draft_align_tables.ipynb

draft_align_dfs.ipynb

gistfile1.txt

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 8,
   "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>chrom</th>\n",
       "      <th>start</th>\n",
       "      <th>end</th>\n",
       "      <th>strand2</th>\n",
       "      <th>animal</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>22</th>\n",
       "      <td>chr1</td>\n",
       "      <td>0</td>\n",
       "      <td>6</td>\n",
       "      <td>+</td>\n",
       "      <td>cat</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>chr1</td>\n",
       "      <td>8</td>\n",
       "      <td>10</td>\n",
       "      <td>+</td>\n",
       "      <td>dog</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>chrX</td>\n",
       "      <td>1</td>\n",
       "      <td>8</td>\n",
       "      <td>+</td>\n",
       "      <td>cat</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   chrom  start  end strand2 animal\n",
       "22  chr1      0    6       +    cat\n",
       "11  chr1      8   10       +    dog\n",
       "16  chrX      1    8       +    cat"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import bioframe\n",
    "import pyranges as pr\n",
    "import numpy as np\n",
    "from io import StringIO\n",
    "from bioframe.ops import _get_default_colnames, _verify_columns\n",
    "\n",
    "df1 = pd.DataFrame(\n",
    "    [\n",
    "        [\"chr1\", 0, 6, \"+\"],\n",
    "        [\"chr1\", 8, 10, \"-\"],\n",
    "        [\"chrX\", 1, 8, \"+\"],\n",
    "    ],\n",
    "    columns=[\"chrom\", \"start\", \"end\", \"strand\"],\n",
    ")\n",
    "\n",
    "df2 = pd.DataFrame(\n",
    "    [\n",
    "        [\"chr1\", 0, 6, \"+\", \"cat\"],\n",
    "        [\"chr1\", 8, 10, \"+\", \"dog\"],\n",
    "        [\"chrX\", 1, 8, \"+\", \"cat\"],\n",
    "    ],\n",
    "    columns=[\"chrom\", \"start\", \"end\", \"strand2\", \"animal\"],\n",
    ")\n",
    "df2.set_index(pd.Index([22,11, 16]), inplace=True)\n",
    "df2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "def align_tables_pd(df1,df2,cols1=None,cols2=None):\n",
    "    ck1, sk1, ek1 = _get_default_colnames() if cols1 is None else cols2\n",
    "    ck2, sk2, ek2 = _get_default_colnames() if cols2 is None else cols2\n",
    "    df1.reset_index(inplace=True,drop=True)\n",
    "    df2.reset_index(inplace=True,drop=True)\n",
    "    pd.testing.assert_frame_equal(df1[[ck1,sk1,ek1 ]],df2[[ck2, sk2, ek2 ]], ) \n",
    "    return df1,df2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "def align_tables_by_values(df1,df2,cols1=None,cols2=None):\n",
    "    ck1, sk1, ek1 = _get_default_colnames() if cols1 is None else cols2\n",
    "    ck2, sk2, ek2 = _get_default_colnames() if cols2 is None else cols2\n",
    "    if not (df1[[ck1,sk1,ek1 ]].eq(df2[[ck1,sk1,ek1 ]].values) | \n",
    "        (df1[[ck1,sk1,ek1 ]].isnull().values & df2[[ck1,sk1,ek1 ]].isnull().values)).all().all():\n",
    "        raise AssertionError('dataframes not equivalent')\n",
    "    else:\n",
    "        df1.reset_index(inplace=True,drop=True)\n",
    "        df2.reset_index(inplace=True,drop=True)\n",
    "    return df1,df2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(  chrom  start  end strand\n",
       " 0  chr1      0    6      +\n",
       " 1  chr1      8   10      -\n",
       " 2  chrX      1    8      +,\n",
       "   chrom  start  end strand2 animal\n",
       " 0  chr1      0    6       +    cat\n",
       " 1  chr1      8   10       +    dog\n",
       " 2  chrX      1    8       +    cat)"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df1,df2 = align_tables_np(df1,df2)\n",
    "df1,df2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.8.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}