wildfire_test_kai.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Wildfire Size Class Prediction"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 95,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import datetime as dt\n",
    "import sqlite3\n",
    "import julian"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Load in data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 96,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Select only pertinent features (this should make loading in data faster)\n",
    "con = sqlite3.connect(\"wildfire_data.sqlite\")\n",
    "query=\"\"\"\n",
    "SELECT \n",
    "FIRE_NAME,\n",
    "FIRE_SIZE_CLASS,\n",
    "STAT_CAUSE_DESCR, STAT_CAUSE_CODE,\n",
    "STATE, COUNTY,\n",
    "LONGITUDE, LATITUDE,\n",
    "DISCOVERY_DATE, \n",
    "DISCOVERY_TIME, \n",
    "CONT_DATE, \n",
    "CONT_TIME,\n",
    "FIRE_YEAR\n",
    "from Fires\n",
    "\"\"\"\n",
    "query=query.strip()\n",
    "df = pd.read_sql_query(query, con)\n",
    "con.close();"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 97,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(1880465, 13)\n"
     ]
    },
    {
     "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>FIRE_NAME</th>\n",
       "      <th>FIRE_SIZE_CLASS</th>\n",
       "      <th>STAT_CAUSE_DESCR</th>\n",
       "      <th>STAT_CAUSE_CODE</th>\n",
       "      <th>STATE</th>\n",
       "      <th>COUNTY</th>\n",
       "      <th>LONGITUDE</th>\n",
       "      <th>LATITUDE</th>\n",
       "      <th>DISCOVERY_DATE</th>\n",
       "      <th>DISCOVERY_TIME</th>\n",
       "      <th>CONT_DATE</th>\n",
       "      <th>CONT_TIME</th>\n",
       "      <th>FIRE_YEAR</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>FOUNTAIN</td>\n",
       "      <td>A</td>\n",
       "      <td>Miscellaneous</td>\n",
       "      <td>9.0</td>\n",
       "      <td>CA</td>\n",
       "      <td>63</td>\n",
       "      <td>-121.005833</td>\n",
       "      <td>40.036944</td>\n",
       "      <td>2453403.5</td>\n",
       "      <td>1300</td>\n",
       "      <td>2453403.5</td>\n",
       "      <td>1730</td>\n",
       "      <td>2005</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>PIGEON</td>\n",
       "      <td>A</td>\n",
       "      <td>Lightning</td>\n",
       "      <td>1.0</td>\n",
       "      <td>CA</td>\n",
       "      <td>61</td>\n",
       "      <td>-120.404444</td>\n",
       "      <td>38.933056</td>\n",
       "      <td>2453137.5</td>\n",
       "      <td>0845</td>\n",
       "      <td>2453137.5</td>\n",
       "      <td>1530</td>\n",
       "      <td>2004</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>SLACK</td>\n",
       "      <td>A</td>\n",
       "      <td>Debris Burning</td>\n",
       "      <td>5.0</td>\n",
       "      <td>CA</td>\n",
       "      <td>17</td>\n",
       "      <td>-120.735556</td>\n",
       "      <td>38.984167</td>\n",
       "      <td>2453156.5</td>\n",
       "      <td>1921</td>\n",
       "      <td>2453156.5</td>\n",
       "      <td>2024</td>\n",
       "      <td>2004</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>DEER</td>\n",
       "      <td>A</td>\n",
       "      <td>Lightning</td>\n",
       "      <td>1.0</td>\n",
       "      <td>CA</td>\n",
       "      <td>3</td>\n",
       "      <td>-119.913333</td>\n",
       "      <td>38.559167</td>\n",
       "      <td>2453184.5</td>\n",
       "      <td>1600</td>\n",
       "      <td>2453189.5</td>\n",
       "      <td>1400</td>\n",
       "      <td>2004</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>STEVENOT</td>\n",
       "      <td>A</td>\n",
       "      <td>Lightning</td>\n",
       "      <td>1.0</td>\n",
       "      <td>CA</td>\n",
       "      <td>3</td>\n",
       "      <td>-119.933056</td>\n",
       "      <td>38.559167</td>\n",
       "      <td>2453184.5</td>\n",
       "      <td>1600</td>\n",
       "      <td>2453189.5</td>\n",
       "      <td>1200</td>\n",
       "      <td>2004</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  FIRE_NAME FIRE_SIZE_CLASS STAT_CAUSE_DESCR  STAT_CAUSE_CODE STATE COUNTY  \\\n",
       "0  FOUNTAIN               A    Miscellaneous              9.0    CA     63   \n",
       "1    PIGEON               A        Lightning              1.0    CA     61   \n",
       "2     SLACK               A   Debris Burning              5.0    CA     17   \n",
       "3      DEER               A        Lightning              1.0    CA      3   \n",
       "4  STEVENOT               A        Lightning              1.0    CA      3   \n",
       "\n",
       "    LONGITUDE   LATITUDE  DISCOVERY_DATE DISCOVERY_TIME  CONT_DATE CONT_TIME  \\\n",
       "0 -121.005833  40.036944       2453403.5           1300  2453403.5      1730   \n",
       "1 -120.404444  38.933056       2453137.5           0845  2453137.5      1530   \n",
       "2 -120.735556  38.984167       2453156.5           1921  2453156.5      2024   \n",
       "3 -119.913333  38.559167       2453184.5           1600  2453189.5      1400   \n",
       "4 -119.933056  38.559167       2453184.5           1600  2453189.5      1200   \n",
       "\n",
       "   FIRE_YEAR  \n",
       "0       2005  \n",
       "1       2004  \n",
       "2       2004  \n",
       "3       2004  \n",
       "4       2004  "
      ]
     },
     "execution_count": 97,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "print(df.shape)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Drop rows with missing data\n",
    "Given our data is not sparse at all, we have the freedom to just drop all rows that are missing data we care about."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 98,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(892007, 13)"
      ]
     },
     "execution_count": 98,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# drop the following rows if they have missing data for the following features\n",
    "needed_cols = ['FIRE_SIZE_CLASS', 'DISCOVERY_DATE', 'DISCOVERY_TIME', 'CONT_DATE', 'CONT_TIME', 'STAT_CAUSE_CODE', 'STATE', 'LONGITUDE', 'LATITUDE']\n",
    "df = df.dropna(subset=needed_cols) # remove rows where both of these are missing\n",
    "df.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Create new columns to work with\n",
    "\n",
    "Map fire size class to integers so they can be ordered."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 99,
   "metadata": {},
   "outputs": [],
   "source": [
    "di = {\"A\": 1, \"B\": 2, \"C\": 3, \"D\": 4, \"E\": 5, \"F\": 6, \"G\": 7}\n",
    "df['FIRE_SIZE_CLASS'] = df['FIRE_SIZE_CLASS'].map(di)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Map states to indices to help handle categorical"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 100,
   "metadata": {},
   "outputs": [],
   "source": [
    "states = df.STATE.unique()\n",
    "ind = states.argsort(axis=0)\n",
    "state_di = {states[i]: i for i in ind}\n",
    "df['STATE_CODE']=df['STATE'].map(state_di)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Convert the date/time columns to datetime objects. Originally they are in julian time. Also calculate the time to containment (time delta of containment date - discovery date)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 101,
   "metadata": {},
   "outputs": [],
   "source": [
    "#To make these dates and times easier to manage, let's convert them to datetime. We can add new columns DISCOVERY_DATETIME and CONTAINMENT_DATETIME.\n",
    "df['DISCOVERY_DATETIME'] = df['DISCOVERY_DATE'];\n",
    "df['CONT_DATETIME'] = df['CONT_DATE'];"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 102,
   "metadata": {},
   "outputs": [],
   "source": [
    "#To populate those two rows, let's convert them into datetime.\n",
    "df['DISCOVERY_DATETIME'] = df['DISCOVERY_DATETIME'].apply(lambda x: julian.from_jd(x, fmt=\"jd\"))\n",
    "df['CONT_DATETIME'] = df['CONT_DATETIME'].apply(lambda x:julian.from_jd(x, fmt=\"jd\"))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 103,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0   2005-02-02 13:00:00\n",
       "1   2004-05-12 08:45:00\n",
       "2   2004-05-31 19:21:00\n",
       "3   2004-06-28 16:00:00\n",
       "4   2004-06-28 16:00:00\n",
       "Name: DISCOVERY_DATETIME, dtype: datetime64[ns]"
      ]
     },
     "execution_count": 103,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Let's also add the time \n",
    "temp_df = pd.DataFrame();\n",
    "temp_df['dt'] = df['DISCOVERY_TIME'].apply(lambda x: dt.timedelta(hours=int(x[0:2]), minutes=int(x[2:5])))\n",
    "df['DISCOVERY_DATETIME'] = df['DISCOVERY_DATETIME'] + temp_df['dt']\n",
    "df['DISCOVERY_DATETIME'].head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 104,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0   2005-02-02 17:30:00\n",
       "1   2004-05-12 15:30:00\n",
       "2   2004-05-31 20:24:00\n",
       "3   2004-07-03 14:00:00\n",
       "4   2004-07-03 12:00:00\n",
       "Name: CONT_DATETIME, dtype: datetime64[ns]"
      ]
     },
     "execution_count": 104,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Do the same thing for CONT_DATETIME\n",
    "temp_df = pd.DataFrame();\n",
    "temp_df['dt'] = df['CONT_TIME'].apply(lambda x: dt.timedelta(hours=int(x[0:2]), minutes=int(x[2:5])))\n",
    "df['CONT_DATETIME'] = df['CONT_DATETIME'] + temp_df['dt']\n",
    "df['CONT_DATETIME'].head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 105,
   "metadata": {},
   "outputs": [],
   "source": [
    "df.to_csv(\"data_with_target.csv\")\n",
    "#Checkpoint to save the data with the above columns before reloading"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 106,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Applications/anaconda3/lib/python3.6/site-packages/IPython/core/interactiveshell.py:3049: DtypeWarning: Columns (1,6) have mixed types. Specify dtype option on import or set low_memory=False.\n",
      "  interactivity=interactivity, compiler=compiler, result=result)\n"
     ]
    }
   ],
   "source": [
    "df = pd.read_csv(\"data_with_target.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 107,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{9.0: 'Miscellaneous',\n",
       " 1.0: 'Lightning',\n",
       " 5.0: 'Debris Burning',\n",
       " 4.0: 'Campfire',\n",
       " 2.0: 'Equipment Use',\n",
       " 7.0: 'Arson',\n",
       " 8.0: 'Children',\n",
       " 6.0: 'Railroad',\n",
       " 3.0: 'Smoking',\n",
       " 11.0: 'Powerline',\n",
       " 12.0: 'Structure',\n",
       " 10.0: 'Fireworks',\n",
       " 13.0: 'Missing/Undefined'}"
      ]
     },
     "execution_count": 107,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dict(zip(df.STAT_CAUSE_CODE,df.STAT_CAUSE_DESCR))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 108,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count                     892007\n",
       "mean      1 days 06:44:52.524004\n",
       "std      13 days 19:33:02.720135\n",
       "min              0 days 00:00:00\n",
       "25%              0 days 00:30:00\n",
       "50%              0 days 01:28:00\n",
       "75%              0 days 04:45:00\n",
       "max           3653 days 01:30:00\n",
       "Name: TIME_TO_CONT, dtype: object"
      ]
     },
     "execution_count": 108,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['CONT_DATETIME'] = df['CONT_DATETIME'].apply(lambda x: dt.datetime.strptime(x, '%Y-%m-%d %H:%M:%S'))\n",
    "df['DISCOVERY_DATETIME'] = df['DISCOVERY_DATETIME'].apply(lambda x: dt.datetime.strptime(x, '%Y-%m-%d %H:%M:%S'))\n",
    "df['TIME_TO_CONT'] = df['CONT_DATETIME'] - df['DISCOVERY_DATETIME']\n",
    "\n",
    "df['TIME_TO_CONT'].describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 109,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count    892007.000000\n",
       "mean         30.728347\n",
       "std         331.551520\n",
       "min           0.000000\n",
       "25%           0.000000\n",
       "50%           1.000000\n",
       "75%           5.000000\n",
       "max       87674.000000\n",
       "Name: HOURS_TO_CONT, dtype: float64"
      ]
     },
     "execution_count": 109,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# convert to hours for easier sorting\n",
    "df['HOURS_TO_CONT'] = df['TIME_TO_CONT'].apply(lambda x: round(float(x.total_seconds()/60/60)),2)\n",
    "df.HOURS_TO_CONT.describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Investigate the outliers in HOURS_TO_CONT \n",
    "\n",
    "75% is only 5 hours to cont, but max is abnormally high. \n",
    "Some dates seem to be incorrect (in record) -- month/day and time of day (h/m) are correct but wrong only in year.\n",
    "\n",
    "Be careful because some differences in year are okay (Dec/Jan fires).\n",
    "\n",
    "Since total dataset is 892007 instances, and of those, only 6000 are greater than 1000 hours to cont, these are definitely outliers and may need to be omitted from training for better accuracy/performance. We could also use a model that is insensitive to outliers."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 110,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count     5994.000000\n",
       "mean      2289.123624\n",
       "std       3257.553581\n",
       "min       1001.000000\n",
       "25%       1340.250000\n",
       "50%       1776.000000\n",
       "75%       2392.750000\n",
       "max      87674.000000\n",
       "Name: HOURS_TO_CONT, dtype: float64"
      ]
     },
     "execution_count": 110,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[df.HOURS_TO_CONT > 1000].HOURS_TO_CONT.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 111,
   "metadata": {},
   "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>Unnamed: 0</th>\n",
       "      <th>FIRE_NAME</th>\n",
       "      <th>FIRE_SIZE_CLASS</th>\n",
       "      <th>STAT_CAUSE_DESCR</th>\n",
       "      <th>STAT_CAUSE_CODE</th>\n",
       "      <th>STATE</th>\n",
       "      <th>COUNTY</th>\n",
       "      <th>LONGITUDE</th>\n",
       "      <th>LATITUDE</th>\n",
       "      <th>DISCOVERY_DATE</th>\n",
       "      <th>DISCOVERY_TIME</th>\n",
       "      <th>CONT_DATE</th>\n",
       "      <th>CONT_TIME</th>\n",
       "      <th>FIRE_YEAR</th>\n",
       "      <th>STATE_CODE</th>\n",
       "      <th>DISCOVERY_DATETIME</th>\n",
       "      <th>CONT_DATETIME</th>\n",
       "      <th>TIME_TO_CONT</th>\n",
       "      <th>HOURS_TO_CONT</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>182280</th>\n",
       "      <td>182647</td>\n",
       "      <td>ML5</td>\n",
       "      <td>3</td>\n",
       "      <td>Children</td>\n",
       "      <td>8.0</td>\n",
       "      <td>MN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-93.765300</td>\n",
       "      <td>46.212700</td>\n",
       "      <td>2449480.5</td>\n",
       "      <td>1450</td>\n",
       "      <td>2449845.5</td>\n",
       "      <td>1600</td>\n",
       "      <td>1994</td>\n",
       "      <td>14</td>\n",
       "      <td>1994-05-08 14:50:00</td>\n",
       "      <td>1995-05-08 16:00:00</td>\n",
       "      <td>365 days 01:10:00</td>\n",
       "      <td>8761</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>254190</th>\n",
       "      <td>256371</td>\n",
       "      <td>TRACKS</td>\n",
       "      <td>3</td>\n",
       "      <td>Arson</td>\n",
       "      <td>7.0</td>\n",
       "      <td>SD</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-100.540700</td>\n",
       "      <td>45.670000</td>\n",
       "      <td>2452773.5</td>\n",
       "      <td>2120</td>\n",
       "      <td>2453139.5</td>\n",
       "      <td>2300</td>\n",
       "      <td>2003</td>\n",
       "      <td>10</td>\n",
       "      <td>2003-05-14 21:20:00</td>\n",
       "      <td>2004-05-14 23:00:00</td>\n",
       "      <td>366 days 01:40:00</td>\n",
       "      <td>8786</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>288931</th>\n",
       "      <td>291193</td>\n",
       "      <td>RALSTON</td>\n",
       "      <td>3</td>\n",
       "      <td>Miscellaneous</td>\n",
       "      <td>9.0</td>\n",
       "      <td>OK</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-96.752800</td>\n",
       "      <td>36.507800</td>\n",
       "      <td>2453385.5</td>\n",
       "      <td>1215</td>\n",
       "      <td>2453750.5</td>\n",
       "      <td>1330</td>\n",
       "      <td>2005</td>\n",
       "      <td>19</td>\n",
       "      <td>2005-01-15 12:15:00</td>\n",
       "      <td>2006-01-15 13:30:00</td>\n",
       "      <td>365 days 01:15:00</td>\n",
       "      <td>8761</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>512944</th>\n",
       "      <td>1286206</td>\n",
       "      <td>ADON ROAD</td>\n",
       "      <td>3</td>\n",
       "      <td>Lightning</td>\n",
       "      <td>1.0</td>\n",
       "      <td>WY</td>\n",
       "      <td>Campbell</td>\n",
       "      <td>-105.276150</td>\n",
       "      <td>44.454340</td>\n",
       "      <td>2455430.5</td>\n",
       "      <td>2059</td>\n",
       "      <td>2455804.5</td>\n",
       "      <td>2059</td>\n",
       "      <td>2010</td>\n",
       "      <td>4</td>\n",
       "      <td>2010-08-22 20:59:00</td>\n",
       "      <td>2011-08-31 20:59:00</td>\n",
       "      <td>374 days 00:00:00</td>\n",
       "      <td>8976</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>359258</th>\n",
       "      <td>365024</td>\n",
       "      <td>2100 CENTE</td>\n",
       "      <td>3</td>\n",
       "      <td>Miscellaneous</td>\n",
