Time Series Classification Module Development Tutorial¶

I. Overview¶

Time series classification involves identifying and categorizing different patterns in time series data by analyzing trends, periodicity, seasonality, and other factors that vary over time. This technique is widely used in medical diagnosis and other fields, effectively classifying key information in time series data to provide robust support for decision-making.

II. Supported Model List¶

Model Name	Model Download Link	Acc(%)	Model Size (M)	Description
TimesNet_cls	Inference Model/Trained Model	87.5	792K	TimesNet is an adaptive and high-accuracy time series classification model through multi-period analysis

Test Environment Description:

Performance Test Environment
Test Dataset: UWaveGestureLibrary.
Hardware Configuration:
- GPU: NVIDIA Tesla T4
- CPU: Intel Xeon Gold 6271C @ 2.60GHz
- Other Environments: Ubuntu 20.04 / cuDNN 8.6 / TensorRT 8.5.2.2
Inference Mode Description

Mode	GPU Configuration	CPU Configuration	Acceleration Technology Combination
Normal Mode	FP32 Precision / No TRT Acceleration	FP32 Precision / 8 Threads	PaddleInference
High-Performance Mode	Optimal combination of pre-selected precision types and acceleration strategies	FP32 Precision / 8 Threads	Pre-selected optimal backend (Paddle/OpenVINO/TRT, etc.)

III. Quick Integration¶

❗ Before quick integration, please install the PaddleX wheel package. For detailed instructions, refer to PaddleX Local Installation Guide

After installing the wheel package, you can perform inference for the time series classification module with just a few lines of code. You can switch models under this module freely, and you can also integrate the model inference of the time series classification module into your project. Before running the following code, please download the demo csv to your local machine.

from paddlex import create_model
model = create_model(model_name="TimesNet_cls")
output = model.predict("ts_cls.csv", batch_size=1)
for res in output:
    res.print()
    res.save_to_csv(save_path="./output/")
    res.save_to_json(save_path="./output/res.json")

After running, the result obtained is:

{
    "res": {
        "input_path": "ts_cls.csv",
        "classification": [
            {
                "classid": 0,
                "score": 0.617687881
            }
        ]
    }
}

The meanings of the parameters in the running results are as follows: - input_path: Indicates the path to the input time-series file for prediction. - classification: Indicates the time-series classification result. classid represents the predicted category, and score represents the prediction confidence. You can save the prediction results to a CSV file using res.save_to_csv() or to a JSON file using res.save_to_json().

Descriptions of related methods, parameters, etc., are as follows:

The create_model method instantiates a time-series classification model (using TimesNet_cls as an example). Specific descriptions are as follows:

Parameter	Description	Type	Options	Default Value
`model_name`	The name of the model	`str`	All model names supported by PaddleX	None
`model_dir`	The storage path of the model	`str`	None	None

The model_name must be specified. After specifying model_name, PaddleX's built-in model parameters are used by default. If model_dir is specified, the user-defined model is used.
The predict() method of the time-series classification model is called for inference prediction. The parameters of the predict() method are input and batch_size, with specific descriptions as follows:

Parameter	Description	Type	Options	Default Value
`input`	Data to be predicted, supporting multiple input types	`Python Var`/`str`/`list`	Python variable, such as time-series data represented by `pandas.DataFrame` File path, such as the local path of a time-series file: `/root/data/ts.csv` URL link, such as the network URL of a time-series file: Example Local directory, which must contain data files for prediction, such as the local path: `/root/data/` List, elements of the list must be of the above types, such as `[pandas.DataFrame, pandas.DataFrame]`, `[\"/root/data/ts1.csv\", \"/root/data/ts2.csv\"]`, `[\"/root/data1\", \"/root/data2\"]`, `[{\"ts\": \"/root/data1\"}, {\"ts\": \"/root/data2/ts.csv\"}]`	None
`batch_size`	Batch size	`int`	Any integer greater than 0	1

The prediction results are processed for each sample, with the prediction result being of type dict, and support operations such as printing, saving as a csv file, and saving as a json file:

