Getting Started

This guide showcases the features of skrub, an open-source package that aims at bridging the gap between tabular data sources and machine-learning models.

Much of skrub revolves around vectorizing, assembling, and encoding tabular data, to prepare data in a format that shallow or classic machine-learning models understand.

Downloading example datasets

The datasets module allows us to download tabular datasets and demonstrate skrub’s features.

from skrub.datasets import fetch_employee_salaries

dataset = fetch_employee_salaries()
employees_df, salaries = dataset.X, dataset.y

Explore all the available datasets in Downloading a dataset.

Generating an interactive report for a dataframe

To quickly get an overview of a dataframe’s contents, use the TableReport.

from skrub import TableReport

TableReport(employees_df)

Please enable javascript

The skrub table reports need javascript to display correctly. If you are displaying a report in a Jupyter notebook and you see this message, you may need to re-execute the cell or to trust the notebook (button on the top right or "File > Trust notebook").

You can use the interactive display above to explore the dataset visually.

Note

You can see a few more example reports online. We also provide an experimental online demo that allows you to select a CSV or parquet file and generate a report directly in your web browser, without installing anything.

It is also possible to tell skrub to replace the default pandas & polars displays with TableReport.

from skrub import patch_display, unpatch_display

patch_display()

employees_df

Please enable javascript

The skrub table reports need javascript to display correctly. If you are displaying a report in a Jupyter notebook and you see this message, you may need to re-execute the cell or to trust the notebook (button on the top right or "File > Trust notebook").

The effect of patch_display can be undone with skrub.unpatch_display()

unpatch_display()

Easily building a strong baseline for tabular machine learning

The goal of skrub is to ease tabular data preparation for machine learning. The tabular_learner() function provides an easy way to build a simple but reliable machine-learning model, working well on most tabular data.

from sklearn.model_selection import cross_validate

from skrub import tabular_learner

model = tabular_learner("regressor")
results = cross_validate(model, employees_df, salaries)
results["test_score"]

array([0.89370447, 0.89279068, 0.92282557, 0.92319094, 0.92162666])

To handle rich tabular data and feed it to a machine-learning model, the pipeline returned by tabular_learner() preprocesses and encodes strings, categories and dates using the TableVectorizer. See its documentation or Encoding: from a dataframe to a numerical matrix for machine learning for more details. An overview of the chosen defaults is available in End-to-end predictive models.

Assembling data

Skrub allows imperfect assembly of data, such as joining dataframes on columns that contain typos. Skrub’s joiners have fit and transform methods, storing information about the data across calls.

The Joiner allows fuzzy-joining multiple tables, each row of a main table will be augmented with values from the best match in the auxiliary table. You can control how distant fuzzy-matches are allowed to be with the max_dist parameter.

In the following, we add information about countries to a table containing airports and the cities they are in:

import pandas as pd

from skrub import Joiner

airports = pd.DataFrame(
    {
        "airport_id": [1, 2],
        "airport_name": ["Charles de Gaulle", "Aeroporto Leonardo da Vinci"],
        "city": ["Paris", "Roma"],
    }
)
# notice the "Rome" instead of "Roma"
capitals = pd.DataFrame(
    {"capital": ["Berlin", "Paris", "Rome"], "country": ["Germany", "France", "Italy"]}
)
joiner = Joiner(
    capitals,
    main_key="city",
    aux_key="capital",
    max_dist=0.8,
    add_match_info=False,
)
joiner.fit_transform(airports)

	airport_id	airport_name	city	capital	country
0	1	Charles de Gaulle	Paris	Paris	France
1	2	Aeroporto Leonardo da Vinci	Roma	Rome	Italy

Information about countries have been added, even if the rows aren’t exactly matching.

It’s also possible to augment data by joining and aggregating multiple dataframes with the AggJoiner. This is particularly useful to summarize information scattered across tables, for instance adding statistics about flights to the dataframe of airports:

from skrub import AggJoiner

flights = pd.DataFrame(
    {
        "flight_id": range(1, 7),
        "from_airport": [1, 1, 1, 2, 2, 2],
        "total_passengers": [90, 120, 100, 70, 80, 90],
        "company": ["DL", "AF", "AF", "DL", "DL", "TR"],
    }
)
agg_joiner = AggJoiner(
    aux_table=flights,
    main_key="airport_id",
    aux_key="from_airport",
    cols=["total_passengers"],  # the cols to perform aggregation on
    operations=["mean", "std"],  # the operations to compute
)
agg_joiner.fit_transform(airports)

	airport_id	airport_name	city	total_passengers_mean	total_passengers_std
0	1	Charles de Gaulle	Paris	103.333333	15.275252
1	2	Aeroporto Leonardo da Vinci	Roma	80.000000	10.000000

For joining multiple auxiliary tables on a main table at once, use the MultiAggJoiner.

See other ways to join multiple tables in Assembling: joining multiple tables.

Encoding data

When a column contains categories with variations and typos, it can be encoded using one of skrub’s encoders, such as the GapEncoder.

The GapEncoder creates a continuous encoding, based on the activation of latent categories. It will create the encoding based on combinations of substrings which frequently co-occur.

For instance, we might want to encode a column X that contains information about cities, being either Madrid or Rome :

from skrub import GapEncoder

X = pd.Series(
    [
        "Rome, Italy",
        "Rome",
        "Roma, Italia",
        "Madrid, SP",
        "Madrid, spain",
        "Madrid",
        "Romq",
        "Rome, It",
    ],
    name="city",
)
enc = GapEncoder(n_components=2, random_state=0)  # 2 topics in the data
enc.fit(X)

GapEncoder(n_components=2, random_state=0)

In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.

The GapEncoder has found the following two topics:

enc.get_feature_names_out()

['city: madrid, spain, sp', 'city: italia, italy, romq']

Which correspond to the two cities.

Let’s see the activation of each topic depending on the rows of X:

encoded = enc.fit_transform(X).assign(original=X)
encoded

	city: madrid, spain, sp	city: italia, italy, romq	original
0	0.052257	13.547743	Rome, Italy
1	0.050202	3.049798	Rome
2	0.063282	15.036718	Roma, Italia
3	12.047028	0.052972	Madrid, SP
4	16.547818	0.052182	Madrid, spain
5	6.048861	0.051139	Madrid
6	0.050019	3.049981	Romq
7	0.053193	9.046807	Rome, It

The higher the activation, the closer the row to the latent topic. These columns can now be understood by a machine-learning model.

The other encoders are presented in Encoding: creating feature matrices.

Next steps

We have briefly covered pipeline creation, vectorizing, assembling, and encoding data. We presented the main functionalities of skrub, but there is much more to it !

Please refer to our User guide for a more in-depth presentation of skrub’s concepts, or visit our examples for more illustrations of the tools that we provide !