{ "cells": [ { "cell_type": "code", "execution_count": null, "metadata": { "id": "K6Ek26jtEbzM" }, "outputs": [], "source": [ "import pandas as pd" ] }, { "cell_type": "code", "execution_count": 2, "metadata": { "id": "jSok_FhgFQPa" }, "outputs": [], "source": [ "df = pd.read_csv('data/data.csv')" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Index(['valence', 'year', 'acousticness', 'artists', 'danceability',\n", " 'duration_ms', 'energy', 'explicit', 'id', 'instrumentalness', 'key',\n", " 'liveness', 'loudness', 'mode', 'name', 'popularity', 'release_date',\n", " 'speechiness', 'tempo'],\n", " dtype='object')" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.columns" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [], "source": [ "selected_columns = ['valence', 'year', 'acousticness', 'artists', 'danceability',\n", " 'duration_ms', 'energy','id', 'instrumentalness', 'key',\n", " 'liveness', 'loudness', 'mode', 'name', 'popularity',\n", " 'speechiness', 'tempo']\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "df.to_csv('data/data_clean.csv', columns=selected_columns, index=False)" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
valenceyearacousticnessartistsdanceabilityduration_msenergyexplicitidinstrumentalnesskeylivenessloudnessmodenamepopularityrelease_datespeechinesstempo
00.059419210.982['Sergei Rachmaninoff', 'James Levine', 'Berli...0.2798316670.21104BJqT0PrAfrxzMOxytFOIz0.878000100.665-20.0961Piano Concerto No. 3 in D Minor, Op. 30: III. ...419210.036680.954
10.963019210.732['Dennis Day']0.8191805330.34107xPhfUan2yNtyFG0cUWkt80.00000070.160-12.4411Clancy Lowered the Boom519210.415060.936
20.039419210.961['KHP Kridhamardawa Karaton Ngayogyakarta Hadi...0.3285000620.16601o6I8BglA6ylDMrIELygv10.91300030.101-14.8501Gati Bali519210.0339110.339
30.165019210.967['Frank Parker']0.2752100000.30903ftBPsC5vPBKxYSee08FDH0.00002850.381-9.3161Danny Boy319210.0354100.109
40.253019210.957['Phil Regan']0.4181666930.19304d6HGyGT8e121BsdKmw9v60.00000230.229-10.0961When Irish Eyes Are Smiling219210.0380101.665
\n", "
" ], "text/plain": [ " valence year acousticness \\\n", "0 0.0594 1921 0.982 \n", "1 0.9630 1921 0.732 \n", "2 0.0394 1921 0.961 \n", "3 0.1650 1921 0.967 \n", "4 0.2530 1921 0.957 \n", "\n", " artists danceability \\\n", "0 ['Sergei Rachmaninoff', 'James Levine', 'Berli... 0.279 \n", "1 ['Dennis Day'] 0.819 \n", "2 ['KHP Kridhamardawa Karaton Ngayogyakarta Hadi... 0.328 \n", "3 ['Frank Parker'] 0.275 \n", "4 ['Phil Regan'] 0.418 \n", "\n", " duration_ms energy explicit id instrumentalness \\\n", "0 831667 0.211 0 4BJqT0PrAfrxzMOxytFOIz 0.878000 \n", "1 180533 0.341 0 7xPhfUan2yNtyFG0cUWkt8 0.000000 \n", "2 500062 0.166 0 1o6I8BglA6ylDMrIELygv1 0.913000 \n", "3 210000 0.309 0 3ftBPsC5vPBKxYSee08FDH 0.000028 \n", "4 166693 0.193 0 4d6HGyGT8e121BsdKmw9v6 0.000002 \n", "\n", " key liveness loudness mode \\\n", "0 10 0.665 -20.096 1 \n", "1 7 0.160 -12.441 1 \n", "2 3 0.101 -14.850 1 \n", "3 5 0.381 -9.316 1 \n", "4 3 0.229 -10.096 1 \n", "\n", " name popularity release_date \\\n", "0 Piano Concerto No. 3 in D Minor, Op. 30: III. ... 4 1921 \n", "1 Clancy Lowered the Boom 5 1921 \n", "2 Gati Bali 5 1921 \n", "3 Danny Boy 3 1921 \n", "4 When Irish Eyes Are Smiling 2 1921 \n", "\n", " speechiness tempo \n", "0 0.0366 80.954 \n", "1 0.4150 60.936 \n", "2 0.0339 110.339 \n", "3 0.0354 100.109 \n", "4 0.0380 101.665 " ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.head()" ] } ], "metadata": { "colab": { "provenance": [] }, "kernelspec": { "display_name": "Python 3", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.12.4" } }, "nbformat": 4, "nbformat_minor": 0 }