VictorMylle/Thesis
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Rewrote dataset to be able to include new features

Browse Source
This commit is contained in:
Victor Mylle
2023-11-08 23:17:47 +00:00
parent 56c763a6f4
commit 2f48363292
10 changed files with 311218 additions and 118 deletions
Download Patch File Download Diff File Expand all files Collapse all files

99
src/notebooks/training.ipynb
View File

@@ -8,7 +8,7 @@
"source": [
"import sys\n",
"sys.path.append('..')\n",
"from data import DataProcessor\n",
"from data import DataProcessor, DataConfig\n",
"from trainers.quantile_trainer import QuantileTrainer\n",
"from trainers.autoregressive_trainer import AutoRegressiveTrainer\n",
"from trainers.trainer import Trainer\n",
@@ -50,35 +50,40 @@
"name": "stdout",
"output_type": "stream",
"text": [
"ClearML Task: created new task id=909da25a8d214f75ab3858506ae615e8\n",
"2023-11-07 16:29:35,665 - clearml.Task - INFO - Storing jupyter notebook directly as code\n",
"ClearML results page: http://192.168.1.182:8080/projects/2e46d4af6f1e4c399cf9f5aa30bc8795/experiments/909da25a8d214f75ab3858506ae615e8/output/log\n",
"2023-11-07 16:30:08,121 - clearml.model - WARNING - 500 model found when searching for `file:///workspaces/Thesis/src/notebooks/checkpoint.pt`\n",
"2023-11-07 16:30:08,123 - clearml.model - WARNING - Selected model `Quantile Regression - Linear` (id=bc0cb0d7fc614e2e8b0edf5b85348646)\n",
"2023-11-07 16:30:08,130 - clearml.frameworks - INFO - Found existing registered model id=bc0cb0d7fc614e2e8b0edf5b85348646 [/workspaces/Thesis/src/notebooks/checkpoint.pt] reusing it.\n",
"2023-11-07 16:30:08,677 - clearml.Task - INFO - Completed model upload to http://192.168.1.182:8081/Thesis/NrvForecast/Non-AutoRegressive%20-%20Non%20Linear%20%283%20hidden%20layers%20-%201024%20units%29.909da25a8d214f75ab3858506ae615e8/models/checkpoint.pt\n",
"2023-11-07 16:30:10,302 - clearml.Task - INFO - Completed model upload to http://192.168.1.182:8081/Thesis/NrvForecast/Non-AutoRegressive%20-%20Non%20Linear%20%283%20hidden%20layers%20-%201024%20units%29.909da25a8d214f75ab3858506ae615e8/models/checkpoint.pt\n",
"ClearML Task: created new task id=ae9d93e6bf3f4d228832378707574777\n",
"ClearML results page: http://192.168.1.182:8080/projects/2e46d4af6f1e4c399cf9f5aa30bc8795/experiments/ae9d93e6bf3f4d228832378707574777/output/log\n",
"2023-11-08 21:46:32,338 - clearml.Task - INFO - Storing jupyter notebook directly as code\n",
"2023-11-08 21:46:32,342 - clearml.Repository Detection - WARNING - Can't get url information for git repo in /workspaces/Thesis/src/notebooks\n",
"2023-11-08 21:46:35,244 - clearml.model - WARNING - 500 model found when searching for `file:///workspaces/Thesis/src/notebooks/checkpoint.pt`\n",
"2023-11-08 21:46:35,245 - clearml.model - WARNING - Selected model `Untitled Task` (id=bc0cb0d7fc614e2e8b0edf5b85348646)\n",
"2023-11-08 21:46:35,254 - clearml.frameworks - INFO - Found existing registered model id=bc0cb0d7fc614e2e8b0edf5b85348646 [/workspaces/Thesis/src/notebooks/checkpoint.pt] reusing it.\n",
"2023-11-08 21:46:35,748 - clearml.Task - INFO - Completed model upload to http://192.168.1.182:8081/Thesis/NrvForecast/Untitled%20Task.ae9d93e6bf3f4d228832378707574777/models/checkpoint.pt\n",
"2023-11-08 21:46:37,673 - clearml.Task - INFO - Completed model upload to http://192.168.1.182:8081/Thesis/NrvForecast/Untitled%20Task.ae9d93e6bf3f4d228832378707574777/models/checkpoint.pt\n",