Method	Description	Parameter	Type	Explanation	Default Value
`print()`	Print the result to the terminal	`format_json`	`bool`	Whether to format the output content with `JSON` indentation	`True`
		`indent`	`int`	Specify the indentation level to beautify the output `JSON` data, making it more readable. Only effective when `format_json` is `True`	4
		`ensure_ascii`	`bool`	Control whether non-`ASCII` characters are escaped to `Unicode`. When set to `True`, all non-`ASCII` characters will be escaped; `False` retains the original characters. Only effective when `format_json` is `True`	`False`
`save_to_json()`	Save the result as a `json` file	`save_path`	`str`	The file path for saving. When a directory is provided, the saved file name matches the input file name	None
		`indent`	`int`	Specify the indentation level to beautify the output `JSON` data, making it more readable. Only effective when `format_json` is `True`	4
		`ensure_ascii`	`bool`	Control whether non-`ASCII` characters are escaped to `Unicode`. When set to `True`, all non-`ASCII` characters will be escaped; `False` retains the original characters. Only effective when `format_json` is `True`	`False`
`save_to_csv()`	Save the result as a time-series `csv` file	`save_path`	`str`	The file path for saving. When a directory is provided, the saved file name matches the input file name	None

Additionally, it also supports obtaining the visualized time-series with results and the prediction results via attributes, as follows:

Attribute	Description
`json`	Get the prediction result in `json` format
`csv`	Get the time-series classification prediction result in `csv` format

For more information on using PaddleX's single-model inference APIs, refer to PaddleX Single Model Python Script Usage Instructions.

IV. Custom Development¶

If you aim for higher accuracy with existing models, you can leverage PaddleX's custom development capabilities to develop better time series classification models. Before using PaddleX to develop time series classification models, ensure you have installed the PaddleTS plugin. Refer to the PaddleX Local Installation Guide for the installation process.

4.1 Data Preparation¶

Before model training, you need to prepare the dataset for the corresponding task module. PaddleX provides data validation functionality for each module, and only data that passes validation can be used for model training. Additionally, PaddleX provides demo datasets for each module, which you can use to complete subsequent development. If you wish to use private datasets for subsequent model training, refer to PaddleX Time Series Classification Task Module Data Annotation Tutorial.

4.1.1 Demo Data Download¶

You can use the following commands to download the demo dataset to a specified folder:

wget https://paddle-model-ecology.bj.bcebos.com/paddlex/data/ts_classify_examples.tar -P ./dataset
tar -xf ./dataset/ts_classify_examples.tar -C ./dataset/

4.1.2 Data Validation¶

You can complete data validation with a single command:

python main.py -c paddlex/configs/modules/ts_classification/TimesNet_cls.yaml \
    -o Global.mode=check_dataset \
    -o Global.dataset_dir=./dataset/ts_classify_examples

After executing the above command, PaddleX will validate the dataset, summarize its basic information, and print Check dataset passed ! in the log if the command runs successfully. The validation result file is saved in ./output/check_dataset_result.json, and related outputs are saved in the current directory's ./output/check_dataset directory, including example time series data and class distribution histograms.

👉 Validation Result Details (Click to Expand)

The specific content of the validation result file is:

{
  "done_flag": true,
  "check_pass": true,
  "attributes": {
    "train_samples": 82620,
    "train_table": [
      [
        "Unnamed: 0",
        "group_id",
        "dim_0",
        ...,
        "dim_60",
        "label",
        "time"
      ],
      [
        0.0,
        0.0,
        0.000949,
        ...,
        0.12107,
        1.0,
        0.0
      ]
    ],
    "val_samples": 83025,
    "val_table": [
      [
        "Unnamed: 0",
        "group_id",
        "dim_0",
        ...,
        "dim_60",
        "label",
        "time"
      ],
      [
        0.0,
        0.0,
        0.004578,
        ...,
        0.15728,
        1.0,
        0.0
      ]
    ]
  },
  "analysis": {
    "histogram": "check_dataset/histogram.png"
  },
  "dataset_path": "./dataset/ts_classify_examples",
  "show_type": "csv",
  "dataset_type": "TSCLSDataset"
}

The verification results above indicate that check_pass being True means the dataset format meets the requirements. Explanations for other indicators are as follows:

attributes.train_samples: The number of training samples in this dataset is 12194;
attributes.val_samples: The number of validation samples in this dataset is 3484;
attributes.train_sample_paths: A list of relative paths to the top 10 rows of training samples in this dataset;
attributes.val_sample_paths: A list of relative paths to the top 10 rows of validation samples in this dataset;

Furthermore, the dataset validation also involved an analysis of the distribution of sample numbers across all categories within the dataset, and a distribution histogram (histogram.png) was generated accordingly.