       "      <td>9.0</td>\n",
       "      <td>IN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-85.423200</td>\n",
       "      <td>38.937900</td>\n",
       "      <td>2452004.5</td>\n",
       "      <td>1300</td>\n",
       "      <td>2452379.5</td>\n",
       "      <td>1200</td>\n",
       "      <td>2001</td>\n",
       "      <td>26</td>\n",
       "      <td>2001-04-05 13:00:00</td>\n",
       "      <td>2002-04-15 12:00:00</td>\n",
       "      <td>374 days 23:00:00</td>\n",
       "      <td>8999</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>507286</th>\n",
       "      <td>1276621</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3</td>\n",
       "      <td>Debris Burning</td>\n",
       "      <td>5.0</td>\n",
       "      <td>PA</td>\n",
       "      <td>FAYETTE</td>\n",
       "      <td>-79.827778</td>\n",
       "      <td>40.017222</td>\n",
       "      <td>2452352.5</td>\n",
       "      <td>1007</td>\n",
       "      <td>2453448.5</td>\n",
       "      <td>1007</td>\n",
       "      <td>2002</td>\n",
       "      <td>37</td>\n",
       "      <td>2002-03-19 10:07:00</td>\n",
       "      <td>2005-03-19 10:07:00</td>\n",
       "      <td>1096 days 00:00:00</td>\n",
       "      <td>26304</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>416614</th>\n",
       "      <td>1063028</td>\n",
       "      <td>FOOT</td>\n",
       "      <td>3</td>\n",
       "      <td>Miscellaneous</td>\n",
       "      <td>9.0</td>\n",
       "      <td>CA</td>\n",
       "      <td>63</td>\n",
       "      <td>-121.052500</td>\n",
       "      <td>39.803889</td>\n",
       "      <td>2453557.5</td>\n",
       "      <td>1638</td>\n",
       "      <td>2453928.5</td>\n",
       "      <td>1800</td>\n",
       "      <td>2005</td>\n",
       "      <td>0</td>\n",
       "      <td>2005-07-06 16:38:00</td>\n",
       "      <td>2006-07-12 18:00:00</td>\n",
       "      <td>371 days 01:22:00</td>\n",
       "      <td>8905</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>468934</th>\n",
       "      <td>1234308</td>\n",
       "      <td>EARLY MORNING</td>\n",
       "      <td>3</td>\n",
       "      <td>Missing/Undefined</td>\n",
       "      <td>13.0</td>\n",
       "      <td>AZ</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-109.923000</td>\n",
       "      <td>31.970500</td>\n",
       "      <td>2454581.5</td>\n",
       "      <td>217</td>\n",
       "      <td>2454946.5</td>\n",
       "      <td>217</td>\n",
       "      <td>2008</td>\n",
       "      <td>9</td>\n",
       "      <td>2008-04-25 02:17:00</td>\n",
       "      <td>2009-04-25 02:17:00</td>\n",
       "      <td>365 days 00:00:00</td>\n",
       "      <td>8760</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>708514</th>\n",
       "      <td>1579610</td>\n",
       "      <td>BIRCH CREEK</td>\n",
       "      <td>4</td>\n",
       "      <td>Missing/Undefined</td>\n",
       "      <td>13.0</td>\n",
       "      <td>OR</td>\n",
       "      <td>Malheur</td>\n",
       "      <td>-117.290000</td>\n",
       "      <td>44.322200</td>\n",
       "      <td>2456090.5</td>\n",
       "      <td>1756</td>\n",
       "      <td>2456456.5</td>\n",
       "      <td>1830</td>\n",
       "      <td>2012</td>\n",
       "      <td>2</td>\n",
       "      <td>2012-06-12 17:56:00</td>\n",
       "      <td>2013-06-13 18:30:00</td>\n",
       "      <td>366 days 00:34:00</td>\n",
       "      <td>8785</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>549414</th>\n",
       "      <td>1324066</td>\n",
       "      <td>JIMS BRANCH</td>\n",
       "      <td>4</td>\n",
       "      <td>Arson</td>\n",
       "      <td>7.0</td>\n",
       "      <td>WV</td>\n",
       "      <td>Wyoming</td>\n",
       "      <td>-81.349864</td>\n",
       "      <td>37.511007</td>\n",
       "      <td>2449661.5</td>\n",
       "      <td>1310</td>\n",
       "      <td>2450393.5</td>\n",
       "      <td>1310</td>\n",
       "      <td>1994</td>\n",
       "      <td>33</td>\n",
       "      <td>1994-11-05 13:10:00</td>\n",
       "      <td>1996-11-06 13:10:00</td>\n",
       "      <td>732 days 00:00:00</td>\n",
       "      <td>17568</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>465662</th>\n",
       "      <td>1227849</td>\n",
       "      <td>30305</td>\n",
       "      <td>4</td>\n",
       "      <td>Arson</td>\n",
       "      <td>7.0</td>\n",
       "      <td>OK</td>\n",
       "      <td>Adair</td>\n",
       "      <td>-94.743133</td>\n",
       "      <td>36.035600</td>\n",
       "      <td>2452723.5</td>\n",
       "      <td>1400</td>\n",
       "      <td>2453454.5</td>\n",
       "      <td>1400</td>\n",
       "      <td>2003</td>\n",
       "      <td>19</td>\n",
       "      <td>2003-03-25 14:00:00</td>\n",
       "      <td>2005-03-25 14:00:00</td>\n",
       "      <td>731 days 00:00:00</td>\n",
       "      <td>17544</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>455084</th>\n",
       "      <td>1210677</td>\n",
       "      <td>NE 30495</td>\n",
       "      <td>4</td>\n",
       "      <td>Arson</td>\n",
       "      <td>7.0</td>\n",
       "      <td>OK</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-94.898000</td>\n",
       "      <td>36.284700</td>\n",
       "      <td>2455501.5</td>\n",
       "      <td>710</td>\n",
       "      <td>2455866.5</td>\n",
       "      <td>1210</td>\n",
       "      <td>2010</td>\n",
       "      <td>19</td>\n",
       "      <td>2010-11-01 07:10:00</td>\n",
       "      <td>2011-11-01 12:10:00</td>\n",
       "      <td>365 days 05:00:00</td>\n",
       "      <td>8765</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>413299</th>\n",
       "      <td>1059663</td>\n",
       "      <td>INDIAN RUN</td>\n",
       "      <td>4</td>\n",
       "      <td>Miscellaneous</td>\n",
       "      <td>9.0</td>\n",
       "      <td>CO</td>\n",
       "      <td>107</td>\n",
       "      <td>-107.408333</td>\n",
       "      <td>40.284167</td>\n",
       "      <td>2454741.5</td>\n",
       "      <td>1700</td>\n",
       "      <td>2455107.5</td>\n",
       "      <td>1200</td>\n",
       "      <td>2008</td>\n",
       "      <td>5</td>\n",
       "      <td>2008-10-02 17:00:00</td>\n",
       "      <td>2009-10-03 12:00:00</td>\n",
       "      <td>365 days 19:00:00</td>\n",
       "      <td>8779</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>352731</th>\n",
       "      <td>356156</td>\n",
       "      <td>BUENAVISTA</td>\n",
       "      <td>4</td>\n",
       "      <td>Lightning</td>\n",
       "      <td>1.0</td>\n",
       "      <td>CA</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-119.522800</td>\n",
       "      <td>37.658900</td>\n",
       "      <td>2451763.5</td>\n",
       "      <td>1600</td>\n",
       "      <td>2453644.5</td>\n",
       "      <td>1800</td>\n",
       "      <td>2000</td>\n",
       "      <td>0</td>\n",
       "      <td>2000-08-07 16:00:00</td>\n",
       "      <td>2005-10-01 18:00:00</td>\n",
       "      <td>1881 days 02:00:00</td>\n",
       "      <td>45146</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>302770</th>\n",
       "      <td>305237</td>\n",
       "      <td>KILIOVILIK</td>\n",
       "      <td>4</td>\n",
       "      <td>Lightning</td>\n",
       "      <td>1.0</td>\n",
       "      <td>AK</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-157.519400</td>\n",
       "      <td>66.566100</td>\n",
       "      <td>2452071.5</td>\n",
       "      <td>2010</td>\n",
       "      <td>2453172.5</td>\n",
       "      <td>1719</td>\n",
       "      <td>2001</td>\n",
       "      <td>31</td>\n",
       "      <td>2001-06-11 20:10:00</td>\n",
       "      <td>2004-06-16 17:19:00</td>\n",
       "      <td>1100 days 21:09:00</td>\n",
       "      <td>26421</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>708515</th>\n",
       "      <td>1579611</td>\n",
       "      <td>SKULL</td>\n",
       "      <td>4</td>\n",
       "      <td>Lightning</td>\n",
       "      <td>1.0</td>\n",
       "      <td>OR</td>\n",
       "      <td>Malheur</td>\n",
       "      <td>-117.838110</td>\n",
       "      <td>43.478810</td>\n",
       "      <td>2456162.5</td>\n",
       "      <td>1231</td>\n",
       "      <td>2456528.5</td>\n",
       "      <td>1850</td>\n",
       "      <td>2012</td>\n",
       "      <td>2</td>\n",
       "      <td>2012-08-23 12:31:00</td>\n",
       "      <td>2013-08-24 18:50:00</td>\n",
       "      <td>366 days 06:19:00</td>\n",
       "      <td>8790</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>353877</th>\n",
       "      <td>357487</td>\n",
       "      <td>ROAD 09-08 WF</td>\n",
       "      <td>5</td>\n",
       "      <td>Arson</td>\n",
       "      <td>7.0</td>\n",
       "      <td>AL</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-85.597800</td>\n",
       "      <td>34.449700</td>\n",
       "      <td>2453799.5</td>\n",
       "      <td>1145</td>\n",
       "      <td>2454534.5</td>\n",
       "      <td>1400</td>\n",
       "      <td>2006</td>\n",
       "      <td>35</td>\n",
       "      <td>2006-03-05 11:45:00</td>\n",
       "      <td>2008-03-09 14:00:00</td>\n",
       "      <td>735 days 02:15:00</td>\n",
       "      <td>17642</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>512976</th>\n",
       "      <td>1286272</td>\n",
       "      <td>THUNDER</td>\n",
       "      <td>5</td>\n",
       "      <td>Miscellaneous</td>\n",
       "      <td>9.0</td>\n",
       "      <td>WY</td>\n",
       "      <td>Campbell</td>\n",
       "      <td>-105.264870</td>\n",
       "      <td>43.740000</td>\n",
       "      <td>2455427.5</td>\n",
       "      <td>1345</td>\n",
       "      <td>2455796.5</td>\n",
       "      <td>1741</td>\n",
       "      <td>2010</td>\n",
       "      <td>4</td>\n",
       "      <td>2010-08-19 13:45:00</td>\n",
       "      <td>2011-08-23 17:41:00</td>\n",
       "      <td>369 days 03:56:00</td>\n",
       "      <td>8860</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>579673</th>\n",
       "      <td>1360116</td>\n",
       "      <td>COAL CREEK</td>\n",
       "      <td>5</td>\n",
       "      <td>Missing/Undefined</td>\n",
       "      <td>13.0</td>\n",
       "      <td>OK</td>\n",
       "      <td>Leflore</td>\n",
       "      <td>-94.866111</td>\n",
       "      <td>34.940000</td>\n",
       "      <td>2454486.5</td>\n",
       "      <td>1358</td>\n",
       "      <td>2454854.5</td>\n",
       "      <td>830</td>\n",
       "      <td>2008</td>\n",
       "      <td>19</td>\n",
       "      <td>2008-01-21 13:58:00</td>\n",
       "      <td>2009-01-23 08:30:00</td>\n",
       "      <td>367 days 18:32:00</td>\n",
       "      <td>8827</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>708588</th>\n",
       "      <td>1579684</td>\n",
       "      <td>HOPEWELL</td>\n",
       "      <td>5</td>\n",
       "      <td>Missing/Undefined</td>\n",
       "      <td>13.0</td>\n",
       "      <td>PA</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-75.761400</td>\n",
       "      <td>40.213300</td>\n",
       "      <td>2456026.5</td>\n",
       "      <td>1228</td>\n",
       "      <td>2456396.5</td>\n",
       "      <td>1700</td>\n",
       "      <td>2012</td>\n",
       "      <td>37</td>\n",
       "      <td>2012-04-09 12:28:00</td>\n",
       "      <td>2013-04-14 17:00:00</td>\n",
       "      <td>370 days 04:32:00</td>\n",
       "      <td>8885</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>701530</th>\n",
       "      <td>1572579</td>\n",
       "      <td>SIXTEEN COMPLEX</td>\n",
       "      <td>7</td>\n",
       "      <td>Arson</td>\n",
       "      <td>7.0</td>\n",
       "      <td>CA</td>\n",
       "      <td>Colusa</td>\n",
       "      <td>-122.344500</td>\n",
       "      <td>38.944440</td>\n",
       "      <td>2456174.5</td>\n",
       "      <td>345</td>\n",
       "      <td>2456545.5</td>\n",
       "      <td>1800</td>\n",
       "      <td>2012</td>\n",
       "      <td>0</td>\n",
       "      <td>2012-09-04 03:45:00</td>\n",
       "      <td>2013-09-10 18:00:00</td>\n",
       "      <td>371 days 14:15:00</td>\n",
       "      <td>8918</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        Unnamed: 0        FIRE_NAME  FIRE_SIZE_CLASS   STAT_CAUSE_DESCR  \\\n",
       "182280      182647              ML5                3           Children   \n",
       "254190      256371           TRACKS                3              Arson   \n",
       "288931      291193          RALSTON                3      Miscellaneous   \n",
       "512944     1286206        ADON ROAD                3          Lightning   \n",
       "359258      365024       2100 CENTE                3      Miscellaneous   \n",
       "507286     1276621              NaN                3     Debris Burning   \n",
       "416614     1063028             FOOT                3      Miscellaneous   \n",
       "468934     1234308    EARLY MORNING                3  Missing/Undefined   \n",
       "708514     1579610      BIRCH CREEK                4  Missing/Undefined   \n",
       "549414     1324066      JIMS BRANCH                4              Arson   \n",
       "465662     1227849            30305                4              Arson   \n",
       "455084     1210677         NE 30495                4              Arson   \n",
       "413299     1059663       INDIAN RUN                4      Miscellaneous   \n",
       "352731      356156       BUENAVISTA                4          Lightning   \n",
       "302770      305237       KILIOVILIK                4          Lightning   \n",
       "708515     1579611            SKULL                4          Lightning   \n",
       "353877      357487    ROAD 09-08 WF                5              Arson   \n",
       "512976     1286272          THUNDER                5      Miscellaneous   \n",
       "579673     1360116       COAL CREEK                5  Missing/Undefined   \n",
       "708588     1579684         HOPEWELL                5  Missing/Undefined   \n",
       "701530     1572579  SIXTEEN COMPLEX                7              Arson   \n",
       "\n",
       "        STAT_CAUSE_CODE STATE    COUNTY   LONGITUDE   LATITUDE  \\\n",
       "182280              8.0    MN       NaN  -93.765300  46.212700   \n",
       "254190              7.0    SD       NaN -100.540700  45.670000   \n",
       "288931              9.0    OK       NaN  -96.752800  36.507800   \n",
       "512944              1.0    WY  Campbell -105.276150  44.454340   \n",
       "359258              9.0    IN       NaN  -85.423200  38.937900   \n",
       "507286              5.0    PA   FAYETTE  -79.827778  40.017222   \n",
       "416614              9.0    CA        63 -121.052500  39.803889   \n",
       "468934             13.0    AZ       NaN -109.923000  31.970500   \n",
       "708514             13.0    OR   Malheur -117.290000  44.322200   \n",
       "549414              7.0    WV   Wyoming  -81.349864  37.511007   \n",
       "465662              7.0    OK     Adair  -94.743133  36.035600   \n",
       "455084              7.0    OK       NaN  -94.898000  36.284700   \n",
       "413299              9.0    CO       107 -107.408333  40.284167   \n",
       "352731              1.0    CA       NaN -119.522800  37.658900   \n",
       "302770              1.0    AK       NaN -157.519400  66.566100   \n",
       "708515              1.0    OR   Malheur -117.838110  43.478810   \n",
       "353877              7.0    AL       NaN  -85.597800  34.449700   \n",
       "512976              9.0    WY  Campbell -105.264870  43.740000   \n",
       "579673             13.0    OK   Leflore  -94.866111  34.940000   \n",
       "708588             13.0    PA       NaN  -75.761400  40.213300   \n",
       "701530              7.0    CA    Colusa -122.344500  38.944440   \n",
       "\n",
       "        DISCOVERY_DATE  DISCOVERY_TIME  CONT_DATE  CONT_TIME  FIRE_YEAR  \\\n",
       "182280       2449480.5            1450  2449845.5       1600       1994   \n",
       "254190       2452773.5            2120  2453139.5       2300       2003   \n",
       "288931       2453385.5            1215  2453750.5       1330       2005   \n",
       "512944       2455430.5            2059  2455804.5       2059       2010   \n",
       "359258       2452004.5            1300  2452379.5       1200       2001   \n",
       "507286       2452352.5            1007  2453448.5       1007       2002   \n",
       "416614       2453557.5            1638  2453928.5       1800       2005   \n",
       "468934       2454581.5             217  2454946.5        217       2008   \n",
       "708514       2456090.5            1756  2456456.5       1830       2012   \n",
       "549414       2449661.5            1310  2450393.5       1310       1994   \n",
       "465662       2452723.5            1400  2453454.5       1400       2003   \n",
       "455084       2455501.5             710  2455866.5       1210       2010   \n",
       "413299       2454741.5            1700  2455107.5       1200       2008   \n",
       "352731       2451763.5            1600  2453644.5       1800       2000   \n",
       "302770       2452071.5            2010  2453172.5       1719       2001   \n",
       "708515       2456162.5            1231  2456528.5       1850       2012   \n",
       "353877       2453799.5            1145  2454534.5       1400       2006   \n",
       "512976       2455427.5            1345  2455796.5       1741       2010   \n",
