In [1]:
from pathlib import Path

import numpy as np
import pandas as pd
import scanpy as sc
import seaborn as sns

sns.set()

here = Path(".")
data = here / "data"
data.mkdir(exist_ok=True, parents=True)
In [2]:
# This is a dataframe (like tibble).
spotify_songs = pd.read_csv(data / "spotify_songs.csv")
spotify_songs.to_csv(data / 'spotify_songs.csv', index=False)

spotify_songs
Out[2]:
track_id track_name track_artist track_popularity track_album_id track_album_name track_album_release_date playlist_name playlist_id playlist_genre ... key loudness mode speechiness acousticness instrumentalness liveness valence tempo duration_ms
0 6f807x0ima9a1j3VPbc7VN I Don't Care (with Justin Bieber) - Loud Luxur... Ed Sheeran 66 2oCs0DGTsRO98Gh5ZSl2Cx I Don't Care (with Justin Bieber) [Loud Luxury... 2019-06-14 Pop Remix 37i9dQZF1DXcZDD7cfEKhW pop ... 6 -2.634 1 0.0583 0.102000 0.000000 0.0653 0.5180 122.036 194754
1 0r7CVbZTWZgbTCYdfa2P31 Memories - Dillon Francis Remix Maroon 5 67 63rPSO264uRjW1X5E6cWv6 Memories (Dillon Francis Remix) 2019-12-13 Pop Remix 37i9dQZF1DXcZDD7cfEKhW pop ... 11 -4.969 1 0.0373 0.072400 0.004210 0.3570 0.6930 99.972 162600
2 1z1Hg7Vb0AhHDiEmnDE79l All the Time - Don Diablo Remix Zara Larsson 70 1HoSmj2eLcsrR0vE9gThr4 All the Time (Don Diablo Remix) 2019-07-05 Pop Remix 37i9dQZF1DXcZDD7cfEKhW pop ... 1 -3.432 0 0.0742 0.079400 0.000023 0.1100 0.6130 124.008 176616
3 75FpbthrwQmzHlBJLuGdC7 Call You Mine - Keanu Silva Remix The Chainsmokers 60 1nqYsOef1yKKuGOVchbsk6 Call You Mine - The Remixes 2019-07-19 Pop Remix 37i9dQZF1DXcZDD7cfEKhW pop ... 7 -3.778 1 0.1020 0.028700 0.000009 0.2040 0.2770 121.956 169093
4 1e8PAfcKUYoKkxPhrHqw4x Someone You Loved - Future Humans Remix Lewis Capaldi 69 7m7vv9wlQ4i0LFuJiE2zsQ Someone You Loved (Future Humans Remix) 2019-03-05 Pop Remix 37i9dQZF1DXcZDD7cfEKhW pop ... 1 -4.672 1 0.0359 0.080300 0.000000 0.0833 0.7250 123.976 189052
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
32828 7bxnKAamR3snQ1VGLuVfC1 City Of Lights - Official Radio Edit Lush & Simon 42 2azRoBBWEEEYhqV6sb7JrT City Of Lights (Vocal Mix) 2014-04-28 ♥ EDM LOVE 2020 6jI1gFr6ANFtT8MmTvA2Ux edm ... 2 -1.814 1 0.0936 0.076600 0.000000 0.0668 0.2100 128.170 204375
32829 5Aevni09Em4575077nkWHz Closer - Sultan & Ned Shepard Remix Tegan and Sara 20 6kD6KLxj7s8eCE3ABvAyf5 Closer Remixed 2013-03-08 ♥ EDM LOVE 2020 6jI1gFr6ANFtT8MmTvA2Ux edm ... 0 -4.462 1 0.0420 0.001710 0.004270 0.3750 0.4000 128.041 353120
32830 7ImMqPP3Q1yfUHvsdn7wEo Sweet Surrender - Radio Edit Starkillers 14 0ltWNSY9JgxoIZO4VzuCa6 Sweet Surrender (Radio Edit) 2014-04-21 ♥ EDM LOVE 2020 6jI1gFr6ANFtT8MmTvA2Ux edm ... 6 -4.899 0 0.0481 0.108000 0.000001 0.1500 0.4360 127.989 210112
32831 2m69mhnfQ1Oq6lGtXuYhgX Only For You - Maor Levi Remix Mat Zo 15 1fGrOkHnHJcStl14zNx8Jy Only For You (Remixes) 2014-01-01 ♥ EDM LOVE 2020 6jI1gFr6ANFtT8MmTvA2Ux edm ... 2 -3.361 1 0.1090 0.007920 0.127000 0.3430 0.3080 128.008 367432
32832 29zWqhca3zt5NsckZqDf6c Typhoon - Original Mix Julian Calor 27 0X3mUOm6MhxR7PzxG95rAo Typhoon/Storm 2014-03-03 ♥ EDM LOVE 2020 6jI1gFr6ANFtT8MmTvA2Ux edm ... 5 -4.571 0 0.0385 0.000133 0.341000 0.7420 0.0894 127.984 337500

32833 rows × 23 columns

In [3]:
## How many songs are in each genre?
spotify_songs.groupby('playlist_genre').size()
Out[3]:
playlist_genre
edm      6043
latin    5155
pop      5507
r&b      5431
rap      5746
rock     4951
dtype: int64
In [4]:
## What is average value of energy and acousticness in the latin genre in this dataset?
spotify_songs[spotify_songs['playlist_genre'] == 'latin'][['energy', 'acousticness']].mean()

## Calculate the average duration of song (in minutes) across all subgenres. Which subgenre has the longest song on average?
spotify_songs.groupby('playlist_subgenre')['duration_ms'].mean().sort_values(ascending=False) / 60000

# Make two boxplots side-by-side of the danceability of songs stratifying by whether a song has a fast or slow tempo.
# Define fast tempo as any song that has a tempo above its median value.
median = spotify_songs['tempo'].median()
spotify_songs['tempo_type'] = np.where(spotify_songs['tempo'] > median, 'fast', 'slow')

sns.boxplot(spotify_songs, x='tempo_type', y='danceability')
Out[4]:
<AxesSubplot: xlabel='tempo_type', ylabel='danceability'>
In [5]:
sns.violinplot(spotify_songs, x='tempo_type', y='danceability')
Out[5]:
<AxesSubplot: xlabel='tempo_type', ylabel='danceability'>

Part 2¶

Use this tutorial. The dataset can be procured as followed:

In [6]:
adata = sc.datasets.pbmc3k()
adata

100%|██████████| 5.58M/5.58M [00:01<00:00, 5.19MB/s]
Out[6]:
AnnData object with n_obs × n_vars = 2700 × 32738
    var: 'gene_ids'
In [ ]: