaN47.26667, 15.31667
\n", + "

1 rows × 30 columns

\n", + "" + ], + "text/plain": [ + " Unnamed: 0 akon_id id altitude building city color \\\n", + "23435 23435 AK042_533 25265 434.0 NaN Frohnleiten False \n", + "\n", + " comment mountain other ... feature_class feature_code \\\n", + "23435 NaN NaN NaN ... P PPLA3 \n", + "\n", + " geoname_id latitude longitude name country_id admin_name_1 \\\n", + "23435 2779202.0 47.26667 15.31667 Frohnleiten AT NaN \n", + "\n", + " admin_code_1 geo \n", + "23435 NaN 47.26667, 15.31667 \n", + "\n", + "[1 rows x 30 columns]" + ] + }, + "execution_count": 67, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "raw_data.sample()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Combine Data" + ] + }, + { + "cell_type": "code", + "execution_count": 68, + "metadata": {}, + "outputs": [], + "source": [ + "combined_data = pd.merge(colors_hsv_clip[['akon_id', 'hex_colors', 'image_link']],\n", + " raw_data[['akon_id', 'name', 'date']],\n", + " on='akon_id')" + ] + }, + { + "cell_type": "code", + "execution_count": 69, + "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", + "
akon_idhex_colorsimage_linknamedate
23217AK041_595['#ada896', '#fcf6d5', '#767467', '#484739', '...https://iiif.onb.ac.at/images/AKON/AK041_595/5...Ötscher1909
\n", + "
" + ], + "text/plain": [ + " akon_id hex_colors \\\n", + "23217 AK041_595 ['#ada896', '#fcf6d5', '#767467', '#484739', '... \n", + "\n", + " image_link name date \n", + "23217 https://iiif.onb.ac.at/images/AKON/AK041_595/5... Ötscher 1909 " + ] + }, + "execution_count": 69, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "combined_data.sample()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Flatten hex_colors" + ] + }, + { + "cell_type": "code", + "execution_count": 70, + "metadata": {}, + "outputs": [], + "source": [ + "combined_data['hex_colors_list'] = combined_data['hex_colors'].apply(lambda c: json.loads(c.replace(\"'\", '\"')))" + ] + }, + { + "cell_type": "code", + "execution_count": 71, + "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", + "
akon_idhex_colorsimage_linknamedatehex_colors_list
15996AK014_589['#020100', '#fbfae8', '#88887e', '#64645a', '...https://iiif.onb.ac.at/images/AKON/AK014_589/5...Maria Taferl1909[#020100, #fbfae8, #88887e, #64645a, #4d4f49, ...
\n", + "
" + ], + "text/plain": [ + " akon_id hex_colors \\\n", + "15996 AK014_589 ['#020100', '#fbfae8', '#88887e', '#64645a', '... \n", + "\n", + " image_link name date \\\n", + "15996 https://iiif.onb.ac.at/images/AKON/AK014_589/5... Maria Taferl 1909 \n", + "\n", + " hex_colors_list \n", + "15996 [#020100, #fbfae8, #88887e, #64645a, #4d4f49, ... " + ] + }, + "execution_count": 71, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "combined_data.sample()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Sanitize and Reorder" + ] + }, + { + "cell_type": "code", + "execution_count": 73, + "metadata": {}, + "outputs": [], + "source": [ + "combined_data = combined_data.drop(columns=['hex_colors']).copy()" + ] + }, + { + "cell_type": "code", + "execution_count": 74, + "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", + "
akon_idimage_linknamedatehex_colors_list
19590AK028_177https://iiif.onb.ac.at/images/AKON/AK028_177/1...Frohnleiten1906[#020100, #a8a599, #7b7a6f, #fbf9e5, #4b4b40, ...
\n", + "
" + ], + "text/plain": [ + " akon_id image_link \\\n", + "19590 AK028_177 https://iiif.onb.ac.at/images/AKON/AK028_177/1... \n", + "\n", + " name date hex_colors_list \n", + "19590 Frohnleiten 1906 [#020100, #a8a599, #7b7a6f, #fbf9e5, #4b4b40, ... " + ] + }, + "execution_count": 74, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "combined_data.sample()" + ] + }, + { + "cell_type": "code", + "execution_count": 78, + "metadata": {}, + "outputs": [], + "source": [ + "combined_data = combined_data.rename(columns={'hex_colors_list': 'hex_colors'})" + ] + }, + { + "cell_type": "code", + "execution_count": 79, + "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", + "
akon_idimage_linknamedatehex_colors
33304AK087_042https://iiif.onb.ac.at/images/AKON/AK087_042/0...Abcoudevor 1905[#f8eacd, #aca391, #5b5747, #6e6a5e, #525148, ...
\n", + "
" + ], + "text/plain": [ + " akon_id image_link name \\\n", + "33304 AK087_042 https://iiif.onb.ac.at/images/AKON/AK087_042/0... Abcoude \n", + "\n", + " date hex_colors \n", + "33304 vor 1905 [#f8eacd, #aca391, #5b5747, #6e6a5e, #525148, ... " + ] + }, + "execution_count": 79, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "combined_data.sample()" + ] + }, + { + "cell_type": "code", + "execution_count": 81, + "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", + "
akon_idhex_colorsimage_linknamedate
25575AK031_287[#444626, #caccbc, #4a4d41, #48504f, #5b7073, ...https://iiif.onb.ac.at/images/AKON/AK031_287/2...Ebensee1907
\n", + "
" + ], + "text/plain": [ + " akon_id hex_colors \\\n", + "25575 AK031_287 [#444626, #caccbc, #4a4d41, #48504f, #5b7073, ... \n", + "\n", + " image_link name date \n", + "25575 https://iiif.onb.ac.at/images/AKON/AK031_287/2... Ebensee 1907 " + ] + }, + "execution_count": 81, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "combined_data = combined_data[['akon_id', 'hex_colors', 'image_link', 'name', 'date']]\n", + "combined_data.sample()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Sample and Write" + ] + }, + { + "cell_type": "code", + "execution_count": 82, + "metadata": {}, + "outputs": [], + "source": [ + "combined_data.iloc[:100].to_json('swatches_100.json', orient='values')" + ] + }, + { + "cell_type": "code", + "execution_count": 83, + "metadata": {}, + "outputs": [], + "source": [ + "combined_data.to_json('swatches_all.json', orient='values')" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Alternate