"2023-11-08 21:46:41,215 - clearml.Task - INFO - Completed model upload to http://192.168.1.182:8081/Thesis/NrvForecast/Untitled%20Task.ae9d93e6bf3f4d228832378707574777/models/checkpoint.pt\n",
"2023-11-08 21:46:43,004 - clearml.Task - INFO - Completed model upload to http://192.168.1.182:8081/Thesis/NrvForecast/Untitled%20Task.ae9d93e6bf3f4d228832378707574777/models/checkpoint.pt\n",
"2023-11-08 21:46:44,745 - clearml.Task - INFO - Completed model upload to http://192.168.1.182:8081/Thesis/NrvForecast/Untitled%20Task.ae9d93e6bf3f4d228832378707574777/models/checkpoint.pt\n",
"Early stopping triggered\n"
]
}
],
"source": [
"#### Hyperparameters ####\n",
"inputDim = 96\n",
"inputDim = 96 + 96\n",
"learningRate = 0.0003\n",
"epochs = 50\n",
"epochs = 150\n",
"\n",
"# model = LinearRegression(inputDim, 96)\n",
"model = NonLinearRegression(inputDim, 96, hiddenSize=1024, numLayers=5)\n",
"optimizer = torch.optim.Adam(model.parameters(), lr=learningRate)\n",
"\n",
"#### Data Processor ####\n",
"data_processor = DataProcessor()\n",
"data_config = DataConfig()\n",
"data_processor = DataProcessor(data_config)\n",
"data_processor.set_batch_size(1024)\n",
"\n",
"\n",
"data_processor.set_train_range((datetime(year=2015, month=1, day=1, tzinfo=pytz.UTC), datetime(year=2022, month=11, day=30, tzinfo=pytz.UTC)))\n",
"data_processor.set_test_range((datetime(year=2023, month=1, day=1, tzinfo=pytz.UTC), np.inf))\n",
"data_processor.set_test_range((datetime(year=2023, month=1, day=1, tzinfo=pytz.UTC), datetime(year=2023, month=6, day=20, tzinfo=pytz.UTC)))\n",
"\n",
"#### ClearML ####\n",
"clearml_helper = ClearMLHelper(project_name=\"Thesis/NrvForecast\")\n",
@@ -87,7 +92,7 @@
"trainer = Trainer(model, optimizer, nn.MSELoss(), data_processor, \"cuda\", debug=False, clearml_helper=clearml_helper)\n",
"trainer.add_metrics_to_track([MSELoss(), L1Loss()])\n",
"trainer.plot_every(10)\n",
"trainer.early_stopping(patience=10)\n",
"trainer.early_stopping(patience=40)\n",
"trainer.train(epochs=epochs)"
]
},
@@ -100,15 +105,30 @@
},
{
"cell_type": "code",
"execution_count": 3,
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"InsecureRequestWarning: Certificate verification is disabled! Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#ssl-warnings\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"ClearML Task: created new task id=6467cef37fdc408d95b89f0dca0e26dd\n",
"ClearML results page: http://192.168.1.182:8080/projects/2e46d4af6f1e4c399cf9f5aa30bc8795/experiments/6467cef37fdc408d95b89f0dca0e26dd/output/log\n",
"ClearML Task: created new task id=e4983af7aad748e8ae71e5fa46767d60\n",
"ClearML results page: http://192.168.1.182:8080/projects/2e46d4af6f1e4c399cf9f5aa30bc8795/experiments/e4983af7aad748e8ae71e5fa46767d60/output/log\n",
"2023-11-08 22:51:38,769 - clearml.Task - INFO - Storing jupyter notebook directly as code\n",
"2023-11-08 22:51:38,773 - clearml.Repository Detection - WARNING - Can't get url information for git repo in /workspaces/Thesis/src/notebooks\n",
"2023-11-08 22:51:41,704 - clearml.model - WARNING - 500 model found when searching for `file:///workspaces/Thesis/src/notebooks/checkpoint.pt`\n",
"2023-11-08 22:51:41,705 - clearml.model - WARNING - Selected model `Untitled Task` (id=bc0cb0d7fc614e2e8b0edf5b85348646)\n",
