kbaseincubator · jayrbolton · Jan 20, 2021 · Jan 20, 2021 · realmarcin · Jan 21, 2021
diff --git a/README.md b/README.md
@@ -1 +1,7 @@
-# KE_KG
+# KE_KG
+
+* Source and output data can be found in `/data`
+
+## Torben data transforms
+
+* Run sample data transform: `python data/torben_transform_samples.py`
diff --git a/Torben_samples_to_tsv.py b/Torben_samples_to_tsv.py
diff --git a/data/README.md b/data/README.md
@@ -0,0 +1,2 @@
+* `/data/source` are source files that scripts in `/transform` take as input
+* `/data/out` are transformed output files using scripts from `/transform`
diff --git a/data/out/torben/Torben_IMG-data_linked_to-GOLD_v2.biolink-edges.tsv b/data/out/torben/Torben_IMG-data_linked_to-GOLD_v2.biolink-edges.tsv
diff --git a/data/out/torben/Torben_IMG-data_linked_to-GOLD_v2.biolink-nodes.tsv b/data/out/torben/Torben_IMG-data_linked_to-GOLD_v2.biolink-nodes.tsv
diff --git a/data/source/torben/Torben_IMG-data_linked_to-GOLD_v2.tsv b/data/source/torben/Torben_IMG-data_linked_to-GOLD_v2.tsv
diff --git a/transform/IMGVR_to_tsv.py b/transform/IMGVR_to_tsv.py
@@ -135,10 +135,8 @@
 kgx_header_nodes = "id\tname\tcategory\tprovided_by\\n"
 
 
-
 def load(source_path):
     df = pd.read_csv(source_path, sep='\t')
-
     columns = df.columns.str
     print(type(columns))
     print(columns)
@@ -266,4 +264,4 @@ def write(output, outfile, header):
 node_output = tuple2[1]
 node_outfile = "IMGVR_sample_KGX_nodes.tsv"
 print("writing "+node_outfile)
-write(node_output, node_outfile, kgx_header_nodes)
+write(node_output, node_outfile, kgx_header_nodes)
diff --git a/transform/Torben_samples_to_tsv.py b/transform/Torben_samples_to_tsv.py
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1,2 @@
		* `/data/source` are source files that scripts in `/transform` take as input
Copy link Copy Markdown Collaborator realmarcin Jan 21, 2021 Choose a reason for hiding this comment The reason will be displayed to describe this comment to others. Learn more. here let's align to the KGX dir structure: ls -1 data/ raw transform merged and then subdirs for each source as in the merge.yaml https://github.com/kbaseIncubator/KE_KG/blob/main/merge.yaml
		* `/data/out` are transformed output files using scripts from `/transform`