File size: 33,937 Bytes
f43af3c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 |
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"provenance": []
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"language_info": {
"name": "python"
}
},
"cells": [
{
"cell_type": "markdown",
"source": [
"[](https://colab.research.google.com/github/ant-research/EasyTemporalPointProcess/blob/main/notebooks/easytpp_3_train_eval.ipynb)\n",
"\n",
"# Tutorial 3：Training and Evaluation Pipeline in EasyTPP\n",
"\n",
"In this tutorial, we'll walk through the complete process of training and evaluating temporal point process (TPP) models using the **EasyTPP** framework.\n",
"\n",
"In this notebook, we will cover the following key aspects:\n",
"- **Data Preparation**: Loading and preprocessing event sequence data.\n",
"- **Model Training**: Configuring and training a Neural Hawkes Process (NHP) model.\n",
"- **Model Evaluation**: Assessing model performance using various metrics.\n",
"- **Visualization**: Analyzing and visualizing model predictions and results.\n",
"\n",
"We begin by installing the package"
],
"metadata": {
"id": "mprLutjnft_a"
}
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 1000
},
"collapsed": true,
"id": "aH28ufHMa-QU",
"outputId": "2e4ca8e1-41a4-4c44-deb5-9fc0a904a2fc"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Requirement already satisfied: easy-tpp in /usr/local/lib/python3.11/dist-packages (0.1.0)\n",
"Collecting easy-tpp\n",
" Downloading easy_tpp-0.1.2-py3-none-any.whl.metadata (533 bytes)\n",
"Requirement already satisfied: PyYAML>=5.1 in /usr/local/lib/python3.11/dist-packages (from easy-tpp) (6.0.2)\n",
"Requirement already satisfied: numpy in /usr/local/lib/python3.11/dist-packages (from easy-tpp) (2.0.2)\n",
"Requirement already satisfied: pandas in /usr/local/lib/python3.11/dist-packages (from easy-tpp) (2.2.2)\n",
"Requirement already satisfied: torch in /usr/local/lib/python3.11/dist-packages (from easy-tpp) (2.6.0+cu124)\n",
"Requirement already satisfied: tensorboard in /usr/local/lib/python3.11/dist-packages (from easy-tpp) (2.18.0)\n",
"Requirement already satisfied: packaging in /usr/local/lib/python3.11/dist-packages (from easy-tpp) (24.2)\n",
"Requirement already satisfied: datasets in /usr/local/lib/python3.11/dist-packages (from easy-tpp) (3.5.0)\n",
"Requirement already satisfied: omegaconf in /usr/local/lib/python3.11/dist-packages (from easy-tpp) (2.3.0)\n",
"Requirement already satisfied: filelock in /usr/local/lib/python3.11/dist-packages (from datasets->easy-tpp) (3.18.0)\n",
"Requirement already satisfied: pyarrow>=15.0.0 in /usr/local/lib/python3.11/dist-packages (from datasets->easy-tpp) (18.1.0)\n",
"Requirement already satisfied: dill<0.3.9,>=0.3.0 in /usr/local/lib/python3.11/dist-packages (from datasets->easy-tpp) (0.3.8)\n",
"Requirement already satisfied: requests>=2.32.2 in /usr/local/lib/python3.11/dist-packages (from datasets->easy-tpp) (2.32.3)\n",
"Requirement already satisfied: tqdm>=4.66.3 in /usr/local/lib/python3.11/dist-packages (from datasets->easy-tpp) (4.67.1)\n",
"Requirement already satisfied: xxhash in /usr/local/lib/python3.11/dist-packages (from datasets->easy-tpp) (3.5.0)\n",
"Requirement already satisfied: multiprocess<0.70.17 in /usr/local/lib/python3.11/dist-packages (from datasets->easy-tpp) (0.70.16)\n",
"Requirement already satisfied: fsspec<=2024.12.0,>=2023.1.0 in /usr/local/lib/python3.11/dist-packages (from fsspec[http]<=2024.12.0,>=2023.1.0->datasets->easy-tpp) (2024.12.0)\n",
"Requirement already satisfied: aiohttp in /usr/local/lib/python3.11/dist-packages (from datasets->easy-tpp) (3.11.15)\n",
"Requirement already satisfied: huggingface-hub>=0.24.0 in /usr/local/lib/python3.11/dist-packages (from datasets->easy-tpp) (0.30.1)\n",
"Requirement already satisfied: antlr4-python3-runtime==4.9.* in /usr/local/lib/python3.11/dist-packages (from omegaconf->easy-tpp) (4.9.3)\n",
"Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.11/dist-packages (from pandas->easy-tpp) (2.8.2)\n",
"Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.11/dist-packages (from pandas->easy-tpp) (2025.2)\n",
"Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.11/dist-packages (from pandas->easy-tpp) (2025.2)\n",
