{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": { "collapsed": true }, "outputs": [], "source": [ "import pandas as pd" ] }, { "cell_type": "code", "execution_count": 2, "metadata": { "collapsed": false }, "outputs": [], "source": [ "inspections = pd.read_csv(\"../data/inspections.csv\", index_col=0)" ] }, { "cell_type": "code", "execution_count": 3, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/html": [ "
\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
CAMISDBABOROBUILDINGSTREETZIPCODEPHONECUISINE DESCRIPTIONINSPECTION DATEACTIONVIOLATION CODEVIOLATION DESCRIPTIONCRITICAL FLAGSCOREGRADEGRADE DATERECORD DATEINSPECTION TYPE
041158108NICK'S GOURMET DELIQUEENS7415DITMARS BOULEVARD113707182788338American07/21/2015Violations were cited in the following area(s).04LEvidence of mice or live mice present in facil...Critical11.0NaNNaN09/27/2016Cycle Inspection / Initial Inspection
141187577HANSOL NUTRITION CENTERQUEENS16026NORTHERN BOULEVARD113587188880200Korean07/13/2016Violations were cited in the following area(s).06APersonal cleanliness inadequate. Outer garment...Critical30.0NaNNaN09/27/2016Cycle Inspection / Initial Inspection
241705988KURAMANHATTAN130ST MARKS PLACE100092122281010Japanese05/08/2013Violations were cited in the following area(s).02BHot food item not held at or above 140º F.Critical27.0NaNNaN09/27/2016Pre-permit (Operational) / Initial Inspection
\n", "
" ], "text/plain": [ " CAMIS DBA BORO BUILDING STREET \\\n", "0 41158108 NICK'S GOURMET DELI QUEENS 7415 DITMARS BOULEVARD \n", "1 41187577 HANSOL NUTRITION CENTER QUEENS 16026 NORTHERN BOULEVARD \n", "2 41705988 KURA MANHATTAN 130 ST MARKS PLACE \n", "\n", " ZIPCODE PHONE CUISINE DESCRIPTION INSPECTION DATE \\\n", "0 11370 7182788338 American 07/21/2015 \n", "1 11358 7188880200 Korean 07/13/2016 \n", "2 10009 2122281010 Japanese 05/08/2013 \n", "\n", " ACTION VIOLATION CODE \\\n", "0 Violations were cited in the following area(s). 04L \n", "1 Violations were cited in the following area(s). 06A \n", "2 Violations were cited in the following area(s). 02B \n", "\n", " VIOLATION DESCRIPTION CRITICAL FLAG SCORE \\\n", "0 Evidence of mice or live mice present in facil... Critical 11.0 \n", "1 Personal cleanliness inadequate. Outer garment... Critical 30.0 \n", "2 Hot food item not held at or above 140º F. Critical 27.0 \n", "\n", " GRADE GRADE DATE RECORD DATE INSPECTION TYPE \n", "0 NaN NaN 09/27/2016 Cycle Inspection / Initial Inspection \n", "1 NaN NaN 09/27/2016 Cycle Inspection / Initial Inspection \n", "2 NaN NaN 09/27/2016 Pre-permit (Operational) / Initial Inspection " ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "inspections.head(3)" ] }, { "cell_type": "code", "execution_count": 3, "metadata": { "collapsed": false }, "outputs": [], "source": [ "inspections['INSPECTION DATE'] = pd.to_datetime(inspections['INSPECTION DATE'])" ] }, { "cell_type": "code", "execution_count": 47, "metadata": { "collapsed": false, "scrolled": false }, "outputs": [], "source": [ "# random_camis = inspections.sample().iloc[0]['CAMIS']\n", "# inspections[inspections['CAMIS'] == random_camis].sort_values(by='INSPECTION DATE')['INSPECTION DATE']" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Get initial inspection date." ] }, { "cell_type": "code", "execution_count": 4, "metadata": { "collapsed": false, "scrolled": true }, "outputs": [], "source": [ "inspections_f = inspections.groupby('CAMIS')\\\n", " .apply(lambda df: inspections[inspections['CAMIS'] == df['CAMIS'].iloc[0]]\\\n", " .sort_values(by=\"INSPECTION DATE\")\\\n", " .iloc[0]\\\n", " .drop('CAMIS')\n", " )\\\n", " .rename(columns={'INSPECTION DATE': 'INITIAL INSPECTION DATE'})" ] }, { "cell_type": "code", "execution_count": 5, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/html": [ "
\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
DBABOROBUILDINGSTREETZIPCODEPHONECUISINE DESCRIPTIONINITIAL INSPECTION DATEACTIONVIOLATION CODEVIOLATION DESCRIPTIONCRITICAL FLAGSCOREGRADEGRADE DATERECORD DATEINSPECTION TYPE
CAMIS
50001937TASTY CHICKENBROOKLYN168786TH STREET112147182591111American08/21/2013Violations were cited in the following area(s).15LSmoke free workplace smoking policy inadequate...Not CriticalNaNNaNNaN09/27/2016Smoke-Free Air Act / Initial Inspection
\n", "
" ], "text/plain": [ " DBA BORO BUILDING STREET ZIPCODE PHONE \\\n", "CAMIS \n", "50001937 TASTY CHICKEN BROOKLYN 1687 86TH STREET 11214 7182591111 \n", "\n", " CUISINE DESCRIPTION INITIAL INSPECTION DATE \\\n", "CAMIS \n", "50001937 American 08/21/2013 \n", "\n", " ACTION VIOLATION CODE \\\n", "CAMIS \n", "50001937 Violations were cited in the following area(s). 15L \n", "\n", " VIOLATION DESCRIPTION CRITICAL FLAG \\\n", "CAMIS \n", "50001937 Smoke free workplace smoking policy inadequate... Not Critical \n", "\n", " SCORE GRADE GRADE DATE RECORD DATE \\\n", "CAMIS \n", "50001937 NaN NaN NaN 09/27/2016 \n", "\n", " INSPECTION TYPE \n", "CAMIS \n", "50001937 Smoke-Free Air Act / Initial Inspection " ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "inspections_f.sample(1)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Not sure why, but this operation drops the `DBA` field. None others are affected. Maybe something with the indexing?" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Let's take the most recent inspection date." ] }, { "cell_type": "code", "execution_count": 5, "metadata": { "collapsed": false }, "outputs": [], "source": [ "inspections_ff = inspections_f.copy()\n", "inspections_ff['LATEST INSPECTION DATE'] = inspections_ff\\\n", " .apply(lambda srs: inspections[inspections['CAMIS'] == srs.name]\\\n", " .sort_values(by='INSPECTION DATE')\\\n", " .iloc[-1]\\\n", " ['INSPECTION DATE'],\n", " axis='columns')" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Rename the `INSPECTION TYPE` to `INITIAL INSPECTION TYPE` (this flags new establishments from pre-existing ones, in the cotext of our dataset)." ] }, { "cell_type": "code", "execution_count": 6, "metadata": { "collapsed": false, "scrolled": false }, "outputs": [], "source": [ "inspections_ff = inspections_ff.rename(columns={'INSPECTION TYPE': 'INITIAL INSPECTION TYPE'})" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Checking the flags:" ] }, { "cell_type": "code", "execution_count": 91, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "Cycle Inspection / Initial Inspection 12537\n", "Pre-permit (Operational) / Initial Inspection 7630\n", "Pre-permit (Non-operational) / Initial Inspection 2256\n", "Cycle Inspection / Re-inspection 877\n", "Administrative Miscellaneous / Initial Inspection 683\n", "Smoke-Free Air Act / Initial Inspection 281\n", "Trans Fat / Initial Inspection 247\n", "Pre-permit (Operational) / Re-inspection 82\n", "Trans Fat / Compliance Inspection 80\n", "Trans Fat / Re-inspection 75\n", "Inter-Agency Task Force / Initial Inspection 53\n", "Calorie Posting / Initial Inspection 30\n", "Trans Fat / Second Compliance Inspection 27\n", "Administrative Miscellaneous / Re-inspection 27\n", "Smoke-Free Air Act / Re-inspection 23\n", "Administrative Miscellaneous / Compliance Inspection 14\n", "Cycle Inspection / Compliance Inspection 12\n", "Pre-permit (Operational) / Compliance Inspection 12\n", "Cycle Inspection / Reopening Inspection 8\n", "Smoke-Free Air Act / Compliance Inspection 6\n", "Calorie Posting / Re-inspection 5\n", "Pre-permit (Operational) / Reopening Inspection 4\n", "Pre-permit (Non-operational) / Re-inspection 3\n", "Cycle Inspection / Second Compliance Inspection 2\n", "Administrative Miscellaneous / Second Compliance Inspection 2\n", "Pre-permit (Operational) / Second Compliance Inspection 1\n", "Smoke-Free Air Act / Limited Inspection 1\n", "Calorie Posting / Compliance Inspection 1\n", "Smoke-Free Air Act / Second Compliance Inspection 1\n", "Name: INITIAL INSPECTION TYPE, dtype: int64" ] }, "execution_count": 91, "metadata": {}, "output_type": "execute_result" } ], "source": [ "inspections_ff['INITIAL INSPECTION TYPE'].value_counts()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "A lot of them are null." ] }, { "cell_type": "code", "execution_count": 93, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "1094" ] }, "execution_count": 93, "metadata": {}, "output_type": "execute_result" } ], "source": [ "inspections_ff['INITIAL INSPECTION TYPE'].isnull().astype(int).sum()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Remember, this is new establishments that have not been inspected yet. That the numbers match up here is encouraging." ] }, { "cell_type": "code", "execution_count": 94, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "1094" ] }, "execution_count": 94, "metadata": {}, "output_type": "execute_result" } ], "source": [ "inspections['INSPECTION TYPE'].isnull().astype(int).sum()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "We reattach the lost DBA column." ] }, { "cell_type": "code", "execution_count": 95, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/html": [ "
