schema: '2.0'
stages:
prepare:
cmd: node bin/address-to-area.mjs > data/area-address.tsv
deps:
- path: bin/address-to-area.mjs
md5: 586c0f15529591e46a6b22e2a05770d5
size: 942
- path: data/addresses-40-cnrs-rnsr-big-classes-train.txt
md5: 612c9731294d230f5fd4ed8c10d67468
size: 3694626
- path: data/netscity-ville-aire-uniq.tsv
md5: 85e405b8cc452b953e8dfd12dae5d8d6
size: 341275
- path: libs/geo.mjs
md5: af499b4463e041aeb5f4ca58af486565
size: 2443
params:
params.yaml:
prepare.input: data/addresses-40-cnrs-rnsr-big-classes-train.txt
outs:
- path: data/area-address.tsv
md5: 179a8eb09f2ddf72dd9aa2add136fb87
size: 4010846
extract-areas:
cmd: cat data/area-address.tsv| cut -f1 | sort -u > data/areas.txt
deps:
- path: data/area-address.tsv
md5: 179a8eb09f2ddf72dd9aa2add136fb87
size: 4010846
outs:
- path: data/areas.txt
md5: 6102ce8099fd61bccb6eb606b66ef260
size: 964