Data Format Without Link" + ] + }, + { + "cell_type": "code", + "execution_count": 84, + "metadata": {}, + "outputs": [], + "source": [ + "sans_link = combined_data[['akon_id', 'hex_colors', 'name', 'date']]" + ] + }, + { + "cell_type": "code", + "execution_count": 85, + "metadata": {}, + "outputs": [], + "source": [ + "sans_link.iloc[:100].to_json('swatches_100_nolink.json', orient='values')" + ] + }, + { + "cell_type": "code", + "execution_count": 86, + "metadata": {}, + "outputs": [], + "source": [ + "sans_link.to_json('swatches_all_nolink.json', orient='values')" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3 User Default", + "language": "python", + "name": "python_3_user_default" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.6.5" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +} diff --git a/LOC Colors - Production.ipynb b/LOC Colors - Production.ipynb new file mode 100644 index 0000000..c70a5b8 --- /dev/null +++ b/LOC Colors - Production.ipynb @@ -0,0 +1,787 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# LOC Colors - Production" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "*Calculate color swatches for historic postcards*" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Code" + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "metadata": {}, + "outputs": [], + "source": [ + "from PIL import Image\n", + "from sys import exit\n", + "from io import BytesIO\n", + "from colorsys import rgb_to_hsv, hsv_to_rgb\n", + "from scipy.cluster.vq import kmeans\n", + "from numpy import array" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": {}, + "outputs": [], + "source": [ + "DEFAULT_NUM_COLORS = 6\n", + "# default minimum and maximum values are used to clamp the color values to a specific range\n", + "# originally this was set to 170 and 200, but I'm running with 0 and 256 in order to \n", + "# not clamp the values. This can also be set as a parameter. \n", + "DEFAULT_MINV = 0\n", + "DEFAULT_MAXV = 256\n", + "\n", + "THUMB_SIZE = (200, 200)\n", + "SCALE = 256.0\n", + "\n", + "def down_scale(x):\n", + " return x / SCALE\n", + "\n", + "def up_scale(x):\n", + " return int(x * SCALE)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "The original code by Laura Wrubel uses the [RGB (red, green, blue) color space](https://en.wikipedia.org/wiki/RGB_color_space) for most color computations.\n", + "\n", + "We're using the [HSV (hue, saturation, value) color space](https://en.wikipedia.org/wiki/HSL_and_HSV) for clustering in the hope of getting prettier and more colorful results for our historic postcards.\n", + "\n", + "That necessitates modifying some utility functions:" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": {}, + "outputs": [], + "source": [ + "def clamp_hsv(color, min_v, max_v):\n", + " \"\"\"\n", + " Clamps a color such that the value (lightness) is between min_v and max_v.\n", + " \"\"\"\n", + " # use down_scale to convert color to value between 0-1 as expected by rgb_hsv\n", + " h, s, v = [down_scale(c) for c in color]\n", + " # also convert the min_v and max_v to values between 0-1\n", + " min_v, max_v = map(down_scale, (min_v, max_v))\n", + " # get the maximum of the min value and the color's value (therefore bumping it up if needed)\n", + " # then get the minimum of that number and the max_v (bumping the value down if needed)\n", + " v = min(max(min_v, v), max_v)\n", + " # apply upscale to get the h, s, v(which has been clamped) back to 0-255, return as tuple\n", + " return tuple(map(up_scale, (h, s, v)))\n", + "\n", + "\n", + "def order_by_hue_hsv(colors):\n", + " \"\"\"\n", + " Orders colors by hue.\n", + " \"\"\"\n", + " hsvs = [list(map(down_scale, color)) for color in colors]\n", + " hsvs.sort(key=lambda t: t[0])\n", + " return [tuple(map(up_scale, hsv_to_rgb(*hsv))) for hsv in hsvs]" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "All postcards are scanned in front of a black background, and many contain a lot of very dark colors. This function lets us experiment on removing all colors under a certain saturation or value threshold: colorless (grey-ish) and dark colors, respectively." + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": {}, + "outputs": [], + "source": [ + "def clip_hsv(colors_hsv, min_s, min_v):\n", + " min_s = down_scale(min_s)\n", + " min_v = down_scale(min_v)\n", + " hsvs = [tuple(map(down_scale, color)) for color in colors_hsv]\n", + " hsvs = filter(lambda hsv: (hsv[1] >= min_s) and (hsv[2] >= min_v), hsvs)\n", + " return [tuple(map(up_scale, hsv)) for hsv in hsvs]" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "If a certain color appears more than once in the picture (when `count >= 1`), we add it more than once to the dataset. This way, large areas of a single color factor in heavily in the resulting clusters:" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "metadata": {}, + "outputs": [], + "source": [ + "def get_colors(img, colorspace='HSV'):\n", + " \"\"\"\n", + " Returns a list of all the image's colors.\n", + " \"\"\"\n", + " w, h = img.size\n", + " # convert('RGB') converts the image's pixels info to RGB \n", + " # getcolors() returns an unsorted list of (count, pixel) values\n", + " # w * h ensures that maxcolors parameter is set so that each pixel could be unique\n", + " # there are three values returned in a list\n", + " # return [color for count, color in img.convert(colorspace).getcolors(w * h)]\n", + " return [single_color for count, color in img.convert(colorspace).getcolors(w * h) for single_color in [color] * count]" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": {}, + "outputs": [], + "source": [ + "def hexify(rgb):\n", + " return \"#{0:02x}{1:02x}{2:02x}\".format(*rgb)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "For experimentation, allow scaling of the colorspace (effectively making clustering along scaled down axes more likely, and along scaled up axes less likely), clipping of pixels with low saturation and/or low value.