kwokhing / visualizing-datasets-with-facets Goto Github PK

# Add the facets overview python code to the python path
import sys
# FACETS_PATH is the full path to the python file in the clonde github repo of Facets.
# It should look similar to this: ".../facets/facets_overview/python"
# If you have cloned the facets repo to your current working directory, you can proceed.
# If you have chosen another location, just add it here.

FACETS_PATH = 'facets-master/facets_overview/python'
sys.path.append(FACETS_PATH)

import pandas as pd

train_data = pd.read_csv(
    "train.csv",
    #sep=r'\s*,\s*',
    engine='python',
    na_values="?")

test_data = pd.read_csv(
    "test.csv",
    #sep=r'\s*,\s*',
    engine='python',
    na_values="?")

test_salaries = pd.read_csv(
    "test_salaries.csv",
    #sep=r'\s*,\s*',
    engine='python',
    na_values="?")

test_data = pd.concat([test_salaries, test_data], axis=1)

# Calculate the feature statistics proto from the datasets and stringify it for use in 
# facets overview
from generic_feature_statistics_generator import GenericFeatureStatisticsGenerator
import base64

gfsg = GenericFeatureStatisticsGenerator()
proto = gfsg.ProtoFromDataFrames([{'name': 'train', 'table': train_data},
                                  {'name': 'test', 'table': test_data}])
protostr = base64.b64encode(proto.SerializeToString()).decode("utf-8")

# Display the facets overview visualization for this data
from IPython.core.display import display, HTML

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))