Note: Only data that has passed validation can be used for training and evaluation.

4.1.3 Dataset Format Conversion/Dataset Splitting (Optional)¶

After completing data validation, you can convert the dataset format and re-split the training/validation ratio by modifying the configuration file or appending hyperparameters.

👉 Details on Format Conversion/Dataset Splitting (Click to Expand)

(1) Dataset Format Conversion

Time-series classification supports converting xlsx and xls format datasets to csv format.

Parameters related to dataset validation can be set by modifying the fields under CheckDataset in the configuration file. Examples of some parameters in the configuration file are as follows:

CheckDataset:
convert:
enable: Whether to perform dataset format conversion, supporting conversion from xlsx and xls formats to CSV format, default is False;
src_dataset_type: If dataset format conversion is performed, the source dataset format does not need to be set, default is null;

To enable format conversion, modify the configuration as follows:

......
CheckDataset:
  ......
  convert:
    enable: True
    src_dataset_type: null
  ......

Then execute the command:

python main.py -c paddlex/configs/modules/ts_classification/TimesNet_cls.yaml \
    -o Global.mode=check_dataset \
    -o Global.dataset_dir=./dataset/ts_classify_examples

The above parameters can also be set by appending command line arguments:

python main.py -c paddlex/configs/modules/ts_classification/TimesNet_cls.yaml \
    -o Global.mode=check_dataset \
    -o Global.dataset_dir=./dataset/ts_classify_examples \
    -o CheckDataset.convert.enable=True

(2) Dataset Splitting

Parameters related to dataset validation can be set by modifying the fields under CheckDataset in the configuration file. Examples of some parameters in the configuration file are as follows:

CheckDataset:
convert:
enable: Whether to perform dataset format conversion, True to enable, default is False;
src_dataset_type: If dataset format conversion is performed, time-series classification only supports converting xlsx annotation files to csv, the source dataset format does not need to be set, default is null;
split:
enable: Whether to re-split the dataset, True to enable, default is False;
train_percent: If the dataset is re-split, the percentage of the training set needs to be set, an integer between 0-100, ensuring the sum with val_percent is 100;
val_percent: If the dataset is re-split, the percentage of the validation set needs to be set, an integer between 0-100, ensuring the sum with train_percent is 100;

For example, if you want to re-split the dataset with a 90% training set and a 10% validation set, modify the configuration file as follows:

......
CheckDataset:
  ......
  split:
    enable: True
    train_percent: 90
    val_percent: 10
  ......

Then execute the command:

python main.py -c paddlex/configs/modules/ts_classification/TimesNet_cls.yaml \
    -o Global.mode=check_dataset \
    -o Global.dataset_dir=./dataset/ts_classify_examples

After dataset splitting, the original annotation files will be renamed to xxx.bak in the original path.

The above parameters can also be set by appending command line arguments:

python main.py -c paddlex/configs/modules/ts_classification/TimesNet_cls.yaml \
    -o Global.mode=check_dataset \
    -o Global.dataset_dir=./dataset/ts_classify_examples \
    -o CheckDataset.split.enable=True \
    -o CheckDataset.split.train_percent=90 \
    -o CheckDataset.split.val_percent=10

4.2 Model Training¶

Model training can be completed with just one command. Here, we use the Time Series Forecasting model (TimesNet_cls) as an example:

python main.py -c paddlex/configs/modules/ts_classification/TimesNet_cls.yaml \
    -o Global.mode=train \
    -o Global.dataset_dir=./dataset/ts_classify_examples

You need to follow these steps:

Specify the .yaml configuration file path for the model (here it's TimesNet_cls.yaml,When training other models, you need to specify the corresponding configuration files. The relationship between the model and configuration files can be found in the PaddleX Model List (CPU/GPU)).
Set the mode to model training: -o Global.mode=train
Specify the training dataset path: -o Global.dataset_dir

Other related parameters can be set by modifying the Global and Train fields in the .yaml configuration file, or adjusted by appending parameters in the command line. For example, to train using the first two GPUs: -o Global.device=gpu:0,1; to set the number of training epochs to 10: -o Train.epochs_iters=10. For more modifiable parameters and their detailed explanations, refer to the PaddleX TS Configuration Parameters Documentation.

