Working function (see code Python Pandas 'apply' returns series; can't convert to dataframe) has stopped working. Only difference is I'm passing it a string concatenation.
# Get geocode, return LAT and LON
def locate(x):
geolocator = Nominatim()
print("'" + x + "'")
location = geolocator.geocode(x) # Get geocode
print(location)
lat = location.latitude
lon = location.longitude
try:
#Get geocode
location = geolocator.geocode(x, timeout=8, exactly_one=True)
lat = location.latitude
lon = location.longitude
except:
#didn't work for some reason that I really don't care about
lat = np.nan
lon = np.nan
print(lat,lon)
return pd.Series([lat, lon])
This works
In[4] locate('MOSCOW 123098 RUSSIA')
'MOSCOW 123098 RUSSIA'
Москва, Центральный административный округ, Москва, ЦФО, Россия
Out[4]:
0 55.751633
1 37.618704
dtype: float64
But this does not:
df_addr[['LAT','LON']] = df_addr['COUNTRY'].apply(locate(df_addr['CITY'] + ' ' + \
df_addr['PROVINCE'] + ' ' + \
df_addr['STATE'] + ' ' + \
df_addr['ZIP_CODE'] + ' ' + \
df_addr['COUNTRY'])) # Geocode it!
I see the function echoing the correct input strings:
0 'INNSBRUCK AUSTRIA'
1 'BERN CH-3001 SWITZERLAND'
2 'INNSBRUCK AUSTRIA'
3 'MOSCOW 123098 RUSSIA'
4 'MOSCOW 123098 RUSSIA'
5 'FREDERICK MD 21702 USA'
Removing the try/except I get the following fugly exception info
.
.
99 'GLASGOW LANARK G20 9NB SCOTLAND'
dtype: object
---------------------------------------------------------------------------
HTTPError Traceback (most recent call last)
C:\Users\gn\Anaconda3\lib\site-packages\geopy\geocoders\base.py in _call_geocoder(self, url, timeout, raw, requester, deserializer, **kwargs)
131 try:
--> 132 page = requester(url, timeout=(timeout or self.timeout), **kwargs)
133 except Exception as error: # pylint: disable=W0703
C:\Users\gn\Anaconda3\lib\urllib\request.py in urlopen(url, data, timeout, cafile, capath, cadefault)
152 opener = _opener
--> 153 return opener.open(url, data, timeout)
154
C:\Users\gn\Anaconda3\lib\urllib\request.py in open(self, fullurl, data, timeout)
460 meth = getattr(processor, meth_name)
--> 461 response = meth(req, response)
462
C:\Users\gn\Anaconda3\lib\urllib\request.py in http_response(self, request, response)
570 response = self.parent.error(
--> 571 'http', request, response, code, msg, hdrs)
572
C:\Users\gn\Anaconda3\lib\urllib\request.py in error(self, proto, *args)
498 args = (dict, 'default', 'http_error_default') + orig_args
--> 499 return self._call_chain(*args)
500
C:\Users\gn\Anaconda3\lib\urllib\request.py in _call_chain(self, chain, kind, meth_name, *args)
432 func = getattr(handler, meth_name)
--> 433 result = func(*args)
434 if result is not None:
C:\Users\gn\Anaconda3\lib\urllib\request.py in http_error_default(self, req, fp, code, msg, hdrs)
578 def http_error_default(self, req, fp, code, msg, hdrs):
--> 579 raise HTTPError(req.full_url, code, msg, hdrs, fp)
580
HTTPError: HTTP Error 500: Internal Server Error
During handling of the above exception, another exception occurred:
KeyError Traceback (most recent call last)
C:\Users\gn\Anaconda3\lib\site-packages\geopy\geocoders\base.py in _call_geocoder(self, url, timeout, raw, requester, deserializer, **kwargs)
146 try:
--> 147 raise ERROR_CODE_MAP[code](message)
148 except KeyError:
KeyError: 500
During handling of the above exception, another exception occurred:
GeocoderServiceError Traceback (most recent call last)
<ipython-input-6-7412c2e27dd8> in <module>()
----> 1 df_addr[['LAT','LON']] = df_addr['COUNTRY'].apply(locate(df_addr['CITY'] + ' ' + df_addr['PROVINCE'] + ' ' + df_addr['STATE'] + ' ' + df_addr['ZIP_CODE'] + ' ' + df_addr['COUNTRY'])) # Geocode it!
2 df_addr.head()
<ipython-input-3-d957ac2e2e2e> in locate(x)
3 geolocator = Nominatim()
4 print("'" + x + "'")
----> 5 location = geolocator.geocode(x,timeout=20) # Get geocode
6 print(location)
7 lat = location.latitude
C:\Users\gn\Anaconda3\lib\site-packages\geopy\geocoders\osm.py in geocode(self, query, exactly_one, timeout, addressdetails, language, geometry)
190 logger.debug("%s.geocode: %s", self.__class__.__name__, url)
191 return self._parse_json(
--> 192 self._call_geocoder(url, timeout=timeout), exactly_one
193 )
194
C:\Users\gn\Anaconda3\lib\site-packages\geopy\geocoders\base.py in _call_geocoder(self, url, timeout, raw, requester, deserializer, **kwargs)
147 raise ERROR_CODE_MAP[code](message)
148 except KeyError:
--> 149 raise GeocoderServiceError(message)
150 elif isinstance(error, URLError):
151 if "timed out" in message:
GeocoderServiceError: HTTP Error 500: Internal Server Error
Am in over my head. Updated all libraries, but no change in the problem.
Thanks in advance
What you're doing is a little perverse to be honest, you're calling apply on a series and then trying to construct a str from lots of columns, this is the wrong way to go about this, you can call apply on the df and pass axis=1 so that the row is passed and either access each column in a lambda func and pass them to locate or in locate extract each column value, or just create a series from the concatenation of all the columns and call apply on this:
df_addr[['LAT','LON']] = (df_addr['CITY'] + ' ' + df_addr['PROVINCE'] + ' ' + df_addr['STATE'] + ' ' + df_addr['ZIP_CODE'] + ' ' + df_addr['COUNTRY']).apply(locate)
The above should work I believe.