From 1a88f19e372d0038d38e486b6a27fd692c3ee994 Mon Sep 17 00:00:00 2001 From: SuryanarayanaY <116063290+SuryanarayanaY@users.noreply.github.com> Date: Tue, 20 Jun 2023 15:16:39 +0530 Subject: [PATCH 1/7] Update encoding in movielens_recommendations_transformers.py At present the example tutorial raising the UnicodeDecodeError at the code movies=pd.read_csv() UnicodeDecodeError: 'utf-8' codec can't decode byte 0xe9 in position 3114: invalid continuation byte Hence adding the encoding='latin-1' to the movies=pd.read_csv(...,encoding='latin-1') will get rid of this error. Hence I proposed this code change for review and approval. --- .../structured_data/movielens_recommendations_transformers.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/examples/structured_data/movielens_recommendations_transformers.py b/examples/structured_data/movielens_recommendations_transformers.py index bf979d0b31..832cff7b02 100644 --- a/examples/structured_data/movielens_recommendations_transformers.py +++ b/examples/structured_data/movielens_recommendations_transformers.py @@ -92,7 +92,7 @@ ) movies = pd.read_csv( - "ml-1m/movies.dat", sep="::", names=["movie_id", "title", "genres"] + "ml-1m/movies.dat", sep="::", names=["movie_id", "title", "genres"],encoding='latin-1' ) """ From 4de56ef3c4a827c625d523425e780b224f90b53e Mon Sep 17 00:00:00 2001 From: SuryanarayanaY <116063290+SuryanarayanaY@users.noreply.github.com> Date: Fri, 23 Jun 2023 14:37:53 +0530 Subject: [PATCH 2/7] Update movielens_recommendations_transformers.py Done the suggested changes --- .../structured_data/movielens_recommendations_transformers.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/examples/structured_data/movielens_recommendations_transformers.py b/examples/structured_data/movielens_recommendations_transformers.py index 832cff7b02..ee0f39e65b 100644 --- a/examples/structured_data/movielens_recommendations_transformers.py +++ b/examples/structured_data/movielens_recommendations_transformers.py @@ -92,7 +92,8 @@ ) movies = pd.read_csv( - "ml-1m/movies.dat", sep="::", names=["movie_id", "title", "genres"],encoding='latin-1' + "ml-1m/movies.dat", sep="::", names=["movie_id", "title", "genres"], + encoding='latin-1' ) """ From 98f62fdecf5d7f901aab146c36ef1b6f54d5678d Mon Sep 17 00:00:00 2001 From: SuryanarayanaY <116063290+SuryanarayanaY@users.noreply.github.com> Date: Fri, 23 Jun 2023 14:52:39 +0530 Subject: [PATCH 3/7] Update movielens_recommendations_transformers.ipynb Updated encoding in .ipynb file also as requested --- .../ipynb/movielens_recommendations_transformers.ipynb | 1 + 1 file changed, 1 insertion(+) diff --git a/examples/structured_data/ipynb/movielens_recommendations_transformers.ipynb b/examples/structured_data/ipynb/movielens_recommendations_transformers.ipynb index 49d90e85fa..bc0cd235b8 100644 --- a/examples/structured_data/ipynb/movielens_recommendations_transformers.ipynb +++ b/examples/structured_data/ipynb/movielens_recommendations_transformers.ipynb @@ -151,6 +151,7 @@ "\n", "movies = pd.read_csv(\n", " \"ml-1m/movies.dat\", sep=\"::\", names=[\"movie_id\", \"title\", \"genres\"]\n", + " encoding='latin-1'\n", ")" ] }, From ded1da5cc93b7757bdc1372bfd9510bc6bd4f1d3 Mon Sep 17 00:00:00 2001 From: SuryanarayanaY <116063290+SuryanarayanaY@users.noreply.github.com> Date: Fri, 23 Jun 2023 14:57:12 +0530 Subject: [PATCH 4/7] Update movielens_recommendations_transformers.md Updated encoding in .md file as requested. --- .../md/movielens_recommendations_transformers.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/examples/structured_data/md/movielens_recommendations_transformers.md b/examples/structured_data/md/movielens_recommendations_transformers.md index 138e4b7c2a..ead5662b0b 100644 --- a/examples/structured_data/md/movielens_recommendations_transformers.md +++ b/examples/structured_data/md/movielens_recommendations_transformers.md @@ -97,7 +97,8 @@ ratings = pd.read_csv( ) movies = pd.read_csv( - "ml-1m/movies.dat", sep="::", names=["movie_id", "title", "genres"] + "ml-1m/movies.dat", sep="::", names=["movie_id", "title", "genres"], + encoding='latin-1' ) ``` From f4b9e9ee49f2b6a923d5b74dadb23f99572b7697 Mon Sep 17 00:00:00 2001 From: SuryanarayanaY <116063290+SuryanarayanaY@users.noreply.github.com> Date: Wed, 12 Jul 2023 22:07:10 +0530 Subject: [PATCH 5/7] Update movielens_recommendations_transformers.py Done the changes as suggested for black format --- .../structured_data/movielens_recommendations_transformers.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/examples/structured_data/movielens_recommendations_transformers.py b/examples/structured_data/movielens_recommendations_transformers.py index ee0f39e65b..8180d092d9 100644 --- a/examples/structured_data/movielens_recommendations_transformers.py +++ b/examples/structured_data/movielens_recommendations_transformers.py @@ -92,7 +92,9 @@ ) movies = pd.read_csv( - "ml-1m/movies.dat", sep="::", names=["movie_id", "title", "genres"], + "ml-1m/movies.dat", + sep="::", + names=["movie_id", "title", "genres"], encoding='latin-1' ) From c6ba9ed40320ad16e2040549712d66f0064a6b6a Mon Sep 17 00:00:00 2001 From: SuryanarayanaY <116063290+SuryanarayanaY@users.noreply.github.com> Date: Thu, 20 Jul 2023 18:48:04 +0530 Subject: [PATCH 6/7] remove lint errors movielens_recommendations_transformers.py Corrected lint errors --- .../structured_data/movielens_recommendations_transformers.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/examples/structured_data/movielens_recommendations_transformers.py b/examples/structured_data/movielens_recommendations_transformers.py index 8180d092d9..df83438b50 100644 --- a/examples/structured_data/movielens_recommendations_transformers.py +++ b/examples/structured_data/movielens_recommendations_transformers.py @@ -95,7 +95,7 @@ "ml-1m/movies.dat", sep="::", names=["movie_id", "title", "genres"], - encoding='latin-1' + encoding="latin-1" ) """ From 6490e9bfc4fa735f6528ef784be6c5de1adcaff4 Mon Sep 17 00:00:00 2001 From: SuryanarayanaY <116063290+SuryanarayanaY@users.noreply.github.com> Date: Thu, 27 Jul 2023 10:36:31 +0530 Subject: [PATCH 7/7] Update movielens_recommendations_transformers.py Removed white spaces and done required changes for black format. --- .../movielens_recommendations_transformers.py | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/examples/structured_data/movielens_recommendations_transformers.py b/examples/structured_data/movielens_recommendations_transformers.py index df83438b50..8c5722934a 100644 --- a/examples/structured_data/movielens_recommendations_transformers.py +++ b/examples/structured_data/movielens_recommendations_transformers.py @@ -92,10 +92,10 @@ ) movies = pd.read_csv( - "ml-1m/movies.dat", - sep="::", + "ml-1m/movies.dat", + sep="::", names=["movie_id", "title", "genres"], - encoding="latin-1" + encoding="latin-1", ) """