"Requirement already satisfied: absl-py>=0.4 in /usr/local/lib/python3.11/dist-packages (from tensorboard->easy-tpp) (1.4.0)\n",
"Requirement already satisfied: grpcio>=1.48.2 in /usr/local/lib/python3.11/dist-packages (from tensorboard->easy-tpp) (1.71.0)\n",
"Requirement already satisfied: markdown>=2.6.8 in /usr/local/lib/python3.11/dist-packages (from tensorboard->easy-tpp) (3.7)\n",
"Requirement already satisfied: protobuf!=4.24.0,>=3.19.6 in /usr/local/lib/python3.11/dist-packages (from tensorboard->easy-tpp) (5.29.4)\n",
"Requirement already satisfied: setuptools>=41.0.0 in /usr/local/lib/python3.11/dist-packages (from tensorboard->easy-tpp) (75.2.0)\n",
"Requirement already satisfied: six>1.9 in /usr/local/lib/python3.11/dist-packages (from tensorboard->easy-tpp) (1.17.0)\n",
"Requirement already satisfied: tensorboard-data-server<0.8.0,>=0.7.0 in /usr/local/lib/python3.11/dist-packages (from tensorboard->easy-tpp) (0.7.2)\n",
"Requirement already satisfied: werkzeug>=1.0.1 in /usr/local/lib/python3.11/dist-packages (from tensorboard->easy-tpp) (3.1.3)\n",
"Requirement already satisfied: typing-extensions>=4.10.0 in /usr/local/lib/python3.11/dist-packages (from torch->easy-tpp) (4.13.0)\n",
"Requirement already satisfied: networkx in /usr/local/lib/python3.11/dist-packages (from torch->easy-tpp) (3.4.2)\n",
"Requirement already satisfied: jinja2 in /usr/local/lib/python3.11/dist-packages (from torch->easy-tpp) (3.1.6)\n",
"Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.4.127 in /usr/local/lib/python3.11/dist-packages (from torch->easy-tpp) (12.4.127)\n",
"Requirement already satisfied: nvidia-cuda-runtime-cu12==12.4.127 in /usr/local/lib/python3.11/dist-packages (from torch->easy-tpp) (12.4.127)\n",
"Requirement already satisfied: nvidia-cuda-cupti-cu12==12.4.127 in /usr/local/lib/python3.11/dist-packages (from torch->easy-tpp) (12.4.127)\n",
"Requirement already satisfied: nvidia-cudnn-cu12==9.1.0.70 in /usr/local/lib/python3.11/dist-packages (from torch->easy-tpp) (9.1.0.70)\n",
"Requirement already satisfied: nvidia-cublas-cu12==12.4.5.8 in /usr/local/lib/python3.11/dist-packages (from torch->easy-tpp) (12.4.5.8)\n",
"Requirement already satisfied: nvidia-cufft-cu12==11.2.1.3 in /usr/local/lib/python3.11/dist-packages (from torch->easy-tpp) (11.2.1.3)\n",
"Requirement already satisfied: nvidia-curand-cu12==10.3.5.147 in /usr/local/lib/python3.11/dist-packages (from torch->easy-tpp) (10.3.5.147)\n",
"Requirement already satisfied: nvidia-cusolver-cu12==11.6.1.9 in /usr/local/lib/python3.11/dist-packages (from torch->easy-tpp) (11.6.1.9)\n",
"Requirement already satisfied: nvidia-cusparse-cu12==12.3.1.170 in /usr/local/lib/python3.11/dist-packages (from torch->easy-tpp) (12.3.1.170)\n",
"Requirement already satisfied: nvidia-cusparselt-cu12==0.6.2 in /usr/local/lib/python3.11/dist-packages (from torch->easy-tpp) (0.6.2)\n",
"Requirement already satisfied: nvidia-nccl-cu12==2.21.5 in /usr/local/lib/python3.11/dist-packages (from torch->easy-tpp) (2.21.5)\n",
"Requirement already satisfied: nvidia-nvtx-cu12==12.4.127 in /usr/local/lib/python3.11/dist-packages (from torch->easy-tpp) (12.4.127)\n",
"Requirement already satisfied: nvidia-nvjitlink-cu12==12.4.127 in /usr/local/lib/python3.11/dist-packages (from torch->easy-tpp) (12.4.127)\n",
"Requirement already satisfied: triton==3.2.0 in /usr/local/lib/python3.11/dist-packages (from torch->easy-tpp) (3.2.0)\n",
"Requirement already satisfied: sympy==1.13.1 in /usr/local/lib/python3.11/dist-packages (from torch->easy-tpp) (1.13.1)\n",
"Requirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.11/dist-packages (from sympy==1.13.1->torch->easy-tpp) (1.3.0)\n",
"Requirement already satisfied: aiohappyeyeballs>=2.3.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp->datasets->easy-tpp) (2.6.1)\n",
"Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.11/dist-packages (from aiohttp->datasets->easy-tpp) (1.3.2)\n",
"Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp->datasets->easy-tpp) (25.3.0)\n",
"Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.11/dist-packages (from aiohttp->datasets->easy-tpp) (1.5.0)\n",
"Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.11/dist-packages (from aiohttp->datasets->easy-tpp) (6.3.1)\n",
"Requirement already satisfied: propcache>=0.2.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp->datasets->easy-tpp) (0.3.1)\n",
"Requirement already satisfied: yarl<2.0,>=1.17.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp->datasets->easy-tpp) (1.18.3)\n",
"Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.11/dist-packages (from requests>=2.32.2->datasets->easy-tpp) (3.4.1)\n",
"Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.11/dist-packages (from requests>=2.32.2->datasets->easy-tpp) (3.10)\n",
"Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.11/dist-packages (from requests>=2.32.2->datasets->easy-tpp) (2.3.0)\n",
"Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.11/dist-packages (from requests>=2.32.2->datasets->easy-tpp) (2025.1.31)\n",
"Requirement already satisfied: MarkupSafe>=2.1.1 in /usr/local/lib/python3.11/dist-packages (from werkzeug>=1.0.1->tensorboard->easy-tpp) (3.0.2)\n",
"Downloading easy_tpp-0.1.2-py3-none-any.whl (126 kB)\n",
"\u001B[2K \u001B[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001B[0m \u001B[32m126.5/126.5 kB\u001B[0m \u001B[31m2.9 MB/s\u001B[0m eta \u001B[36m0:00:00\u001B[0m\n",
"\u001B[?25hInstalling collected packages: easy-tpp\n",
" Attempting uninstall: easy-tpp\n",
" Found existing installation: easy-tpp 0.1.0\n",
" Uninstalling easy-tpp-0.1.0:\n",
" Successfully uninstalled easy-tpp-0.1.0\n",
"Successfully installed easy-tpp-0.1.2\n"
]
},
{
"output_type": "display_data",
"data": {
"application/vnd.colab-display-data+json": {
"pip_warning": {
"packages": [
"easy_tpp"
]
},
"id": "a33b6aa166cb43cfa25793118ff1aafc"
}
},
"metadata": {}
}
],
"source": [
"! pip install --upgrade easy-tpp"
]
},
{
"cell_type": "markdown",
"source": [
"# Step 1: setup the config file\n",
"\n",
"The EasyTPP framework uses a YAML-based configuration system that consists of two main components:\n",
"- **data configuration**, which specifies the data sources and their formats. It defines where to find the training, validation, and test datasets (see below as an example). The full explanation of the dataset can be found in the previous tutorial [EasyTPP-Dataset](https://github.com/ant-research/EasyTemporalPointProcess/blob/main/notebooks/easytpp_1_dataset.ipynb).\n",
"- **model configuration**, which defines the model architecture, hyperparameters, and training settings.\n",
"\n",
"Let's first look at the data configuration:"
],
"metadata": {
"id": "iz34tMDNg80K"
}
},
{
"cell_type": "code",
"source": [
"data_config = \"\"\"\n",
"data:\n",
" taxi:\n",
" data_format: json\n",
" train_dir: ./data/taxi/train.json\n",
" valid_dir: ./data/taxi/dev.json\n",
" test_dir: ./data/taxi/test.json\n",
"\n",
"\"\"\""
],
"metadata": {
"id": "3Sap8WlqgNQz"
},
"execution_count": 1,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"The model configuration specifies the neural network architecture and training hyperparameters. It is structured into two main sections: base configuration for general settings and trainer-specific configuration for detailed training parameters:\n"
],
"metadata": {
"id": "ZJTYO2u02q6h"
}
},
{
"cell_type": "code",
"source": [
"model_config = \"\"\"\n",
"NHP_train:\n",
" base_config:\n",
" stage: train\n",
" backend: torch\n",
" dataset_id: taxi\n",
" runner_id: std_tpp\n",
" model_id: NHP # model name\n",
" base_dir: './checkpoints/'\n",
" trainer_config:\n",
" batch_size: 256\n",
" max_epoch: 2\n",
" shuffle: True\n",
" optimizer: adam\n",
" learning_rate: 1.e-3\n",
" valid_freq: 1\n",
" use_tfb: False\n",
" metrics: [ 'acc', 'rmse' ]\n",
" seed: 2019\n",
" gpu: -1\n",
"\"\"\""
],
"metadata": {
"id": "Yq9hnfrAzXxI"
},
"execution_count": 2,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"As an illustrative example, we write the YAML content to a file yaml_content as below. Note that `runner_config` is the pipeline configuration ID that tells EasyTPP which configuration to use. We combine the data configuration\n",
"and model configuration into a single YAML file. This file will be used to initialize the model runner, which will handle the training process based on the specified parameters."
