pd_conventers.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 4,
   "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>name</th>\n",
       "      <th>comment</th>\n",
       "      <th>temperature</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>james</td>\n",
       "      <td>The world has ended XXXX</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>jack</td>\n",
       "      <td>24 hours to go before XXXX is gone</td>\n",
       "      <td>17.78</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    name                             comment  temperature\n",
       "0  james            The world has ended XXXX         0.00\n",
       "1   jack  24 hours to go before XXXX is gone        17.78"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import io\n",
    "import re\n",
    "import pandas as pd\n",
    "\n",
    "\n",
    "# data example\n",
    "csv_ish = io.StringIO(\n",
    "\"\"\"name,comment,temperature\n",
    "james,The world has ended 007,32\n",
    "jack,24 hours to go before CTU is gone,64\n",
    "\"\"\"\n",
    ")\n",
    "\n",
    "\n",
    "def remove_sensitive_data(text: str) -> str:\n",
    "\t# remove sensitive func logic example\n",
    "\tsensitive = {\"007\", \"CTU\"}\n",
    "\tpattern = re.compile(\"|\".join(sensitive))\n",
    "\ttext = re.sub(pattern, \"XXXX\", text)\n",
    "\treturn text\n",
    "\n",
    "\n",
    "def fahrenheit_to_celsius(temp: str) -> float:\n",
    "\t# data transformation example\n",
    "\ttry:\n",
    "\t\treturn round((float(temp) - 32) * 5 / 9, 2)\n",
    "\texcept TypeError:\n",
    "\t\treturn None\n",
    "\n",
    "\n",
    "# Usage:\n",
    "# using converters to transform columns during data read\n",
    "\n",
    "pd.read_csv(\n",
    "\tcsv_ish,\n",
    "\tconverters={\n",
    "\t\t'comment': remove_sensitive_data,\n",
    "\t\t'temperature': fahrenheit_to_celsius\n",
    "\t}\n",
    ")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "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>name</th>\n",
       "      <th>comment</th>\n",
       "      <th>temperature</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>james</td>\n",
       "      <td>The world has ended XXXX</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>jack</td>\n",
       "      <td>24 hours to go before XXXX is gone</td>\n",
       "      <td>17.78</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    name                             comment  temperature\n",
       "0  james            The world has ended XXXX         0.00\n",
       "1   jack  24 hours to go before XXXX is gone        17.78"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "FILE_PATH = io.StringIO(\n",
    "\"\"\"name,comment,temperature\n",
    "james,The world has ended 007,32\n",
    "jack,24 hours to go before CTU is gone,64\n",
    "\"\"\"\n",
    ")\n",
    "CHUNK_SIZE = 100_000\n",
    "\n",
    "reader = pd.read_csv(FILE_PATH, chunksize=CHUNK_SIZE, low_memory=False, converters={\n",
    "\t\t'comment': remove_sensitive_data,\n",
    "\t\t'temperature': fahrenheit_to_celsius\n",
    "\t})\n",
    "for index, dataf_chunk in enumerate(reader):\n",
    "    ...\n",
    "    display(dataf_chunk)\n",
    "    # do something awesome with dataf_chunk"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "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>name</th>\n",
       "      <th>comment</th>\n",
       "      <th>temperature</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>james</td>\n",
       "      <td>The world has ended 007</td>\n",
       "      <td>32</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>jack</td>\n",
       "      <td>24 hours to go before CTU is gone</td>\n",
       "      <td>64</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    name                            comment  temperature\n",
       "0  james            The world has ended 007           32\n",
       "1   jack  24 hours to go before CTU is gone           64"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "csv_ish = io.StringIO(\n",
    "\"\"\"name,comment,temperature\n",
    "james,The world has ended 007,32\n",
    "jack,24 hours to go before CTU is gone,64\n",
    "\"\"\"\n",
    ")\n",
    "pd.read_csv(csv_ish,)"
   ]
  }
 ],
 "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": "3.6.6+"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}