{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "# # Styling notebook\n",
    "# from IPython.core.display import HTML\n",
    "# def css_styling():\n",
    "#     styles = open(\"/Users/ashokkhosla/.jupyter/custom/custom.css\", \"r\").read()\n",
    "#     return HTML(styles)\n",
    "# css_styling();"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<a href=\"../index.html\"><img width=128 height=128 align=\"left\" src=\"https://www.khipufieldguide.com/notebook/images/khipu_field_guide_logo.jpg\"/></a>\n",
    "<br/><br/>"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Workbench"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "        <script type=\"text/javascript\">\n",
       "        window.PlotlyConfig = {MathJaxConfig: 'local'};\n",
       "        if (window.MathJax && window.MathJax.Hub && window.MathJax.Hub.Config) {window.MathJax.Hub.Config({SVG: {font: \"STIX-Web\"}});}\n",
       "        if (typeof require !== 'undefined') {\n",
       "        require.undef(\"plotly\");\n",
       "        requirejs.config({\n",
       "            paths: {\n",
       "                'plotly': ['https://cdn.plot.ly/plotly-2.24.1.min']\n",
       "            }\n",
       "        });\n",
       "        require(['plotly'], function(Plotly) {\n",
       "            window._Plotly = Plotly;\n",
       "        });\n",
       "        }\n",
       "        </script>\n",
       "        "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "<Figure size 6000x3000 with 0 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "from pandas import Series, DataFrame\n",
    "import time\n",
    "import itertools\n",
    "from collections import Counter\n",
    "import re\n",
    "import os\n",
    "import sys  \n",
    "\n",
    "# Import Khipu classes\n",
    "sys.path.insert(0, '/Users/ashokkhosla/Desktop/Khipu/fieldguide/code/classes') \n",
    "\n",
    "# Natural Language Processing Analysis\n",
    "import math\n",
    "import statistics\n",
    "from statistics import mean \n",
    "import random\n",
    "import nltk\n",
    "import scipy\n",
    "\n",
    "from sklearn import feature_extraction\n",
    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
    "from scipy.cluster.hierarchy import ward, dendrogram\n",
    "from sklearn.cluster import KMeans\n",
    "from sklearn.metrics.pairwise import cosine_similarity\n",
    "\n",
    "# Seaborn settings\n",
    "import matplotlib as mpl\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "sns.set(rc={'axes.facecolor':'#dfe7f4', 'figure.facecolor':'#dfe7f4'})\n",
    "\n",
    "# Plotly\n",
    "import plotly\n",
    "from plotly.offline import iplot, init_notebook_mode\n",
    "init_notebook_mode(connected = True)\n",
    "import plotly.graph_objs as go\n",
    "import plotly.express as px\n",
    "import plotly.figure_factory as ff\n",
    "\n",
    "#IPython/Jupyter settings\n",
    "from IPython import get_ipython\n",
    "from IPython.core.interactiveshell import InteractiveShell\n",
    "InteractiveShell.ast_node_interactivity = \"all\"\n",
    "np.set_printoptions(precision=4, suppress=True)\n",
    "fig=plt.figure(figsize=(20, 10), dpi= 300, facecolor='w', edgecolor='k')\n",
    "\n",
    "#import dtale as dtale\n",
    "def display_dataframe(adataframe):\n",
    "    return adataframe\n",
    "\n",
    "# Economist style...\n",
    "def set_economist_style():\n",
    "    params = {\"figure.facecolor\": \"#cad9e1\",\n",
    "              \"axes.facecolor\": \"#cad9e1\",\n",
    "              \"axes.grid\" : True,\n",
    "              \"axes.grid.axis\" : \"y\",\n",
    "              \"grid.color\"    : \"#ffffff\",\n",
    "              \"grid.linewidth\": .75,\n",
    "              \"grid.linestyle\": 'dotted',\n",
    "              \"axes.spines.left\" : False,\n",
    "              \"axes.spines.right\" : False,\n",
    "              \"axes.spines.top\" : False,\n",
    "              \"ytick.major.size\": 0,\n",
    "              \"ytick.minor.size\": 0,\n",
    "              \"xtick.direction\" : \"in\",\n",
    "              \"xtick.major.size\" : 7,\n",
    "              \"xtick.color\"      : \"#191919\",\n",
    "              \"axes.edgecolor\"    :\"#191919\",\n",
    "              \"axes.prop_cycle\" : plt.cycler('color',\n",
    "                          ['#006767', '#ff7f0e', '#2ca02c', '#d62728',\n",
    "                           '#9467bd', '#8c564b', '#e377c2', '#7f7f7f',\n",
    "                           '#bcbd22', '#17becf'])\n",
    "              }\n",
    "    plt.rcParams.update(params)\n",
    "    mpl.rcParams['font.family'] = 'sans-serif'\n",
    "    mpl.rcParams['font.sans-serif'] = ['Lucida Grande', 'Tahoma', 'Monaco']\n",
    "    mpl.rcParams['figure.dpi']= 120\n",
    "    mpl.rcParams['axes.axisbelow'] = True\n",
    "set_economist_style();\n",
    "\n",
    "def prep_plot(aPlotHeight = 5):\n",
    "    set_economist_style()\n",
    "    plt.figure(figsize=(12, aPlotHeight))\n",
    "    plt.grid(linestyle='dotted', linewidth=.75, axis='y')\n",
    "    \n",
    "import khipu_kamayuq as kamayuq  # A Khipu Maker is known (in Quechua) as a Khipu Kamayuq\n",
    "import khipu_qollqa as kq\n",
