{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "\n",
    "# Let's read in the data file\n",
    "df = pd.read_csv('../data/epa/RD_501_88101_2012-0.txt', sep = \"|\")\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df[1:] # delete the first row starting with \"# RC\"\n",
    "df = df[:-1] # delete last row with number of entries\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df.columns # list all columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df2 = pd.DataFrame(df, columns = ['# RD', 'Action Code', 'State Code', 'County Code', 'Site ID',\n",
    "       'Parameter', 'POC', 'Sample Duration', 'Unit', 'Method', 'Date',\n",
    "       'Start Time', 'Sample Value', 'Null Data Code', 'Sampling Frequency',\n",
    "       'Monitor Protocol (MP) ID'])\n",
    "df2.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "t = df2.pivot_table('Sampling Frequency', index=['State Code'],\n",
    "                    aggfunc='count')\n",
    "t"
   ]
  },
  {
   "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": "3.6.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}