Develop Reference

Bitcoin Price Prediction using LSTM

So I wanted to predict the future price of bitcoin using LSTM but as I am new to this domain I'm stuck at what to do in order to print just the price of future lets say I want to predict the price for 3 months ahead from now what should i do in order to just get the closing price for BTC after 3 months from now?
It will be really appreciated if you guys can help me with this problem.
train_data, test_data = train_test_split(df, test_size=test_size)
X_train = extract_window_data(train_data, window_len, zero_base)
X_test = extract_window_data(test_data, window_len, zero_base)
y_train = train_data[target_col][window_len:].values
y_test = test_data[target_col][window_len:].values
if zero_base:
y_train = y_train / train_data[target_col][:-window_len].values - 1
y_test = y_test / test_data[target_col][:-window_len].values - 1
return train_data, test_data, X_train, X_test, y_train, y_test
def build_lstm_model(input_data, output_size, neurons=100, activ_func='linear',
dropout=0.2, loss='mse', optimizer='adam'):
model = Sequential()
model.add(LSTM(neurons, input_shape=(input_data.shape[1], input_data.shape[2])))
model.add(Dropout(dropout))
model.add(Dense(units=output_size))
model.add(Activation(activ_func))
model.compile(loss=loss, optimizer=optimizer)
return model
np.random.seed(42)
window_len = 5
test_size = 0.2
zero_base = True
lstm_neurons = 100
epochs = 200
batch_size = 32
loss = 'mse'
dropout = 0.2
optimizer = 'adam'
train, test, X_train, X_test, y_train, y_test = prepare_data(
hist, target_col, window_len=window_len, zero_base=zero_base, test_size=test_size)
print(X_test)
model = build_lstm_model(
X_train, output_size=1, neurons=lstm_neurons, dropout=dropout, loss=loss,
optimizer=optimizer)
history = model.fit(
X_train, y_train, validation_data=(X_test, y_test), epochs=epochs, batch_size=batch_size, verbose=1, shuffle=True)
preds = test[target_col].values[:-window_len] * (preds + 1)
preds = pd.Series(index=targets.index, data=preds)
print(test)
line_plot(targets, preds, 'actual', 'prediction', lw=3)

how can i use cross validation in ensembling models (like voting)?

I am trying to use voting model in the ensembling methods, how can i add a cross validation to it?
Thanks
model_1 = SGD_cls=SGDClassifier(random_state=0)
model_2 = DecisionTreeClassifier(criterion='entropy', max_depth=12,max_leaf_nodes=35,splitter='best')
model_3 = GradientBoostingClassifier(n_estimators=100, random_state=42)
model_4 = MLPClassifier(random_state=42)
# model_3 = KNeighborsClassifier(n_neighbors=2)
X = df1.drop('product', axis = 1)
y = df1['product']
X_new = res_fit.transform(X)
#X_new =pd.DataFrame(X_new,columns = X.iloc[:,res_fit.support_].columns)
y_pred=cross_val_predict(model,X_new,y,cv=10)
X_train, X_test, y_train, y_test = train_test_split(X_new, y, test_size=0.25, random_state=42)
model_5 = VotingClassifier([('ADA', model_1),
('Tree', model_2),
('GradBoost',model_3),
('MLP',model_4)],
voting='hard')
for model in (model_1, model_2, model_3,model_4,model_5):
model.fit(X_train, y_train)
print(model.__class__.__name__, model.score(X_test, y_test))

Create dataframe serie from the prediction of a neural network

I am using a neural network. When I try to compare the predictions with the real values from the test set, I cannot do it because it does not let me create a dataframe with the predictions. So basicly I am not able to get test_predictions.shape = (10092,) instead o (10092,1). This "1" is causing me all the troubles. Can somebody help?
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.7, random_state=101)
model = keras.Sequential()
model.add(Dense(500,activation='relu'))
model.add(Dense(500,activation='relu'))
model.add(Dense(500,activation='relu'))
model.add(Dense(1))
model.compile(optimizer='rmsprop',loss = 'mse')
model.fit(X_train, y_train, epochs=100, batch_size=25, verbose=1, validation_split=0.2)
test_predictions = model.predict(X_test)
y_test = pd.Series(y_test)
test_predictions = pd.Series(test_predictions)

test_predictions = np.squeeze(test_predictions) should do the trick, it collapses all dimensions that have just one Element

