notebook.community

Edit and run



In [12]:

    
import clusterpy
datos = clusterpy.importArcData('data/distritos_variables')
datos.cluster('arisel', ['viv'], 50, wType='rook', inits=10, dissolve=0)
datos.fieldNames









    



Loading data/distritos_variables.dbf
Loading data/distritos_variables.shp
Done
Getting variables
Variables successfully extracted
Running original Arisel algorithm
Number of areas:  156
Number of regions:  50
initial Solution:  [25, 25, 29, 21, 38, 2, 34, 38, 30, 28, 27, 12, 24, 42, 30, 39, 29, 44, 10, 15, 38, 16, 21, 0, 48, 30, 5, 1, 49, 6, 16, 15, 20, 18, 24, 6, 16, 8, 6, 15, 33, 49, 14, 30, 15, 35, 30, 20, 14, 25, 26, 39, 7, 43, 24, 49, 17, 38, 4, 29, 14, 25, 47, 0, 11, 36, 25, 29, 39, 25, 21, 16, 34, 31, 44, 25, 32, 23, 33, 3, 27, 42, 21, 29, 9, 40, 46, 25, 25, 29, 38, 48, 20, 25, 49, 21, 45, 25, 21, 25, 16, 49, 15, 45, 29, 35, 22, 13, 37, 41, 21, 30, 25, 30, 40, 39, 46, 30, 7, 13, 19, 21, 25, 36, 30, 25, 30, 33, 21, 21, 29, 49, 22, 49, 41, 15, 38, 28, 16, 13, 25, 15, 30, 4, 15, 38, 21, 25, 47, 27, 25, 45, 47, 15, 20, 47]
initial O.F:  3540007005.0
FINAL SOLUTION:  [25, 25, 29, 21, 38, 2, 34, 38, 30, 23, 40, 12, 24, 35, 30, 39, 29, 44, 10, 15, 38, 16, 21, 0, 48, 30, 5, 1, 49, 6, 16, 15, 20, 18, 24, 6, 21, 8, 6, 15, 25, 49, 14, 30, 15, 35, 30, 20, 14, 25, 26, 39, 7, 43, 24, 49, 17, 38, 4, 29, 14, 25, 47, 25, 11, 36, 25, 29, 39, 25, 21, 21, 34, 31, 44, 25, 28, 23, 33, 3, 27, 35, 21, 29, 9, 0, 46, 15, 25, 29, 38, 48, 20, 25, 49, 32, 45, 25, 21, 25, 16, 49, 15, 39, 29, 35, 42, 13, 37, 41, 21, 30, 25, 30, 0, 39, 46, 30, 7, 13, 19, 21, 25, 36, 30, 15, 30, 33, 21, 31, 29, 49, 22, 49, 49, 15, 38, 23, 16, 13, 25, 15, 30, 4, 15, 38, 4, 25, 47, 40, 38, 39, 47, 15, 20, 24]
FINAL OF:  2383192095.0
Done
Adding variables
Done






    Out[12]:





['ID',
 'comercio',
 'cve_dist',
 'entrada',
 'gid',
 'id',
 'loop',
 'ocio',
 'pob',
 'salida',
 'servicios',
 'viv',
 'arisel_20160406114543']



In [13]:

    
datos.cluster('arisel', ['comercio'], 50, wType='rook', inits=10, dissolve=0)
datos.fieldNames









    



Getting variables
Variables successfully extracted
Running original Arisel algorithm
Number of areas:  156
Number of regions:  50
initial Solution:  [16, 20, 43, 42, 20, 11, 9, 43, 7, 31, 45, 36, 4, 10, 1, 36, 43, 42, 32, 36, 43, 26, 42, 15, 38, 7, 43, 6, 13, 8, 39, 36, 11, 21, 14, 20, 39, 20, 20, 13, 20, 13, 24, 7, 13, 10, 13, 23, 11, 20, 36, 13, 3, 13, 4, 13, 0, 20, 5, 43, 13, 28, 4, 15, 13, 13, 3, 43, 13, 45, 42, 42, 4, 18, 42, 20, 40, 26, 41, 10, 35, 36, 25, 43, 0, 45, 39, 38, 41, 7, 20, 36, 23, 20, 13, 40, 12, 20, 25, 19, 41, 13, 22, 36, 7, 34, 49, 13, 37, 2, 17, 1, 20, 7, 45, 36, 39, 32, 13, 13, 2, 25, 20, 13, 7, 7, 7, 41, 47, 48, 43, 2, 49, 13, 2, 36, 43, 40, 29, 13, 45, 27, 13, 44, 33, 20, 0, 3, 4, 45, 20, 36, 4, 13, 30, 46]
initial O.F:  24936479.0
FINAL SOLUTION:  [16, 20, 43, 42, 20, 11, 9, 43, 7, 31, 45, 36, 4, 10, 1, 36, 43, 42, 32, 33, 43, 26, 42, 15, 38, 20, 43, 6, 13, 8, 39, 36, 23, 21, 14, 20, 39, 20, 20, 13, 20, 24, 2, 7, 13, 10, 13, 23, 11, 20, 36, 13, 3, 13, 4, 24, 0, 20, 44, 43, 13, 28, 4, 15, 13, 24, 3, 43, 13, 45, 42, 42, 9, 18, 42, 20, 29, 26, 41, 10, 35, 36, 25, 43, 0, 45, 39, 33, 41, 20, 20, 5, 23, 20, 13, 40, 12, 20, 25, 19, 41, 24, 22, 36, 7, 34, 10, 13, 37, 2, 17, 1, 20, 20, 45, 36, 39, 32, 13, 13, 2, 25, 20, 13, 7, 7, 7, 41, 47, 48, 43, 2, 49, 13, 2, 33, 43, 29, 29, 13, 45, 27, 13, 44, 33, 43, 0, 3, 9, 45, 20, 33, 4, 36, 30, 46]
FINAL OF:  20005070.0
Done
Adding variables
Done






