In [1]:

    

%matplotlib inline
import sys
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import math
import os


    

In [2]:

    

# Dataset: https://archive.ics.uci.edu/ml/datasets/Iris/
# IRIS Dataset Size: 150 samples
# Train: 70%  Eval: 30%


    

In [3]:

    

df = pd.read_csv('../Data/ClassExamples/Iris/iris.data.csv')


    

In [4]:

    

df.head()


    

    
Out[4]:







  

    

      

      
sepal_length
      
sepal_width
      
petal_length
      
petal_width
      
class
    
  
  

    

      
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 [5]:

    

df.tail()


    

    
Out[5]:







  

    

      

      
sepal_length
      
sepal_width
      
petal_length
      
petal_width
      
class
    
  
  

    

      
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 [6]:

    

# Print first 5 index values and last 5 index values
index_list = list(df.index)
print(index_list[:5])
print(index_list[-5:])


    

    




[0, 1, 2, 3, 4]
[145, 146, 147, 148, 149]

In [7]:

    

# Randomize a list
np.random.seed(5)
np.random.shuffle(index_list)


    

In [8]:

    

print('Shuffled list')
print(index_list[:5])
print(index_list[-5:])


    

    




Shuffled list
[82, 134, 114, 42, 109]
[8, 73, 144, 118, 99]

In [9]:

    

# Dataframe is now shuffled
df = df.iloc[index_list]


    

In [10]:

    

df.head()


    

    
Out[10]:







  

    

      

      
sepal_length
      
sepal_width
      
petal_length
      
petal_width
      
class
    
  
  

    

      
82
      
5.8
      
2.7
      
3.9
      
1.2
      
Iris-versicolor
    
    

      
134
      
6.1
      
2.6
      
5.6
      
1.4
      
Iris-virginica
    
    

      
114
      
5.8
      
2.8
      
5.1
      
2.4
      
Iris-virginica
    
    

      
42
      
4.4
      
3.2
      
1.3
      
0.2
      
Iris-setosa
    
    

      
109
      
7.2
      
3.6
      
6.1
      
2.5
      
Iris-virginica
    
  

In [11]:

    

data_path = '../Data/ClassExamples/Iris/'

df.to_csv(os.path.join(data_path, 'iris_data_train.csv'),
          index = True,
          index_label = 'Row',
          columns=['sepal_length',
                   'sepal_width',
                   'petal_length',
                   'petal_width',
                   'class'])


    

In [12]:

    

df.to_csv(os.path.join(data_path,'iris_data_classifier_test.csv'),
          index = True,
          index_label = 'Row',
          columns=['sepal_length',
                   'sepal_width',
                   'petal_length',
                   'petal_width'])


    

In [13]:

    

df['class'].value_counts()


    

    
Out[13]:





Iris-versicolor    50
Iris-setosa        50
Iris-virginica     50
Name: class, dtype: int64

In [14]:

    

df.describe()


    

    
Out[14]:







  

    

      

      
sepal_length
      
sepal_width
      
petal_length
      
petal_width
    
  
  

    

      
count
      
150.000000
      
150.000000
      
150.000000
      
150.000000
    
    

      
mean
      
5.843333
      
3.054000
      
3.758667
      
1.198667
    
    

      
std
      
0.828066
      
0.433594
      
1.764420
      
0.763161
    
    

      
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 [15]:

    

# Find all rows that match the condition.  Returns a Series that contains index value and True/False
setosa = df['class'] == 'Iris-setosa'


    

In [16]:

    

setosa.head()


    

    
Out[16]:





82     False
134    False
114    False
42      True
109    False
Name: class, dtype: bool

In [17]:

    

# Pull only setosa's
df[setosa].head()


    

    
Out[17]:







  

    

      

      
sepal_length
      
sepal_width
      
petal_length
      
petal_width
      
class
    
  
  

    

      
42
      
4.4
      
3.2
      
1.3
      
0.2
      
Iris-setosa
    
    

      
1
      
4.9
      
3.0
      
1.4
      
0.2
      
Iris-setosa
    
    

      
25
      
5.0
      
3.0
      
1.6
      
0.2
      
Iris-setosa
    
    

      
26
      
5.0
      
3.4
      
1.6
      
0.4
      
Iris-setosa
    
    

      
23
      
5.1
      
3.3
      
1.7
      
0.5
      
Iris-setosa
    
  

In [18]:

    

plt.hist(df.petal_length, )
plt.grid(True)
plt.xlabel('Petal Length')
plt.ylabel('Count')
plt.title('Petal Length Histogram')


    

    
Out[18]:





<matplotlib.text.Text at 0x1dd5bca7390>






    

In [19]:

    

plt.scatter(df.index, df.petal_length)
plt.grid(True)
plt.xlabel('Sample')
plt.ylabel('Petal Length')
plt.title('Petal Length Scatter Plot')


    

    
Out[19]:





<matplotlib.text.Text at 0x1dd5bec27b8>