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

# In[ ]:


import panel as pn

import pandas as pd
import holoviews as hv

from sklearn.cluster import KMeans

penguins = pd.read_csv('https://raw.githubusercontent.com/mwaskom/seaborn-data/master/penguins.csv')
cols = list(penguins.columns)[:-1]

pn.extension('ace')

import hvplot.pandas


# In[ ]:


slider = pn.widgets.IntSlider(start=0, end=10)

img = pn.pane.JPG(f"https://picsum.photos/800/300?image=0", embed=False, height=300)

slider.jscallback(args={'img': img}, value="""
img.text = '<img src="https://picsum.photos/800/300?image='+cb_obj.value+'" width=800 height=300></img>'
""")

app = pn.Column(slider, img)

ace = pn.widgets.Ace(readonly=True, width=800, height=200, language='python', theme='monokai', value=\
"""slider = pn.widgets.IntSlider(start=0, end=10)

def slideshow(index):
    url = f"https://picsum.photos/800/300?image={index}"
    return pn.pane.JPG(url)

output = pn.bind(slideshow, slider)

app = pn.Column(slider, output)""")

app1 = pn.Tabs(('Output', app), ('Code', ace))

penguins = pd.read_csv('https://raw.githubusercontent.com/mwaskom/seaborn-data/master/penguins.csv').dropna()
cols = list(penguins.columns)[2:6]

x = pn.widgets.Select(name='x', options=cols)
y = pn.widgets.Select(name='y', options=cols, value='bill_depth_mm')
n_clusters = pn.widgets.IntSlider(name='n_clusters', start=2, end=5, value=3)

def cluster(data, n_clusters):
    kmeans = KMeans(n_clusters=n_clusters)
    est = kmeans.fit(data)
    return est.labels_.astype('str')

def plot(x, y, n_clusters):
    penguins['labels'] = cluster(penguins.iloc[:, 2:6].values, n_clusters)
    centers = penguins.groupby('labels').mean()
    return (penguins.sort_values('labels').hvplot.scatter(
        x, y, c='labels', hover_cols=['species'], line_width=1, size=60, frame_width=400, frame_height=400
    ).opts(marker=hv.dim('species').categorize({'Adelie': 'square', 'Chinstrap': 'circle', 'Gentoo': 'triangle'})) * centers.hvplot.scatter(
        x, y, marker='x', color='black', size=400, padding=0.1, line_width=5
    ))

explanation = pn.pane.Markdown("""
This app applies k-means clustering on the Palmer Penguins dataset using scikit-learn, parameterizing the number of clusters and the variables to plot.
<br><br>
Each cluster is denoted by one color while the penguin species is indicated using markers: 
<br><br>
● - Adelie, ▲ - Gentoo, ■ - Chinstrap
<br><br>
By comparing the two we can assess the performance of the clustering algorithm.
<br><br>
""")

code = pn.widgets.Ace(language='python', theme='monokai', height=360, value=\
"""x = pn.widgets.Select(name='x', options=cols)
y = pn.widgets.Select(name='y', options=cols, value='bill_depth_mm')
n_clusters = pn.widgets.IntSlider(name='n_clusters', start=2, end=5, value=3)
explanation = pn.pane.Markdown(...)

def plot_clusters(x, y, n_clusters):
    ...
    
pn.Row(
    pn.WidgetBox(x, y, n_clusters, explanation),  
    pn.bind(plot, x, y, n_clusters)
)""", width=800)

app2 = pn.Tabs(
    ('Output', pn.Column(
        pn.Row(
            pn.WidgetBox(x, y, n_clusters, explanation),  
            pn.bind(plot, x, y, n_clusters)
        )
    )),
    ('Code', code)
)

pn.Row(pn.layout.HSpacer(), pn.Tabs(
  ('Penguin K-Means Clustering', app2),
  ('Slideshow', app1)
), pn.layout.HSpacer(), sizing_mode='stretch_width').embed(max_opts=4, json=True, json_prefix='json')