       "579673       2454486.5            1358  2454854.5        830       2008   \n",
       "708588       2456026.5            1228  2456396.5       1700       2012   \n",
       "701530       2456174.5             345  2456545.5       1800       2012   \n",
       "\n",
       "        STATE_CODE  DISCOVERY_DATETIME       CONT_DATETIME       TIME_TO_CONT  \\\n",
       "182280          14 1994-05-08 14:50:00 1995-05-08 16:00:00  365 days 01:10:00   \n",
       "254190          10 2003-05-14 21:20:00 2004-05-14 23:00:00  366 days 01:40:00   \n",
       "288931          19 2005-01-15 12:15:00 2006-01-15 13:30:00  365 days 01:15:00   \n",
       "512944           4 2010-08-22 20:59:00 2011-08-31 20:59:00  374 days 00:00:00   \n",
       "359258          26 2001-04-05 13:00:00 2002-04-15 12:00:00  374 days 23:00:00   \n",
       "507286          37 2002-03-19 10:07:00 2005-03-19 10:07:00 1096 days 00:00:00   \n",
       "416614           0 2005-07-06 16:38:00 2006-07-12 18:00:00  371 days 01:22:00   \n",
       "468934           9 2008-04-25 02:17:00 2009-04-25 02:17:00  365 days 00:00:00   \n",
       "708514           2 2012-06-12 17:56:00 2013-06-13 18:30:00  366 days 00:34:00   \n",
       "549414          33 1994-11-05 13:10:00 1996-11-06 13:10:00  732 days 00:00:00   \n",
       "465662          19 2003-03-25 14:00:00 2005-03-25 14:00:00  731 days 00:00:00   \n",
       "455084          19 2010-11-01 07:10:00 2011-11-01 12:10:00  365 days 05:00:00   \n",
       "413299           5 2008-10-02 17:00:00 2009-10-03 12:00:00  365 days 19:00:00   \n",
       "352731           0 2000-08-07 16:00:00 2005-10-01 18:00:00 1881 days 02:00:00   \n",
       "302770          31 2001-06-11 20:10:00 2004-06-16 17:19:00 1100 days 21:09:00   \n",
       "708515           2 2012-08-23 12:31:00 2013-08-24 18:50:00  366 days 06:19:00   \n",
       "353877          35 2006-03-05 11:45:00 2008-03-09 14:00:00  735 days 02:15:00   \n",
       "512976           4 2010-08-19 13:45:00 2011-08-23 17:41:00  369 days 03:56:00   \n",
       "579673          19 2008-01-21 13:58:00 2009-01-23 08:30:00  367 days 18:32:00   \n",
       "708588          37 2012-04-09 12:28:00 2013-04-14 17:00:00  370 days 04:32:00   \n",
       "701530           0 2012-09-04 03:45:00 2013-09-10 18:00:00  371 days 14:15:00   \n",
       "\n",
       "        HOURS_TO_CONT  \n",
       "182280           8761  \n",
       "254190           8786  \n",
       "288931           8761  \n",
       "512944           8976  \n",
       "359258           8999  \n",
       "507286          26304  \n",
       "416614           8905  \n",
       "468934           8760  \n",
       "708514           8785  \n",
       "549414          17568  \n",
       "465662          17544  \n",
       "455084           8765  \n",
       "413299           8779  \n",
       "352731          45146  \n",
       "302770          26421  \n",
       "708515           8790  \n",
       "353877          17642  \n",
       "512976           8860  \n",
       "579673           8827  \n",
       "708588           8885  \n",
       "701530           8918  "
      ]
     },
     "execution_count": 111,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[(df.HOURS_TO_CONT > 8000) & (df.FIRE_SIZE_CLASS > 2)].sort_values(by='FIRE_SIZE_CLASS')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 112,
   "metadata": {},
   "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>Unnamed: 0</th>\n",
       "      <th>FIRE_NAME</th>\n",
       "      <th>FIRE_SIZE_CLASS</th>\n",
       "      <th>STAT_CAUSE_DESCR</th>\n",
       "      <th>STAT_CAUSE_CODE</th>\n",
       "      <th>STATE</th>\n",
       "      <th>COUNTY</th>\n",
       "      <th>LONGITUDE</th>\n",
       "      <th>LATITUDE</th>\n",
       "      <th>DISCOVERY_DATE</th>\n",
       "      <th>DISCOVERY_TIME</th>\n",
       "      <th>CONT_DATE</th>\n",
       "      <th>CONT_TIME</th>\n",
       "      <th>FIRE_YEAR</th>\n",
       "      <th>STATE_CODE</th>\n",
       "      <th>DISCOVERY_DATETIME</th>\n",
       "      <th>CONT_DATETIME</th>\n",
       "      <th>TIME_TO_CONT</th>\n",
       "      <th>HOURS_TO_CONT</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>25196</th>\n",
       "      <td>25280</td>\n",
       "      <td>DOMKE</td>\n",
       "      <td>7</td>\n",
       "      <td>Lightning</td>\n",
       "      <td>1.0</td>\n",
       "      <td>WA</td>\n",
       "      <td>7</td>\n",
       "      <td>-120.599444</td>\n",
       "      <td>48.167222</td>\n",
       "      <td>2454317.5</td>\n",
       "      <td>1900</td>\n",
       "      <td>2454472.5</td>\n",
       "      <td>900</td>\n",
       "      <td>2007</td>\n",
       "      <td>6</td>\n",
       "      <td>2007-08-05 19:00:00</td>\n",
       "      <td>2008-01-07 09:00:00</td>\n",
       "      <td>154 days 14:00:00</td>\n",
       "      <td>3710</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>34638</th>\n",
       "      <td>34763</td>\n",
       "      <td>LICK RUN</td>\n",
       "      <td>2</td>\n",
       "      <td>Lightning</td>\n",
       "      <td>1.0</td>\n",
       "      <td>VA</td>\n",
       "      <td>15</td>\n",
       "      <td>-79.146944</td>\n",
       "      <td>38.368611</td>\n",
       "      <td>2454583.5</td>\n",
       "      <td>1630</td>\n",
       "      <td>2454948.5</td>\n",
       "      <td>2100</td>\n",
       "      <td>2008</td>\n",
       "      <td>27</td>\n",
       "      <td>2008-04-27 16:30:00</td>\n",
       "      <td>2009-04-27 21:00:00</td>\n",
       "      <td>365 days 04:30:00</td>\n",
       "      <td>8764</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>48522</th>\n",
       "      <td>48658</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1</td>\n",
       "      <td>Lightning</td>\n",
       "      <td>1.0</td>\n",
       "      <td>CA</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-118.708333</td>\n",
       "      <td>36.295000</td>\n",
       "      <td>2448922.5</td>\n",
       "      <td>1800</td>\n",
       "      <td>2449287.5</td>\n",
       "      <td>1930</td>\n",
       "      <td>1992</td>\n",
       "      <td>0</td>\n",
       "      <td>1992-10-27 18:00:00</td>\n",
       "      <td>1993-10-27 19:30:00</td>\n",
       "      <td>365 days 01:30:00</td>\n",
       "      <td>8762</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>80627</th>\n",
       "      <td>80774</td>\n",
       "      <td>VICTORIA</td>\n",
       "      <td>1</td>\n",
       "      <td>Miscellaneous</td>\n",
       "      <td>9.0</td>\n",
       "      <td>CA</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-117.180000</td>\n",
       "      <td>34.243333</td>\n",
       "      <td>2449726.5</td>\n",
       "      <td>1409</td>\n",
       "      <td>2450091.5</td>\n",
       "      <td>1500</td>\n",
       "      <td>1995</td>\n",
       "      <td>0</td>\n",
       "      <td>1995-01-09 14:09:00</td>\n",
       "      <td>1996-01-09 15:00:00</td>\n",
       "      <td>365 days 00:51:00</td>\n",
       "      <td>8761</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>114195</th>\n",
       "      <td>114369</td>\n",
       "      <td>FREIDLEIN</td>\n",
       "      <td>2</td>\n",
       "      <td>Campfire</td>\n",
       "      <td>4.0</td>\n",
       "      <td>AZ</td>\n",
       "      <td>5</td>\n",
       "      <td>-111.691667</td>\n",
       "      <td>35.291667</td>\n",
       "      <td>2451530.5</td>\n",
       "      <td>950</td>\n",
       "      <td>2451547.5</td>\n",
       "      <td>1600</td>\n",
       "      <td>1999</td>\n",
       "      <td>9</td>\n",
       "      <td>1999-12-18 09:50:00</td>\n",
       "      <td>2000-01-04 16:00:00</td>\n",
       "      <td>17 days 06:10:00</td>\n",
       "      <td>414</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>114196</th>\n",
       "      <td>114370</td>\n",
       "      <td>LION</td>\n",
       "      <td>2</td>\n",
       "      <td>Miscellaneous</td>\n",
       "      <td>9.0</td>\n",
       "      <td>AZ</td>\n",
       "      <td>5</td>\n",
       "      <td>-111.713333</td>\n",
       "      <td>35.315000</td>\n",
       "      <td>2451535.5</td>\n",
       "      <td>700</td>\n",
       "      <td>2451547.5</td>\n",
       "      <td>1600</td>\n",
       "      <td>1999</td>\n",
       "      <td>9</td>\n",
       "      <td>1999-12-23 07:00:00</td>\n",
       "      <td>2000-01-04 16:00:00</td>\n",
       "      <td>12 days 09:00:00</td>\n",
       "      <td>297</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>131788</th>\n",
       "      <td>132006</td>\n",
       "      <td>LAVA BUTTE</td>\n",
       "      <td>5</td>\n",
       "      <td>Miscellaneous</td>\n",
       "      <td>9.0</td>\n",
       "      <td>CA</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-118.861944</td>\n",
       "      <td>36.782778</td>\n",
       "      <td>2451908.5</td>\n",
       "      <td>1500</td>\n",
       "      <td>2451917.5</td>\n",
       "      <td>1000</td>\n",
       "      <td>2000</td>\n",
       "      <td>0</td>\n",
       "      <td>2000-12-30 15:00:00</td>\n",
       "      <td>2001-01-08 10:00:00</td>\n",
       "      <td>8 days 19:00:00</td>\n",
       "      <td>211</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>132252</th>\n",
       "      <td>132471</td>\n",
       "      <td>WATTERMILL</td>\n",
       "      <td>1</td>\n",
       "      <td>Debris Burning</td>\n",
       "      <td>5.0</td>\n",
       "      <td>MI</td>\n",
       "      <td>85</td>\n",
       "      <td>-85.804167</td>\n",
       "      <td>43.863889</td>\n",
       "      <td>2451648.5</td>\n",
       "      <td>1658</td>\n",
       "      <td>2452378.5</td>\n",
       "      <td>1710</td>\n",
       "      <td>2000</td>\n",
       "      <td>23</td>\n",
       "      <td>2000-04-14 16:58:00</td>\n",
       "      <td>2002-04-14 17:10:00</td>\n",
       "      <td>730 days 00:12:00</td>\n",
       "      <td>17520</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>134128</th>\n",
       "      <td>134351</td>\n",
       "      <td>DECEMBER</td>\n",
       "      <td>4</td>\n",
       "      <td>Campfire</td>\n",
       "      <td>4.0</td>\n",
       "      <td>AZ</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-111.333889</td>\n",
       "      <td>34.417500</td>\n",
       "      <td>2451896.5</td>\n",
       "      <td>1400</td>\n",
       "      <td>2451914.5</td>\n",
       "      <td>1600</td>\n",
       "      <td>2000</td>\n",
       "      <td>9</td>\n",
       "      <td>2000-12-18 14:00:00</td>\n",
       "      <td>2001-01-05 16:00:00</td>\n",
       "      <td>18 days 02:00:00</td>\n",
       "      <td>434</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>134986</th>\n",
       "      <td>135209</td>\n",
       "      <td>SHANKS GULCH</td>\n",
       "      <td>1</td>\n",
       "      <td>Miscellaneous</td>\n",
       "      <td>9.0</td>\n",
       "      <td>SD</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-103.383333</td>\n",
       "      <td>44.060000</td>\n",
       "      <td>2451916.5</td>\n",
       "      <td>2002</td>\n",
       "      <td>2452282.5</td>\n",
       "      <td>36</td>\n",
       "      <td>2001</td>\n",
       "      <td>10</td>\n",
       "      <td>2001-01-07 20:02:00</td>\n",
       "      <td>2002-01-08 00:36:00</td>\n",
       "      <td>365 days 04:34:00</td>\n",
       "      <td>8765</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>151345</th>\n",
       "      <td>151618</td>\n",
       "      <td>CARP</td>\n",
       "      <td>1</td>\n",
       "      <td>Lightning</td>\n",
       "      <td>1.0</td>\n",
       "      <td>UT</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-111.527500</td>\n",
       "      <td>41.883056</td>\n",
       "      <td>2452500.5</td>\n",
       "      <td>1915</td>\n",
       "      <td>2452867.5</td>\n",
       "      <td>1800</td>\n",
       "      <td>2002</td>\n",
       "      <td>8</td>\n",
       "      <td>2002-08-14 19:15:00</td>\n",
       "      <td>2003-08-16 18:00:00</td>\n",
       "      <td>366 days 22:45:00</td>\n",
       "      <td>8807</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>156458</th>\n",
       "      <td>156750</td>\n",
       "      <td>COAL SEAM #4</td>\n",
       "      <td>1</td>\n",
       "      <td>Miscellaneous</td>\n",
       "      <td>9.0</td>\n",
       "      <td>MT</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-104.232222</td>\n",
       "      <td>45.610556</td>\n",
       "      <td>2452625.5</td>\n",
       "      <td>1400</td>\n",
       "      <td>2452653.5</td>\n",
       "      <td>1600</td>\n",
       "      <td>2002</td>\n",
       "      <td>7</td>\n",
       "      <td>2002-12-17 14:00:00</td>\n",
       "      <td>2003-01-14 16:00:00</td>\n",
       "      <td>28 days 02:00:00</td>\n",
       "      <td>674</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>164729</th>\n",
       "      <td>165052</td>\n",
       "      <td>ALPHA</td>\n",
       "      <td>2</td>\n",
       "      <td>Campfire</td>\n",
       "      <td>4.0</td>\n",
       "      <td>NM</td>\n",
       "      <td>3</td>\n",
       "      <td>-108.315278</td>\n",
       "      <td>33.387778</td>\n",
       "      <td>2452977.5</td>\n",
       "      <td>1315</td>\n",
       "      <td>2453026.5</td>\n",
       "      <td>800</td>\n",
       "      <td>2003</td>\n",
       "      <td>1</td>\n",
       "      <td>2003-12-04 13:15:00</td>\n",
       "      <td>2004-01-22 08:00:00</td>\n",
       "      <td>48 days 18:45:00</td>\n",
       "      <td>1171</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>182280</th>\n",
       "      <td>182647</td>\n",
       "      <td>ML5</td>\n",
       "      <td>3</td>\n",
       "      <td>Children</td>\n",
       "      <td>8.0</td>\n",
       "      <td>MN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-93.765300</td>\n",
       "      <td>46.212700</td>\n",
       "      <td>2449480.5</td>\n",
       "      <td>1450</td>\n",
       "      <td>2449845.5</td>\n",
       "      <td>1600</td>\n",
       "      <td>1994</td>\n",
       "      <td>14</td>\n",
       "      <td>1994-05-08 14:50:00</td>\n",
       "      <td>1995-05-08 16:00:00</td>\n",
       "      <td>365 days 01:10:00</td>\n",
       "      <td>8761</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>182283</th>\n",
       "      <td>182650</td>\n",
       "      <td>ML14</td>\n",
       "      <td>2</td>\n",
       "      <td>Debris Burning</td>\n",
       "      <td>5.0</td>\n",
       "      <td>MN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-92.887700</td>\n",
       "      <td>46.012500</td>\n",
       "      <td>2449491.5</td>\n",
       "      <td>1930</td>\n",
       "      <td>2449856.5</td>\n",
       "      <td>1955</td>\n",
       "      <td>1994</td>\n",
       "      <td>14</td>\n",
       "      <td>1994-05-19 19:30:00</td>\n",
       "      <td>1995-05-19 19:55:00</td>\n",
       "      <td>365 days 00:25:00</td>\n",
       "      <td>8760</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>185848</th>\n",
       "      <td>186216</td>\n",
       "      <td>HOCHUNK 3</td>\n",
       "      <td>1</td>\n",
       "      <td>Arson</td>\n",
       "      <td>7.0</td>\n",
       "      <td>WI</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-90.759900</td>\n",
       "      <td>44.349400</td>\n",
       "      <td>2451021.5</td>\n",
       "      <td>1205</td>\n",
       "      <td>2452482.5</td>\n",
       "      <td>1237</td>\n",
       "      <td>1998</td>\n",
       "      <td>34</td>\n",
       "      <td>1998-07-27 12:05:00</td>\n",
       "      <td>2002-07-27 12:37:00</td>\n",
       "      <td>1461 days 00:32:00</td>\n",
       "      <td>35065</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>216913</th>\n",
       "      <td>217383</td>\n",
       "      <td>BORDER 109</td>\n",
       "      <td>1</td>\n",
       "      <td>Miscellaneous</td>\n",
       "      <td>9.0</td>\n",
       "      <td>CA</td>\n",
       "      <td>San Diego</td>\n",
       "      <td>-116.698961</td>\n",
       "      <td>32.575669</td>\n",
       "      <td>2451156.5</td>\n",
       "      <td>945</td>\n",
       "      <td>2451179.5</td>\n",
       "      <td>1030</td>\n",
       "      <td>1998</td>\n",
       "      <td>0</td>\n",
       "      <td>1998-12-09 09:45:00</td>\n",
       "      <td>1999-01-01 10:30:00</td>\n",
       "      <td>23 days 00:45:00</td>\n",
       "      <td>553</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>231521</th>\n",
       "      <td>232104</td>\n",
       "      <td>COYOTE CR.</td>\n",
       "      <td>1</td>\n",
       "      <td>Lightning</td>\n",
       "      <td>1.0</td>\n",
       "      <td>OR</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-123.281800</td>\n",
       "      <td>43.805400</td>\n",
       "      <td>2449218.5</td>\n",
       "      <td>1215</td>\n",
       "      <td>2449583.5</td>\n",
       "      <td>1430</td>\n",
       "      <td>1993</td>\n",
       "      <td>2</td>\n",
       "      <td>1993-08-19 12:15:00</td>\n",
       "      <td>1994-08-19 14:30:00</td>\n",
       "      <td>365 days 02:15:00</td>\n",
       "      <td>8762</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>242661</th>\n",
       "      <td>244355</td>\n",
       "      <td>VET</td>\n",
       "      <td>3</td>\n",
       "      <td>Miscellaneous</td>\n",
       "      <td>9.0</td>\n",
       "      <td>HI</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-155.081700</td>\n",
