def get_house_results(self):
zip_code = zipcode.isequal(self.zip)
d = zip_code.to_dict()
point = (d['lat'], d['lon'])
zips = zipcode.isinradius(point, self.radius)
zips = [new_zip for new_zip in zips if not new_zip.decommisioned != "FALSE"]
zips = [new_zip.zip for new_zip in zips if new_zip.zip_type == "STANDARD"]
ads_info = []
for zip in zips:
self.bro.driver.get("https://www.zillow.com/homes/for_sale/{0}_rb/house,condo,apartment_duplex,mobile,townhouse_type/?fromHomePage=true&shouldFireSellPageImplicitClaimGA=false&fromHomePageTab=buy".format(zip))
try:
next_button = self.bro.driver.find_element_by_xpath("//li[@class='zsg-pagination-next']")
except:
next_button = 'Something'
while next_button:
ads = self.bro.driver.find_elements_by_xpath("//div[@id='search-results']//article")
for ad in ads:
properties = self._get_ad_properties(ad)
if properties:
ads_info.extend([properties])
try:
next_button = self.bro.driver.find_element_by_xpath("//li[@class='zsg-pagination-next']")
next_button.click()
except:
break
time.sleep(2) # Should get rid of this
self.bro.driver.close()
write_to_csv("Zillow", ads_info)
def local_city_list_maker(starting_zip='98119', mile_radius=100):
"""returns a set of cities within radius of starting zip,
formatted with state space city to use in weather_station_code_finder function"""
zip_obj = zipcode.isequal(starting_zip)
local_zips = zipcode.isinradius((zip_obj.lat, zip_obj.lon),
mile_radius)
return {' '.join([i.state, i.city]) for i in local_zips}
def coords2zipcode(latlon, radius=1.5):
try:
return zipcode.isinradius(latlon, radius)[0].zip
except:
zipcodes = [11232, 10001, 11211, 10026, 11101]
zipcode = random.sample(zipcodes, 1)[0]
print(zipcode)
return zipcode
def local_zipcodes(startingzip='98119', radius=10):
""" Returns zipcodes within radius of startingzip """
zip_obj = zipcode.isequal(startingzip)
try:
local_zips = zipcode.isinradius((zip_obj.lat, zip_obj.lon), radius)
return [i.zip for i in local_zips]
except AttributeError:
return 'No surrounding data available for ' + startingzip
def local_city_list_maker(starting_zip='98119', mile_radius=100):
"""returns list of cities within radius of starting zip"""
city_list = []
zip_obj = zipcode.isequal(starting_zip)
local_zips = zipcode.isinradius((zip_obj.lat, zip_obj.lon), mile_radius)
for i in local_zips:
state_city = i.state + ' ' + i.city
if state_city not in city_list:
city_list.append(state_city)
return city_list
def local_city_list_maker(starting_zip='98119', mile_radius=100):
"""returns list of cities within radius of starting zip"""
city_list = []
zip_obj = zipcode.isequal(starting_zip)
local_zips = zipcode.isinradius((zip_obj.lat, zip_obj.lon), mile_radius)
for i in local_zips:
state_city = i.state + ' ' + i.city
if state_city not in city_list:
city_list.append(state_city)
return city_list
def local_city_grabber(starting_zip='98119', mile_radius=100):
"""returns dict of zipcodes within radius of starting zip"""
cities = {}
zip_obj = zipcode.isequal(starting_zip)
local_zips = zipcode.isinradius((zip_obj.lat, zip_obj.lon), mile_radius)
for i in local_zips:
state_city = i.state + ' ' + i.city
if state_city not in cities:
cities[state_city] = {'zip': i.zip}
return cities
def zipcodes_list(st_items):
# (lat, lon, radius)
if type(st_items) == tuple:
zc_objects = zipcode.isinradius(st_items[:2], st_items[2])
output = [str(i).split(" ", 1)[1].split(">")[0] for i in zc_objects]
