Correlation analysis

Libraries

Show the code
library(tidyverse)
library(skimr)
library(GGally)

Data

Show the code
leic_emb <- 
  read_csv("../data/leicester-1864_emb_gnnuf_model_v0-5_incl-pool-with-stats.csv")

leic_emb %>% 
  skim()
Data summary
Name Piped data
Number of rows 12984
Number of columns 20
_______________________
Column type frequency:
numeric 20
________________________
Group variables None

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
osmnx_node_id 0 1 1.389551e+09 1.798869e+09 337976.00 248456812.00 683864917.00 1.692438e+09 8.270480e+09 ▇▂▁▁▁
EMB000 0 1 2.600000e-01 7.700000e-01 -1.00 -0.64 0.63 1.000000e+00 1.000000e+00 ▃▁▁▂▇
EMB001 0 1 1.700000e-01 7.700000e-01 -1.00 -0.55 0.48 9.900000e-01 1.000000e+00 ▅▂▁▂▇
EMB000pooled 0 1 1.500000e-01 4.100000e-01 -0.89 -0.16 0.18 4.800000e-01 9.700000e-01 ▂▅▇▇▃
EMB001pooled 0 1 1.300000e-01 4.300000e-01 -0.97 -0.21 0.18 4.700000e-01 1.000000e+00 ▂▅▆▇▃
closeness_networkwide 0 1 1.000000e-02 0.000000e+00 0.00 0.01 0.02 2.000000e-02 2.000000e-02 ▁▁▁▇▇
betweenness_networkwide 0 1 0.000000e+00 1.000000e-02 0.00 0.00 0.00 0.000000e+00 1.600000e-01 ▇▁▁▁▁
closeness_egograph 0 1 2.100000e-01 6.000000e-02 0.00 0.16 0.20 2.500000e-01 6.200000e-01 ▁▇▃▁▁
betweenness_egograph 0 1 1.900000e-01 1.800000e-01 0.00 0.00 0.16 3.200000e-01 7.700000e-01 ▇▅▃▂▁
n 0 1 4.502000e+01 2.296000e+01 9.00 28.00 41.00 5.700000e+01 1.480000e+02 ▇▇▂▁▁
m 0 1 9.095000e+01 4.564000e+01 9.00 57.00 84.00 1.170000e+02 2.980000e+02 ▆▇▃▁▁
k_avg 0 1 4.050000e+00 4.100000e-01 2.00 3.81 4.00 4.300000e+00 5.580000e+00 ▁▁▇▅▁
edge_length_total 0 1 6.214190e+03 2.869930e+03 676.23 3980.57 5838.42 8.153090e+03 1.752522e+04 ▅▇▅▁▁
edge_length_avg 0 1 7.201000e+01 1.945000e+01 30.48 57.87 70.44 8.451000e+01 1.930200e+02 ▅▇▂▁▁
streets_per_node_avg 0 1 2.620000e+00 3.000000e-01 1.89 2.37 2.63 2.860000e+00 3.370000e+00 ▂▇▇▇▂
intersection_count 0 1 3.497000e+01 1.919000e+01 4.00 21.00 31.00 4.500000e+01 1.260000e+02 ▇▇▂▁▁
street_length_total 0 1 3.471060e+03 1.789600e+03 434.37 2118.08 3153.16 4.520500e+03 1.058424e+04 ▆▇▃▁▁
street_segment_count 0 1 5.174000e+01 2.914000e+01 8.00 31.00 46.00 6.600000e+01 1.930000e+02 ▇▆▂▁▁
street_length_avg 0 1 7.104000e+01 1.947000e+01 30.48 56.91 69.52 8.351000e+01 1.764400e+02 ▅▇▂▁▁
circuity_avg 0 1 1.040000e+00 5.000000e-02 1.00 1.02 1.03 1.050000e+00 1.750000e+00 ▇▁▁▁▁

Correlations

Show the code
leic_emb %>%
  select(-osmnx_node_id) %>% 
  relocate(EMB000, .after = last_col()) %>%
  relocate(EMB001, .after = last_col()) %>%
  relocate(EMB000pooled, .after = last_col()) %>%
  relocate(EMB001pooled, .after = last_col()) %>%
  ggpairs(
    upper = list(continuous = wrap(ggally_cor, method = "kendall")),
    lower = list(continuous = wrap("points", alpha = 0.3, size=0.1))
  )