YouTube

Visualizing the total number of subscribers and the total number of views for the top 30 YouTube channels (January 2020) in the music category by using the FacetGrid() function provided by Seaborn.

Importing libraries and packages

# Warnings
import warnings

# Mathematical operations and data manipulation
import pandas as pd

# Plotting
import matplotlib.pyplot as plt
import seaborn as sns

sns.set()
warnings.filterwarnings("ignore")

Set paths

# Path to datasets directory
data_path = "./datasets"
# Path to assets directory (for saving results to)
assets_path = "./assets"

Loading dataset

dataset = pd.read_csv(f"{data_path}/YouTube.csv")

Exploring dataset

# Shape of the dataset
print("Shape of the dataset: ", dataset.shape)
# View
dataset

Shape of the dataset:  (30, 3)

	Channel	Subs (in millions)	Views (in millions)
0	T-Series	123.0	94410
1	Canal KondZilla	54.5	27860
2	Zee Music Company	48.5	22689
3	Ed Sheeran	43.2	18905
4	EminemMusic	40.2	773
5	Ariana Grande	39.3	953
6	Taylor Swift	36.8	310
7	JustinBieberVEVO	33.1	19326
8	BLACKPINK	32.4	8112
9	Alan Walker	31.7	7470
10	Shemaroo Filmi Gaane	31.0	14708
11	ibighit	30.9	7659
12	One Direction	30.4	356
13	Wave Music	30.4	20569
14	Sony Music India	29.9	12077
15	El Reino Infantil	29.2	26159
16	Maroon 5	29.2	294
17	Trap Nation	27.9	10195
18	Speed Records	27.4	13769
19	GR6 EXPLODE	27.2	13341
20	TaylorSwiftVEVO	27.0	18096
21	SonyMusicIndiaVEVO	27.0	12577
22	Ozuna	27.0	13059
23	Daddy Yankee	26.9	9796
24	YRF	26.8	14253
25	Spinnin' Records	26.4	15738
26	Bruno Mars	26.3	11411
27	RihannaVEVO	25.9	14768
28	T-Series Bhakti Sagar	25.8	10552
29	KatyPerryVEVO	25.8	18603

Preprocessing

channels = dataset[dataset.columns[0]].tolist()
print(channels)

['T-Series', 'Canal KondZilla', 'Zee Music Company', 'Ed Sheeran ', 'EminemMusic ', 'Ariana Grande ', 'Taylor Swift', 'JustinBieberVEVO ', ' BLACKPINK', 'Alan Walker', 'Shemaroo Filmi Gaane', 'ibighit', 'One Direction', 'Wave Music ', 'Sony Music India ', 'El Reino Infantil', 'Maroon 5 ', 'Trap Nation', 'Speed Records', 'GR6 EXPLODE ', 'TaylorSwiftVEVO ', 'SonyMusicIndiaVEVO', 'Ozuna', 'Daddy Yankee', 'YRF', "Spinnin' Records", 'Bruno Mars', 'RihannaVEVO ', 'T-Series Bhakti Sagar', 'KatyPerryVEVO']

subs = dataset[dataset.columns[1]].tolist()
print(subs)

[123.0, 54.5, 48.5, 43.2, 40.2, 39.3, 36.8, 33.1, 32.4, 31.7, 31.0, 30.9, 30.4, 30.4, 29.9, 29.2, 29.2, 27.9, 27.4, 27.2, 27.0, 27.0, 27.0, 26.9, 26.8, 26.4, 26.3, 25.9, 25.8, 25.8]

views = dataset[dataset.columns[2]].tolist()
print(views)

[94410, 27860, 22689, 18905, 773, 953, 310, 19326, 8112, 7470, 14708, 7659, 356, 20569, 12077, 26159, 294, 10195, 13769, 13341, 18096, 12577, 13059, 9796, 14253, 15738, 11411, 14768, 10552, 18603]

data = pd.DataFrame(
    {
        "YouTube Channels": channels + channels,
        "Subscribers/Views in millions": subs + views,
        "Type": ["Subscribers"] * len(subs) + ["Views"] * len(views),
    }
)
data

	YouTube Channels	Subscribers/Views in millions	Type
0	T-Series	123.0	Subscribers
1	Canal KondZilla	54.5	Subscribers
2	Zee Music Company	48.5	Subscribers
3	Ed Sheeran	43.2	Subscribers
4	EminemMusic	40.2	Subscribers
5	Ariana Grande	39.3	Subscribers
6	Taylor Swift	36.8	Subscribers
7	JustinBieberVEVO	33.1	Subscribers
8	BLACKPINK	32.4	Subscribers
9	Alan Walker	31.7	Subscribers
10	Shemaroo Filmi Gaane	31.0	Subscribers
11	ibighit	30.9	Subscribers
12	One Direction	30.4	Subscribers
13	Wave Music	30.4	Subscribers
14	Sony Music India	29.9	Subscribers
15	El Reino Infantil	29.2	Subscribers
16	Maroon 5	29.2	Subscribers
17	Trap Nation	27.9	Subscribers
18	Speed Records	27.4	Subscribers
19	GR6 EXPLODE	27.2	Subscribers
20	TaylorSwiftVEVO	27.0	Subscribers
21	SonyMusicIndiaVEVO	27.0	Subscribers
22	Ozuna	27.0	Subscribers
23	Daddy Yankee	26.9	Subscribers
24	YRF	26.8	Subscribers
25	Spinnin' Records	26.4	Subscribers
26	Bruno Mars	26.3	Subscribers
27	RihannaVEVO	25.9	Subscribers
28	T-Series Bhakti Sagar	25.8	Subscribers
29	KatyPerryVEVO	25.8	Subscribers
30	T-Series	94410.0	Views
31	Canal KondZilla	27860.0	Views
32	Zee Music Company	22689.0	Views
33	Ed Sheeran	18905.0	Views
34	EminemMusic	773.0	Views
35	Ariana Grande	953.0	Views
36	Taylor Swift	310.0	Views
37	JustinBieberVEVO	19326.0	Views
38	BLACKPINK	8112.0	Views
39	Alan Walker	7470.0	Views
40	Shemaroo Filmi Gaane	14708.0	Views
41	ibighit	7659.0	Views
42	One Direction	356.0	Views
43	Wave Music	20569.0	Views
44	Sony Music India	12077.0	Views
45	El Reino Infantil	26159.0	Views
46	Maroon 5	294.0	Views
47	Trap Nation	10195.0	Views
48	Speed Records	13769.0	Views
49	GR6 EXPLODE	13341.0	Views
50	TaylorSwiftVEVO	18096.0	Views
51	SonyMusicIndiaVEVO	12577.0	Views
52	Ozuna	13059.0	Views
53	Daddy Yankee	9796.0	Views
54	YRF	14253.0	Views
55	Spinnin' Records	15738.0	Views
56	Bruno Mars	11411.0	Views
57	RihannaVEVO	14768.0	Views
58	T-Series Bhakti Sagar	10552.0	Views
59	KatyPerryVEVO	18603.0	Views

Visualisation

# Plot a FacetGrid with two columns
g = sns.FacetGrid(data, col="Type", hue="Type", sharex=False, height=8)
g.map(sns.barplot, "Subscribers/Views in millions", "YouTube Channels")
plt.show()