Learn practical skills, build real-world projects, and advance your career
Updated 3 years ago
Preparing Spotify Data for Tableau
Anne Bode
import pandas as pd
import numpy as np
import requests
Creating Streaming/Library Dataframe
# read your 1+ StreamingHistory files (depending on how extensive your streaming history is) into pandas dataframes
df_stream0 = pd.read_json('StreamingHistory0.json')
df_stream1 = pd.read_json('streamingHistory1.json')
# merge streaming dataframes
df_stream = pd.concat([df_stream0, df_stream1])
# create a 'UniqueID' for each song by combining the fields 'artistName' and 'trackName'
df_stream['UniqueID'] = df_stream['artistName'] + ":" + df_stream['trackName']
df_stream.head()
# read your edited Library json file into a pandas dataframe
df_library = pd.read_json('YourLibrary1.json')
# add UniqueID column (same as above)
df_library['UniqueID'] = df_library['artist'] + ":" + df_library['track']
# add column with track URI stripped of 'spotify:track:'
new = df_library["uri"].str.split(":", expand = True)
df_library['track_uri'] = new[2]
df_library.head()