from sklearn.externals.six import StringIO  
from IPython.display import Image  
from sklearn.tree import export_graphviz
import pydotplus

#split into train and test 
df_iris_train,df_iris_test = train_test_split(df_iris, petal_width > 5.5)

#build and train the classifier
dt_model = sktree.DecisionTreeClassifier(max_depth=1,
                                         criterion='entropy')
#given first 4 columns, learn the species
dt_model.fit(df_iris_train.ix[:,:4],df_iris_train.species)

dot_data = StringIO()
export_graphviz(dt_model, out_file=dot_data,  
                filled=True, rounded=True,
                special_characters=True)
graph = pydotplus.graph_from_dot_data(dot_data.getvalue())  
Image(graph.create_png())

#Deploying a decision tree
#this is testing the model 
predicted_labels = dt_model.predict(df_iris_test.ix[:,:4])
df_iris_test['predicted_label_tree'] = predicted_labels
df_iris_test.sample(10)

#Determine the overall accuracy
from sklearn.metrics import accuracy_score
accuracy = accuracy_score(df_iris_test.species, predicted_labels)
print("Accuracy: {0:.2%}".format(accuracy))

#utility class to compare the predictions versus ground truth
def comparePlot(input_frame,real_column,predicted_column):
    df_a = input_frame.copy()
    df_b = input_frame.copy()
    df_a['label_source'] = 'Species'
    df_b['label_source'] = 'Classifier'
    df_a['label'] = df_a[real_column]
    df_b['label'] = df_b[predicted_column].apply(lambda x: 'Predict %s'%x)
    df_c = pd.concat((df_a, df_b), axis=0, ignore_index=True)
    sns.lmplot(x='sepal_length', y='sepal_width', col='label_source',
               hue='label', data=df_c, fit_reg=False, size=4);

#see the difference
comparePlot(df_iris_test,"species","predicted_label_tree")