jamesthomson

%pyspark
#read in datafile
data = sc.textFile('s3://bucket/clustering/zep_tracks.csv')
#read as rdd
import csv
rdd = data.mapPartitions(lambda x: csv.reader(x))
#convert to dataframe
dataframe = rdd.toDF(['artist','artist_id','album','album_id','track','track_id','track_number','track_length',
	'preview_url','danceability','energy','key','loudness','mode','speechiness','acousticness','instrumentalness',

jamesthomson

library(httr)

country = "GB"
albumType = "album"
artist="Led Zeppelin"

#get artist id
url <- paste0("https://api.spotify.com/v1/search?q=", sub(" ", "%20", artist), "&type=artist")
search <- content(GET(url))
search$artists$items[[1]]

jamesthomson

library(plotly)

#read in data
final<-read.csv("outputFile.txt", header=FALSE)[,-c(1,2)]
original<-read.csv("zep_tracks.csv", header=FALSE)

#join together
merged<-merge(original, final, by.x="V5", by.y="V7")

#grab key vars and fix labels

jamesthomson

library(twitteR)

#twitter authorisation
consumer_key = ''
consumer_secret = ''
access_token = ''
access_secret = ''
setup_twitter_oauth(consumer_key, consumer_secret, access_token, access_secret)

user<-getUser("inspirationinf")

jamesthomson

#required libraries
import urllib
import scipy.io.wavfile
import pydub

#a temp folder for downloads
temp_folder="/Users/home/Desktop/"

#spotify mp3 sample file