    "import khipu_utils as ku"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'/Users/ashokkhosla/.jupyter'"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import jupyter_core\n",
    "jupyter_core.paths.jupyter_config_dir()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0: 1000166\n",
      "25: 1000334\n"
     ]
    }
   ],
   "source": [
    "#=======================================================\n",
    "# INITIALIZE\n",
    "# Read in the Fieldmark and its associated dataframes\n",
    "#=======================================================\n",
    "# from fieldmark_ascher_pendant_pendant_sum import Fieldmark_Pendant_Pendant_Sum\n",
    "# aFieldmark = Fieldmark_Pendant_Pendant_Sum()\n",
    "# khipu_df = aFieldmark.dataframes[0].dataframe\n",
    "# sum_cord_df = aFieldmark.dataframes[1].dataframe\n",
    "from khipu import Khipu\n",
    "(khipu_dict, all_khipus) = kamayuq.fetch_khipus()\n",
    "# for index,aName in enumerate(khipu_dict.keys()):\n",
    "#     print(index,aName)\n",
    "#     khipu_dict[aName] = Khipu(aName)\n",
    "\n",
    "# Initialize plotly\n",
    "plotly.offline.init_notebook_mode(connected = False);\n",
    "len(khipu_dict.keys())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1200x1200 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import numpy as np\n",
    "import matplotlib.pyplot as plt \n",
    "# Import the MarkovChain class from markovchain.py\n",
    "from markovchain import MarkovChain\n",
    "\n",
    "P = np.array([\n",
    "    [0.8, 0.1, 0.1, 0.0],\n",
    "    [0.1, 0.7, 0.0, 0.2],\n",
    "    [0.1, 0.0, 0.7, 0.2],\n",
    "    [0.1, 0.0, 0.7, 0.2]\n",
    "])\n",
    "mc = MarkovChain(P, ['1', '2', '3', '4'])\n",
    "mc.draw(\"/Users/ashokkhosla/Desktop/markup.png\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "cluster_data = \"\"\"\n",
    "156.5cm group of 11 pendants (418-428) space of 1.5cm\n",
    "160.0cm group of 10 pendants (429-438) space of 1.5cm\n",
    "163.5cm group of 11 pendants (439-449) space of 1.5cm\n",
    "167.0cm group of 12 pendants (450-461) space of 2.0cm\n",
    "171.0cm group of 6 pendants (462-467) space of 1.5cm\n",
    "173.5cm group of 10 pendants (468-477) space of 1.5cm\n",
    "177.0cm group of 11 pendants (478-488) space of 1.0cm\n",
    "180.0cm group of 11 pendants (489-499) space of 1.5cm\n",
    "183.0cm group of 11 pendants (500-510) space of 1.0cm\n",
    "186.5cm group of 11 pendants (511-521) space of 1.5cm\n",
    "189.5cm group of 11 pendants (522-532) space of 1.0cm\n",
    "193.0cm group of 10 pendants (533-542) space of 1.5cm\n",
    "196.0cm group of 11 pendants (543-553) space of 3.5cm\n",
    "202.0cm group of 11 pendants (554-564) space of 1.5cm\n",
    "205.0cm group of 11 pendants (565-575) space of 1.5cm\n",
    "208.5cm group of 11 pendants (576-586) space of 1.0cm\n",
    "212.0cm group of 11 pendants (587-597) space of 1.5cm\n",
    "215.5cm group of 12 pendants (598-609) space of 1.5cm\n",
    "219.5cm group of 11 pendants (610-620) space of 1.5cm\n",
    "223.0cm group of 11 pendants (621-631) space of 1.5cm\n",
    "227.0cm group of 11 pendants (632-642) space of 1.5cm\n",
    "230.0cm group of 11 pendants (643-653) space of 1.5cm\n",
    "233.0cm group of 11 pendants (654-664) space of 1.5cm\n",
    "236.5cm group of 11 pendants (665-675) space of 1.5cm\n",
    "240.0cm group of 11 pendants (676-686) space of 1.5cm\n",
    "243.5cm group of 11 pendants (687-697) space of 2.0cm\n",
    "248.0cm group of 11 pendants (698-708) space of 2.5cm\n",
    "253.0cm group of 11 pendants (709-719) space of 1.5cm\n",
    "256.5cm group of 11 pendants (720-730) space of 1.5cm\n",
    "260.0cm group of 11 pendants (731-741) space of 1.5cm\n",
    "263.5cm group of 11 pendants (742-752) space of 1.5cm\n",
    "267.0cm group of 12 pendants (753-764) space of 1.5cm\n",
    "270.5cm group of 11 pendants (765-775) space of 1.5cm\n",
    "274.0cm group of 11 pendants (776-786) space of 1.5cm\n",
    "277.0cm group of 11 pendants (787-797) space of 1.0cm\n",
    "280.5cm group of 11 pendants (798-808) space of 1.5cm\n",
    "284.0cm group of 11 pendants (809-819) space of 1.5cm\n",
    "287.5cm group of 12 pendants (820-831) space of 1.5cm\n",
    "291.0cm group of 12 pendants (832-843) space of 1.0cm\n",
    "294.5cm group of 11 pendants (844-854) space of 0.5cm\n",
    "297.0cm group of 10 pendants (855-864) space of 4.0cm\n",
    "\"\"\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "cord_data = \"\"\"\n",
    "\"p418\",\n",
    "\"p419\",\n",
    "\"p420\",\n",
    "\"p421\",\n",
    "\"p422\",\n",
    "\"p423\",\n",
    "\"p424\",\n",
    "\"p425\",\n",
    "\"p426\",\n",
    "\"p427\",\n",
    "\"p428\",\n",
    "\"p429\",\n",
    "\"p430\",\n",
    "\"p431\",\n",
    "\"p432\",\n",
    "\"p433\",\n",
    "\"p434\",\n",
    "\"p435\",\n",
    "\"p436\",\n",
    "\"p437\",\n",
    "\"p438\",\n",
    "\"p439\",\n",
    "\"p440\",\n",
    "\"p441\",\n",
    "\"p442\",\n",
    "\"p443\",\n",
    "\"p444\",\n",
    "\"p445\",\n",
    "\"p446\",\n",
    "\"p447\",\n",
    "\"p448\",\n",
    "\"p449\",\n",
    "\"p450\",\n",
    "\"p451\",\n",
    "\"p452\",\n",
    "\"p453\",\n",
    "\"p454\",\n",
    "\"p455\",\n",
