feat: add DVC (zad1, zad2, zad3)

.dvc/.gitignore

@@ -0,0 +1,3 @@
+/config.local
+/tmp
+/cache

.dvc/config

@@ -0,0 +1,4 @@
+[core]
+    remote = ium_ssh_remote
+['remote "ium_ssh_remote"']
+    url = ssh://ium-sftp@tzietkiewicz.vm.wmi.amu.edu.pl

.dvcignore

@@ -0,0 +1,7 @@
+# Add patterns of files dvc should ignore, which could improve
+# the performance. Learn more at
+# https://dvc.org/doc/user-guide/dvcignore
+.vscode
+__pycache__
+sacred/
+mlruns/

.gitignore

@@ -1,5 +1,7 @@
 .vscode
 __pycache__
-data/
+data/*.csv
+data/*/*.csv
 results/
-sacred/
+sacred/
+mlruns/

data/dataset/test.csv.dvc

@@ -0,0 +1,4 @@
+outs:
+- md5: 9dd26ae5484ab058be21ae695098b9c6
+  size: 10985891
+  path: test.csv

data/dataset/train.csv.dvc

@@ -0,0 +1,4 @@
+outs:
+- md5: b4c5dfbc36c057a27137766197adbeca
+  size: 89199212
+  path: train.csv

data/dataset/val.csv.dvc

@@ -0,0 +1,4 @@
+outs:
+- md5: 64b7d344d7d4d7117b2cf9d7e31be771
+  size: 11229062
+  path: val.csv

environment.yml

@@ -16,5 +16,8 @@ dependencies:
   - transformers
   - matplotlib
   - pymongo
+  - dvc
+  - dvc-ssh 
+  - pip
   - pip:
       - sacred==0.8.4