fscottfoti

{
  "presets": [
    "@babel/preset-env",
  ]
}

fscottfoti

fscottfoti

geometry,county_id,apn,land_use_type_id,res_type,land_value,improvement_value,year_assessed,year_built,building_sqft,non_residential_sqft,residential_units,stories,tax_exempt,condo_identifier,imputation_flag,development_type_id,calc_area,parcel_id,zone_id,general_plan_name,city,priority,x,y
"POLYGON ((-122.3990274713002 37.79395382339768, -122.3993259511759 37.79391578933188, -122.3993538562597 37.79405130905006, -122.3990561343018 37.79408924715813, -122.3990274713002 37.79395382339768))",San Francisco,0237046,MIXED,,555469.0,225936.0,,1907.0,8250.0,8250.0,0.0,2.0,0.0, ,_,ME,405.240852503,893634,1.0,DOWNTOWN- OFFICE-350-S,San Francisco,1.0,-122.399190847,37.7940025136
"POLYGON ((-122.3964937400307 37.79335498674916, -122.397325320222 37.79271016640127, -122.3974696743914 37.79341132542675, -122.3965299855578 37.79353105082634, -122.3964937400307 37.79335498674916))",San Francisco,0264004,MIPS,,79131319.0,83209623.0,,2005.0,570000.0,570000.0,0.0,32.0,0.0, ,_,,4134.37730242,893997,1.0,DOWNTOWN- OFFICE-400-S,Sa

fscottfoti

"""
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

fscottfoti

from pymongo import MongoClient
from bson.objectid import ObjectId
import json
import time
from string import join
import pandas as pd
import cPickle

MONGO = True
JURIS = None

fscottfoti

from sklearn.neighbors import KDTree
import pandas as pd
from geopy.distance import vincenty

WALKING_SPEED = 3 # walking assumed at 3 miles per hour
TRANSFER_TIME = 10 # transfer time in minutes

# assume df1 and df2 each have 2 float columns specifying x and y
# in the same order and coordinate system and no nans.  returns the indexes
# from df1 that are closest to each row in df2

fscottfoti

// Copyright (c) 2012 Sutoiku, Inc.

// Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:

// The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.

// THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE O

fscottfoti

# this should be fairly self explanitory if you know ipf
# seed_matrix is your best bet at the totals, col_marginals are
# observed column marginals and row_marginals is the same for rows
def simple_ipf(seed_matrix, col_marginals, row_marginals, tolerance=1, cnt=0):
    assert np.absolute(row_marginals.sum() - col_marginals.sum()) < 5.0

    # first normalize on columns
    ratios = col_marginals / seed_matrix.sum(axis=0)
    seed_matrix *= ratios
    closeness = np.absolute(row_marginals - seed_matrix.sum(axis=1)).sum()

fscottfoti

def make_network(name, weight_col, max_distance):
    st = pd.HDFStore(os.path.join(misc.data_dir(), name), "r")
    nodes, edges = st.nodes, st.edges
    net = pdna.Network(nodes["x"], nodes["y"], edges["from"], edges["to"],
                       edges[[weight_col]])
    net.precompute(max_distance)
    return net

@orca.step('local_pois')
def local_pois(settings):

fscottfoti

from sklearn.neighbors import KDTree

def nearest_neighbor(df1, df2):
    kdt = KDTree(df1.as_matrix())
    distances, indexes = kdt.query(df2.as_matrix(), k=1, return_distance=True)
    return pd.Series(distances.flatten(), index=df1.index.values[indexes.flatten()])


import sys
import pandas as pd