\n", + "\n", + "The scaling is inverted after the clustering algorithm is executed." + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": {}, + "outputs": [], + "source": [ + "def colorz(image_url, n=DEFAULT_NUM_COLORS, min_v=DEFAULT_MINV, max_v=DEFAULT_MAXV,\n", + " order_colors=True, coefficients=[1.0, 1.0, 1.0], clip_colors=False, min_clip_s=20, min_clip_v=20):\n", + " \"\"\"\n", + " Get the n most dominant colors of an image.\n", + " Clamps value to between min_v and max_v.\n", + "\n", + " Total number of colors returned is n, optionally ordered by hue.\n", + " Returns as a list of RGB triples.\n", + "\n", + " \"\"\"\n", + " try:\n", + " r = requests.get(image_url)\n", + " except ValueError:\n", + " print(\"{0} was not a valid URL.\".format(image_file))\n", + " exit(1)\n", + " img = Image.open(BytesIO(r.content))\n", + " img.thumbnail(THUMB_SIZE) # replace with a thumbnail with same aspect ratio, no larger than THUMB_SIZE\n", + "\n", + " obs = get_colors(img, 'HSV') # gets a list of RGB/HSV colors (e.g. (213, 191, 152)) for each pixel\n", + " # adjust the value of each color, if you've chosen to change minimum and maximum values\n", + " clamped = [clamp_hsv(color, min_v, max_v) for color in obs]\n", + " clipped = clip_hsv(clamped, min_clip_s, min_clip_v) if clip_colors else clamped\n", + " # turns the list of colors into a numpy array of floats, then applies scipy's k-means function\n", + " clusters, _ = kmeans(array(clipped).astype(float) * coefficients, n)\n", + " normalized_clusters = clusters / coefficients\n", + " colors = order_by_hue_hsv(normalized_clusters) if order_colors else normalized_clusters\n", + " \n", + " hex_colors = list(map(hexify, colors)) # turn RGB into hex colors for web\n", + " return hex_colors" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": {}, + "outputs": [], + "source": [ + "def draw_row_with_links(link_and_colors):\n", + " html = \"\"\n", + " url, colors = link_and_colors\n", + " for count, color in enumerate(colors):\n", + " square = ''.format(((count * 30)), 0, color)\n", + " html += square\n", + " full_html = '{1}'.format(url, html, len(colors) * 30)\n", + " return full_html" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Test" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Let's take a look at how different parameters affect how the swatches look." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "We'll need an image link. Grab a link to a IIIF manifest from [https://labs.onb.ac.at/en/dataset/akon/](https://labs.onb.ac.at/en/dataset/akon/) or take the one provided down below." + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": {}, + "outputs": [], + "source": [ + "import requests" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "{'@context': 'https://iiif.io/api/presentation/2/context.json',\n", + " '@id': 'https://iiif.onb.ac.at/presentation/AKON/AK115_479/manifest',\n", + " '@type': 'sc:Manifest',\n", + " 'label': 'Dresden',\n", + " 'metadata': [{'label': [{'@value': 'Id', '@language': 'en'},\n", + " {'@value': 'Id', '@language': 'ger'}],\n", + " 'value': 'AK115_479'},\n", + " {'label': [{'@value': 'Title', '@language': 'en'},\n", + " {'@value': 'Titel', '@language': 'ger'}],\n", + " 'value': 'Dresden'},\n", + " {'label': [{'@value': 'Place', '@language': 'en'},\n", + " {'@value': 'Ort', '@language': 'ger'}],\n", + " 'value': \"Dresden\"},\n", + " {'label': [{'@value': 'Year', '@language': 'en'},\n", + " {'@value': 'Jahr', '@language': 'ger'}],\n", + " 'value': '1906'},\n", + " {'label': [{'@value': 'Disseminator', '@language': 'en'},\n", + " {'@value': 'Anbieter', '@language': 'ger'}],\n", + " 'value': \"Ansichtskarten Online\"},\n", + " {'label': [{'@value': 'Physical Location', '@language': 'en'},\n", + " {'@value': 'Standort', '@language': 'ger'}],\n", + " 'value': 'Niederösterreichische Landesbibliothek 1672 - ÖNB'}],\n", + " 'description': 'Ministerium, Dampferlandeplatz',\n", + " 'viewingDirection': 'left-to-right',\n", + " 'viewingHint': 'paged',\n", + " 'license': 'http://creativecommons.org/publicdomain/mark/1.0/',\n", + " 'attribution': [{'@value': 'Austrian National Library', '@language': 'en'},\n", + " {'@value': 'Österreichische Nationalbibliothek', '@language': 'ger'}],\n", + " 'logo': 'https://iiif.onb.ac.at/logo/',\n", + " 'seeAlso': [{'@id': 'http://data.onb.ac.at/AKON/AK115_479',\n", + " 'format': 'text/html'},\n", + " {'@id': 'http://data.onb.ac.at/AKON/AK115_479.rdf',\n", + " 'format': 'application/rdf+xml'}],\n", + " 'sequences': [{'@context': 'https://iiif.io/api/presentation/2/context.json',\n", + " '@id': 'https://iiif.onb.ac.at/presentation/AKON/AK115_479/sequence/normal',\n", + " '@type': 'sc:Sequence',\n", + " 'startCanvas': 'https://iiif.onb.ac.at/presentation/AKON/AK115_479/canvas/479',\n", + " 'canvases': [{'@context': 'https://iiif.io/api/presentation/2/context.json',\n", + " '@id': 'https://iiif.onb.ac.at/presentation/AKON/AK115_479/canvas/479',\n", + " '@type': 'sc:Canvas',\n", + " 'label': 'Dresden',\n", + " 'height': 1462,\n", + " 'width': 2200,\n", + " 'images': [{'@context': 'https://iiif.io/api/presentation/2/context.json',\n", + " '@id': 'https://iiif.onb.ac.at/presentation/AKON/AK115_479/annotation/479',\n", + " '@type': 'oa:Annotation',\n", + " 'motivation': 'sc:painting',\n", + " 'resource': {'@id': 'https://iiif.onb.ac.at/images/AKON/AK115_479/479/full/full/0/native.jpg',\n", + " '@type': 'dctypes:Image',\n", + " 'height': 1462,\n", + " 'width': 2200,\n", + " 'format': 'image/jpeg',\n", + " 'service': {'@context': 'https://iiif.io/api/image/2/context.json',\n", + " '@id': 'https://iiif.onb.ac.at/images/AKON/AK115_479/479',\n", + " 'profile': 'https://iiif.io/api/image/2/level2.json'}},\n", + " 'on': 'https://iiif.onb.ac.at/presentation/AKON/AK115_479/canvas/479'}]}]}]}" + ] + }, + "execution_count": 10, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "r = requests.get('https://iiif.onb.ac.at/presentation/AKON/AK115_479/manifest/')\n", + "r.json()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "The image link can be found under `sequences[*].canvases[*].images[*].resource.