{ "cells": [ { "cell_type": "markdown", "metadata": { "cell_id": "00dd38b5-5d55-49b4-86a5-f094fd84fded", "deepnote_cell_type": "markdown", "tags": [] }, "source": [ "# Spotify dataset\n", "\n", "[Recording of lecture from 1/24/2022](https://uci.zoom.us/rec/share/JBsBgWKEEa9fweZFzQH2J8SiWKWcVSDiMQx0dOt56nxRQ0b8dpW-Nj6-Hrp_ijkQ._1bDpwn5N2eTJ4u-?startTime=1643039871000)\n", "\n", "The csv file attached to this project was originally taken from this [Kaggle dataset](https://www.kaggle.com/sashankpillai/spotify-top-200-charts-20202021/version/1).\n", "\n", "To start out we want to plot Energy vs Loudness using Altair.\n", "\n", "To change the default colors, we can select a different [color scheme](https://vega.github.io/vega/docs/schemes/)." ] }, { "cell_type": "code", "execution_count": 1, "metadata": { "cell_id": "09575021-3c29-4a89-97c6-8b95dd69d753", "deepnote_cell_type": "code", "deepnote_to_be_reexecuted": false, "execution_millis": 444, "execution_start": 1643039982296, "source_hash": "46e6bd77", "tags": [] }, "outputs": [], "source": [ "import pandas as pd\n", "import altair as alt" ] }, { "cell_type": "code", "execution_count": 2, "metadata": { "cell_id": "45fec56c-60e9-46af-bbfe-879d8823d22b", "deepnote_cell_type": "code", "deepnote_output_heights": [ 21.1875 ], "deepnote_to_be_reexecuted": false, "execution_millis": 3329, "execution_start": 1643040318436, "source_hash": "3f39c031", "tags": [] }, "outputs": [], "source": [ "df = pd.read_csv(\"../data/spotify_dataset.csv\")" ] }, { "cell_type": "code", "execution_count": 3, "metadata": { "cell_id": "c18ddc29-ba52-4dc4-b859-e7a46e74f3e8", "deepnote_cell_type": "code", "deepnote_output_heights": [ 212 ], "deepnote_to_be_reexecuted": false, "execution_millis": 25, "execution_start": 1643040323719, "source_hash": "c085b6ba", "tags": [] }, "outputs": [ { "data": { "text/html": [ "
\n", " | Index | \n", "Highest Charting Position | \n", "Number of Times Charted | \n", "Week of Highest Charting | \n", "Song Name | \n", "Streams | \n", "Artist | \n", "Artist Followers | \n", "Song ID | \n", "Genre | \n", "... | \n", "Danceability | \n", "Energy | \n", "Loudness | \n", "Speechiness | \n", "Acousticness | \n", "Liveness | \n", "Tempo | \n", "Duration (ms) | \n", "Valence | \n", "Chord | \n", "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", "1 | \n", "1 | \n", "8 | \n", "2021-07-23--2021-07-30 | \n", "Beggin' | \n", "48,633,449 | \n", "Måneskin | \n", "3377762 | \n", "3Wrjm47oTz2sjIgck11l5e | \n", "['indie rock italiano', 'italian pop'] | \n", "... | \n", "0.714 | \n", "0.8 | \n", "-4.808 | \n", "0.0504 | \n", "0.127 | \n", "0.359 | \n", "134.002 | \n", "211560 | \n", "0.589 | \n", "B | \n", "
1 | \n", "2 | \n", "2 | \n", "3 | \n", "2021-07-23--2021-07-30 | \n", "STAY (with Justin Bieber) | \n", "47,248,719 | \n", "The Kid LAROI | \n", "2230022 | \n", "5HCyWlXZPP0y6Gqq8TgA20 | \n", "['australian hip hop'] | \n", "... | \n", "0.591 | \n", "0.764 | \n", "-5.484 | \n", "0.0483 | \n", "0.0383 | \n", "0.103 | \n", "169.928 | \n", "141806 | \n", "0.478 | \n", "C#/Db | \n", "
2 | \n", "3 | \n", "1 | \n", "11 | \n", "2021-06-25--2021-07-02 | \n", "good 4 u | \n", "40,162,559 | \n", "Olivia Rodrigo | \n", "6266514 | \n", "4ZtFanR9U6ndgddUvNcjcG | \n", "['pop'] | \n", "... | \n", "0.563 | \n", "0.664 | \n", "-5.044 | \n", "0.154 | \n", "0.335 | \n", "0.0849 | \n", "166.928 | \n", "178147 | \n", "0.688 | \n", "A | \n", "