# If st_items is a single zipcode string.
elif type(st_items) == str:
zc_objects = zipcode.islike(st_items)
output = [str(i).split(" ", 1)[1].split(">")[0] for i in zc_objects]
# If st_items is a list of zipcode strings.
elif type(st_items) == list:
zc_objects = [n for i in st_items for n in zipcode.islike(str(i))]
output = [str(i).split(" ", 1)[1].split(">")[0] for i in zc_objects]
else:
raise ValueError("input 'st_items' must be of type str or list")
return (output)
import zipcode
import re
my_zip = zipcode.isequal('98119')
local_zips = zipcode.isinradius((my_zip.lat, my_zip.lon), 100)
zip_dict = {}
## good code!!!
for i in local_zips:
state_city = i.state + ' ' + i.city
if state_city not in zip_dict:
zip_dict[state_city] = [i.zip]
zip_dict[state_city].append(i.zip)
## good code!!!
print(zip_dict)
code_db = open('weather_codes.txt', 'r').read()
for i in zip_dict:
#m = re.search('{}.+'.format(i), code_db)
m = re.search(i + '.*[PKXQ]\w{3}\s\s', code_db)
#cm = re.search('^[PKXQ]{4}', m.group)
# m = re.findall(i +'\s^[PKXQ]{4}', code_db)
try:
airbnb_nyc_2b_by_zipcode = airbnb_nyc_2b_by_zipcode[(airbnb_nyc_2b_by_zipcode['rental_data_points_count']>3)]
print("#"*terminal_width)
# join data from zillow
lastest = len(zillow_df.columns) - 1
zillow_df = pd.concat([zillow_df.ix[:,1],zillow_df.ix[:,lastest]], axis=1)
zillow_df.columns = ['RegionName','propertyPrice']
main_df = pd.merge(airbnb_nyc_2b_by_zipcode, zillow_df, left_on = 'zipcode', right_on = 'RegionName', how = 'left')
print main_df.info()
# Since we are going to purchase properties recently, I used the latest price, which is the last column
print "only 18 records with a property price"
print("#"*terminal_width)
# In the following, I will try to match the property price according to adjacent zipcodes
import zipcode
import zipcodes
# estimate the missing property prices
main_df['adjacentZipcodes'] = main_df['zipcode'].map(lambda x: zipcode.isinradius((zipcodes.matching(x)[0]['lat'],zipcodes.matching(x)[0]['long']),1))
# save zipcodes with actual property price into a dict
actualPrices = main_df[['RegionName','propertyPrice']].set_index('RegionName')['propertyPrice'].to_dict()
def f(x):
res = []
for i in x:
if i.zip in actualPrices.keys():
res.append(actualPrices[i.zip])
return np.mean(res)
main_df['propertyPrice1st'] = main_df['adjacentZipcodes'].map(f)
main_df['estimatePrice'] = main_df['propertyPrice']
main_df.estimatePrice.fillna(main_df.propertyPrice1st, inplace=True)
print "the number of zip codes with a property price:"
print main_df['estimatePrice'].count()
# 76
def local_city_list_maker(starting_zip='98119', mile_radius=100):
"""returns a set of cities within radius of starting zip,
formatted with state space city to use in weather_station_code_finder function"""
zip_obj = zipcode.isequal(starting_zip)
local_zips = zipcode.isinradius((zip_obj.lat, zip_obj.lon), mile_radius)
return {' '.join([i.state, i.city]) for i in local_zips}
def local_city_grabber(starting_zip='98119', mile_radius=100):
"""returns set of cities within radius of starting zip"""
zip_obj = zipcode.isequal(starting_zip)
local_zips = zipcode.isinradius((zip_obj.lat, zip_obj.lon), mile_radius)
return {'{} {}'.format(i.state, i.city) for i in local_zips}