@id`" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "metadata": {}, + "outputs": [], + "source": [ + "image_link = 'https://iiif.onb.ac.at/images/AKON/AK115_479/479/full/!200,200/0/native.jpg'" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Let's look at it. For our calculation, we'll use a much smaller variant of the image. Using the [IIIF Image API](https://iiif.io/api/image/2.1/), we can request an image of a certain size. To do this, we'll substitute the second `full` parameter by `!200,200`, meaning the resulting image should fit inside a 200x200 square." + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "metadata": {}, + "outputs": [ + { + "data": { + "image/jpeg": "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\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "import IPython.display as ipd\n", + "\n", + "im_r = requests.get(image_link)\n", + "ipd.display(ipd.Image(im_r.content))" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Let's create the color swatches..." + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "['#beaea3', '#494440', '#211d11', '#313c3f', '#8e9da2', '#534a4e']" + ] + }, + "execution_count": 13, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "cols1 = colorz(image_link)\n", + "cols1" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "...and display them as well:" + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "metadata": {}, + "outputs": [], + "source": [ + "def display_colors(color_array, link):\n", + " html = draw_row_with_links((link, color_array))\n", + " ipd.display(ipd.HTML(html))" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "" + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "display_colors(cols1, image_link)" + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "['#c4aa9e', '#5b5651', '#242411', '#8a9597', '#435158', '#5d5559']" + ] + }, + "execution_count": 16, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "cols2 = colorz(image_link, coefficients=[1.0, 2.0, 0.6])\n", + "cols2" + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "" + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "display_colors(cols2, image_link)" + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "['#c8aea2', '#4b4540', '#3d3422', '#4b5e62', '#829396', '#594f52']" + ] + }, + "execution_count": 18, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "cols3 = colorz(image_link, coefficients=[1.0, 2.0, 0.6], clip_colors=True, min_clip_v=30)\n", + "cols3" + ] + }, + { + "cell_type": "code", + "execution_count": 19, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "" + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "display_colors(cols3, image_link)" + ] + }, + { + "cell_type": "code", + "execution_count": 20, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "['#c9ac9f', '#49413b', '#332c1c', '#8ba9b0', '#2f393d', '#5d6b72']" + ] + }, + "execution_count": 20, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "cols5 = colorz(image_link, clip_colors=True, min_clip_s=30, min_clip_v=30)\n", + "cols5" + ] + }, + { + "cell_type": "code", + "execution_count": 21, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "" + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "display_colors(cols5, image_link)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "This is getting tedious.\n", + "\n", + "Let's define a function that computes swatches and then displays the original image and the swatches side by side:" + ] + }, + { + "cell_type": "code", + "execution_count": 22, + "metadata": {}, + "outputs": [], + "source": [ + "def colorize_and_display(image_link=image_link, **kwargs):\n", + " cols = colorz(image_link, **kwargs)\n", + " display_colors(cols, image_link)\n", + " ipd.display(ipd.Image(requests.get(image_link).content))" + ] + }, + { + "cell_type": "code", + "execution_count": 23, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "" + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/jpeg": "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\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "colorize_and_display(clip_colors=True, min_clip_s=50, min_clip_v=0)" + ] + }, + { + "cell_type": "code", + "execution_count": 24, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "" + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/jpeg": "/9j/4AAQSkZJRgABAQAAAQABAAD//gAXR2VuZXJhdGVkIGJ5IElJUEltYWdl/9sAQwADAgIDAgIDAwMDBAMDBAUIBQUEBAUKBwcGCAwKDAwLCgsLDQ4SEA0OEQ4LCxAWEBETFBUVFQwPFxgWFBgSFBUU/9sAQwEDBAQFBAUJBQUJFA0LDRQUFBQUFBQUFBQUFBQUFBQUFBQUFBQUFBQUFBQUFBQUFBQUFBQUFBQUFBQUFBQUFBQU/8AAEQgAhADIAwEiAAIRAQMRAf/EAB8AAAEFAQEBAQEBAAAAAAAAAAABAgMEBQYHCAkKC//EALUQAAIBAwMCBAMFBQQEAAABfQECAwAEEQUSITFBBhNRYQcicRQygZGhCCNCscEVUtHwJDNicoIJChYXGBkaJSYnKCkqNDU2Nzg5OkNERUZHSElKU1RVVldYWVpjZGVmZ2hpanN0dXZ3eHl6g4SFhoeIiYqSk5SVlpeYmZqio6Slpqeoqaqys7S1tre4ubrCw8TFxsfIycrS09TV1tfY2drh4uPk5ebn6Onq8fLz9PX29/j5+v/EAB8BAAMBAQEBAQEBAQEAAAAAAAABAgMEBQYHCAkKC//EALURAAIBAgQEAwQHBQQEAAECdwABAgMRBAUhMQYSQVEHYXETIjKBCBRCkaGxwQkjM1LwFWJy0QoWJDThJfEXGBkaJicoKSo1Njc4OTpDREVGR0hJSlNUVVZXWFlaY2RlZmdoaWpzdHV2d3h5eoKDhIWGh4iJipKTlJWWl5iZmqKjpKWmp6ipqrKztLW2t7i5usLDxMXGx8jJytLT1NXW19jZ2uLj5OXm5+jp6vLz9PX29/j5+v/aAAwDAQACEQMRAD8A+I/gb8B5PjHBq9x/bK6VFYPFGf8AR/NaQuHP95cY2+vevVW/YXjwCPGLgHru0wcf+Ra0v2ELI3Oh+LSCRi6txkf7j19TNpsjpENxKuC2PYd+ffFenQo05Q5pbng4rF14VnCD0R8jx/sJM8Zb/hMtuOmdN/8AttA/YSLsQvjLcD0P9mcEf9/favrP7Xa21yLSWeOKYqJDEWw3uc9P8+9WLfU9Lkgt3W8hMNwnmws5GGj/AL/0yBznrx9dPY0f6ZgsVjGr6/d/wD5H/wCGDn7+Mh7/APEt6fX97701f2Dbh2wni8Nzj/kG9f8AyLX2bMdLsZJVuLmK3dHMfluQuTgHAB9AR+dbGhQ2Gp2101pfWiMmd2JlBQKedxGcduR61y1pYWiryZ6GFhmOJklBad7HxTZ/8E8NXvWYReKxkAEZ0w5x/wB/aszf8E39eh358Tg7ccrphI6nv5vtX3vbaktlKjnV7WOCXeq8CNd4QglTyNwKk85GAPlyCSxvEUseZW1qxZi8cnyyfKUHl7gMsSPuy87iTv74GfG+v0n8END6WOUYlL36uvp/wD8/G/4J+X8RKyeL1TnGG0wjv/11/wA8Vcsf+CdGq36s0XiwEL3GmE/+1a+8ZNVW+0JEu9WsJr8SD/SSVAKh1YqMd9gYZx79RW9pXi3SIrFVt2tmiXGWDg7SQCOf+BDn3961eNotWUdTm/szGRbbneK7L/gHwba/8EvNeuYy6+Mogg6A6YQf1lFZ+o/8E2dV01wk3jJMeq6Z9f8Apr9P85r9BbLx1ZCMSrqNu0EjBIz5oIJ27sZHqpB/Gr0fivSb6dba5uLNmYfKDMuSORkc/wCyefY+lRHFRvdrQ1ngKyjeMn9x+bT/APBPm7jYq3jLn1OlH/47/nNNg/4J66hOwC+MYhxn/kGnPt/y0r9FdU0zSrwyLYywOUAZ4I5QxAPqByKzIrdLdtwjMZHykEH8s+n+etehTqUaiukeDU+s0pcs5fgfn5L/AME99QR3z40j29VI00nP/kWoj/wT/vkj3HxnFnp/yDT+Z/e/5/Ovv+fToJHZto3NwQePzH61nPYKvzOrFQMlW6jJz6EDn/PWumNOm+hzuvXW0j4Ug/4J8atICU8YQZ6cWDf/AByrMP8AwTk1y5CmLxbA2Rkn+zmwPx8yvvXQ0htnkM0W6NVwCTk9ent0rpf+Eit7KyLbQ8g5KA989a8ytiqNOfIonr4fDYmrDnlP8Efn3Yf8ExtavyF/4TmyiYEbg+nP8v1/eVduv+CWevQW7Sx+O7S4IGfLXTWBI/GSvuiPxDZrMPsw2Ix3H5jxz9OldBY6mvllWzkjAB6Z9fp/jXP7duXkep9VtT3uz8xJv2ANSt3dJfGFurDqP7Obr/38pg/YE1FQN3jG3BzzjT2P/s9foJ4g0FbzUJJE+Tcx3EHj/P8An63rHwNbi0bcWZyM7QcZxz6/SvXboRipSPml9dnNwj08j86v+GCdQMZb/hMbc9CB/Z7f/HKWX9gW/RW/4rG23YzzYHnr/wBNPb9a/QG68HlG2RIQV4Ge/b/P/wCus2bwzNA7FY259B+ufyrSMaMtjCVXFx3/ACPzU+LH7KuqfCzwfeeIJdag1C3tjGJI1gaNvnkWMdSe7iivq79szTZLb4BeJS6kbTZhiQf+fuHp+v50Vy1IqMmo7Hp4apOpTvPc82/4J5WUd1onjVmJV1ubXJPZdj+v419nWfh9ZC7SKCvQKR26j8TXyR/wTZtzP4c8bHA2rfWxBPYmNvx9P85r7QgcLHFJFLgygeWwOC+Rn8eMn6A1yPHOlJw7HespjiI+2vqzIt/BttcBwbO1d5VCM+wFioyQpOOQM/8Ajxq3B4JsjZkvZwOFJVFkjXAzlTgEcDk8e5Hc50YZ2W4Egbac4y3T6Zx25+mRVo6pbwxDzCFOMDIyep4wPx9ufxrN5iuhUcna66GRc+FLG5jIntbaVySczW4kwcYJHHXGMn6VqaF4X0u1tnhSxtosgb0SFQhJxnIXg5wOfYelZb6tJPKjR2FxJEpz542rweO7Z9O1X9H1AXmoNbt8rjhBImOQT05ORjFZvEUsRpURrHC18Gr0ZmhLo+jGOKGW0tJIYshIjbrtVeDwCOASAfqPah9K8PyRvu0u0aYYbzGgTdn7uc49AR/jVmXSWEYV0DjbjIP+ffpWZ/ZyyMUYM2SAVLbmGQDg8n/J9K2pwwy1itTmqYvGtWk9Bg8MaHfKsDaTp3ljIQrbou3r04yM89KrP4f0u2823WwslRztdBAu1wCCN3GDzg/h24q//ZSguUeQseWUNx17jFRX2nNJGSI33DBMjd/wHXvWeJowrJKNkzTCYyrQu5ttFi30zTkWUfZrM7pDK4MSnLngscjBOAAep49qz207TZdQMi6bZPJGQDL9nTjbuC4wvbe2PTcemaSLTZnAQAjA3fMep5/XgdvSn2thLbzFiQ2cMM9CM/0roo0VTjyy1OPE4udaXNFtL1Oi0Sw0+2R/JsoYZ5Budo4ghYknJOAOSaWTSrdsSALknHzcnqeD71RN2iptMbFlAOUOPrz3qtLqss74VvL2cheTgZ/z+lEKUk3yscq1KcVzK7KWpsbCUj7q9AAeBzz1/wA+1VWvIZF2mGNiTkA9/bFTaqZrtjuBZh1Yk9M8/r7elVm0wsr5Kq3IwD09v5/r9a9KDSVpPU8mpGTleCdh0JimRgECkjkhgG/T86ZcadFLAoRAsu7I2jGOO45/rUcNhLC8mXLMOmeeOT9ev+e9SNBiNfmC5bG48jNZVaNKfvM3o4itS91GctsYlVnkVWOACQcZ9B7cjH405dVntEk3oWZCcEDp09v8/wAr0lsTks+4jI+fuevr6/zqNvnjZCxDN90Nzgeo56/556VySpUrXR2wxNe+qKS6tMDJO6gyN2LZznkn3HH16Vuab4lkZEUocdM9c47jB5HSsF7NJPMUOuT/AA85OCev5Z+oqO3s5oYgc4xgYI5/zz/Ookk42epvRk4z5lod/aawJkAMYxnHK5xz6/hViK8t4wNwJyOcnnAzXI6XcPMypv2tjg9B0zjj0q7eSNbovlkDjOR+f9P/ANdciTi7Jnsv2dSHM0eN/t4Wls/7MHi64iXBElhhiPW9g4/Kiua/bY1K4m/Z08WwtI3l+bZbl4A/4/ISB1orugmlq7nkT5L+4rI+MPgJ8bvFvwi0fUk8NNZlb+7Bkju7YyhmRBjowPRu1e06N+3b4709NMuNa8P6dfacspjNxbRSxeeVjKMBIXZS2HBwOcjng186fCvTo9RsLy3MSyyXF1HbL5qFkRWHLHBBJGQdvQ45FeqXHg7X5rG4tpFtZLCOGSRYpI52RgIZXC48zA4WMZwOCPasJ0YTbbRpCvVhZRlofbfhb49eD/GHhKy1mDWrTT47s+WYLyeOKaGTnKMu4nIIPTIOOCcjNy7+K/gmziIXxfoguHYKS+pQ53cdcN6HpnvX502Pg3TddRlZjAUAyHtpZiAQTjdnkcNjv19qkn+HQs7ZY49Q8pJNkeHtnRVJKnG4ZHGV6eo7VxPAx3Umdyx9S1nFH6cyX8Wk2Ety13GLYxFw7SABEA659OM8fWr3hu6tbqyiu7WaK5WaJZBLEwdXU8ghhwR0Ix/WvgLwp4q8Z698KdQ8INrZ/s2yWGQSwA/aEt3VwbbexX5OAcHGAAu45Arc8J/EL4weCJdL8K6Rf2Emio/2K0uNRtUkljCjBQZbJC7cKCce+MY8+dFxbTkrnoQxCkk+V2Z98JqDW87C4uCqcsHkkxtA6gkk9Oua+dvgf+0RafET4u+LbBo70afqhhvtLiuxApj8qJYpt+yRiC+Ito5ztzx3+avjB4h+KPxLmvLO81hNU0Bf30lqClpD7AxFiSBsyAc4Pucnhm+GV5p0WnXst08t0sVtfxWkUalskb12EMRkbe3PtnGdqUIRi+aWrMKzlOS5Y6I/WOW7tmTEY8vB+deCA3Oc/wCfSla9RlIIcN689eef1r5L/Z3+P1zDPq+h+M710txJ9qsdWuVkMjhljzCVCdBlmHQjLAjpn2PWPjj4F02FJJfEMC+YVQD7PM3J74CH2z25pxVVapNo19nhrWdk/M9Da/mXMascMNvOMDn6fQd+v5AWa8BmkBjJIGAOvt1/z715zZ/GbwVqyrJbeI7YsrANuSSPJ54+ZR3/AJe1Xx8U/CocGPXbIk8n95gjrwOfb9frWqrVf5X9zMHhqD2a/A7xdMiiV2uZkO5QcsM5/Lt/WoYoI0jbJ/eDkhf/AK9cZ/ws7wxPk/29aHaMHZIOnTJ9u1WoviV4ZZhjWLRscgeZ0OT/AJ6//X09vV7P8SFg6HdfgdkpjRQPlLA4LHIz79Pr/nqyZVLO6ngDaFA4H8/1Pp7muTX4meF4EAk1mzQ/3d/+eMf59WH4n+Fndyuv2BGepmAJyff/AD+VRzVHrZ/czsjCgly3X4HQXFus0hYp8w5BzzUEVsVZFcxkDgYyBx3wP5cVkf8ACxvCwZS3iDTtrMNu+6UBiTgdTzyePXNSyfEPwy2wHX9NUMSoP2lMFh17/T9Kaq1IrUX1ejLVWNhLUkqF2g7QB1BA/wA/1p404oPmIYgDJxkVgz/FHwvatbrJ4h00G5cor/aoyuQrN8zZwv3SMk8kqByRVW8+MHg23ZRL4t0WMnIU/bo+3XndjuPzqHUbVhewgux0senL8wZFCnjGAB39fenNpMcSFUCkf3ioyfbiufb4keH1kjA1i0KOoMbLIpVsnGAQcZ9uv5GpF+Iugm7NuNa07f5K3AJukwYyAVYHPQhgQe4NTGq47jdCMuxcFj9jVhHGVYgbiR1/z/nvUIeVIipRiB0BP3fb8Kjt/iHoVzqF3bDVbBlto4XaSOcFcyMVCk9M/c7/AMYzjim3XxE8IxWJuZfEGlxxbC6s15GnAz0DNn1xxXSq6etjm+r20UtDwX9tOB1/Z18TOQ2fMst27Gc/a4hg/r/nNFSfto+IdK1T9mrxMbO7trgyPp7oYZFfIa7jK4I65CN+Cmiu2hPni2ebiKfsp8vkfBPw9l1ODQ7x9OhVpDcsDLLeLbquI07sy5PJ7966j/hNr20nMeoi5LNGqMtvfiRAQxywZXwdwyMDgYGOlefeGoLe40s+d5uRcvjy3CjGyP1U1uJY6eTjbckgZ5kU/wDslTKqoto5r2Ny28d3FtbTJC90HMY+aO5VASAQDgnnqMj2+uWzfEHUL6yNrOkrrG+6LzbtWG3gfNnvx/8AW6AYr6RpwZm3S57Dz1X+cdJY6NbXN0scEdzKXHCRzoSWyBgYQ/3un+Tj7fTcOY7Hw78V73w4t+Baw3K3YXDPdR7kKq47qeu8nnnp+O1pPxjK61pV5PbfZo7WSWQulxAxDOki7lBIHG5OD/tewrzoaPaOke+Kdpj0CXCoCMDGAYzxz61atPDlvcMVt9OuLhgu4r9sQ5HrgIDjGaxfsqju9zWFacVZM7a8+Kn2fVtTsLVxPpF27ot5NIvmrGDIIxtjBBIDY4zyTzjmp9Q+IMF5Bpy28k63VjZ28Tu9t8rMkQHXBJGQ59MD655C20BJC8Ufh5ZbiANJIBLKdqICX3qGyAMZJyMAHn0kubOa6+wrb6Baw5u0ijSKW4YNvyPLO6ZhyGzxg/nzLhTvaxvDFTW5oeKPHNnr+gafZaLeXEV5DLt+aMRptAIXDrkknuOnAx3FZ2ga1eWupR2+q3zalHBsJhZHkZMsr9CODgd+ea37j4e+ItOE0P8Awi8dl5JLSt9k3QwoCRvZ3yqrkH5mIHIweaq6VaBNWs7nULnSXgumd28n7O7MQjFiY4vmyQpxxyQAOcA7U3GCtG9jGrOVWXNJaltfF+pxak7WUIt7O9uDHbwxWpEkhycIpxljyOATnA+p3bzUddsR51xbajZ5kw73MAj2kjOMNgYx1JPH0qxo/wAI/E134bfxRYXMNnb6bIVjlt/Ojni8zEbYVU8wAhjxj7pJ6HFSaV8GPE+oTXl1Gl5fRyxNDM/2KdjICv3V85QcngbscZ4PWtY1JpPlT/r5mfsYyetx1hrXiK1i+0tpd3c27xtKssloyEovLFfuggA8+gPTmrdt8TZmuLNzpF8FdSVWJMhifXAJ4GOOMVoaH8PPiKGIl0nXZIJictcqkmQMleG3MDn2GBk8mvR9N+GXxDv57a5stHvtEmjt/skcsV7bRqkZwcMJQ7dQvK88cdMnRV6ito/6+YLCxtueW6Jq3iTTzql5rHh/xLdfaI82slvPJbRQMS5yQhAbkrx/sjtTPGvjmY2ejWd9oOp201vOstwJplc3EJ3AKTuySQSvOT09q+tvhx8OvG3huFxqfjG/mheFo0tI7iOYxljncJJIM7lOdpA7nduwMd/AniSxsoo4plvRHCkYkvJhvfHG59qqCx6nAGc9K1i9ee1mU0+XkvdH5wXHxP1y6u79oLrUowEOMsqmOMvkDIOD6DGPb30NM+It9e2SxWGkandSPGInlkCKd+OWzvxkkZxX1r8U/hp4v+IV/pV4bTQreOwdyQzkfaC7R/K+VOR8gAH+13rWPwthuJnab4deAME8hbQnIyfVPas5R9o9f6/EIvkWj/A+KvFGo6v4jhtEuPD+o2/kFtr+TkE9DnLY/wAM1zOpaPrasn+halBb7xtzCAuAf9lj2UevT2r7+m+DukI48v4f+ELeVGDK0CNGcjuCqjFc5r/gzTtH1nw9p9t4I8PfbNcuJ7eGZLiZChS2mnJbAycrER9cUJNLlshp6812fD1xcXupSzy251SSaZykCWqPJ845JAB3Y6846k1c0TRfEem6bqUDaRqrvd+V5Dm0lzGULFSpIyDkrgj0r6p8C/srax4T837Wum6nDI0jMPt9xau4ZiwJaJUOQccA44HHAx0V/wDAK7vbeaNFubAbdqi18T3zBSOm3zNw7DqD9MU3Hm3Q4u2vN+B8cXcXidGjt7u8vLUxMfKiuorgMjOmxiRsJywU5I689apXfibVNBsrawuNUhRop0uolmtpuSUZctuhO7OV+8COMivp3xh8DvEHg2ziutL8X6xYPd6na27r/aER3tPcxozcQKS/fJJ+73Gc+e/Gb4e67Hd6HNq3jZvE4SeaO3S4ubcfZ5DEX3MRGuAdi5GMkAgEHrNulvxJ5LptM8B8ZPrEui311ezC6juRG7Tujq8hMitu+ZRnkHn0H1FFdd44viPhPqNja6xY3UMbQ+daRef5hVZLdBIN0YG0MFGSRkycZxRWtNpoizW5hfBiz1SXSbmWzOlSQrelWiv0SSQNsj+ZULoSAM5wcfoa9ttvhjqF5ctAvinStMhHlKzS6JaZ5JByDK5PAGD/ABEnOMbj5r+zXpzXuj6pIjFHivFwwcqVzGoJGASe3FfRVlpAtI8oROzbQ0oPzEDHr9Dnj8PU5ObUm6OK0v4Y3dna3Ln4m6VcFrQo0dppRVoyyElkZIByMDBJ6Z4BIrF174aXWmrph0jXfEHi69X7QyhI4oQi7VLEvMu5hkL65ACgDdke76Vp0Fvp0QClspt3LgkjA5z3qOOO3stSjfzFULE0SeZ8vBIJ4Xr0HX29TTVO2wcyRwWmeDvF3xC8JWOk+K/Dtlbw3Mam8v4JIYbx3Xc6OwEWFywQYU9M+prjPC/7M2szXSxXukxqkaZnlvLx1TJdtvleU4JAAHU+/pX0XbeJLa3hIR89PmzkH9Pf9aVfGUSxIVbAZsZ7ev8AI1Spt9Be2jE860f9nDw9pNvDcT2am8xmSeDUbmFsmMqfuvjuR0HUjpxXM/EL4KWWqXyWmjXFlp1td3MVokc9obuRGZpMuskjDbhNuMfMMEbsV7Nc+KXkOd+Rzlm9Kzg9tcXNvOzITHIsn7xcbSO/4ZpqlboHtk+pzngH4A+I9I0uXT9Y8aXV1Yl9yW0Klo3jPBUiQtwRnj3PWujufgtpEMsZtY7a2jGMrBbRISRjBLbdx6DqTXYjX7dQIzJhmyBwe2M8fjU0t0hVmLKSTkoDyKfIuo1VfRmB4B+FPh7wCJ5tNtJmu5GYNdee3mKG2blByODsXoOdoz0FdrolpZ6YJXtbdYpJCHdwPmfPqT1796xn1BFWRj82eMjrnvii01dI1OE2/wCzg8fX9afJoR7R9TsLe8LuwUjb1BJ/+v6CoNP1PWo9a1I350hdDAjSwNtJMb0uADIZlYCMJ8w27ST69a51tQjt97tNjjG1n/i68j8qp+IPF0dnotu/2mL7W948ZjeTLIvlxk8ZyOoP40uSzH7XRnpg11FUN5gYNjPJ/P61HJ4lwgVGIBABVenr1614VD8VrJkkxe28+wjcY3LDqByV9yB9SB3q2nj5bzTp42ZCsodPlZ/Q7gO+eDnuMH0rb2Whh7fW1zvfiD4juLPw1+6uHhk/tHTE3xAM21tQt1YYKkcqzDp9MVtP4nRWYySqrk+uC3pwa8P8ffEFZrARkR+YdS059xyOl/A2B+VY3if41R6ZJJtZZHyWBjBAx6d/84pezS3F7bse9eKvihpvgrQLnVtWvILPTbdkRp5g4jUtIEUEqrEDLqOFOM54GSPGPEvx70zxB4v8MXGna74XVfD13LfvJca8iicSW9zblUO3J4lDdM9cgDBPinin4uav4q02+tlaC2gkVSiun+rZTuVs4yWyPoCB715F4L8B6JdGzn1TWfItYZy0mnyq/mGNWXhdqdX5AGR0ySODWE7L4TelJy+I/Q/wB8bNJ8faXFLbajp0twLb7VPa291JJJAGwCrbokAwWxj27cgO8c/F/T/AvhTVNcv3+0RWKoWWIjezMwRV9Mliv+NfLWmfEDR9B1yE+EtIfT7X7Ilm5ubgvuUSO5YEHAJ3KOOP3a4A74HxJ/aClS9uPDV5odtrllKIiwkbcGLKGXaMfeBPFKLjytvcJNudo6o1/Fn7TVp8VZrRriXxPY3lnOs9lY6TbW4tZJEYsjzu8zE7Sc5UDr3wMLo8llrmhWsvifxZ40sYDHNFd2FreyXsbxqw2FWDybmJZARtH3XGMYJ53wxpUl1Etv8A8InD4ejQ4kuNQ1k29weMENFCFJbGOCqjr07dNa6TcWMok0m0s7hdkjb77UruYYBB/wBWu4KenGT16+ufObKEt7HnH7Q/jJvEtjpsVkmrJptrbC0e41DTntXvGWTf5khOAzZYDgDhV44FFaHxe0q9uPhvf6he/wBhzTRvbOZ7JJGm+Z1H3ztAzuBIwQQBjFFXDYc7p6jP2YZQuh62rMFU3a5/79j/AAr3SG6kY7SXZVPIYng5HOOa+ef2drnydD1hSwXN0p+9jPyL7f5/n7BDqKAIFY89NrcdDzz9D1//AFd1Ne6eVVb53Y7r7ZK0JUxCROwxu57ce3+PWq324R/OsCRlh2A5HPJ4+tc+t9JJFguFQ9xgkD3rH1G9LucXDBzxx1P0x71bSMlKXc6ifVTcmUIcqByNpwP8+v60y0uJ7mN/LDA9iy4Jz64/z1rldNllViPMPQMdpPI68joK0Y3nMThZ2IBwVcAEEH0oVgd+51FtdzRx53sFHJBP+RnpT7Od7hw3IJOflHH09vSueN9cBFUTMSGwCqrz/wCO+tNs9R86WRIr2S4ljG94oNshRfUhVyB74x79MFhp2PQotSVCAu7kZ2jqB+f0/Sllv23MgfDBscj35zXnlvrv2mNZLeW5vUfIDxmNk4zzkDkcHkdeDTrO61jVrgw2gbzFJLMzKV4xwPlDZ+YcFR9aLBzdzuA15G05WXKhsoCoG3sQcduh9ck9qpTf2jc6ZJNBcahbsgzIw8hfKxn1U55AHpgk5yAK898J+JtS8Wa14j022uJbltOEe1NPBfcHJUghVVlKkBSCeDkduczRvDOo+JtSS1sbCfR7p742hk1K2UygpGWO8xtv3EuDhyW4JOdxJzlKyNqcHJ2sWF+M+ixaIjw2Or6vcwwqbgsJApG9UJAZmjyc7gvHHGRVfSPiHd+LfC+vW0FuNN1i3txfWyRov/HyFMKKylG4/wBZwGOCvQEEnzbxDfeJPAnibWfDPifTrN7uwMcWI45djqzq0W0KyExFfmB+VsYzzwca98b6vrKq8l2lmjcQxWcYREH90NtaRzuZzgv3B9jwSqVO6R6EKNNbps9S1jw4/ifTrK7stV8QeIdW+3obi9tkZIIkCxeWCA+Ad5Dbgg9NuQDWxph8R+C/CMVheW+qieRHkFxLbPcxl5CT+8mQfKwYkAEZyoyuOa8f8AeLZ/Cvitdb1iC41rVNNWNrKK6m3LBcKrK5k3HKldzkAfxgZ6V9a/D74oeI/id4R1HUbTTU0qWCSOGE3Vyojv5W3EpDghmUBVztbPzjsDnNSqxlpK5rKnRmrWseJ+K/EV+J9Jh1u1h0DTLya3ma7mmZnhRblc/uyOSuAxUn7rZ9a8zufEv264cQie9dAVRYxhQeAd24dMgsB1+bB6cfSHx98A+HZpvD954j102t5a/ZLKS3mGJVMlwpmcQnLlVQP1JJyvJIOfGfFnxW0vTbrXdH8F6Rbvps1ywsp7i1CNAu7jYoPzYCxbS+eVJxkmtm5y1kzCNOnHRIgRL6G0829tWt53AKxJGvOVB7uOcEnHX8Kv6b8PtQvre0v72KCw0+4xIj3JVCYycb1QOSeh6jnHtXQeEdDvIvDNt4k8T3xBdQYLaUgPdNgkFic5XJz+f40/EfiQz3U9zdXUIuZgqSr52SoyMLj+EcAcAHAxnBxSeisi4wT1eiLrN4V0aUAu+olOA20QJu544DE/mOore074gQ28Mr6dpVpZvs2vOljGJXHozbMn/PWvL5L+bUZoLPTtOur64lOI0t1aRnJViAqgZPKntnGOlek+E/2d/iD4s2LdQQ+F7EgFpLtg0wHPRVy2enDFRUqDe5onGOxQufFKQXkf2xxG9wCUR9qjgZOB07+lRah8RYrSFxYabc6jPDBMrRQKAoJClmOOQoAJJx/XHtHhr9l3wd4c1qG41Sa+8S3SI/7u5UpBuJHJ2HPb7rMc88HFdj4ifwtaaDqehadZAedHJbTxaZbp8hZSGDMfkRsN0Yg9ODxkUErlc0mfKXxgfxNrfwy8YSajpLaLZ6Rc2UU8V0rLLI8rxOiDK4yoZSw4wCvriiu3/ad1/U9Q+Dmuwz2ttZxNc2sky27F2kcSQqGdiByQqdBn5RnjglaRMpXvqeIfAWQxaFqpBwDdgEEcH5F4r0saqsUwj3OuMAhx8w9/YdO9eUfBJimiang7c3OC4zn7i8Y9Px/wDr96b3b85kDKWznbtwP5ev510Rk0jyqkb1GdEdYAQruGFAHJA59P8AOKovqiSSPGsm8kDdyTj/APX71z13q5YEK2SCSFBB7/n71lnV5F+YhVJPViwA9z6/lV85monajVCSyCUF/wDe+ZeO4/8AretWopNU8pJIbY3NntfzHjYM6lSuAEAyR83J6D5c/eFeetq9y8YVJAvQZCjj35H9KuW8HheSCQat4x1jSo5C0k0b2fnR+ayMGwUQ8EhV5OcH/Z+YdS3Q2hS5t2dF4i8QppF+Ybq0vNRuXRP3USBlDZYncScAkegJOM4rkJviFObZI7fTrWF1mBCs/msrK4OMDAz8vIIBA/OrWpy/DtNNuXsfG2q6tqqKi2tvfWHl22FIyHIUEYG7GAc9AB36Hwr4Bt/EOl3DTXC2yiBJZBsMSglnUPFI+GU/u2BVkYHcMDcVIxnVl0R1U6EdnucDfePtblliWTWCiqclIGVABtxyUCsSTnO4/jWFea7LNcSlru42SqMxW0j/ALwgfxM7M345PWvolP2O7xbUR6bajVtT89oZItRumtoYYgr+XMSnJLMqfKA45PXBr2bUfgf4B8Daro94l/p/hfTLSTzpbS6ihuJdRIbIBklywXHBWPGc81zupNnTGlCKPirwVoHjDWbqUeFtH1O8kJ2MbRJZPLycEswIwegye3Fd18P/AIffEiPQP7a0a/8AtOkfb90a6a/2tpJiq8rHbludijL5CgE/PyK+ktY+JPw18P6lPqem299qmoOpj3QySR26LiMbFVmCop8pD8inkZ78+ea7+1o+jaTnQrHT9EsIj5UI0+ETFD2C8KnT/ZNTZ7stSitEcf8AFz9kf4j6h4gs1tnu/GQFpvm1KJQixvvIMaKTvb5VDbjnIfAHBzxvw/8ABfhv4c+IbC78Ta3azX1nqESPb2bCWWJg3B2EgEKy/MCykeueKqfFX4+eL/FWbGLV557GeM+bMZSI3OcFVJO3gDPy/wB70rynS5BZXCXEt4GKMGCwru5HbdwB+GaaYaM9U8X/ALS/jWC41zw9pmtx3mgmaW3tb6TSrO3v3gDkKfNjT5WwBypPHQjisXwv8UtbFhNb+d4h1Z3Iknt5tem8iYAYAkWFUl2YHQSr9etUV8TLPpFxpNrpFkkcxUCVog8vByDn8BwfX6V3fgj4P+L9Y029jbTHsvPMTQy3Z8lcAtklTgn+E8A/jTTXQl3ZzWs3t/rFrpwuYrayh81Ils7C0SJYsliANoJbHTLszHuTV7SU0/w8bgW0cGo6jLIwiErbzu5GFVec8Drzz9K9y0X4C2dsIh4svkuIbVlkQ2EpRGYKF+clAQODyPXqMV3XwtttEsLfXDp2lW+nmw1i50/ztpMj7NhyWPP8fQk1a7kqLPHdN+H3xK8afZobqL7BZLLlF1aWSNETbgbYsBuDkjKj3r0PQP2atItzbNrt/NrBjCfJEv2aJtpz0UljyezDpXd614k03RWEk98qSysRGuATN6hUHLY6nb074FcnP8SdTvGEen2nlRAY+03PzbzzysYI492bPse5exfLfc9E03SNC8FadK9jbWmk2iLmVgiQooHd246epNQ3nxFS2IXS7ZrySQDbNcExQ455HG5jjngYIGSw7+Rz6jPPMlxd3U99c78iabBwRn7irhUx/sqM555qWLWHXEjEudvU4BAz6j1P4fjnKui1E7W+1e51iST7ZfPciQ5EEYMcK8/3Qcvx/fLewHWltEjKCMYhjQABFwqoOwx269OnNcmdXjhP7zBdeVBO4L2OPyqRNeRvPAceWjEuWyNv1Hbk/rU7lqy2OJ/afljPwo1jY25jLboQOQv7+M/5yaK5f9oPxSNa+Gt9DbIHtvNhLXLDAl/epjZjr05PTpjPYrSJhPc8u+D6xroN67ldovG4LYz+7THb3rq7u4CEnLs2STg5PPoM4/Sud+EGk3GoeCtRns7Wa5ktr2Rrgwru2R+VFgkenD84PQ9hxPc3sUkm4AN+ROcegrSDTWh51WLjPUfNcyyNs3EHAHOBkfrj+tVpGYDPmMzj/ZHI/CkEw3FRnYe5OOPTH/16rmWJQd/zDBHzcfTir0ISL2i2v9s3bQfb7LTYkXzDPqV0sEeM4wM8sfZQT+uOkuG8D+HdHu573WtS8S3ZiP7vRrMR20Z9558ZGcdEJ56Vxf2qFwMKvGMAjIJ9uuf51xeo67c3zXUITcrEfMDgYHrmofqbwS7Dta8WRX1881rpkdoC+RvbLdeM4AGfwre8KfFPxRok+dNvls12FCPKDgrzxhs57/nXFw6a0hbzHRB6L8x/Dt39a1rOyWzLPsMh4yrkkNyc5AwazudCaWx7LH8dPE8kUX2rX9S1C5jjFu1mbgxRSDABI2YOTgdec8jmuZ1zx9dPfpLB5MLMS06TMZJUIP3SxXOf+A5rkFtJ763kdyY1wfliG0AYB6DGP61v6V4QtvN37PMTBCCTJxkEg5HB/wD11K90Pi3M2TxhctdXNxDLNJuXaFP3E6ZA6/3evHU+tRJYXTwxiO0EcAYhDEvyjHH3uT6e30r0ay0eziiAl2qWQRsUY56dBn3rcsr+005gqx7VUZGRnn8aV2VGB5jYfCjX/EE7SSw/YoX4D3bYIx0O372Pwr0rwt8B9D0+RZtQvLm9lXAKQ4iG7nIznP54/Ctc+MVK7FOwE42k8f5zV3Tte811ijOMDPAyAAec+gAoujSx2Hh+w0rwralNH0qC1YcCdU3vnPTeefxwK6Gz8UXkjyqSYweUfqWHOQD/AJ+teZ3vjmwsUyZnu7jP3EICe7bhnI68jj+uNffES4vFdBObWEDaqW+VZh/tHqenQnHHTPXPnLSbPXtQ8X2GmPMk0jyS9ZY1G+UDHTGcLntuIrlJfGMsFrPFpVpDpFvNK08ggKmRmbGWJ+6pOADtBPHDHrXnseuxQWuFB+Zic7eB6/y6dqf/AG/FIm1XJB6rwOOaOdjUUdJDrqwzlljQu4xveQtI3OQGZiSe/c1N/bdxIGYArn0GfqOvTrXKRaxboBgkKOV4Pzfl/KpY/EUcaOqgMNvO719B/j70uZmljfj8QtNJi4dAmdyOQS2fU+vt1HOfQ1Dea8Y5WaJw2DtO7kr6nH+f0rAk1GGUEjjAxgn/AD/hz+b9Pvi7lYR5jg8vnOPU1Nwsat14ijtbYyPM+du7CgZIx+frVIarcanMv2gC2tFOFhkwHkP+2P12/nnpVK6nNzqHkt5giRRJI7jO5s/Kv04yR7Cqsl7JIrMu6O0IyzgZMi89D2GATnv29S7isZ/xi1NZvBWo2iHzGjaLzHUAKuJUwPrz07Z+lFZHjXcfhpfOyGObZBKwVQArtOhIH0zjj0PpyVtTd0YVFqeOWt5PalmgmkgLDBMblc/lTmv7pmObmY55OZDzRRWtjEaL+6bLG5myRyfMP+NILqc8maTJ5++aKKSGPW9uIiSlxKpPGQ5HFRedJ83zse/3jRRQhiedIACHbp608XUxP+tfnr8xooo6iHLe3AJ/fy8D++akGr3xUA3k+F6fvDx+tFFOw0C6pe/Ni8nGD2kNOi1zUYnEkd/cpIvIZZmBB+uaKKVguB1e/dyzX1wWOSWMrZP609Nc1Fk2/b7nZnO3zmx+WaKKLDGnV7/n/Tbj/v63+NN/tW9wV+2T4z/z1b/GiilZBcDq17/z+T8f9NW9frSrql6f+Xyf/v4f8aKKEguC6vfbSPtk4BPI81uf1pV1e+6fbJwB/wBNW/xoop2C4n9r3wX/AI/bjHp5rY/nQmr364AvbgfSVv8AGiinZBdjm1vUH3Mb65JPX963P6+5pp1i/IIN7cY9PNbHf3oopJIV2R3Gp3d4oWe6mnUHgSSFgPzNFFFPYTP/2Q==\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "colorize_and_display(clip_colors=True, min_clip_s=50, min_clip_v=30)" + ] + }, + { + "cell_type": "code", + "execution_count": 25, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "" + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/jpeg": "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\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "colorize_and_display(clip_colors=True, min_clip_s=20, min_clip_v=30)" + ] + }, + { + "cell_type": "code", + "execution_count": 26, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "" + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/jpeg": "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\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "colorize_and_display(clip_colors=True, min_clip_s=20, min_clip_v=30, coefficients=[1.0, 2.0, 0.6])" + ] + }, + { + "cell_type": "code", + "execution_count": 27, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "" + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/jpeg": "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\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "colorize_and_display(clip_colors=True, coefficients=[1.0, 2.0, 0.6], min_clip_s=20, min_clip_v=20)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "This looks like a winner to me. We'll use `create_swatches.py` to create swatches for all available images in batch." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3 User Default", + "language": "python", + "name": "python_3_user_default" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.6.5" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +} diff --git a/create_swatches.py b/create_swatches.py new file mode 100644 index 0000000..b20dfd5 --- /dev/null +++ b/create_swatches.py @@ -0,0 +1,166 @@ +# Create all swatches for public domain AKON + +import pandas as pd +import requests +import jsonpath_ng as jp + +from PIL import Image +from io import BytesIO +from colorsys import rgb_to_hsv, hsv_to_rgb +from scipy.cluster.vq import kmeans +from numpy import array + + +DEFAULT_NUM_COLORS = 6 +SCALE = 256.0 + +DEFAULT_MINV = 0 +DEFAULT_MAXV = 256 + + +def get_raw_data(): + df = pd.read_csv(filepath_or_buffer='https://labs.onb.ac.at/gitlab/labs-team/raw-metadata/raw/master/akon_postcards_public_domain.csv.bz2', compression='bz2') + out_df = df[['akon_id']] + return out_df + + +jp_image_link = jp.parse('sequences[*].canvases[*].images[*].resource.@id') + +def get_image_link_for_akon_id(akon_id): + r = requests.get(f'https://iiif.onb.ac.at/presentation/AKON/{akon_id}/manifest') + r.raise_for_status() + links = [m.value for m in jp_image_link.find(r.json())] + if len(links) > 1: + print(f'{len(links)} images found for id {akon_id}.', file=sys.stderr) + return links[0] + + +def get_clamped_image_link(original_iiif_image_link, max_width=200, max_height=200): + slices = original_iiif_image_link.split('/') + slices[-3] = f'!{max_width:d},{max_height:d}' + return '/'.join(slices) + + +def down_scale(x): + return x / SCALE + + +def up_scale(x): + return int(x * SCALE) + + +def clamp_hsv(color, min_v, max_v): + """ + Clamps a color such that the value (lightness) is between min_v and max_v. + """ + # use down_scale to convert color to value between 0-1 as expected by rgb_hsv + h, s, v = [down_scale(c) for c in color] + # also convert the min_v and max_v to values between 0-1 + min_v, max_v = map(down_scale, (min_v, max_v)) + # get the maximum of the min value and the color's value (therefore bumping it up if needed) + # then get the minimum of that number and the max_v (bumping the value down if needed) + v = min(max(min_v, v), max_v) + # apply upscale to get the h, s, v(which has been clamped) back to 0-255, return as tuple + return tuple(map(up_scale, (h, s, v))) + + +def clip_hsv(colors_hsv, min_v): + min_v = down_scale(min_v) + hsvs = [tuple(map(down_scale, color)) for color in colors_hsv] + hsvs = filter(lambda hsv: hsv[2] >= min_v, hsvs) + return [tuple(map(up_scale, hsv)) for hsv in hsvs] + + +def order_by_hue_hsv(colors): + """ + Orders colors by hue. + """ + hsvs = [list(map(down_scale, color)) for color in colors] + hsvs.sort(key=lambda t: t[0]) + return [tuple(map(up_scale, hsv_to_rgb(*hsv))) for hsv in hsvs] + + +def get_colors(img): + """ + Returns a list of all the image's colors. + """ + w, h = img.size + # convert('HSV') converts the image's pixels info to HSV + # getcolors() returns an unsorted list of (count, pixel) values + # w * h ensures that maxcolors parameter is set so that each pixel could be unique + # there are three values returned in a list + return [single_color for count, color in img.convert('HSV').getcolors(w * h) for single_color in [color] * count] + + +def hexify(rgb): + return "#{0:02x}{1:02x}{2:02x}".format(*rgb) + + +def colorz(image_url, n=DEFAULT_NUM_COLORS, min_v=DEFAULT_MINV, max_v=DEFAULT_MAXV, + order_colors=True, coefficients=[1.0, 1.0, 1.0], clip_colors=False, min_clip_s=20, min_clip_v=20): + """ + Get the n most dominant colors of an image. + + Total number of colors returned is n, optionally ordered by hue. + Returns as a list of RGB triples. + + """ + r = requests.get(image_url) + r.raise_for_status() + img = Image.open(BytesIO(r.content)) + + obs = get_colors(img) # gets a list of HSV colors (e.g. (213, 191, 152)) for each pixel + # adjust the value of each color, if you've chosen to change minimum and maximum values + clamped = [clamp_hsv(color, min_v, max_v) for color in obs] + clipped = clip_hsv(clamped, min_clip_v) if clip_colors else clamped + # turns the list of colors into a numpy array of floats, then applies scipy's k-means function + clusters, _ = kmeans(array(clipped).astype(float) * coefficients, n) + normalized_clusters = clusters / coefficients + colors = order_by_hue_hsv(normalized_clusters) if order_colors else normalized_clusters + + hex_colors = list(map(hexify, colors)) # turn RGB into hex colors for web + return hex_colors + + +def draw_row_with_links(link_and_colors): + html = "" + url = link_and_colors[0] + for count, color in enumerate(link_and_colors[1]): + square = ''.format(((count * 30)), 0, color) + html += square + full_html = '{1}'.format(url, html, len(link_and_colors) * 30) + return full_html + + +def get_link_and_colors(akon_id): + image_link = get_image_link_for_akon_id(akon_id) + thumb_link = get_clamped_image_link(image_link) + color_swatches = colorz(thumb_link, 6, True) + return image_link, color_swatches + + +def get_color_swatches(image_link): + print(image_link, end='') + thumb_link = get_clamped_image_link(image_link) + print('.', end='') + color_swatches = colorz(thumb_link, 6, order_colors=True, coefficients=[1.0, 2.0, 0.6], clip_colors=True, min_clip_s=20, min_clip_v=20) + print('.') + return color_swatches + + +if __name__ == '__main__': + FILE_NAME = 'historic_postcards_color_swatches.csv.bz2' + + df = get_raw_data() + print('Data loaded.') + # For testing, use only a tiny part of the available data + # df = df.sample(100).copy() + df['image_link'] = df['akon_id'].apply(get_image_link_for_akon_id) + print('Image links created.') + df['hex_colors'] = df['image_link'].apply(get_color_swatches) + print('Colors computed.') + df['html'] = df[['image_link', 'hex_colors']].apply(draw_row_with_links, axis='columns') + print('HTML created.') + df.to_csv(FILE_NAME, compression='bz2') + print(f'Output file {FILE_NAME} written.') + diff --git a/requirements.txt b/requirements.txt new file mode 100644 index 0000000..7b1f347 --- /dev/null +++ b/requirements.txt @@ -0,0 +1,5 @@ +pandas +jsonpath_ng +Pillow +requests +scipy -- GitLab