from sklearn.metrics import accuracy_score
import sklearn.ensemble as skens

# build a random forest
rf_model = skens.RandomForestClassifier(n_estimators=10,oob_score=True, criterion='entropy')
rf_model.fit(df_iris_train.ix[:,:4],df_iris_train.species)

# predict the model 
predicted_labels = rf_model.predict(df_iris_test.ix[:,:4])
df_iris_test['predicted_rf_tree'] = predicted_labels

# find accuracy score
accuracy = accuracy_score(df_iris_test.species, predicted_labels)

# 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);

# compare plot
comparePlot(df_iris_test,"species","predicted_rf_tree")