codebook roundtrip to csv.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<xarray.Codebook (target: 2, c: 3, r: 2)>\n",
       "array([[[0, 1],\n",
       "        [0, 0],\n",
       "        [1, 0]],\n",
       "\n",
       "       [[0, 0],\n",
       "        [1, 1],\n",
       "        [0, 0]]], dtype=uint8)\n",
       "Coordinates:\n",
       "  * target   (target) object a3866318-c57d-4dce-ba4f-948b83daa665 41eb0d65-5312-437b-a740-bec1fdb4efb4\n",
       "  * c        (c) int64 0 1 2\n",
       "  * r        (r) int64 0 1"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from starfish import Codebook\n",
    "codebook = Codebook.synthetic_one_hot_codebook(n_round=2, n_channel=3, n_codes=2)\n",
    "codebook"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th>v</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>target</th>\n",
       "      <th>c</th>\n",
       "      <th>r</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"5\" valign=\"top\">a3866318-c57d-4dce-ba4f-948b83daa665</th>\n",
       "      <th rowspan=\"2\" valign=\"top\">0</th>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">1</th>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                          v\n",
       "target                               c r   \n",
       "a3866318-c57d-4dce-ba4f-948b83daa665 0 0  0\n",
       "                                       1  1\n",
       "                                     1 0  0\n",
       "                                       1  0\n",
       "                                     2 0  1"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = codebook.to_dataframe(name='v')\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "df.to_csv('codebook.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "target,c,r,v\n",
      "a3866318-c57d-4dce-ba4f-948b83daa665,0,0,0\n",
      "a3866318-c57d-4dce-ba4f-948b83daa665,0,1,1\n",
      "a3866318-c57d-4dce-ba4f-948b83daa665,1,0,0\n",
      "a3866318-c57d-4dce-ba4f-948b83daa665,1,1,0\n",
      "a3866318-c57d-4dce-ba4f-948b83daa665,2,0,1\n",
      "a3866318-c57d-4dce-ba4f-948b83daa665,2,1,0\n",
      "41eb0d65-5312-437b-a740-bec1fdb4efb4,0,0,0\n",
      "41eb0d65-5312-437b-a740-bec1fdb4efb4,0,1,0\n",
      "41eb0d65-5312-437b-a740-bec1fdb4efb4,1,0,1\n",
      "41eb0d65-5312-437b-a740-bec1fdb4efb4,1,1,1\n",
      "41eb0d65-5312-437b-a740-bec1fdb4efb4,2,0,0\n",
      "41eb0d65-5312-437b-a740-bec1fdb4efb4,2,1,0\n"
     ]
    }
   ],
   "source": [
    "%%bash\n",
    "less codebook.csv"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "codebook2 = pd.read_csv('codebook.csv',index_col=[0,1,2])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<xarray.DataArray 'v' (target: 2, c: 3, r: 2)>\n",
       "array([[[0, 0],\n",
       "        [1, 1],\n",
       "        [0, 0]],\n",
       "\n",
       "       [[0, 1],\n",
       "        [0, 0],\n",
       "        [1, 0]]])\n",
       "Coordinates:\n",
       "  * target   (target) object '41eb0d65-5312-437b-a740-bec1fdb4efb4' 'a3866318-c57d-4dce-ba4f-948b83daa665'\n",
       "  * c        (c) int64 0 1 2\n",
       "  * r        (r) int64 0 1"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "codebook2.to_xarray()['v']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "starfish",
   "language": "python",
   "name": "starfish"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}