feat: repro unzip data stage in pipeline #10

jsappl · May 17, 2024 · bcd45f2 · bcd45f2
1 parent 51dbfb1
commit bcd45f2
Show file tree

Hide file tree

Showing 2 changed files with 22 additions and 0 deletions.
diff --git a/assets/data/raw/.gitignore b/assets/data/raw/.gitignore
@@ -1 +1,3 @@
 /archive.zip
+/stand_small_train
+/stand_small_test
diff --git a/dvc.lock b/dvc.lock
@@ -0,0 +1,20 @@
+schema: '2.0'
+stages:
+  extract:
+    cmd: unzip ./assets/data/raw/archive.zip -d ./assets/data/raw/
+    deps:
+    - path: ./assets/data/raw/archive.zip
+      hash: md5
+      md5: 5fec93197ff1c389e18f9acf02e1d00e
+      size: 9069236425
+    outs:
+    - path: ./assets/data/raw/stand_small_test/
+      hash: md5
+      md5: 2d661d03282605379d6f3e2ca0acbf58.dir
+      size: 93093259
+      nfiles: 1000
+    - path: ./assets/data/raw/stand_small_train/
+      hash: md5
+      md5: d1cb9475cd45a296650d969d5f3165ed.dir
+      size: 9352344396
+      nfiles: 100000