       "      <td>19.317200</td>\n",
       "      <td>2449656.5</td>\n",
       "      <td>1130</td>\n",
       "      <td>2449720.5</td>\n",
       "      <td>800</td>\n",
       "      <td>1994</td>\n",
       "      <td>48</td>\n",
       "      <td>1994-10-31 11:30:00</td>\n",
       "      <td>1995-01-03 08:00:00</td>\n",
       "      <td>63 days 20:30:00</td>\n",
       "      <td>1532</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>248424</th>\n",
       "      <td>250579</td>\n",
       "      <td>PICKENS #3</td>\n",
       "      <td>2</td>\n",
       "      <td>Miscellaneous</td>\n",
       "      <td>9.0</td>\n",
       "      <td>OK</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-95.055300</td>\n",
       "      <td>34.430300</td>\n",
       "      <td>2453625.5</td>\n",
       "      <td>1710</td>\n",
       "      <td>2453990.5</td>\n",
       "      <td>2359</td>\n",
       "      <td>2005</td>\n",
       "      <td>19</td>\n",
       "      <td>2005-09-12 17:10:00</td>\n",
       "      <td>2006-09-12 23:59:00</td>\n",
       "      <td>365 days 06:49:00</td>\n",
       "      <td>8767</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>252307</th>\n",
       "      <td>254483</td>\n",
       "      <td>318</td>\n",
       "      <td>2</td>\n",
       "      <td>Arson</td>\n",
       "      <td>7.0</td>\n",
       "      <td>ND</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-98.846100</td>\n",
       "      <td>47.982200</td>\n",
       "      <td>2453494.5</td>\n",
       "      <td>1700</td>\n",
       "      <td>2453859.5</td>\n",
       "      <td>1800</td>\n",
       "      <td>2005</td>\n",
       "      <td>32</td>\n",
       "      <td>2005-05-04 17:00:00</td>\n",
       "      <td>2006-05-04 18:00:00</td>\n",
       "      <td>365 days 01:00:00</td>\n",
       "      <td>8761</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>254190</th>\n",
       "      <td>256371</td>\n",
       "      <td>TRACKS</td>\n",
       "      <td>3</td>\n",
       "      <td>Arson</td>\n",
       "      <td>7.0</td>\n",
       "      <td>SD</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-100.540700</td>\n",
       "      <td>45.670000</td>\n",
       "      <td>2452773.5</td>\n",
       "      <td>2120</td>\n",
       "      <td>2453139.5</td>\n",
       "      <td>2300</td>\n",
       "      <td>2003</td>\n",
       "      <td>10</td>\n",
       "      <td>2003-05-14 21:20:00</td>\n",
       "      <td>2004-05-14 23:00:00</td>\n",
       "      <td>366 days 01:40:00</td>\n",
       "      <td>8786</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>287466</th>\n",
       "      <td>289721</td>\n",
       "      <td>WHITEWOLF</td>\n",
       "      <td>2</td>\n",
       "      <td>Debris Burning</td>\n",
       "      <td>5.0</td>\n",
       "      <td>WY</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-108.771200</td>\n",
       "      <td>43.026600</td>\n",
       "      <td>2453612.5</td>\n",
       "      <td>1525</td>\n",
       "      <td>2454342.5</td>\n",
       "      <td>1730</td>\n",
       "      <td>2005</td>\n",
       "      <td>4</td>\n",
       "      <td>2005-08-30 15:25:00</td>\n",
       "      <td>2007-08-30 17:30:00</td>\n",
       "      <td>730 days 02:05:00</td>\n",
       "      <td>17522</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>288931</th>\n",
       "      <td>291193</td>\n",
       "      <td>RALSTON</td>\n",
       "      <td>3</td>\n",
       "      <td>Miscellaneous</td>\n",
       "      <td>9.0</td>\n",
       "      <td>OK</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-96.752800</td>\n",
       "      <td>36.507800</td>\n",
       "      <td>2453385.5</td>\n",
       "      <td>1215</td>\n",
       "      <td>2453750.5</td>\n",
       "      <td>1330</td>\n",
       "      <td>2005</td>\n",
       "      <td>19</td>\n",
       "      <td>2005-01-15 12:15:00</td>\n",
       "      <td>2006-01-15 13:30:00</td>\n",
       "      <td>365 days 01:15:00</td>\n",
       "      <td>8761</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>291926</th>\n",
       "      <td>294214</td>\n",
       "      <td>FOREST DRIVE</td>\n",
       "      <td>2</td>\n",
       "      <td>Miscellaneous</td>\n",
       "      <td>9.0</td>\n",
       "      <td>NM</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-105.746900</td>\n",
       "      <td>33.163400</td>\n",
       "      <td>2453901.5</td>\n",
       "      <td>1424</td>\n",
       "      <td>2454997.5</td>\n",
       "      <td>1920</td>\n",
       "      <td>2006</td>\n",
       "      <td>1</td>\n",
       "      <td>2006-06-15 14:24:00</td>\n",
       "      <td>2009-06-15 19:20:00</td>\n",
       "      <td>1096 days 04:56:00</td>\n",
       "      <td>26309</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>291927</th>\n",
       "      <td>294215</td>\n",
       "      <td>NAICHE</td>\n",
       "      <td>2</td>\n",
       "      <td>Miscellaneous</td>\n",
       "      <td>9.0</td>\n",
       "      <td>NM</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-105.734200</td>\n",
       "      <td>33.256500</td>\n",
       "      <td>2453901.5</td>\n",
       "      <td>1550</td>\n",
       "      <td>2454997.5</td>\n",
       "      <td>2129</td>\n",
       "      <td>2006</td>\n",
       "      <td>1</td>\n",
       "      <td>2006-06-15 15:50:00</td>\n",
       "      <td>2009-06-15 21:29:00</td>\n",
       "      <td>1096 days 05:39:00</td>\n",
       "      <td>26310</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>291928</th>\n",
       "      <td>294216</td>\n",
       "      <td>WHITETAIL SUMMIT</td>\n",
       "      <td>2</td>\n",
       "      <td>Miscellaneous</td>\n",
       "      <td>9.0</td>\n",
       "      <td>NM</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-105.613300</td>\n",
       "      <td>33.247000</td>\n",
       "      <td>2453909.5</td>\n",
       "      <td>1300</td>\n",
       "      <td>2455006.5</td>\n",
       "      <td>1153</td>\n",
       "      <td>2006</td>\n",
       "      <td>1</td>\n",
       "      <td>2006-06-23 13:00:00</td>\n",
       "      <td>2009-06-24 11:53:00</td>\n",
       "      <td>1096 days 22:53:00</td>\n",
       "      <td>26327</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>294005</th>\n",
       "      <td>296307</td>\n",
       "      <td>CANAL 2</td>\n",
       "      <td>2</td>\n",
       "      <td>Miscellaneous</td>\n",
       "      <td>9.0</td>\n",
       "      <td>AZ</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-114.289700</td>\n",
       "      <td>34.029700</td>\n",
       "      <td>2453728.5</td>\n",
       "      <td>2337</td>\n",
       "      <td>2453741.5</td>\n",
       "      <td>1530</td>\n",
       "      <td>2005</td>\n",
       "      <td>9</td>\n",
       "      <td>2005-12-24 23:37:00</td>\n",
       "      <td>2006-01-06 15:30:00</td>\n",
       "      <td>12 days 15:53:00</td>\n",
       "      <td>304</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>294048</th>\n",
       "      <td>296350</td>\n",
       "      <td>TRACTOR</td>\n",
       "      <td>2</td>\n",
       "      <td>Miscellaneous</td>\n",
       "      <td>9.0</td>\n",
       "      <td>AZ</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-114.516900</td>\n",
       "      <td>33.870300</td>\n",
       "      <td>2454093.5</td>\n",
       "      <td>826</td>\n",
       "      <td>2454103.5</td>\n",
       "      <td>1530</td>\n",
       "      <td>2006</td>\n",
       "      <td>9</td>\n",
       "      <td>2006-12-24 08:26:00</td>\n",
       "      <td>2007-01-03 15:30:00</td>\n",
       "      <td>10 days 07:04:00</td>\n",
       "      <td>247</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>296220</th>\n",
       "      <td>298607</td>\n",
       "      <td>AVENUE</td>\n",
       "      <td>1</td>\n",
       "      <td>Miscellaneous</td>\n",
       "      <td>9.0</td>\n",
       "      <td>CA</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-114.625000</td>\n",
       "      <td>32.730300</td>\n",
       "      <td>2453027.5</td>\n",
       "      <td>800</td>\n",
       "      <td>2453401.5</td>\n",
       "      <td>1600</td>\n",
       "      <td>2004</td>\n",
       "      <td>0</td>\n",
       "      <td>2004-01-23 08:00:00</td>\n",
       "      <td>2005-01-31 16:00:00</td>\n",
       "      <td>374 days 08:00:00</td>\n",
       "      <td>8984</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>701530</th>\n",
       "      <td>1572579</td>\n",
       "      <td>SIXTEEN COMPLEX</td>\n",
       "      <td>7</td>\n",
       "      <td>Arson</td>\n",
       "      <td>7.0</td>\n",
       "      <td>CA</td>\n",
       "      <td>Colusa</td>\n",
       "      <td>-122.344500</td>\n",
       "      <td>38.944440</td>\n",
       "      <td>2456174.5</td>\n",
       "      <td>345</td>\n",
       "      <td>2456545.5</td>\n",
       "      <td>1800</td>\n",
       "      <td>2012</td>\n",
       "      <td>0</td>\n",
       "      <td>2012-09-04 03:45:00</td>\n",
       "      <td>2013-09-10 18:00:00</td>\n",
       "      <td>371 days 14:15:00</td>\n",
       "      <td>8918</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>705567</th>\n",
       "      <td>1576636</td>\n",
       "      <td>ROCK II</td>\n",
       "      <td>2</td>\n",
       "      <td>Arson</td>\n",
       "      <td>7.0</td>\n",
       "      <td>ND</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-98.899700</td>\n",
       "      <td>47.988100</td>\n",
       "      <td>2456214.5</td>\n",
       "      <td>2130</td>\n",
       "      <td>2456579.5</td>\n",
       "      <td>2330</td>\n",
       "      <td>2012</td>\n",
       "      <td>32</td>\n",
       "      <td>2012-10-14 21:30:00</td>\n",
       "      <td>2013-10-14 23:30:00</td>\n",
       "      <td>365 days 02:00:00</td>\n",
       "      <td>8762</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>705571</th>\n",
       "      <td>1576640</td>\n",
       "      <td>GOLDEN ROAD</td>\n",
       "      <td>1</td>\n",
       "      <td>Arson</td>\n",
       "      <td>7.0</td>\n",
       "      <td>ND</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-98.899700</td>\n",
       "      <td>47.993600</td>\n",
       "      <td>2456225.5</td>\n",
       "      <td>1845</td>\n",
       "      <td>2456590.5</td>\n",
       "      <td>2045</td>\n",
       "      <td>2012</td>\n",
       "      <td>32</td>\n",
       "      <td>2012-10-25 18:45:00</td>\n",
       "      <td>2013-10-25 20:45:00</td>\n",
       "      <td>365 days 02:00:00</td>\n",
       "      <td>8762</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>706277</th>\n",
       "      <td>1577348</td>\n",
       "      <td>GLADE</td>\n",
       "      <td>1</td>\n",
       "      <td>Missing/Undefined</td>\n",
       "      <td>13.0</td>\n",
       "      <td>NM</td>\n",
       "      <td>San Juan</td>\n",
       "      <td>-108.150300</td>\n",
       "      <td>36.819700</td>\n",
       "      <td>2456264.5</td>\n",
       "      <td>1159</td>\n",
       "      <td>2456630.5</td>\n",
       "      <td>1500</td>\n",
       "      <td>2012</td>\n",
       "      <td>1</td>\n",
       "      <td>2012-12-03 11:59:00</td>\n",
       "      <td>2013-12-04 15:00:00</td>\n",
       "      <td>366 days 03:01:00</td>\n",
       "      <td>8787</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>708514</th>\n",
       "      <td>1579610</td>\n",
       "      <td>BIRCH CREEK</td>\n",
       "      <td>4</td>\n",
       "      <td>Missing/Undefined</td>\n",
       "      <td>13.0</td>\n",
       "      <td>OR</td>\n",
       "      <td>Malheur</td>\n",
       "      <td>-117.290000</td>\n",
       "      <td>44.322200</td>\n",
       "      <td>2456090.5</td>\n",
       "      <td>1756</td>\n",
       "      <td>2456456.5</td>\n",
       "      <td>1830</td>\n",
       "      <td>2012</td>\n",
       "      <td>2</td>\n",
       "      <td>2012-06-12 17:56:00</td>\n",
       "      <td>2013-06-13 18:30:00</td>\n",
       "      <td>366 days 00:34:00</td>\n",
       "      <td>8785</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>708515</th>\n",
       "      <td>1579611</td>\n",
       "      <td>SKULL</td>\n",
       "      <td>4</td>\n",
       "      <td>Lightning</td>\n",
       "      <td>1.0</td>\n",
       "      <td>OR</td>\n",
       "      <td>Malheur</td>\n",
       "      <td>-117.838110</td>\n",
       "      <td>43.478810</td>\n",
       "      <td>2456162.5</td>\n",
       "      <td>1231</td>\n",
       "      <td>2456528.5</td>\n",
       "      <td>1850</td>\n",
       "      <td>2012</td>\n",
       "      <td>2</td>\n",
       "      <td>2012-08-23 12:31:00</td>\n",
       "      <td>2013-08-24 18:50:00</td>\n",
       "      <td>366 days 06:19:00</td>\n",
       "      <td>8790</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>708588</th>\n",
       "      <td>1579684</td>\n",
       "      <td>HOPEWELL</td>\n",
       "      <td>5</td>\n",
       "      <td>Missing/Undefined</td>\n",
       "      <td>13.0</td>\n",
       "      <td>PA</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-75.761400</td>\n",
       "      <td>40.213300</td>\n",
       "      <td>2456026.5</td>\n",
       "      <td>1228</td>\n",
       "      <td>2456396.5</td>\n",
       "      <td>1700</td>\n",
       "      <td>2012</td>\n",
       "      <td>37</td>\n",
       "      <td>2012-04-09 12:28:00</td>\n",
       "      <td>2013-04-14 17:00:00</td>\n",
       "      <td>370 days 04:32:00</td>\n",
       "      <td>8885</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>723294</th>\n",
       "      <td>1597193</td>\n",
       "      <td>SLEEPING PINE (11)</td>\n",
       "      <td>2</td>\n",
       "      <td>Campfire</td>\n",
       "      <td>4.0</td>\n",
       "      <td>FL</td>\n",
       "      <td>Collier</td>\n",
       "      <td>-81.537500</td>\n",
       "      <td>26.249000</td>\n",
       "      <td>2455928.5</td>\n",
       "      <td>932</td>\n",
       "      <td>2456294.5</td>\n",
       "      <td>1029</td>\n",
       "      <td>2012</td>\n",
       "      <td>16</td>\n",
       "      <td>2012-01-02 09:32:00</td>\n",
       "      <td>2013-01-02 10:29:00</td>\n",
       "      <td>366 days 00:57:00</td>\n",
       "      <td>8785</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>724261</th>\n",
       "      <td>1598307</td>\n",
       "      <td>JACKS DRAW</td>\n",
       "      <td>2</td>\n",
       "      <td>Lightning</td>\n",
       "      <td>1.0</td>\n",
       "      <td>WY</td>\n",
       "      <td>Albany</td>\n",
       "      <td>-105.380710</td>\n",
       "      <td>42.076180</td>\n",
       "      <td>2456132.5</td>\n",
       "      <td>1400</td>\n",
       "      <td>2456497.5</td>\n",
       "      <td>2000</td>\n",
       "      <td>2012</td>\n",
       "      <td>4</td>\n",
       "      <td>2012-07-24 14:00:00</td>\n",
       "      <td>2013-07-24 20:00:00</td>\n",
       "      <td>365 days 06:00:00</td>\n",
       "      <td>8766</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>729394</th>\n",
       "      <td>1608450</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1</td>\n",
       "      <td>Equipment Use</td>\n",
       "      <td>2.0</td>\n",
       "      <td>NJ</td>\n",
       "      <td>Camden</td>\n",
       "      <td>-74.535000</td>\n",
       "      <td>39.435000</td>\n",
       "      <td>2456283.5</td>\n",
       "      <td>1410</td>\n",
       "      <td>2456298.5</td>\n",
       "      <td>1200</td>\n",
       "      <td>2012</td>\n",
       "      <td>47</td>\n",
       "      <td>2012-12-22 14:10:00</td>\n",
       "      <td>2013-01-06 12:00:00</td>\n",
       "      <td>14 days 21:50:00</td>\n",
       "      <td>358</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>741821</th>\n",
       "      <td>1624828</td>\n",
       "      <td>10077</td>\n",
       "      <td>2</td>\n",
       "      <td>Equipment Use</td>\n",
       "      <td>2.0</td>\n",
       "      <td>OK</td>\n",
       "      <td>McCurtain</td>\n",
       "      <td>-95.038056</td>\n",
       "      <td>34.463056</td>\n",
       "      <td>2456083.5</td>\n",
       "      <td>1343</td>\n",
       "      <td>2456448.5</td>\n",
       "      <td>1512</td>\n",
       "      <td>2012</td>\n",
       "      <td>19</td>\n",
       "      <td>2012-06-05 13:43:00</td>\n",
       "      <td>2013-06-05 15:12:00</td>\n",
       "      <td>365 days 01:29:00</td>\n",
       "      <td>8761</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>790523</th>\n",
       "      <td>1723408</td>\n",
       "      <td>BARN</td>\n",
       "      <td>2</td>\n",
       "      <td>Debris Burning</td>\n",
       "      <td>5.0</td>\n",
       "      <td>OH</td>\n",
       "      <td>Lawrence</td>\n",
       "      <td>-82.721944</td>\n",
       "      <td>38.633056</td>\n",
       "      <td>2456970.5</td>\n",
       "      <td>1230</td>\n",
       "      <td>2457028.5</td>\n",
       "      <td>1330</td>\n",
       "      <td>2014</td>\n",
       "      <td>25</td>\n",
       "      <td>2014-11-09 12:30:00</td>\n",
       "      <td>2015-01-06 13:30:00</td>\n",
       "      <td>58 days 01:00:00</td>\n",
       "      <td>1393</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>794287</th>\n",
       "      <td>1727218</td>\n",
       "      <td>986</td>\n",
       "      <td>1</td>\n",
       "      <td>Campfire</td>\n",
       "      <td>4.0</td>\n",
       "      <td>OR</td>\n",
       "      <td>Crook</td>\n",