    "\"p456\",\n",
    "\"p457\",\n",
    "\"p458\",\n",
    "\"p459\",\n",
    "\"p460\",\n",
    "\"p461\",\n",
    "\"p462\",\n",
    "\"p463\",\n",
    "\"p464\",\n",
    "\"p465\",\n",
    "\"p466\",\n",
    "\"p467\",\n",
    "\"p468\",\n",
    "\"p469\",\n",
    "\"p470\",\n",
    "\"p471\",\n",
    "\"p472\",\n",
    "\"p473\",\n",
    "\"p474\",\n",
    "\"p475\",\n",
    "\"p476\",\n",
    "\"p477\",\n",
    "\"p478\",\n",
    "\"p479\",\n",
    "\"p480\",\n",
    "\"p481\",\n",
    "\"p482\",\n",
    "\"p483\",\n",
    "\"p484\",\n",
    "\"p485\",\n",
    "\"p486\",\n",
    "\"p487\",\n",
    "\"p488\",\n",
    "\"p489\",\n",
    "\"p490\",\n",
    "\"p491\",\n",
    "\"p492\",\n",
    "\"p493\",\n",
    "\"p494\",\n",
    "\"p495\",\n",
    "\"p496\",\n",
    "\"p497\",\n",
    "\"p498\",\n",
    "\"p499\",\n",
    "\"p500\",\n",
    "\"p501\",\n",
    "\"p502\",\n",
    "\"p503\",\n",
    "\"p504\",\n",
    "\"p505\",\n",
    "\"p506\",\n",
    "\"p507\",\n",
    "\"p508\",\n",
    "\"p509\",\n",
    "\"p510\",\n",
    "\"p511\",\n",
    "\"p511s1\",\n",
    "\"p512\",\n",
    "\"p512s1\",\n",
    "\"p513\",\n",
    "\"p513s1\",\n",
    "\"p514\",\n",
    "\"p514s1\",\n",
    "\"p515\",\n",
    "\"p515s1\",\n",
    "\"p516\",\n",
    "\"p516s1\",\n",
    "\"p517\",\n",
    "\"p517s1\",\n",
    "\"p518\",\n",
    "\"p518s1\",\n",
    "\"p519\",\n",
    "\"p519s1\",\n",
    "\"p520\",\n",
    "\"p520s1\",\n",
    "\"p521\",\n",
    "\"p521s1\",\n",
    "\"p522\",\n",
    "\"p523\",\n",
    "\"p524\",\n",
    "\"p525\",\n",
    "\"p526\",\n",
    "\"p527\",\n",
    "\"p528\",\n",
    "\"p529\",\n",
    "\"p530\",\n",
    "\"p531\",\n",
    "\"p532\",\n",
    "\"p533\",\n",
    "\"p534\",\n",
    "\"p535\",\n",
    "\"p536\",\n",
    "\"p537\",\n",
    "\"p538\",\n",
    "\"p539\",\n",
    "\"p540\",\n",
    "\"p541\",\n",
    "\"p542\",\n",
    "\"p543\",\n",
    "\"p544\",\n",
    "\"p545\",\n",
    "\"p546\",\n",
    "\"p547\",\n",
    "\"p548\",\n",
    "\"p549\",\n",
    "\"p550\",\n",
    "\"p551\",\n",
    "\"p552\",\n",
    "\"p553\",\n",
    "\"p554\",\n",
    "\"p555\",\n",
    "\"p556\",\n",
    "\"p557\",\n",
    "\"p558\",\n",
    "\"p559\",\n",
    "\"p560\",\n",
    "\"p561\",\n",
    "\"p562\",\n",
    "\"p563\",\n",
    "\"p564\",\n",
    "\"p565\",\n",
    "\"p566\",\n",
    "\"p567\",\n",
    "\"p568\",\n",
    "\"p569\",\n",
    "\"p570\",\n",
    "\"p571\",\n",
    "\"p572\",\n",
    "\"p573\",\n",
    "\"p574\",\n",
    "\"p575\",\n",
    "\"p576\",\n",
    "\"p577\",\n",
    "\"p578\",\n",
    "\"p579\",\n",
    "\"p580\",\n",
    "\"p581\",\n",
    "\"p582\",\n",
    "\"p583\",\n",
    "\"p584\",\n",
    "\"p585\",\n",
    "\"p586\",\n",
    "\"p587\",\n",
    "\"p588\",\n",
    "\"p589\",\n",
    "\"p590\",\n",
    "\"p591\",\n",
    "\"p592\",\n",
    "\"p593\",\n",
    "\"p594\",\n",
    "\"p595\",\n",
    "\"p596\",\n",
    "\"p597\",\n",
    "\"p598\",\n",
    "\"p599\",\n",
    "\"p600\",\n",
    "\"p601\",\n",
    "\"p602\",\n",
    "\"p603\",\n",
    "\"p604\",\n",
    "\"p605\",\n",
    "\"p606\",\n",
    "\"p607\",\n",
    "\"p608\",\n",
    "\"p609\",\n",
    "\"p610\",\n",
    "\"p610s1\",\n",
    "\"p611\",\n",
    "\"p611s1\",\n",
    "\"p612\",\n",
    "\"p612s1\",\n",
    "\"p613\",\n",
    "\"p613s1\",\n",
    "\"p614\",\n",
    "\"p614s1\",\n",
    "\"p615\",\n",
    "\"p615s1\",\n",
    "\"p616\",\n",
    "\"p616s1\",\n",
    "\"p617\",\n",
    "\"p617s1\",\n",
    "\"p618\",\n",
    "\"p618s1\",\n",
    "\"p619\",\n",
    "\"p619s1\",\n",
    "\"p620\",\n",
    "\"p620s1\",\n",
    "\"p621\",\n",
    "\"p622\",\n",
    "\"p623\",\n",
    "\"p624\",\n",
    "\"p625\",\n",
    "\"p626\",\n",
    "\"p627\",\n",
    "\"p628\",\n",
    "\"p629\",\n",
    "\"p630\",\n",
    "\"p631\",\n",
    "\"p632\",\n",
    "\"p633\",\n",
    "\"p634\",\n",
    "\"p635\",\n",
    "\"p636\",\n",
    "\"p637\",\n",
    "\"p638\",\n",
    "\"p639\",\n",
    "\"p640\",\n",
    "\"p641\",\n",
    "\"p642\",\n",
    "\"p643\",\n",
    "\"p644\",\n",
    "\"p645\",\n",
    "\"p646\",\n",
    "\"p647\",\n",
    "\"p648\",\n",
    "\"p649\",\n",
    "\"p650\",\n",
    "\"p651\",\n",
    "\"p652\",\n",
    "\"p653\",\n",
    "\"p654\",\n",
    "\"p655\",\n",
    "\"p656\",\n",
    "\"p657\",\n",
    "\"p658\",\n",
    "\"p659\",\n",
    "\"p660\",\n",
    "\"p661\",\n",
    "\"p662\",\n",
    "\"p663\",\n",
    "\"p664\",\n",
    "\"p665\",\n",
    "\"p665s1\",\n",
    "\"p666\",\n",
    "\"p666s1\",\n",
    "\"p667\",\n",
    "\"p667s1\",\n",
    "\"p668\",\n",
    "\"p668s1\",\n",
    "\"p669\",\n",
    "\"p669s1\",\n",
    "\"p670\",\n",
    "\"p670s1\",\n",
    "\"p671\",\n",
    "\"p671s1\",\n",
    "\"p672\",\n",
    "\"p672s1\",\n",
    "\"p673\",\n",
    "\"p673s1\",\n",
    "\"p674\",\n",
    "\"p674s1\",\n",
    "\"p675\",\n",
    "\"p675s1\",\n",
    "\"p676\",\n",
    "\"p677\",\n",
    "\"p678\",\n",
    "\"p679\",\n",
    "\"p680\",\n",
    "\"p681\",\n",
    "\"p682\",\n",
    "\"p683\",\n",
    "\"p684\",\n",
    "\"p685\",\n",
    "\"p686\",\n",
    "\"p687\",\n",
    "\"p688\",\n",
    "\"p689\",\n",
    "\"p690\",\n",
    "\"p691\",\n",
    "\"p692\",\n",
    "\"p693\",\n",
    "\"p694\",\n",
