{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 112,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 104,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['chair_yellow',\n",
       " 'chair_lime',\n",
       " 'bike',\n",
       " 'chair_red',\n",
       " 'table',\n",
       " 'chair_white',\n",
       " 'chair_black',\n",
       " 'chair_blue']"
      ]
     },
     "execution_count": 104,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# hardcoded\n",
    "data_folders = ['chair_yellow',\n",
    " 'chair_lime',\n",
    " 'bike',\n",
    " 'chair_red',\n",
    " 'table',\n",
    " 'chair_white',\n",
    " 'chair_black',\n",
    " 'chair_blue']\n",
    "data_folders"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 113,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "chair_yellow150.jpg\n",
      "chair_lime293.jpg\n",
      "bike612.jpg\n",
      "chair_red526.jpg\n",
      "table026.jpg\n",
      "chair_white076.jpg\n",
      "chair_black157.jpg\n",
      "chair_blue104.jpg\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "[673, 729, 782, 751, 680, 742, 689, 672]"
      ]
     },
     "execution_count": 113,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# array of arrays, containing the list files, grouped by folder\n",
    "filenames = [os.listdir(f) for f in data_folders]\n",
    "[print(f[1]) for f in filenames]\n",
    "[len(f) for f in filenames]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 114,
   "metadata": {},
   "outputs": [],
   "source": [
    "files_dict = dict(zip(data_folders, filenames))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 107,
   "metadata": {},
   "outputs": [],
   "source": [
    "base_gcs_path = 'gs://cloudml-demo-vcm/chairs_table_bike/'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 108,
   "metadata": {},
   "outputs": [],
   "source": [
    "# What we want:\n",
    "# gs://cloudml-demo-vcm/chairs_table_bike/chair_black/chair_black157.jpg, 'chair_black' \n",
    "# base_gcs_path + dict_key + '/' + filename\n",
    "\n",
    "data_array = []\n",
    "\n",
    "for (dict_key, files_list) in files_dict.items():\n",
    "    for filename in files_list:\n",
    "#         print(base_gcs_path + dict_key + '/' + filename)\n",
    "        if '.jpg' not in filename: \n",
    "            continue # don't include non-photos\n",
    "\n",
    "        label = dict_key\n",
    "#         label = 'chair' if 'chair' in dict_key else dict_key # for grouping all chairs as one label\n",
    "        \n",
    "        data_array.append((base_gcs_path + dict_key + '/' + filename , label))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 115,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow636.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow150.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow144.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow622.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow178.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow193.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow187.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow352.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow434.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow420.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow346.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow408.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow391.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow385.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow226.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow540.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow554.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow232.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow568.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow583.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow597.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow024.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow030.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow018.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow019.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow031.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow025.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow596.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow582.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow569.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow555.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow233.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow227.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow541.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow384.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow390.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow409.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow421.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow347.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow353.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow435.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow186.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow192.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow179.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow145.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow623.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow637.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow151.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow621.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow147.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow153.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow635.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow609.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow184.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow190.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow345.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow423.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow437.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow351.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow379.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow386.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow392.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow231.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow557.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow543.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow225.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow219.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow594.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow580.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow033.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow027.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow026.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow032.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow581.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow595.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow218.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow542.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow224.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow230.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow556.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow393.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow387.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow378.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow436.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow350.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow344.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow422.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow191.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow185.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow608.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow152.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow634.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow620.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow146.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow618.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow142.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow624.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow630.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow156.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow181.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow195.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow368.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow426.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow340.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow354.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow432.jpg',\n",
       "  'chair_yellow'),\n",
       " ('gs://cloudml-demo-vcm/chairs_table_bike/chair_yellow/chair_yellow383.jpg',\n",
       "  'chair_yellow'),\n",
       " ...]"