],
"metadata": {
"id": "ZhppAAZ-2xMN"
}
},
{
"cell_type": "code",
"source": [
"yaml_content = \"\"\"\n",
"pipeline_config_id: runner_config\n",
"\n",
"data:\n",
" taxi:\n",
" data_format: json\n",
" train_dir: easytpp/taxi # ./data/taxi/train.json\n",
" valid_dir: easytpp/taxi # ./data/taxi/dev.json\n",
" test_dir: easytpp/taxi # ./data/taxi/test.json\n",
" data_specs:\n",
" num_event_types: 10\n",
" pad_token_id: 10\n",
" padding_side: right\n",
"\n",
"\n",
"NHP_train:\n",
" base_config:\n",
" stage: train\n",
" backend: torch\n",
" dataset_id: taxi\n",
" runner_id: std_tpp\n",
" model_id: NHP # model name\n",
" base_dir: './checkpoints/'\n",
" trainer_config:\n",
" batch_size: 256\n",
" max_epoch: 2\n",
" shuffle: False\n",
" optimizer: adam\n",
" learning_rate: 1.e-3\n",
" valid_freq: 1\n",
" use_tfb: True\n",
" metrics: [ 'acc', 'rmse' ]\n",
" seed: 2019\n",
" gpu: -1\n",
" model_config:\n",
" hidden_size: 32\n",
" loss_integral_num_sample_per_step: 20\n",
" thinning:\n",
" num_seq: 10\n",
" num_sample: 1\n",
" num_exp: 500 # number of i.i.d. Exp(intensity_bound) draws at one time in thinning algorithm\n",
" look_ahead_time: 10\n",
" patience_counter: 5 # the maximum iteration used in adaptive thinning\n",
" over_sample_rate: 5\n",
" num_samples_boundary: 5\n",
" dtime_max: 5\n",
" num_step_gen: 1\n",
"\"\"\"\n",
"\n",
"# Save the content to a file named config.yaml\n",
"with open(\"config.yaml\", \"w\") as file:\n",
" file.write(yaml_content)"
],
"metadata": {
"id": "BZk6_2092xrD"
},
"execution_count": 3,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"## Step 2: Train the model\n",
"\n",
"Then we can initialize the model runner using the configuration file we just created. The model runner will handle the training process based on the specified parameters in our configuration.\n",
"\n",
"We'll use the `Config` class to build the configuration from the YAML file and specify an experiment ID (key of the `model_config`). Then, we'll create a `Runner` instance from this configuration and run the training process."
