Facets fro Colab

facets_colab.py

import shutil
if os.path.exists('./facets'):
  shutil.rmtree("./facets")

!git clone https://github.com/PAIR-code/facets
!jupyter nbextension install facets/facets-dist/ 

import sys
import os
sys.path.append(os.path.abspath('./facets/facets_overview/python/'))

from generic_feature_statistics_generator import GenericFeatureStatisticsGenerator
import base64

class FacetsOverview(object):
  def __init__(self, df_train, df_test):
    gfsg = GenericFeatureStatisticsGenerator()
    self._proto = gfsg.ProtoFromDataFrames([{'name': 'train', 'table': df_train},
                                      {'name': 'test', 'table': df_test}])
  
  def _repr_html_(self):
    protostr = base64.b64encode(self._proto.SerializeToString()).decode("utf-8")

    HTML_TEMPLATE = """<link rel="import" href="/nbextensions/facets-dist/facets-jupyter.html" >
            <facets-overview id="elem"></facets-overview>
            <script>
              document.querySelector("#elem").protoInput = "{protostr}";
            </script>"""
    html = HTML_TEMPLATE.format(protostr=protostr)
    return html
  
class FacetsDive(object):
  def __init__(self, data):
    self._data = data
    self.height = 1000
    
  def _repr_html_(self):
    HTML_TEMPLATE = """<link rel="import" href="/nbextensions/facets-dist/facets-jupyter.html" >
        <facets-dive id="elem" height="{height}"></facets-dive>
        <script>
          document.querySelector("#elem").data = {data};
        </script>"""
    html = HTML_TEMPLATE.format(data=self._data.to_json(orient='records'), height=self.height)
    return html