Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
70 changes: 34 additions & 36 deletions dvc.lock
Original file line number Diff line number Diff line change
Expand Up @@ -54,7 +54,7 @@ stages:
md5: f021afa12f9d7c893412a0b2980ab187.dir
size: 104535557
nfiles: 13
filter_sql:
filter_wikipedia_sql:
cmd: filter_wikipedia_sql data/Wiki/wp_SQL/enwiki-page.sql.gz
data/filtered/wikidata_titles.txt -o
data/filtered/OneZoom_enwiki-latest-page.sql
Expand Down Expand Up @@ -83,12 +83,13 @@ stages:
md5: 87ff995e9d5028efc185857f34448746.dir
size: 587064765
nfiles: 3
add_ott_numbers:
add_ott_numbers_to_trees:
cmd:
- rm -rf data/OZTreeBuild/AllLife/BespokeTree/include_OT_v16.1
- mkdir -p data/OZTreeBuild/AllLife/BespokeTree/include_OT_v16.1
- add_ott_numbers_to_trees --savein
data/OZTreeBuild/AllLife/BespokeTree/include_OT_v16.1
data/OZTreeBuild/AllLife/BespokeTree/include_OT_v16.1 --output_info
data/add_ott_numbers_to_trees.log
data/OZTreeBuild/AllLife/BespokeTree/include_noAutoOTT/*.[pP][hH][yY]
deps:
- path: data/OZTreeBuild/AllLife/BespokeTree/include_noAutoOTT/
Expand All @@ -103,23 +104,20 @@ stages:
outs:
- path: data/OZTreeBuild/AllLife/BespokeTree/include_OT_v16.1/
hash: md5
md5: 3981ca3104e6e42846f0dca4dae932d4.dir
size: 1805911
nfiles: 56
prepare_open_trees:
md5: cfe57e6fbd3572028ac2d83203a96fe4.dir
size: 1534894
nfiles: 55
get_open_trees_from_one_zoom:
cmd:
- mkdir -p data/OZTreeBuild/AllLife/OpenTreeParts/OpenTree_all
- cp -n data/OZTreeBuild/AllLife/OpenTreeParts/OT_required/*.nwk
data/OZTreeBuild/AllLife/OpenTreeParts/OpenTree_all/ 2>/dev/null || true
- cd data/OZTreeBuild/AllLife && get_open_trees_from_one_zoom
../../OpenTree/v16.1/draftversion.tre OpenTreeParts/OpenTree_all/
BespokeTree/include_OT_v16.1/*.PHY
deps:
- path: data/OZTreeBuild/AllLife/BespokeTree/include_OT_v16.1/
hash: md5
md5: 3981ca3104e6e42846f0dca4dae932d4.dir
size: 1805911
nfiles: 56
md5: cfe57e6fbd3572028ac2d83203a96fe4.dir
size: 1534894
nfiles: 55
- path: data/OZTreeBuild/AllLife/OpenTreeParts/OT_required/
hash: md5
md5: 81be05fde561126fb58b7bb7e8a0fbcd.dir
Expand All @@ -136,9 +134,9 @@ stages:
outs:
- path: data/OZTreeBuild/AllLife/OpenTreeParts/OpenTree_all/
hash: md5
md5: 3f8df65320201c2db0ee35b17916c7cb.dir
size: 81928129
nfiles: 229
md5: ed1333f8ed0fc9f2ca4315ce9cb3cc42.dir
size: 81927748
nfiles: 227
download_eol:
cmd:
- curl -L -D data/EOL/.headers -o data/EOL/provider_ids.csv.gz
Expand Down Expand Up @@ -174,22 +172,22 @@ stages:
hash: md5
md5: f7c9bb8374957c07168bec36d6591347
size: 221682224
build_tree:
build_oz_tree:
cmd:
- cd data/OZTreeBuild/AllLife && build_oz_tree
BespokeTree/include_OT_v16.1/Base.PHY OpenTreeParts/OpenTree_all/
AllLife_full_tree.phy
deps:
- path: data/OZTreeBuild/AllLife/BespokeTree/include_OT_v16.1/
hash: md5
md5: 3981ca3104e6e42846f0dca4dae932d4.dir
size: 1805911
nfiles: 56
md5: cfe57e6fbd3572028ac2d83203a96fe4.dir
size: 1534894
nfiles: 55
- path: data/OZTreeBuild/AllLife/OpenTreeParts/OpenTree_all/
hash: md5
md5: 3f8df65320201c2db0ee35b17916c7cb.dir
size: 81928129
nfiles: 229
md5: ed1333f8ed0fc9f2ca4315ce9cb3cc42.dir
size: 81927748
nfiles: 227
params:
params.yaml:
ot_version: v16.1
Expand All @@ -199,7 +197,7 @@ stages:
hash: md5
md5: 0b17680b0a0a633f8ae50e4a8f68f17a
size: 83061022
create_tables:
CSV_base_table_creator:
cmd:
- mkdir -p data/output_files
- CSV_base_table_creator data/OZTreeBuild/AllLife/AllLife_full_tree.phy
Expand All @@ -210,7 +208,7 @@ stages:
--version 28017344 --exclude Archosauria_ott335588 Dinosauria_ott90215
--extra_source_file
data/OZTreeBuild/AllLife/BespokeTree/SupplementaryTaxonomy.tsv 2>
data/output_files/ordered_output.log
data/CSV_base_table_creator.log
deps:
- path: data/OZTreeBuild/AllLife/AllLife_full_tree.phy
hash: md5
Expand Down Expand Up @@ -251,34 +249,34 @@ stages:
outs:
- path: data/output_files/
hash: md5
md5: 80b98cbf1167374064c0fdf6f4cec926.dir
size: 1182677604
nfiles: 8
make_js:
md5: 81dfa9c3747bbe94c57161cc8e22d5c9.dir
size: 1158499655
nfiles: 7
make_js_treefiles:
cmd:
- mkdir -p data/js_output
- make_js_treefiles --outdir data/js_output
deps:
- path: data/output_files/
hash: md5
md5: 80b98cbf1167374064c0fdf6f4cec926.dir
size: 1182677604
nfiles: 8
md5: 81dfa9c3747bbe94c57161cc8e22d5c9.dir
size: 1158499655
nfiles: 7
outs:
- path: data/js_output/
hash: md5
md5: b6808a7ee61a8b566f757ed5dca39a46.dir
size: 8293094
md5: 9782411b79a64d6da09afacae2f3f047.dir
size: 8297912
nfiles: 6
discover_wikidata_url:
discover_latest_wikidata_dump_url:
cmd: discover_latest_wikidata_dump_url >
data/Wiki/wd_JSON/latest-all-json-bz2-url.txt
outs:
- path: data/Wiki/wd_JSON/latest-all-json-bz2-url.txt
hash: md5
md5: e094b0f57c0c14e1016842c2dac5482e
size: 90
discover_enwiki_sql_url:
discover_latest_enwiki_sql_url:
cmd: discover_latest_enwiki_sql_url >
data/Wiki/wp_SQL/enwiki-page-sql-gz-url.txt
outs:
Expand Down
21 changes: 10 additions & 11 deletions dvc.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -10,13 +10,14 @@ stages:
- data/OpenTree/${ot_version}/

