Feat: huggingface raw dataset with readme and instruct readme (#26)

* feat: add push raw dataset script

* feat: add push instruct dataset script

* refactor: dvc commit raw_dataset_readme

* feat: extend scripts readme

data/datasets/pl/readme/.gitignore

@@ -0,0 +1,2 @@
+/raw
+/instruct

dvc.lock

@@ -425,3 +425,36 @@ stages:
       hash: md5
       md5: 68b09dd0ce741e6ee1fff4e37c954fa6
       size: 564
+  raw_dataset_readme:
+    cmd: jupyter nbconvert  --no-input  --to markdown  --execute nbs/Data/02_Dataset_Description_Raw.ipynb
+      --output-dir data/datasets/pl/readme/raw --output README
+    deps:
+    - path: data/datasets/pl/raw
+      hash: md5
+      md5: 5dd44be2eea852bcce3d0918ff8b97da.dir
+      size: 10234880729
+      nfiles: 17
+    - path: nbs/Data/02_Dataset_Description_Raw.ipynb
+      hash: md5
+      md5: d3d7509d084b85676857e13a2f20b82a
+      size: 73872
+    outs:
+    - path: data/datasets/pl/readme/raw/
+      hash: md5
+      md5: f1d267b2829519729d5615b4a128e03b.dir
+      size: 473589
+      nfiles: 8
+  instruct_dataset_readme:
+    cmd: jupyter nbconvert  --no-input  --to markdown  --execute nbs/Data/03_Dataset_Description_Instruct.ipynb
+      --output-dir data/datasets/pl/readme/instruct --output README
+    deps:
+    - path: nbs/Data/03_Dataset_Description_Instruct.ipynb
+      hash: md5
+      md5: 27e6d517445028d45e5c40b22febece4
+      size: 16215
+    outs:
+    - path: data/datasets/pl/readme/instruct/
+      hash: md5
+      md5: de02794df3d74d86f8610f040a17dcbe.dir
+      size: 144326
+      nfiles: 5

dvc.yaml

@@ -1,4 +1,30 @@
 stages:
+  raw_dataset_readme:
+    cmd: >-
+      jupyter nbconvert 
+      --no-input 
+      --to markdown 
+      --execute nbs/Data/02_Dataset_Description_Raw.ipynb
+      --output-dir data/datasets/pl/readme/raw
+      --output README
+    deps:
+      - nbs/Data/02_Dataset_Description_Raw.ipynb
+      - data/datasets/pl/raw
+    outs:
+      - data/datasets/pl/readme/raw/
+
+  instruct_dataset_readme:
+    cmd: >-
+      jupyter nbconvert 
+      --no-input 
+      --to markdown 
+      --execute nbs/Data/03_Dataset_Description_Instruct.ipynb
+      --output-dir data/datasets/pl/readme/instruct
+      --output README
+    deps:
+      - nbs/Data/03_Dataset_Description_Instruct.ipynb
+    outs:
+      - data/datasets/pl/readme/instruct/
   build_instruct_dataset:
     cmd: >-
       PYTHONPATH=. python scripts/dataset/build_instruct_dataset.py