While executing this script, I get the following Typerror. From debug I see that the training dataset, test datasets are not NoneType. Please help me fix this issue.
modeling_time_series_transformer.py", line 1378, in forward
transformer_inputs, loc, scale, static_feat = self.create_network_inputs(
File “.venv\Lib\site-packages\transformers\models\time_series_transformer\modeling_time_series_transformer.py”, line 1252, in create_network_inputs
torch.cat(
TypeError: expected Tensor as element 1 in argument 0, but got NoneType
import pandas as pd
import numpy as np
from transformers import TimeSeriesTransformerModel, TimeSeriesTransformerConfig, Trainer, TrainingArguments, default_data_collator
from sklearn.preprocessing import MinMaxScaler, OneHotEncoder
from sklearn.metrics import mean_squared_error
import torch
from torch.utils.data import Dataset
# Load the CSV file
file_path = './spy-stock-price - Spy_Ind_Signal.csv'
data = pd.read_csv(file_path)
# Exclude specified columns
exclude_columns = ['20SMA','50SMA','200SMA','20EMA','10EMA','AVWAP']
data = data.drop(columns=exclude_columns)
# Preprocess the data
data['Date'] = pd.to_datetime(data['Date'])
data = data.sort_values('Date')
data_transformed = data
# Drop the 'Date' column
data_transformed = data_transformed.drop(columns=['Date'])
# Normalize the dataset
scaler = MinMaxScaler(feature_range=(0, 1))
scaled_data = scaler.fit_transform(data_transformed)
# Convert the data to a supervised learning problem
def create_dataset(data, look_back=1):
X, Y = [], []
for i in range(len(data) - look_back - 1):
a = data[i:(i + look_back)]
X.append(a)
Y.append(data[i + look_back, -1:]) # Include the last two columns as targets
if Y[-1] is None:
print(f"NoneType found at index {i + look_back}")
print(f"data shape: {data.shape}")
print(f"data[{i + look_back}] = {data[i + look_back]}")
return np.array(X), np.array(Y)
look_back = 3
X, y = create_dataset(scaled_data, look_back)
# Split into train and test sets
train_size = int(len(X) * 0.67)
X_train, X_test = X[0:train_size], X[train_size:]
y_train, y_test = y[0:train_size], y[train_size:]
# Reshape input to be [samples, time steps, features]
X_train = np.reshape(X_train, (X_train.shape[0], X_train.shape[1], data_transformed.shape[1]))
X_test = np.reshape(X_test, (X_test.shape[0], X_test.shape[1], data_transformed.shape[1]))
# Create observed mask for the transformer model
def create_observed_mask(data):
mask = np.ones_like(data, dtype=np.float32)
return mask
train_observed_mask = create_observed_mask(X_train)
test_observed_mask = create_observed_mask(X_test)
# Convert data to PyTorch tensors
X_train = torch.tensor(X_train, dtype=torch.float32)
X_test = torch.tensor(X_test, dtype=torch.float32)
y_train = torch.tensor(y_train, dtype=torch.float32)
y_test = torch.tensor(y_test, dtype=torch.float32)
train_observed_mask = torch.tensor(train_observed_mask, dtype=torch.float32)
test_observed_mask = torch.tensor(test_observed_mask, dtype=torch.float32)
# Create a custom dataset class
class TimeSeriesDataset(Dataset):
def __init__(self, X, y, observed_mask):
self.X = X
self.y = y
self.observed_mask = observed_mask
def __len__(self):
return len(self.X)
def __getitem__(self, idx):
sample = {
'past_values': self.X[idx],
'past_time_features': self.X[idx], # Assuming no extra time features, just using past values
'past_observed_mask': self.observed_mask[idx],
'future_values': self.y[idx], # Correct shape for future values
}
print(f"Sample {idx} - past_values shape: {sample['past_values'].shape}, past_time_features shape: {sample['past_time_features'].shape}, past_observed_mask shape: {sample['past_observed_mask'].shape}, future_values shape: {sample['future_values'].shape}")
return sample
train_dataset = TimeSeriesDataset(X_train, y_train, train_observed_mask)
test_dataset = TimeSeriesDataset(X_test, y_test, test_observed_mask)
# Model configuration
config = TimeSeriesTransformerConfig(
prediction_length=1,
context_length=look_back,
lags_seq=[1, 2, 3],
input_size=data_transformed.shape[1],
output_size=1, # Predicting both price_change and bull_bear_signal
num_time_features=1, # No extra time features
num_static_categorical_features=0,
num_static_real_features=0,
cardinality=[],
embedding_dimension=[]
)
model = TimeSeriesTransformerModel(config)
# Training configuration
training_args = TrainingArguments(
output_dir="./results",
eval_strategy="epoch",
learning_rate=1e-4,
per_device_train_batch_size=16,
per_device_eval_batch_size=16,
num_train_epochs=10,
weight_decay=0.01,
logging_dir="./logs",
)
# Training
trainer = Trainer(
model=model,
args=training_args,
train_dataset=train_dataset,
eval_dataset=test_dataset,
data_collator=default_data_collator,
)
# Training
trainer.train()
# Evaluation
predictions, labels, _ = trainer.predict(test_dataset)
# Inverse transform the predictions and labels
predictions = scaler.inverse_transform(predictions)
labels = scaler.inverse_transform(y_test.numpy())
# Separate the predictions and labels for price_change and bull_bear_signal
predictions_bull_bear_signal = predictions[:, 0]
labels_bull_bear_signal = labels[:, 0]
# For bull_bear_signal, we can use accuracy as the metric
accuracy_bull_bear_signal = np.mean(predictions_bull_bear_signal.round() == labels_bull_bear_signal.round())
print(f"Accuracy for Bull Bear Signal: {accuracy_bull_bear_signal}")