From 692cdef78db93c0c029075304409a9310a6f0245 Mon Sep 17 00:00:00 2001
From: eugene <eugene.polyakow@gmail.com>
Date: Fri, 29 Sep 2023 18:06:12 +0200
Subject: [PATCH] add dvc.yaml with defined pipeline

---
 .gitignore | 16 ++--------------
 dvc.lock   | 28 ++++++++++++++++++++++++++++
 2 files changed, 30 insertions(+), 14 deletions(-)
 create mode 100644 dvc.lock

diff --git a/.gitignore b/.gitignore
index ac1c488..f53e30b 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,14 +1,2 @@
-# ---> VisualStudioCode
-.vscode/*
-!.vscode/settings.json
-!.vscode/tasks.json
-!.vscode/launch.json
-!.vscode/extensions.json
-!.vscode/*.code-snippets
-
-# Local History for Visual Studio Code
-.history/
-
-# Built Visual Studio Code Extensions
-*.vsix
-
+venv
+/model.pth
diff --git a/dvc.lock b/dvc.lock
new file mode 100644
index 0000000..6147a43
--- /dev/null
+++ b/dvc.lock
@@ -0,0 +1,28 @@
+schema: '2.0'
+stages:
+  preprocess:
+    cmd: python better_preprocess.py
+    deps:
+    - path: 25k_IMDb_movie_Dataset.csv
+      hash: md5
+      md5: 07989327c5c9a7d7a8d17e80e3e56fdf
+      size: 12515047
+    outs:
+    - path: data.csv
+      hash: md5
+      md5: 0ae3ee0112169b038031c83f8e6e39c3
+      size: 11917252
+      isexec: true
+  train:
+    cmd: python script5_3.py
+    deps:
+    - path: data.csv
+      hash: md5
+      md5: 0ae3ee0112169b038031c83f8e6e39c3
+      size: 11917252
+    outs:
+    - path: model.pth
+      hash: md5
+      md5: 2fda66181bcd728ff2847031481abe37
+      size: 2195
+      isexec: true