\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
DBABOROBUILDINGSTREETZIPCODEPHONECUISINE DESCRIPTIONINITIAL INSPECTION DATEACTIONVIOLATION CODEVIOLATION DESCRIPTIONCRITICAL FLAGSCOREGRADEGRADE DATERECORD DATEINITIAL INSPECTION TYPELATEST INSPECTION DATE
CAMIS
30075445NaNBRONX1007.0MORRIS PARK AVE104627.188925e+09Bakery2013-06-01Violations were cited in the following area(s).16BThe original nutritional fact labels and/or in...Not CriticalNaNNaNNaN09/24/2016Trans Fat / Compliance Inspection2016-02-18
\n", "
" ], "text/plain": [ " DBA BORO BUILDING STREET ZIPCODE PHONE \\\n", "CAMIS \n", "30075445 NaN BRONX 1007.0 MORRIS PARK AVE 10462 7.188925e+09 \n", "\n", " CUISINE DESCRIPTION INITIAL INSPECTION DATE \\\n", "CAMIS \n", "30075445 Bakery 2013-06-01 \n", "\n", " ACTION VIOLATION CODE \\\n", "CAMIS \n", "30075445 Violations were cited in the following area(s). 16B \n", "\n", " VIOLATION DESCRIPTION CRITICAL FLAG \\\n", "CAMIS \n", "30075445 The original nutritional fact labels and/or in... Not Critical \n", "\n", " SCORE GRADE GRADE DATE RECORD DATE \\\n", "CAMIS \n", "30075445 NaN NaN NaN 09/24/2016 \n", "\n", " INITIAL INSPECTION TYPE LATEST INSPECTION DATE \n", "CAMIS \n", "30075445 Trans Fat / Compliance Inspection 2016-02-18 " ] }, "execution_count": 95, "metadata": {}, "output_type": "execute_result" } ], "source": [ "inspections_ff.head(1)" ] }, { "cell_type": "code", "execution_count": 7, "metadata": { "collapsed": false }, "outputs": [], "source": [ "inspections_fff = inspections_ff.copy()\n", "inspections_fff['DBA'] = inspections_fff.apply(lambda srs: \n", " inspections[inspections['CAMIS'] == srs.name]\\\n", " .iloc[0]['DBA'],\n", " axis='columns')" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Prepend descriptors, to more easily distinguish things down the road." ] }, { "cell_type": "code", "execution_count": 8, "metadata": { "collapsed": true }, "outputs": [], "source": [ "inspections_fff.columns = [\"DOHMH \" + col for col in inspections_fff.columns]" ] }, { "cell_type": "code", "execution_count": 105, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/html": [ "
\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
DOHMH DBADOHMH BORODOHMH BUILDINGDOHMH STREETDOHMH ZIPCODEDOHMH PHONEDOHMH CUISINE DESCRIPTIONDOHMH INITIAL INSPECTION DATEDOHMH ACTIONDOHMH VIOLATION CODEDOHMH VIOLATION DESCRIPTIONDOHMH CRITICAL FLAGDOHMH SCOREDOHMH GRADEDOHMH GRADE DATEDOHMH RECORD DATEDOHMH INITIAL INSPECTION TYPEDOHMH LATEST INSPECTION DATE
CAMIS
40374834CASA BELLAMANHATTAN127.0MULBERRY STREET100132.124314e+09Italian2013-08-15Violations were cited in the following area(s).06DFood contact surface not properly washed, rins...Critical6.0NaNNaN09/24/2016Cycle Inspection / Initial Inspection2016-04-26
\n", "
" ], "text/plain": [ " DOHMH DBA DOHMH BORO DOHMH BUILDING DOHMH STREET \\\n", "CAMIS \n", "40374834 CASA BELLA MANHATTAN 127.0 MULBERRY STREET \n", "\n", " DOHMH ZIPCODE DOHMH PHONE DOHMH CUISINE DESCRIPTION \\\n", "CAMIS \n", "40374834 10013 2.124314e+09 Italian \n", "\n", " DOHMH INITIAL INSPECTION DATE \\\n", "CAMIS \n", "40374834 2013-08-15 \n", "\n", " DOHMH ACTION \\\n", "CAMIS \n", "40374834 Violations were cited in the following area(s). \n", "\n", " DOHMH VIOLATION CODE \\\n", "CAMIS \n", "40374834 06D \n", "\n", " DOHMH VIOLATION DESCRIPTION \\\n", "CAMIS \n", "40374834 Food contact surface not properly washed, rins... \n", "\n", " DOHMH CRITICAL FLAG DOHMH SCORE DOHMH GRADE DOHMH GRADE DATE \\\n", "CAMIS \n", "40374834 Critical 6.0 NaN NaN \n", "\n", " DOHMH RECORD DATE DOHMH INITIAL INSPECTION TYPE \\\n", "CAMIS \n", "40374834 09/24/2016 Cycle Inspection / Initial Inspection \n", "\n", " DOHMH LATEST INSPECTION DATE \n", "CAMIS \n", "40374834 2016-04-26 " ] }, "execution_count": 105, "metadata": {}, "output_type": "execute_result" } ], "source": [ "inspections_fff.sample()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Now we get information from Yelp!" ] }, { "cell_type": "code", "execution_count": 9, "metadata": { "collapsed": false }, "outputs": [], "source": [ "from yelp.client import Client\n", "from yelp.oauth1_authenticator import Oauth1Authenticator\n", "from yelp.errors import BusinessUnavailable\n", "import os\n", "import json\n", "\n", "def import_credentials(filename='../data/yelp_credentials.json'):\n", " try:\n", " data = json.load(open(filename))\n", " return data\n", " except:\n", " raise IOError('This API requires Yelp credentials to work. Did you forget to define them?')\n", "\n", "credentials = import_credentials()\n", "\n", "auth = Oauth1Authenticator(\n", " consumer_key=credentials['consumer_key'],\n", " consumer_secret=credentials['consumer_secret'],\n", " token=credentials['token'],\n", " token_secret=credentials['token_secret']\n", ")\n", "\n", "client = Client(auth)" ] }, { "cell_type": "code", "execution_count": 10, "metadata": { "collapsed": true }, "outputs": [], "source": [ "from tqdm import tqdm" ] }, { "cell_type": "code", "execution_count": 77, "metadata": { "collapsed": false }, "outputs": [ { "ename": "ImportError", "evalue": "No module named 'httplib2.error'", "output_type": "error", "traceback": [ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[0;31mImportError\u001b[0m Traceback (most recent call last)", "\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0;32mfrom\u001b[0m \u001b[0mhttplib2\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0merror\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mHTTPError\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m", "\u001b[0;31mImportError\u001b[0m: No module named 'httplib2.error'" ] } ], "source": [ "import httplib2.HttpLib2Error" ] }, { "cell_type": "code", "execution_count": 82, "metadata": { "collapsed": false }, "outputs": [], "source": [ "from urllib.error import HTTPError\n", "import yelp\n", "\n", "def yelp_phone_fetch(num):\n", " \"\"\"\n", " Performs the phone search described in notebook 02 to fetch information on the entity associated with a number.\n", " \"\"\"\n", " if not num:\n", " return None\n", " else:\n", " try:\n", " business = client.phone_search(num).businesses[0]\n", " if business and business.location and business.location.coordinate:\n", " return {\n", " 'Yelp ID': business.id,\n", " 'Yelp Is Claimed': business.is_claimed,\n", " 'Yelp Is Closed': business.is_closed,\n", " 'Yelp Name': business.name,\n", " 'Yelp URL': business.url,\n", " 'Yelp Review Count': business.review_count,\n", " 'Yelp Categories': business.categories,\n", " 'Yelp Rating': business.rating,\n", " 'Yelp Address': business.location.address,\n", " 'Yelp Neighborhoods': business.location.neighborhoods,\n", " 'Yelp Latitude': business.location.coordinate.latitude,\n", " 'Yelp Longitude': business.location.coordinate.longitude,\n", " }\n", " else: # Partial information, skip.\n", " return None\n", " except IndexError: # Phone search failed!\n", " return None\n", " except yelp.errors.InvalidParameter: # Invalid number!