👉 More Details (Click to Expand)

During model training, PaddleX automatically saves model weight files, with the default path being output. To specify a different save path, use the -o Global.output field in the configuration file.
PaddleX abstracts the concepts of dynamic graph weights and static graph weights from you. During model training, both dynamic and static graph weights are produced, and static graph weights are used by default for model inference.
After model training, all outputs are saved in the specified output directory (default is ./output/), typically including:
train_result.json: Training result record file, including whether the training task completed successfully, produced weight metrics, and related file paths.
train.log: Training log file, recording model metric changes, loss changes, etc.
config.yaml: Training configuration file, recording the hyperparameters used for this training session.
best_accuracy.pdparams.tar, scaler.pkl, .checkpoints, .inference: Model weight-related files, including Model weight-related files, including network parameters, optimizers, and network architecture.

4.3 Model Evaluation¶

After completing model training, you can evaluate the specified model weights file on the validation set to verify the model's accuracy. Using PaddleX for model evaluation can be done with a single command:

python main.py -c paddlex/configs/modules/ts_classification/TimesNet_cls.yaml \
    -o Global.mode=evaluate \
    -o Global.dataset_dir=./dataset/ts_classify_examples

Similar to model training, the following steps are required:

Specify the path to the model's .yaml configuration file (here it's TimesNet_cls.yaml)
Specify the mode as model evaluation: -o Global.mode=evaluate
Specify the path to the validation dataset: -o Global.dataset_dir Other relevant parameters can be set by modifying the Global and Evaluate fields in the .yaml configuration file. For details, refer to PaddleX Time Series Task Model Configuration File Parameter Description.

👉 More Details (Click to Expand)

When evaluating the model, you need to specify the model weights file path. Each configuration file has a default weight save path built-in. If you need to change it, simply set it by appending a command line parameter, such as -o Evaluate.weight_path=./output/best_model/model.pdparams.

After completing the model evaluation, typically, the following outputs are generated:

Upon completion of model evaluation, an evaluate_result.json file is produced, which records the evaluation results, specifically whether the evaluation task was completed successfully and the model's evaluation metrics, including Top-1 Accuracy and F1 score.

4.4 Model Inference and Model Integration¶

After completing model training and evaluation, you can use the trained model weights for inference prediction or Python integration.

4.4.1 Model Inference¶

To perform inference prediction via the command line, simply use the following command:

Before running the following code, please download the demo csv to your local machine.

python main.py -c paddlex/configs/modules/ts_classification/TimesNet_cls.yaml \
    -o Global.mode=predict \
    -o Predict.model_dir="./output/inference" \
    -o Predict.input="ts_cls.csv"

Similar to model training and evaluation, the following steps are required:

Specify the path to the model's .yaml configuration file (here it's TimesNet_cls.yaml - Note: This should likely be TimesNet_cls.yaml for consistency)
Specify the mode as model inference prediction: -o Global.mode=predict
Specify the model weights path: -o Predict.model_dir="./output/inference"
Specify the input data path: -o Predict.input="..." Other relevant parameters can be set by modifying the Global and Predict fields in the .yaml configuration file. For details, refer to PaddleX Time Series Task Model Configuration File Parameter Description.

4.4.2 Model Integration¶

Models can be directly integrated into the PaddleX pipeline or directly into your own projects.

Pipeline Integration

The time series prediction module can be integrated into PaddleX pipelines such as Time Series Classification. Simply replace the model path to update the time series prediction model. In pipeline integration, you can use service deployment to deploy your trained model.

Module Integration

The weights you produce can be directly integrated into the time series classification module. Refer to the Python example code in Quick Integration (Note: This section header is in Chinese and should be translated or removed for consistency), simply replace the model with the path to your trained model.

You can also use the PaddleX high-performance inference plugin to optimize the inference process of your model and further improve efficiency. For detailed procedures, please refer to the PaddleX High-Performance Inference Guide.