From 5b83a8c1dd4f076220fee55ca2792d5162d67a9b Mon Sep 17 00:00:00 2001
From: Frank Sauerburger <frank@sauerburger.com>
Date: Sat, 27 Aug 2022 10:22:58 +0200
Subject: [PATCH] Move data files
---
.gitignore | 2 --
MovieLense20M.dvc | 5 -----
data/.gitignore | 6 ++++++
data/MoveLense20M.dvc | 5 +++++
MovieLenseSmall.dvc => data/MovieLenseSmall.dvc | 0
movies.py | 4 ++--
6 files changed, 13 insertions(+), 9 deletions(-)
delete mode 100644 MovieLense20M.dvc
create mode 100644 data/.gitignore
create mode 100644 data/MoveLense20M.dvc
rename MovieLenseSmall.dvc => data/MovieLenseSmall.dvc (100%)
diff --git a/.gitignore b/.gitignore
index 7bbaed8..9232e76 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,5 +1,3 @@
-/MovieLenseSmall
-/MovieLense20M
__pycache__/
.ipynb_checkpoints/
*.ipynb
diff --git a/MovieLense20M.dvc b/MovieLense20M.dvc
deleted file mode 100644
index 8978b83..0000000
--- a/MovieLense20M.dvc
+++ /dev/null
@@ -1,5 +0,0 @@
-outs:
-- md5: c6a87cfd78593a7f45605e0156cee479.dir
- size: 691847025
- nfiles: 2
- path: MovieLense20M
diff --git a/data/.gitignore b/data/.gitignore
new file mode 100644
index 0000000..5bf17d5
--- /dev/null
+++ b/data/.gitignore
@@ -0,0 +1,6 @@
+/MoveLense20M
+/MoveLense20M
+/MoveLense20M
+/MovieLenseSmall
+/MovieLenseSmall
+/MovieLenseSmall
diff --git a/data/MoveLense20M.dvc b/data/MoveLense20M.dvc
new file mode 100644
index 0000000..f047369
--- /dev/null
+++ b/data/MoveLense20M.dvc
@@ -0,0 +1,5 @@
+outs:
+- md5: 25a20e70e982dc413786f68366518a85.dir
+ size: 697892721
+ nfiles: 3
+ path: MoveLense20M
diff --git a/MovieLenseSmall.dvc b/data/MovieLenseSmall.dvc
similarity index 100%
rename from MovieLenseSmall.dvc
rename to data/MovieLenseSmall.dvc
diff --git a/movies.py b/movies.py
index 858d463..fa2218e 100644
--- a/movies.py
+++ b/movies.py
@@ -9,10 +9,10 @@ import pandas as pd
def load_movielense():
"""Load an return movies and ratings as dataframes"""
- ratings_filename = "MovieLense20M/rating.csv"
+ ratings_filename = "data/MovieLense20M/rating.csv"
ratings_df = pd.read_csv(ratings_filename)
- movies_filename = "MovieLense20M/movie.csv"
+ movies_filename = "data/MovieLense20M/movie.csv"
movies_df = pd.read_csv(movies_filename)
return ratings_df, movies_df
--
GitLab