\n", " return None" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "After some testing there appears to be a *very* significant miss rate. Remember, we're fuzzy matching phone numbers from one data set with phone numbers in another dataset. It's far from 100% that we'll get something back out. I'm interested in what percentage of the time we're successful." ] }, { "cell_type": "code", "execution_count": 12, "metadata": { "collapsed": true }, "outputs": [], "source": [ "def random_number_dba_tuple():\n", " random_number, random_dba = inspections_fff.sample().iloc[0][['DOHMH PHONE', 'DOHMH DBA']]\n", " random_number = str(int(random_number))\n", " return random_number, random_dba" ] }, { "cell_type": "code", "execution_count": 15, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "(2125878880, 'MULTI TASTES DINER')" ] }, "execution_count": 15, "metadata": {}, "output_type": "execute_result" } ], "source": [ "random_number_dba_tuple()" ] }, { "cell_type": "code", "execution_count": 127, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "{'Yelp Address': ['41 E 11th St'],\n", " 'Yelp Categories': [Category(name='Japanese', alias='japanese')],\n", " 'Yelp ID': 'ootoya-greenwich-village-new-york',\n", " 'Yelp Is Claimed': True,\n", " 'Yelp Is Closed': False,\n", " 'Yelp Latitude': 40.7333107,\n", " 'Yelp Longitude': -73.9929962,\n", " 'Yelp Name': 'Ootoya Greenwich Village',\n", " 'Yelp Neighborhoods': ['Greenwich Village'],\n", " 'Yelp Rating': 4.0,\n", " 'Yelp Review Count': 135,\n", " 'Yelp URL': 'https://www.yelp.com/biz/ootoya-greenwich-village-new-york?adjust_creative=dkJPGu_jtTyHwsEgZIZN6g&utm_campaign=yelp_api&utm_medium=api_v2_phone_search&utm_source=dkJPGu_jtTyHwsEgZIZN6g'}" ] }, "execution_count": 127, "metadata": {}, "output_type": "execute_result" } ], "source": [ "yelp_phone_fetch(random_number_dba_tuple()[0])" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Hey I've been there! Nice. More rigorously:" ] }, { "cell_type": "code", "execution_count": 133, "metadata": { "collapsed": true }, "outputs": [], "source": [ "one_hundred_randoms = [random_number_dba_tuple() for i in range(100)]" ] }, { "cell_type": "code", "execution_count": 138, "metadata": { "collapsed": false }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "\n", " 0%| | 0/100 [00:00\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
DOHMH DBADOHMH BORODOHMH BUILDINGDOHMH STREETDOHMH ZIPCODEDOHMH PHONEDOHMH CUISINE DESCRIPTIONDOHMH INITIAL INSPECTION DATEDOHMH ACTIONDOHMH VIOLATION CODEDOHMH VIOLATION DESCRIPTIONDOHMH CRITICAL FLAGDOHMH SCOREDOHMH GRADEDOHMH GRADE DATEDOHMH RECORD DATEDOHMH INITIAL INSPECTION TYPEDOHMH LATEST INSPECTION DATE
CAMIS
41405535TWO BOOTSMANHATTAN625.09 AVENUE100362.129563e+09Pizza2014-06-24Violations were cited in the following area(s).04LEvidence of mice or live mice present in facil...Critical15.0NaNNaN09/27/2016Cycle Inspection / Initial Inspection2016-09-13
\n", "" ], "text/plain": [ " DOHMH DBA DOHMH BORO DOHMH BUILDING DOHMH STREET DOHMH ZIPCODE \\\n", "CAMIS \n", "41405535 TWO BOOTS MANHATTAN 625.0 9 AVENUE 10036 \n", "\n", " DOHMH PHONE DOHMH CUISINE DESCRIPTION \\\n", "CAMIS \n", "41405535 2.129563e+09 Pizza \n", "\n", " DOHMH INITIAL INSPECTION DATE \\\n", "CAMIS \n", "41405535 2014-06-24 \n", "\n", " DOHMH ACTION \\\n", "CAMIS \n", "41405535 Violations were cited in the following area(s). \n", "\n", " DOHMH VIOLATION CODE \\\n", "CAMIS \n", "41405535 04L \n", "\n", " DOHMH VIOLATION DESCRIPTION \\\n", "CAMIS \n", "41405535 Evidence of mice or live mice present in facil... \n", "\n", " DOHMH CRITICAL FLAG DOHMH SCORE DOHMH GRADE DOHMH GRADE DATE \\\n", "CAMIS \n", "41405535 Critical 15.0 NaN NaN \n", "\n", " DOHMH RECORD DATE DOHMH INITIAL INSPECTION TYPE \\\n", "CAMIS \n", "41405535 09/27/2016 Cycle Inspection / Initial Inspection \n", "\n", " DOHMH LATEST INSPECTION DATE \n", "CAMIS \n", "41405535 2016-09-13 " ] }, "execution_count": 92, "metadata": {}, "output_type": "execute_result" } ], "source": [ "inspections_fff.sample(1)" ] }, { "cell_type": "code", "execution_count": 127, "metadata": { "collapsed": false }, "outputs": [], "source": [ "all_raws[0] = {'Yelp Address': ['1007 Morris Park Avenue'],\n", " 'Yelp Categories': [\"Category(name='Bakeries', alias='bakeries')\",\n", " \"Category(name='Desserts', alias='desserts')\"],\n", " 'Yelp ID': 'morris-pk-bake-shop-bronx',\n", " 'Yelp Is Claimed': False,\n", " 'Yelp Is Closed': False,\n", " 'Yelp Latitude': 40.848445892334,\n", " 'Yelp Longitude': -73.8560791015625,\n", " 'Yelp Name': 'Morris Pk Bake Shop',\n", " 'Yelp Neighborhoods': ['Morris Park'],\n", " 'Yelp Rating': 4.5,\n", " 'Yelp Review Count': 27,\n", " 'Yelp URL': 'https://www.yelp.com/biz/morris-pk-bake-shop-bronx?adjust_creative=dkJPGu_jtTyHwsEgZIZN6g&utm_campaign=yelp_api&utm_medium=api_v2_phone_search&utm_source=dkJPGu_jtTyHwsEgZIZN6g'}" ] }, { "cell_type": "code", "execution_count": 131, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "{'Yelp Address': ['1007 Morris Park Avenue'],\n", " 'Yelp Categories': [\"Category(name='Bakeries', alias='bakeries')\",\n", " \"Category(name='Desserts', alias='desserts')\"],\n", " 'Yelp ID': 'morris-pk-bake-shop-bronx',\n", " 'Yelp Is Claimed': False,\n", " 'Yelp Is Closed': False,\n", " 'Yelp Latitude': 40.848445892334,\n", " 'Yelp Longitude': -73.8560791015625,\n", " 'Yelp Name': 'Morris Pk Bake Shop',\n", " 'Yelp Neighborhoods': ['Morris Park'],\n", " 'Yelp Rating': 4.5,\n", " 'Yelp Review Count': 27,\n", " 'Yelp URL': 'https://www.yelp.com/biz/morris-pk-bake-shop-bronx?adjust_creative=dkJPGu_jtTyHwsEgZIZN6g&utm_campaign=yelp_api&utm_medium=api_v2_phone_search&utm_source=dkJPGu_jtTyHwsEgZIZN6g'}" ] }, "execution_count": 131, "metadata": {}, "output_type": "execute_result" } ], "source": [ "all_raws[0]" ] }, { "cell_type": "code", "execution_count": 232, "metadata": { "collapsed": false }, "outputs": [], "source": [ "import re\n", "import copy\n", "re_cat_word = re.compile(\"name='[-\\w\\s&()/,']+(?=')\")\n", "\n", "def safe_group(match_obj):\n", " try:\n", " return match_obj.group().replace(\"name='\", \"\")\n", " except AttributeError:\n", " return None\n", "\n", "def format_data(yelp_dict):\n", " if yelp_dict:\n", " ret = copy.deepcopy(yelp_dict)\n", " if ret['Yelp Address']:\n", " ret['Yelp Address'] = ret['Yelp Address'][0]\n", " cats = ret['Yelp Categories']\n", " # print(cats)\n", " if cats:\n", " try:\n", " parsed_cats = [re.search(re_cat_word, str(cat)).group().replace(\"name='\", \"\") for cat in cats]\n", " except:\n", " print(cats)\n", " parsed_cats = []\n", " # print(parsed_cats)\n", " ret['Yelp Categories'] = \"|\".join(parsed_cats)\n", " neighborhoods = ret['Yelp Neighborhoods']\n", " if neighborhoods:\n", " ret['Yelp Neighborhoods'] = \"|\".join(ret['Yelp Neighborhoods'])\n", " del ret['Yelp URL']\n", " return ret\n", " else:\n", " return None" ] }, { "cell_type": "code", "execution_count": 235, "metadata": { "collapsed": false }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[Category(name=\"Women's Clothing\", alias='womenscloth')]\n", "[Category(name='Department Stores', alias='deptstores'), Category(name=\"Men's Clothing\", alias='menscloth'), Category(name=\"Women's Clothing\", alias='womenscloth')]\n", "[Category(name=\"Men's Clothing\", alias='menscloth'), Category(name=\"Women's Clothing\", alias='womenscloth')]\n", "[Category(name=\"Men's Clothing\", alias='menscloth'), Category(name='Used, Vintage & Consignment', alias='vintage')]\n", "[Category(name='Jewelry', alias='jewelry'), Category(name=\"Women's Clothing\", alias='womenscloth')]\n", "[Category(name='Motorcycle Gear', alias='motorcyclinggear'), Category(name=\"Men's Clothing\", alias='menscloth'), Category(name='Coffee & Tea', alias='coffee')]\n", "[Category(name=\"Children's Clothing\", alias='childcloth'), Category(name='Ice Cream & Frozen Yogurt', alias='icecream'), Category(name='Desserts', alias='desserts')]\n", "[Category(name='Shoe Stores', alias='shoes'), Category(name=\"Men's Clothing\", alias='menscloth'), Category(name=\"Women's Clothing\", alias='womenscloth')]\n", "[Category(name='Toy Stores', alias='toys'), Category(name=\"Men's Clothing\", alias='menscloth'), Category(name=\"Women's Clothing\", alias='womenscloth')]\n" ] } ], "source": [ "formatted_yelp_data = []\n", "\n", "for raw in tqdm_notebook(all_raws):\n", " formatted_yelp_data.append(format_data(raw))" ] }, { "cell_type": "code", "execution_count": 236, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "{'Yelp Address': '1007 Morris Park Avenue',\n", " 'Yelp Categories': 'Bakeries|Desserts',\n", " 'Yelp ID': 'morris-pk-bake-shop-bronx',\n", " 'Yelp Is Claimed': False,\n", " 'Yelp Is Closed': False,\n", " 'Yelp Latitude': 40.848445892334,\n", " 'Yelp Longitude': -73.8560791015625,\n", " 'Yelp Name': 'Morris Pk Bake Shop',\n", " 'Yelp Neighborhoods': 'Morris Park',\n", " 'Yelp Rating': 4.5,\n", " 'Yelp Review Count': 27}" ] }, "execution_count": 236, "metadata": {}, "output_type": "execute_result" } ], "source": [ "formatted_yelp_data[0]" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Now assign." ] }, { "cell_type": "code", "execution_count": 241, "metadata": { "collapsed": false }, "outputs": [], "source": [ "inspections_ffff = inspections_fff.copy()\n", "\n", "for key in formatted_yelp_data[0].keys():\n", " inspections_ffff[key] = [s[key] if s else None for s in formatted_yelp_data]" ] }, { "cell_type": "code", "execution_count": 249, "metadata": { "collapsed": false }, "outputs": [], "source": [ "inspections_ffff.columns = [col.upper() for col in inspections_ffff.columns]" ] }, { "cell_type": "code", "execution_count": 250, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/html": [ "