    "\"p695\",\n",
    "\"p696\",\n",
    "\"p697\",\n",
    "\"p698\",\n",
    "\"p699\",\n",
    "\"p700\",\n",
    "\"p701\",\n",
    "\"p702\",\n",
    "\"p703\",\n",
    "\"p704\",\n",
    "\"p705\",\n",
    "\"p706\",\n",
    "\"p707\",\n",
    "\"p708\",\n",
    "\"p709\",\n",
    "\"p710\",\n",
    "\"p711\",\n",
    "\"p712\",\n",
    "\"p713\",\n",
    "\"p714\",\n",
    "\"p715\",\n",
    "\"p716\",\n",
    "\"p717\",\n",
    "\"p718\",\n",
    "\"p719\",\n",
    "\"p720\",\n",
    "\"p721\",\n",
    "\"p722\",\n",
    "\"p723\",\n",
    "\"p724\",\n",
    "\"p725\",\n",
    "\"p726\",\n",
    "\"p727\",\n",
    "\"p728\",\n",
    "\"p729\",\n",
    "\"p730\",\n",
    "\"p731\",\n",
    "\"p732\",\n",
    "\"p733\",\n",
    "\"p734\",\n",
    "\"p735\",\n",
    "\"p736\",\n",
    "\"p737\",\n",
    "\"p738\",\n",
    "\"p739\",\n",
    "\"p740\",\n",
    "\"p741\",\n",
    "\"p742\",\n",
    "\"p743\",\n",
    "\"p744\",\n",
    "\"p745\",\n",
    "\"p746\",\n",
    "\"p747\",\n",
    "\"p748\",\n",
    "\"p749\",\n",
    "\"p750\",\n",
    "\"p751\",\n",
    "\"p752\",\n",
    "\"p753\",\n",
    "\"p754\",\n",
    "\"p755\",\n",
    "\"p756\",\n",
    "\"p757\",\n",
    "\"p758\",\n",
    "\"p759\",\n",
    "\"p760\",\n",
    "\"p761\",\n",
    "\"p762\",\n",
    "\"p763\",\n",
    "\"p764\",\n",
    "\"p764s1\",\n",
    "\"p765\",\n",
    "\"p765s1\",\n",
    "\"p766\",\n",
    "\"p766s1\",\n",
    "\"p767\",\n",
    "\"p767s1\",\n",
    "\"p768\",\n",
    "\"p768s1\",\n",
    "\"p769\",\n",
    "\"p770\",\n",
    "\"p770s1\",\n",
    "\"p771\",\n",
    "\"p771s1\",\n",
    "\"p772\",\n",
    "\"p772s1\",\n",
    "\"p773\",\n",
    "\"p773s1\",\n",
    "\"p774\",\n",
    "\"p774s1\",\n",
    "\"p775\",\n",
    "\"p775s1\",\n",
    "\"p776\",\n",
    "\"p777\",\n",
    "\"p778\",\n",
    "\"p779\",\n",
    "\"p780\",\n",
    "\"p781\",\n",
    "\"p782\",\n",
    "\"p783\",\n",
    "\"p784\",\n",
    "\"p785\",\n",
    "\"p786\",\n",
    "\"p787\",\n",
    "\"p788\",\n",
    "\"p789\",\n",
    "\"p790\",\n",
    "\"p791\",\n",
    "\"p792\",\n",
    "\"p793\",\n",
    "\"p794\",\n",
    "\"p795\",\n",
    "\"p796\",\n",
    "\"p797\",\n",
    "\"p798\",\n",
    "\"p799\",\n",
    "\"p800\",\n",
    "\"p801\",\n",
    "\"p802\",\n",
    "\"p803\",\n",
    "\"p804\",\n",
    "\"p805\",\n",
    "\"p806\",\n",
    "\"p807\",\n",
    "\"p808\",\n",
    "\"p809\",\n",
    "\"p810\",\n",
    "\"p811\",\n",
    "\"p812\",\n",
    "\"p813\",\n",
    "\"p814\",\n",
    "\"p815\",\n",
    "\"p816\",\n",
    "\"p817\",\n",
    "\"p818\",\n",
    "\"p819\",\n",
    "\"p820\",\n",
    "\"p821\",\n",
    "\"p822\",\n",
    "\"p823\",\n",
    "\"p824\",\n",
    "\"p825\",\n",
    "\"p826\",\n",
    "\"p827\",\n",
    "\"p828\",\n",
    "\"p829\",\n",
    "\"p830\",\n",
    "\"p831\",\n",
    "\"p832\",\n",
    "\"p833\",\n",
    "\"p834\",\n",
    "\"p835\",\n",
    "\"p836\",\n",
    "\"p837\",\n",
    "\"p838\",\n",
    "\"p839\",\n",
    "\"p840\",\n",
    "\"p841\",\n",
    "\"p842\",\n",
    "\"p843\",\n",
    "\"p844\",\n",
    "\"p845\",\n",
    "\"p846\",\n",
    "\"p847\",\n",
    "\"p848\",\n",
    "\"p849\",\n",
    "\"p850\",\n",
    "\"p851\",\n",
    "\"p852\",\n",
    "\"p853\",\n",
    "\"p854\",\n",
    "\"p855\",\n",
    "\"p856\",\n",
    "\"p857\",\n",
    "\"p858\",\n",
    "\"p859\",\n",
    "\"p860\",\n",
    "\"p861\",\n",
    "\"p862\",\n",
    "\"p863\",\n",
    "\"p864\"\n",
    "\"\"\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "p1\n",
      "p2\n",
      "p3\n",
      "p4\n",
      "p5\n",
      "p6\n",
      "p7\n",
      "p8\n",
      "p9\n",
      "p10\n",
      "p11\n",
      "p12\n",
      "p13\n",
      "p14\n",
      "p15\n",
      "p16\n",
      "p17\n",
      "p18\n",
      "p19\n",
      "p20\n",
      "p21\n",
      "p22\n",
      "p23\n",
      "p24\n",
      "p25\n",
      "p26\n",
      "p27\n",
      "p28\n",
      "p29\n",
      "p30\n",
      "p31\n",
      "p32\n",
      "p33\n",
      "p34\n",
      "p35\n",
      "p36\n",
      "p37\n",
      "p38\n",
      "p39\n",
      "p40\n",
      "p41\n",
      "p42\n",
      "p43\n",
      "p44\n",
      "p45\n",
      "p46\n",
      "p47\n",
      "p48\n",
      "p49\n",
      "p50\n",
      "p51\n",
      "p52\n",
      "p53\n",
      "p54\n",
      "p55\n",
      "p56\n",
      "p57\n",
      "p58\n",
      "p59\n",
      "p60\n",
      "p61\n",
      "p62\n",
      "p63\n",
      "p64\n",
      "p65\n",
      "p66\n",
      "p67\n",
      "p68\n",
      "p69\n",
      "p70\n",
      "p71\n",
      "p72\n",
      "p73\n",
      "p74\n",
      "p75\n",
      "p76\n",
      "p77\n",
      "p78\n",
      "p79\n",
      "p80\n",
      "p81\n",
      "p82\n",
      "p83\n",
      "p84\n",
      "p85\n",
      "p86\n",
      "p87\n",
      "p88\n",
      "p89\n",
      "p90\n",
      "p91\n",
      "p92\n",
      "p93\n",
      "p94\n",
      "p94s1\n",
      "p95\n",
      "p95s1\n",
      "p96\n",
      "p96s1\n",
      "p97\n",
      "p97s1\n",
      "p98\n",
      "p98s1\n",
      "p99\n",
      "p99s1\n",
      "p100\n",
      "p100s1\n",
      "p101\n",
      "p101s1\n",
      "p102\n",
      "p102s1\n",
      "p103\n",
      "p103s1\n",
