:: install_github ("LukeCe/spflow" ,force = TRUE )
Using github PAT from envvar GITHUB_PAT
Downloading GitHub repo LukeCe/spflow@HEAD
── R CMD build ─────────────────────────────────────────────────────────────────
* checking for file 'C:\Users\idrin\AppData\Local\Temp\Rtmp48lcIE\remotes573c72cf387f\LukeCe-spflow-df91367/DESCRIPTION' ... OK
* preparing 'spflow':
* checking DESCRIPTION meta-information ... OK
* installing the package to process help pages
Loading required namespace: spflow
* saving partial Rd database
* checking for LF line-endings in source and make files and shell scripts
* checking for empty or unneeded directories
* building 'spflow_0.1.0.9010.tar.gz'
:: p_load (tmap, sf, spdep, sp, Matrix, spflow, reshape2, knitr, tidyverse)
<- st_read (dsn = "data/geospatial" ,layer = "MPSZ-2019" ) %>% st_transform (crs = 3414 )
Reading layer `MPSZ-2019' from data source
`C:\kekekay\ISSS624\In-class_Ex5\data\geospatial' using driver `ESRI Shapefile'
Simple feature collection with 332 features and 6 fields
Geometry type: MULTIPOLYGON
Dimension: XY
Bounding box: xmin: 103.6057 ymin: 1.158699 xmax: 104.0885 ymax: 1.470775
Geodetic CRS: WGS 84
intersect to see how many busstops in each planning subzone
filter 0 values - mpsz-busstop
prepare spatial weights
use k-means to find 3 nearby neighbors mpsz_nb - summary of neighbour list
take note -preparing the spatial weights - exclude those messy maps
#| eval:false - for those time consuming computation, hide it
Getting started
<- read_rds ("data/rds/mpsz_nb.rds" ) <- read_rds ("data/rds/mpsz_flow.rds" ) <- read_rds ("data/rds/mpsz_var.rds" )
origin-sz should be grid , must be char
the 0 values can be retained coz it jusr measn there is no flow between 2 bus stops
<- spflow_network (id_net = "sg" ,node_neighborhood = nb2mat (mpsz_nb$ by_contiguity),node_data = mpsz_var,node_key_column = "SZ_CODE" )
Spatial network nodes with id: sg
--------------------------------------------------
Number of nodes: 313
Average number of links per node: 6.077
Density of the neighborhood matrix: 1.94% (non-zero connections)
Data on nodes:
SZ_NAME SZ_CODE BUSSTOP_COUNT AGE7_12 AGE13_24 AGE25_64
1 INSTITUTION HILL RVSZ05 2 330 360 2260
2 ROBERTSON QUAY SRSZ01 10 320 350 2200
3 FORT CANNING MUSZ02 6 0 10 30
4 MARINA EAST (MP) MPSZ05 2 0 0 0
5 SENTOSA SISZ01 1 200 260 1440
6 CITY TERMINALS BMSZ17 10 0 0 0
--- --- --- --- --- --- ---
308 NEE SOON YSSZ07 12 90 140 590
309 UPPER THOMSON BSSZ01 47 1590 3660 15980
310 SHANGRI-LA AMSZ05 12 810 1920 9650
311 TOWNSVILLE AMSZ04 9 980 2000 11320
312 MARYMOUNT BSSZ02 25 1610 4060 16860
313 TUAS VIEW EXTENSION TSSZ06 11 0 0 0
SCHOOL_COUNT BUSINESS_COUNT RETAILS_COUNT FINSERV_COUNT ENTERTN_COUNT
1 1 6 26 3 0
2 0 4 207 18 6
3 0 7 17 0 3
4 0 0 0 0 0
5 0 1 84 29 2
6 0 11 14 4 0
--- --- --- --- --- ---
308 0 0 7 0 0
309 3 21 305 30 0
310 3 0 53 9 0