       "      <td>-120.339444</td>\n",
       "      <td>44.456944</td>\n",
       "      <td>2456962.5</td>\n",
       "      <td>1439</td>\n",
       "      <td>2457027.5</td>\n",
       "      <td>1146</td>\n",
       "      <td>2014</td>\n",
       "      <td>2</td>\n",
       "      <td>2014-11-01 14:39:00</td>\n",
       "      <td>2015-01-05 11:46:00</td>\n",
       "      <td>64 days 21:07:00</td>\n",
       "      <td>1557</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>796172</th>\n",
       "      <td>1729152</td>\n",
       "      <td>DMPTR 4</td>\n",
       "      <td>1</td>\n",
       "      <td>Arson</td>\n",
       "      <td>7.0</td>\n",
       "      <td>AK</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-146.996700</td>\n",
       "      <td>64.696700</td>\n",
       "      <td>2456773.5</td>\n",
       "      <td>2045</td>\n",
       "      <td>2457138.5</td>\n",
       "      <td>2330</td>\n",
       "      <td>2014</td>\n",
       "      <td>31</td>\n",
       "      <td>2014-04-26 20:45:00</td>\n",
       "      <td>2015-04-26 23:30:00</td>\n",
       "      <td>365 days 02:45:00</td>\n",
       "      <td>8763</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>796303</th>\n",
       "      <td>1729284</td>\n",
       "      <td>WALKER</td>\n",
       "      <td>6</td>\n",
       "      <td>Missing/Undefined</td>\n",
       "      <td>13.0</td>\n",
       "      <td>AZ</td>\n",
       "      <td>Yuma</td>\n",
       "      <td>-114.445600</td>\n",
       "      <td>32.855600</td>\n",
       "      <td>2457014.5</td>\n",
       "      <td>1711</td>\n",
       "      <td>2457037.5</td>\n",
       "      <td>600</td>\n",
       "      <td>2014</td>\n",
       "      <td>9</td>\n",
       "      <td>2014-12-23 17:11:00</td>\n",
       "      <td>2015-01-15 06:00:00</td>\n",
       "      <td>22 days 12:49:00</td>\n",
       "      <td>541</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>798854</th>\n",
       "      <td>1731848</td>\n",
       "      <td>CI</td>\n",
       "      <td>1</td>\n",
       "      <td>Debris Burning</td>\n",
       "      <td>5.0</td>\n",
       "      <td>MT</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-107.539500</td>\n",
       "      <td>45.715800</td>\n",
       "      <td>2456772.5</td>\n",
       "      <td>1853</td>\n",
       "      <td>2457137.5</td>\n",
       "      <td>1905</td>\n",
       "      <td>2014</td>\n",
       "      <td>7</td>\n",
       "      <td>2014-04-25 18:53:00</td>\n",
       "      <td>2015-04-25 19:05:00</td>\n",
       "      <td>365 days 00:12:00</td>\n",
       "      <td>8760</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>799851</th>\n",
       "      <td>1732845</td>\n",
       "      <td>OXBOW OVERLOOK 15</td>\n",
       "      <td>1</td>\n",
       "      <td>Miscellaneous</td>\n",
       "      <td>9.0</td>\n",
       "      <td>ND</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-103.429200</td>\n",
       "      <td>47.607200</td>\n",
       "      <td>2456931.5</td>\n",
       "      <td>1200</td>\n",
       "      <td>2457295.5</td>\n",
       "      <td>800</td>\n",
       "      <td>2014</td>\n",
       "      <td>32</td>\n",
       "      <td>2014-10-01 12:00:00</td>\n",
       "      <td>2015-09-30 08:00:00</td>\n",
       "      <td>363 days 20:00:00</td>\n",
       "      <td>8732</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>799852</th>\n",
       "      <td>1732846</td>\n",
       "      <td>GLACIER 15</td>\n",
       "      <td>1</td>\n",
       "      <td>Lightning</td>\n",
       "      <td>1.0</td>\n",
       "      <td>ND</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-103.430600</td>\n",
       "      <td>47.613900</td>\n",
       "      <td>2456931.5</td>\n",
       "      <td>1200</td>\n",
       "      <td>2457295.5</td>\n",
       "      <td>800</td>\n",
       "      <td>2014</td>\n",
       "      <td>32</td>\n",
       "      <td>2014-10-01 12:00:00</td>\n",
       "      <td>2015-09-30 08:00:00</td>\n",
       "      <td>363 days 20:00:00</td>\n",
       "      <td>8732</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>799853</th>\n",
       "      <td>1732847</td>\n",
       "      <td>COAL VEIN 15</td>\n",
       "      <td>2</td>\n",
       "      <td>Lightning</td>\n",
       "      <td>1.0</td>\n",
       "      <td>ND</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-103.390300</td>\n",
       "      <td>47.612800</td>\n",
       "      <td>2456931.5</td>\n",
       "      <td>1200</td>\n",
       "      <td>2457295.5</td>\n",
       "      <td>800</td>\n",
       "      <td>2014</td>\n",
       "      <td>32</td>\n",
       "      <td>2014-10-01 12:00:00</td>\n",
       "      <td>2015-09-30 08:00:00</td>\n",
       "      <td>363 days 20:00:00</td>\n",
       "      <td>8732</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>802912</th>\n",
       "      <td>1735914</td>\n",
       "      <td>GUNLOCK ROAD</td>\n",
       "      <td>2</td>\n",
       "      <td>Debris Burning</td>\n",
       "      <td>5.0</td>\n",
       "      <td>UT</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-113.780197</td>\n",
       "      <td>37.207100</td>\n",
       "      <td>2456673.5</td>\n",
       "      <td>32</td>\n",
       "      <td>2457039.5</td>\n",
       "      <td>1600</td>\n",
       "      <td>2014</td>\n",
       "      <td>8</td>\n",
       "      <td>2014-01-16 00:32:00</td>\n",
       "      <td>2015-01-17 16:00:00</td>\n",
       "      <td>366 days 15:28:00</td>\n",
       "      <td>8799</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>805521</th>\n",
       "      <td>1739206</td>\n",
       "      <td>GOLDEN HIKE</td>\n",
       "      <td>1</td>\n",
       "      <td>Lightning</td>\n",
       "      <td>1.0</td>\n",
       "      <td>WA</td>\n",
       "      <td>047</td>\n",
       "      <td>-120.127600</td>\n",
       "      <td>48.196800</td>\n",
       "      <td>2456852.5</td>\n",
       "      <td>1200</td>\n",
       "      <td>2457063.5</td>\n",
       "      <td>1200</td>\n",
       "      <td>2014</td>\n",
       "      <td>6</td>\n",
       "      <td>2014-07-14 12:00:00</td>\n",
       "      <td>2015-02-10 12:00:00</td>\n",
       "      <td>211 days 00:00:00</td>\n",
       "      <td>5064</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>805522</th>\n",
       "      <td>1739208</td>\n",
       "      <td>FRENCH CREEK</td>\n",
       "      <td>1</td>\n",
       "      <td>Lightning</td>\n",
       "      <td>1.0</td>\n",
       "      <td>WA</td>\n",
       "      <td>047</td>\n",
       "      <td>-120.009400</td>\n",
       "      <td>48.207600</td>\n",
       "      <td>2456853.5</td>\n",
       "      <td>1201</td>\n",
       "      <td>2457063.5</td>\n",
       "      <td>1200</td>\n",
       "      <td>2014</td>\n",
       "      <td>6</td>\n",
       "      <td>2014-07-15 12:01:00</td>\n",
       "      <td>2015-02-10 12:00:00</td>\n",
       "      <td>209 days 23:59:00</td>\n",
       "      <td>5040</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>808503</th>\n",
       "      <td>1743527</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1</td>\n",
       "      <td>Equipment Use</td>\n",
       "      <td>2.0</td>\n",
       "      <td>NJ</td>\n",
       "      <td>Monmouth</td>\n",
       "      <td>-74.325200</td>\n",
       "      <td>40.099800</td>\n",
       "      <td>2456983.5</td>\n",
       "      <td>1645</td>\n",
       "      <td>2457024.5</td>\n",
       "      <td>1000</td>\n",
       "      <td>2014</td>\n",
       "      <td>47</td>\n",
       "      <td>2014-11-22 16:45:00</td>\n",
       "      <td>2015-01-02 10:00:00</td>\n",
       "      <td>40 days 17:15:00</td>\n",
       "      <td>977</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>810920</th>\n",
       "      <td>1747767</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1</td>\n",
       "      <td>Campfire</td>\n",
       "      <td>4.0</td>\n",
       "      <td>NJ</td>\n",
       "      <td>Ocean</td>\n",
       "      <td>-74.270700</td>\n",
       "      <td>40.057000</td>\n",
       "      <td>2457012.5</td>\n",
       "      <td>1530</td>\n",
       "      <td>2457024.5</td>\n",
       "      <td>1000</td>\n",
       "      <td>2014</td>\n",
       "      <td>47</td>\n",
       "      <td>2014-12-21 15:30:00</td>\n",
       "      <td>2015-01-02 10:00:00</td>\n",
       "      <td>11 days 18:30:00</td>\n",
       "      <td>282</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>810921</th>\n",
       "      <td>1747769</td>\n",
       "      <td>WA-FA-001</td>\n",
       "      <td>1</td>\n",
       "      <td>Campfire</td>\n",
       "      <td>4.0</td>\n",
       "      <td>UT</td>\n",
       "      <td>WASHINGTON</td>\n",
       "      <td>-113.638745</td>\n",
       "      <td>37.088696</td>\n",
       "      <td>2456783.5</td>\n",
       "      <td>15</td>\n",
       "      <td>2457150.5</td>\n",
       "      <td>1640</td>\n",
       "      <td>2014</td>\n",
       "      <td>8</td>\n",
       "      <td>2014-05-06 00:15:00</td>\n",
       "      <td>2015-05-08 16:40:00</td>\n",
       "      <td>367 days 16:25:00</td>\n",
       "      <td>8824</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>834137</th>\n",
       "      <td>1782782</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1</td>\n",
       "      <td>Miscellaneous</td>\n",
       "      <td>9.0</td>\n",
       "      <td>NJ</td>\n",
       "      <td>Ocean</td>\n",
       "      <td>-74.275800</td>\n",
       "      <td>40.059000</td>\n",
       "      <td>2456982.5</td>\n",
       "      <td>1000</td>\n",
       "      <td>2457024.5</td>\n",
       "      <td>1000</td>\n",
       "      <td>2014</td>\n",
       "      <td>47</td>\n",
       "      <td>2014-11-21 10:00:00</td>\n",
       "      <td>2015-01-02 10:00:00</td>\n",
       "      <td>42 days 00:00:00</td>\n",
       "      <td>1008</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>834138</th>\n",
       "      <td>1782784</td>\n",
       "      <td>WC - 131</td>\n",
       "      <td>3</td>\n",
       "      <td>Miscellaneous</td>\n",
       "      <td>9.0</td>\n",
       "      <td>WA</td>\n",
       "      <td>045</td>\n",
       "      <td>-123.472000</td>\n",
       "      <td>47.309700</td>\n",
       "      <td>2456977.5</td>\n",
       "      <td>1830</td>\n",
       "      <td>2457045.5</td>\n",
       "      <td>1430</td>\n",
       "      <td>2014</td>\n",
       "      <td>6</td>\n",
       "      <td>2014-11-16 18:30:00</td>\n",
       "      <td>2015-01-23 14:30:00</td>\n",
       "      <td>67 days 20:00:00</td>\n",
       "      <td>1628</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>834139</th>\n",
       "      <td>1782785</td>\n",
       "      <td>WATSON ORCHARD</td>\n",
       "      <td>1</td>\n",
       "      <td>Miscellaneous</td>\n",
       "      <td>9.0</td>\n",
       "      <td>WA</td>\n",
       "      <td>047</td>\n",
       "      <td>-119.897600</td>\n",
       "      <td>48.067900</td>\n",
       "      <td>2456854.5</td>\n",
       "      <td>1200</td>\n",
       "      <td>2457063.5</td>\n",
       "      <td>1200</td>\n",
       "      <td>2014</td>\n",
       "      <td>6</td>\n",
       "      <td>2014-07-16 12:00:00</td>\n",
       "      <td>2015-02-10 12:00:00</td>\n",
       "      <td>209 days 00:00:00</td>\n",
       "      <td>5016</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>834140</th>\n",
       "      <td>1782786</td>\n",
       "      <td>RISING EAGLE ROAD</td>\n",
       "      <td>5</td>\n",
       "      <td>Miscellaneous</td>\n",
       "      <td>9.0</td>\n",
       "      <td>WA</td>\n",
       "      <td>047</td>\n",
       "      <td>-120.146000</td>\n",
       "      <td>48.412900</td>\n",
       "      <td>2456870.5</td>\n",
       "      <td>1345</td>\n",
       "      <td>2457063.5</td>\n",
       "      <td>1200</td>\n",
       "      <td>2014</td>\n",
       "      <td>6</td>\n",
       "      <td>2014-08-01 13:45:00</td>\n",
       "      <td>2015-02-10 12:00:00</td>\n",
       "      <td>192 days 22:15:00</td>\n",
       "      <td>4630</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>834141</th>\n",
       "      <td>1782787</td>\n",
       "      <td>MONTE CARLO</td>\n",
       "      <td>1</td>\n",
       "      <td>Miscellaneous</td>\n",
       "      <td>9.0</td>\n",
       "      <td>NV</td>\n",
       "      <td>Elko</td>\n",
       "      <td>-115.781791</td>\n",
       "      <td>40.850472</td>\n",
       "      <td>2456760.5</td>\n",
       "      <td>1548</td>\n",
       "      <td>2457157.5</td>\n",
       "      <td>1328</td>\n",
       "      <td>2014</td>\n",
       "      <td>12</td>\n",
       "      <td>2014-04-13 15:48:00</td>\n",
       "      <td>2015-05-15 13:28:00</td>\n",
       "      <td>396 days 21:40:00</td>\n",
       "      <td>9526</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>141 rows × 19 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        Unnamed: 0           FIRE_NAME  FIRE_SIZE_CLASS   STAT_CAUSE_DESCR  \\\n",
       "25196        25280               DOMKE                7          Lightning   \n",
       "34638        34763            LICK RUN                2          Lightning   \n",
       "48522        48658                 NaN                1          Lightning   \n",
       "80627        80774            VICTORIA                1      Miscellaneous   \n",
       "114195      114369           FREIDLEIN                2           Campfire   \n",
       "114196      114370                LION                2      Miscellaneous   \n",
       "131788      132006          LAVA BUTTE                5      Miscellaneous   \n",
       "132252      132471          WATTERMILL                1     Debris Burning   \n",
       "134128      134351            DECEMBER                4           Campfire   \n",
       "134986      135209        SHANKS GULCH                1      Miscellaneous   \n",
       "151345      151618                CARP                1          Lightning   \n",
       "156458      156750        COAL SEAM #4                1      Miscellaneous   \n",
       "164729      165052               ALPHA                2           Campfire   \n",
       "182280      182647                 ML5                3           Children   \n",
       "182283      182650                ML14                2     Debris Burning   \n",
       "185848      186216           HOCHUNK 3                1              Arson   \n",
       "216913      217383          BORDER 109                1      Miscellaneous   \n",
       "231521      232104          COYOTE CR.                1          Lightning   \n",
       "242661      244355                 VET                3      Miscellaneous   \n",
       "248424      250579          PICKENS #3                2      Miscellaneous   \n",
       "252307      254483                 318                2              Arson   \n",
       "254190      256371              TRACKS                3              Arson   \n",
       "287466      289721           WHITEWOLF                2     Debris Burning   \n",
       "288931      291193             RALSTON                3      Miscellaneous   \n",
       "291926      294214        FOREST DRIVE                2      Miscellaneous   \n",
       "291927      294215              NAICHE                2      Miscellaneous   \n",
       "291928      294216    WHITETAIL SUMMIT                2      Miscellaneous   \n",
       "294005      296307             CANAL 2                2      Miscellaneous   \n",
       "294048      296350             TRACTOR                2      Miscellaneous   \n",
       "296220      298607              AVENUE                1      Miscellaneous   \n",
       "...            ...                 ...              ...                ...   \n",
       "701530     1572579     SIXTEEN COMPLEX                7              Arson   \n",
       "705567     1576636             ROCK II                2              Arson   \n",
       "705571     1576640         GOLDEN ROAD                1              Arson   \n",
       "706277     1577348               GLADE                1  Missing/Undefined   \n",
       "708514     1579610         BIRCH CREEK                4  Missing/Undefined   \n",
       "708515     1579611               SKULL                4          Lightning   \n",
       "708588     1579684            HOPEWELL                5  Missing/Undefined   \n",
       "723294     1597193  SLEEPING PINE (11)                2           Campfire   \n",
       "724261     1598307          JACKS DRAW                2          Lightning   \n",
       "729394     1608450                 NaN                1      Equipment Use   \n",
       "741821     1624828               10077                2      Equipment Use   \n",
       "790523     1723408                BARN                2     Debris Burning   \n",
       "794287     1727218                 986                1           Campfire   \n",
       "796172     1729152             DMPTR 4                1              Arson   \n",
       "796303     1729284              WALKER                6  Missing/Undefined   \n",
       "798854     1731848                  CI                1     Debris Burning   \n",
       "799851     1732845   OXBOW OVERLOOK 15                1      Miscellaneous   \n",
       "799852     1732846          GLACIER 15                1          Lightning   \n",
       "799853     1732847        COAL VEIN 15                2          Lightning   \n",
