One of the first steps in analysing a dataset is the Data Exploration. The box plots is a standardized way of displaying the distribution of data. Boxplots gives information about the minimum, first quartile, median, third quartile, and maximum.
In this short post, I will focus on the vizualization of the data and the outliers using BoxPlot. To learn more on Data Exploration, check this very thorough post .
I will be using data from an assignment of the Machine Learning Nanodegree: customer segmentation. The dataset is made of 400 businesses: restaurants, retailers, etc…, with their purchasing pattern for Milk products, Grocery products, and more…
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import seaborn as sns | |
| #create "melted" dataframe | |
| df = pd.DataFrame(columns=['variable', 'value']) | |
| for col in log_data.columns: | |
| df = df.append(pd.melt(log_data, value_vars=[col])) | |
| print(df.shape) | |
| # create the boxplot with data points overlay | |
| plt.figure(figsize=(8,6)) | |
| sns.boxplot(x="value", y="variable", data=df, color="c") | |
| sns.stripplot(x="value", y="variable", data=df, jitter=True, | |
| size=4, alpha=.4, color=".3", linewidth=0) | |
| sns.despine(trim=True) |
You can also check out this post where Matplotlib was used to generate the boxplots. link