In [1]:
import numpy as np, pandas as pd, os
from synthicity.utils import misc
from drcog.models import elcm_simulation, hlcm_simulation, regression_model_simulation, dataset
dset = dataset.DRCOGDataset(os.path.join(misc.data_dir(),'drcog.h5'))

#Variable Library
from drcog.variables import variable_library
variable_library.calculate_variables(dset)


Fetching parcels
Fetching modify_table
Fetching buildings
Fetching establishments
Fetching modify_table
Fetching modify_table
Fetching households_for_estimation
Fetching modify_table
Fetching households
Fetching modify_table
Fetching zones
Fetching modify_table
Fetching travel_data
Fetching modify_table

In [2]:
establishments = dset.establishments
households = dset.households
households_for_estimation = dset.households_for_estimation
buildings = dset.buildings

In [17]:
def export_uc(variable,name):
    df = pd.DataFrame({'values':variable}, index=variable.index)
    df = df[df.values>0]
    df.to_csv('c://users//janowicz//desktop//%s.csv'%name)

In [18]:
variable = buildings.groupby('parcel_id').non_residential_sqft.sum()
export_uc(variable,'non_residential_sqft')

In [19]:
variable = buildings.groupby('parcel_id').residential_units.sum()
export_uc(variable,'residential_units')

In [3]:
dset.travel_data.columns


Out[3]:
Index([u'am_bike_to_work_travel_time', u'am_walk_time_in_minutes', u'am_biking_person_trips', u'am_pk_period_drive_alone_vehicle_trips', u'am_transit_person_trip_table', u'am_total_transit_time_walk', u'single_vehicle_to_work_travel_cost', u'am_single_vehicle_to_work_travel_time', u'am_walking_person_trips', u'gid'], dtype=object)

In [5]:
td = dset.travel_data
td.am_single_vehicle_to_work_travel_time = td.am_single_vehicle_to_work_travel_time*2

In [10]:
td.head()


Out[10]:
am_bike_to_work_travel_time am_walk_time_in_minutes am_biking_person_trips am_pk_period_drive_alone_vehicle_trips am_transit_person_trip_table am_total_transit_time_walk single_vehicle_to_work_travel_cost am_single_vehicle_to_work_travel_time am_walking_person_trips gid
from_zone_id to_zone_id
5 90 180.679993 NaN NaN 0 0 NaN 5.32 124.339996 NaN 6626
6 2558 453.390015 NaN NaN 0 0 NaN 10.95 203.419998 NaN 11926
7 762 337.440002 NaN NaN 0 0 NaN 7.79 145.119995 NaN 12962
10 2764 247.100006 NaN NaN 0 0 NaN 6.49 147.740005 NaN 18996
11 2033 317.130005 NaN NaN 0 0 NaN 8.86 164.080002 NaN 23958

In [8]:
td.to_csv('C:\\urbansim\\data\\swap\\travel_data.csv')

In [11]:
td2 = pd.read_csv('C:\\urbansim\\data\\swap\\travel_data.csv', index_col=['from_zone_id','to_zone_id'])

In [15]:
td2.head()


Out[15]:
am_bike_to_work_travel_time am_walk_time_in_minutes am_biking_person_trips am_pk_period_drive_alone_vehicle_trips am_transit_person_trip_table am_total_transit_time_walk single_vehicle_to_work_travel_cost am_single_vehicle_to_work_travel_time am_walking_person_trips gid
from_zone_id to_zone_id
5 90 180.679993 NaN NaN 0 0 NaN 5.32 124.339996 NaN 6626
6 2558 453.390015 NaN NaN 0 0 NaN 10.95 203.419998 NaN 11926
7 762 337.440002 NaN NaN 0 0 NaN 7.79 145.119995 NaN 12962
10 2764 247.100006 NaN NaN 0 0 NaN 6.49 147.740005 NaN 18996
11 2033 317.130005 NaN NaN 0 0 NaN 8.86 164.080002 NaN 23958

In [2]:
dist_rail = dset.parcels[['dist_rail']]

In [5]:
dist_rail.to_csv('C:\\urbansim\\data\\swap\\parcel_dist_rail.csv')

In [8]:
dist_rail.dist_rail.index.values.max()


Out[8]:
1128935

In [22]:
if dset.parcels.index.name != 'parcel_id':
    print 'yoyo'
    dset.parcels = dset.parcels.set_index('parcel_id')


yoyo

In [10]:
p2 = pd.read_csv('C:\\urbansim\\data\\swap\\parcel_dist_rail.csv', index_col=['parcel_id'])

In [15]:
p2.dist_rail


Out[15]:
parcel_id
1120000      123324
1120001      151541
1120002      152660
1120003       72416
1120004       82803
1120005      109602
1120006      114092
1120007       64585
1120008       64683
1120009       65086
1120010       64487
1120011       66009
1120012       65978
1120013       65898
1120014       65948
...
612086         8194
612087         8168
612088         8140
612089         8114
612090         8088
612091         8062
612092         8023
612093         8197
612094         8218
612095         8240
612096         8264
1062940      159529
1078965      108407
1085170      116760
1078882      108734
Name: dist_rail, Length: 949484, dtype: int64

In [14]:
dist_rail.di


Out[14]:
<class 'pandas.core.frame.DataFrame'>
Int64Index: 949484 entries, 1120000 to 1078882
Data columns (total 1 columns):
dist_rail    949484  non-null values
dtypes: int64(1)

In [25]:
dset.parcels


Out[25]:
<class 'pandas.core.frame.DataFrame'>
Int64Index: 949484 entries, 1120000 to 1078882
Data columns (total 32 columns):
county_id                       949484  non-null values
parcel_sqft                     949484  non-null values
land_value                      949484  non-null values
zone_id                         949484  non-null values
lu_type_id                      949484  non-null values
centroid_x                      949484  non-null values
centroid_y                      949484  non-null values
tax_exempt_flag                 949484  non-null values
school_district                 949484  non-null values
zoning_id                       949484  non-null values
dist_bus                        949484  non-null values
dist_rail                       949484  non-null values
in_ugb                          949484  non-null values
in_uga                          949484  non-null values
env_constr_park                 949484  non-null values
env_constr_lake                 949484  non-null values
env_constr_floodplain           949484  non-null values
env_constr_river                949484  non-null values
env_constr_landslide            949484  non-null values
far_id                          949484  non-null values
prop_constrained                949484  non-null values
in_denver                       949484  non-null values
ln_dist_rail                    949484  non-null values
ln_dist_bus                     949484  non-null values
ln_land_value                   949484  non-null values
land_value_per_sqft             949484  non-null values
rail_within_mile                949484  non-null values
cherry_creek_school_district    949484  non-null values
acres                           949484  non-null values
ln_acres                        949484  non-null values
nonres_far                      686965  non-null values
ln_units_per_acre               686965  non-null values
dtypes: float64(15), int32(3), int64(14)