311 1 0 83 11 0
312 3 19 135 8 0
313 0 53 3 1 0
FB_COUNT LR_COUNT COORD_X COORD_Y
1 4 3 103.84 1.29
2 38 11 103.84 1.29
3 4 7 103.85 1.29
4 0 0 103.88 1.29
5 38 20 103.83 1.25
6 15 0 103.85 1.26
--- --- --- --- ---
308 0 0 103.81 1.4
309 5 11 103.83 1.36
310 0 0 103.84 1.37
311 1 1 103.85 1.36
312 3 11 103.84 1.35
313 0 0 103.61 1.26
spflow_network : neighbour list ,which matrix to use(Kmeans or contiguity)
id_net: re-assign ID - new
so that we can have a table includes all the areas and their neighbours
adding in flow w the net
take note of the sequence of orig_key_col and des_key_col
<- spflow_network_pair (id_orig_net = "sg" ,id_dest_net = "sg" ,pair_data = mpsz_flow,orig_key_column = "ORIGIN_SZ" ,dest_key_column = "DESTIN_SZ" )
Spatial network pair with id: sg_sg
--------------------------------------------------
Origin network id: sg (with 313 nodes)
Destination network id: sg (with 313 nodes)
Number of pairs: 97969
Completeness of pairs: 100.00% (97969/97969)
Data on node-pairs:
DESTIN_SZ ORIGIN_SZ DISTANCE TRIPS
1 RVSZ05 RVSZ05 0 67
314 SRSZ01 RVSZ05 305.74 251
627 MUSZ02 RVSZ05 951.83 0
940 MPSZ05 RVSZ05 5254.07 0
1253 SISZ01 RVSZ05 4975 0
1566 BMSZ17 RVSZ05 3176.16 0
--- --- --- --- ---
96404 YSSZ07 TSSZ06 26972.97 0
96717 BSSZ01 TSSZ06 25582.48 0
97030 AMSZ05 TSSZ06 26714.79 0
97343 AMSZ04 TSSZ06 27572.74 0
97656 BSSZ02 TSSZ06 26681.7 0
97969 TSSZ06 TSSZ06 0 270
combine mpsz_net and net_pairs to get mpsz_multi_net
<- spflow_network_multi (mpsz_net, mpsz_net_pairs)
Collection of spatial network nodes and pairs
--------------------------------------------------
Contains 1 spatial network nodes
With id : sg
Contains 1 spatial network pairs
With id : sg_sg
Availability of origin-destination pair information:
ID_ORIG_NET ID_DEST_NET ID_NET_PAIR COMPLETENESS C_PAIRS C_ORIG C_DEST
sg sg sg_sg 100.00% 97969/97969 313/313 313/313
since we only have 313 geo areas after we removed all the nobusstop value, so total number of flow should be 313^2 - check this if not will have error msg
before regression model, always rmb to check multicollinearity
pair_cor() - create correlation matrix (instead 1 by 1)
cor_image() -
for those highly correlated vars, either exclude or combine them tgt if they have similiar
<- log (1 + TRIPS) ~ # dependant var - usually is the flow + + + + + + + + P_ (log (DISTANCE + 1 ))<- pair_cor (spflow_formula = cor_formula,add_lags_x = FALSE ) # just to test the input var, no need the lag(from continguity) colnames (cor_mat) <- paste0 (substr (colnames (cor_mat),1 ,3 ),"..." )cor_image (cor_mat)
<- spflow (spflow_formula = log (1 + TRIPS) ~ O_ (BUSSTOP_COUNT + + D_ (SCHOOL_COUNT + + + + P_ (log (DISTANCE + 1 )),spflow_networks = mpsz_multi_net)
--------------------------------------------------
Spatial interaction model estimated by: MLE
Spatial correlation structure: SDM (model_9)
Dependent variable: log(1 + TRIPS)
--------------------------------------------------
Coefficients:
est sd t.stat p.val
rho_d 0.680 0.004 192.554 0.000
rho_o 0.678 0.004 187.733 0.000
rho_w -0.396 0.006 -65.592 0.000
(Intercept) 0.410 0.065 6.267 0.000
(Intra) 1.312 0.081 16.262 0.000
D_SCHOOL_COUNT 0.017 0.002 7.885 0.000
D_SCHOOL_COUNT.lag1 0.002 0.004 0.552 0.581
D_BUSINESS_COUNT 0.000 0.000 3.015 0.003
D_BUSINESS_COUNT.lag1 0.000 0.000 -0.249 0.804
D_RETAILS_COUNT 0.000 0.000 -0.306 0.759
D_RETAILS_COUNT.lag1 0.000 0.000 0.152 0.880
D_FINSERV_COUNT 0.002 0.000 6.787 0.000
D_FINSERV_COUNT.lag1 -0.002 0.001 -3.767 0.000
O_BUSSTOP_COUNT 0.002 0.000 6.807 0.000
O_BUSSTOP_COUNT.lag1 -0.001 0.000 -2.364 0.018
O_AGE25_64 0.000 0.000 7.336 0.000
O_AGE25_64.lag1 0.000 0.000 -2.797 0.005
P_log(DISTANCE + 1) -0.050 0.007 -6.794 0.000
--------------------------------------------------
R2_corr: 0.6942947
Observations: 97969
Model coherence: Validated
= par (mfrow = c (1 ,3 ),mar = c (2 ,2 ,2 ,2 ))spflow_moran_plots (base_model)
par (old_par)<- pair_cor (base_model)colnames (corr_residual) <- substr (colnames (corr_residual),1 ,3 )cor_image (corr_residual)
<- log (1 + TRIPS) ~ O_ (BUSSTOP_COUNT + + D_ (SCHOOL_COUNT + + + + P_ (log (DISTANCE + 1 ))<- spflow_control (estimation_method = "mle" ,model = "model_1" )<- spflow (spflow_networks = mpsz_multi_net,estimation_control = model_control)
<- log (1 + TRIPS) ~ O_ (BUSSTOP_COUNT + + D_ (SCHOOL_COUNT + + + + P_ (log (DISTANCE + 1 ))<- spflow_control (estimation_method = "mle" ,model = "model_8" )<- spflow (spflow_networks = mpsz_multi_net,estimation_control = model_control)
--------------------------------------------------
Spatial interaction model estimated by: MLE
Spatial correlation structure: SDM (model_8)
Dependent variable: log(1 + TRIPS)
--------------------------------------------------
Coefficients:
est sd t.stat p.val
rho_d 0.689 0.003 196.832 0.000
rho_o 0.687 0.004 192.214 0.000
rho_w -0.473 0.003 -142.469 0.000
(Intercept) 1.086 0.049 22.275 0.000
(Intra) 0.840 0.075 11.255 0.000
D_SCHOOL_COUNT 0.019 0.002 8.896 0.000
D_SCHOOL_COUNT.lag1 0.019 0.004 5.130 0.000
D_BUSINESS_COUNT 0.000 0.000 3.328 0.001
D_BUSINESS_COUNT.lag1 0.000 0.000 1.664 0.096
D_RETAILS_COUNT 0.000 0.000 -0.414 0.679
D_RETAILS_COUNT.lag1 0.000 0.000 -0.171 0.864
D_FINSERV_COUNT 0.002 0.000 6.150 0.000
D_FINSERV_COUNT.lag1 -0.003 0.001 -4.601 0.000
O_BUSSTOP_COUNT 0.003 0.000 7.676 0.000
O_BUSSTOP_COUNT.lag1 0.000 0.000 0.552 0.581
O_AGE25_64 0.000 0.000 6.870 0.000
O_AGE25_64.lag1 0.000 0.000 -0.462 0.644
P_log(DISTANCE + 1) -0.125 0.005 -22.865 0.000
--------------------------------------------------
R2_corr: 0.6965974
Observations: 97969
Model coherence: Validated
in this model libray, total have 3 models? so can manually change it from 1 2 8?
check documentation again
