notebook.community

Edit and run



In [1]:

    
import pandas as pd
import matplotlib.pyplot as plt
import matplotlib
%matplotlib inline
from pandas.tools.plotting import parallel_coordinates



In [ ]:

    
a









    



---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-1-60b725f10c9c> in <module>()
----> 1 a

NameError: name 'a' is not defined



In [2]:

    
# TODO: Load up the Seeds Dataset into a Dataframe
# It's located at 'Datasets/wheat.data'
# 
# .. your code here ..



In [3]:

    
# TODO: Create a slice of your dataframe (call it s1)
# that only includes the 'area' and 'perimeter' features
# 
# .. your code here ..



In [4]:

    
df = pd.read_csv('Datasets/wheat.data')
df.head(5)









    Out[4]:






  
    
      
      id
      area
      perimeter
      compactness
      length
      width
      asymmetry
      groove
      wheat_type
    
  
  
    
      0
      0
      15.26
      14.84
      0.8710
      5.763
      3.312
      2.221
      5.220
      kama
    
    
      1
      1
      14.88
      14.57
      0.8811
      5.554
      3.333
      1.018
      4.956
      kama
    
    
      2
      2
      14.29
      14.09
      0.9050
      5.291
      3.337
      2.699
      4.825
      kama
    
    
      3
      3
      13.84
      13.94
      0.8955
      5.324
      3.379
      2.259
      4.805
      kama
    
    
      4
      4
      16.14
      14.99
      0.9034
      5.658
      3.562
      1.355
      5.175
      kama



In [5]:

    
dfsli1 = df[['area','perimeter']]
dfsli1.head(5)



In [6]:

    
# TODO: Create another slice of your dataframe (call it s2)
# that only includes the 'groove' and 'asymmetry' features
# 
# .. your code here ..



In [7]:

    
dfsli2 = df[['groove','asymmetry']]
dfsli2.head(5)



In [8]:

    
# TODO: Create a histogram plot using the first slice,
# and another histogram plot using the second slice.
# Be sure to set alpha=0.75
# 
# .. your code here ..


# Display the graphs:



In [9]:

    
# Look pretty...
# matplotlib.style.use('ggplot')
plt.style.use('ggplot')
dfsli1.plot.hist(alpha = 0.75)









    Out[9]:





<matplotlib.axes._subplots.AxesSubplot at 0x197b3d3b048>



In [10]:

    
dfsli2.plot.hist(alpha = 0.75)









    Out[10]:





<matplotlib.axes._subplots.AxesSubplot at 0x197b41b7e10>



In [11]:

    
df.plot.scatter(x = 'area', y = 'perimeter')









    Out[11]:





<matplotlib.axes._subplots.AxesSubplot at 0x197b42a5a58>



In [12]:

    
df.plot.scatter(x = 'groove', y = 'asymmetry')









    Out[12]:





<matplotlib.axes._subplots.AxesSubplot at 0x197b42f2be0>



In [13]:

    
df.plot.scatter(x = 'compactness', y = 'width')









    Out[13]:





<matplotlib.axes._subplots.AxesSubplot at 0x197b43592e8>



In [14]:

    
from mpl_toolkits.mplot3d import Axes3D



In [15]:

    
fig = plt.figure()
ax = fig.add_subplot(111, projection = '3d')
ax.set_xlabel('area')
ax.set_ylabel('perimeter')
ax.set_zlabel('asymmetry')
ax.scatter(df.area, df.perimeter, df.asymmetry, c='red', marker='*')









    Out[15]:





<mpl_toolkits.mplot3d.art3d.Path3DCollection at 0x197b546f278>



In [16]:

    
fig = plt.figure()
ax = fig.add_subplot(111, projection = '3d')
ax.set_xlabel('width')
ax.set_ylabel('groove')
ax.set_zlabel('length')
ax.scatter(df.width, df.groove, df.length, c='green', marker='*')









    Out[16]:





<mpl_toolkits.mplot3d.art3d.Path3DCollection at 0x197b59450f0>



In [17]:

    
del df['id']
plt.figure()
parallel_coordinates(df, 'wheat_type')









    Out[17]:





<matplotlib.axes._subplots.AxesSubplot at 0x197b5965b00>

	id	area	perimeter	compactness	length	width	asymmetry	groove	wheat_type
0	0	15.26	14.84	0.8710	5.763	3.312	2.221	5.220	kama
1	1	14.88	14.57	0.8811	5.554	3.333	1.018	4.956	kama
2	2	14.29	14.09	0.9050	5.291	3.337	2.699	4.825	kama
3	3	13.84	13.94	0.8955	5.324	3.379	2.259	4.805	kama
4	4	16.14	14.99	0.9034	5.658	3.562	1.355	5.175	kama