In [62]:

    

#all imports, library setups here
import pandas as pd
import numpy as np
import matplotlib

from scipy import stats, integrate

import matplotlib.pyplot as plt
%matplotlib inline
import cufflinks as cf

import plotly
plotly.offline.init_notebook_mode()
import plotly.offline as py
import plotly.graph_objs as go
from plotly.graph_objs import *
print(pd.__version__)

import seaborn as sns
sns.set(color_codes=True)
#sns.set_context('poster')
plot_kwds = {'alpha' : 0.25, 's' : 80, 'linewidths':0}

import sklearn.cluster as cluster
import time


    

    












    




0.18.1

In [5]:

    

#loading iris.csv
df = pd.read_csv('iris.csv',sep=",",header='infer')


    

In [6]:

    

df.head(5)


    

    
Out[6]:






  

    

      

      
sepallength
      
sepalwidth
      
petallength
      
petalwidth
      
species
    
  
  

    

      
0
      
5.1
      
3.5
      
1.4
      
0.2
      
Iris-setosa
    
    

      
1
      
4.9
      
3.0
      
1.4
      
0.2
      
Iris-setosa
    
    

      
2
      
4.7
      
3.2
      
1.3
      
0.2
      
Iris-setosa
    
    

      
3
      
4.6
      
3.1
      
1.5
      
0.2
      
Iris-setosa
    
    

      
4
      
5.0
      
3.6
      
1.4
      
0.2
      
Iris-setosa
    
  

In [7]:

    

df.tail(5)


    

    
Out[7]:






  

    

      

      
sepallength
      
sepalwidth
      
petallength
      
petalwidth
      
species
    
  
  

    

      
145
      
6.7
      
3.0
      
5.2
      
2.3
      
Iris-virginica
    
    

      
146
      
6.3
      
2.5
      
5.0
      
1.9
      
Iris-virginica
    
    

      
147
      
6.5
      
3.0
      
5.2
      
2.0
      
Iris-virginica
    
    

      
148
      
6.2
      
3.4
      
5.4
      
2.3
      
Iris-virginica
    
    

      
149
      
5.9
      
3.0
      
5.1
      
1.8
      
Iris-virginica
    
  

In [12]:

    

df.describe()


    

    
Out[12]:






  

    

      

      
sepallength
      
sepalwidth
      
petallength
      
petalwidth
    
  
  

    

      
count
      
150.000000
      
150.000000
      
150.000000
      
150.000000
    
    

      
mean
      
5.843333
      
3.057333
      
3.758000
      
1.199333
    
    

      
std
      
0.828066
      
0.435866
      
1.765298
      
0.762238
    
    

      
min
      
4.300000
      
2.000000
      
1.000000
      
0.100000
    
    

      
25%
      
5.100000
      
2.800000
      
1.600000
      
0.300000
    
    

      
50%
      
5.800000
      
3.000000
      
4.350000
      
1.300000
    
    

      
75%
      
6.400000
      
3.300000
      
5.100000
      
1.800000
    
    

      
max
      
7.900000
      
4.400000
      
6.900000
      
2.500000
    
  

In [13]:

    

df.dtypes


    

    
Out[13]:





sepallength    float64
sepalwidth     float64
petallength    float64
petalwidth     float64
species         object
dtype: object

In [14]:

    

df.columns


    

    
Out[14]:





Index(['sepallength', 'sepalwidth', 'petallength', 'petalwidth', 'species'], dtype='object')

In [15]:

    

sl = df.sepallength.values
sw = df.sepalwidth.values
sp = df.species.values

pl = df.petallength.values
pw = df.petalwidth.values


    

In [16]:

    

plt.plot(sl,sw,"bo")
plt.xlabel("Sepal Length")
plt.ylabel("Sepal Width")
plt.show()


    

In [17]:

    

plt.plot(pl,pw,"go")
plt.xlabel("Petal Length")
plt.ylabel("Petal Width")
plt.show()


    

In [18]:

    

pivoted = pd.pivot_table(df,values='sepallength',columns='species',index='sepalwidth')
pivoted.plot()


    

    
Out[18]:





<matplotlib.axes._subplots.AxesSubplot at 0x119d9cac8>






    

In [19]:

    

pivoted = pd.pivot_table(df,values='petallength',columns='species',index='petalwidth')
pivoted.plot()


    

    
Out[19]:





<matplotlib.axes._subplots.AxesSubplot at 0x11a1a54a8>






    

In [20]:

    

sns.stripplot(x="sepallength",y="species",data=df,jitter=1)


    

    
Out[20]:





<matplotlib.axes._subplots.AxesSubplot at 0x11a1e1898>






    

In [21]:

    

sns.boxplot(x="sepallength",y="species",data=df)


    

    
Out[21]:





<matplotlib.axes._subplots.AxesSubplot at 0x11a8e6278>






    

In [22]:

    

#write cluster plot function to help us
def plot_clusters(data, algorithm, args, kwds):
    start_time = time.time()
    labels = algorithm(*args, **kwds).fit_predict(data)
    end_time = time.time()
    palette = sns.color_palette('deep', np.unique(labels).max() + 1)
    colors = [palette[x] if x >= 0 else (0.0, 0.0, 0.0) for x in labels]
    plt.scatter(data.T[0], data.T[1], c=colors, **plot_kwds)
    frame = plt.gca()
    frame.axes.get_xaxis().set_visible(False)
    frame.axes.get_yaxis().set_visible(False)
    plt.title('Clusters found by {}'.format(str(algorithm.__name__)), fontsize=24)
    plt.text(-0.5, 0.7, 'Clustering took {:.2f} s'.format(end_time - start_time), fontsize=14)


    

In [45]:

    

#let us massage our data into shape
cdf = df.drop('species',1)
cdf.head(5)
cdf = cdf.as_matrix()


    

In [60]:

    

#introduction to clustering
#k-means
#centroid based clustering
#step 1: specify number of clusters
#step 2: calculate centroids depending on a distance metric
#step 3: assign points to a cluster centroid depending on wcss
#step 4: calculate new centroid based on these observations
# what are the advantages and disadvantages

plot_clusters(cdf, cluster.KMeans, (), {'n_clusters':3})


    

In [58]:

    

#DBScan
#eps parameter = max distance between 2 points in same neighborhood
plot_clusters(cdf, cluster.DBSCAN, (), {'eps':0.5})


    

In [70]:

    

#graph based: affinity propagation
plot_clusters(cdf, cluster.AffinityPropagation, (), {'preference':-9.0, 'damping':0.80})