],
"metadata": {
"id": "tWzAAQrk25zZ"
}
},
{
"cell_type": "code",
"source": [
"from easy_tpp.config_factory import Config\n",
"from easy_tpp.runner import Runner\n",
"\n",
"config = Config.build_from_yaml_file('./config.yaml', experiment_id='NHP_train')\n",
"\n",
"model_runner = Runner.build_from_config(config)\n",
"\n",
"model_runner.run()"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "mkwjV7hL21Q6",
"outputId": "b5002b2f-ccf3-4267-c009-2848d679d311"
},
"execution_count": 4,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"\u001B[31;1m2025-04-06 05:42:18,953 - config.py[pid:60211;line:34:build_from_yaml_file] - CRITICAL: Load pipeline config class RunnerConfig\u001B[0m\n",
"\u001B[31;1m2025-04-06 05:42:18,957 - runner_config.py[pid:60211;line:151:update_config] - CRITICAL: train model NHP using CPU with torch backend\u001B[0m\n",
"\u001B[38;20m2025-04-06 05:42:18,970 - runner_config.py[pid:60211;line:35:__init__] - INFO: Save the config to ./checkpoints/60211_133800770625536_250406-054218/NHP_train_output.yaml\u001B[0m\n",
"\u001B[38;20m2025-04-06 05:42:18,972 - base_runner.py[pid:60211;line:176:save_log] - INFO: Save the log to ./checkpoints/60211_133800770625536_250406-054218/log\u001B[0m\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"/usr/local/lib/python3.11/dist-packages/huggingface_hub/utils/_auth.py:94: UserWarning: \n",
"The secret `HF_TOKEN` does not exist in your Colab secrets.\n",
"To authenticate with the Hugging Face Hub, create a token in your settings tab (https://huggingface.co/settings/tokens), set it as secret in your Google Colab and restart your session.\n",
"You will be able to reuse this secret in all of your notebooks.\n",
"Please note that authentication is recommended but still optional to access public models or datasets.\n",
" warnings.warn(\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"0.2244252199397379 0.29228809611195583\n",
"min_dt: 0.000277777777777\n",
"max_dt: 5.721388888888889\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"WARNING:tensorflow:From /usr/local/lib/python3.11/dist-packages/tensorflow/python/compat/v2_compat.py:98: disable_resource_variables (from tensorflow.python.ops.resource_variables_toggle) is deprecated and will be removed in a future version.\n",
"Instructions for updating:\n",
"non-resource variables are not supported in the long term\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\u001B[38;20m2025-04-06 05:42:34,617 - tpp_runner.py[pid:60211;line:60:_init_model] - INFO: Num of model parameters 15252\u001B[0m\n",
"\u001B[38;20m2025-04-06 05:42:36,901 - base_runner.py[pid:60211;line:98:train] - INFO: Data 'taxi' loaded...\u001B[0m\n",
"\u001B[38;20m2025-04-06 05:42:36,902 - base_runner.py[pid:60211;line:103:train] - INFO: Start NHP training...\u001B[0m\n",
"\u001B[38;20m2025-04-06 05:42:39,574 - tpp_runner.py[pid:60211;line:96:_train_model] - INFO: [ Epoch 0 (train) ]: train loglike is -1.755373397054743, num_events is 50454\u001B[0m\n",
"\u001B[38;20m2025-04-06 05:42:45,689 - tpp_runner.py[pid:60211;line:107:_train_model] - INFO: [ Epoch 0 (valid) ]: valid loglike is -1.6691416010202664, num_events is 7204, acc is 0.4415602443087174, rmse is 0.33315836060539783\u001B[0m\n",
"\u001B[38;20m2025-04-06 05:42:54,655 - tpp_runner.py[pid:60211;line:122:_train_model] - INFO: [ Epoch 0 (test) ]: test loglike is -1.6577474861303745, num_events is 14420, acc is 0.4467406380027739, rmse is 0.34015134195006963\u001B[0m\n",
"\u001B[31;1m2025-04-06 05:42:54,657 - tpp_runner.py[pid:60211;line:124:_train_model] - CRITICAL: current best loglike on valid set is -1.6691 (updated at epoch-0), best updated at this epoch\u001B[0m\n",
"\u001B[38;20m2025-04-06 05:42:57,202 - tpp_runner.py[pid:60211;line:96:_train_model] - INFO: [ Epoch 1 (train) ]: train loglike is -1.6284447567648255, num_events is 50454\u001B[0m\n",