\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
DOHMH DBADOHMH BORODOHMH BUILDINGDOHMH STREETDOHMH ZIPCODEDOHMH PHONEDOHMH CUISINE DESCRIPTIONDOHMH INITIAL INSPECTION DATEDOHMH ACTIONDOHMH VIOLATION CODE...YELP LATITUDEYELP ADDRESSYELP IDYELP RATINGYELP REVIEW COUNTYELP IS CLAIMEDYELP LONGITUDEYELP NEIGHBORHOODSYELP CATEGORIESYELP NAME
CAMIS
30075445MORRIS PARK BAKE SHOPBRONX1007.0MORRIS PARK AVE104627.188925e+09Bakery2013-06-01Violations were cited in the following area(s).16B...40.8484461007 Morris Park Avenuemorris-pk-bake-shop-bronx4.527.0False-73.856079Morris ParkBakeries|DessertsMorris Pk Bake Shop
30112340WENDY'SBROOKLYN469.0FLATBUSH AVENUE112257.182875e+09Hamburgers2014-06-05Violations were cited in the following area(s).10B...40.662952469 Flatbush Avewendys-brooklyn-42.023.0False-73.961753Prospect Heights|Prospect Lefferts GardensFast Food|BurgersWendy's
30191841DJ REYNOLDS PUB AND RESTAURANTMANHATTAN351.0WEST 57 STREET100192.122453e+09Irish2013-07-22Violations were cited in the following area(s).10B...40.767750351 W 57th Stdj-reynolds-new-york-33.075.0False-73.984870Midtown West|Hell's KitchenIrish|PubsDJ Reynolds
40356018RIVIERA CATERERBROOKLYN2780.0STILLWELL AVENUE112247.183723e+09American2013-06-05Violations were cited in the following area(s).10F...40.5795212780 Stillwell Averiviera-caterers-brooklyn4.023.0True-73.982430Coney IslandCaterersRiviera Caterers
40356151BRUNOS ON THE BOULEVARDQUEENS8825.0ASTORIA BOULEVARD113697.183351e+09American2014-04-11Violations were cited in the following area(s).04J...40.7642408825 Astoria Blvdevents-by-brunos-jackson-heights4.015.0True-73.880410East ElmhurstCaterers|Venues & Event SpacesEvents By Bruno's
40356483WILKEN'S FINE FOODBROOKLYN7114.0AVENUE U112347.184444e+09Delicatessen2013-07-09Violations were cited in the following area(s).02H...40.6199007114 Ave Uwilkens-ii-deli-brooklyn3.525.0False-73.906853Bergen BeachDelisWilkens II Deli
40356731TASTE THE TROPICS ICE CREAMBROOKLYN1839.0NOSTRAND AVENUE112267.188561e+09Ice Cream, Gelato, Yogurt, Ices2013-07-10Violations were cited in the following area(s).10B...40.6408201839 Nostrand Avetaste-the-tropics-brooklyn4.516.0False-73.948151FlatbushIce Cream & Frozen YogurtTaste the Tropics
40357217WILD ASIABRONX2300.0SOUTHERN BOULEVARD104607.182208e+09American2013-06-19Violations were cited in the following area(s).10B...NaNNoneNoneNaNNaNNoneNaNNoneNoneNone
40357437C & C CATERING SERVICEBROOKLYN7715.018 AVENUE112147.182323e+09American2014-04-16Violations were cited in the following area(s).06D...40.6117137715 18th Avec-and-c-catering-service-brooklyn3.02.0True-73.997261BensonhurstCaterersC & C Catering Service
403594801 EAST 66TH STREET KITCHENMANHATTAN1.0EAST 66 STREET100652.128794e+09American2014-05-07Violations were cited in the following area(s).10B...40.7686841 E 66th Stwyeth-james-new-york0.00.0False-73.969337Upper East SideNoneWyeth James
40359705NATHAN'S FAMOUSBROOKLYN1310.0SURF AVENUE112247.183332e+09Hotdogs2013-12-03Violations were cited in the following area(s).10F...NaNNoneNoneNaNNaNNoneNaNNoneNoneNone
40360045SEUDA FOODSBROOKLYN705.0KINGS HIGHWAY112237.183752e+09Jewish/Kosher2013-10-10Violations were cited in the following area(s).08A...40.606472705 Kings Hwyseuda-foods-brooklyn4.53.0False-73.965415Midwood|GravesendCaterersSeuda Foods
40360076CARVEL ICE CREAMBROOKLYN203.0CHURCH AVENUE112187.184390e+09Ice Cream, Gelato, Yogurt, Ices2014-02-10Violations were cited in the following area(s).10F...40.643380203 Church Avecarvel-brooklyn-33.518.0False-73.978199Kensington|FlatbushIce Cream & Frozen YogurtCarvel
40361322CARVEL ICE CREAMQUEENS26515.0HILLSIDE AVENUE110047.183430e+09Ice Cream, Gelato, Yogurt, Ices2013-09-18Violations were cited in the following area(s).08A...40.74360526515 Hillside Avecarvel-glen-oaks-25.04.0False-73.660313NoneIce Cream & Frozen YogurtCarvel
40361606THE MOVABLE FEASTBROOKLYN284.0PROSPECT PARK WEST112157.189653e+09American2013-11-14Violations were cited in the following area(s).10F...40.658035284 Prospect Park Wthe-movable-feast-brooklyn4.516.0True-73.982879South Slope|Windsor TerraceCaterersThe Movable Feast
40361618SAL'S DELIQUEENS12908.020 AVENUE113567.186619e+09Delicatessen2014-08-16Violations were cited in the following area(s).08C...40.78147112908 20th Avesals-deli-college-point4.54.0False-73.839287College PointDelis|SandwichesSal's Deli
40361708BULLY'S DELIMANHATTAN759.0BROADWAY100032.122550e+09Delicatessen2014-01-21Violations were cited in the following area(s).10J...40.730826759 Broadwaybullys-deli-new-york-133.0110.0True-73.992404Greenwich VillageDelisBully's Deli
40361998STEVE CHU'S DELI & GROCERYQUEENS3406.010 STREET111067.187269e+09Delicatessen2013-03-13Violations were cited in the following area(s).10F...40.7647483406 10th Ststeve-chus-deli-and-grocery-astoria4.04.0False-73.938873AstoriaDelisSteve Chu's Deli & Grocery
40362098HARRIET'S KITCHENMANHATTAN502.0AMSTERDAM AVENUE100242.127210e+09American2014-02-03Violations were cited in the following area(s).04M...40.786678502 Amsterdam Aveharriets-kitchen-new-york3.0106.0True-73.976074Upper West SideAmerican (Traditional)|BurgersHarriet's Kitchen
40362264P & S DELI GROCERYMANHATTAN730.0COLUMBUS AVENUE100252.129323e+09American2013-04-08Violations were cited in the following area(s).02G...40.792419724 Columbus Aveps-deli-and-grocery-manhattan4.02.0False-73.967912Upper West SideGroceryPS Deli and Grocery
40362274ANGELIKA FILM CENTERMANHATTAN18.0WEST HOUSTON STREET100122.129953e+09American2013-04-05Violations were cited in the following area(s).10F...40.72589118 W Houston Stangelika-film-center-and-cafe-new-york-new-york-23.5396.0True-73.996986Greenwich VillageCinema|CafesAngelika Film Center & Cafe - New York
40362432HO MEI RESTAURANTQUEENS10305.037 AVENUE113687.187797e+09Chinese2013-05-02Violations were cited in the following area(s).06D...40.75355210305 37th Avenueho-mei-corona5.03.0False-73.864227North CoronaRestaurantsHo Mei
40362715THE COUNTRY CAFEMANHATTAN60.0WALL STREET100053.474279e+09Sandwiches/Salads/Mixed Buffet2013-09-18Violations were cited in the following area(s).06B...40.70624160 Wall Stthe-country-cafe-new-york-22.516.0False-74.008506Financial DistrictSandwiches|Cafes|Breakfast & BrunchThe Country Cafe
40362869SHASHEMENE INT'L RESTAURABROOKLYN195.0EAST 56 STREET112033.474301e+09Caribbean2013-05-08Violations were cited in the following area(s).10B...NaNNoneNoneNaNNaNNoneNaNNoneNoneNone
40363093CARVEL ICE CREAMBRONX1006.0EAST 233 STREET104667.186527e+09Ice Cream, Gelato, Yogurt, Ices2013-08-02Violations were cited in the following area(s).06D...40.8903311006 E 233rd Stcarvel-bronx-32.05.0False-73.848595EdenwaldIce Cream & Frozen YogurtCarvel
40363098DUNKIN' DONUTSBROOKLYN56.0COURT STREET112017.186252e+09Donuts2013-01-08Violations were cited in the following area(s).08A...40.69227256 Court stdunkin-donuts-brooklyn-1311.02.0False-73.991493Brooklyn HeightsDonuts|Coffee & TeaDunkin' Donuts
40363289HAPPY GARDENBRONX1236.0238 SPOFFORD AVE104747.186172e+09Chinese2013-12-30Violations were cited in the following area(s).10F...40.8140021236 Spofford Avenuechinese-fried-chicken-bronx-30.00.0False-73.889529Hunts PointChineseChinese Fried Chicken
40363298CAFE METROMANHATTAN625.08 AVENUE100182.127149e+09American2013-12-13Violations were cited in the following area(s).06D...40.756252625 8th Ave Bsmt 2cosane-new-york0.00.0False-73.990685Theater District|Midtown West|Hell's KitchenCoffee & TeaCosane
40363333TONY'S DELIQUEENS1069.0WYCKOFF AVENUE113857.183868e+09Delicatessen2013-06-10Violations were cited in the following area(s).04N...40.6949201069 Wyckoff Avenuetonts-too-deli-and-coffee-shop-ridgewood0.00.0False-73.902460Bushwick|RidgewoodDelis|SandwichesTont's Too Deli & Coffee Shop
40363426LEXLER DELIMANHATTAN405.0LEXINGTON AVENUE101742.126871e+09Sandwiches/Salads/Mixed Buffet2013-08-21Violations were cited in the following area(s).10F...40.751910405 Lexington Avelexler-deli-new-york4.515.0False-73.975530Midtown EastDelisLexler Deli
..................................................................
