Spotify Data Analysis
This report uses a random 50% sample of the Spotify dataset.
Dataset and Sample
| Sample | Observations |
|---|---|
| Original Dataset | 4573 |
| Sample Used | 2286 |
The original dataset contained 4573 observations. I randomly selected 2286 observations, or approximately 50%.
EDA 1: Track Popularity
EDA 1 is a univariate analysis of track popularity. This analysis uses descriptive statistics and a histogram.
| Statistic | Value |
|---|---|
| Mean | 52.51 |
| Median | 57.00 |
| Minimum | 0.00 |
| Maximum | 99.00 |
| Standard Deviation | 23.48 |
EDA 2: Artist vs. Track Popularity
EDA 2 is a bivariate analysis of two popularity variables. This analysis uses correlation and a scatterplot.
| Measurement | Value |
|---|---|
| Observations Used | 2185.00 |
| Pearson Correlation | 0.51 |
What I Learned
Track popularity varies considerably across the Spotify sample. Artist popularity has a positive relationship with track popularity. Different EDA techniques can reveal different patterns in marketing data.
Dataset Source
Source: https://www.kaggle.com/code/marawanmohsen1/spotify?scriptVersionId=283816192&cellId=1