Notebook

Got Scotch?¶

In [13]:

import pandas as pd
import numpy as np
import os

In [14]:

import ipywidgets as widgets
from traitlets import Unicode, List, Instance, link, HasTraits
from IPython.display import display, clear_output, HTML, Javascript

In [15]:

features = [[2, 2, 2, 0, 0, 2, 1, 2, 2, 2, 2, 2],
 [3, 3, 1, 0, 0, 4, 3, 2, 2, 3, 3, 2],
 [1, 3, 2, 0, 0, 2, 0, 0, 2, 2, 3, 1],
 [4, 1, 4, 4, 0, 0, 2, 0, 1, 2, 1, 0],
 [2, 2, 2, 0, 0, 1, 1, 1, 2, 3, 1, 3],
 [2, 3, 1, 1, 0, 1, 1, 1, 0, 1, 1, 1],
 [0, 2, 0, 0, 0, 1, 1, 0, 2, 2, 3, 1],
 [2, 3, 1, 0, 0, 2, 1, 2, 2, 2, 2, 2],
 [2, 2, 1, 0, 0, 1, 0, 0, 2, 2, 2, 1],
 [2, 3, 2, 1, 0, 0, 2, 0, 2, 1, 2, 3],
 [4, 3, 2, 0, 0, 2, 1, 3, 3, 0, 1, 2],
 [3, 2, 1, 0, 0, 3, 2, 1, 0, 2, 2, 2],
 [4, 2, 2, 0, 0, 2, 2, 0, 2, 2, 2, 2],
 [2, 2, 1, 0, 0, 2, 2, 0, 0, 2, 3, 1],
 [3, 2, 2, 0, 0, 3, 1, 1, 2, 3, 2, 2],
 [2, 2, 2, 0, 0, 2, 2, 1, 2, 2, 2, 2],
 [1, 2, 1, 0, 0, 0, 1, 1, 0, 2, 2, 1],
 [2, 2, 2, 0, 0, 1, 2, 2, 2, 2, 2, 2],
 [2, 2, 3, 1, 0, 2, 2, 1, 1, 1, 1, 3],
 [1, 1, 2, 2, 0, 2, 2, 1, 2, 2, 2, 3],
 [1, 2, 1, 1, 0, 1, 1, 1, 1, 2, 2, 1],
 [3, 1, 4, 2, 1, 0, 2, 0, 2, 1, 1, 0],
 [1, 3, 1, 0, 0, 1, 1, 0, 2, 2, 2, 1],
 [3, 2, 3, 3, 1, 0, 2, 0, 1, 1, 2, 0],
 [2, 2, 2, 0, 1, 2, 2, 1, 2, 2, 1, 2],
 [2, 3, 2, 1, 0, 0, 1, 0, 2, 2, 2, 1],
 [4, 2, 2, 0, 0, 1, 2, 2, 2, 2, 2, 2],
 [3, 2, 2, 1, 0, 1, 2, 2, 1, 2, 3, 2],
 [2, 2, 2, 0, 0, 2, 1, 0, 1, 2, 2, 1],
 [2, 2, 1, 0, 0, 2, 1, 1, 1, 3, 2, 2],
 [2, 3, 1, 1, 0, 0, 0, 0, 1, 2, 2, 1],
 [2, 3, 1, 0, 0, 2, 1, 1, 4, 2, 2, 2],
 [2, 3, 1, 1, 1, 1, 1, 2, 0, 2, 0, 3],
 [2, 3, 1, 0, 0, 2, 1, 1, 1, 1, 2, 1],
 [2, 1, 3, 0, 0, 0, 3, 1, 0, 2, 2, 3],
 [1, 2, 0, 0, 0, 1, 0, 1, 2, 1, 2, 1],
 [2, 3, 1, 0, 0, 1, 2, 1, 2, 1, 2, 2],
 [1, 2, 1, 0, 0, 1, 2, 1, 2, 2, 2, 1],
 [3, 2, 1, 0, 0, 1, 2, 1, 1, 2, 2, 2],
 [2, 2, 2, 2, 0, 1, 0, 1, 2, 2, 1, 3],
 [1, 3, 1, 0, 0, 0, 1, 1, 1, 2, 0, 1],
 [1, 3, 1, 0, 0, 1, 1, 0, 1, 2, 2, 1],
 [4, 2, 2, 0, 0, 2, 1, 4, 2, 2, 2, 2],
 [3, 2, 1, 0, 0, 2, 1, 2, 1, 2, 3, 2],
 [2, 4, 1, 0, 0, 1, 2, 3, 2, 3, 2, 2],
 [1, 3, 1, 0, 0, 0, 0, 0, 0, 2, 2, 1],
 [1, 2, 0, 0, 0, 1, 1, 1, 2, 2, 3, 1],
 [1, 2, 1, 0, 0, 1, 2, 0, 0, 2, 2, 1],
 [2, 3, 1, 0, 0, 2, 2, 2, 1, 2, 2, 2],
 [1, 2, 1, 0, 0, 1, 2, 0, 1, 2, 2, 1],
 [2, 2, 1, 1, 0, 1, 2, 0, 2, 1, 2, 1],
 [2, 3, 1, 0, 0, 1, 1, 2, 1, 2, 2, 2],
 [2, 3, 1, 0, 0, 2, 2, 2, 2, 2, 1, 2],
 [2, 2, 3, 1, 0, 2, 1, 1, 1, 2, 1, 3],
 [1, 3, 1, 1, 0, 2, 2, 0, 1, 2, 1, 1],
 [2, 1, 2, 2, 0, 1, 1, 0, 2, 1, 1, 3],
 [2, 3, 1, 0, 0, 2, 2, 1, 2, 1, 2, 2],
 [4, 1, 4, 4, 1, 0, 1, 2, 1, 1, 1, 0],
 [4, 2, 4, 4, 1, 0, 0, 1, 1, 1, 0, 0],
 [2, 3, 1, 0, 0, 1, 1, 2, 0, 1, 3, 1],
 [1, 1, 1, 1, 0, 1, 1, 0, 1, 2, 1, 1],
 [3, 2, 1, 0, 0, 1, 1, 1, 3, 3, 2, 2],
 [4, 3, 1, 0, 0, 2, 1, 4, 2, 2, 3, 2],
 [2, 1, 1, 0, 0, 1, 1, 1, 2, 1, 2, 1],
 [2, 4, 1, 0, 0, 1, 0, 0, 2, 1, 1, 1],
 [3, 2, 2, 0, 0, 2, 3, 3, 2, 1, 2, 2],
 [2, 2, 2, 2, 0, 0, 2, 0, 2, 2, 2, 3],
 [1, 2, 2, 0, 1, 2, 2, 1, 2, 3, 1, 3],
 [2, 1, 2, 2, 1, 0, 1, 1, 2, 2, 2, 3],
 [2, 3, 2, 1, 1, 1, 2, 1, 0, 2, 3, 1],
 [3, 2, 2, 0, 0, 2, 2, 2, 2, 2, 3, 2],
 [2, 2, 1, 1, 0, 2, 1, 1, 2, 2, 2, 2],
 [2, 4, 1, 0, 0, 2, 1, 0, 0, 2, 1, 1],
 [2, 2, 1, 0, 0, 1, 0, 1, 2, 2, 2, 1],
 [2, 2, 2, 2, 0, 2, 2, 1, 2, 1, 0, 3],
 [2, 2, 1, 0, 0, 2, 2, 2, 3, 3, 3, 2],
 [2, 3, 1, 0, 0, 0, 2, 0, 2, 1, 3, 1],
 [4, 2, 3, 3, 0, 1, 3, 0, 1, 2, 2, 0],
 [1, 2, 1, 0, 0, 2, 0, 1, 1, 2, 2, 1],
 [1, 3, 2, 0, 0, 0, 2, 0, 2, 1, 2, 1],
 [2, 2, 2, 1, 0, 0, 2, 0, 0, 0, 2, 3],
 [1, 1, 1, 0, 0, 1, 0, 0, 1, 2, 2, 1],
 [2, 3, 2, 0, 0, 2, 2, 1, 1, 2, 0, 3],
 [0, 3, 1, 0, 0, 2, 2, 1, 1, 2, 1, 1],
 [2, 2, 1, 0, 0, 1, 0, 1, 2, 1, 0, 3],
 [2, 3, 0, 0, 1, 0, 2, 1, 1, 2, 2, 1]]