       "802912     1735914        GUNLOCK ROAD                2     Debris Burning   \n",
       "805521     1739206         GOLDEN HIKE                1          Lightning   \n",
       "805522     1739208        FRENCH CREEK                1          Lightning   \n",
       "808503     1743527                 NaN                1      Equipment Use   \n",
       "810920     1747767                 NaN                1           Campfire   \n",
       "810921     1747769           WA-FA-001                1           Campfire   \n",
       "834137     1782782                 NaN                1      Miscellaneous   \n",
       "834138     1782784            WC - 131                3      Miscellaneous   \n",
       "834139     1782785      WATSON ORCHARD                1      Miscellaneous   \n",
       "834140     1782786   RISING EAGLE ROAD                5      Miscellaneous   \n",
       "834141     1782787         MONTE CARLO                1      Miscellaneous   \n",
       "\n",
       "        STAT_CAUSE_CODE STATE      COUNTY   LONGITUDE   LATITUDE  \\\n",
       "25196               1.0    WA           7 -120.599444  48.167222   \n",
       "34638               1.0    VA          15  -79.146944  38.368611   \n",
       "48522               1.0    CA         NaN -118.708333  36.295000   \n",
       "80627               9.0    CA         NaN -117.180000  34.243333   \n",
       "114195              4.0    AZ           5 -111.691667  35.291667   \n",
       "114196              9.0    AZ           5 -111.713333  35.315000   \n",
       "131788              9.0    CA         NaN -118.861944  36.782778   \n",
       "132252              5.0    MI          85  -85.804167  43.863889   \n",
       "134128              4.0    AZ         NaN -111.333889  34.417500   \n",
       "134986              9.0    SD         NaN -103.383333  44.060000   \n",
       "151345              1.0    UT         NaN -111.527500  41.883056   \n",
       "156458              9.0    MT         NaN -104.232222  45.610556   \n",
       "164729              4.0    NM           3 -108.315278  33.387778   \n",
       "182280              8.0    MN         NaN  -93.765300  46.212700   \n",
       "182283              5.0    MN         NaN  -92.887700  46.012500   \n",
       "185848              7.0    WI         NaN  -90.759900  44.349400   \n",
       "216913              9.0    CA   San Diego -116.698961  32.575669   \n",
       "231521              1.0    OR         NaN -123.281800  43.805400   \n",
       "242661              9.0    HI         NaN -155.081700  19.317200   \n",
       "248424              9.0    OK         NaN  -95.055300  34.430300   \n",
       "252307              7.0    ND         NaN  -98.846100  47.982200   \n",
       "254190              7.0    SD         NaN -100.540700  45.670000   \n",
       "287466              5.0    WY         NaN -108.771200  43.026600   \n",
       "288931              9.0    OK         NaN  -96.752800  36.507800   \n",
       "291926              9.0    NM         NaN -105.746900  33.163400   \n",
       "291927              9.0    NM         NaN -105.734200  33.256500   \n",
       "291928              9.0    NM         NaN -105.613300  33.247000   \n",
       "294005              9.0    AZ         NaN -114.289700  34.029700   \n",
       "294048              9.0    AZ         NaN -114.516900  33.870300   \n",
       "296220              9.0    CA         NaN -114.625000  32.730300   \n",
       "...                 ...   ...         ...         ...        ...   \n",
       "701530              7.0    CA      Colusa -122.344500  38.944440   \n",
       "705567              7.0    ND         NaN  -98.899700  47.988100   \n",
       "705571              7.0    ND         NaN  -98.899700  47.993600   \n",
       "706277             13.0    NM    San Juan -108.150300  36.819700   \n",
       "708514             13.0    OR     Malheur -117.290000  44.322200   \n",
       "708515              1.0    OR     Malheur -117.838110  43.478810   \n",
       "708588             13.0    PA         NaN  -75.761400  40.213300   \n",
       "723294              4.0    FL     Collier  -81.537500  26.249000   \n",
       "724261              1.0    WY      Albany -105.380710  42.076180   \n",
       "729394              2.0    NJ      Camden  -74.535000  39.435000   \n",
       "741821              2.0    OK   McCurtain  -95.038056  34.463056   \n",
       "790523              5.0    OH    Lawrence  -82.721944  38.633056   \n",
       "794287              4.0    OR       Crook -120.339444  44.456944   \n",
       "796172              7.0    AK         NaN -146.996700  64.696700   \n",
       "796303             13.0    AZ        Yuma -114.445600  32.855600   \n",
       "798854              5.0    MT         NaN -107.539500  45.715800   \n",
       "799851              9.0    ND         NaN -103.429200  47.607200   \n",
       "799852              1.0    ND         NaN -103.430600  47.613900   \n",
       "799853              1.0    ND         NaN -103.390300  47.612800   \n",
       "802912              5.0    UT         NaN -113.780197  37.207100   \n",
       "805521              1.0    WA         047 -120.127600  48.196800   \n",
       "805522              1.0    WA         047 -120.009400  48.207600   \n",
       "808503              2.0    NJ    Monmouth  -74.325200  40.099800   \n",
       "810920              4.0    NJ       Ocean  -74.270700  40.057000   \n",
       "810921              4.0    UT  WASHINGTON -113.638745  37.088696   \n",
       "834137              9.0    NJ       Ocean  -74.275800  40.059000   \n",
       "834138              9.0    WA         045 -123.472000  47.309700   \n",
       "834139              9.0    WA         047 -119.897600  48.067900   \n",
       "834140              9.0    WA         047 -120.146000  48.412900   \n",
       "834141              9.0    NV        Elko -115.781791  40.850472   \n",
       "\n",
       "        DISCOVERY_DATE  DISCOVERY_TIME  CONT_DATE  CONT_TIME  FIRE_YEAR  \\\n",
       "25196        2454317.5            1900  2454472.5        900       2007   \n",
       "34638        2454583.5            1630  2454948.5       2100       2008   \n",
       "48522        2448922.5            1800  2449287.5       1930       1992   \n",
       "80627        2449726.5            1409  2450091.5       1500       1995   \n",
       "114195       2451530.5             950  2451547.5       1600       1999   \n",
       "114196       2451535.5             700  2451547.5       1600       1999   \n",
       "131788       2451908.5            1500  2451917.5       1000       2000   \n",
       "132252       2451648.5            1658  2452378.5       1710       2000   \n",
       "134128       2451896.5            1400  2451914.5       1600       2000   \n",
       "134986       2451916.5            2002  2452282.5         36       2001   \n",
       "151345       2452500.5            1915  2452867.5       1800       2002   \n",
       "156458       2452625.5            1400  2452653.5       1600       2002   \n",
       "164729       2452977.5            1315  2453026.5        800       2003   \n",
       "182280       2449480.5            1450  2449845.5       1600       1994   \n",
       "182283       2449491.5            1930  2449856.5       1955       1994   \n",
       "185848       2451021.5            1205  2452482.5       1237       1998   \n",
       "216913       2451156.5             945  2451179.5       1030       1998   \n",
       "231521       2449218.5            1215  2449583.5       1430       1993   \n",
       "242661       2449656.5            1130  2449720.5        800       1994   \n",
       "248424       2453625.5            1710  2453990.5       2359       2005   \n",
       "252307       2453494.5            1700  2453859.5       1800       2005   \n",
       "254190       2452773.5            2120  2453139.5       2300       2003   \n",
       "287466       2453612.5            1525  2454342.5       1730       2005   \n",
       "288931       2453385.5            1215  2453750.5       1330       2005   \n",
       "291926       2453901.5            1424  2454997.5       1920       2006   \n",
       "291927       2453901.5            1550  2454997.5       2129       2006   \n",
       "291928       2453909.5            1300  2455006.5       1153       2006   \n",
       "294005       2453728.5            2337  2453741.5       1530       2005   \n",
       "294048       2454093.5             826  2454103.5       1530       2006   \n",
       "296220       2453027.5             800  2453401.5       1600       2004   \n",
       "...                ...             ...        ...        ...        ...   \n",
       "701530       2456174.5             345  2456545.5       1800       2012   \n",
       "705567       2456214.5            2130  2456579.5       2330       2012   \n",
       "705571       2456225.5            1845  2456590.5       2045       2012   \n",
       "706277       2456264.5            1159  2456630.5       1500       2012   \n",
       "708514       2456090.5            1756  2456456.5       1830       2012   \n",
       "708515       2456162.5            1231  2456528.5       1850       2012   \n",
       "708588       2456026.5            1228  2456396.5       1700       2012   \n",
       "723294       2455928.5             932  2456294.5       1029       2012   \n",
       "724261       2456132.5            1400  2456497.5       2000       2012   \n",
       "729394       2456283.5            1410  2456298.5       1200       2012   \n",
       "741821       2456083.5            1343  2456448.5       1512       2012   \n",
       "790523       2456970.5            1230  2457028.5       1330       2014   \n",
       "794287       2456962.5            1439  2457027.5       1146       2014   \n",
       "796172       2456773.5            2045  2457138.5       2330       2014   \n",
       "796303       2457014.5            1711  2457037.5        600       2014   \n",
       "798854       2456772.5            1853  2457137.5       1905       2014   \n",
       "799851       2456931.5            1200  2457295.5        800       2014   \n",
       "799852       2456931.5            1200  2457295.5        800       2014   \n",
       "799853       2456931.5            1200  2457295.5        800       2014   \n",
       "802912       2456673.5              32  2457039.5       1600       2014   \n",
       "805521       2456852.5            1200  2457063.5       1200       2014   \n",
       "805522       2456853.5            1201  2457063.5       1200       2014   \n",
       "808503       2456983.5            1645  2457024.5       1000       2014   \n",
       "810920       2457012.5            1530  2457024.5       1000       2014   \n",
       "810921       2456783.5              15  2457150.5       1640       2014   \n",
       "834137       2456982.5            1000  2457024.5       1000       2014   \n",
       "834138       2456977.5            1830  2457045.5       1430       2014   \n",
       "834139       2456854.5            1200  2457063.5       1200       2014   \n",
       "834140       2456870.5            1345  2457063.5       1200       2014   \n",
       "834141       2456760.5            1548  2457157.5       1328       2014   \n",
       "\n",
       "        STATE_CODE  DISCOVERY_DATETIME       CONT_DATETIME       TIME_TO_CONT  \\\n",
       "25196            6 2007-08-05 19:00:00 2008-01-07 09:00:00  154 days 14:00:00   \n",
       "34638           27 2008-04-27 16:30:00 2009-04-27 21:00:00  365 days 04:30:00   \n",
       "48522            0 1992-10-27 18:00:00 1993-10-27 19:30:00  365 days 01:30:00   \n",
       "80627            0 1995-01-09 14:09:00 1996-01-09 15:00:00  365 days 00:51:00   \n",
       "114195           9 1999-12-18 09:50:00 2000-01-04 16:00:00   17 days 06:10:00   \n",
       "114196           9 1999-12-23 07:00:00 2000-01-04 16:00:00   12 days 09:00:00   \n",
       "131788           0 2000-12-30 15:00:00 2001-01-08 10:00:00    8 days 19:00:00   \n",
       "132252          23 2000-04-14 16:58:00 2002-04-14 17:10:00  730 days 00:12:00   \n",
       "134128           9 2000-12-18 14:00:00 2001-01-05 16:00:00   18 days 02:00:00   \n",
       "134986          10 2001-01-07 20:02:00 2002-01-08 00:36:00  365 days 04:34:00   \n",
       "151345           8 2002-08-14 19:15:00 2003-08-16 18:00:00  366 days 22:45:00   \n",
       "156458           7 2002-12-17 14:00:00 2003-01-14 16:00:00   28 days 02:00:00   \n",
       "164729           1 2003-12-04 13:15:00 2004-01-22 08:00:00   48 days 18:45:00   \n",
       "182280          14 1994-05-08 14:50:00 1995-05-08 16:00:00  365 days 01:10:00   \n",
       "182283          14 1994-05-19 19:30:00 1995-05-19 19:55:00  365 days 00:25:00   \n",
       "185848          34 1998-07-27 12:05:00 2002-07-27 12:37:00 1461 days 00:32:00   \n",
       "216913           0 1998-12-09 09:45:00 1999-01-01 10:30:00   23 days 00:45:00   \n",
       "231521           2 1993-08-19 12:15:00 1994-08-19 14:30:00  365 days 02:15:00   \n",
       "242661          48 1994-10-31 11:30:00 1995-01-03 08:00:00   63 days 20:30:00   \n",
       "248424          19 2005-09-12 17:10:00 2006-09-12 23:59:00  365 days 06:49:00   \n",
       "252307          32 2005-05-04 17:00:00 2006-05-04 18:00:00  365 days 01:00:00   \n",
       "254190          10 2003-05-14 21:20:00 2004-05-14 23:00:00  366 days 01:40:00   \n",
       "287466           4 2005-08-30 15:25:00 2007-08-30 17:30:00  730 days 02:05:00   \n",
       "288931          19 2005-01-15 12:15:00 2006-01-15 13:30:00  365 days 01:15:00   \n",
       "291926           1 2006-06-15 14:24:00 2009-06-15 19:20:00 1096 days 04:56:00   \n",
       "291927           1 2006-06-15 15:50:00 2009-06-15 21:29:00 1096 days 05:39:00   \n",
       "291928           1 2006-06-23 13:00:00 2009-06-24 11:53:00 1096 days 22:53:00   \n",
       "294005           9 2005-12-24 23:37:00 2006-01-06 15:30:00   12 days 15:53:00   \n",
       "294048           9 2006-12-24 08:26:00 2007-01-03 15:30:00   10 days 07:04:00   \n",
       "296220           0 2004-01-23 08:00:00 2005-01-31 16:00:00  374 days 08:00:00   \n",
       "...            ...                 ...                 ...                ...   \n",
       "701530           0 2012-09-04 03:45:00 2013-09-10 18:00:00  371 days 14:15:00   \n",
       "705567          32 2012-10-14 21:30:00 2013-10-14 23:30:00  365 days 02:00:00   \n",
       "705571          32 2012-10-25 18:45:00 2013-10-25 20:45:00  365 days 02:00:00   \n",
       "706277           1 2012-12-03 11:59:00 2013-12-04 15:00:00  366 days 03:01:00   \n",
       "708514           2 2012-06-12 17:56:00 2013-06-13 18:30:00  366 days 00:34:00   \n",
       "708515           2 2012-08-23 12:31:00 2013-08-24 18:50:00  366 days 06:19:00   \n",
       "708588          37 2012-04-09 12:28:00 2013-04-14 17:00:00  370 days 04:32:00   \n",
       "723294          16 2012-01-02 09:32:00 2013-01-02 10:29:00  366 days 00:57:00   \n",
       "724261           4 2012-07-24 14:00:00 2013-07-24 20:00:00  365 days 06:00:00   \n",
       "729394          47 2012-12-22 14:10:00 2013-01-06 12:00:00   14 days 21:50:00   \n",
       "741821          19 2012-06-05 13:43:00 2013-06-05 15:12:00  365 days 01:29:00   \n",
       "790523          25 2014-11-09 12:30:00 2015-01-06 13:30:00   58 days 01:00:00   \n",
       "794287           2 2014-11-01 14:39:00 2015-01-05 11:46:00   64 days 21:07:00   \n",
       "796172          31 2014-04-26 20:45:00 2015-04-26 23:30:00  365 days 02:45:00   \n",
       "796303           9 2014-12-23 17:11:00 2015-01-15 06:00:00   22 days 12:49:00   \n",
       "798854           7 2014-04-25 18:53:00 2015-04-25 19:05:00  365 days 00:12:00   \n",
       "799851          32 2014-10-01 12:00:00 2015-09-30 08:00:00  363 days 20:00:00   \n",
       "799852          32 2014-10-01 12:00:00 2015-09-30 08:00:00  363 days 20:00:00   \n",
       "799853          32 2014-10-01 12:00:00 2015-09-30 08:00:00  363 days 20:00:00   \n",
       "802912           8 2014-01-16 00:32:00 2015-01-17 16:00:00  366 days 15:28:00   \n",
       "805521           6 2014-07-14 12:00:00 2015-02-10 12:00:00  211 days 00:00:00   \n",
       "805522           6 2014-07-15 12:01:00 2015-02-10 12:00:00  209 days 23:59:00   \n",
       "808503          47 2014-11-22 16:45:00 2015-01-02 10:00:00   40 days 17:15:00   \n",
       "810920          47 2014-12-21 15:30:00 2015-01-02 10:00:00   11 days 18:30:00   \n",
       "810921           8 2014-05-06 00:15:00 2015-05-08 16:40:00  367 days 16:25:00   \n",
       "834137          47 2014-11-21 10:00:00 2015-01-02 10:00:00   42 days 00:00:00   \n",
       "834138           6 2014-11-16 18:30:00 2015-01-23 14:30:00   67 days 20:00:00   \n",
       "834139           6 2014-07-16 12:00:00 2015-02-10 12:00:00  209 days 00:00:00   \n",
       "834140           6 2014-08-01 13:45:00 2015-02-10 12:00:00  192 days 22:15:00   \n",
       "834141          12 2014-04-13 15:48:00 2015-05-15 13:28:00  396 days 21:40:00   \n",
       "\n",
       "        HOURS_TO_CONT  \n",
       "25196            3710  \n",
       "34638            8764  \n",
       "48522            8762  \n",
       "80627            8761  \n",
       "114195            414  \n",
       "114196            297  \n",
       "131788            211  \n",
       "132252          17520  \n",
       "134128            434  \n",
       "134986           8765  \n",
       "151345           8807  \n",
       "156458            674  \n",
       "164729           1171  \n",
       "182280           8761  \n",
