Use XGBoost to forecast ticket sales (time series data).

[Instructions]

1. 1_Prepare_Train_Data.ipynb

Prepare training data.

Setting parameters:

• x_time_seq: length of time series

• input_filename: input data file path

• output_filename: output time series data file path

After the setting is completed, it can be executed.

2. 2_Train.ipynb

Train the XGBoost model.

Setting parameters:

• train_input_filename: input data file path

• model_filename: the path of the output model file

• scaler_filename: output normalized file path

• train_output_filename: the path of the output prediction file

• modelEstimators: the number of Estimators

After the setting is completed, it can be executed.

3. 3_Prepare_Inference_Data.ipynb

Prepare inference data.

Setting parameters:

• x_time_seq: length of time series

• input_filename: input data file path

• output_filename: output time series data file path

After the setting is completed, it can be executed.

4. 4_Inference.ipynb

Use the trained model to make inferences.

Setting parameters:

• inference_input_filename: input data file path

• model_filename: input model file path

• scaler_filename: input normalized file path

• inference_output_filename: the path of the output prediction file

After the setting is completed, it can be executed.

After execution, you can see the results of XGBoost inference.

Jupyter-Data-XGBoost-Regression-Time-Series-inference.png

This SDK is built in AppForAI - AI Dev Tools.

Purchase license separately: USD 600, permanent authorization, single APP authorization, single machine authorization, one-year activation, one-year download, one-year update, one-year email technical support.