Develop Reference

Why does geolocate not give me the right addresses?

So I was analyzing a data set with addresses in Philadelphia, PA. Now, in order to make use of these, I wanted to get the exact longitude and latitude to later show them on a map.
I have gotten the unique entries of the column as a list and have implemented a loop to get me the longitude and latitude, though it's giving me the same coordinates for every city and sometimes even ones that are outside of Philadelphia.
Here's what I did so far:
from geopy.geocoders import Nominatim
geolocator = Nominatim(user_agent="my_user_agent")
geocode = lambda query: geolocator.geocode("%s, Philadelphia PA" % query)
cities = list(philly["station_name"].unique())
for city in cities:
address = city
location = geolocator.geocode(address)
if(location != None):
philly["longitude"] = location.longitude
philly["latitude"] = location.latitude
philly["coordinates"] = list(zip(philly["latitude"], philly["longitude"]))

If "philly" is a list of dictionary objects then you can iterate over the list and add the location properties to each record.
from geopy.geocoders import Nominatim
philly = [{'station_name': '30th Street Station'}]
geolocator = Nominatim(user_agent="my_user_agent")
for row in philly:
address = row["station_name"]
location = geolocator.geocode(f"{address}, Philadelphia, PA", country_codes="us")
if location:
print(address)
print(">>", location.longitude, location.latitude)
row["longitude"] = location.longitude
row["latitude"] = location.latitude
row["coordinates"] = (location.longitude, location.latitude)
print(philly)
Output:
30th Street Station
>> -75.1821442 39.9552836
[{'station_name': '30th Street Station', 'longitude': -75.1821442, 'latitude': 39.9552836, 'coordinates': (-75.1821442, 39.9552836)}]
If working with a Pandas dataframe then you can iterate over each record in the dataframe then set the latitude, longitude and coordinates fields in it.
You can do something like this:
from geopy.geocoders import Nominatim
import pandas as pd
geolocator = Nominatim(user_agent="my_user_agent")
philly = [{'station_name': '30th Street Station'}]
df = pd.DataFrame(philly)
# add empty location columns to data frame
df["latitude"] = ""
df["longitude"] = ""
df["coordinates"] = ""
for _, row in df.iterrows():
address = row.station_name
location = geolocator.geocode(f"{address}, Philadelphia, PA", country_codes="us")
if location:
row["latitude"] = location.latitude
row["longitude"] = location.longitude
row["coordinates"] = (location.longitude, location.latitude)
print(df)
Output:
station_name latitude longitude coordinates
0 30th Street Station 39.955284 -75.182144 (-75.1821442, 39.9552836)
If you have a list with duplicate station names then you should cache the results so you don't make duplicate geolocation requests.

How to setup Pandas groupby into subplots of tables?

So I currently have what is above.
I've managed to separate them into categories using groupby but now I would like to put them in a subplot of tables.
##open comma separated file and the columns Name, In Stock, committed, reorder point
file = pd.read_csv('Katana/InventoryItems-2022-01-06-09_10.csv',
usecols=['Name','In stock','Committed', 'Reorder point','Category'])
##take the columns and put them in to a list
Name = file['Name'].tolist()
InStock = file['In stock'].tolist()
Committed = file['Committed'].tolist()
ReorderPT = file['Reorder point'].tolist()
Category = file['Category'].tolist()
##take the lists and change them into appropriate type of data
inStock = [int(float(i)) for i in InStock]
commited = [int(float(i)) for i in Committed]
reorderpt = [int(float(i)) for i in ReorderPT]
##have the liss with correct data type and arrange them
inventory = {'Name': Name,
'In stock': inStock,
'Committed': commited,
'Reorder point': reorderpt,
'Category': Category
}
##take the inventory arrangement and display them into a table
frame = DataFrame(inventory)
grouped = frame.groupby(frame.Category)
df_elec = grouped.get_group('Electronics')
df_bedp = grouped.get_group('Bed Packaging')
df_fil = grouped.get_group('Filament')
df_fast = grouped.get_group('Fasteners')
df_kit = grouped.get_group('Kit Packaging')
df_pap = grouped.get_group('Paper')

Try something along the lines of:
import matplotlib.pyplot as plt
fig,axs = plt.subplots(nrows=6,ncols=1)
for ax,data in zip(axs,[df_elec,df_bedp,df_fil,df_fast,df_kit,df_pap]):
data.plot(ax=ax,table=True)

Using Foursquare API with python

How do i extract the list of hospitals in each neighborhood in a city using foursquare API? and putting it into a data frame.
This is what i am trying to achieve as a DataFrame:
Neighborhood No. of hospitals
0 Neighborhood1 5
1 Neighborhood2 1
2 Neighborhood3 3
3 Neighborhood4 4
4 Neighborhood5 5
I am trying out a code from a previous tutorial to achieve this, I expected the error but i don't know where to start.
def getNearbyVenues(names, latitudes, longitudes, radius=500):
venues_list=[]
for name, lat, lng in zip(names, latitudes, longitudes):
print(name)
# create the API request URL
url = 'https://api.foursquare.com/v2/venues/search?&client_id={}&client_secret={}&v={}&ll={}&query=supermarket,{}&radius={}&limit={}'.format(
CLIENT_ID,
CLIENT_SECRET,
VERSION,
lat,
lng,
radius,
LIMIT)
# make the GET request
results = requests.get(url).json()["response"]['groups'][0]['items']
# return only relevant information for each nearby venue
venues_list.append([(
name,
lat,
lng,
v['venue']['name'],
v['venue']['location']['lat'],
v['venue']['location']['lng'],
v['venue']['categories'][0]['name']) for v in results])
nearby_venues = pd.DataFrame([item for venue_list in venues_list for item in venue_list])
nearby_venues.columns = ['Neighborhood',
'Neighborhood Latitude',
'Neighborhood Longitude',
'Venue',
'Venue Latitude',
'Venue Longitude',
'Venue Category']
return(nearby_venues)
Next cell:
Toronto_venues = getNearbyVenues(names=Toronto_df['Neighborhood'],
latitudes=Toronto_df['Latitude'],
longitudes=Toronto_df['Longitude']
)
Thank you in advance!

Thank you for your response,
Toronto_venues = getNearbyVenues(names=Toronto_df['Neighborhood'],
latitudes=Toronto_df['Latitude'],
longitudes=Toronto_df['Longitude']
)
But this cell gives back this error,
---------------------------------------------------------------------------
KeyError Traceback (most recent call last)
<ipython-input-16-03f6027f84a2> in <module>()
1 Toronto_venues = getNearbyVenues(names=Toronto_df['Neighborhood'],
2 latitudes=Toronto_df['Latitude'],
----> 3 longitudes=Toronto_df['Longitude']
4 )
<ipython-input-13-0c3ca691c166> in getNearbyVenues(names, latitudes, longitudes, radius)
16
17 # make the GET request
---> 18 results = requests.get(url).json()["response"]['groups'][0]['items']
19
20 # return only relevant information for each nearby venue
KeyError: 'groups'

You need to do value counts, then separate out any column and rename it.
df = Toronto_venues.groupby('Neighborhood').count() # Get the counts
df = pd.DataFrame(df['Venue']) # Convert the counts to a dataframe
df.rename(columns={'Venue': 'No. of Hospitals'}, inplace=True)
At this point you will have a dataframe, but the first column which is your hospital names, is the index. If you want to pull it out into a column, then use this code as well:
df.reset_index(level=0, inplace=True)

Calling a request from foursquare

I am trying to use the below function to retrieve venues for different locations but I keep getting this error and I can't figure it out because I used it before and it worked perfectly but with different locations. Please help!
def getNearbyVenues(names, latitudes, longitudes, radius=500):
venues_list=[]
for name, lat, lng in zip(names, latitudes, longitudes):
print(name)
# create the API request URL
url = 'https://api.foursquare.com/v2/venues/explore?&client_id={}&client_secret={}&v={}&ll={},{}&radius={}&limit={}'.format(
CLIENT_ID,
CLIENT_SECRET,
VERSION,
lat,
lng,
radius,
LIMIT)
# make the GET request
results = requests.get(url).json()["response"]['groups'][0]['items']
# return only relevant information for each nearby venue
venues_list.append([(
name,
lat,
lng,
v['venue']['name'],
v['venue']['location']['lat'],
v['venue']['location']['lng'],
v['venue']['categories'][0]['name']) for v in results])
nearby_venues = pd.DataFrame([item for venue_list in venues_list for item in venue_list])
nearby_venues.columns = ['Neighbourhood',
'Neighbourhood Latitude',
'Neighbourhood Longitude',
'Venue',
'Venue Latitude',
'Venue Longitude',
'Venue Category']
return(nearby_venues)`
london_venues = getNearbyVenues(names=df['Location'],
latitudes=df['Latitude'],
longitudes=df['Longitude']
)
This is the error I am getting
---------------------------------------------------------------------------
KeyError Traceback (most recent call last)
<ipython-input-180-4f13fb178c94> in <module>
1 london_venues = getNearbyVenues(names=df['Location'],
2 latitudes=df['Latitude'],
----> 3 longitudes=df['Longitude']
4 )
<ipython-input-177-d194f1c67c83> in getNearbyVenues(names, latitudes, longitudes, radius)
16
17 # make the GET request
---> 18 results = requests.get(url).json()["response"]['groups'][0]['items']
19
20 # return only relevant information for each nearby venue
KeyError: 'groups'

you might have exceeded your API call limit if you are using sandbox account, or there is no such key named "groups". If not, then please provide the coordinates of the location.

