Documentation | Mail List & Forum

Dataprep is a collection of functions that helps you accomplish tasks before you build a predictive model.

Currently, you can use dataprep to:

• Collect data from common data sources (through dataprep.data_connector)
• Do your exploratory data analysis (through dataprep.eda)
• ...

pip install dataprep

dataprep is in its alpha stage now, so please manually specific the version number.

More detailed examples can be found at the examples folder.

You can download Yelp business search result into a pandas DataFrame, using two lines of code, without taking deep looking into the Yelp documentation!

from dataprep.data_connector import Connector

dc = Connector("yelp", auth_params={"access_token":"<Your yelp access token>"})
df = dc.query("businesses", term="ramen", location="vancouver")

There are common tasks during the exploratory data analysis stage, like a quick look at the columnar distribution, or understanding the correlations between columns.

The EDA module categorizes these EDA tasks into functions helping you finish EDA tasks with a single function call.

• Want to understand the distributions for each DataFrame column? Use plot.

from dataprep.eda import plot

df = ...

plot(df)

• Want to understand the correlation between columns? Use plot_correlation.

from dataprep.eda import plot_correlation

df = ...

plot_correlation(df)

• Or, if you want to understand the impact of the missing values for each column, use plot_missing.

from dataprep.eda import plot_missing

df = ...

plot_missing(df)

• You can even drill down to get more information by given plot, plot_correlation and plot_missing a column name.

df = ...

plot_missing(df, x="some_column_name")

Don't forget to checkout the examples folder for detailed demonstration!

Contribution is always welcome. If you want to contribute to dataprep, be sure to read the contribution guidelines.