      ]
     },
     "execution_count": 115,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data_array"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 116,
   "metadata": {},
   "outputs": [],
   "source": [
    "dataframe = pd.DataFrame(data_array)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 117,
   "metadata": {
    "scrolled": true
   },
   "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>0</th>\n",
       "      <th>1</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_yellow</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_yellow</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_yellow</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_yellow</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_yellow</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_yellow</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_yellow</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_yellow</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_yellow</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_yellow</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_yellow</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_yellow</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_yellow</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_yellow</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_yellow</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_yellow</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_yellow</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_yellow</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_yellow</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_yellow</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_yellow</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_yellow</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_yellow</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_yellow</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_yellow</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_yellow</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_yellow</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_yellow</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>28</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_yellow</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_yellow</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5679</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_blue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5680</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_blue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5681</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_blue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5682</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_blue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5683</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_blue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5684</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_blue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5685</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_blue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5686</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_blue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5687</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_blue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5688</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_blue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5689</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_blue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5690</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_blue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5691</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_blue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5692</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_blue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5693</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_blue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5694</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_blue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5695</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_blue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5696</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_blue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5697</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_blue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5698</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_blue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5699</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_blue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5700</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_blue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5701</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_blue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5702</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_blue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5703</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_blue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5704</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_blue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5705</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_blue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5706</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_blue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5707</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_blue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5708</th>\n",