"\u001B[38;20m2025-04-06 05:43:01,056 - tpp_runner.py[pid:60211;line:107:_train_model] - INFO: [ Epoch 1 (valid) ]: valid loglike is -1.5259201159945863, num_events is 7204, acc is 0.4582176568573015, rmse is 0.3376860494138715\u001B[0m\n",
"\u001B[38;20m2025-04-06 05:43:10,024 - tpp_runner.py[pid:60211;line:122:_train_model] - INFO: [ Epoch 1 (test) ]: test loglike is -1.5121817029299585, num_events is 14420, acc is 0.4597087378640777, rmse is 0.34172900829909414\u001B[0m\n",
"\u001B[31;1m2025-04-06 05:43:10,025 - tpp_runner.py[pid:60211;line:124:_train_model] - CRITICAL: current best loglike on valid set is -1.5259 (updated at epoch-1), best updated at this epoch\u001B[0m\n",
"\u001B[38;20m2025-04-06 05:43:10,028 - base_runner.py[pid:60211;line:110:train] - INFO: End NHP train! Cost time: 0.552m\u001B[0m\n"
]
}
]
},
{
"cell_type": "markdown",
"source": [
"# Step 2: Evaluate a model\n",
"\n",
"After training completes, we can evaluate the model's performance on the test dataset. EasyTPP offers streamlined methods for loading trained models and conducting evaluations.\n",
"\n",
"First, we need to locate the saved model directory within the `checkpoints` folder specified in our configuration. For example, the model might be stored at `./checkpoints/60211_133800770625536_250406-054218/models/saved_model`.\n",
"\n",
"Next, we'll create a new configuration file specifically for evaluation. This evaluation process performs one-step prediction on the validation set defined in the `valid_dir` parameter.\n",
"\n",
"For demonstration purposes, we'll use the same dataset for our evaluation as we used during training.\n",
"\n",
"We write the YAML config for evaluation as below. This configuration specifies:\n",
"- The data sources for training, validation, and testing (only validation will be used, the other two are optional).\n",
"- The evaluation stage and backend framework\n",
"- Model parameters and batch size\n",
"- The path to our pretrained model from the previous training step\n",
"\n",
"Note: Make sure the `thinning_config` is included in the configuration. Also, ensure that 'rmse' and 'acc' are specified in the `metrics` list under `trainer_config` to properly compute and return these evaluation metrics. The error in the previous run was due to missing 'rmse' in the metrics configuration."
],
"metadata": {
"id": "66aUobRvJktc"
}
},
{
"cell_type": "code",
"source": [
"eval_yaml =\"\"\"\n",
"pipeline_config_id: runner_config\n",
"\n",
"data:\n",
" taxi:\n",
" data_format: json\n",
" train_dir: easytpp/taxi # ./data/taxi/train.json\n",
" valid_dir: easytpp/taxi # ./data/taxi/dev.json\n",
" test_dir: easytpp/taxi # ./data/taxi/test.json\n",
" data_specs:\n",
" num_event_types: 10\n",
" pad_token_id: 10\n",
" padding_side: right\n",
"\n",
"NHP_eval:\n",
" base_config:\n",
" stage: eval\n",
" backend: torch\n",
" dataset_id: taxi\n",
" runner_id: std_tpp\n",
" base_dir: './checkpoints/'\n",
" model_id: NHP\n",
" trainer_config:\n",
" batch_size: 256\n",
" max_epoch: 1\n",
" metrics: [ 'acc', 'rmse' ]\n",
" model_config:\n",
" hidden_size: 32\n",
" use_ln: False\n",
" seed: 2019\n",
" gpu: -1\n",
" pretrained_model_dir: ./checkpoints/60211_133800770625536_250406-054218/models/saved_model\n",
" thinning:\n",
" num_seq: 10\n",
" num_sample: 1\n",
" num_exp: 500 # number of i.i.d. Exp(intensity_bound) draws at one time in thinning algorithm\n",
" look_ahead_time: 10\n",
" patience_counter: 5 # the maximum iteration used in adaptive thinning\n",
" over_sample_rate: 5\n",
" num_samples_boundary: 5\n",
" dtime_max: 5\n",
"\"\"\"\n",
"\n",
"# Save the content to a file named config.yaml\n",
"with open(\"eval_config.yaml\", \"w\") as file:\n",
" file.write(eval_yaml)"
],
"metadata": {
"id": "8ADVVKg1JlG1"
},
