In [15]:

    

## make imports
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
import seaborn as sns
%matplotlib inline
sns.set(style="ticks", color_codes=True)

## load the iris data
iris = sns.load_dataset("iris")
g = sns.pairplot(iris)


    

In [19]:

    

g = sns.pairplot(iris, hue="species",palette="husl")


    

In [17]:

    

iris.info()


    

    




<class 'pandas.core.frame.DataFrame'>
RangeIndex: 150 entries, 0 to 149
Data columns (total 5 columns):
sepal_length    150 non-null float64
sepal_width     150 non-null float64
petal_length    150 non-null float64
petal_width     150 non-null float64
species         150 non-null object
dtypes: float64(4), object(1)
memory usage: 5.9+ KB

In [18]:

    

iris.head()


    

    
Out[18]:







  

    

      

      
sepal_length
      
sepal_width
      
petal_length
      
petal_width
      
species
    
  
  

    

      
0
      
5.1
      
3.5
      
1.4
      
0.2
      
setosa
    
    

      
1
      
4.9
      
3.0
      
1.4
      
0.2
      
setosa
    
    

      
2
      
4.7
      
3.2
      
1.3
      
0.2
      
setosa
    
    

      
3
      
4.6
      
3.1
      
1.5
      
0.2
      
setosa
    
    

      
4
      
5.0
      
3.6
      
1.4
      
0.2
      
setosa
    
  

In [20]:

    

iris.groupby('species').mean()


    

    
Out[20]:







  

    

      

      
sepal_length
      
sepal_width
      
petal_length
      
petal_width
    
    

      
species
      

      

      

      

    
  
  

    

      
setosa
      
5.006
      
3.428
      
1.462
      
0.246
    
    

      
versicolor
      
5.936
      
2.770
      
4.260
      
1.326
    
    

      
virginica
      
6.588
      
2.974
      
5.552
      
2.026
    
  

In [26]:

    

## make a histogram the pandas way
ax = iris["sepal_length"].plot(kind='hist')
ax.set_title("my title");


    

In [25]:

    

## make a histogram the matplotlib way
fig = plt.figure(figsize=(10,8))
ax = fig.add_subplot(1,1,1)
ax.hist(iris['sepal_length']);


    

In [ ]:

    

## clustering


# import some data to play with
#iris = datasets.load_iris()
#X = iris.data[:, :2]  # we only take the first two features.
#Y = iris.target