       "      <td>gs://cloudml-demo-vcm/chairs_table_bike/chair_...</td>\n",
       "      <td>chair_blue</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5709 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                      0             1\n",
       "0     gs://cloudml-demo-vcm/chairs_table_bike/chair_...  chair_yellow\n",
       "1     gs://cloudml-demo-vcm/chairs_table_bike/chair_...  chair_yellow\n",
       "2     gs://cloudml-demo-vcm/chairs_table_bike/chair_...  chair_yellow\n",
       "3     gs://cloudml-demo-vcm/chairs_table_bike/chair_...  chair_yellow\n",
       "4     gs://cloudml-demo-vcm/chairs_table_bike/chair_...  chair_yellow\n",
       "5     gs://cloudml-demo-vcm/chairs_table_bike/chair_...  chair_yellow\n",
       "6     gs://cloudml-demo-vcm/chairs_table_bike/chair_...  chair_yellow\n",
       "7     gs://cloudml-demo-vcm/chairs_table_bike/chair_...  chair_yellow\n",
       "8     gs://cloudml-demo-vcm/chairs_table_bike/chair_...  chair_yellow\n",
       "9     gs://cloudml-demo-vcm/chairs_table_bike/chair_...  chair_yellow\n",
       "10    gs://cloudml-demo-vcm/chairs_table_bike/chair_...  chair_yellow\n",
       "11    gs://cloudml-demo-vcm/chairs_table_bike/chair_...  chair_yellow\n",
       "12    gs://cloudml-demo-vcm/chairs_table_bike/chair_...  chair_yellow\n",
       "13    gs://cloudml-demo-vcm/chairs_table_bike/chair_...  chair_yellow\n",
       "14    gs://cloudml-demo-vcm/chairs_table_bike/chair_...  chair_yellow\n",
       "15    gs://cloudml-demo-vcm/chairs_table_bike/chair_...  chair_yellow\n",
       "16    gs://cloudml-demo-vcm/chairs_table_bike/chair_...  chair_yellow\n",
       "17    gs://cloudml-demo-vcm/chairs_table_bike/chair_...  chair_yellow\n",
       "18    gs://cloudml-demo-vcm/chairs_table_bike/chair_...  chair_yellow\n",
       "19    gs://cloudml-demo-vcm/chairs_table_bike/chair_...  chair_yellow\n",
       "20    gs://cloudml-demo-vcm/chairs_table_bike/chair_...  chair_yellow\n",
       "21    gs://cloudml-demo-vcm/chairs_table_bike/chair_...  chair_yellow\n",
       "22    gs://cloudml-demo-vcm/chairs_table_bike/chair_...  chair_yellow\n",
       "23    gs://cloudml-demo-vcm/chairs_table_bike/chair_...  chair_yellow\n",
       "24    gs://cloudml-demo-vcm/chairs_table_bike/chair_...  chair_yellow\n",
       "25    gs://cloudml-demo-vcm/chairs_table_bike/chair_...  chair_yellow\n",
       "26    gs://cloudml-demo-vcm/chairs_table_bike/chair_...  chair_yellow\n",
       "27    gs://cloudml-demo-vcm/chairs_table_bike/chair_...  chair_yellow\n",
       "28    gs://cloudml-demo-vcm/chairs_table_bike/chair_...  chair_yellow\n",
       "29    gs://cloudml-demo-vcm/chairs_table_bike/chair_...  chair_yellow\n",
       "...                                                 ...           ...\n",
       "5679  gs://cloudml-demo-vcm/chairs_table_bike/chair_...    chair_blue\n",
       "5680  gs://cloudml-demo-vcm/chairs_table_bike/chair_...    chair_blue\n",
       "5681  gs://cloudml-demo-vcm/chairs_table_bike/chair_...    chair_blue\n",
       "5682  gs://cloudml-demo-vcm/chairs_table_bike/chair_...    chair_blue\n",
       "5683  gs://cloudml-demo-vcm/chairs_table_bike/chair_...    chair_blue\n",
       "5684  gs://cloudml-demo-vcm/chairs_table_bike/chair_...    chair_blue\n",
       "5685  gs://cloudml-demo-vcm/chairs_table_bike/chair_...    chair_blue\n",
       "5686  gs://cloudml-demo-vcm/chairs_table_bike/chair_...    chair_blue\n",
       "5687  gs://cloudml-demo-vcm/chairs_table_bike/chair_...    chair_blue\n",
       "5688  gs://cloudml-demo-vcm/chairs_table_bike/chair_...    chair_blue\n",
       "5689  gs://cloudml-demo-vcm/chairs_table_bike/chair_...    chair_blue\n",
       "5690  gs://cloudml-demo-vcm/chairs_table_bike/chair_...    chair_blue\n",
       "5691  gs://cloudml-demo-vcm/chairs_table_bike/chair_...    chair_blue\n",
       "5692  gs://cloudml-demo-vcm/chairs_table_bike/chair_...    chair_blue\n",
       "5693  gs://cloudml-demo-vcm/chairs_table_bike/chair_...    chair_blue\n",
       "5694  gs://cloudml-demo-vcm/chairs_table_bike/chair_...    chair_blue\n",
       "5695  gs://cloudml-demo-vcm/chairs_table_bike/chair_...    chair_blue\n",
       "5696  gs://cloudml-demo-vcm/chairs_table_bike/chair_...    chair_blue\n",
       "5697  gs://cloudml-demo-vcm/chairs_table_bike/chair_...    chair_blue\n",
       "5698  gs://cloudml-demo-vcm/chairs_table_bike/chair_...    chair_blue\n",
       "5699  gs://cloudml-demo-vcm/chairs_table_bike/chair_...    chair_blue\n",
       "5700  gs://cloudml-demo-vcm/chairs_table_bike/chair_...    chair_blue\n",
       "5701  gs://cloudml-demo-vcm/chairs_table_bike/chair_...    chair_blue\n",
       "5702  gs://cloudml-demo-vcm/chairs_table_bike/chair_...    chair_blue\n",
       "5703  gs://cloudml-demo-vcm/chairs_table_bike/chair_...    chair_blue\n",
       "5704  gs://cloudml-demo-vcm/chairs_table_bike/chair_...    chair_blue\n",
       "5705  gs://cloudml-demo-vcm/chairs_table_bike/chair_...    chair_blue\n",
       "5706  gs://cloudml-demo-vcm/chairs_table_bike/chair_...    chair_blue\n",
       "5707  gs://cloudml-demo-vcm/chairs_table_bike/chair_...    chair_blue\n",
       "5708  gs://cloudml-demo-vcm/chairs_table_bike/chair_...    chair_blue\n",
       "\n",
       "[5709 rows x 2 columns]"
      ]
     },
     "execution_count": 117,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dataframe"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 111,
   "metadata": {},
   "outputs": [],
   "source": [
    "dataframe.to_csv('all_data.csv', index=False, header=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 87,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "gsutil cp all_data.csv gs://cloudml-demo-vcm/chairs_table_bike/"
   ]
  }
 ],
 "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": "3.6.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}