"2023-11-08 22:51:41,713 - clearml.frameworks - INFO - Found existing registered model id=bc0cb0d7fc614e2e8b0edf5b85348646 [/workspaces/Thesis/src/notebooks/checkpoint.pt] reusing it.\n",
"2023-11-08 22:51:42,239 - clearml.Task - INFO - Completed model upload to http://192.168.1.182:8081/Thesis/NrvForecast/Untitled%20Task.e4983af7aad748e8ae71e5fa46767d60/models/checkpoint.pt\n",
"2023-11-08 22:51:43,980 - clearml.Task - INFO - Completed model upload to http://192.168.1.182:8081/Thesis/NrvForecast/Untitled%20Task.e4983af7aad748e8ae71e5fa46767d60/models/checkpoint.pt\n",
"2023-11-08 22:51:45,684 - clearml.Task - INFO - Completed model upload to http://192.168.1.182:8081/Thesis/NrvForecast/Untitled%20Task.e4983af7aad748e8ae71e5fa46767d60/models/checkpoint.pt\n",
"Early stopping triggered\n"
]
}
@@ -124,7 +144,9 @@
"optimizer = torch.optim.Adam(model.parameters(), lr=learningRate)\n",
"\n",
"#### Data Processor ####\n",
"data_processor = DataProcessor()\n",
"data_config = DataConfig()\n",
"data_config.LOAD_FORECAST = False\n",
"data_processor = DataProcessor(data_config)\n",
"data_processor.set_batch_size(1024)\n",
"\n",
"\n",
@@ -151,26 +173,18 @@
},
{
"cell_type": "code",
"execution_count": 4,
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/workspaces/Thesis/src/notebooks/../trainers/quantile_trainer.py:16: UserWarning:\n",
"\n",
"To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).\n",
"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"ClearML Task: created new task id=07a2dc72793446d8a8101eafce0d80db\n",
"ClearML results page: http://192.168.1.182:8080/projects/2e46d4af6f1e4c399cf9f5aa30bc8795/experiments/07a2dc72793446d8a8101eafce0d80db/output/log\n",
"Early stopping triggered\n"
"ename": "TypeError",
"evalue": "DataProcessor.__init__() missing 1 required positional argument: 'data_config'",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mTypeError\u001b[0m Traceback (most recent call last)",
"\u001b[1;32m/workspaces/Thesis/src/notebooks/training.ipynb Cell 7\u001b[0m line \u001b[0;36m1\n\u001b[1;32m <a href='vscode-notebook-cell://dev-container%2B7b22686f737450617468223a222f686f6d652f766963746f726d796c6c652f53656144726976652f4d79204c69627261726965732f4750552d7365727665722f546865736973222c226c6f63616c446f636b6572223a66616c73652c22636f6e66696746696c65223a7b22246d6964223a312c2270617468223a222f686f6d652f766963746f726d796c6c652f53656144726976652f4d79204c69627261726965732f4750552d7365727665722f5468657369732f2e646576636f6e7461696e65722f646576636f6e7461696e65722e6a736f6e222c22736368656d65223a227673636f64652d66696c65486f7374227d7d@ssh-remote%2Bvictormylle.be/workspaces/Thesis/src/notebooks/training.ipynb#X10sdnNjb2RlLXJlbW90ZQ%3D%3D?line=13'>14</a>\u001b[0m data_config \u001b[39m=\u001b[39m DataConfig()\n\u001b[1;32m <a href='vscode-notebook-cell://dev-container%2B7b22686f737450617468223a222f686f6d652f766963746f726d796c6c652f53656144726976652f4d79204c69627261726965732f4750552d7365727665722f546865736973222c226c6f63616c446f636b6572223a66616c73652c22636f6e66696746696c65223a7b22246d6964223a312c2270617468223a222f686f6d652f766963746f726d796c6c652f53656144726976652f4d79204c69627261726965732f4750552d7365727665722f5468657369732f2e646576636f6e7461696e65722f646576636f6e7461696e65722e6a736f6e222c22736368656d65223a227673636f64652d66696c65486f7374227d7d@ssh-remote%2Bvictormylle.be/workspaces/Thesis/src/notebooks/training.ipynb#X10sdnNjb2RlLXJlbW90ZQ%3D%3D?line=14'>15</a>\u001b[0m data_config\u001b[39m.