      "p104\n",
      "p104s1\n",
      "p105\n",
      "p106\n",
      "p107\n",
      "p108\n",
      "p109\n",
      "p110\n",
      "p111\n",
      "p112\n",
      "p113\n",
      "p114\n",
      "p115\n",
      "p116\n",
      "p117\n",
      "p118\n",
      "p119\n",
      "p120\n",
      "p121\n",
      "p122\n",
      "p123\n",
      "p124\n",
      "p125\n",
      "p126\n",
      "p127\n",
      "p128\n",
      "p129\n",
      "p130\n",
      "p131\n",
      "p132\n",
      "p133\n",
      "p134\n",
      "p135\n",
      "p136\n",
      "p137\n",
      "p138\n",
      "p139\n",
      "p140\n",
      "p141\n",
      "p142\n",
      "p143\n",
      "p144\n",
      "p145\n",
      "p146\n",
      "p147\n",
      "p148\n",
      "p149\n",
      "p150\n",
      "p151\n",
      "p152\n",
      "p153\n",
      "p154\n",
      "p155\n",
      "p156\n",
      "p157\n",
      "p158\n",
      "p159\n",
      "p160\n",
      "p161\n",
      "p162\n",
      "p163\n",
      "p164\n",
      "p165\n",
      "p166\n",
      "p167\n",
      "p168\n",
      "p169\n",
      "p170\n",
      "p171\n",
      "p172\n",
      "p173\n",
      "p174\n",
      "p175\n",
      "p176\n",
      "p177\n",
      "p178\n",
      "p179\n",
      "p180\n",
      "p181\n",
      "p182\n",
      "p183\n",
      "p184\n",
      "p185\n",
      "p186\n",
      "p187\n",
      "p188\n",
      "p189\n",
      "p190\n",
      "p191\n",
      "p192\n",
      "p193\n",
      "p193s1\n",
      "p194\n",
      "p194s1\n",
      "p195\n",
      "p195s1\n",
      "p196\n",
      "p196s1\n",
      "p197\n",
      "p197s1\n",
      "p198\n",
      "p198s1\n",
      "p199\n",
      "p199s1\n",
      "p200\n",
      "p200s1\n",
      "p201\n",
      "p201s1\n",
      "p202\n",
      "p202s1\n",
      "p203\n",
      "p203s1\n",
      "p204\n",
      "p205\n",
      "p206\n",
      "p207\n",
      "p208\n",
      "p209\n",
      "p210\n",
      "p211\n",
      "p212\n",
      "p213\n",
      "p214\n",
      "p215\n",
      "p216\n",
      "p217\n",
      "p218\n",
      "p219\n",
      "p220\n",
      "p221\n",
      "p222\n",
      "p223\n",
      "p224\n",
      "p225\n",
      "p226\n",
      "p227\n",
      "p228\n",
      "p229\n",
      "p230\n",
      "p231\n",
      "p232\n",
      "p233\n",
      "p234\n",
      "p235\n",
      "p236\n",
      "p237\n",
      "p238\n",
      "p239\n",
      "p240\n",
      "p241\n",
      "p242\n",
      "p243\n",
      "p244\n",
      "p245\n",
      "p246\n",
      "p247\n",
      "p248\n",
      "p248s1\n",
      "p249\n",
      "p249s1\n",
      "p250\n",
      "p250s1\n",
      "p251\n",
      "p251s1\n",
      "p252\n",
      "p252s1\n",
      "p253\n",
      "p253s1\n",
      "p254\n",
      "p254s1\n",
      "p255\n",
      "p255s1\n",
      "p256\n",
      "p256s1\n",
      "p257\n",
      "p257s1\n",
      "p258\n",
      "p258s1\n",
      "p259\n",
      "p260\n",
      "p261\n",
      "p262\n",
      "p263\n",
      "p264\n",
      "p265\n",
      "p266\n",
      "p267\n",
      "p268\n",
      "p269\n",
      "p270\n",
      "p271\n",
      "p272\n",
      "p273\n",
      "p274\n",
      "p275\n",
      "p276\n",
      "p277\n",
      "p278\n",
      "p279\n",
      "p280\n",
      "p281\n",
      "p282\n",
      "p283\n",
      "p284\n",
      "p285\n",
      "p286\n",
      "p287\n",
      "p288\n",
      "p289\n",
      "p290\n",
      "p291\n",
      "p292\n",
      "p293\n",
      "p294\n",
      "p295\n",
      "p296\n",
      "p297\n",
      "p298\n",
      "p299\n",
      "p300\n",
      "p301\n",
      "p302\n",
      "p303\n",
      "p304\n",
      "p305\n",
      "p306\n",
      "p307\n",
      "p308\n",
      "p309\n",
      "p310\n",
      "p311\n",
      "p312\n",
      "p313\n",
      "p314\n",
      "p315\n",
      "p316\n",
      "p317\n",
      "p318\n",
      "p319\n",
      "p320\n",
      "p321\n",
      "p322\n",
      "p323\n",
      "p324\n",
      "p325\n",
      "p326\n",
      "p327\n",
      "p328\n",
      "p329\n",
      "p330\n",
      "p331\n",
      "p332\n",
      "p333\n",
      "p334\n",
      "p335\n",
      "p336\n",
      "p337\n",
      "p338\n",
      "p339\n",
      "p340\n",
      "p341\n",
      "p342\n",
      "p343\n",
      "p344\n",
      "p345\n",
      "p346\n",
      "p347\n",
      "p347s1\n",
      "p348\n",
      "p348s1\n",
      "p349\n",
      "p349s1\n",
      "p350\n",
      "p350s1\n",
      "p351\n",
      "p351s1\n",
      "p352\n",
      "p353\n",
      "p353s1\n",
      "p354\n",
      "p354s1\n",
      "p355\n",
      "p355s1\n",
      "p356\n",
      "p356s1\n",
      "p357\n",
      "p357s1\n",
      "p358\n",
      "p358s1\n",
      "p359\n",
      "p360\n",
      "p361\n",
      "p362\n",
      "p363\n",
      "p364\n",
      "p365\n",
      "p366\n",
      "p367\n",
      "p368\n",
      "p369\n",
      "p370\n",
      "p371\n",
      "p372\n",
      "p373\n",
      "p374\n",
      "p375\n",
      "p376\n",
      "p377\n",
      "p378\n",
      "p379\n",
      "p380\n",
      "p381\n",
      "p382\n",
      "p383\n",
      "p384\n",
      "p385\n",
      "p386\n",
      "p387\n",
      "p388\n",
      "p389\n",
      "p390\n",
      "p391\n",
      "p392\n",
