pandas, dask , pyspark.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "ename": "FileNotFoundError",
     "evalue": "[Errno 2] No such file or directory: 'C:\\\\Users\\\\kanis\\\\OneDrive\\\\Desktop\\\\Flight test data\\\\capstone_airline_reviews3.xlsx'",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mFileNotFoundError\u001b[0m                         Traceback (most recent call last)",
      "\u001b[1;32m<ipython-input-2-ef000164a9c5>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mpd\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mread_excel\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34mr\"C:\\Users\\kanis\\OneDrive\\Desktop\\Flight test data\\capstone_airline_reviews3.xlsx\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\pandas\\io\\excel\\_base.py\u001b[0m in \u001b[0;36mread_excel\u001b[1;34m(io, sheet_name, header, names, index_col, usecols, squeeze, dtype, engine, converters, true_values, false_values, skiprows, nrows, na_values, keep_default_na, verbose, parse_dates, date_parser, thousands, comment, skipfooter, convert_float, mangle_dupe_cols, **kwds)\u001b[0m\n\u001b[0;32m    302\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    303\u001b[0m     \u001b[1;32mif\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0misinstance\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mio\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mExcelFile\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 304\u001b[1;33m         \u001b[0mio\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mExcelFile\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mio\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mengine\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mengine\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    305\u001b[0m     \u001b[1;32melif\u001b[0m \u001b[0mengine\u001b[0m \u001b[1;32mand\u001b[0m \u001b[0mengine\u001b[0m \u001b[1;33m!=\u001b[0m \u001b[0mio\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mengine\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    306\u001b[0m         raise ValueError(\n",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\pandas\\io\\excel\\_base.py\u001b[0m in \u001b[0;36m__init__\u001b[1;34m(self, io, engine)\u001b[0m\n\u001b[0;32m    822\u001b[0m         \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_io\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mstringify_path\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mio\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    823\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 824\u001b[1;33m         \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_reader\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_engines\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mengine\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_io\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    825\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    826\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0m__fspath__\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\pandas\\io\\excel\\_xlrd.py\u001b[0m in \u001b[0;36m__init__\u001b[1;34m(self, filepath_or_buffer)\u001b[0m\n\u001b[0;32m     19\u001b[0m         \u001b[0merr_msg\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;34m\"Install xlrd >= 1.0.0 for Excel support\"\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     20\u001b[0m         \u001b[0mimport_optional_dependency\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"xlrd\"\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mextra\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0merr_msg\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 21\u001b[1;33m         \u001b[0msuper\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__init__\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mfilepath_or_buffer\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     22\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     23\u001b[0m     \u001b[1;33m@\u001b[0m\u001b[0mproperty\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\pandas\\io\\excel\\_base.py\u001b[0m in \u001b[0;36m__init__\u001b[1;34m(self, filepath_or_buffer)\u001b[0m\n\u001b[0;32m    351\u001b[0m             \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mbook\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mload_workbook\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mfilepath_or_buffer\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    352\u001b[0m         \u001b[1;32melif\u001b[0m \u001b[0misinstance\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mfilepath_or_buffer\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mstr\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 353\u001b[1;33m             \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mbook\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mload_workbook\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mfilepath_or_buffer\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    354\u001b[0m         \u001b[1;32melif\u001b[0m \u001b[0misinstance\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mfilepath_or_buffer\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mbytes\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    355\u001b[0m             \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mbook\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mload_workbook\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mBytesIO\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mfilepath_or_buffer\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\pandas\\io\\excel\\_xlrd.py\u001b[0m in \u001b[0;36mload_workbook\u001b[1;34m(self, filepath_or_buffer)\u001b[0m\n\u001b[0;32m     34\u001b[0m             \u001b[1;32mreturn\u001b[0m \u001b[0mopen_workbook\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mfile_contents\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mdata\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     35\u001b[0m         \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 36\u001b[1;33m             \u001b[1;32mreturn\u001b[0m \u001b[0mopen_workbook\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mfilepath_or_buffer\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     