('feature_selection', SelectFromModel(LinearSVC(penalty="l2"))),
('classification', KNeighborsClassifier(n_neighbors=k, metric='manhattan'))
])
for i in range(10):
print "round %d %d" % (k, i)
train_data = data[train[i]]
train_labels = labels[[train[i]]]
cv_data = data[test[i]]
cv_labels = labels[test[i]]
#######TRAIN#####
# convert from panda frame to numpy matrix
nn.fit(train_data, train_labels.T[0].tolist())
# Scoring
cv_predicted = nn.predict(cv_data)
cv_mis_rate = s.misclassification_rate(np.array(cv_predicted, dtype=int), cv_labels.T[0])
cv_error.append(cv_mis_rate)
#Test set
test_predicted = nn.predict(test_data).tolist()
test_mis_rate = s.misclassification_rate(np.array(test_predicted, dtype=int), test_labels)
test_error.append(test_mis_rate)
#confusion matrix
if k == 1 :
print confusion_matrix(y_true= test_labels, y_pred=test_predicted, labels = np.unique(np.concatenate((test_labels, test_predicted), axis=1)).tolist())
#F1 score test set
f1score.append([f1_score(test_labels, test_predicted, average='micro'), k , 'Micro'])
f1score.append([f1_score(test_labels, test_predicted, average='macro'), k , 'Macro'])
total_cv_error.append([np.mean(np.abs(cv_error)), k, 'Cross Validation Set'])
for i in range(10):
print "round %d %d" % (k, i)
train_data = ndata.ix[train[i]]
test_data = ndata.ix[test[i]]
#######TRAIN#####
nn = NearestNeighborsClassifier(n_neighbors=k)
# convert from panda frame to numpy matrix
nn.fit(train_data[features].as_matrix(), train_data[target_feature].as_matrix())
train_predicted = nn.predict(train_data[features].as_matrix())
test_predicted = nn.predict(test_data[features].as_matrix())
# Scoring
test_mis_rate = s.misclassification_rate(np.array(test_predicted), test_data[target_feature].values.T[0])
train_mis_rate = s.misclassification_rate(np.array(train_predicted), train_data[target_feature].values.T[0])
test_error.append(test_mis_rate)
train_error.append(train_mis_rate)
total_train_error.append([np.mean(np.abs(train_error)), k, 1])
total_test_error.append([np.mean(np.abs(test_error)), k, 0])
np_stage = np.vstack((np.array(total_train_error), np.array(total_test_error)))
plot_data = DataFrame()
plot_data['x'] = np_stage[:, 1].astype(int)
plot_data['y'] = np_stage[:, 0]
plot_data['Train=1/Test=0'] = np_stage[:, 2].astype(int)
# plot_data = pd.read_csv('plot.csv')