From 515065a8ec56ac13ed297b83e7061527ce13c0b6 Mon Sep 17 00:00:00 2001 From: Simon Malm <alf.simon.malm@gmail.com> Date: Thu, 21 Dec 2023 21:06:00 +0100 Subject: [PATCH] refactor --- .../data/final_processed_dataset.csv | Bin .../datapackage.json | 0 .../original/Final processed dataset.xlsx | Bin notebook.ipynb | 4 ++-- 4 files changed, 2 insertions(+), 2 deletions(-) rename billboard_top100_lyrics/{tazwar2700-billboard-hot-100-with-lyrics-and-emotion-mined-scores => }/data/final_processed_dataset.csv (100%) rename billboard_top100_lyrics/{tazwar2700-billboard-hot-100-with-lyrics-and-emotion-mined-scores => }/datapackage.json (100%) rename billboard_top100_lyrics/{tazwar2700-billboard-hot-100-with-lyrics-and-emotion-mined-scores => }/original/Final processed dataset.xlsx (100%) diff --git a/billboard_top100_lyrics/tazwar2700-billboard-hot-100-with-lyrics-and-emotion-mined-scores/data/final_processed_dataset.csv b/billboard_top100_lyrics/data/final_processed_dataset.csv similarity index 100% rename from billboard_top100_lyrics/tazwar2700-billboard-hot-100-with-lyrics-and-emotion-mined-scores/data/final_processed_dataset.csv rename to billboard_top100_lyrics/data/final_processed_dataset.csv diff --git a/billboard_top100_lyrics/tazwar2700-billboard-hot-100-with-lyrics-and-emotion-mined-scores/datapackage.json b/billboard_top100_lyrics/datapackage.json similarity index 100% rename from billboard_top100_lyrics/tazwar2700-billboard-hot-100-with-lyrics-and-emotion-mined-scores/datapackage.json rename to billboard_top100_lyrics/datapackage.json diff --git a/billboard_top100_lyrics/tazwar2700-billboard-hot-100-with-lyrics-and-emotion-mined-scores/original/Final processed dataset.xlsx b/billboard_top100_lyrics/original/Final processed dataset.xlsx similarity index 100% rename from billboard_top100_lyrics/tazwar2700-billboard-hot-100-with-lyrics-and-emotion-mined-scores/original/Final processed dataset.xlsx rename to billboard_top100_lyrics/original/Final processed dataset.xlsx diff --git a/notebook.ipynb b/notebook.ipynb index e4df85e..fba47fd 100644 --- a/notebook.ipynb +++ b/notebook.ipynb @@ -23,7 +23,7 @@ "source": [ "import pandas as pd\n", "\n", - "songs = pd.read_csv(\"billboard_top100_lyrics/tazwar2700-billboard-hot-100-with-lyrics-and-emotion-mined-scores/data/final_processed_dataset.csv\", encoding = \"ISO-8859-1\")" + "songs = pd.read_csv(\"billboard_top100_lyrics/data/final_processed_dataset.csv\", encoding = \"ISO-8859-1\")" ] }, { @@ -436,7 +436,7 @@ "# Create tokenized lyrics for all songs.\n", "# Save data to json-file if first time, load data otherwise for efficiency. \n", "for year, songlist in zip(years, all_songs):\n", - " filename = f\"tokenized_songs_{year}.json\"\n", + " filename = f\"tokenized/tokenized_songs_{year}.json\"\n", " if not os.path.exists(filename):\n", " print(f\"Tokenizing songs from {year}s...\")\n", " tokenized = tokenize_lyrics(songlist.lyrics.tolist())\n", -- GitLab