      "p393\n",
      "p394\n",
      "p395\n",
      "p396\n",
      "p397\n",
      "p398\n",
      "p399\n",
      "p400\n",
      "p401\n",
      "p402\n",
      "p403\n",
      "p404\n",
      "p405\n",
      "p406\n",
      "p407\n",
      "p408\n",
      "p409\n",
      "p410\n",
      "p411\n",
      "p412\n",
      "p413\n",
      "p414\n",
      "p415\n",
      "p416\n",
      "p417\n",
      "p418\n",
      "p419\n",
      "p420\n",
      "p421\n",
      "p422\n",
      "p423\n",
      "p424\n",
      "p425\n",
      "p426\n",
      "p427\n",
      "p428\n",
      "p429\n",
      "p430\n",
      "p431\n",
      "p432\n",
      "p433\n",
      "p434\n",
      "p435\n",
      "p436\n",
      "p437\n",
      "p438\n",
      "p439\n",
      "p440\n",
      "p441\n",
      "p442\n",
      "p443\n",
      "p444\n",
      "p445\n",
      "p446\n",
      "p447\n"
     ]
    }
   ],
   "source": [
    "cord_lines = [aLine for aLine in cord_data.split('\\n') if len(aLine.strip()) > 0]\n",
    "\n",
    "def shift_pendant_name(aName, delta_pendants):\n",
    "    numbers = re.findall(r'[\\d\\.]+', aName)  \n",
    "    if len(numbers) > 0:\n",
    "        numbers[0] = str(int(numbers[0]) + delta_pendants)\n",
    "        return \"p\" + \"s\".join(numbers)\n",
    "    else:\n",
    "        print(\"!!!! Couldn't process {aName}\")\n",
    "\n",
    "for line in cord_lines:\n",
    "    delta_pendants = -417\n",
    "    print(shift_pendant_name(line, delta_pendants))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['',\n",
       " '22.0cm group of 6 pendants (40-45) space of 1.5cm',\n",
       " '26.5cm group of 11 pendants (46-56) space of 1.5cm',\n",
       " '30.0cm group of 10 pendants (57-66) space of 1.5cm',\n",
       " '34.0cm group of 11 pendants (67-77) space of 1.5cm',\n",
       " '37.5cm group of 11 pendants (78-88) space of 1.5cm',\n",
       " '41.5cm group of 10 pendants (89-98) space of 1.5cm',\n",
       " '45.5cm group of 11 pendants (99-109) space of 1.5cm',\n",
       " '49.0cm group of 11 pendants (110-120) space of 4.0cm',\n",
       " '55.0cm group of 11 pendants (121-131) space of 3.0cm',\n",
       " '61.0cm group of 11 pendants (132-142) space of 1.0cm',\n",
       " '64.5cm group of 11 pendants (143-153) space of 1.5cm',\n",
       " '68.0cm group of 11 pendants (154-164) space of 1.0cm',\n",
       " '71.0cm group of 11 pendants (165-175) space of 1.0cm',\n",
       " '74.0cm group of 12 pendants (176-187) space of 1.0cm',\n",
       " '77.5cm group of 11 pendants (188-198) space of 1.0cm',\n",
       " '80.5cm group of 11 pendants (199-209) space of 4.5cm',\n",
       " '87.0cm group of 10 pendants (210-219) space of 1.0cm',\n",
       " '90.0cm group of 11 pendants (220-230) space of 1.5cm',\n",
       " '93.5cm group of 11 pendants (231-241) space of 1.0cm',\n",
       " '96.5cm group of 11 pendants (242-252) space of 3.5cm',\n",
       " '102.0cm group of 11 pendants (253-263) space of 3.5cm',\n",
       " '108.5cm group of 11 pendants (264-274) space of 1.0cm',\n",
       " '111.0cm group of 11 pendants (275-285) space of 1.0cm',\n",
       " '114.0cm group of 11 pendants (286-296) space of 1.0cm',\n",
       " '117.5cm group of 11 pendants (297-307) space of 1.0cm',\n",
       " '120.5cm group of 12 pendants (308-319) space of 1.0cm',\n",
       " '124.0cm group of 11 pendants (320-330) space of 1.0cm',\n",
       " '127.5cm group of 10 pendants (331-340) space of 1.5cm',\n",
       " '130.5cm group of 11 pendants (341-351) space of 1.0cm',\n",
       " '133.5cm group of 11 pendants (352-362) space of 1.0cm',\n",
       " '137.0cm group of 8 pendants (363-370) space of 1.0cm',\n",
       " '140.0cm group of 7 pendants (371-377) space of 1.5cm',\n",
       " '143.5cm group of 11 pendants (378-388) space of 0.5cm',\n",
       " '146.0cm group of 11 pendants (389-399) space of 0.5cm',\n",
       " '148.5cm group of 10 pendants (400-409) space of 3.0cm',\n",
       " '154.0cm group of 8 pendants (410-417) space of 0.5cm',\n",
       " '156.5cm group of 11 pendants (418-428) space of 1.5cm',\n",
       " '160.0cm group of 10 pendants (429-438) space of 1.5cm',\n",
       " '163.5cm group of 11 pendants (439-449) space of 1.5cm',\n",
       " '167.0cm group of 12 pendants (450-461) space of 2.0cm',\n",
       " '171.0cm group of 6 pendants (462-467) space of 1.5cm',\n",
       " '173.5cm group of 10 pendants (468-477) space of 1.5cm',\n",
       " '177.0cm group of 11 pendants (478-488) space of 1.0cm',\n",
       " '180.0cm group of 11 pendants (489-499) space of 1.5cm',\n",
       " '183.0cm group of 11 pendants (500-510) space of 1.0cm',\n",
       " '186.5cm group of 11 pendants (511-521) space of 1.5cm',\n",
       " '189.5cm group of 11 pendants (522-532) space of 1.0cm',\n",
       " '193.0cm group of 10 pendants (533-542) space of 1.5cm',\n",
       " '196.0cm group of 11 pendants (543-553) space of 3.5cm',\n",
       " '202.0cm group of 11 pendants (554-564) space of 1.5cm',\n",
       " '205.0cm group of 11 pendants (565-575) space of 1.5cm',\n",
       " '208.5cm group of 11 pendants (576-586) space of 1.0cm',\n",
       " '212.0cm group of 11 pendants (587-597) space of 1.5cm',\n",
