def ensemble_models(data, args):
# split, train, test
data.process()
dense_out = len(data.labels[0])
# split for all models
X_train_, X_test_, Y_train, Y_test = train_test_split(data.text, data.labels,
test_size=0.20, random_state=42)
# Prep data for the LSTM model
tokenizer = Tokenizer(num_words=max_fatures, split=' ')
tokenizer.fit_on_texts(X_train_)
X_train = tokenizer.texts_to_sequences(X_train_)
X_train = pad_sequences(X_train, maxlen=max_len)
X_test = tokenizer.texts_to_sequences(X_test_)
X_test = pad_sequences(X_test, maxlen=max_len)
# Train the LSTM model
lstm_model = simple_lstm(max_fatures, dense_out, X_train.shape[1], embed_dim, lstm_out)
model_hist = lstm_model.fit(X_train, Y_train, epochs=args.epochs, batch_size=batch_size,
verbose=1, validation_data=(X_test, Y_test))
lstm_acc = model_hist.history['acc'][-1]
print("LSTM model accuracy ", lstm_acc)
# And make predictions using the LSTM model
lstm_predictions = lstm_model.predict(X_test)
# Now prep data for the one-hot CNN model
X_train_cnn = np.asarray([to_one_hot(x) for x in X_train_])
X_test_cnn = np.asarray([to_one_hot(x) for x in X_test_])
# And train the one-hot CNN classifier
model_cnn = one_hot_cnn(dense_out, max_len)
model_hist_cnn = model_cnn.fit(X_train_cnn, Y_train, batch_size=batch_size, epochs=args.epochs,
verbose=1, validation_data=(X_test_cnn, Y_test))
cnn_acc = model_hist_cnn.history['acc'][-1]
print("CNN model accuracy: ", cnn_acc)
# And make predictions
one_hot_cnn_predictions = model_cnn.predict(X_test_cnn)
# Using the accuracies create an ensemble
accuracies = [lstm_acc, cnn_acc]
norm_accuracies = [a / sum(accuracies) for a in accuracies]
print("Ensembling with weights: ")
for na in norm_accuracies:
print(na)
ensembled_predictions = simple_ensembler([lstm_predictions, one_hot_cnn_predictions],
norm_accuracies)
final_preds = np.argmax(ensembled_predictions, axis=1)
# Get the final accuracy
print(classification_report(np.argmax(Y_test, axis=1), final_preds,
target_names=data.labels_0.columns.values))
def run_loss(args):
data = args['data']
# For each run we want to get a new random balance
data.process()
# split, train, test
dense_out = len(data.labels[0])
# split for all models
X_train_, X_test_, Y_train, Y_test = train_test_split(data.text, data.labels,
test_size=0.20, random_state=42)
print(args)
# Prep data for the LSTM model
# This currently will train the tokenizer on all text (unbalanced and train/test)
# It would be nice to replace this with a pretrained embedding on larger text
tokenizer = Tokenizer(num_words=int(args['max_features']), split=' ')
tokenizer.fit_on_texts(data.all_text)
X_train = tokenizer.texts_to_sequences(X_train_)
X_train = pad_sequences(X_train, maxlen=max_len)
X_test = tokenizer.texts_to_sequences(X_test_)
X_test = pad_sequences(X_test, maxlen=max_len)
# Train the LSTM model
lstm_model = simple_lstm(int(args['max_features']), dense_out, X_train.shape[1],
int(args['embed_dim']), int(args['lstm_out']), args['dropout'])
if args['epochs'] == 0:
args['epochs'] = 1
es = EarlyStopping(monitor='val_acc', min_delta=0, patience=6, verbose=0, mode='max')
model_hist = lstm_model.fit(X_train, Y_train, epochs=args['epochs'], batch_size=batch_size,
verbose=1, validation_data=(X_test, Y_test), callbacks=[es])
lstm_acc = model_hist.history['val_acc'][-1]
print("LSTM model accuracy ", lstm_acc)
# This minimizes, so the maximize we have to take the inverse :)
return 1 - lstm_acc