       "182283           8760  \n",
       "185848          35065  \n",
       "216913            553  \n",
       "231521           8762  \n",
       "242661           1532  \n",
       "248424           8767  \n",
       "252307           8761  \n",
       "254190           8786  \n",
       "287466          17522  \n",
       "288931           8761  \n",
       "291926          26309  \n",
       "291927          26310  \n",
       "291928          26327  \n",
       "294005            304  \n",
       "294048            247  \n",
       "296220           8984  \n",
       "...               ...  \n",
       "701530           8918  \n",
       "705567           8762  \n",
       "705571           8762  \n",
       "706277           8787  \n",
       "708514           8785  \n",
       "708515           8790  \n",
       "708588           8885  \n",
       "723294           8785  \n",
       "724261           8766  \n",
       "729394            358  \n",
       "741821           8761  \n",
       "790523           1393  \n",
       "794287           1557  \n",
       "796172           8763  \n",
       "796303            541  \n",
       "798854           8760  \n",
       "799851           8732  \n",
       "799852           8732  \n",
       "799853           8732  \n",
       "802912           8799  \n",
       "805521           5064  \n",
       "805522           5040  \n",
       "808503            977  \n",
       "810920            282  \n",
       "810921           8824  \n",
       "834137           1008  \n",
       "834138           1628  \n",
       "834139           5016  \n",
       "834140           4630  \n",
       "834141           9526  \n",
       "\n",
       "[141 rows x 19 columns]"
      ]
     },
     "execution_count": 112,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[\n",
    "    (df['DISCOVERY_DATETIME'].apply(lambda x: x.year) != df['CONT_DATETIME'].apply(lambda x: x.year))\n",
    "    &\n",
    "    (df['HOURS_TO_CONT'] > 200)\n",
    "]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Conclusion on outliers:\n",
    "\n",
    "Probably best to drop ones with greater than 3000 hours. Looking at the fires that have > 1000 hours, most are within 2392. Safe to drop those with more as they are likely outliers."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 113,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Save intermediate copy\n",
    "df.to_pickle(\"data_with_target.pkl\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Test model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 114,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Intel(R) Data Analytics Acceleration Library (Intel(R) DAAL) solvers for sklearn enabled: https://intelpython.github.io/daal4py/sklearn.html\n"
     ]
    }
   ],
   "source": [
    "from sklearn import tree\n",
    "from sklearn.tree import DecisionTreeClassifier\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn import metrics"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 120,
   "metadata": {},
   "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>FIRE_SIZE_CLASS</th>\n",
       "      <th>STAT_CAUSE_CODE</th>\n",
       "      <th>LONGITUDE</th>\n",
       "      <th>LATITUDE</th>\n",
       "      <th>DISCOVERY_TIME</th>\n",
       "      <th>CONT_TIME</th>\n",
       "      <th>FIRE_YEAR</th>\n",
       "      <th>STATE_CODE</th>\n",
       "      <th>DISCOVERY_DATETIME</th>\n",
       "      <th>HOURS_TO_CONT</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>9.0</td>\n",
       "      <td>-121.005833</td>\n",
       "      <td>40.036944</td>\n",
       "      <td>1300</td>\n",
       "      <td>1730</td>\n",
       "      <td>2005</td>\n",
       "      <td>0</td>\n",
       "      <td>2005-02-02 13:00:00</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>-120.404444</td>\n",
       "      <td>38.933056</td>\n",
       "      <td>845</td>\n",
       "      <td>1530</td>\n",
       "      <td>2004</td>\n",
       "      <td>0</td>\n",
       "      <td>2004-05-12 08:45:00</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>5.0</td>\n",
       "      <td>-120.735556</td>\n",
       "      <td>38.984167</td>\n",
       "      <td>1921</td>\n",
       "      <td>2024</td>\n",
       "      <td>2004</td>\n",
       "      <td>0</td>\n",
       "      <td>2004-05-31 19:21:00</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>-119.913333</td>\n",
       "      <td>38.559167</td>\n",
       "      <td>1600</td>\n",
       "      <td>1400</td>\n",
       "      <td>2004</td>\n",
       "      <td>0</td>\n",
       "      <td>2004-06-28 16:00:00</td>\n",
       "      <td>118</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>-119.933056</td>\n",
       "      <td>38.559167</td>\n",
       "      <td>1600</td>\n",
       "      <td>1200</td>\n",
       "      <td>2004</td>\n",
       "      <td>0</td>\n",
       "      <td>2004-06-28 16:00:00</td>\n",
       "      <td>116</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   FIRE_SIZE_CLASS  STAT_CAUSE_CODE   LONGITUDE   LATITUDE  DISCOVERY_TIME  \\\n",
       "0                1              9.0 -121.005833  40.036944            1300   \n",
       "1                1              1.0 -120.404444  38.933056             845   \n",
       "2                1              5.0 -120.735556  38.984167            1921   \n",
       "3                1              1.0 -119.913333  38.559167            1600   \n",
       "4                1              1.0 -119.933056  38.559167            1600   \n",
       "\n",
       "   CONT_TIME  FIRE_YEAR  STATE_CODE  DISCOVERY_DATETIME  HOURS_TO_CONT  \n",
       "0       1730       2005           0 2005-02-02 13:00:00              4  \n",
       "1       1530       2004           0 2004-05-12 08:45:00              7  \n",
       "2       2024       2004           0 2004-05-31 19:21:00              1  \n",
       "3       1400       2004           0 2004-06-28 16:00:00            118  \n",
       "4       1200       2004           0 2004-06-28 16:00:00            116  "
      ]
     },
     "execution_count": 120,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# drop cols not used in model\n",
    "drop_cols = ['FIRE_NAME', 'STAT_CAUSE_DESCR', 'STATE', 'COUNTY', 'DISCOVERY_DATE',\n",
    "            'DISCOVERY_DATETIME', 'CONT_DATE', 'CONT_DATETIME', 'TIME_TO_CONT', 'Unnamed: 0']\n",
    "data_without_outliers = df.drop(drop_cols, axis=1)\n",
    "data_without_outliers = data_without_outliers[data_without_outliers.HOURS_TO_CONT < 3000]\n",
    "data_without_outliers.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 121,
   "metadata": {},
   "outputs": [],
   "source": [
    "data_without_outliers.to_pickle('final_data_without_outliers.pkl')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 122,
   "metadata": {},
   "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>FIRE_SIZE_CLASS</th>\n",
       "      <th>STAT_CAUSE_CODE</th>\n",
       "      <th>LONGITUDE</th>\n",
       "      <th>LATITUDE</th>\n",
       "      <th>DISCOVERY_TIME</th>\n",
       "      <th>CONT_TIME</th>\n",
       "      <th>FIRE_YEAR</th>\n",
       "      <th>STATE_CODE</th>\n",
       "      <th>DISCOVERY_DATETIME</th>\n",
       "      <th>HOURS_TO_CONT</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>9.0</td>\n",
       "      <td>-121.005833</td>\n",
       "      <td>40.036944</td>\n",
       "      <td>1300</td>\n",
       "      <td>1730</td>\n",
       "      <td>2005</td>\n",
       "      <td>0</td>\n",
       "      <td>2005-02-02 13:00:00</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>-120.404444</td>\n",
       "      <td>38.933056</td>\n",
       "      <td>845</td>\n",
       "      <td>1530</td>\n",
       "      <td>2004</td>\n",
       "      <td>0</td>\n",
       "      <td>2004-05-12 08:45:00</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>5.0</td>\n",
       "      <td>-120.735556</td>\n",
       "      <td>38.984167</td>\n",
       "      <td>1921</td>\n",
       "      <td>2024</td>\n",
       "      <td>2004</td>\n",
       "      <td>0</td>\n",
       "      <td>2004-05-31 19:21:00</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>-119.913333</td>\n",
       "      <td>38.559167</td>\n",
       "      <td>1600</td>\n",
       "      <td>1400</td>\n",
       "      <td>2004</td>\n",
       "      <td>0</td>\n",
       "      <td>2004-06-28 16:00:00</td>\n",
       "      <td>118</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>-119.933056</td>\n",
       "      <td>38.559167</td>\n",
       "      <td>1600</td>\n",
       "      <td>1200</td>\n",
       "      <td>2004</td>\n",
       "      <td>0</td>\n",
       "      <td>2004-06-28 16:00:00</td>\n",
       "      <td>116</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   FIRE_SIZE_CLASS  STAT_CAUSE_CODE   LONGITUDE   LATITUDE  DISCOVERY_TIME  \\\n",
       "0                1              9.0 -121.005833  40.036944            1300   \n",
       "1                1              1.0 -120.404444  38.933056             845   \n",
       "2                1              5.0 -120.735556  38.984167            1921   \n",
       "3                1              1.0 -119.913333  38.559167            1600   \n",
       "4                1              1.0 -119.933056  38.559167            1600   \n",
       "\n",
       "   CONT_TIME  FIRE_YEAR  STATE_CODE  DISCOVERY_DATETIME  HOURS_TO_CONT  \n",
       "0       1730       2005           0 2005-02-02 13:00:00              4  \n",
       "1       1530       2004           0 2004-05-12 08:45:00              7  \n",
       "2       2024       2004           0 2004-05-31 19:21:00              1  \n",
       "3       1400       2004           0 2004-06-28 16:00:00            118  \n",
       "4       1200       2004           0 2004-06-28 16:00:00            116  "
      ]
     },
     "execution_count": 122,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# only drop columns not used in feature analysis\n",
    "drop_cols = ['FIRE_NAME', 'STAT_CAUSE_DESCR', 'COUNTY', 'DISCOVERY_DATE',\n",
    "             'CONT_DATE', 'CONT_DATETIME', 'TIME_TO_CONT', 'Unnamed: 0']\n",
    "data_for_features = df.drop(drop_cols, axis=1)\n",
    "data_for_features = data_without_outliers[data_without_outliers.HOURS_TO_CONT < 3000]\n",
    "data_for_features.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 123,
   "metadata": {},
   "outputs": [],
   "source": [
    "data_without_outliers.to_pickle('data_for_features.pkl')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "metadata": {},
   "outputs": [],
   "source": [
    "# drop cols not used in model\n",
    "drop_cols = ['FIRE_SIZE_CLASS', 'FIRE_NAME', 'STAT_CAUSE_DESCR', 'STATE', 'COUNTY', 'DISCOVERY_DATE',\n",
    "            'DISCOVERY_DATETIME', 'CONT_DATE', 'CONT_DATETIME', 'TIME_TO_CONT']\n",
    "X = df.drop(drop_cols, axis=1)\n",
    "y = df['FIRE_SIZE_CLASS']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "# create testing set\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, shuffle=True,test_size=0.2, random_state=1)\n",
    "\n",
    "# create training and validation sets\n",
    "X_train, X_val, y_train, y_val = train_test_split(X_train, y_train, shuffle=True, test_size=0.25, random_state=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "md = 10\n",
    "clf = DecisionTreeClassifier(max_depth=md).fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Tree depth:  10\n",
      "# of leaves:  828\n",
      "Feature importance: \n",
      "\tUnnamed: 0: 0.207\n",
      "\tSTAT_CAUSE_CODE: 0.055\n",
      "\tLONGITUDE: 0.312\n",
      "\tLATITUDE: 0.073\n",
      "\tDISCOVERY_TIME: 0.004\n",
      "\tCONT_TIME: 0.01\n",
      "\tSTATE_CODE: 0.108\n",
      "\tHOURS_TO_CONT: 0.231\n",
      "Train score:  0.6598823250243365\n",
      "Test score:  0.6548188921648861\n"
     ]
    }
   ],
   "source": [
    "print(\"Tree depth: \", clf.get_depth())\n",
    "print(\"# of leaves: \", clf.get_n_leaves())\n",
    "print(\"Feature importance: \")\n",
    "for feature, value in dict(zip(X.columns.values, clf.feature_importances_)).items():\n",
    "    print(f\"\\t{feature:8}: {round(value,3)}\")\n",
    "print(\"Train score: \", clf.score(X_train, y_train))\n",
    "print(\"Test score: \", clf.score(X_test, y_test))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [],
   "source": [
    "# remove \"outliers\" and see if improvement\n",
    "X = df[df.HOURS_TO_CONT < 3000].drop(drop_cols, axis=1)\n",
    "y = df[df.HOURS_TO_CONT < 3000]['FIRE_SIZE_CLASS']\n",
    "# create testing set\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, shuffle=True,test_size=0.2, random_state=1)\n",
    "\n",
    "# create training and validation sets\n",
    "X_train, X_val, y_train, y_val = train_test_split(X_train, y_train, shuffle=True,test_size=0.25, random_state=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Tree depth:  10\n",
      "# of leaves:  829\n",
      "Feature importance: \n",
      "\tUnnamed: 0: 0.209\n",
      "\tSTAT_CAUSE_CODE: 0.054\n",
      "\tLONGITUDE: 0.315\n",
      "\tLATITUDE: 0.074\n",
      "\tDISCOVERY_TIME: 0.004\n",
      "\tCONT_TIME: 0.01\n",
      "\tSTATE_CODE: 0.103\n",
      "\tHOURS_TO_CONT: 0.231\n",
      "Train score:  0.6615288220551379\n",
      "Test score:  0.6559945236532171\n"
     ]
    }
   ],
   "source": [
    "md = 10\n",
    "clf = DecisionTreeClassifier(max_depth=md).fit(X_train, y_train)\n",
    "print(\"Tree depth: \", clf.get_depth())\n",
    "print(\"# of leaves: \", clf.get_n_leaves())\n",
    "print(\"Feature importance: \")\n",
    "for feature, value in dict(zip(X.columns.values, clf.feature_importances_)).items():\n",
    "    print(f\"\\t{feature:8}: {round(value,3)}\")\n",
    "print(\"Train score: \", clf.score(X_train, y_train))\n",
    "print(\"Test score: \", clf.score(X_test, y_test))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Try undersampling to improve performance"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "2    386748\n",
       "1    380835\n",
       "3     92523\n",
       "4     14622\n",
       "5      8544\n",
       "6      5584\n",
       "7      3151\n",
       "Name: FIRE_SIZE_CLASS, dtype: int64"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.FIRE_SIZE_CLASS.value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [],
   "source": [
    "# skewed data, let's undersample 1 and 2\n",
    "sample2=df[df.FIRE_SIZE_CLASS == 2].sample(10000)\n",
    "sample1=df[df.FIRE_SIZE_CLASS == 1].sample(10000)\n",
    "sample3=df[df.FIRE_SIZE_CLASS == 3].sample(10000)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(154424, 17)\n"
     ]
    },
    {
     "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>FIRE_NAME</th>\n",
       "      <th>FIRE_SIZE_CLASS</th>\n",
       "      <th>STAT_CAUSE_DESCR</th>\n",
       "      <th>STAT_CAUSE_CODE</th>\n",
       "      <th>STATE</th>\n",
       "      <th>COUNTY</th>\n",
       "      <th>LONGITUDE</th>\n",
       "      <th>LATITUDE</th>\n",
       "      <th>DISCOVERY_DATE</th>\n",
       "      <th>DISCOVERY_TIME</th>\n",
       "      <th>CONT_DATE</th>\n",
       "      <th>CONT_TIME</th>\n",
       "      <th>STATE_CODE</th>\n",
       "      <th>DISCOVERY_DATETIME</th>\n",
       "      <th>CONT_DATETIME</th>\n",
       "      <th>TIME_TO_CONT</th>\n",
       "      <th>HOURS_TO_CONT</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>141589</th>\n",
       "      <td>POWERLINE</td>\n",
       "      <td>1</td>\n",
       "      <td>Miscellaneous</td>\n",
       "      <td>9.0</td>\n",
       "      <td>WA</td>\n",
       "      <td>51</td>\n",
       "      <td>-117.038056</td>\n",
       "      <td>48.341667</td>\n",
       "      <td>2452134.5</td>\n",
       "      <td>1701</td>\n",
       "      <td>2452134.5</td>\n",
       "      <td>1910</td>\n",
       "      <td>6</td>\n",
       "      <td>2001-08-13 17:01:00</td>\n",
       "      <td>2001-08-13 19:10:00</td>\n",
       "      <td>02:09:00</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>108195</th>\n",
       "      <td>FOSTER 3</td>\n",
       "      <td>1</td>\n",
       "      <td>Lightning</td>\n",
       "      <td>1.0</td>\n",
       "      <td>OR</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-122.391667</td>\n",
       "      <td>43.031667</td>\n",
       "      <td>2451022.5</td>\n",
       "      <td>1900</td>\n",
       "      <td>2451022.5</td>\n",
       "      <td>2130</td>\n",
       "      <td>2</td>\n",
       "      <td>1998-07-28 19:00:00</td>\n",
       "      <td>1998-07-28 21:30:00</td>\n",
       "      <td>02:30:00</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>783453</th>\n",
       "      <td>NaN</td>\n",
       "      <td>1</td>\n",
       "      <td>Arson</td>\n",
       "      <td>7.0</td>\n",
       "      <td>SC</td>\n",
       "      <td>Dillon County</td>\n",
       "      <td>-79.320457</td>\n",
       "      <td>34.437176</td>\n",
       "      <td>2456571.5</td>\n",
       "      <td>1512</td>\n",
       "      <td>2456571.5</td>\n",
       "      <td>1556</td>\n",
       "      <td>17</td>\n",
       "      <td>2013-10-06 15:12:00</td>\n",
       "      <td>2013-10-06 15:56:00</td>\n",
       "      <td>00:44:00</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>867354</th>\n",
       "      <td>NaN</td>\n",
       "      <td>1</td>\n",
       "      <td>Debris Burning</td>\n",
       "      <td>5.0</td>\n",
       "      <td>NY</td>\n",
       "      <td>Broome</td>\n",
       "      <td>-75.909600</td>\n",
       "      <td>42.146200</td>\n",
