zip_dataframes.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import string\n",
    "import random\n",
    "import numpy as np\n",
    "import zipfile\n",
    "import io"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['a', 'y', 'k', 'd', 't', 'l']"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "random.sample(string.ascii_lowercase, 6)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[54,  7, 97, 48, 72, 34],\n",
       "       [56, 59, 52, 51, 90, 15],\n",
       "       [55, 13, 15, 46, 17, 98],\n",
       "       [23, 90, 71, 38, 33, 34],\n",
       "       [48, 61, 49, 19, 32, 32],\n",
       "       [49, 65, 33, 51, 28, 60],\n",
       "       [82, 36, 44, 91, 25, 53],\n",
       "       [51, 86, 62, 54, 17, 71],\n",
       "       [18, 76,  8, 22,  2, 42],\n",
       "       [72, 30, 39, 52, 86, 62]])"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.random.randint(1,100, (10, 6))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "def generate_a_df():\n",
    "    cols = random.sample(string.ascii_lowercase, random.randint(5,10))\n",
    "    n = random.randint(10,100)\n",
    "    return pd.DataFrame(np.random.randint(1, 100, (n, len(cols))), columns=cols) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "dfs = {f\"df{i:04}\": generate_a_df() for i in range(15)}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "with zipfile.ZipFile(\"my.zip\", \"w\") as z:\n",
    "    for name, df in dfs.items():\n",
    "        buf = io.BytesIO()\n",
    "        df.to_csv(buf, index=False)\n",
    "        buf.seek(0)\n",
    "        z.writestr(f\"{name}.csv\", buf.read())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "-rw-r--r-- 1 udi udi 20255 Apr 26 16:18 my.zip\n"
     ]
    }
   ],
   "source": [
    "!ls -l my.zip"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Archive:  my.zip\n",
      "  Length      Date    Time    Name\n",
      "---------  ---------- -----   ----\n",
      "     1228  2021-04-26 16:18   df0000.csv\n",
      "      588  2021-04-26 16:18   df0001.csv\n",
      "     1679  2021-04-26 16:18   df0002.csv\n",
      "     1886  2021-04-26 16:18   df0003.csv\n",
      "     1627  2021-04-26 16:18   df0004.csv\n",
      "     1783  2021-04-26 16:18   df0005.csv\n",
      "      218  2021-04-26 16:18   df0006.csv\n",
      "      455  2021-04-26 16:18   df0007.csv\n",
      "     2805  2021-04-26 16:18   df0008.csv\n",
      "      377  2021-04-26 16:18   df0009.csv\n",
      "      950  2021-04-26 16:18   df0010.csv\n",
      "     1565  2021-04-26 16:18   df0011.csv\n",
      "      171  2021-04-26 16:18   df0012.csv\n",
      "     1791  2021-04-26 16:18   df0013.csv\n",
      "     1670  2021-04-26 16:18   df0014.csv\n",
      "---------                     -------\n",
      "    18793                     15 files\n"
     ]
    }
   ],
   "source": [
    "!unzip -l my.zip"
   ]
  },
  {
   "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": "3.9.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}