# ~20 secs
add_ott_numbers:
add_ott_numbers_to_trees:
cmd:
- rm -rf data/OZTreeBuild/${oz_tree}/BespokeTree/include_OT_${ot_version}
- mkdir -p data/OZTreeBuild/${oz_tree}/BespokeTree/include_OT_${ot_version}
- >-
add_ott_numbers_to_trees
--savein data/OZTreeBuild/${oz_tree}/BespokeTree/include_OT_${ot_version}
--output_info data/add_ott_numbers_to_trees.log
data/OZTreeBuild/${oz_tree}/BespokeTree/include_noAutoOTT/*.[pP][hH][yY]
deps:
- data/OZTreeBuild/${oz_tree}/BespokeTree/include_noAutoOTT/
Expand All @@ -27,10 +28,8 @@ stages:
- data/OZTreeBuild/${oz_tree}/BespokeTree/include_OT_${ot_version}/

# ~a few secs
prepare_open_trees:
get_open_trees_from_one_zoom:
cmd:
- mkdir -p data/OZTreeBuild/${oz_tree}/OpenTreeParts/OpenTree_all
- cp -n data/OZTreeBuild/${oz_tree}/OpenTreeParts/OT_required/*.nwk data/OZTreeBuild/${oz_tree}/OpenTreeParts/OpenTree_all/ 2>/dev/null || true
- >-
cd data/OZTreeBuild/${oz_tree} &&
get_open_trees_from_one_zoom
Expand All @@ -47,7 +46,7 @@ stages:
outs:
- data/OZTreeBuild/${oz_tree}/OpenTreeParts/OpenTree_all/

build_tree:
build_oz_tree:
cmd:
- >-
cd data/OZTreeBuild/${oz_tree} &&
Expand Down Expand Up @@ -92,7 +91,7 @@ stages:
outs:
- data/filtered/OneZoom_provider_ids.csv

discover_wikidata_url:
discover_latest_wikidata_dump_url:
cmd: >-
discover_latest_wikidata_dump_url > data/Wiki/wd_JSON/latest-all-json-bz2-url.txt
outs:
Expand All @@ -119,7 +118,7 @@ stages:
outs:
- data/filtered/wikidata_titles.txt

discover_enwiki_sql_url:
discover_latest_enwiki_sql_url:
cmd: >-
discover_latest_enwiki_sql_url > data/Wiki/wp_SQL/enwiki-page-sql-gz-url.txt
outs:
Expand All @@ -134,7 +133,7 @@ stages:
outs:
- data/Wiki/wp_SQL/enwiki-page.sql.gz

filter_sql:
filter_wikipedia_sql:
cmd: >-
filter_wikipedia_sql
data/Wiki/wp_SQL/enwiki-page.sql.gz
Expand All @@ -160,7 +159,7 @@ stages:
persist: true

# ~10 mins
create_tables:
CSV_base_table_creator:
cmd:
- mkdir -p data/output_files
- >-
Expand All @@ -175,7 +174,7 @@ stages:
--version ${build_version}
--exclude ${exclude_from_popularity}
--extra_source_file data/OZTreeBuild/${oz_tree}/BespokeTree/SupplementaryTaxonomy.tsv
2> data/output_files/ordered_output.log
2> data/CSV_base_table_creator.log
deps:
- data/OZTreeBuild/${oz_tree}/${oz_tree}_full_tree.phy
- data/OpenTree/${ot_version}/taxonomy.tsv
Expand All @@ -192,7 +191,7 @@ stages:
outs:
- data/output_files/

make_js:
make_js_treefiles:
cmd:
- mkdir -p data/js_output
- make_js_treefiles --outdir data/js_output
Expand Down
Loading
Loading