"execution_count": 6,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"We use the following script to evaluate the trained model. This will load the pretrained model from the specified directory and evaluate it on the test dataset\n",
""
],
"metadata": {
"id": "32WAmhBrClUD"
}
},
{
"cell_type": "code",
"source": [
"from easy_tpp.config_factory import Config\n",
"from easy_tpp.runner import Runner\n",
"\n",
"config = Config.build_from_yaml_file('./eval_config.yaml', experiment_id='NHP_eval')\n",
"\n",
"model_runner = Runner.build_from_config(config)\n",
"\n",
"model_runner.run()"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "bwPC6DI9J2LT",
"outputId": "08030865-15eb-49f8-c2a7-f53363cac43d"
},
"execution_count": 7,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"\u001B[31;1m2025-04-06 05:43:28,529 - config.py[pid:60211;line:34:build_from_yaml_file] - CRITICAL: Load pipeline config class RunnerConfig\u001B[0m\n",
"\u001B[31;1m2025-04-06 05:43:28,532 - runner_config.py[pid:60211;line:151:update_config] - CRITICAL: validate model NHP using CPU with torch backend\u001B[0m\n",
"\u001B[38;20m2025-04-06 05:43:28,543 - runner_config.py[pid:60211;line:35:__init__] - INFO: Save the config to ./checkpoints/60211_133800770625536_250406-054328/NHP_eval_output.yaml\u001B[0m\n",
"\u001B[38;20m2025-04-06 05:43:28,545 - base_runner.py[pid:60211;line:176:save_log] - INFO: Save the log to ./checkpoints/60211_133800770625536_250406-054328/log\u001B[0m\n",
"0.2244252199397379 0.29228809611195583\n",
"min_dt: 0.000277777777777\n",
"max_dt: 5.721388888888889\n",
"\u001B[38;20m2025-04-06 05:43:29,769 - tpp_runner.py[pid:60211;line:60:_init_model] - INFO: Num of model parameters 15252\u001B[0m\n",
"\u001B[31;1m2025-04-06 05:43:29,773 - tpp_runner.py[pid:60211;line:81:_load_model] - CRITICAL: Load model from ./checkpoints/60211_133800770625536_250406-054218/models/saved_model\u001B[0m\n",
"\u001B[38;20m2025-04-06 05:43:30,305 - base_runner.py[pid:60211;line:117:evaluate] - INFO: Data 'taxi' loaded...\u001B[0m\n",
"\u001B[38;20m2025-04-06 05:43:30,306 - base_runner.py[pid:60211;line:122:evaluate] - INFO: Start NHP evaluation...\u001B[0m\n",
"\u001B[31;1m2025-04-06 05:43:35,132 - tpp_runner.py[pid:60211;line:148:_evaluate_model] - CRITICAL: Evaluation result: loglike is -1.5259201159945863, num_events is 7204, acc is 0.4583564686285397, rmse is 0.3325426308842327\u001B[0m\n",
"\u001B[38;20m2025-04-06 05:43:35,133 - base_runner.py[pid:60211;line:128:evaluate] - INFO: End NHP evaluation! Cost time: 0.080m\u001B[0m\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"np.float64(0.3325426308842327)"
]
},
"metadata": {},
"execution_count": 7
}
]
},
{
"cell_type": "markdown",
"source": [
"# Step 3: Generate predictions\n",
"\n",
"After training and evaluation, we can generate predictions for new events given a sequence as `context`.\n",
"\n",
"The generation process uses the trained model to perform the one-step (by default) or multi-step prediction.\n",
"\n",
"In order to evaluate the prediction accuracy, we automatically mask the last-n events (where n depends on the prediction step count) and use them as ground truth (golden events) to compare against our model's predictions.\n",
"\n",
"We'll use the same configuration file we used for evaluation, but we'll specify a different experiment ID for the prediction task.\n",
"\n"
],
"metadata": {
"id": "ewCrMYQ0HxLU"
}
},
{
"cell_type": "code",
"source": [
"gen_yaml =\"\"\"\n",
"pipeline_config_id: runner_config\n",
"\n",
"data:\n",
" taxi:\n",
" data_format: json\n",
" train_dir: easytpp/taxi # ./data/taxi/train.json\n",
" valid_dir: easytpp/taxi # ./data/taxi/dev.json\n",
" test_dir: easytpp/taxi # ./data/taxi/test.json\n",
" data_specs:\n",
" num_event_types: 10\n",
" pad_token_id: 10\n",
" padding_side: right\n",
"\n",
