def generate_facets(config, df):
proto = GenericFeatureStatisticsGenerator().ProtoFromDataFrames([{
'name':
'facets-iss',
'table':
df
}])
protostr = base64.b64encode(proto.SerializeToString()).decode("utf-8")
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)
return html
def overview(tables: typing.Union[pandas.DataFrame, typing.Mapping[str, pandas.DataFrame]]) -> HTML:
# Element ID MUST be unique
elem_id = _generate_element_id()
if isinstance(tables, pandas.DataFrame):
tables = {"default": tables}
table_list = []
for name, table in tables.items():
# Convert PandasExtensionDType column to object column because facets currently doesn't support it.
view = table.copy()
for k, v in view.dtypes.iteritems():
if not isinstance(v, numpy.dtype):
view[k] = view[k].astype(object)
table_list.append({'name': name, 'table': view})
proto = GenericFeatureStatisticsGenerator().ProtoFromDataFrames(table_list)
proto_str = base64.b64encode(proto.SerializeToString()).decode("utf-8")
return HTML(FACETS_OVERVIEW_TEMPLATE.format(elem_id=elem_id, proto_str=proto_str))
def generate_html(self, datasets: List[Dict[Text, pd.DataFrame]]) -> str:
"""Generates html for facet.
Args:
datasets: List of dicts of dataframes to be visualized as stats.
Returns:
HTML template with proto string embedded.
"""
proto = GenericFeatureStatisticsGenerator().ProtoFromDataFrames(
datasets)
protostr = base64.b64encode(proto.SerializeToString()).decode("utf-8")
template = os.path.join(
os.path.abspath(os.path.dirname(__file__)),
"stats.html",
)
html_template = fileio.read_file_contents_as_string(template)
html_ = html_template.replace("protostr", protostr)
return html_
my_pipeline = make_pipeline(Imputer(), RandomForestRegressor())
my_pipeline.fit(train_X, train_y)
predictions = my_pipeline.predict(test_X)
print("Error:" + str(mean_absolute_error(predictions, test_y)))
#%%
train = pd.read_csv('ML/train.csv')
test = pd.read_csv('ML/test.csv')
from facets_overview.generic_feature_statistics_generator import GenericFeatureStatisticsGenerator
#%%
proto = GenericFeatureStatisticsGenerator().ProtoFromDataFrames([{
'name': 'test',
'table': test
}])
#%%
from IPython.core.display import display, HTML
import base64
protostr = base64.b64encode(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)
display(HTML(html))
#%%