    Out[13]:





['ID',
 'comercio',
 'cve_dist',
 'entrada',
 'gid',
 'id',
 'loop',
 'ocio',
 'pob',
 'salida',
 'servicios',
 'viv',
 'arisel_20160406114543',
 'arisel_20160406114812']



In [14]:

    
datos.cluster('arisel', ['entrada'], 50, wType='rook', inits=10, dissolve=0)
datos.fieldNames









    



Getting variables
Variables successfully extracted
Running original Arisel algorithm
Number of areas:  156
Number of regions:  50
initial Solution:  [20, 4, 15, 23, 2, 0, 39, 37, 21, 2, 49, 31, 46, 8, 5, 48, 18, 27, 29, 18, 15, 37, 34, 49, 18, 21, 24, 8, 26, 16, 23, 48, 0, 8, 7, 10, 23, 10, 10, 48, 4, 47, 47, 21, 38, 18, 22, 0, 42, 20, 31, 47, 11, 49, 13, 47, 25, 16, 18, 15, 42, 19, 39, 6, 49, 43, 20, 15, 48, 12, 9, 23, 39, 27, 23, 10, 37, 28, 30, 31, 49, 18, 36, 17, 9, 6, 33, 18, 30, 15, 2, 31, 49, 3, 47, 27, 48, 10, 40, 32, 28, 47, 32, 48, 15, 18, 8, 0, 39, 39, 40, 32, 14, 10, 49, 48, 33, 29, 35, 39, 48, 40, 20, 47, 21, 41, 21, 28, 27, 9, 15, 39, 8, 45, 39, 48, 2, 37, 33, 0, 19, 48, 43, 40, 48, 10, 18, 1, 39, 49, 44, 18, 39, 22, 0, 46]
initial O.F:  26823685414.0
FINAL SOLUTION:  [20, 4, 17, 23, 2, 0, 39, 37, 21, 2, 49, 31, 7, 8, 5, 48, 18, 23, 29, 18, 15, 37, 34, 49, 18, 21, 24, 8, 26, 16, 23, 18, 0, 8, 7, 10, 23, 10, 10, 18, 28, 47, 47, 21, 38, 18, 22, 0, 42, 44, 31, 47, 11, 49, 13, 47, 25, 44, 18, 15, 42, 19, 39, 6, 49, 43, 20, 15, 47, 12, 9, 23, 39, 27, 23, 10, 37, 28, 30, 31, 49, 18, 36, 17, 9, 6, 33, 18, 2, 17, 2, 31, 49, 3, 47, 27, 48, 10, 40, 43, 28, 43, 38, 8, 17, 18, 8, 0, 39, 39, 36, 32, 14, 10, 49, 48, 33, 29, 35, 39, 48, 36, 20, 47, 21, 41, 21, 2, 27, 9, 17, 39, 8, 45, 39, 18, 2, 37, 33, 0, 19, 48, 43, 36, 18, 10, 18, 1, 39, 49, 44, 18, 39, 22, 0, 46]
FINAL OF:  20259491144.0
Done
Adding variables
Done






    Out[14]:





['ID',
 'comercio',
 'cve_dist',
 'entrada',
 'gid',
 'id',
 'loop',
 'ocio',
 'pob',
 'salida',
 'servicios',
 'viv',
 'arisel_20160406114543',
 'arisel_20160406114812',
 'arisel_20160406115125']



In [15]:

    
datos.exportArcData('data/variables_regiones')









    



