feat: add dvc sample and sentiment analysis data (#2)

* feat: init dvc * feat: add data sample * feat: add sentiment-analysis data * feat: add output folder
leomaurodesenv · Nov 2, 2023 · 382de19 · 382de19
1 parent c34dd24
commit 382de19
Show file tree

Hide file tree

Showing 9 changed files with 27 additions and 0 deletions.
diff --git a/.dvc/.gitignore b/.dvc/.gitignore
@@ -0,0 +1,3 @@
+/config.local
+/tmp
+/cache
diff --git a/.dvc/config b/.dvc/config
@@ -0,0 +1,4 @@
+[core]
+    remote = myremote
+['remote "myremote"']
+    url = /tmp/dvcstore
diff --git a/.dvcignore b/.dvcignore
@@ -0,0 +1,3 @@
+# Add patterns of files dvc should ignore, which could improve
+# the performance. Learn more at
+# https://dvc.org/doc/user-guide/dvcignore
diff --git a/README.md b/README.md
@@ -1,2 +1,5 @@
 # dvc-luigi
 This is a learning repository about DVC Data Version Control and Luigi Pipelines
+
+- setup https://github.com/Kaggle/kaggle-api
+- `kaggle competitions download -c sentiment-analysis-on-movie-reviews -p data`
diff --git a/data/.gitignore b/data/.gitignore
@@ -0,0 +1,2 @@
+/data.xml
+/sentiment-analysis-on-movie-reviews.zip
diff --git a/data/data.xml.dvc b/data/data.xml.dvc
@@ -0,0 +1,5 @@
+outs:
+- md5: 22a1a2931c8370d3aeedd7183606fd7f
+  size: 14445097
+  hash: md5
+  path: data.xml
diff --git a/data/output/.gitkeep b/data/output/.gitkeep
diff --git a/data/sentiment-analysis-on-movie-reviews.zip.dvc b/data/sentiment-analysis-on-movie-reviews.zip.dvc
@@ -0,0 +1,5 @@
+outs:
+- md5: 297ae2983c4a07603ed2fd31613c1b5e
+  size: 1991138
+  hash: md5
+  path: sentiment-analysis-on-movie-reviews.zip
diff --git a/requirements.txt b/requirements.txt
@@ -0,0 +1,2 @@
+kaggle==1.5.16
+dvc==3.28.0
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1,2 @@
		/data.xml
		/sentiment-analysis-on-movie-reviews.zip