37\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     38\u001b[0m     \u001b[1;33m@\u001b[0m\u001b[0mproperty\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\xlrd\\__init__.py\u001b[0m in \u001b[0;36mopen_workbook\u001b[1;34m(filename, logfile, verbosity, use_mmap, file_contents, encoding_override, formatting_info, on_demand, ragged_rows)\u001b[0m\n\u001b[0;32m    109\u001b[0m     \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    110\u001b[0m         \u001b[0mfilename\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mos\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mpath\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mexpanduser\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mfilename\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 111\u001b[1;33m         \u001b[1;32mwith\u001b[0m \u001b[0mopen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mfilename\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m\"rb\"\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0mf\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    112\u001b[0m             \u001b[0mpeek\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mf\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mread\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mpeeksz\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    113\u001b[0m     \u001b[1;32mif\u001b[0m \u001b[0mpeek\u001b[0m \u001b[1;33m==\u001b[0m \u001b[1;34mb\"PK\\x03\\x04\"\u001b[0m\u001b[1;33m:\u001b[0m \u001b[1;31m# a ZIP file\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;31mFileNotFoundError\u001b[0m: [Errno 2] No such file or directory: 'C:\\\\Users\\\\kanis\\\\OneDrive\\\\Desktop\\\\Flight test data\\\\capstone_airline_reviews3.xlsx'"
     ]
    }
   ],
   "source": [
    "pd.read_excel(r\"C:\\Users\\kanis\\OneDrive\\Desktop\\Flight test data\\capstone_airline_reviews3.xlsx\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "pip install dask\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import dask.array as dt\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "dt.random.randint(10,100)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "dt.random.randint(10,100,100000000)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "a = dt.random.randint(10,100,100000000)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "a = dt.random.randint(10,100,100000000).reshape(1000000,100)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "a\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "a.compute()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import dask.dataframe as dd\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "data = dd.read_csv(r\"C:\\Users\\kanis\\OneDrive\\Desktop\\Flight test data\\Ball_by_Ball.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "data.compute()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "pip install pyspark"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pyspark as spark"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from pyspark import SparkContext, SQLContext "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "pip install findspark"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "ename": "ValueError",
     "evalue": "Couldn't find Spark, make sure SPARK_HOME env is set or Spark is in an expected location (e.g. from homebrew installation).",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mValueError\u001b[0m                                Traceback (most recent call last)",
      "\u001b[1;32m<ipython-input-3-84edcc0ab449>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m      1\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mfindspark\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 2\u001b[1;33m \u001b[0mfindspark\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0minit\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m      3\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      4\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mpyspark\u001b[0m \u001b[1;31m# only run after findspark.init()\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      5\u001b[0m \u001b[1;32mfrom\u001b[0m \u001b[0mpyspark\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msql\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mSparkSession\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\findspark.py\u001b[0m in \u001b[0;36minit\u001b[1;34m(spark_home, python_path, edit_rc, edit_profile)\u001b[0m\n\u001b[0;32m    127\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    128\u001b[0m     \u001b[1;32mif\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0mspark_home\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 129\u001b[1;33m         \u001b[0mspark_home\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mfind\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    130\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    131\u001b[0m     \u001b[1;32mif\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0mpython_path\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\findspark.py\u001b[0m in \u001b[0;36mfind\u001b[1;34m()\u001b[0m\n\u001b[0;32m     33\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     34\u001b[0m     \u001b[1;32mif\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0mspark_home\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 35\u001b[1;33m         raise ValueError(\n\u001b[0m\u001b[0;32m     36\u001b[0m             \u001b[1;34m\"Couldn't find Spark, make sure SPARK_HOME env is set\"\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     37\u001b[0m             \u001b[1;34m\" or Spark is in an expected location (e.g. from homebrew installation).\"\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;31mValueError\u001b[0m: Couldn't find Spark, make sure SPARK_HOME env is set or Spark is in an expected location (e.g. from homebrew installation)."
     ]
    }
   ],
   "source": [
    "import findspark\n",
    "findspark.init()\n",
    "\n",
    "import pyspark # only run after findspark.init()\n",
    "from pyspark.sql import SparkSession\n",
    "spark = SparkSession.builder.getOrCreate()\n",
    "\n",
    "df = spark.sql('''select 'spark' as hello ''')\n",
    "df.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "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": "3.8.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}