Writing ESRI files
Writing DBF file
Done
ESRI files created



In [16]:

    
from geopandas import GeoDataFrame
import numpy as np
datos = GeoDataFrame.from_file('data/variables_regiones.shp')
intensidad = datos['comercio'] + datos['viv'] + datos['ocio'] + datos['servicios']
prop_comercio = datos['comercio'] / intensidad
prop_viv = datos['viv'] / intensidad
prop_ocio = datos['ocio'] / intensidad
prop_servicios = datos['servicios'] / intensidad
entropia = (prop_comercio*np.log(prop_comercio) + prop_viv*np.log(prop_viv) + prop_ocio*np.log(prop_ocio)
           + prop_servicios*np.log(prop_servicios))/np.log(4)
entropia.head()









    Out[16]:





0   -0.443781
1   -0.250027
2   -0.303138
3   -0.178275
4   -0.235811
dtype: float64



In [17]:

    
datos['entropia'] = entropia
datos.head()









    Out[17]:






  
    
      
      ID
      comercio
      cve_dist
      entrada
      geometry
      gid
      id_1
      loop
      ocio
      pob
      region_1
      region_2
      region_3
      salida
      servicios
      viv
      entropia
    
  
  
    
      0
      1
      9614
      034
      201286
      POLYGON ((486947.2187500237 2148842.250066909,...
      1
      None
      27627
      95
      2125687
      25
      16
      20
      200217
      579
      32618
      -0.443781
    
    
      1
      2
      2905
      083
      209264
      POLYGON ((478110.2187500393 2134697.250066519,...
      2
      None
      76022
      82
      3563363
      25
      20
      4
      209859
      949
      42238
      -0.250027
    
    
      2
      3
      2944
      113
      65701
      POLYGON ((501006.0312499983 2148019.750066887,...
      3
      None
      10611
      72
      3128496
      29
      43
      17
      66706
      459
      26003
      -0.303138
    
    
      3
      4
      2425
      131
      42385
      (POLYGON ((507974.718749986 2125105.250066254,...
      4
      None
      8468
      60
      4842162
      21
      42
      23
      43106
      256
      44080
      -0.178275
    
    
      4
      5
      2849
      063
      128608
      POLYGON ((487190.7500000236 2140396.250066676,...
      5
      None
      24472
      30
      4146145
      38
      20
      2
      128756
      441
      35981
      -0.235811



In [18]:

    
datos.to_file('data/variables_regiones.shp')



In [19]:

    
datos = GeoDataFrame.from_file('data/variables_regiones.shp')
datos.head()









    Out[19]:






  
    
      
      ID
      comercio
      cve_dist
      entrada
      entropia
      geometry
      gid
      id_1
      loop
      ocio
      pob
      region_1
      region_2
      region_3
      salida
      servicios
      viv
    
  
  
    
      0
      1
      9614
      034
      201286
      -0.443781
      POLYGON ((486947.2187500237 2148842.250066909,...
      1
      None
      27627
      95
      2125687
      25
      16
      20
      200217
      579
      32618
    
    
      1
      2
      2905
      083
      209264
      -0.250027
      POLYGON ((478110.2187500393 2134697.250066519,...
      2
      None
      76022
      82
      3563363
      25
      20
      4
      209859
      949
      42238
    
    
      2
      3
      2944
      113
      65701
      -0.303138
      POLYGON ((501006.0312499983 2148019.750066887,...
      3
      None
      10611
      72
      3128496
      29
      43
      17
      66706
      459
      26003
    
    
      3
      4
      2425
      131
      42385
      -0.178275
      (POLYGON ((507974.718749986 2125105.250066254,...
      4
      None
      8468
      60
      4842162
      21
      42
      23
      43106
      256
      44080
    
    
      4
      5
      2849
      063
      128608
      -0.235811
      POLYGON ((487190.7500000236 2140396.250066676,...
      5
      None
      24472
      30
      4146145
      38
      20
      2
      128756
      441
      35981

	ID	comercio	cve_dist	entrada	geometry	gid	id_1	loop	ocio	pob	region_1	region_2	region_3	salida	servicios	viv	entropia
0	1	9614	034	201286	POLYGON ((486947.2187500237 2148842.250066909,...	1	None	27627	95	2125687	25	16	20	200217	579	32618	-0.443781
1	2	2905	083	209264	POLYGON ((478110.2187500393 2134697.250066519,...	2	None	76022	82	3563363	25	20	4	209859	949	42238	-0.250027
2	3	2944	113	65701	POLYGON ((501006.0312499983 2148019.750066887,...	3	None	10611	72	3128496	29	43	17	66706	459	26003	-0.303138
3	4	2425	131	42385	(POLYGON ((507974.718749986 2125105.250066254,...	4	None	8468	60	4842162	21	42	23	43106	256	44080	-0.178275
4	5	2849	063	128608	POLYGON ((487190.7500000236 2140396.250066676,...	5	None	24472	30	4146145	38	20	2	128756	441	35981	-0.235811