Comparing numpy arrays and pandas data frames

foo.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import hashlib"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[['42' 'foo' '42']\n",
      " ['42' 'foo' 'foo']\n",
      " ['42' 'bar' '42']]\n",
      "    0    1    2\n",
      "0  42  foo   42\n",
      "1  42  foo  foo\n",
      "2  42  bar   42\n",
      "52db9328682317c44370b8186a5c6bae75f2a94c9d0d5b24d61f602857acd3de\n",
      "02c8520959ae029e3d968a0f4fc2b0d036445578dd80c54d75ccfe7ab0c863bd\n",
      "aa93ea3aeae7d27581dbf0ea8ea43250b16e7fe340cd72655a694fc857a2a4be\n",
      "942282b41afac938d2d5be69cd1868918c55fa18b96106677f01dfaf816c9cba\n"
     ]
    }
   ],
   "source": [
    "np.random.seed(42)\n",
    "arr = np.random.choice(['foo', 'bar', 42], size=(3,3))\n",
    "df = pd.DataFrame(arr)\n",
    "print(arr)\n",
    "print(df)\n",
    "print(hashlib.sha256(arr.tobytes()).hexdigest())\n",
    "print(hashlib.sha256(df.values.tobytes()).hexdigest())\n",
    "print(hashlib.sha256(df.to_json().encode()).hexdigest())\n",
    "print(hashlib.sha256(df.to_csv().encode()).hexdigest())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([['42', 'foo', '42'],\n",
       "       ['42', 'foo', 'foo'],\n",
       "       ['42', 'bar', '42']], \n",
       "      dtype='<U3')"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "arr"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([['42', 'foo', '42'],\n",
       "       ['42', 'foo', 'foo'],\n",
       "       ['42', 'bar', '42']], dtype=object)"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.array_equal(arr , df.values )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[42 41 42]\n",
      " [42 41 41]\n",
      " [42 43 42]]\n",
      "    0   1   2\n",
      "0  42  41  42\n",
      "1  42  41  41\n",
      "2  42  43  42\n",
      "ddfee4572d380bef86d3ebe3cb7bfa7c68b7744f55f67f4e1ca5f6872c2c9ba1\n",
      "ddfee4572d380bef86d3ebe3cb7bfa7c68b7744f55f67f4e1ca5f6872c2c9ba1\n"
     ]
    }
   ],
   "source": [
    "np.random.seed(42)\n",
    "arr = np.random.choice([41, 43, 42], size=(3,3))\n",
    "df = pd.DataFrame(arr)\n",
    "print(arr)\n",
    "print(df)\n",
    "print(hashlib.sha256(arr.tobytes()).hexdigest())\n",
    "print(hashlib.sha256(df.values.tobytes()).hexdigest())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[42, 41, 42],\n",
       "       [42, 41, 41],\n",
       "       [42, 43, 42]])"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "arr"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[42, 41, 42],\n",
       "       [42, 41, 41],\n",
       "       [42, 43, 42]])"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.array_equal(arr, df.values)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python [conda root]",
   "language": "python",
   "name": "conda-root-py"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}