human learn:
data
Human-Learn contains scikit-learn compatible tools that should make it easier to construct and benchmark rule based systems that are designed by humans. You can also use it in combination with ML models. In this series of videos we'll demonstrate some of the features.
Notes
Let's make some drawings without supplying a label column.
from hulearn.experimental.interactive import InteractiveCharts
# Note that we now supply a list of labels to draw.
charts = InteractiveCharts(df, labels=["group_one", "group_two"])
charts.add_chart(x="bill_length_mm", y="bill_depth_mm")
These drawn features can also be applied as a featurization step. Both scikit-learn pipelines and pandas pipelines are supported.
from hulearn.preprocessing import InteractivePreprocessor
tfm = InteractivePreprocessor(json_desc=charts.data())
# The flow for scikit-learn
tfm.fit(df).transform(df)
# The flow for pandas
df.pipe(tfm.pandas_pipe)
Feedback? See an issue? Something unclear? Feel free to mention it here.
If you want to be kept up to date, consider signing up for the newsletter.