       " '215.5cm group of 12 pendants (598-609) space of 1.5cm',\n",
       " '219.5cm group of 11 pendants (610-620) space of 1.5cm',\n",
       " '223.0cm group of 11 pendants (621-631) space of 1.5cm',\n",
       " '227.0cm group of 11 pendants (632-642) space of 1.5cm',\n",
       " '230.0cm group of 11 pendants (643-653) space of 1.5cm',\n",
       " '233.0cm group of 11 pendants (654-664) space of 1.5cm',\n",
       " '236.5cm group of 11 pendants (665-675) space of 1.5cm',\n",
       " '240.0cm group of 11 pendants (676-686) space of 1.5cm',\n",
       " '243.5cm group of 11 pendants (687-697) space of 2.0cm',\n",
       " '248.0cm group of 11 pendants (698-708) space of 2.5cm',\n",
       " '253.0cm group of 11 pendants (709-719) space of 1.5cm',\n",
       " '256.5cm group of 11 pendants (720-730) space of 1.5cm',\n",
       " '260.0cm group of 11 pendants (731-741) space of 1.5cm',\n",
       " '263.5cm group of 11 pendants (742-752) space of 1.5cm',\n",
       " '267.0cm group of 12 pendants (753-764) space of 1.5cm',\n",
       " '270.5cm group of 11 pendants (765-775) space of 1.5cm',\n",
       " '274.0cm group of 11 pendants (776-786) space of 1.5cm',\n",
       " '277.0cm group of 11 pendants (787-797) space of 1.0cm',\n",
       " '280.5cm group of 11 pendants (798-808) space of 1.5cm',\n",
       " '284.0cm group of 11 pendants (809-819) space of 1.5cm',\n",
       " '287.5cm group of 12 pendants (820-831) space of 1.5cm',\n",
       " '291.0cm group of 12 pendants (832-843) space of 1.0cm',\n",
       " '294.5cm group of 11 pendants (844-854) space of 0.5cm',\n",
       " '297.0cm group of 10 pendants (855-864) space of 4.0cm',\n",
       " '']"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cluster_lines"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "dks = [\"AS072\",\n",
    "\"AS130 B\",\n",
    "\"AS190\",\n",
    "\"HP009\",\n",
    "\"HP033\",\n",
    "\"HP034\",\n",
    "\"HP036\",\n",
    "\"HP037\",\n",
    "\"HP038\",\n",
    "\"HP039\",\n",
    "\"HP040\",\n",
    "\"HP041\",\n",
    "\"HP042\",\n",
    "\"HP043\",\n",
    "\"HP044\",\n",
    "\"HP045\",\n",
    "\"HP046 A\",\n",
    "\"HP046 B\",\n",
    "\"HP047\",\n",
    "\"HP048\",\n",
    "\"HP051 A\",\n",
    "\"HP053\",\n",
    "\"HP054\",\n",
    "\"HP055\",\n",
    "\"HP057\",\n",
    "\"JC001\",\n",
    "\"JC002\",\n",
    "\"JC003\",\n",
    "\"JC004\",\n",
    "\"JC005\",\n",
    "\"JC006\",\n",
    "\"JC007\",\n",
    "\"JC008\",\n",
    "\"JC009\",\n",
    "\"JC010\",\n",
    "\"JC011\",\n",
    "\"JC012\",\n",
    "\"JC013\",\n",
    "\"JC014\",\n",
    "\"JC015\",\n",
    "\"JC016\",\n",
    "\"JC017\",\n",
    "\"JC018\",\n",
    "\"JC019\",\n",
    "\"JC020\",\n",
    "\"JC021\",\n",
    "\"JC022\",\n",
    "\"JC023\",\n",
    "\"QU01\",\n",
    "\"QU02\",\n",
    "\"QU03\",\n",
    "\"QU04\",\n",
    "\"QU05\",\n",
    "\"QU06\",\n",
    "\"QU07\",\n",
    "\"QU08\",\n",
    "\"QU09\",\n",
    "\"QU10\",\n",
    "\"QU11\",\n",
    "\"QU13\",\n",
    "\"QU16\",\n",
    "\"UR001\",\n",
    "\"UR004\",\n",
    "\"UR017\",\n",
    "\"UR039\",\n",
    "\"UR044\",\n",
    "\"UR050\",\n",
    "\"UR052\",\n",
    "\"UR054\",\n",
    "\"UR055\",\n",
    "\"UR110\",\n",
    "\"UR112\",\n",
    "\"UR144\",\n",
    "\"UR155\",\n",
    "\"UR165\",\n",
    "\"UR167\",\n",
    "\"UR190\",\n",
    "\"UR193\",\n",
    "\"UR196\",\n",
    "\"UR206\",\n",
    "\"UR209\",\n",
    "\"UR221\",\n",
    "\"UR251\",\n",
    "\"UR252\",\n",
    "\"UR253\",\n",
    "\"UR254\",\n",
    "\"UR255\",\n",
    "\"UR257\",\n",
    "\"UR258\",\n",
    "\"UR259\",\n",
    "\"UR260\",\n",
    "\"UR261\",\n",
    "\"UR262\",\n",
    "\"UR263\",\n",
    "\"UR266\",\n",
    "\"UR267A\",\n",
    "\"UR267B\",\n",
    "\"UR268\",\n",
    "\"UR269\",\n",
    "\"UR270\",\n",
    "\"UR271\",\n",
    "\"UR272\",\n",
    "\"UR273A\",\n",
    "\"UR273B\",\n",
    "\"UR274A\",\n",
    "\"UR275\",\n",
    "\"UR276\",\n",
    "\"UR277\",\n",
    "\"UR278\",\n",
    "\"UR279\",\n",
    "\"UR280\",\n",
    "\"UR281\",\n",
    "\"UR284\",\n",
    "\"UR288\",\n",
    "\"UR292A\",\n",
    "\"UR293\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "AS072ERROR\n",
      "AS130 BERROR\n",
      "AS190ERROR\n",
      "1000428\n",
      "1000562\n",
      "1000563\n",
      "HP036ERROR\n",
      "1000566\n",
      "1000567\n",
      "1000593\n",
      "1000569\n",
      "HP041ERROR\n",
      "1000571\n",
      "1000572\n",
      "1000573\n",
      "HP045ERROR\n",
      "1000575\n",
      "1000576\n",
      "HP047ERROR\n",
      "HP048ERROR\n",
      "1000581\n",
      "1000584\n",
      "1000585\n",
      "HP055ERROR\n",
      "1000587\n",
      "1000625\n",
      "1000626\n",
      "1000627\n",
      "1000628\n",
      "1000629\n",
      "1000630\n",
      "1000631\n",
      "1000632\n",
      "1000633\n",
      "1000634\n",
      "1000635\n",
      "1000636\n",
      "1000637\n",
      "1000638\n",
      "1000639\n",
      "1000640\n",
      "1000641\n",
      "1000642\n",
      "1000643\n",
      "1000644\n",
      "1000645\n",
      "1000646\n",
      "1000647\n",
      "QU01ERROR\n",
      "QU02ERROR\n",
      "QU03ERROR\n",
      "QU04ERROR\n",
      "QU05ERROR\n",
      "QU06ERROR\n",
      "QU07ERROR\n",
      "QU08ERROR\n",
      "QU09ERROR\n",
      "QU10ERROR\n",
      "QU11ERROR\n",
      "QU13ERROR\n",
      "QU16ERROR\n",
      "UR001ERROR\n",
      "UR004ERROR\n",
      "UR017ERROR\n",
      "UR039ERROR\n",
      "UR044ERROR\n",
      "UR050ERROR\n",
      "UR052ERROR\n",
      "UR054ERROR\n",
      "UR055ERROR\n",
      "UR110ERROR\n",
      "UR112ERROR\n",
      "UR144ERROR\n",
      "UR155ERROR\n",
      "UR165ERROR\n",
      "UR167ERROR\n",
      "UR190ERROR\n",
      "UR193ERROR\n",
      "1000507\n",
      "1000517\n",
      "1000520\n",
      "UR221ERROR\n",
      "1000589\n",
      "1000590\n",
      "UR253ERROR\n",
      "1000592\n",
      "UR255ERROR\n",
      "1000595\n",
      "1000599\n",
      "1000600\n",
      "1000601\n",
      "1000602\n",
      "1000603\n",
      "1000604\n",
      "1000607\n",
      "1000608\n",
      "1000609\n",
      "1000610\n",
      "1000611\n",
      "1000612\n",
      "1000613\n",
      "1000614\n",
      "1000615\n",
      "1000616\n",
      "1000617\n",
      "1000619\n",
      "1000620\n",
      "1000622\n",
      "1000623\n",
      "1000621\n",
      "UR280ERROR\n",
      "UR281ERROR\n",
      "1000651\n",
      "1000655\n",
      "UR292AERROR\n",
      "1000660\n"
     ]
    }
   ],
   "source": [
    "sum_df = pd.read_csv(\"/Users/ashokkhosla/Desktop/Khipu/fieldguide/data/CSV/khipu_summary.csv\")\n",
    "def khipu_name_to_id(aName): \n",
    "    try:\n",
    "        sum_df[sum_df['kfg_name']==aName]['khipu_id'].values[0]\n",
    "    except: \n",
    "        return f\"{aName}ERROR\"\n",
    "for dk in dks:\n",
    "    print(khipu_name_to_id(dk))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "def as_digitcode_vector(aList, asChars=False):\n",
    "    \"\"\" Akin to onehot encoding \n",
    "        >>> list_to_setdict(['a','b','c','a','b','c','d'])\n",
    "        returns a three-tuple\n",
    "        ([0, 1, 2, 0, 1, 2, 3],            #The encoded result\n",
    "         {0: 'a', 1: 'b', 2: 'c', 3: 'd'}, #The source to target dict\n",
    "         {'a': 0, 'b': 1, 'c': 2, 'd': 3}) #The target to source dict\n",
    "\n",
    "         if asChars is True, then the encoded result is a string, starting with 'A'\n",
    "         if you have more than 52 unique items, you'll need to rethink this\n",
    "    \"\"\"\n",
    "    the_values = sorted(set(aList))\n",
    "    if asChars: \n",
    "        source_to_target = {value:chr(ord('A')+index) for index, value in enumerate(the_values)}\n",
    "        target_to_source = {value:key for key,value in source_to_target.items()}\n",
    "    else:\n",
    "        source_to_target = {value:key for key,value in enumerate(the_values)}\n",
    "        target_to_source = dict(enumerate(the_values))\n",
    "\n",
    "    encoded = [source_to_target[aValue] for aValue in aList]\n",
    "    return (encoded, source_to_target, target_to_source)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "foo = ['ashok', 'bob', 'carlos', 'ashok', 'bob', 'carlos', 'doug']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(['A', 'B', 'C', 'A', 'B', 'C', 'D'],\n",
       " {'ashok': 'A', 'bob': 'B', 'carlos': 'C', 'doug': 'D'},\n",
       " {'A': 'ashok', 'B': 'bob', 'C': 'carlos', 'D': 'doug'})"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "as_digitcode_vector(foo, asString=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan]\n"
     ]
    }
   ],
   "source": [
    "ascher_cord_color_df = pd.read_csv(f\"/Users/ashokkhosla/Desktop/Khipu/fieldguide/data/CSV/ascher_cord_color.csv\")\n",
    "mixed_colors = [aColor for aColor in ascher_cord_color_df['FULL_COLOR'].tolist() if isinstance(aColor, str)]\n",
    "mixed_colors"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "hide_input": false,
  "kernelspec": {
   "display_name": "Python 3.9.7 ('k3')",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.3"
  },
  "toc": {
   "base_numbering": 1,
   "nav_menu": {},
   "number_sections": true,
   "sideBar": true,
   "skip_h1_title": false,
   "title_cell": "Table of Contents",
   "title_sidebar": "Contents",
   "toc_cell": false,
   "toc_position": {
    "height": "calc(100% - 180px)",
    "left": "10px",
    "top": "150px",
    "width": "432.390625px"
   },
   "toc_section_display": true,
   "toc_window_display": false
  },
  "varInspector": {
   "cols": {
    "lenName": 16,
    "lenType": 16,
    "lenVar": 40
   },
   "kernels_config": {
    "python": {
     "delete_cmd_postfix": "",
     "delete_cmd_prefix": "del ",
     "library": "var_list.py",
     "varRefreshCmd": "print(var_dic_list())"
    },
    "r": {
     "delete_cmd_postfix": ") ",
     "delete_cmd_prefix": "rm(",
     "library": "var_list.r",
     "varRefreshCmd": "cat(var_dic_list()) "
    }
   },
   "position": {
    "height": "1001px",
    "left": "1762px",
    "right": "20px",
    "top": "147px",
    "width": "350px"
   },
   "types_to_exclude": [
    "module",
    "function",
    "builtin_function_or_method",
    "instance",
    "_Feature"
   ],
   "window_display": false
  },
  "vscode": {
   "interpreter": {
    "hash": "df9b677c74e96b08390c21d09147c66890eda01aaf7360804550a39a4b9cadbd"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}