       "      <td>2457291.5</td>\n",
       "      <td>1454</td>\n",
       "      <td>2457291.5</td>\n",
       "      <td>1538</td>\n",
       "      <td>41</td>\n",
       "      <td>2015-09-26 14:54:00</td>\n",
       "      <td>2015-09-26 15:38:00</td>\n",
       "      <td>00:44:00</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>619510</th>\n",
       "      <td>NaN</td>\n",
       "      <td>1</td>\n",
       "      <td>Debris Burning</td>\n",
       "      <td>5.0</td>\n",
       "      <td>GA</td>\n",
       "      <td>Laurens</td>\n",
       "      <td>-83.025800</td>\n",
       "      <td>32.424000</td>\n",
       "      <td>2449055.5</td>\n",
       "      <td>1622</td>\n",
       "      <td>2449055.5</td>\n",
       "      <td>1705</td>\n",
       "      <td>30</td>\n",
       "      <td>1993-03-09 16:22:00</td>\n",
       "      <td>1993-03-09 17:05:00</td>\n",
       "      <td>00:43:00</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        FIRE_NAME  FIRE_SIZE_CLASS STAT_CAUSE_DESCR  STAT_CAUSE_CODE STATE  \\\n",
       "141589  POWERLINE                1    Miscellaneous              9.0    WA   \n",
       "108195   FOSTER 3                1        Lightning              1.0    OR   \n",
       "783453        NaN                1            Arson              7.0    SC   \n",
       "867354        NaN                1   Debris Burning              5.0    NY   \n",
       "619510        NaN                1   Debris Burning              5.0    GA   \n",
       "\n",
       "                      COUNTY   LONGITUDE   LATITUDE  DISCOVERY_DATE  \\\n",
       "141589                    51 -117.038056  48.341667       2452134.5   \n",
       "108195                   NaN -122.391667  43.031667       2451022.5   \n",
       "783453         Dillon County  -79.320457  34.437176       2456571.5   \n",
       "867354                Broome  -75.909600  42.146200       2457291.5   \n",
       "619510  Laurens               -83.025800  32.424000       2449055.5   \n",
       "\n",
       "        DISCOVERY_TIME  CONT_DATE  CONT_TIME  STATE_CODE  DISCOVERY_DATETIME  \\\n",
       "141589            1701  2452134.5       1910           6 2001-08-13 17:01:00   \n",
       "108195            1900  2451022.5       2130           2 1998-07-28 19:00:00   \n",
       "783453            1512  2456571.5       1556          17 2013-10-06 15:12:00   \n",
       "867354            1454  2457291.5       1538          41 2015-09-26 14:54:00   \n",
       "619510            1622  2449055.5       1705          30 1993-03-09 16:22:00   \n",
       "\n",
       "             CONT_DATETIME TIME_TO_CONT  HOURS_TO_CONT  \n",
       "141589 2001-08-13 19:10:00     02:09:00              2  \n",
       "108195 1998-07-28 21:30:00     02:30:00              2  \n",
       "783453 2013-10-06 15:56:00     00:44:00              1  \n",
       "867354 2015-09-26 15:38:00     00:44:00              1  \n",
       "619510 1993-03-09 17:05:00     00:43:00              1  "
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sampled_df= pd.concat([sample1, sample2, sample3,df[(df.FIRE_SIZE_CLASS != 1) & (df.FIRE_SIZE_CLASS != 2)]])\n",
    "sampled_df=sampled_df.drop('Unnamed: 0', axis=1)\n",
    "print(sampled_df.shape)\n",
    "sampled_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\somet\\anaconda3\\lib\\site-packages\\ipykernel_launcher.py:2: UserWarning: Boolean Series key will be reindexed to match DataFrame index.\n",
      "  \n",
      "C:\\Users\\somet\\anaconda3\\lib\\site-packages\\ipykernel_launcher.py:3: UserWarning: Boolean Series key will be reindexed to match DataFrame index.\n",
      "  This is separate from the ipykernel package so we can avoid doing imports until\n"
     ]
    }
   ],
   "source": [
    "# remove \"outliers\" and see if improvement\n",
    "X = sampled_df[df.HOURS_TO_CONT < 3000].drop(drop_cols, axis=1)\n",
    "y = sampled_df[df.HOURS_TO_CONT < 3000]['FIRE_SIZE_CLASS']\n",
    "# create testing set\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, shuffle=True, random_state=1)\n",
    "\n",
    "# create training and validation sets\n",
    "X_train, X_val, y_train, y_val = train_test_split(X_train, y_train, test_size=0.25, shuffle=True,random_state=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Tree depth:  10\n",
      "# of leaves:  787\n",
      "Feature importance: \n",
      "\tSTAT_CAUSE_CODE: 0.06\n",
      "\tLONGITUDE: 0.332\n",
      "\tLATITUDE: 0.1\n",
      "\tDISCOVERY_TIME: 0.029\n",
      "\tCONT_TIME: 0.033\n",
      "\tSTATE_CODE: 0.133\n",
      "\tHOURS_TO_CONT: 0.314\n",
      "Train score:  0.7099859505025398\n",
      "Test score:  0.6864868369861237\n"
     ]
    }
   ],
   "source": [
    "md = 10\n",
    "clf = DecisionTreeClassifier(max_depth=md).fit(X_train, y_train)\n",
    "print(\"Tree depth: \", clf.get_depth())\n",
    "print(\"# of leaves: \", clf.get_n_leaves())\n",
    "print(\"Feature importance: \")\n",
    "for feature, value in dict(zip(X.columns.values, clf.feature_importances_)).items():\n",
    "    print(f\"\\t{feature:8}: {round(value,3)}\")\n",
    "print(\"Train score: \", clf.score(X_train, y_train))\n",
    "print(\"Test score: \", clf.score(X_test, y_test))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Conclusion**: performance improved a lot"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Even sampling across everything\n",
    "\n",
    "Sample so everything is max the lowest count of fire size classes."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 172,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(22057, 17)\n"
     ]
    }
   ],
   "source": [
    "# skewed data, let's undersample 1 and 2\n",
    "sample1=df[df.FIRE_SIZE_CLASS == 1].sample(3151)\n",
    "sample2=df[df.FIRE_SIZE_CLASS == 2].sample(3151)\n",
    "sample3=df[df.FIRE_SIZE_CLASS == 3].sample(3151)\n",
    "sample4=df[df.FIRE_SIZE_CLASS == 4].sample(3151)\n",
    "sample5=df[df.FIRE_SIZE_CLASS == 5].sample(3151)\n",
    "sample6=df[df.FIRE_SIZE_CLASS == 6].sample(3151)\n",
    "sample7=df[df.FIRE_SIZE_CLASS==7]\n",
    "\n",
    "sampled_df= pd.concat([sample1, sample2, sample3, sample4, sample5, sample6, sample7])\n",
    "print(sampled_df.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 177,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\somet\\anaconda3\\lib\\site-packages\\ipykernel_launcher.py:2: UserWarning: Boolean Series key will be reindexed to match DataFrame index.\n",
      "  \n",
      "C:\\Users\\somet\\anaconda3\\lib\\site-packages\\ipykernel_launcher.py:3: UserWarning: Boolean Series key will be reindexed to match DataFrame index.\n",
      "  This is separate from the ipykernel package so we can avoid doing imports until\n"
     ]
    }
   ],
   "source": [
    "# remove \"outliers\" and see if improvement\n",
    "X = sampled_df[df.HOURS_TO_CONT < 8000].drop(drop_cols, axis=1)\n",
    "y = sampled_df[df.HOURS_TO_CONT < 8000]['FIRE_SIZE_CLASS']\n",
    "# create testing set\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, shuffle=True, random_state=1)\n",
    "\n",
    "# create training and validation sets\n",
    "X_train, X_val, y_train, y_val = train_test_split(X_train, y_train, test_size=0.25, shuffle=True,random_state=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 178,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Tree depth:  10\n",
      "# of leaves:  717\n",
      "Feature importance: \n",
      "\tSTAT_CAUSE_CODE: 0.046\n",
      "\tLONGITUDE: 0.216\n",
      "\tLATITUDE: 0.141\n",
      "\tDISCOVERY_TIME: 0.06\n",
      "\tCONT_TIME: 0.064\n",
      "\tHOURS_TO_CONT: 0.427\n",
      "\tSTATE_CODE: 0.046\n",
      "Train score:  0.5544554455445545\n",
      "Test score:  0.4180457946043981\n"
     ]
    }
   ],
   "source": [
    "md = 10\n",
    "clf = DecisionTreeClassifier(max_depth=md).fit(X_train, y_train)\n",
    "print(\"Tree depth: \", clf.get_depth())\n",
    "print(\"# of leaves: \", clf.get_n_leaves())\n",
    "print(\"Feature importance: \")\n",
    "for feature, value in dict(zip(X.columns.values, clf.feature_importances_)).items():\n",
    "    print(f\"\\t{feature:8}: {round(value,3)}\")\n",
    "print(\"Train score: \", clf.score(X_train, y_train))\n",
    "print(\"Test score: \", clf.score(X_test, y_test))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Conclusion**: performance degraded drastically by overrepresenting the rarer fire classes"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## What next\n",
    "\n",
    "Select best max depth decision tree?\n",
    "\n",
    "Ensemble method Random Forest?"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Removing DISCOVERY_TIME,  CONT_TIME columns as well (low feature importance)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "metadata": {},
   "outputs": [],
   "source": [
    "# skewed data, let's undersample 1 and 2\n",
    "sample2=df[df.FIRE_SIZE_CLASS == 2].sample(10000)\n",
    "sample1=df[df.FIRE_SIZE_CLASS == 1].sample(10000)\n",
    "sample3=df[df.FIRE_SIZE_CLASS == 3].sample(10000)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(154424, 17)\n"
     ]
    },
    {
     "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>FIRE_NAME</th>\n",
       "      <th>FIRE_SIZE_CLASS</th>\n",
       "      <th>STAT_CAUSE_DESCR</th>\n",
       "      <th>STAT_CAUSE_CODE</th>\n",
       "      <th>STATE</th>\n",
       "      <th>COUNTY</th>\n",
       "      <th>LONGITUDE</th>\n",
       "      <th>LATITUDE</th>\n",
       "      <th>DISCOVERY_DATE</th>\n",
       "      <th>DISCOVERY_TIME</th>\n",
       "      <th>CONT_DATE</th>\n",
       "      <th>CONT_TIME</th>\n",
       "      <th>STATE_CODE</th>\n",
       "      <th>DISCOVERY_DATETIME</th>\n",
       "      <th>CONT_DATETIME</th>\n",
       "      <th>TIME_TO_CONT</th>\n",
       "      <th>HOURS_TO_CONT</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>171252</th>\n",
       "      <td>THIRSTY FIRE</td>\n",
       "      <td>1</td>\n",
       "      <td>Lightning</td>\n",
       "      <td>1.0</td>\n",
       "      <td>OR</td>\n",
       "      <td>19</td>\n",
       "      <td>-122.080556</td>\n",
       "      <td>43.281389</td>\n",
       "      <td>2453230.5</td>\n",
       "      <td>1622</td>\n",
       "      <td>2453231.5</td>\n",
       "      <td>1910</td>\n",
       "      <td>2</td>\n",
       "      <td>2004-08-13 16:22:00</td>\n",
       "      <td>2004-08-14 19:10:00</td>\n",
       "      <td>1 days 02:48:00</td>\n",
       "      <td>27</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>77138</th>\n",
       "      <td>HUFFER</td>\n",
       "      <td>1</td>\n",
       "      <td>Smoking</td>\n",
       "      <td>3.0</td>\n",
       "      <td>AZ</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-111.383333</td>\n",
       "      <td>34.486667</td>\n",
       "      <td>2449879.5</td>\n",
       "      <td>1630</td>\n",
       "      <td>2449879.5</td>\n",
       "      <td>1715</td>\n",
       "      <td>9</td>\n",
       "      <td>1995-06-11 16:30:00</td>\n",
       "      <td>1995-06-11 17:15:00</td>\n",
       "      <td>0 days 00:45:00</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>748523</th>\n",
       "      <td>HALL</td>\n",
       "      <td>1</td>\n",
       "      <td>Lightning</td>\n",
       "      <td>1.0</td>\n",
       "      <td>AZ</td>\n",
       "      <td>001</td>\n",
       "      <td>-109.511667</td>\n",
       "      <td>34.157222</td>\n",
       "      <td>2456487.5</td>\n",
       "      <td>808</td>\n",
       "      <td>2456488.5</td>\n",
       "      <td>1214</td>\n",
       "      <td>9</td>\n",
       "      <td>2013-07-14 08:08:00</td>\n",
       "      <td>2013-07-15 12:14:00</td>\n",
       "      <td>1 days 04:06:00</td>\n",
       "      <td>28</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>202147</th>\n",
       "      <td>JACOBTALAS</td>\n",
       "      <td>1</td>\n",
       "      <td>Debris Burning</td>\n",
       "      <td>5.0</td>\n",
       "      <td>AZ</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-110.467400</td>\n",
       "      <td>35.783300</td>\n",
       "      <td>2451339.5</td>\n",
       "      <td>1830</td>\n",
       "      <td>2451339.5</td>\n",
       "      <td>2030</td>\n",
       "      <td>9</td>\n",
       "      <td>1999-06-10 18:30:00</td>\n",
       "      <td>1999-06-10 20:30:00</td>\n",
       "      <td>0 days 02:00:00</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>846757</th>\n",
       "      <td>TWENTY-ONE</td>\n",
       "      <td>1</td>\n",
       "      <td>Arson</td>\n",
       "      <td>7.0</td>\n",
       "      <td>NM</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-106.689597</td>\n",
       "      <td>34.908500</td>\n",
       "      <td>2457157.5</td>\n",
       "      <td>1226</td>\n",
       "      <td>2457157.5</td>\n",
       "      <td>1303</td>\n",
       "      <td>1</td>\n",
       "      <td>2015-05-15 12:26:00</td>\n",
       "      <td>2015-05-15 13:03:00</td>\n",
       "      <td>0 days 00:37:00</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           FIRE_NAME  FIRE_SIZE_CLASS STAT_CAUSE_DESCR  STAT_CAUSE_CODE STATE  \\\n",
       "171252  THIRSTY FIRE                1        Lightning              1.0    OR   \n",
       "77138         HUFFER                1          Smoking              3.0    AZ   \n",
       "748523          HALL                1        Lightning              1.0    AZ   \n",
       "202147    JACOBTALAS                1   Debris Burning              5.0    AZ   \n",
       "846757    TWENTY-ONE                1            Arson              7.0    NM   \n",
       "\n",
       "       COUNTY   LONGITUDE   LATITUDE  DISCOVERY_DATE  DISCOVERY_TIME  \\\n",
       "171252     19 -122.080556  43.281389       2453230.5            1622   \n",
       "77138     NaN -111.383333  34.486667       2449879.5            1630   \n",
       "748523    001 -109.511667  34.157222       2456487.5             808   \n",
       "202147    NaN -110.467400  35.783300       2451339.5            1830   \n",
       "846757    NaN -106.689597  34.908500       2457157.5            1226   \n",
       "\n",
       "        CONT_DATE  CONT_TIME  STATE_CODE  DISCOVERY_DATETIME  \\\n",
       "171252  2453231.5       1910           2 2004-08-13 16:22:00   \n",
       "77138   2449879.5       1715           9 1995-06-11 16:30:00   \n",
       "748523  2456488.5       1214           9 2013-07-14 08:08:00   \n",
       "202147  2451339.5       2030           9 1999-06-10 18:30:00   \n",
       "846757  2457157.5       1303           1 2015-05-15 12:26:00   \n",
       "\n",
       "             CONT_DATETIME    TIME_TO_CONT  HOURS_TO_CONT  \n",
       "171252 2004-08-14 19:10:00 1 days 02:48:00             27  \n",
       "77138  1995-06-11 17:15:00 0 days 00:45:00              1  \n",
       "748523 2013-07-15 12:14:00 1 days 04:06:00             28  \n",
       "202147 1999-06-10 20:30:00 0 days 02:00:00              2  \n",
       "846757 2015-05-15 13:03:00 0 days 00:37:00              1  "
      ]
     },
     "execution_count": 66,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sampled_df= pd.concat([sample1, sample2, sample3,df[(df.FIRE_SIZE_CLASS != 1) & (df.FIRE_SIZE_CLASS != 2)]])\n",
    "sampled_df=sampled_df.drop('Unnamed: 0', axis=1)\n",
    "print(sampled_df.shape)\n",
    "sampled_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\somet\\anaconda3\\lib\\site-packages\\ipykernel_launcher.py:3: UserWarning: Boolean Series key will be reindexed to match DataFrame index.\n",
      "  This is separate from the ipykernel package so we can avoid doing imports until\n",
      "C:\\Users\\somet\\anaconda3\\lib\\site-packages\\ipykernel_launcher.py:4: UserWarning: Boolean Series key will be reindexed to match DataFrame index.\n",
      "  after removing the cwd from sys.path.\n"
     ]
    }
   ],
   "source": [
    "# remove \"outliers\" and see if improvement\n",
    "drop_cols2 = drop_cols + ['DISCOVERY_TIME', 'CONT_TIME']\n",
    "X = sampled_df[df.HOURS_TO_CONT < 3000].drop(drop_cols2, axis=1)\n",
    "y = sampled_df[df.HOURS_TO_CONT < 3000]['FIRE_SIZE_CLASS']\n",
    "# create testing set\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, shuffle=True, random_state=1)\n",
    "\n",
    "# create training and validation sets\n",
    "X_train, X_val, y_train, y_val = train_test_split(X_train, y_train, test_size=0.25, shuffle=True,random_state=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Tree depth:  10\n",
      "# of leaves:  843\n",
      "Feature importance: \n",
      "\tSTAT_CAUSE_CODE: 0.059\n",
      "\tLONGITUDE: 0.348\n",
      "\tLATITUDE: 0.136\n",
      "\tSTATE_CODE: 0.137\n",
      "\tHOURS_TO_CONT: 0.32\n",
      "Train score:  0.7086535032260156\n",
      "Test score:  0.685870833873687\n"
     ]
    }
   ],
   "source": [
    "md = 10\n",
    "clf = DecisionTreeClassifier(max_depth=md).fit(X_train, y_train)\n",
    "print(\"Tree depth: \", clf.get_depth())\n",
    "print(\"# of leaves: \", clf.get_n_leaves())\n",
    "print(\"Feature importance: \")\n",
    "for feature, value in dict(zip(X.columns.values, clf.feature_importances_)).items():\n",
    "    print(f\"\\t{feature:8}: {round(value,3)}\")\n",
    "print(\"Train score: \", clf.score(X_train, y_train))\n",
    "print(\"Test score: \", clf.score(X_test, y_test))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Conclusion**: not that much improvement actually"
   ]
  },
  {
   "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": "3.6.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}