"NHP_gen:\n",
" base_config:\n",
" stage: gen\n",
" backend: torch\n",
" dataset_id: taxi\n",
" runner_id: std_tpp\n",
" base_dir: './checkpoints/'\n",
" model_id: NHP\n",
" trainer_config:\n",
" batch_size: 256\n",
" max_epoch: 1\n",
" metrics: [ 'acc', 'rmse' ]\n",
" model_config:\n",
" hidden_size: 32\n",
" use_ln: False\n",
" seed: 2019\n",
" gpu: -1\n",
" pretrained_model_dir: ./checkpoints/60211_133800770625536_250406-054218/models/saved_model\n",
" thinning:\n",
" num_seq: 10\n",
" num_sample: 1\n",
" num_exp: 500 # number of i.i.d. Exp(intensity_bound) draws at one time in thinning algorithm\n",
" look_ahead_time: 10\n",
" patience_counter: 5 # the maximum iteration used in adaptive thinning\n",
" over_sample_rate: 5\n",
" num_samples_boundary: 5\n",
" dtime_max: 5\n",
" num_step_gen: 1\n",
"\"\"\"\n",
"\n",
"# Save the content to a file named config.yaml\n",
"with open(\"gen_config.yaml\", \"w\") as file:\n",
" file.write(gen_yaml)"
],
"metadata": {
"id": "FIGDkivPLO3N"
},
"execution_count": 8,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"We continue to use a similar configuration file to launch the generation process. Note that it is necessary to explicitly specify `num_gen_step` in the thinning config. The results will be saved in a pickle file.\n",
"\n",
"We acknowledge that the generation pipeline is still a work in progress. For instance, the multi-step sampling process can be further improved (ongoing work), and the output format could be enhanced to facilitate easier evaluation."
],
"metadata": {
"id": "ymXwak6WoOGB"
}
},
{
"cell_type": "code",
"source": [
"from easy_tpp.config_factory import Config\n",
"from easy_tpp.runner import Runner\n",
"\n",
"config = Config.build_from_yaml_file('./gen_config.yaml', experiment_id='NHP_gen')\n",
"\n",
"model_runner = Runner.build_from_config(config)\n",
"\n",
"model_runner.run()"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "kgJVjrh9HisJ",
"outputId": "f62fe3bc-8484-49f5-f814-166971d2a27a"
},
"execution_count": 9,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"\u001B[31;1m2025-04-06 05:43:48,495 - config.py[pid:60211;line:34:build_from_yaml_file] - CRITICAL: Load pipeline config class RunnerConfig\u001B[0m\n",
"\u001B[31;1m2025-04-06 05:43:48,498 - runner_config.py[pid:60211;line:151:update_config] - CRITICAL: predict model NHP using CPU with torch backend\u001B[0m\n",
"\u001B[38;20m2025-04-06 05:43:48,508 - runner_config.py[pid:60211;line:35:__init__] - INFO: Save the config to ./checkpoints/60211_133800770625536_250406-054348/NHP_gen_output.yaml\u001B[0m\n",
"\u001B[38;20m2025-04-06 05:43:48,510 - base_runner.py[pid:60211;line:176:save_log] - INFO: Save the log to ./checkpoints/60211_133800770625536_250406-054348/log\u001B[0m\n",
"0.2244252199397379 0.29228809611195583\n",
"min_dt: 0.000277777777777\n",
"max_dt: 5.721388888888889\n",
"\u001B[38;20m2025-04-06 05:43:49,245 - tpp_runner.py[pid:60211;line:60:_init_model] - INFO: Num of model parameters 15252\u001B[0m\n",
"\u001B[31;1m2025-04-06 05:43:49,249 - tpp_runner.py[pid:60211;line:81:_load_model] - CRITICAL: Load model from ./checkpoints/60211_133800770625536_250406-054218/models/saved_model\u001B[0m\n",
"\u001B[38;20m2025-04-06 05:43:49,777 - base_runner.py[pid:60211;line:135:gen] - INFO: Data 'taxi' loaded...\u001B[0m\n",
"\u001B[38;20m2025-04-06 05:43:49,779 - base_runner.py[pid:60211;line:140:gen] - INFO: Start NHP evaluation...\u001B[0m\n",
"\u001B[31;1m2025-04-06 05:43:50,159 - tpp_runner.py[pid:60211;line:162:_gen_model] - CRITICAL: Save the prediction to pickle file pred.pkl\u001B[0m\n",
"\u001B[38;20m2025-04-06 05:43:50,161 - base_runner.py[pid:60211;line:146:gen] - INFO: End NHP generation! Cost time: 0.006m\u001B[0m\n"
]
}
]
},
{
"cell_type": "markdown",
"source": [],
"metadata": {
"id": "pTreVIxWof_R"
}
}
]
}
|