用facets_overview查看dataset的概览

facets_overview_display.py

import base64
from IPython.core.display import display, HTML
# pip install facets_overview
from facets_overview.generic_feature_statistics_generator import GenericFeatureStatisticsGenerator


def display_overview(df_train, df_test=None):
    gfsg = GenericFeatureStatisticsGenerator()
    if df_test is not None:
        proto = gfsg.ProtoFromDataFrames([{'name': 'train', 'table': df_train},
                                          {'name': 'test', 'table': df_test}])
    else:
        proto = gfsg.ProtoFromDataFrames([{'name': 'train', 'table': df_train}])
    protostr = base64.b64encode(proto.SerializeToString()).decode("utf-8")


    # Display the facets overview visualization for this data
    HTML_TEMPLATE = """
            <script src="https://cdnjs.cloudflare.com/ajax/libs/webcomponentsjs/1.3.3/webcomponents-lite.js"></script>
            <link rel="import" href="https://raw.githubusercontent.com/PAIR-code/facets/1.0.0/facets-dist/facets-jupyter.html" >
            <facets-overview id="elem"></facets-overview>
            <script>
              document.querySelector("#elem").protoInput = "{protostr}";
            </script>"""
    html = HTML_TEMPLATE.format(protostr=protostr)
    display(HTML(html))