def local_zipcodes(startingzip='98119', radius=100):
""" Returns zipcodes within radius of startingzip"""
zip_obj = zipcode.isequal(startingzip)
local_zips = zipcode.isinradius((zip_obj.lat, zip_obj.lon), radius)
return {i.zip for i in local_zips}
def create_dataframe(tweets_data):
tweets = pd.DataFrame(index=range(len(tweets_data)),
columns=[
'text', 'created_at', 'location', 'state',
'sentiment', 'sentiment_cat', 'country_code',
'hour'
])
for i in range(len(tweets_data)):
try:
tweets['text'][i] = tweets_data[i]['text']
except:
tweets['text'][i] = ""
try:
tweets['location'][i] = tweets_data[i]['user']['location']
except:
tweets['location'][i] = 'NA'
try:
tweets['country_code'][i] = tweets_data[i]['place']['country_code']
except:
tweets['country_code'][i] = ''
try:
lon = tweets_data[i]['place']['bounding_box']['coordinates'][0][0][
0]
except:
lon = 'NA'
try:
lat = tweets_data[i]['place']['bounding_box']['coordinates'][0][0][
1]
except:
lat = 'NA'
#print (lat,lon)
try:
tweets['created_at'][i] = tweets_data[i]['created_at']
except:
tweets['created_at'][i] = 'NA'
try:
tweets['hour'][i] = tweets['created_at'][i][11:13]
except:
tweets['hour'][i] = 'NA'
try:
stateFromData = tweets['location'][i].split(',')[1]
except:
stateFromData = ''
if len(stateFromData) == 2:
tweets['state'][i] = stateFromData
else:
if lat != 'NA':
radius = 10
incre = 10
zips = zipcode.isinradius((lat, lon), radius)
while len(zips) == 0:
radius = radius + incre
zips = zipcode.isinradius((lat, lon), radius)
incre = incre + 10
myzip = zipcode.isequal(str(zips[0].zip))
tweets['state'][i] = myzip.state
else:
tweets['state'][i] = 'NA'
blob = TextBlob(tweets['text'][i])
try:
sentence = blob.sentences[0]
tweets['sentiment'][i] = float(sentence.sentiment.polarity)
except:
tweets['sentiment'][i] = 0
if tweets['sentiment'][i] < 0:
tweets['sentiment_cat'][i] = 'Neg'
else:
if tweets['sentiment'][i] > 0:
tweets['sentiment_cat'][i] = 'Pos'
else:
tweets['sentiment_cat'][i] = 'Neu'
print(tweets.head())
return tweets
import json
import zipcode
from pprint import pprint
with open('swimmingpools.json') as data_file:
data = json.load(data_file)
#pprint(data)
myzip = zipcode.isequal('11102')
print myzip.state
print myzip.city.title()
print zipcode.isinradius((40.7788, -73.9227), 2.0)
def local_city_grabber(starting_zip='98119', mile_radius=100):
"""returns set of cities within radius of starting zip"""
zip_obj = zipcode.isequal(starting_zip)
local_zips = zipcode.isinradius((zip_obj.lat, zip_obj.lon), mile_radius)
return {'{} {}'.format(i.state, i.city) for i in local_zips}
import zipcode
import re
my_zip = zipcode.isequal('98119')
local_zips = zipcode.isinradius((my_zip.lat, my_zip.lon), 100)
zip_dict = {}
## good code!!!
for i in local_zips:
state_city = i.state + ' ' + i.city
if state_city not in zip_dict:
zip_dict[state_city] = [i.zip]
zip_dict[state_city].append(i.zip)
## good code!!!
print(zip_dict)
code_db = open('weather_codes.txt', 'r').read()
for i in zip_dict:
#m = re.search('{}.+'.format(i), code_db)
m = re.search(i + '.*[PKXQ]\w{3}\s\s', code_db)
#cm = re.search('^[PKXQ]{4}', m.group)
# m = re.findall(i +'\s^[PKXQ]{4}', code_db)
try:
print(m.group())
cm = re.search('\s[PKXQ]\w{3}\s\s', m.group())
print(cm.group())
# print(m.groups())
except: