How do I set up a baseline forecast to compare with my RNN models in Darts

1. Install Darts

bash
     pip install darts
     

2. Import Libraries

python
     import darts
     from darts.models import NaiveDrift, NaiveMean
     

3. Load and Preprocess Data

python
     df = pd.read_csv('your_data.csv')
     

4. Create Darts Time Series

python
     from darts import TimeSeries

     train_series = TimeSeries.from_dataframe(df, time_col='timestamp', value_cols='target')
     test_series = train_series.split_before(0.8)
     

5. Create Baseline Models

python
     naive_drift_model = NaiveDrift()
     naive_mean_model = NaiveMean()
     

6. Train Baseline Models

python
     naive_drift_model.fit(train_series)
     naive_mean_model.fit(train_series)
     

7. Evaluate Baseline Models

python
     naive_drift_mape = mape(naive_drift_model.predict(test_series), test_series)
     naive_mean_mape = mape(naive_mean_model.predict(test_series), test_series)

     print("Naive Drift MAPE:", naive_drift_mape)
     print("Naive Mean MAPE:", naive_mean_mape)
     

8. Compare with RNN Models

python
     # Evaluate your RNN models
     rnn_model = RNNModel(model="LSTM", hidden_dim=20, dropout=0.2, batch_size=16, n_epochs=300)
     rnn_model.fit(train_series)

     rnn_mape = mape(rnn_model.predict(test_series), test_series)
     print("RNN Model MAPE:", rnn_mape)

     # Compare the MAPE values
     if rnn_mape < naive_drift_mape:
         print("RNN Model performed better than Naive Drift.")
     elif rnn_mape < naive_mean_mape:
         print("RNN Model performed better than Naive Mean.")
     else:
         print("Baseline models performed better.")
     

Conclusion

Here is the complete code:

python
import darts
from darts.models import NaiveDrift, NaiveMean
from darts.metrics import mape

# Load and preprocess data
df = pd.read_csv('your_data.csv')
train_series = TimeSeries.from_dataframe(df, time_col='timestamp', value_cols='target')
test_series = train_series.split_before(0.8)

# Create baseline models
naive_drift_model = NaiveDrift()
naive_mean_model = NaiveMean()

# Train baseline models
naive_drift_model.fit(train_series)
naive_mean_model.fit(train_series)

# Evaluate baseline models
naive_drift_mape = mape(naive_drift_model.predict(test_series), test_series)
naive_mean_mape = mape(naive_mean_model.predict(test_series), test_series)

print("Naive Drift MAPE:", naive_drift_mape)
print("Naive Mean MAPE:", naive_mean_mape)

# Create and train RNN model
rnn_model = RNNModel(model="LSTM", hidden_dim=20, dropout=0.2, batch_size=16, n_epochs=300)
rnn_model.fit(train_series)

# Evaluate RNN model
rnn_mape = mape(rnn_model.predict(test_series), test_series)
print("RNN Model MAPE:", rnn_mape)

# Compare MAPE values
if rnn_mape < naive_drift_mape:
    print("RNN Model performed better than Naive Drift.")
elif rnn_mape < naive_mean_mape:
    print("RNN Model performed better than Naive Mean.")
else:
    print("Baseline models performed better.")

This code sets up and trains the baseline models, evaluates their performance, and compares it with your RNN model. You can adjust the hyperparameters and models to suit your specific forecasting task.