feature_names = ['Body', 'Sweetness', 'Smoky', 
                 'Medicinal', 'Tobacco', 'Honey',
                 'Spicy', 'Winey', 'Nutty',
                 'Malty', 'Fruity', 'cluster']

brand_names = ['Aberfeldy',
 'Aberlour',
 'AnCnoc',
 'Ardbeg',
 'Ardmore',
 'ArranIsleOf',
 'Auchentoshan',
 'Auchroisk',
 'Aultmore',
 'Balblair',
 'Balmenach',
 'Belvenie',
 'BenNevis',
 'Benriach',
 'Benrinnes',
 'Benromach',
 'Bladnoch',
 'BlairAthol',
 'Bowmore',
 'Bruichladdich',
 'Bunnahabhain',
 'Caol Ila',
 'Cardhu',
 'Clynelish',
 'Craigallechie',
 'Craigganmore',
 'Dailuaine',
 'Dalmore',
 'Dalwhinnie',
 'Deanston',
 'Dufftown',
 'Edradour',
 'GlenDeveronMacduff',
 'GlenElgin',
 'GlenGarioch',
 'GlenGrant',
 'GlenKeith',
 'GlenMoray',
 'GlenOrd',
 'GlenScotia',
 'GlenSpey',
 'Glenallachie',
 'Glendronach',
 'Glendullan',
 'Glenfarclas',
 'Glenfiddich',
 'Glengoyne',
 'Glenkinchie',
 'Glenlivet',
 'Glenlossie',
 'Glenmorangie',
 'Glenrothes',
 'Glenturret',
 'Highland Park',
 'Inchgower',
 'Isle of Jura',
 'Knochando',
 'Lagavulin',
 'Laphroig',
 'Linkwood',
 'Loch Lomond',
 'Longmorn',
 'Macallan',
 'Mannochmore',
 'Miltonduff',
 'Mortlach',
 'Oban',
 'OldFettercairn',
 'OldPulteney',
 'RoyalBrackla',
 'RoyalLochnagar',
 'Scapa',
 'Speyburn',
 'Speyside',
 'Springbank',
 'Strathisla',
 'Strathmill',
 'Talisker',
 'Tamdhu',
 'Tamnavulin',
 'Teaninich',
 'Tobermory',
 'Tomatin',
 'Tomintoul',
 'Tormore',
 'Tullibardine']

