In [1]:

    

from datetime import datetime as dt

import numpy as np
import pandas as pd

# viz libs
import matplotlib.pyplot as plt
%matplotlib inline
import matplotlib.cm as cm
from matplotlib.colors import colorConverter

import plotly.graph_objs as go
from plotly import tools
import plotly.figure_factory as ff
from plotly.offline import download_plotlyjs, init_notebook_mode, plot, iplot
init_notebook_mode(connected=True)

random_state=42
nb_start = dt.now()


    

In [2]:

    

from sklearn.cluster import KMeans


from sklearn.metrics import silhouette_samples, silhouette_score


    

In [ ]:

    




    

In [ ]:

    




    

In [3]:

    

%%bash

ls -l | grep iris
cat iris.csv | head -2
cat iris.csv | tail -1


    

    




-rw-rw-r-- 1 1000 1000     2701 May 13 15:09 iris.csv
-rw-r--r-- 1 root root    76961 May 28 04:49 iris.ipynb
5.1,3.5,1.4,0.2,0
4.9,3.0,1.4,0.2,0

In [4]:

    

df = pd.read_csv('iris.csv', header=None, names=['SepalLengthCm', 'SepalWidthCm', 'PetalLengthCm', 'PetalWidthCm', 'Species'])
df.info()


    

    




<class 'pandas.core.frame.DataFrame'>
RangeIndex: 150 entries, 0 to 149
Data columns (total 5 columns):
SepalLengthCm    150 non-null float64
SepalWidthCm     150 non-null float64
PetalLengthCm    150 non-null float64
PetalWidthCm     150 non-null float64
Species          150 non-null int64
dtypes: float64(4), int64(1)
memory usage: 5.9 KB

In [5]:

    

df.head()


    

    
Out[5]:







  

    

      

      
SepalLengthCm
      
SepalWidthCm
      
PetalLengthCm
      
PetalWidthCm
      
Species
    
  
  

    

      
0
      
5.1
      
3.5
      
1.4
      
0.2
      
0
    
    

      
1
      
4.9
      
3.0
      
1.4
      
0.2
      
0
    
    

      
2
      
4.7
      
3.2
      
1.3
      
0.2
      
0
    
    

      
3
      
4.6
      
3.1
      
1.5
      
0.2
      
0
    
    

      
4
      
5.0
      
3.6
      
1.4
      
0.2
      
0
    
  

In [6]:

    

df.tail()


    

    
Out[6]:







  

    

      

      
SepalLengthCm
      
SepalWidthCm
      
PetalLengthCm
      
PetalWidthCm
      
Species
    
  
  

    

      
145
      
6.7
      
3.0
      
5.2
      
2.3
      
2
    
    

      
146
      
6.3
      
2.5
      
5.0
      
1.9
      
2
    
    

      
147
      
6.5
      
3.0
      
5.2
      
2.0
      
2
    
    

      
148
      
6.2
      
3.4
      
5.4
      
2.3
      
2
    
    

      
149
      
5.9
      
3.0
      
5.1
      
1.8
      
2
    
  

In [ ]:

    




    

In [7]:

    

x = df.SepalLengthCm
y = df.SepalWidthCm
c = df.Species

trace = [go.Scatter(
    x = x,
    y = y,
    marker = dict(
        # color = col,
        color = c,
        colorscale='Viridis',
        colorbar=dict(
            title='Labels'
        ),
    ),
    name = 'data',
    mode = 'markers',
    hoverinfo = 'text',
    text = ['x: %s<br>y: %s<br>cluster %i' % (x_i, y_i, c_i) for x_i, y_i, c_i in zip(x, y, c)]
)]

layout = go.Layout(
    xaxis = dict({'title': 'x'}),
    yaxis = dict({'title': 'y'}),
    hovermode='closest',
)

fig = go.Figure(data=trace, layout=layout)
iplot(fig, layout)


    

In [8]:

    

x = df.PetalLengthCm
y = df.PetalWidthCm
c = df.Species

trace = [go.Scatter(
    x = x,
    y = y,
    marker = dict(
        # color = col,
        color = c,
        colorscale='Viridis',
        colorbar=dict(
            title='Labels'
        ),
    ),
    name = 'data',
    mode = 'markers',
    hoverinfo = 'text',
    text = ['x: %s<br>y: %s<br>cluster %i' % (x_i, y_i, c_i) for x_i, y_i, c_i in zip(x, y, c)]
)]

layout = go.Layout(
    xaxis = dict({'title': 'x'}),
    yaxis = dict({'title': 'y'}),
    hovermode='closest',
)

fig = go.Figure(data=trace, layout=layout)
iplot(fig, layout)


    

In [ ]:

    




    

In [ ]:

    




    

In [ ]:

    




    

In [ ]:

    




    

In [ ]:

    




    

In [ ]:

    




    

In [ ]:

    




    

In [ ]:

    




    

In [9]:

    

nb_end = dt.now()

'Time elapsed: %s' % (nb_end - nb_start)


    

    
Out[9]:





'Time elapsed: 0:00:01.158076'

In [ ]: