From 382de19f3df7bd1a9e856388dcafdfbc3623ffdc Mon Sep 17 00:00:00 2001
From: Leonardo Mauro <leo.mauro.desenv@gmail.com>
Date: Thu, 2 Nov 2023 17:54:40 -0300
Subject: [PATCH] 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
---
 .dvc/.gitignore                                  | 3 +++
 .dvc/config                                      | 4 ++++
 .dvcignore                                       | 3 +++
 README.md                                        | 3 +++
 data/.gitignore                                  | 2 ++
 data/data.xml.dvc                                | 5 +++++
 data/output/.gitkeep                             | 0
 data/sentiment-analysis-on-movie-reviews.zip.dvc | 5 +++++
 requirements.txt                                 | 2 ++
 9 files changed, 27 insertions(+)
 create mode 100644 .dvc/.gitignore
 create mode 100644 .dvc/config
 create mode 100644 .dvcignore
 create mode 100644 data/.gitignore
 create mode 100644 data/data.xml.dvc
 create mode 100644 data/output/.gitkeep
 create mode 100644 data/sentiment-analysis-on-movie-reviews.zip.dvc
 create mode 100644 requirements.txt

diff --git a/.dvc/.gitignore b/.dvc/.gitignore
new file mode 100644
index 0000000..528f30c
--- /dev/null
+++ b/.dvc/.gitignore
@@ -0,0 +1,3 @@
+/config.local
+/tmp
+/cache
diff --git a/.dvc/config b/.dvc/config
new file mode 100644
index 0000000..5e0e5be
--- /dev/null
+++ b/.dvc/config
@@ -0,0 +1,4 @@
+[core]
+    remote = myremote
+['remote "myremote"']
+    url = /tmp/dvcstore
diff --git a/.dvcignore b/.dvcignore
new file mode 100644
index 0000000..5197305
--- /dev/null
+++ 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
index 5d2e4b0..4696a10 100644
--- 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`
\ No newline at end of file
diff --git a/data/.gitignore b/data/.gitignore
new file mode 100644
index 0000000..d8ee7f0
--- /dev/null
+++ 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
new file mode 100644
index 0000000..1fd0f22
--- /dev/null
+++ 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
new file mode 100644
index 0000000..e69de29
diff --git a/data/sentiment-analysis-on-movie-reviews.zip.dvc b/data/sentiment-analysis-on-movie-reviews.zip.dvc
new file mode 100644
index 0000000..6a14689
--- /dev/null
+++ 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
new file mode 100644
index 0000000..7216041
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1,2 @@
+kaggle==1.5.16
+dvc==3.28.0