Incompatible shapes in output layer - Tensorflow

I am trying to build a bi-LSTM model in tensorflow, environment google colab. In the training process, the model have an issue: the last layer says that there is shape incompatibility. I wonder if there is any way to reshape the x_train and y_train, to fix this problem
Traceback
ValueError: Shapes (16, 11) and (16, 10) are incompatible
If I change the value of the neurons units to my output layer, from 11 to 10, it does not give any error and the model can be trained. However, I want the output to be 10 and not 11.
# current output layer (run perfectly)
tf.keras.layers.Dense (11, activation = 'softmax')
# expected output layer (shape incompatibility)
tf.keras.layers.Dense (10, activation = 'softmax')
BiLSTM Model
def build_model(vocab_size, embedding_dim=64, input_length=30):
print('\nbuilding the model...\n')
model = tf.keras.Sequential([
tf.keras.layers.Embedding(input_dim=(vocab_size + 1), output_dim=embedding_dim, input_length=input_length),
tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(rnn_units,return_sequences=True, dropout=0.2)),
tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(rnn_units,return_sequences=True, dropout=0.2)),
tf.keras.layers.GlobalMaxPool1D(),
tf.keras.layers.Dropout(0.1),
tf.keras.layers.Dense(64, activation='tanh'),
# softmax output layer
tf.keras.layers.Dense(10, activation='softmax')
])
# optimizer & loss
opt = 'RMSprop' #tf.optimizers.Adam(learning_rate=1e-4)
loss = 'categorical_crossentropy'
# Metrics
metrics = ['accuracy', 'AUC','Precision', 'Recall']
# compile model
model.compile(optimizer=opt,
loss=loss,
metrics=metrics)
model.summary()
return model
The BATCH_SIZE is set to 16. And the shapes of y_train and x_train are:
x_train.shape
(800, 30)
y_train.shape
(800,)
Training
def train(model, x_train, y_train, x_validation, y_validation,
epochs, batch_size=32, patience=5,
verbose=2, monitor_es='accuracy', mode_es='auto', restore=True,
monitor_mc='val_accuracy', mode_mc='max'):
print('\ntraining...\n')
# callback
early_stopping = tf.keras.callbacks.EarlyStopping(monitor=monitor_es,
verbose=1, mode=mode_es, restore_best_weights=restore,
min_delta=1e-3, patience=patience)
model_checkpoint = tf.keras.callbacks.ModelCheckpoint('tfjsmode.h5', monitor=monitor_mc, mode=mode_mc,
verbose=1, save_best_only=True)
# Define Tensorboard as a Keras callback
tensorboard = TensorBoard(
log_dir='./logs',
histogram_freq=1,
write_images=True
)
keras_callbacks = [tensorboard, early_stopping, model_checkpoint]
# train model
history = model.fit(x_train, y_train,
batch_size=batch_size, epochs=epochs, verbose=verbose,
validation_data=(x_validation, y_validation),
callbacks=keras_callbacks)
return history
Preprocessing
def preprocess(x, padding_shape=30):
return np.array([ord(i.lower()) - ord('a')+1 if not i.isdigit() and i != ' ' else 0 for i in list(x)] + ([0] * (padding_shape - len(x))), dtype=int)
def prepare_dataset(labeldict : dict, test_size=.3, validation_size=.1):
print('preparing the dataset...\n')
from sklearn import preprocessing
# load dataset
# split dataset (as string into panda.core.series.Serie object)
x, y = load_clean_dataset()
x = np.array(list(map(preprocess, x)))
y = np.array(list(map(lambda x: labeldict[x.replace(' ', '_')], y)))
print(('y: {}').format(y))
# create/split train, validation and test and shuffle the data
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=test_size, shuffle=True)
print(x.max(), x.min())
x_train_val, x_validation, y_train_val, y_validation = train_test_split(x_train, y_train, test_size=test_size, shuffle=True)
# pandas.core.series.Series to numpy array
x_train, y_train = np.array(x_train), np.array(y_train)
x_validation, y_validation = np.array(x_validation), np.array(y_validation)
x_test, y_test = np.array(x_test), np.array(y_test)
x_train_val, y_train_val = np.array(x_train_val), np.array(y_train_val)
print(('\nx_train: \n{}\n\ny_train: \n{}').format(x_train_val, y_train_val))
y_train = tf.keras.utils.to_categorical(y, num_classes=10)
return (x_train, y_train), (x_validation, y_validation), (x_test, y_test), (x_train_val, y_train_val)

It seems you currently have labels as integers (i.e. not one-hot encoded vectors). For example your y seems to be like,
[0, 1, 8, 9, ....] # a vector of 800 elements
There's two ways to train a model on such data.
Alternative 1 (easiest I guess)
Use sparse_categorical_crossentropy as the loss function of the model
model.compile(optimizer=opt, loss='sparse_categorical_crossentropy', metrics=metrics)
Alternative 2
Convert your labels to one-hot encoded using,
y_onehot = tf.keras.utils.to_categorical(y, num_classes=10)
and then keep the loss of the model as categorical_crossentropy

Reverse one-hot encoded labels in XGBoost?

I'm trying to print the accuracy score for an XGBoost multilabel classifier. However, I'm stuck on this error:
ValueError: Classification metrics can't handle a mix of
multilabel-indicator and binary targets
I think y_test needs to not be one-hot encoded when passed to accuracy_score()? But everything I've tried creates more errors. Any idea how I get this to work?
Code:
X = X.reshape(X.shape[0], -1)
print(X.shape)
# Split the dataset
x_train, x_test, y_train, y_test = train_test_split(X, yy, test_size=0.2, random_state=42, stratify=y)
dtrain = xgb.DMatrix(data=x_train, label=y_train)
dtest = xgb.DMatrix(data=x_test, label=y_test)
eval_list = [(dtest, 'eval')]
# Train the model
params = {
'max_depth': 3,
'objective': 'multi:softmax',
'num_class': 3,
'tree_method':'gpu_hist'
}
# Train the model
model = xgb.train(params, dtrain, evals=eval_list, early_stopping_rounds=20, verbose_eval=True)
# Evaluate predictions
y_pred = model.predict(dtest)
predictions = [round(value) for value in y_pred]
accuracy = accuracy_score(y_test, predictions)
print("Accuracy: %.2f%%" % (accuracy * 100.0))

Adding argmax to y_test seemed to work:
accuracy = accuracy_score(y_test.argmax(axis=1), predictions)