50055989NaNQUEENS25109.0NORTHERN BLVD113623.473282e+09Other1900-01-01NaNNaN...NaNNoneNoneNaNNaNNoneNaNNoneNoneNone
50055990RESTAURANT ASSOCIATES INCMANHATTAN1177.0AVENUE OF THE AMERICAS100362.123363e+09Other1900-01-01NaNNaN...NaNNoneNoneNaNNaNNoneNaNNoneNoneNone
50055996NaNMANHATTANNaNCANAL ST100137.184619e+09Other1900-01-01NaNNaN...40.75979239-15 Main Stalicechencpa-queens1.03.0False-73.830063Flushing|Downtown FlushingFinancial ServicesAliceChenCPA
50055997NaNBRONX1167.0BOSTON RD104567.184508e+09Other1900-01-01NaNNaN...40.8288401167 Boston Rdmikes-pizza-and-pasta-bronx5.01.0False-73.903340MorrisaniaPizzaMike's Pizza and Pasta
50056005SANTA PANZABROOKLYN1079.0BROADWAY112217.186980e+09Other1900-01-01NaNNaN...NaNNoneNoneNaNNaNNoneNaNNoneNoneNone
50056006NaNBROOKLYN239.0BRIGHTON BEACH AVE112359.019072e+09Other1900-01-01NaNNaN...NaNNoneNoneNaNNaNNoneNaNNoneNoneNone
50056007NaNMANHATTAN1.0E 35TH ST100169.178265e+09Other1900-01-01NaNNaN...NaNNoneNoneNaNNaNNoneNaNNoneNoneNone
50056009NaNQUEENS15702.0NORTHERN BLVD113549.176238e+09Other1900-01-01NaNNaN...NaNNoneNoneNaNNaNNoneNaNNoneNoneNone
50056014PIZZA ROYALEBROOKLYN6716.0FORT HAMILTON PKWY112197.182385e+09Other1900-01-01NaNNaN...40.6293316718 Fort Hamilton Pkwypizza-royale-brooklyn3.039.0True-74.011227Dyker HeightsPizza|ItalianPizza Royale
50056016NaNQUEENS1526.0COLLEGE POINT BLVD113569.178734e+09Other1900-01-01NaNNaN...NaNNoneNoneNaNNaNNoneNaNNoneNoneNone
50056017VANGUARD WINE BARMANHATTAN1372.01ST AVE100212.122889e+09Other1900-01-01NaNNaN...NaNNoneNoneNaNNaNNoneNaNNoneNoneNone
50056018NaNBRONX3513.0E TREMONT AVE104657.188220e+09Other1900-01-01NaNNaN...40.8309783513 E Tremont Avelegendary-bar-and-restaurant-bronx4.511.0False-73.826118SchuylervilleBars|ItalianLegendary Bar & Restaurant
50056020DOT & LINEBROOKLYN253.0BERGEN ST112173.475178e+08Other1900-01-01NaNNaN...NaNNoneNoneNaNNaNNoneNaNNoneNoneNone
50056021NaNMANHATTAN2656.0BROADWAY100257.184900e+09Other1900-01-01NaNNaN...40.7975902656 Broadwaylava-kitchen-new-york0.00.0True-73.969310Manhattan ValleyChinese|Asian Fusion|NoodlesLava Kitchen
50056022NaNQUEENS3526.0FARRINGTON ST113547.184600e+09Other1900-01-01NaNNaN...40.7636703526 Farrington Stjoomakgol-flushing4.547.0True-73.831750Flushing|Downtown FlushingKoreanJooMakGol
50056030NaNQUEENS11916.0ROCKAWAY BLVD114209.178057e+09Other1900-01-01NaNNaN...NaNNoneNoneNaNNaNNoneNaNNoneNoneNone
50056031NaNBROOKLYN652.0PENNSYLVANIA AVE112079.174454e+09Other1900-01-01NaNNaN...NaNNoneNoneNaNNaNNoneNaNNoneNoneNone
50056033NaNQUEENS10837.0CORONA AVE113689.172952e+09Other1900-01-01NaNNaN...NaNNoneNoneNaNNaNNoneNaNNoneNoneNone
50056036NORTHERN CAFE INC.QUEENS10113.0NORTHERN BLVD113683.477838e+09Other1900-01-01NaNNaN...NaNNoneNoneNaNNaNNoneNaNNoneNoneNone
50056056NaNQUEENS1304.0BEACH CHANNEL DR116913.478130e+09Other1900-01-01NaNNaN...NaNNoneNoneNaNNaNNoneNaNNoneNoneNone
50056057NaNQUEENS6418.0108TH ST113759.173228e+09Other1900-01-01NaNNaN...NaNNoneNoneNaNNaNNoneNaNNoneNoneNone
50056063NaNMANHATTAN200.0DYCKMAN ST100403.472959e+09Other1900-01-01NaNNaN...NaNNoneNoneNaNNaNNoneNaNNoneNoneNone
50056065NaNMANHATTAN4241.0BROADWAY100336.468212e+09Other1900-01-01NaNNaN...NaNNoneNoneNaNNaNNoneNaNNoneNoneNone
50056067HAROLD'S MEAT & THREEMANHATTAN231.0HUDSON ST100133.476752e+09Other1900-01-01NaNNaN...NaNNoneNoneNaNNaNNoneNaNNoneNoneNone
50056068XELAJU RESTAURANTQUEENS8830.0PARSONS BLVD114327.186573e+09Other1900-01-01NaNNaN...40.70691188-30 Parsons Blvdluna-de-xelaju-restaurant-and-pizzeria-jamaica2.01.0False-73.802483JamaicaSpanishLuna de Xelaju Restaurant & Pizzeria
50056069NaNMANHATTAN4484.0BROADWAY100409.172041e+09Other1900-01-01NaNNaN...NaNNoneNoneNaNNaNNoneNaNNoneNoneNone
50056073CULINART INCMANHATTAN1.0UN PLZ100172.127581e+09Other1900-01-01NaNNaN...NaNNoneNoneNaNNaNNoneNaNNoneNoneNone
50056074ABRACOMANHATTAN81.0E 7TH ST100033.476102e+09Other1900-01-01NaNNaN...NaNNoneNoneNaNNaNNoneNaNNoneNoneNone
50056081NaNMANHATTAN232.0E 111TH ST100299.174841e+09Other1900-01-01NaNNaN...NaNNoneNoneNaNNaNNoneNaNNoneNoneNone
50056087NaNBROOKLYN293.0AVENUE X112239.177708e+09Other1900-01-01NaNNaN...NaNNoneNoneNaNNaNNoneNaNNoneNoneNone
\n", "

26064 rows × 29 columns

\n", "
" ], "text/plain": [ " DOHMH DBA DOHMH BORO DOHMH BUILDING \\\n", "CAMIS \n", "30075445 MORRIS PARK BAKE SHOP BRONX 1007.0 \n", "30112340 WENDY'S BROOKLYN 469.0 \n", "30191841 DJ REYNOLDS PUB AND RESTAURANT MANHATTAN 351.0 \n", "40356018 RIVIERA CATERER BROOKLYN 2780.0 \n", "40356151 BRUNOS ON THE BOULEVARD QUEENS 8825.0 \n", "40356483 WILKEN'S FINE FOOD BROOKLYN 7114.0 \n", "40356731 TASTE THE TROPICS ICE CREAM BROOKLYN 1839.0 \n", "40357217 WILD ASIA BRONX 2300.0 \n", "40357437 C & C CATERING SERVICE BROOKLYN 7715.0 \n", "40359480 1 EAST 66TH STREET KITCHEN MANHATTAN 1.0 \n", "40359705 NATHAN'S FAMOUS BROOKLYN 1310.0 \n", "40360045 SEUDA FOODS BROOKLYN 705.0 \n", "40360076 CARVEL ICE CREAM BROOKLYN 203.0 \n", "40361322 CARVEL ICE CREAM QUEENS 26515.0 \n", "40361606 THE MOVABLE FEAST BROOKLYN 284.0 \n", "40361618 SAL'S DELI QUEENS 12908.0 \n", "40361708 BULLY'S DELI MANHATTAN 759.0 \n", "40361998 STEVE CHU'S DELI & GROCERY QUEENS 3406.0 \n", "40362098 HARRIET'S KITCHEN MANHATTAN 502.0 \n", "40362264 P & S DELI GROCERY MANHATTAN 730.0 \n", "40362274 ANGELIKA FILM CENTER MANHATTAN 18.0 \n", "40362432 HO MEI RESTAURANT QUEENS 10305.0 \n", "40362715 THE COUNTRY CAFE MANHATTAN 60.0 \n", "40362869 SHASHEMENE INT'L RESTAURA BROOKLYN 195.0 \n", "40363093 CARVEL ICE CREAM BRONX 1006.0 \n", "40363098 DUNKIN' DONUTS BROOKLYN 56.0 \n", "40363289 HAPPY GARDEN BRONX 1236.0 \n", "40363298 CAFE METRO MANHATTAN 625.0 \n", "40363333 TONY'S DELI QUEENS 1069.0 \n", "40363426 LEXLER DELI MANHATTAN 405.0 \n", "... ... ... ... \n", "50055989 NaN QUEENS 25109.0 \n", "50055990 RESTAURANT ASSOCIATES INC MANHATTAN 1177.0 \n", "50055996 NaN MANHATTAN NaN \n", "50055997 NaN BRONX 1167.0 \n", "50056005 SANTA PANZA BROOKLYN 1079.0 \n", "50056006 NaN BROOKLYN 239.0 \n", "50056007 NaN MANHATTAN 1.0 \n", "50056009 NaN QUEENS 15702.0 \n", "50056014 PIZZA ROYALE BROOKLYN 6716.0 \n", "50056016 NaN QUEENS 1526.0 \n", "50056017 VANGUARD WINE BAR MANHATTAN 1372.0 \n", "50056018 NaN BRONX 3513.0 \n", "50056020 DOT & LINE BROOKLYN 253.0 \n", "50056021 NaN MANHATTAN 2656.0 \n", "50056022 NaN QUEENS 3526.0 \n", "50056030 NaN QUEENS 11916.0 \n", "50056031 NaN BROOKLYN 652.0 \n", "50056033 NaN QUEENS 10837.0 \n", "50056036 NORTHERN CAFE INC. QUEENS 10113.0 \n", "50056056 NaN QUEENS 1304.0 \n", "50056057 NaN QUEENS 6418.0 \n", "50056063 NaN MANHATTAN 200.0 \n", "50056065 NaN MANHATTAN 4241.0 \n", "50056067 HAROLD'S MEAT & THREE MANHATTAN 231.0 \n", "50056068 XELAJU RESTAURANT QUEENS 8830.0 \n", "50056069 NaN MANHATTAN 4484.0 \n", "50056073 CULINART INC MANHATTAN 1.0 \n", "50056074 ABRACO MANHATTAN 81.0 \n", "50056081 NaN MANHATTAN 232.0 \n", "50056087 NaN BROOKLYN 293.0 \n", "\n", " DOHMH STREET DOHMH ZIPCODE DOHMH PHONE \\\n", "CAMIS \n", "30075445 MORRIS PARK AVE 10462 7.188925e+09 \n", "30112340 FLATBUSH AVENUE 11225 7.182875e+09 \n", "30191841 WEST 57 STREET 10019 2.122453e+09 \n", "40356018 STILLWELL AVENUE 11224 7.183723e+09 \n", "40356151 ASTORIA BOULEVARD 11369 7.183351e+09 \n", "40356483 AVENUE U 11234 7.184444e+09 \n", "40356731 NOSTRAND AVENUE 11226 7.188561e+09 \n", "40357217 SOUTHERN BOULEVARD 10460 7.182208e+09 \n", "40357437 18 AVENUE 11214 7.182323e+09 \n", "40359480 EAST 66 STREET 10065 2.128794e+09 \n", "40359705 SURF AVENUE 11224 7.183332e+09 \n", "40360045 KINGS HIGHWAY 11223 7.183752e+09 \n", "40360076 CHURCH AVENUE 11218 7.184390e+09 \n", "40361322 HILLSIDE AVENUE 11004 7.183430e+09 \n", "40361606 PROSPECT PARK WEST 11215 7.189653e+09 \n", "40361618 20 AVENUE 11356 7.186619e+09 \n", "40361708 BROADWAY 10003 2.122550e+09 \n", "40361998 10 STREET 11106 7.187269e+09 \n", "40362098 AMSTERDAM AVENUE 10024 2.127210e+09 \n", "40362264 COLUMBUS AVENUE 10025 2.129323e+09 \n", "40362274 WEST HOUSTON STREET 10012 2.129953e+09 \n", "40362432 37 AVENUE 11368 7.187797e+09 \n", "40362715 WALL STREET 10005 3.474279e+09 \n", "40362869 EAST 56 STREET 11203 3.474301e+09 \n", "40363093 EAST 233 STREET 10466 7.186527e+09 \n", "40363098 COURT STREET 11201 7.186252e+09 \n", "40363289 238 SPOFFORD AVE 10474 7.186172e+09 \n", "40363298 8 AVENUE 10018 2.127149e+09 \n", "40363333 WYCKOFF AVENUE 11385 7.183868e+09 \n", "40363426 LEXINGTON AVENUE 10174 2.126871e+09 \n", "... ... ... ... \n", "50055989 NORTHERN BLVD 11362 3.473282e+09 \n", "50055990 AVENUE OF THE AMERICAS 10036 2.123363e+09 \n", "50055996 CANAL ST 10013 7.184619e+09 \n", "50055997 BOSTON RD 10456 7.184508e+09 \n", "50056005 BROADWAY 11221 7.186980e+09 \n", "50056006 BRIGHTON BEACH AVE 11235 9.019072e+09 \n", "50056007 E 35TH ST 10016 9.178265e+09 \n", "50056009 NORTHERN BLVD 11354 9.176238e+09 \n", "50056014 FORT HAMILTON PKWY 11219 7.182385e+09 \n", "50056016 COLLEGE POINT BLVD 11356 9.178734e+09 \n", "50056017 1ST AVE 10021 2.122889e+09 \n", "50056018 E TREMONT AVE 10465 7.188220e+09 \n", "50056020 BERGEN ST 11217 3.475178e+08 \n", "50056021 BROADWAY 10025 7.184900e+09 \n", "50056022 FARRINGTON ST 11354 7.184600e+09 \n", "50056030 ROCKAWAY BLVD 11420 9.178057e+09 \n", "50056031 PENNSYLVANIA AVE 11207 9.174454e+09 \n", "50056033 CORONA AVE 11368 9.172952e+09 \n", "50056036 NORTHERN BLVD 11368 3.477838e+09 \n", "50056056 BEACH CHANNEL DR 11691 3.478130e+09 \n", "50056057 108TH ST 11375 9.173228e+09 \n", "50056063 DYCKMAN ST 10040 3.472959e+09 \n", "50056065 BROADWAY 10033 6.468212e+09 \n", "50056067 HUDSON ST 10013 3.476752e+09 \n", "50056068 PARSONS BLVD 11432 7.186573e+09 \n", "50056069 BROADWAY 10040 9.172041e+09 \n", "50056073 UN PLZ 10017 2.127581e+09 \n", "50056074 E 7TH ST 10003 3.476102e+09 \n", "50056081 E 111TH ST 10029 9.174841e+09 \n", "50056087 AVENUE X 11223 9.177708e+09 \n", "\n", " DOHMH CUISINE DESCRIPTION DOHMH INITIAL INSPECTION DATE \\\n", "CAMIS \n", "30075445 Bakery 2013-06-01 \n", "30112340 Hamburgers 2014-06-05 \n", "30191841 Irish 2013-07-22 \n", "40356018 American 2013-06-05 \n", "40356151 American 2014-04-11 \n", "40356483 Delicatessen 2013-07-09 \n", "40356731 Ice Cream, Gelato, Yogurt, Ices 2013-07-10 \n", "40357217 American 2013-06-19 \n", "40357437 American 2014-04-16 \n", "40359480 American 2014-05-07 \n", "40359705 Hotdogs 2013-12-03 \n", "40360045 Jewish/Kosher 2013-10-10 \n", "40360076 Ice Cream, Gelato, Yogurt, Ices 2014-02-10 \n", "40361322 Ice Cream, Gelato, Yogurt, Ices 2013-09-18 \n", "40361606 American 2013-11-14 \n", "40361618 Delicatessen 2014-08-16 \n", "40361708 Delicatessen 2014-01-21 \n", "40361998 Delicatessen 2013-03-13 \n", "40362098 American 2014-02-03 \n", "40362264 American 2013-04-08 \n", "40362274 American 2013-04-05 \n", "40362432 Chinese 2013-05-02 \n", "40362715 Sandwiches/Salads/Mixed Buffet 2013-09-18 \n", "40362869 Caribbean 2013-05-08 \n", "40363093 Ice Cream, Gelato, Yogurt, Ices 2013-08-02 \n", "40363098 Donuts 2013-01-08 \n", "40363289 Chinese 2013-12-30 \n", "40363298 American 2013-12-13 \n", "40363333 Delicatessen 2013-06-10 \n", "40363426 Sandwiches/Salads/Mixed Buffet 2013-08-21 \n", "... ... ... \n", "50055989 Other 1900-01-01 \n", "50055990 Other 1900-01-01 \n", "50055996 Other 1900-01-01 \n", "50055997 Other 1900-01-01 \n", "50056005 Other 1900-01-01 \n", "50056006 Other 1900-01-01 \n", "50056007 Other 1900-01-01 \n", "50056009 Other 1900-01-01 \n", "50056014 Other 1900-01-01 \n", "50056016 Other 1900-01-01 \n", "50056017 Other 1900-01-01 \n", "50056018 Other 1900-01-01 \n", "50056020 Other 1900-01-01 \n", "50056021 Other 1900-01-01 \n", "50056022 Other 1900-01-01 \n", "50056030 Other 1900-01-01 \n", "50056031 Other 1900-01-01 \n", "50056033 Other 1900-01-01 \n", "50056036 Other 1900-01-01 \n", "50056056 Other 1900-01-01 \n", "50056057 Other 1900-01-01 \n", "50056063 Other 1900-01-01 \n", "50056065 Other 1900-01-01 \n", "50056067 Other 1900-01-01 \n", "50056068 Other 1900-01-01 \n", "50056069 Other 1900-01-01 \n", "50056073 Other 1900-01-01 \n", "50056074 Other 1900-01-01 \n", "50056081 Other 1900-01-01 \n", "50056087 Other 1900-01-01 \n", "\n", " DOHMH ACTION \\\n", "CAMIS \n", "30075445 Violations were cited in the following area(s). \n", "30112340 Violations were cited in the following area(s). \n", "30191841 Violations were cited in the following area(s). \n", "40356018 Violations were cited in the following area(s). \n", "40356151 Violations were cited in the following area(s). \n", "40356483 Violations were cited in the following area(s). \n", "40356731 Violations were cited in the following area(s). \n", "40357217 Violations were cited in the following area(s). \n", "40357437 Violations were cited in the following area(s). \n", "40359480 Violations were cited in the following area(s). \n", "40359705 Violations were cited in the following area(s). \n", "40360045 Violations were cited in the following area(s). \n", "40360076 Violations were cited in the following area(s). \n", "40361322 Violations were cited in the following area(s). \n", "40361606 Violations were cited in the following area(s). \n", "40361618 Violations were cited in the following area(s). \n", "40361708 Violations were cited in the following area(s). \n", "40361998 Violations were cited in the following area(s). \n", "40362098 Violations were cited in the following area(s). \n", "40362264 Violations were cited in the following area(s). \n", "40362274 Violations were cited in the following area(s). \n", "40362432 Violations were cited in the following area(s). \n", "40362715 Violations were cited in the following area(s). \n", "40362869 Violations were cited in the following area(s). \n", "40363093 Violations were cited in the following area(s). \n", "40363098 Violations were cited in the following area(s). \n", "40363289 Violations were cited in the following area(s). \n", "40363298 Violations were cited in the following area(s). \n", "40363333 Violations were cited in the following area(s). \n", "40363426 Violations were cited in the following area(s). \n", "... ... \n", "50055989 NaN \n", "50055990 NaN \n", "50055996 NaN \n", "50055997 NaN \n", "50056005 NaN \n", "50056006 NaN \n", "50056007 NaN \n", "50056009 NaN \n", "50056014 NaN \n", "50056016 NaN \n", "50056017 NaN \n", "50056018 NaN \n", "50056020 NaN \n", "50056021 NaN \n", "50056022 NaN \n", "50056030 NaN \n", "50056031 NaN \n", "50056033 NaN \n", "50056036 NaN \n", "50056056 NaN \n", "50056057 NaN \n", "50056063 NaN \n", "50056065 NaN \n", "50056067 NaN \n", "50056068 NaN \n", "50056069 NaN \n", "50056073 NaN \n", "50056074 NaN \n", "50056081 NaN \n", "50056087 NaN \n", "\n", " DOHMH VIOLATION CODE ... \\\n", "CAMIS ... \n", "30075445 16B ... \n", "30112340 10B ... \n", "30191841 10B ... \n", "40356018 10F ... \n", "40356151 04J ... \n", "40356483 02H ... \n", "40356731 10B ... \n", "40357217 10B ... \n", "40357437 06D ... \n", "40359480 10B ... \n", "40359705 10F ... \n", "40360045 08A ... \n", "40360076 10F ... \n", "40361322 08A ... \n", "40361606 10F ... \n", "40361618 08C ... \n", "40361708 10J ... \n", "40361998 10F ... \n", "40362098 04M ... \n", "40362264 02G ... \n", "40362274 10F ... \n", "40362432 06D ... \n", "40362715 06B ... \n", "40362869 10B ... \n", "40363093 06D ... \n", "40363098 08A ... \n", "40363289 10F ... \n", "40363298 06D ... \n", "40363333 04N ... \n", "40363426 10F ... \n", "... ... ... \n", "50055989 NaN ... \n", "50055990 NaN ... \n", "50055996 NaN ... \n", "50055997 NaN ... \n", "50056005 NaN ... \n", "50056006 NaN ... \n", "50056007 NaN ... \n", "50056009 NaN ... \n", "50056014 NaN ... \n", "50056016 NaN ... \n", "50056017 NaN ... \n", "50056018 NaN ... \n", "50056020 NaN ... \n", "50056021 NaN ... \n", "50056022 NaN ... \n", "50056030 NaN ... \n", "50056031 NaN ... \n", "50056033 NaN ... \n", "50056036 NaN ... \n", "50056056 NaN ... \n", "50056057 NaN ... \n", "50056063 NaN ... \n", "50056065 NaN ... \n", "50056067 NaN ... \n", "50056068 NaN ... \n", "50056069 NaN ... \n", "50056073 NaN ... \n", "50056074 NaN ... \n", "50056081 NaN ... \n", "50056087 NaN ... \n", "\n", " YELP LATITUDE YELP ADDRESS \\\n", "CAMIS \n", "30075445 40.848446 1007 Morris Park Avenue \n", "30112340 40.662952 469 Flatbush Ave \n", "30191841 40.767750 351 W 57th St \n", "40356018 40.579521 2780 Stillwell Ave \n", "40356151 40.764240 8825 Astoria Blvd \n", "40356483 40.619900 7114 Ave U \n", "40356731 40.640820 1839 Nostrand Ave \n", "40357217 NaN None \n", "40357437 40.611713 7715 18th Ave \n", "40359480 40.768684 1 E 66th St \n", "40359705 NaN None \n", "40360045 40.606472 705 Kings Hwy \n", "40360076 40.643380 203 Church Ave \n", "40361322 40.743605 26515 Hillside Ave \n", "40361606 40.658035 284 Prospect Park W \n", "40361618 40.781471 12908 20th Ave \n", "40361708 40.730826 759 Broadway \n", "40361998 40.764748 3406 10th St \n", "40362098 40.786678 502 Amsterdam Ave \n", "40362264 40.792419 724 Columbus Ave \n", "40362274 40.725891 18 W Houston St \n", "40362432 40.753552 10305 37th Avenue \n", "40362715 40.706241 60 Wall St \n", "40362869 NaN None \n", "40363093 40.890331 1006 E 233rd St \n", "40363098 40.692272 56 Court st \n", "40363289 40.814002 1236 Spofford Avenue \n", "40363298 40.756252 625 8th Ave Bsmt 2 \n", "40363333 40.694920 1069 Wyckoff Avenue \n", "40363426 40.751910 405 Lexington Ave \n", "... ... ... \n", "50055989 NaN None \n", "50055990 NaN None \n", "50055996 40.759792 39-15 Main St \n", "50055997 40.828840 1167 Boston Rd \n", "50056005 NaN None \n", "50056006 NaN None \n", "50056007 NaN None \n", "50056009 NaN None \n", "50056014 40.629331 6718 Fort Hamilton Pkwy \n", "50056016 NaN None \n", "50056017 NaN None \n", "50056018 40.830978 3513 E Tremont Ave \n", "50056020 NaN None \n", "50056021 40.797590 2656 Broadway \n", "50056022 40.763670 3526 Farrington St \n", "50056030 NaN None \n", "50056031 NaN None \n", "50056033 NaN None \n", "50056036 NaN None \n", "50056056 NaN None \n", "50056057 NaN None \n", "50056063 NaN None \n", "50056065 NaN None \n", "50056067 NaN None \n", "50056068 40.706911 88-30 Parsons Blvd \n", "50056069 NaN None \n", "50056073 NaN None \n", "50056074 NaN None \n", "50056081 NaN None \n", "50056087 NaN None \n", "\n", " YELP ID YELP RATING \\\n", "CAMIS \n", "30075445 morris-pk-bake-shop-bronx 4.5 \n", "30112340 wendys-brooklyn-4 2.0 \n", "30191841 dj-reynolds-new-york-3 3.0 \n", "40356018 riviera-caterers-brooklyn 4.0 \n", "40356151 events-by-brunos-jackson-heights 4.0 \n", "40356483 wilkens-ii-deli-brooklyn 3.5 \n", "40356731 taste-the-tropics-brooklyn 4.5 \n", "40357217 None NaN \n", "40357437 c-and-c-catering-service-brooklyn 3.0 \n", "40359480 wyeth-james-new-york 0.0 \n", "40359705 None NaN \n", "40360045 seuda-foods-brooklyn 4.5 \n", "40360076 carvel-brooklyn-3 3.5 \n", "40361322 carvel-glen-oaks-2 5.0 \n", "40361606 the-movable-feast-brooklyn 4.5 \n", "40361618 sals-deli-college-point 4.5 \n", "40361708 bullys-deli-new-york-13 3.0 \n", "40361998 steve-chus-deli-and-grocery-astoria 4.0 \n", "40362098 harriets-kitchen-new-york 3.0 \n", "40362264 ps-deli-and-grocery-manhattan 4.0 \n", "40362274 angelika-film-center-and-cafe-new-york-new-york-2 3.5 \n", "40362432 ho-mei-corona 5.0 \n", "40362715 the-country-cafe-new-york-2 2.5 \n", "40362869 None NaN \n", "40363093 carvel-bronx-3 2.0 \n", "40363098 dunkin-donuts-brooklyn-131 1.0 \n", "40363289 chinese-fried-chicken-bronx-3 0.0 \n", "40363298 cosane-new-york 0.0 \n", "40363333 tonts-too-deli-and-coffee-shop-ridgewood 0.0 \n", "40363426 lexler-deli-new-york 4.5 \n", "... ... ... \n", "50055989 None NaN \n", "50055990 None NaN \n", "50055996 alicechencpa-queens 1.0 \n", "50055997 mikes-pizza-and-pasta-bronx 5.0 \n", "50056005 None NaN \n", "50056006 None NaN \n", "50056007 None NaN \n", "50056009 None NaN \n", "50056014 pizza-royale-brooklyn 3.0 \n", "50056016 None NaN \n", "50056017 None NaN \n", "50056018 legendary-bar-and-restaurant-bronx 4.5 \n", "50056020 None NaN \n", "50056021 lava-kitchen-new-york 0.0 \n", "50056022 joomakgol-flushing 4.5 \n", "50056030 None NaN \n", "50056031 None NaN \n", "50056033 None NaN \n", "50056036 None NaN \n", "50056056 None NaN \n", "50056057 None NaN \n", "50056063 None NaN \n", "50056065 None NaN \n", "50056067 None NaN \n", "50056068 luna-de-xelaju-restaurant-and-pizzeria-jamaica 2.0 \n", "50056069 None NaN \n", "50056073 None NaN \n", "50056074 None NaN \n", "50056081 None NaN \n", "50056087 None NaN \n", "\n", " YELP REVIEW COUNT YELP IS CLAIMED YELP LONGITUDE \\\n", "CAMIS \n", "30075445 27.0 False -73.856079 \n", "30112340 23.0 False -73.961753 \n", "30191841 75.0 False -73.984870 \n", "40356018 23.0 True -73.982430 \n", "40356151 15.0 True -73.880410 \n", "40356483 25.0 False -73.906853 \n", "40356731 16.0 False -73.948151 \n", "40357217 NaN None NaN \n", "40357437 2.0 True -73.997261 \n", "40359480 0.0 False -73.969337 \n", "40359705 NaN None NaN \n", "40360045 3.0 False -73.965415 \n", "40360076 18.0 False -73.978199 \n", "40361322 4.0 False -73.660313 \n", "40361606 16.0 True -73.982879 \n", "40361618 4.0 False -73.839287 \n", "40361708 110.0 True -73.992404 \n", "40361998 4.0 False -73.938873 \n", "40362098 106.0 True -73.976074 \n", "40362264 2.0 False -73.967912 \n", "40362274 396.0 True -73.996986 \n", "40362432 3.0 False -73.864227 \n", "40362715 16.0 False -74.008506 \n", "40362869 NaN None NaN \n", "40363093 5.0 False -73.848595 \n", "40363098 2.0 False -73.991493 \n", "40363289 0.0 False -73.889529 \n", "40363298 0.0 False -73.990685 \n", "40363333 0.0 False -73.902460 \n", "40363426 15.0 False -73.975530 \n", "... ... ... ... \n", "50055989 NaN None NaN \n", "50055990 NaN None NaN \n", "50055996 3.0 False -73.830063 \n", "50055997 1.0 False -73.903340 \n", "50056005 NaN None NaN \n", "50056006 NaN None NaN \n", "50056007 NaN None NaN \n", "50056009 NaN None NaN \n", "50056014 39.0 True -74.011227 \n", "50056016 NaN None NaN \n", "50056017 NaN None NaN \n", "50056018 11.0 False -73.826118 \n", "50056020 NaN None NaN \n", "50056021 0.0 True -73.969310 \n", "50056022 47.0 True -73.831750 \n", "50056030 NaN None NaN \n", "50056031 NaN None NaN \n", "50056033 NaN None NaN \n", "50056036 NaN None NaN \n", "50056056 NaN None NaN \n", "50056057 NaN None NaN \n", "50056063 NaN None NaN \n", "50056065 NaN None NaN \n", "50056067 NaN None NaN \n", "50056068 1.0 False -73.802483 \n", "50056069 NaN None NaN \n", "50056073 NaN None NaN \n", "50056074 NaN None NaN \n", "50056081 NaN None NaN \n", "50056087 NaN None NaN \n", "\n", " YELP NEIGHBORHOODS \\\n", "CAMIS \n", "30075445 Morris Park \n", "30112340 Prospect Heights|Prospect Lefferts Gardens \n", "30191841 Midtown West|Hell's Kitchen \n", "40356018 Coney Island \n", "40356151 East Elmhurst \n", "40356483 Bergen Beach \n", "40356731 Flatbush \n", "40357217 None \n", "40357437 Bensonhurst \n", "40359480 Upper East Side \n", "40359705 None \n", "40360045 Midwood|Gravesend \n", "40360076 Kensington|Flatbush \n", "40361322 None \n", "40361606 South Slope|Windsor Terrace \n", "40361618 College Point \n", "40361708 Greenwich Village \n", "40361998 Astoria \n", "40362098 Upper West Side \n", "40362264 Upper West Side \n", "40362274 Greenwich Village \n", "40362432 North Corona \n", "40362715 Financial District \n", "40362869 None \n", "40363093 Edenwald \n", "40363098 Brooklyn Heights \n", "40363289 Hunts Point \n", "40363298 Theater District|Midtown West|Hell's Kitchen \n", "40363333 Bushwick|Ridgewood \n", "40363426 Midtown East \n", "... ... \n", "50055989 None \n", "50055990 None \n", "50055996 Flushing|Downtown Flushing \n", "50055997 Morrisania \n", "50056005 None \n", "50056006 None \n", "50056007 None \n", "50056009 None \n", "50056014 Dyker Heights \n", "50056016 None \n", "50056017 None \n", "50056018 Schuylerville \n", "50056020 None \n", "50056021 Manhattan Valley \n", "50056022 Flushing|Downtown Flushing \n", "50056030 None \n", "50056031 None \n", "50056033 None \n", "50056036 None \n", "50056056 None \n", "50056057 None \n", "50056063 None \n", "50056065 None \n", "50056067 None \n", "50056068 Jamaica \n", "50056069 None \n", "50056073 None \n", "50056074 None \n", "50056081 None \n", "50056087 None \n", "\n", " YELP CATEGORIES \\\n", "CAMIS \n", "30075445 Bakeries|Desserts \n", "30112340 Fast Food|Burgers \n", "30191841 Irish|Pubs \n", "40356018 Caterers \n", "40356151 Caterers|Venues & Event Spaces \n", "40356483 Delis \n", "40356731 Ice Cream & Frozen Yogurt \n", "40357217 None \n", "40357437 Caterers \n", "40359480 None \n", "40359705 None \n", "40360045 Caterers \n", "40360076 Ice Cream & Frozen Yogurt \n", "40361322 Ice Cream & Frozen Yogurt \n", "40361606 Caterers \n", "40361618 Delis|Sandwiches \n", "40361708 Delis \n", "40361998 Delis \n", "40362098 American (Traditional)|Burgers \n", "40362264 Grocery \n", "40362274 Cinema|Cafes \n", "40362432 Restaurants \n", "40362715 Sandwiches|Cafes|Breakfast & Brunch \n", "40362869 None \n", "40363093 Ice Cream & Frozen Yogurt \n", "40363098 Donuts|Coffee & Tea \n", "40363289 Chinese \n", "40363298 Coffee & Tea \n", "40363333 Delis|Sandwiches \n", "40363426 Delis \n", "... ... \n", "50055989 None \n", "50055990 None \n", "50055996 Financial Services \n", "50055997 Pizza \n", "50056005 None \n", "50056006 None \n", "50056007 None \n", "50056009 None \n", "50056014 Pizza|Italian \n", "50056016 None \n", "50056017 None \n", "50056018 Bars|Italian \n", "50056020 None \n", "50056021 Chinese|Asian Fusion|Noodles \n", "50056022 Korean \n", "50056030 None \n", "50056031 None \n", "50056033 None \n", "50056036 None \n", "50056056 None \n", "50056057 None \n", "50056063 None \n", "50056065 None \n", "50056067 None \n", "50056068 Spanish \n", "50056069 None \n", "50056073 None \n", "50056074 None \n", "50056081 None \n", "50056087 None \n", "\n", " YELP NAME \n", "CAMIS \n", "30075445 Morris Pk Bake Shop \n", "30112340 Wendy's \n", "30191841 DJ Reynolds \n", "40356018 Riviera Caterers \n", "40356151 Events By Bruno's \n", "40356483 Wilkens II Deli \n", "40356731 Taste the Tropics \n", "40357217 None \n", "40357437 C & C Catering Service \n", "40359480 Wyeth James \n", "40359705 None \n", "40360045 Seuda Foods \n", "40360076 Carvel \n", "40361322 Carvel \n", "40361606 The Movable Feast \n", "40361618 Sal's Deli \n", "40361708 Bully's Deli \n", "40361998 Steve Chu's Deli & Grocery \n", "40362098 Harriet's Kitchen \n", "40362264 PS Deli and Grocery \n", "40362274 Angelika Film Center & Cafe - New York \n", "40362432 Ho Mei \n", "40362715 The Country Cafe \n", "40362869 None \n", "40363093 Carvel \n", "40363098 Dunkin' Donuts \n", "40363289 Chinese Fried Chicken \n", "40363298 Cosane \n", "40363333 Tont's Too Deli & Coffee Shop \n", "40363426 Lexler Deli \n", "... ... \n", "50055989 None \n", "50055990 None \n", "50055996 AliceChenCPA \n", "50055997 Mike's Pizza and Pasta \n", "50056005 None \n", "50056006 None \n", "50056007 None \n", "50056009 None \n", "50056014 Pizza Royale \n", "50056016 None \n", "50056017 None \n", "50056018 Legendary Bar & Restaurant \n", "50056020 None \n", "50056021 Lava Kitchen \n", "50056022 JooMakGol \n", "50056030 None \n", "50056031 None \n", "50056033 None \n", "50056036 None \n", "50056056 None \n", "50056057 None \n", "50056063 None \n", "50056065 None \n", "50056067 None \n", "50056068 Luna de Xelaju Restaurant & Pizzeria \n", "50056069 None \n", "50056073 None \n", "50056074 None \n", "50056081 None \n", "50056087 None \n", "\n", "[26064 rows x 29 columns]" ] }, "execution_count": 250, "metadata": {}, "output_type": "execute_result" } ], "source": [ "inspections_ffff" ] }, { "cell_type": "code", "execution_count": 251, "metadata": { "collapsed": true }, "outputs": [], "source": [ "inspections_ffff.to_csv(\"../data/yelp_dohmh_agg_data.csv\", encoding='utf-8')" ] } ], "metadata": { "anaconda-cloud": {}, "kernelspec": { "display_name": "Python [conda env:nyc-restaurant-trends]", "language": "python", "name": "conda-env-nyc-restaurant-trends-py" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.5.2" } }, "nbformat": 4, "nbformat_minor": 1 }