diff --git a/facets_dive/Dive_demo.html b/facets_dive/Dive_demo.html new file mode 100644 index 0000000..842ae06 --- /dev/null +++ b/facets_dive/Dive_demo.html @@ -0,0 +1,11851 @@ + + + +Dive_demo + + + + + + + + + + + + + + + + + + + +
+
+ +
+
+
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"]
+jsonstr = pd.read_csv(
+    "https://archive.ics.uci.edu/ml/machine-learning-databases/adult/adult.test",
+    names=features,
+    sep=r'\s*,\s*',
+    engine='python',
+    skiprows=[0],
+    na_values="?").to_json(orient='records')
+
+ +
+
+
+ +
+
+
+
In [2]:
+
+
+
# Display the Dive visualization for this data
+from IPython.core.display import display, HTML
+
+HTML_TEMPLATE = """<link rel="import" href="/nbextensions/facets-dist/facets-jupyter.html">
+        <facets-dive id="elem" height="600"></facets-dive>
+        <script>
+          var data = {jsonstr};
+          document.querySelector("#elem").data = data;
+        </script>"""
+html = HTML_TEMPLATE.format(jsonstr=jsonstr)
+display(HTML(html))
+
+ +
+
+
+ +
+
+ + +
+ +
+ + + +
+ + + +
+ +
+ +
+
+ +
+
+
+ + + + + + diff --git a/facets_dive/Dive_demo.ipynb b/facets_dive/Dive_demo.ipynb index 8651710..6c883d5 100644 --- a/facets_dive/Dive_demo.ipynb +++ b/facets_dive/Dive_demo.ipynb @@ -2,10 +2,8 @@ "cells": [ { "cell_type": "code", - "execution_count": 3, - "metadata": { - "collapsed": true - }, + "execution_count": 5, + "metadata": {}, "outputs": [], "source": [ "# Load UCI census and convert to json for sending to the visualization\n", @@ -13,30 +11,34 @@ "features = [\"Age\", \"Workclass\", \"fnlwgt\", \"Education\", \"Education-Num\", \"Marital Status\",\n", " \"Occupation\", \"Relationship\", \"Race\", \"Sex\", \"Capital Gain\", \"Capital Loss\",\n", " \"Hours per week\", \"Country\", \"Target\"]\n", - "jsonstr = pd.read_csv(\n", - " \"https://archive.ics.uci.edu/ml/machine-learning-databases/adult/adult.test\",\n", - " names=features,\n", - " sep=r'\\s*,\\s*',\n", + "\n", + "# Load dataframe from external CSV and add header information\n", + "df = pd.read_csv(\"https://archive.ics.uci.edu/ml/machine-learning-databases/adult/adult.test\",\n", + " names=features, # name features for header row\n", + " sep=r'\\s*,\\s*', # separator used in this dataset\n", " engine='python',\n", - " skiprows=[0],\n", - " na_values=\"?\").to_json(orient='records')" + " skiprows=[0], # skip first row without data \n", + " na_values=\"?\") # add ? where data is missing\n", + "\n", + "# set the sprite_size based on the number of records in dataset,\n", + "# larger datasets can crash the browser if the size is too large (>50000)\n", + "sprite_size = 32 if len(df.index)>50000 else 64\n", + "\n", + "jsonstr = df.to_json(orient='records')\n" ] }, { "cell_type": "code", - "execution_count": 4, - "metadata": { - "scrolled": false - }, + "execution_count": 6, + "metadata": {}, "outputs": [ { "data": { "text/html": [ "\n", - " \n", + " \n", " " ], "text/plain": [ @@ -51,15 +53,26 @@ "# Display the Dive visualization for this data\n", "from IPython.core.display import display, HTML\n", "\n", + "# Create Facets template \n", "HTML_TEMPLATE = \"\"\"\n", - " \n", + " \n", " \"\"\"\n", - "html = HTML_TEMPLATE.format(jsonstr=jsonstr)\n", - "display(HTML(html))" + "\n", + "# Load the json dataset and the sprite_size into the template\n", + "html = HTML_TEMPLATE.format(jsonstr=jsonstr, sprite_size=sprite_size)\n", + "\n", + "# Display the template\n", + "display(HTML(html))\n" ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] } ], "metadata": { @@ -78,7 +91,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.4.3" + "version": "3.6.4" } }, "nbformat": 4,