3 | \n", "4 | \n", "3 | \n", "5 | \n", "2021-07-02--2021-07-09 | \n", "Bad Habits | \n", "37,799,456 | \n", "Ed Sheeran | \n", "83293380 | \n", "6PQ88X9TkUIAUIZJHW2upE | \n", "['pop', 'uk pop'] | \n", "... | \n", "0.808 | \n", "0.897 | \n", "-3.712 | \n", "0.0348 | \n", "0.0469 | \n", "0.364 | \n", "126.026 | \n", "231041 | \n", "0.591 | \n", "B | \n", "
4 | \n", "5 | \n", "5 | \n", "1 | \n", "2021-07-23--2021-07-30 | \n", "INDUSTRY BABY (feat. Jack Harlow) | \n", "33,948,454 | \n", "Lil Nas X | \n", "5473565 | \n", "27NovPIUIRrOZoCHxABJwK | \n", "['lgbtq+ hip hop', 'pop rap'] | \n", "... | \n", "0.736 | \n", "0.704 | \n", "-7.409 | \n", "0.0615 | \n", "0.0203 | \n", "0.0501 | \n", "149.995 | \n", "212000 | \n", "0.894 | \n", "D#/Eb | \n", "
5 rows × 23 columns
\n", "\n", " | Index | \n", "Highest Charting Position | \n", "Number of Times Charted | \n", "Week of Highest Charting | \n", "Song Name | \n", "Streams | \n", "Artist | \n", "Artist Followers | \n", "Song ID | \n", "Genre | \n", "... | \n", "Danceability | \n", "Energy | \n", "Loudness | \n", "Speechiness | \n", "Acousticness | \n", "Liveness | \n", "Tempo | \n", "Duration (ms) | \n", "Valence | \n", "Chord | \n", "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", "1 | \n", "1 | \n", "8 | \n", "2021-07-23--2021-07-30 | \n", "Beggin' | \n", "48,633,449 | \n", "Måneskin | \n", "3377762 | \n", "3Wrjm47oTz2sjIgck11l5e | \n", "['indie rock italiano', 'italian pop'] | \n", "... | \n", "0.714 | \n", "0.8 | \n", "-4.808 | \n", "0.0504 | \n", "0.127 | \n", "0.359 | \n", "134.002 | \n", "211560 | \n", "0.589 | \n", "B | \n", "
1 | \n", "2 | \n", "2 | \n", "3 | \n", "2021-07-23--2021-07-30 | \n", "STAY (with Justin Bieber) | \n", "47,248,719 | \n", "The Kid LAROI | \n", "2230022 | \n", "5HCyWlXZPP0y6Gqq8TgA20 | \n", "['australian hip hop'] | \n", "... | \n", "0.591 | \n", "0.764 | \n", "-5.484 | \n", "0.0483 | \n", "0.0383 | \n", "0.103 | \n", "169.928 | \n", "141806 | \n", "0.478 | \n", "C#/Db | \n", "
2 | \n", "3 | \n", "1 | \n", "11 | \n", "2021-06-25--2021-07-02 | \n", "good 4 u | \n", "40,162,559 | \n", "Olivia Rodrigo | \n", "6266514 | \n", "4ZtFanR9U6ndgddUvNcjcG | \n", "['pop'] | \n", "... | \n", "0.563 | \n", "0.664 | \n", "-5.044 | \n", "0.154 | \n", "0.335 | \n", "0.0849 | \n", "166.928 | \n", "178147 | \n", "0.688 | \n", "A | \n", "
3 rows × 23 columns
\n", "\n", " | Index | \n", "Highest Charting Position | \n", "Number of Times Charted | \n", "Week of Highest Charting | \n", "Song Name | \n", "Streams | \n", "Artist | \n", "Artist Followers | \n", "Song ID | \n", "Genre | \n", "... | \n", "Danceability | \n", "Energy | \n", "Loudness | \n", "Speechiness | \n", "Acousticness | \n", "Liveness | \n", "Tempo | \n", "Duration (ms) | \n", "Valence | \n", "Chord | \n", "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
35 | \n", "36 | \n", "36 | \n", "1 | \n", "2021-07-23--2021-07-30 | \n", "NOT SOBER (feat. Polo G & Stunna Gambino) | \n", "11,869,336 | \n", "The Kid LAROI | \n", "\n", " | \n", " | \n", " | ... | \n", "\n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " |
163 | \n", "164 | \n", "5 | \n", "39 | \n", "2020-10-30--2020-11-06 | \n", "34+35 | \n", "5,453,159 | \n", "Ariana Grande | \n", "\n", " | \n", " | \n", " | ... | \n", "\n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " |
464 | \n", "465 | \n", "118 | \n", "1 | \n", "2021-03-26--2021-04-02 | \n", "Richer (feat. Polo G) | \n", "6,292,362 | \n", "Rod Wave | \n", "\n", " | \n", " | \n", " | ... | \n", "\n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " |
530 | \n", "531 | \n", "20 | \n", "5 | \n", "2021-01-15--2021-01-22 | \n", "34+35 Remix (feat. Doja Cat, Megan Thee Stalli... | \n", "6,162,453 | \n", "Ariana Grande | \n", "\n", " | \n", " | \n", " | ... | \n", "\n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " |
636 | \n", "637 | \n", "22 | \n", "6 | \n", "2020-12-18--2020-12-25 | \n", "Driving Home for Christmas - 2019 Remaster | \n", "8,804,531 | \n", "Chris Rea | \n", "\n", " | \n", " | \n", " | ... | \n", "\n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " |
654 | \n", "655 | \n", "73 | \n", "1 | \n", "2020-12-18--2020-12-25 | \n", "Thank God It's Christmas - Non-Album Single | \n", "10,509,961 | \n", "Queen | \n", "\n", " | \n", " | \n", " | ... | \n", "\n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " |
750 | \n", "751 | \n", "19 | \n", "20 | \n", "2020-07-31--2020-08-07 | \n", "Agua (with J Balvin) - Music From \"Sponge On T... | \n", "5,358,940 | \n", "Tainy | \n", "\n", " | \n", " | \n", " | ... | \n", "\n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " |
784 | \n", "785 | \n", "76 | \n", "14 | \n", "2020-09-04--2020-09-11 | \n", "Lean (feat. Towy, Osquel, Beltito & Sammy & Fa... | \n", "4,739,241 | \n", "Super Yei, Jone Quest | \n", "\n", " | \n", " | \n", " | ... | \n", "\n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " |
876 | \n", "877 | \n", "164 | \n", "4 | \n", "2020-09-18--2020-09-25 | \n", "+Linda | \n", "4,964,708 | \n", "Dalex | \n", "\n", " | \n", " | \n", " | ... | \n", "\n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " |
1140 | \n", "1141 | \n", "131 | \n", "1 | \n", "2020-05-29--2020-06-05 | \n", "In meinem Benz | \n", "5,494,500 | \n", "AK AUSSERKONTROLLE, Bonez MC | \n", "\n", " | \n", " | \n", " | ... | \n", "\n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " |
1538 | \n", "1539 | \n", "176 | \n", "1 | \n", "2020-01-03--2020-01-10 | \n", "fuck, i'm lonely (with Anne-Marie) - from “13 ... | \n", "4,856,458 | \n", "Lauv | \n", "\n", " | \n", " | \n", " | ... | \n", "\n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " | \n", " |
11 rows × 23 columns
\n", "\n", " | Index | \n", "Highest Charting Position | \n", "Number of Times Charted | \n", "Week of Highest Charting | \n", "Song Name | \n", "Streams | \n", "Artist | \n", "Artist Followers | \n", "Song ID | \n", "Genre | \n", "... | \n", "Danceability | \n", "Energy | \n", "Loudness | \n", "Speechiness | \n", "Acousticness | \n", "Liveness | \n", "Tempo | \n", "Duration (ms) | \n", "Valence | \n", "Chord | \n", "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", "1 | \n", "1 | \n", "8 | \n", "2021-07-23--2021-07-30 | \n", "Beggin' | \n", "48,633,449 | \n", "Måneskin | \n", "3377762.0 | \n", "3Wrjm47oTz2sjIgck11l5e | \n", "['indie rock italiano', 'italian pop'] | \n", "... | \n", "0.714 | \n", "0.800 | \n", "-4.808 | \n", "0.0504 | \n", "0.12700 | \n", "0.3590 | \n", "134.002 | \n", "211560.0 | \n", "0.589 | \n", "B | \n", "
1 | \n", "2 | \n", "2 | \n", "3 | \n", "2021-07-23--2021-07-30 | \n", "STAY (with Justin Bieber) | \n", "47,248,719 | \n", "The Kid LAROI | \n", "2230022.0 | \n", "5HCyWlXZPP0y6Gqq8TgA20 | \n", "['australian hip hop'] | \n", "... | \n", "0.591 | \n", "0.764 | \n", "-5.484 | \n", "0.0483 | \n", "0.03830 | \n", "0.1030 | \n", "169.928 | \n", "141806.0 | \n", "0.478 | \n", "C#/Db | \n", "
2 | \n", "3 | \n", "1 | \n", "11 | \n", "2021-06-25--2021-07-02 | \n", "good 4 u | \n", "40,162,559 | \n", "Olivia Rodrigo | \n", "6266514.0 | \n", "4ZtFanR9U6ndgddUvNcjcG | \n", "['pop'] | \n", "... | \n", "0.563 | \n", "0.664 | \n", "-5.044 | \n", "0.1540 | \n", "0.33500 | \n", "0.0849 | \n", "166.928 | \n", "178147.0 | \n", "0.688 | \n", "A | \n", "
3 | \n", "4 | \n", "3 | \n", "5 | \n", "2021-07-02--2021-07-09 | \n", "Bad Habits | \n", "37,799,456 | \n", "Ed Sheeran | \n", "83293380.0 | \n", "6PQ88X9TkUIAUIZJHW2upE | \n", "['pop', 'uk pop'] | \n", "... | \n", "0.808 | \n", "0.897 | \n", "-3.712 | \n", "0.0348 | \n", "0.04690 | \n", "0.3640 | \n", "126.026 | \n", "231041.0 | \n", "0.591 | \n", "B | \n", "
4 | \n", "5 | \n", "5 | \n", "1 | \n", "2021-07-23--2021-07-30 | \n", "INDUSTRY BABY (feat. Jack Harlow) | \n", "33,948,454 | \n", "Lil Nas X | \n", "5473565.0 | \n", "27NovPIUIRrOZoCHxABJwK | \n", "['lgbtq+ hip hop', 'pop rap'] | \n", "... | \n", "0.736 | \n", "0.704 | \n", "-7.409 | \n", "0.0615 | \n", "0.02030 | \n", "0.0501 | \n", "149.995 | \n", "212000.0 | \n", "0.894 | \n", "D#/Eb | \n", "
... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "
1551 | \n", "1552 | \n", "195 | \n", "1 | \n", "2019-12-27--2020-01-03 | \n", "New Rules | \n", "4,630,675 | \n", "Dua Lipa | \n", "27167675.0 | \n", "2ekn2ttSfGqwhhate0LSR0 | \n", "['dance pop', 'pop', 'uk pop'] | \n", "... | \n", "0.762 | \n", "0.700 | \n", "-6.021 | \n", "0.0694 | \n", "0.00261 | \n", "0.1530 | \n", "116.073 | \n", "209320.0 | \n", "0.608 | \n", "A | \n", "
1552 | \n", "1553 | \n", "196 | \n", "1 | \n", "2019-12-27--2020-01-03 | \n", "Cheirosa - Ao Vivo | \n", "4,623,030 | \n", "Jorge & Mateus | \n", "15019109.0 | \n", "2PWjKmjyTZeDpmOUa3a5da | \n", "['sertanejo', 'sertanejo universitario'] | \n", "... | \n", "0.528 | \n", "0.870 | \n", "-3.123 | \n", "0.0851 | \n", "0.24000 | \n", "0.3330 | \n", "152.370 | \n", "181930.0 | \n", "0.714 | \n", "B | \n", "
1553 | \n", "1554 | \n", "197 | \n", "1 | \n", "2019-12-27--2020-01-03 | \n", "Havana (feat. Young Thug) | \n", "4,620,876 | \n", "Camila Cabello | \n", "22698747.0 | \n", "1rfofaqEpACxVEHIZBJe6W | \n", "['dance pop', 'electropop', 'pop', 'post-teen ... | \n", "... | \n", "0.765 | \n", "0.523 | \n", "-4.333 | \n", "0.0300 | \n", "0.18400 | \n", "0.1320 | \n", "104.988 | \n", "217307.0 | \n", "0.394 | \n", "D | \n", "
1554 | \n", "1555 | \n", "198 | \n", "1 | \n", "2019-12-27--2020-01-03 | \n", "Surtada - Remix Brega Funk | \n", "4,607,385 | \n", "Dadá Boladão, Tati Zaqui, OIK | \n", "208630.0 | \n", "5F8ffc8KWKNawllr5WsW0r | \n", "['brega funk', 'funk carioca'] | \n", "... | \n", "0.832 | \n", "0.550 | \n", "-7.026 | \n", "0.0587 | \n", "0.24900 | \n", "0.1820 | \n", "154.064 | \n", "152784.0 | \n", "0.881 | \n", "F | \n", "
1555 | \n", "1556 | \n", "199 | \n", "1 | \n", "2019-12-27--2020-01-03 | \n", "Lover (Remix) [feat. Shawn Mendes] | \n", "4,595,450 | \n", "Taylor Swift | \n", "42227614.0 | \n", "3i9UVldZOE0aD0JnyfAZZ0 | \n", "['pop', 'post-teen pop'] | \n", "... | \n", "0.448 | \n", "0.603 | \n", "-7.176 | \n", "0.0640 | \n", "0.43300 | \n", "0.0862 | \n", "205.272 | \n", "221307.0 | \n", "0.422 | \n", "G | \n", "
1545 rows × 23 columns
\n", "