How Web Scraping Is Used In Apple Music Streaming Data Analysis?

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import plotly_express as px

pd.set_option('display.max_columns', None)

music_df.head()

nans = [col for col in music_df.columns if music_df[col].isnull().all()==True]
print(nans)

['Original Title',
'Provided Audio Bit Depth',
'Provided Audio Channel',
'Provided Audio Sample Rate',
'Provided Bit Rate',
'Provided Codec',
'Provided Playback Format',
'Targeted Audio Bit Depth',
'Targeted Audio Channel',
'Targeted Audio Sample Rate',
'Targeted Bit Rate',
'Targeted Codec',
'Targeted Playback Format',
'User’s Audio Quality',
'User’s Playback Format']

# drop the above columns from the dataframe
music_df.drop(nans, axis=1, inplace=True)

to_delete = ['Apple Id Number', 'Build Version', 'Client IP Address', 'Device Identifier', 'Metrics Bucket Id', 'Metrics Client Id', 'UTC Offset In Seconds', 'Store Country Name']
music_df.drop(to_delete, axis=1, inplace=True)

music_df['Event End Timestamp'] = pd.to_datetime(music_df['Event End Timestamp'], format='%Y-%m-%dT%H:%M:%S')
music_df['Event Received Timestamp'] = pd.to_datetime(music_df['Event Received Timestamp'], format='%Y-%m-%dT%H:%M:%S')
music_df['Event Start Timestamp'] = pd.to_datetime(music_df['Event Start Timestamp'], format='%Y-%m-%dT%H:%M:%S')

fig = px.bar(top_10_artist, title="Top 10 favourite artists", labels={"index":"Artists", 'value':"No. of times song played"}, color_discrete_sequence=px.colors.qualitative.Set2)
fig.show()

fig = px.bar(top_20_songs, title="Top 20 favourite songs", labels={"index":"Songs", 'value':"No. of times song played"}, color_discrete_sequence=px.colors.qualitative.Bold)
fig.update_xaxes(tickangle=22)
fig.show()

fig = px.bar(top_10_labels, title="Top 20 favourite labels", labels={"index":"Music Labels", 'value':"No. of times song label played"}, color_discrete_sequence=px.colors.qualitative.Pastel)
fig.update_xaxes(tickangle=25)
fig.show()

def top_10_song_of_label(label):
    """
    Function to see what are the top musics played from particular label. 
    """
    # use groupby method and sort ascending
    label_df = music_df[music_df['Content Provider'] == label]
    top_10_song = label_df['Content Name'].value_counts()[:10]
    print(top_10_song)
    fig = px.bar(top_10_song, labels={"index": "Song Names", "value": "No. of time song played", "variable":"Song name"}, title=f"Top songs from {label}")
    fig.show()
and it goes like this – for example, top Warner Music Group songs
top_10_song_of_label('The Warner Music Group')

Hola (feat. Maluma)                                     82
I Don't Care                                            69
Thinking Out Loud                                       63
Attention                                               62
Perfect                                                 60
1, 2, 3 (feat. Jason Derulo & De La Ghetto)             59
Dirty Sexy Money (feat. Charli XCX & French Montana)    52
Hymn for the Weekend                                    51
Crown                                                   50
10,000 Hours                                            48
Name: Content Name, dtype: int64

Ishq Tera              66
Chota Sa Fasana        60
Maahi Ve               59
High Rated Gabru       50
Tu Chale               45
Tera Yaar Hoon Main    45
Befikra                41
Zindagi Do Pal Ki      40
Duniyaa                40
Chalte Chalte          40
Name: Content Name, dtype: int64

fig = px.bar(top_longest_played[:10], labels={"Content Name": "Song Names", "value": "Play Time (in mins)", "variable":"Duration"}, color_discrete_sequence=colors.G10_r)
fig.show()

fig = px.bar(top_genre, color_discrete_sequence=colors.T10_r)
fig.show()

fig = px.pie(music_df, names='Media Type', color_discrete_sequence=colors.Dark2, title="Most preferable Media Type (eg. Audio/Video)")
fig.show()

fig = px.pie(music_df, names="Offline", title="Do you prefer listening to music Offline?")
fig.show()

fig = px.bar(hours, title="Most active hours (24hr)", labels={"value": "count", "Event Start Timestamp":"Timings (hours)"}, color_discrete_sequence=colors.Prism)
fig.update_xaxes(dtick=1)
fig.show()

m = ['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug', 'Sept', 'Oct', 'Nov','Dec']
fig = px.bar(months, title="Most active Months", text=m, labels={"value": "count", "Event Start Timestamp":"Months"}, color_discrete_sequence=colors.Light24)
fig.update_xaxes(dtick=1)
fig.show()

fig = px.bar(years, title="Most active year", labels={"value": "count", "Event Start Timestamp":"Year"}, color_discrete_sequence=colors.Prism_r)
fig.update_xaxes(dtick=1)
fig.show()

total_mins = total_time/60000
print("Total minutes spent: {:.2f} mins".format(total_mins))
total_hours = total_mins/60
print("Total hours spent: {:.2f} hours".format(total_hours))
Total minutes spent: 24568.91 mins Total hours spent: 409.48 hours

total_possible_hours = total_possible_time * 24
print("Total possible hours from start to end: {} hours".format(total_possible_hours))
Total possible hours from start to end: 31632 hours

hours_spent_list = np.array([total_hours, total_possible_hours])
hours_spent_list_labels = [" Actual Hours Spent", "Possible Hours"]

fig, ax = plt.subplots(figsize=(12,6))
ax.pie(hours_spent_list, labels= hours_spent_list_labels, autopct='%1.1f%%',  explode=[0.2,0.2], startangle=180, shadow = True);
plt.title("Hours Spent Percentage");

total_songs = music_df.shape[0]
print("Daily average of songs played: {:.2f} songs".format(total_songs/total_possible_time))
Daily average of songs played: 16.04 songs