#!/usr/bin/env python
# coding: utf-8

# In[1]:


# Load UCI census and convert to json for sending to the visualization
import pandas as pd
features = ["Age", "Workclass", "fnlwgt", "Education", "Education-Num", "Marital Status",
            "Occupation", "Relationship", "Race", "Sex", "Capital Gain", "Capital Loss",
            "Hours per week", "Country", "Target"]

# Load dataframe from external CSV and add header information
df = pd.read_csv("https://archive.ics.uci.edu/ml/machine-learning-databases/adult/adult.test",
    names=features, # name features for header row
    sep=r'\s*,\s*', # separator used in this dataset
    engine='python',
    skiprows=[0], # skip first row without data 
    na_values="?") # add ? where data is missing

# set the sprite_size based on the number of records in dataset,
# larger datasets can crash the browser if the size is too large (>50000)
sprite_size = 32 if len(df.index)>50000 else 64

jsonstr = df.to_json(orient='records')


# In[2]:


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

# Create Facets template  
HTML_TEMPLATE = """<link rel="import" href="/nbextensions/facets-dist/facets-jupyter.html">
        <facets-dive sprite-image-width="{sprite_size}" sprite-image-height="{sprite_size}" id="elem" height="600"></facets-dive>
        <script>
          document.querySelector("#elem").data = {jsonstr};
        </script>"""

# Load the json dataset and the sprite_size into the template
html = HTML_TEMPLATE.format(jsonstr=jsonstr, sprite_size=sprite_size)

# Display the template
display(HTML(html))


# In[ ]: