Basic Example
Get to know Evidently in a couple of minutes.
You can launch this hello-world example in Jupyter notebook or Colab.
Install Evidently using the pip package manager:
$ pip install evidently
Install and enable Jupyter nbextension. Run the two following commands in the terminal from the Evidently directory:
$ jupyter nbextension install --sys-prefix --symlink --overwrite --py evidently
$ jupyter nbextension enable evidently --py --sys-prefix
Install Evidently:
!pip install evidently
Import toy data and required Evidently components:
import pandas as pd
from sklearn import datasets
from evidently.test_suite import TestSuite
from evidently.test_preset import DataStabilityTestPreset
from evidently.report import Report
from evidently.metric_preset import DataDriftPreset
iris_data = datasets.load_iris(as_frame='auto')
iris_frame = iris_data.frame
Split the toy data into two batches and compare them:
data_stability= TestSuite(tests=[
DataStabilityTestPreset(),
])
data_stability.run(current_data=iris_frame.iloc[:60], reference_data=iris_frame.iloc[60:], column_mapping=None)
data_stability
Get a visual report to explore the feature distribution drift in detail:
data_drift_report = Report(metrics=[
DataDriftPreset(),
])
data_drift_report.run(current_data=iris_frame.iloc[:60], reference_data=iris_frame.iloc[60:], column_mapping=None)
data_drift_report
Last modified 1mo ago