In [16]:

features_df = pd.DataFrame(features, columns=feature_names, index=brand_names)
features_df = features_df.drop('cluster', axis=1)

In [17]:

norm = (features_df ** 2).sum(axis=1).apply('sqrt')
normed_df = features_df.divide(norm, axis=0)
sim_df = normed_df.dot(normed_df.T)

In [18]:

def radar(df, ax=None):
    # calculate evenly-spaced axis angles
    num_vars = len(df.columns)
    theta = 2*np.pi * np.linspace(0, 1-1./num_vars, num_vars)
    # rotate theta such that the first axis is at the top
    theta += np.pi/2
    if not ax:
        fig = plt.figure(figsize=(4, 4))

        ax = fig.add_subplot(1,1,1, projection='polar')
    else:
        ax.clear()
    for d, color in zip(df.itertuples(), sns.color_palette()):
        ax.plot(theta, d[1:], color=color, alpha=0.7)
        ax.fill(theta, d[1:], facecolor=color, alpha=0.5)
    ax.set_xticklabels(df.columns)

    legend = ax.legend(df.index, loc=(0.9, .95))
    return ax

In [19]:

def get_similar(name, n, top=True):
    a = sim_df[name].sort_values(ascending=False)
    a.name = 'Similarity'
    df = pd.DataFrame(a) #.join(features_df).iloc[start:end]
    return df.head(n) if top else df.tail(n)

In [20]:

def on_pick_scotch(Scotch):
    name = Scotch
    # Get top 6 similar whiskeys, and remove this one
    top_df = get_similar(name, 6).iloc[1:]
    # Get bottom 5 similar whiskeys
    df = top_df
    
    # Make table index a set of links that the radar widget will watch
    df.index = ['''<a class="scotch" href="#" data-factors_keys='["{}","{}"]'>{}</a>'''.format(name, i, i) for i in df.index]
    
    tmpl = f'''<p>If you like {name} you might want to try these five brands. Click one to see how its taste profile compares.</p>'''
    prompt_w.value = tmpl
    table.value = df.to_html(escape=False)
    lines.x = features_df.loc[Scotch].index.values
    lines.y = features_df.loc[Scotch].values

In [21]:

prompt_w = widgets.HTML(value='Aberfeldy')
display(prompt_w)

HTML(value='Aberfeldy')

In [22]:

table = widgets.HTML(
    value="Hello <b>World</b>"
)
display(table)

HTML(value='Hello <b>World</b>')

In [23]:

from bqplot import (OrdinalScale, LinearScale, Bars, Lines,
                    Figure, Axis, ColorScale, ColorAxis, CATEGORY10)
x_ord = OrdinalScale()
y_sc = LinearScale()

lines = Lines(x=features_df.loc['Aberfeldy'].index.values,
              y=features_df.loc['Aberfeldy'].values, scales={'x': x_ord, 'y': y_sc},
              fill='bottom', fill_colors=['#aaaaff'], fill_opacities=[0.4],
              stroke_width=3)
ax_x = Axis(scale=x_ord, tick_rotate=45, tick_style={'font-size': 20})
ax_y = Axis(scale=y_sc, tick_format='0.2f', orientation='vertical')

Figure(marks=[lines], axes=[ax_x, ax_y], animation_duration=500)

Figure(animation_duration=500, axes=[Axis(scale=OrdinalScale(), tick_rotate=45, tick_style={'font-size': 20}),…

In [24]:

picker_w = widgets.interact(on_pick_scotch, Scotch=list(sim_df.index))

interactive(children=(Dropdown(description='Scotch', options=('Aberfeldy', 'Aberlour', 'AnCnoc', 'Ardbeg', 'Ar…

Powered by data from https://www.strath.ac.uk and inspired by analysis from http://blog.revolutionanalytics.com/2013/12/k-means-clustering-86-single-malt-scotch-whiskies.html. This dashboard originated as a Jupyter Notebook.