def mexico_filter(latitude, longitude):
geo = reverse_geocoder.RGeocoder(mode=1, verbose=True, stream=obj_data)
coordinates = (latitude, longitude), (latitude, longitude)
results = geo.query(coordinates)
for response_dictionary in results:
if [x for x in response_dictionary if response_dictionary[x] == 'US']:
#logger.info("####################### MX RECORD ######################################################")
return True
return False
def get_countries(coordinates):
countries = defaultdict(lambda: 0)
geo = rg.RGeocoder(mode=2,
verbose=True,
stream=io.StringIO(
open('./input/rg_cities1000.csv',
encoding='utf-8').read()))
results = geo.query(coordinates)
for i in results:
countries[i['cc'].lower()] += 1
return countries
def mexico_filter(latitude, longitude):
geo = reverse_geocoder.RGeocoder(mode=1, verbose=True, stream=obj_data)
coordinates = (latitude, longitude), (latitude, longitude)
results = geo.query(coordinates)
for response_dictionary in results:
if (response_dictionary['name'] == 'Manhattan'
and response_dictionary['cc']
== 'US') or (response_dictionary['name'] == 'San Francisco'
and response_dictionary['cc'] == 'US'):
return True
else:
return False
# -*- coding: utf-8 -*-
"""
"""
import io
import csv
import reverse_geocoder as rg
from datetime import datetime
# Sets our own zip code data
geo = rg.RGeocoder(mode=1, verbose=True, stream=io.StringIO(open('ny_zip_coords_fixed.csv', encoding='utf-8').read()))
def getZips(coordinates):
return geo.query(coordinates)
# Cleans time from datetime
# Reformats date to match NYPD complaint data
def cleanDate(string):
date = string[:10]
date = string[5:7] + "/" + string[8:10] + "/" + string[0:4]
return date
def writeRows_TDP(numRows, neededInfo, result, outputCSV):
for x in range(0, numRows):
date = cleanDate(str(neededInfo[x][0]))
outRow = [date, result[2*x]['name'], result[2*x+1]['name'], neededInfo[x][1]]
outputCSV.writerow(outRow)
def writeRows_CDP(numRows, neededInfo, result, outputCSV):
for x in range(0, numRows):
#date = cleanDate(str(neededInfo[x][0]))
import io
import reverse_geocoder as rg
from pyspark import SparkContext
from pyspark.sql import HiveContext
# start Spark and Hive SQL contexts
sc = SparkContext("local", "demo app")
hc = HiveContext(sc)
# read GeoNames data file
geo = rg.RGeocoder(mode=2, verbose=True, stream=io.StringIO(open('/data/rohit/script/US_ascii.csv', 'r').read().decode('utf-8')))
print "Printing first 10 rows from rides table."
sqlQuery = "SELECT * FROM rides_yg limit 10"
hc.sql(sqlQuery).show()
coordinates = (40.742596,-74.153481),(41.316105,-74.127701),(40.786224,-74.043663),(40.736961,-74.038422),(40.748005,-74.032402),(41.031322,-74.02137 ),(40.647068,-74.010513),(40.708969,-74.010262),(40.720478,-74.010147)
print geo.query(coordinates)
for venue_cat in venues_cat:
if venue_cat not in cat_schema_mapping:
print(venue_cat)
cat_missing = True
assert cat_missing is False
# reverse geocode the venues
coords = []
for venue_id in venues_list:
venue_lat = venues[venue_id]['lat']
venue_lon = venues[venue_id]['lon']
coords.append((venue_lat, venue_lon))
geo = rg.RGeocoder(mode=2, verbose=True, stream=io.StringIO(
open('cities.csv', encoding='utf-8').read()))
venues_rg = geo.query(coords)
for index, venue_id in enumerate(venues_list):
venues[venue_id]['geonames'] = 'geonames:' + venues_rg[index]['name']
venues[venue_id]['city'] = venues_rg[index]['admin1']
venues[venue_id]['country'] = venues_rg[index]['admin2']
if venues_rg[index]['cc'] != '':
venues[venue_id]['wikidata'] = 'wd:' + venues_rg[index]['cc']
else:
venues[venue_id]['wikidata'] = ''
assert len(venues_rg) == len(venues)
print("Geocoding", len(venues_rg), "venues...")
# load the checkins
import reverse_geocoder as rg
files_list = os.listdir("BlackMarbleLandOnly")
county_light_vals = {}
num_exceptions = 0
# Processed every so iterations
querable_coords = list()
# List of float values
current_pixel_values = []
geo = rg.RGeocoder(mode=2,
verbose=True,
stream=io.StringIO(
open('rg_cities1000.txt', encoding='utf-8').read()))
for curr_file in files_list:
curr_path = "BlackMarbleLandOnly/" + str(curr_file)
with open(curr_path) as csv_file:
# csv_reader = csv.reader(csv_file, delimiter = ',')
# Ignore null bytes
csv_reader = csv.reader((x.replace('\0', '') for x in csv_file),
delimiter=',')
line_count = 0
i = 0
j = 0