Osmnx: How to retreive info on bus-stop info node, which is part of a highway?

I am trying to also show info of OpenStreetMap bus-stop node 439460636 (https://www.openstreetmap.org/node/439460636) which is part of a highway.
I am using Python3 Osmnx
Other POIs all show perfectly. Just not the ones which are not maped as a 'amenity'. (There are more examples)
I am using jupyter notebook for my analysis:
import osmnx as ox
# Retrieve POI shelters
place_name = 'Santa Clara, Santa Clara County, California, USA'
shelter = ox.pois_from_place(place_name, amenities=['shelter'])
cols = ['amenity', 'name', 'element_type', 'shelter_type',
'building', 'network'
]
shelter[cols]
cols = ['amenity', 'name','element_type', 'shelter_type',
'building', 'network'
]
shelter[cols].loc[(shelter['shelter_type'] == 'public_transport') ]
# Look bus-stop in highway
graph = ox.graph_from_place(place_name)
nodes, edges = ox.graph_to_gdfs(graph)
nodes.loc[(nodes['highway'] == 'bus_stop') ]
Overpass:
[out:json][timeout:25];
// gather results
(
area[name="Santa Clara, Santa Clara County, California, USA"];
node(area)["highway"="bus_stop"]({{bbox}});
);
// print results
out body;
>;
out skel qt;
The POI Kino (439460636) is not listed. The shelter right next to the POI is listed. The POI is in the middle of my area, so I do not understand how I can retreive the node info. Can you help?

Manually update Osmnx with the file linked in this post from chesterharvey. https://github.com/gboeing/osmnx/issues/116#issuecomment-439577495
Final testing of feature still incomplete!
import osmnx as ox
# Specify the name that is used to seach for the data
place_name = "Santa Clara, Santa Clara County, California, USA"
tags = {
'amenity':True,
'leisure':True,
'landuse':['retail','commercial'],
'highway':'bus_stop',
}
all_pois = ox.pois_from_place(place=place_name, tags=tags)
all_pois.loc[(all_pois['highway'] == 'bus_stop')]

This functionality as been added to OSMnx as of v0.13.0. It generalizes the POIs module to query using a tags dict instead of an amenities list. It removes the amenities parameter from all POI functions. The tags dict accepts key:value pairs of the form:
'tag' : True (use bool to retrieve all items with tag)
'tag' : 'value' (use string to retrieve all items with tag = value)
'tag' : ['value1', 'value2', etc] (use list to retrieve all items with tag equal to either value1 or value2 etc.
Usage examples of the new POI querying functionality:
import osmnx as ox
ox.config(use_cache=True, log_console=True)
tags = {'amenity' : True,
'landuse' : ['retail', 'commercial'],
'highway' : 'bus_stop'}
gdf = ox.pois_from_place(place='Piedmont, California, USA', tags=tags)

You can do that easily with footprints I think:
#point of interests around an aread
import networkx as nx
import osmnx as ox
import requests
#returns polygon or coordinates of poi
#point = (59.912390, 10.750584)
#amn = ["bus_station",'waste_transfer_station'] #["bus_station",'waste_transfer_station']
#points of interest/amenities we can use: https://wiki.openstreetmap.org/wiki/Key:amenity
def get_interest_points(long,lat,dist,amn[]):
point = (long, lat)
gdf_points = ox.pois_from_point(point, distance=dist, amenities=amn)
return gdf_points[["amenity", "geometry"]]
#Get bus buildings, distance in meter 400 is minimum
#returns polygon of building
def get_buildings(long,lat,dist):
point = (long, lat)
gdf = ox.footprints.footprints_from_point(point=point, distance=dist,footprint_type='buildings')
return gdf["geometry"]
#Get bus, tram or subway
#type = "bus" or "tram" or "subway"
#, distance in meter 400 is minimum
#returns polygon of stop
def get_buildings(long,lat,dist,type):
point = (long, lat)
gdf = ox.footprints.footprints_from_point(point=point, distance=dist,footprint_type=type)
return gdf["geometry"]