In [230]:

    

# Read all the comments, the first approach is taken to highlight a wrong approach
import pandas as pd
import matplotlib.pyplot as plt
from sklearn import datasets
%matplotlib inline


    

In [231]:

    

iris = datasets.load_iris()
iris_pd=pd.DataFrame(iris.data)


    

In [232]:

    

iris_pd.head()


    

    
Out[232]:






  

    

      

      
0
      
1
      
2
      
3
    
  
  

    

      
0
      
5.1
      
3.5
      
1.4
      
0.2
    
    

      
1
      
4.9
      
3.0
      
1.4
      
0.2
    
    

      
2
      
4.7
      
3.2
      
1.3
      
0.2
    
    

      
3
      
4.6
      
3.1
      
1.5
      
0.2
    
    

      
4
      
5.0
      
3.6
      
1.4
      
0.2
    
  

In [233]:

    

iris.keys()


    

    
Out[233]:





dict_keys(['target', 'target_names', 'DESCR', 'feature_names', 'data'])

In [234]:

    

iris_pd.columns=iris.feature_names
iris_pd.head()


    

    
Out[234]:






  

    

      

      
sepal length (cm)
      
sepal width (cm)
      
petal length (cm)
      
petal width (cm)
    
  
  

    

      
0
      
5.1
      
3.5
      
1.4
      
0.2
    
    

      
1
      
4.9
      
3.0
      
1.4
      
0.2
    
    

      
2
      
4.7
      
3.2
      
1.3
      
0.2
    
    

      
3
      
4.6
      
3.1
      
1.5
      
0.2
    
    

      
4
      
5.0
      
3.6
      
1.4
      
0.2
    
  

In [235]:

    

# The Iris Setosa from wiki pulled out
from IPython.display import Image
url = 'http://upload.wikimedia.org/wikipedia/commons/5/56/Kosaciec_szczecinkowaty_Iris_setosa.jpg'
Image(url,width=300, height=300)


    

    
Out[235]:

In [236]:

    

# The Iris Versicolor from Wiki pull out
from IPython.display import Image
url = 'http://upload.wikimedia.org/wikipedia/commons/4/41/Iris_versicolor_3.jpg'
Image(url,width=300, height=300)


    

    
Out[236]:

In [237]:

    

# The Iris Virginica from wiki pull out
from IPython.display import Image
url = 'http://upload.wikimedia.org/wikipedia/commons/9/9f/Iris_virginica.jpg'
Image(url,width=300, height=300)


    

    
Out[237]:

In [238]:

    

from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y)


    

In [239]:

    

# Incorrect approch as we are not seperating the predicted variable
# from sklearn import svm
from sklearn.svm import SVC
svc_model = SVC()
svc_model.fit(X_train,y_train)


    

    
Out[239]:





SVC(C=1.0, cache_size=200, class_weight=None, coef0=0.0,
  decision_function_shape=None, degree=3, gamma='auto', kernel='rbf',
  max_iter=-1, probability=False, random_state=None, shrinking=True,
  tol=0.001, verbose=False)

In [240]:

    

predictions = svc_model.predict(X_test)
from sklearn.metrics import classification_report,confusion_matrix
print(confusion_matrix(y_test,predictions))


    

    




[[13  0  0]
 [ 0 13  0]
 [ 0  0 12]]

In [241]:

    

# Print confusion Matrix


    

In [242]:

    

print(classification_report(y_test,predictions))
# Wrong prediction as we have not dropped the predicted variable


    

    




             precision    recall  f1-score   support

     setosa       1.00      1.00      1.00        13
 versicolor       1.00      1.00      1.00        13
  virginica       1.00      1.00      1.00        12

avg / total       1.00      1.00      1.00        38

In [243]:

    

# Correct approach below
#import seaborn as sns
iris = sns.load_dataset('iris')


    

In [244]:

    

import pandas as pd
import matplotlib.pyplot as plt
%matplotlib inline


    

In [245]:

    

# Setosa is the most separable. 
sns.pairplot(iris,hue='species',palette='Dark2')


    

    
Out[245]:





<seaborn.axisgrid.PairGrid at 0x22085864b00>






    

In [246]:

    

from sklearn.model_selection import train_test_split


    

In [247]:

    

import seaborn as sns
iris = sns.load_dataset('iris')
X = iris.drop('species',axis=1)
y = iris['species']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.30)


    

In [248]:

    

from sklearn.svm import SVC


    

In [249]:

    

svc_model = SVC()


    

In [250]:

    

svc_model.fit(X_train,y_train)


    

    
Out[250]:





SVC(C=1.0, cache_size=200, class_weight=None, coef0=0.0,
  decision_function_shape=None, degree=3, gamma='auto', kernel='rbf',
  max_iter=-1, probability=False, random_state=None, shrinking=True,
  tol=0.001, verbose=False)

In [251]:

    

predictions = svc_model.predict(X_test)


    

In [252]:

    

from sklearn.metrics import classification_report,confusion_matrix


    

In [253]:

    

print(confusion_matrix(y_test,predictions))


    

    




[[21  0  0]
 [ 0 13  1]
 [ 0  0 10]]

In [254]:

    

print(classification_report(y_test,predictions))


    

    




             precision    recall  f1-score   support

     setosa       1.00      1.00      1.00        21
 versicolor       1.00      0.93      0.96        14
  virginica       0.91      1.00      0.95        10

avg / total       0.98      0.98      0.98        45

In [ ]:

    

# Good prediction after column dropped at 98%