{
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "_cell_guid": "934b828d-9de4-dc5b-5d41-252bc3fc66d0"
      },
      "source": ""
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "_cell_guid": "50f983e1-db98-9ad5-1b46-4bcf697ce8ac"
      },
      "outputs": [],
      "source": [
        "import pandas"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "_cell_guid": "855fc5a4-8b58-152d-f562-b2b7eba83184"
      },
      "outputs": [],
      "source": [
        "import pandas\n",
        "\n",
        "# Creating one chunk of 1000 row from each data set and write it to file to work on\n",
        "chunk_size = 10 ** 3\n",
        "print('Starting')\n",
        "for data in pandas.read_csv('../input/train_date.csv', iterator=True, chunksize=chunk_size):\n",
        "    data.to_csv('date_sample.csv')\n",
        "    break\n",
        "for data in pandas.read_csv('../input/train_categorical.csv', iterator=True, chunksize=chunk_size):\n",
        "    data.to_csv('categorical_sample.csv')\n",
        "    break\n",
        "for data in pandas.read_csv('../input/train_numeric.csv', iterator=True, chunksize=chunk_size):\n",
        "    data.to_csv('numeric_sample.csv')\n",
        "    break"
      ]
    }
  ],
  "metadata": {
    "_change_revision": 0,
    "_is_fork": false,
    "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": "3.5.2"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}