easy_pandana_script.py

"""
Steps to install environment

1) 
Get Anaconda (python with includes packages) and install it
https://www.continuum.io/downloads

2)
Get network file and put it in the same directory as this file
http://urbanforecast.com/data/2015_06_01_osm_bayarea4326.h5

3)
Install Pandana - if you let Anaconda add python to your path just run
pip install -U pandana

If you encounter problems, make sure you're using Anaconda

"""


import pandas as pd
import numpy as np
import pandana as pdna
import pyproj
import time


def coord_convert(x, y, srcsrid=3857, tgtsrid=4326):
    bng = pyproj.Proj("+init=EPSG:%d" % srcsrid)
    wgs84 = pyproj.Proj("+init=EPSG:%d" % tgtsrid)
    try:
        lon, lat = pyproj.transform(bng, wgs84, x, y)
    except:
        # this only happens because there are unescaped commas
        lon, lat = np.nan, np.nan
    return lon, lat


def convert_df(df, xname='x', yname='y', srcsrid=3857, tgtsrid=4326):
    x = df[xname].values
    y = df[yname].values
    for i in range(len(df.index)):
        if i % 25000 == 0: print i
        x[i], y[i] = coord_convert(x[i], y[i], srcsrid=srcsrid, tgtsrid=tgtsrid)
    df[xname] = x
    df[yname] = y
    return df

# read csv
df = pd.read_csv("poi.csv",
                 names=["poi_id", "cat", "subcat", "name", "x", "y"],
                 low_memory=False)

print "Converting CRS, will drop names with commas in the name field"
t1 = time.time()
df = convert_df(df)
print df.head()
print "Took {:.2f}s".format(time.time() - t1)

newdf = df.dropna(subset=["x"]).dropna(subset=["y"])
print "Dropping {} rows because names have commas".format(len(df)-len(newdf))
df = newdf

# see docs here for detailed api info
# http://udst.github.io/pandana/tutorial.html

print "\n\nLoading network"
t1 = time.time()
st = pd.HDFStore("2015_06_01_osm_bayarea4326.h5", "r")
nodes, edges = st.nodes, st.edges
net = pdna.Network(nodes["x"], nodes["y"], edges["from"], edges["to"],
                   edges[["weight"]])
print "Took {:.2f}s".format(time.time() - t1)

# initialize 1 category and up to 10 returned pois
net.init_pois(num_categories=1, max_dist=3000, max_pois=10)

# set the cafe locations
print "\n\nInitializing POIs"
t1 = time.time()
# filter to cafes
cafes = df.query("cat == 9376")
print "There are {} cafes".format(len(cafes))
net.set_pois("cafes", cafes.x, cafes.y)
print "Took {:.2f}s".format(time.time() - t1)

# run the query
print "\n\nRunning queries"
t1 = time.time()
output = net.nearest_pois(3000, "cafes", num_pois=10)
# add back the locations
output["x"], output["y"] = nodes["x"], nodes["y"]
output.index.name = "node_id"
print "Took {:.2f}s".format(time.time() - t1)

print output.head()

output.to_csv("nearest_cafes.csv")

output.log

Converting CRS, will drop names with commas in the name field
0
25000
50000
75000
100000
125000
150000
175000
200000
225000
250000
275000
300000
325000
350000
375000
400000
425000
450000
475000
500000
525000
550000
575000
600000
625000
650000
675000
700000
725000
750000
775000
800000
825000
850000
875000
900000
                     poi_id   cat   subcat                             name  \
0  68400002832950.00000000  7302  7302005           Always A Good Ride Llc   
1   68400004491250.00000000  7302  7302005                Barking Elf Ranch   
2   68400010247164.00000000  7302  7302005   Crossroads Ranch Riding Stable   
3   68400007041822.00000000  7303  7303006                 1 Percent Condos   
4   68400024624325.00000000  7303  7303003           1 San Ramon Apartments   

         x        y  
0 -117.582  33.6243  
1 -117.188  33.0879  
2 -122.674  38.3049  
3 -117.127  32.7557  
4 -119.765  36.8143  
Took 43.08s
Dropping 2362 rows because names have commas


Loading network
Generating contraction hierarchies with 4 threads.
Setting CH node vector of size 226060
Setting CH edge vector of size 287161
[info src/contraction_hierarchies/src/libch.cpp:205] Range graph removed 8884 edges of 574322
. 10% . 20% . 30% . 40% . 50% . 60% . 70% . 80% . 90% . 100%
Closing remaining open files:2015_06_01_osm_bayarea4326.h5...done
Took 8.30s


Initializing POIs
There are 13103 cafes
Took 0.08s


Running queries
Took 0.87s
                  1            2            3            4            5  \
node_id                                                                   
8        660.786987  3000.000000  3000.000000  3000.000000  3000.000000   
9        322.532013  2685.018066  2784.846924  2882.115967  2882.115967   
10         0.000000  2362.486084  2462.314941  2559.583984  2559.583984   
11       218.505005  2143.980957  2243.810059  2341.079102  2341.079102   
12       235.199005  2127.287109  2227.115967  2324.385010  2324.385010   

                   6            7            8            9      10  \
node_id                                                               
8        3000.000000  3000.000000  3000.000000  3000.000000  3000.0   
9        2943.325928  2993.888916  3000.000000  3000.000000  3000.0   
10       2620.793945  2671.356934  2802.144043  3000.000000  3000.0   
11       2402.289062  2452.852051  2583.638916  2932.696045  3000.0   
12       2385.594971  2436.157959  2566.945068  2916.001953  3000.0   

                  x          y  
node_id                         
8       -121.546785  36.997092  
9       -121.548863  36.999641  
10      -121.550719  37.002132  
11      -121.550795  37.004075  
12      -121.550784  37.004226