From abf6ceb147cc869d259ca3142c92d434ea204ab7 Mon Sep 17 00:00:00 2001 From: Daniel Himmelstein Date: Wed, 7 Apr 2021 21:26:09 -0400 Subject: [PATCH] generate gzip datasets --- data/affiliations/countries.tsv.gz | 3 +++ data/affiliations/geocode.jsonl.gz | 3 +++ data/names/corresponding-authors.tsv.gz | 3 +++ data/names/fore-names.tsv.gz | 3 +++ data/names/full-names.tsv.gz | 3 +++ data/names/last-names.tsv.gz | 3 +++ data/pmc/affiliations.tsv.gz | 3 +++ data/pmc/authors.tsv.gz | 3 +++ data/pubmed/affiliations.tsv.gz | 3 +++ data/pubmed/articles.tsv.gz | 3 +++ data/pubmed/authors.tsv.gz | 3 +++ data/pubmed/efetch/BMC Bioinformatics.xml.gz | 3 +++ data/pubmed/efetch/Bioinformatics.xml.gz | 3 +++ data/pubmed/efetch/PLoS Comput Biol.xml.gz | 3 +++ data/pubmed/efetch/compbio-english.xml.gz | 3 +++ data/pubmed/efetch/compbio.xml.gz | 3 +++ data/pubmed/esummary/compbio-english.xml.gz | 3 +++ 17 files changed, 51 insertions(+) create mode 100644 data/affiliations/countries.tsv.gz create mode 100644 data/affiliations/geocode.jsonl.gz create mode 100644 data/names/corresponding-authors.tsv.gz create mode 100644 data/names/fore-names.tsv.gz create mode 100644 data/names/full-names.tsv.gz create mode 100644 data/names/last-names.tsv.gz create mode 100644 data/pmc/affiliations.tsv.gz create mode 100644 data/pmc/authors.tsv.gz create mode 100644 data/pubmed/affiliations.tsv.gz create mode 100644 data/pubmed/articles.tsv.gz create mode 100644 data/pubmed/authors.tsv.gz create mode 100644 data/pubmed/efetch/BMC Bioinformatics.xml.gz create mode 100644 data/pubmed/efetch/Bioinformatics.xml.gz create mode 100644 data/pubmed/efetch/PLoS Comput Biol.xml.gz create mode 100644 data/pubmed/efetch/compbio-english.xml.gz create mode 100644 data/pubmed/efetch/compbio.xml.gz create mode 100644 data/pubmed/esummary/compbio-english.xml.gz diff --git a/data/affiliations/countries.tsv.gz b/data/affiliations/countries.tsv.gz new file mode 100644 index 0000000..4f557c7 --- /dev/null +++ b/data/affiliations/countries.tsv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27b68e09107a7dc911f3dfd48b2f7f871dd40879a0d106cfa863700c3df9c0a7 +size 11180807 diff --git a/data/affiliations/geocode.jsonl.gz b/data/affiliations/geocode.jsonl.gz new file mode 100644 index 0000000..bc2bd50 --- /dev/null +++ b/data/affiliations/geocode.jsonl.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed734a7c715ee1d608c62903a051293ab9c240ecb1a95b8c9ff2c6b90a3118ca +size 29003845 diff --git a/data/names/corresponding-authors.tsv.gz b/data/names/corresponding-authors.tsv.gz new file mode 100644 index 0000000..c06600e --- /dev/null +++ b/data/names/corresponding-authors.tsv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab49cb641028be327c58bc6b1e96babdfaa7c998b707be2754139df89ea946f6 +size 3449219 diff --git a/data/names/fore-names.tsv.gz b/data/names/fore-names.tsv.gz new file mode 100644 index 0000000..55d6cb6 --- /dev/null +++ b/data/names/fore-names.tsv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:686477fb70847eb29c6cc6e3f79a6f3b87fe5054c7fe8564e4d3ab4e91ce7b1f +size 834056 diff --git a/data/names/full-names.tsv.gz b/data/names/full-names.tsv.gz new file mode 100644 index 0000000..c2566d5 --- /dev/null +++ b/data/names/full-names.tsv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:197fb6511d4156815162a7b1f12f424f2935d8e4407f54220fe01a131b85e862 +size 9148296 diff --git a/data/names/last-names.tsv.gz b/data/names/last-names.tsv.gz new file mode 100644 index 0000000..6bd0008 --- /dev/null +++ b/data/names/last-names.tsv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80286e437f1404eb86a52f20e55dde69f1b3ff525d001a8681b72eabbb9d9bc4 +size 1262520 diff --git a/data/pmc/affiliations.tsv.gz b/data/pmc/affiliations.tsv.gz new file mode 100644 index 0000000..032d632 --- /dev/null +++ b/data/pmc/affiliations.tsv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f3aeca38cd16b469a0927dd9ba946533e273cc80708cd91d16d431d4566d764 +size 2299932 diff --git a/data/pmc/authors.tsv.gz b/data/pmc/authors.tsv.gz new file mode 100644 index 0000000..2e57c3a --- /dev/null +++ b/data/pmc/authors.tsv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3e5550fc84f1098b9475f162831e448fa1fd0fadc593509a429f5bccf2476db +size 1210330 diff --git a/data/pubmed/affiliations.tsv.gz b/data/pubmed/affiliations.tsv.gz new file mode 100644 index 0000000..41ed002 --- /dev/null +++ b/data/pubmed/affiliations.tsv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f64e57871109df49e32b8139c719e7b3e2bcab79fbf5a19e08149398a1633d5c +size 16819377 diff --git a/data/pubmed/articles.tsv.gz b/data/pubmed/articles.tsv.gz new file mode 100644 index 0000000..9de9420 --- /dev/null +++ b/data/pubmed/articles.tsv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc872e9f64de4670b2d813b6be03aca70db02975fe43cf3c21933b4941ee41be +size 10474759 diff --git a/data/pubmed/authors.tsv.gz b/data/pubmed/authors.tsv.gz new file mode 100644 index 0000000..0901a5f --- /dev/null +++ b/data/pubmed/authors.tsv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e9bcf46ea63d14d00225063a858fdb4be62671ff2370b91e863aea5d25cef52 +size 13104389 diff --git a/data/pubmed/efetch/BMC Bioinformatics.xml.gz b/data/pubmed/efetch/BMC Bioinformatics.xml.gz new file mode 100644 index 0000000..8e28af7 --- /dev/null +++ b/data/pubmed/efetch/BMC Bioinformatics.xml.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4334ae0504202165f23c399651afac828a34b53f57b23a0b9e473f7980bd250e +size 17809079 diff --git a/data/pubmed/efetch/Bioinformatics.xml.gz b/data/pubmed/efetch/Bioinformatics.xml.gz new file mode 100644 index 0000000..d15083b --- /dev/null +++ b/data/pubmed/efetch/Bioinformatics.xml.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bb62005063a436bd64a7474771fdf19dac551dd5fcab707008d04c54dc7bdc5 +size 15670829 diff --git a/data/pubmed/efetch/PLoS Comput Biol.xml.gz b/data/pubmed/efetch/PLoS Comput Biol.xml.gz new file mode 100644 index 0000000..337ccab --- /dev/null +++ b/data/pubmed/efetch/PLoS Comput Biol.xml.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c39bbfe9319e02c110b4bcb6cf6eb4a451d18f85cdfc4d7cc60613daf85cd6e +size 15883208 diff --git a/data/pubmed/efetch/compbio-english.xml.gz b/data/pubmed/efetch/compbio-english.xml.gz new file mode 100644 index 0000000..168177a --- /dev/null +++ b/data/pubmed/efetch/compbio-english.xml.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80857be6705251cf0aaf0cf61d0090a8d91572acd2bba4cf52158e7102d390cf +size 359485614 diff --git a/data/pubmed/efetch/compbio.xml.gz b/data/pubmed/efetch/compbio.xml.gz new file mode 100644 index 0000000..0825a1a --- /dev/null +++ b/data/pubmed/efetch/compbio.xml.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c73ff77300cadfdcf2a77dca96e372f11b611b877439bd526f879bf976c10620 +size 357143274 diff --git a/data/pubmed/esummary/compbio-english.xml.gz b/data/pubmed/esummary/compbio-english.xml.gz new file mode 100644 index 0000000..2e0ecf0 --- /dev/null +++ b/data/pubmed/esummary/compbio-english.xml.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e10705a4567ee7520b648e2190a5a0d4be805da61a6037aa3013904358f3423 +size 42509942