\u001b[39mLOAD_FORECAST \u001b[39m=\u001b[39m \u001b[39mFalse\u001b[39;00m\n\u001b[0;32m---> <a href='vscode-notebook-cell://dev-container%2B7b22686f737450617468223a222f686f6d652f766963746f726d796c6c652f53656144726976652f4d79204c69627261726965732f4750552d7365727665722f546865736973222c226c6f63616c446f636b6572223a66616c73652c22636f6e66696746696c65223a7b22246d6964223a312c2270617468223a222f686f6d652f766963746f726d796c6c652f53656144726976652f4d79204c69627261726965732f4750552d7365727665722f5468657369732f2e646576636f6e7461696e65722f646576636f6e7461696e65722e6a736f6e222c22736368656d65223a227673636f64652d66696c65486f7374227d7d@ssh-remote%2Bvictormylle.be/workspaces/Thesis/src/notebooks/training.ipynb#X10sdnNjb2RlLXJlbW90ZQ%3D%3D?line=15'>16</a>\u001b[0m data_processor \u001b[39m=\u001b[39m DataProcessor()\n\u001b[1;32m <a href='vscode-notebook-cell://dev-container%2B7b22686f737450617468223a222f686f6d652f766963746f726d796c6c652f53656144726976652f4d79204c69627261726965732f4750552d7365727665722f546865736973222c226c6f63616c446f636b6572223a66616c73652c22636f6e66696746696c65223a7b22246d6964223a312c2270617468223a222f686f6d652f766963746f726d796c6c652f53656144726976652f4d79204c69627261726965732f4750552d7365727665722f5468657369732f2e646576636f6e7461696e65722f646576636f6e7461696e65722e6a736f6e222c22736368656d65223a227673636f64652d66696c65486f7374227d7d@ssh-remote%2Bvictormylle.be/workspaces/Thesis/src/notebooks/training.ipynb#X10sdnNjb2RlLXJlbW90ZQ%3D%3D?line=16'>17</a>\u001b[0m data_processor\u001b[39m.\u001b[39mset_batch_size(\u001b[39m1024\u001b[39m)\n\u001b[1;32m <a href='vscode-notebook-cell://dev-container%2B7b22686f737450617468223a222f686f6d652f766963746f726d796c6c652f53656144726976652f4d79204c69627261726965732f4750552d7365727665722f546865736973222c226c6f63616c446f636b6572223a66616c73652c22636f6e66696746696c65223a7b22246d6964223a312c2270617468223a222f686f6d652f766963746f726d796c6c652f53656144726976652f4d79204c69627261726965732f4750552d7365727665722f5468657369732f2e646576636f6e7461696e65722f646576636f6e7461696e65722e6a736f6e222c22736368656d65223a227673636f64652d66696c65486f7374227d7d@ssh-remote%2Bvictormylle.be/workspaces/Thesis/src/notebooks/training.ipynb#X10sdnNjb2RlLXJlbW90ZQ%3D%3D?line=18'>19</a>\u001b[0m data_processor\u001b[39m.\u001b[39mset_train_range((\u001b[39m-\u001b[39mnp\u001b[39m.\u001b[39minf, datetime(year\u001b[39m=\u001b[39m\u001b[39m2022\u001b[39m, month\u001b[39m=\u001b[39m\u001b[39m11\u001b[39m, day\u001b[39m=\u001b[39m\u001b[39m30\u001b[39m, tzinfo\u001b[39m=\u001b[39mpytz\u001b[39m.\u001b[39mUTC)))\n",
"\u001b[0;31mTypeError\u001b[0m: DataProcessor.__init__() missing 1 required positional argument: 'data_config'"
]
}
],
@@ -178,17 +192,19 @@
"#### Hyperparameters ####\n",
"inputDim = 96\n",
"learningRate = 0.0003\n",
"epochs = 50\n",
"epochs = 100\n",
"\n",
"quantiles = torch.tensor([0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9]).to(\"cuda\")\n",
"\n",
"# model = LinearRegression(inputDim, len(quantiles))\n",
"model = NonLinearRegression(inputDim, len(quantiles), hiddenSize=1024, numLayers=5)\n",
"model = NonLinearRegression(inputDim, len(quantiles), hiddenSize=1024, numLayers=5, dropout=0.2)\n",
"model.output_size = 1\n",
"optimizer = torch.optim.Adam(model.parameters(), lr=learningRate)\n",
"\n",
"#### Data Processor ####\n",
"data_processor = DataProcessor()\n",
"data_config = DataConfig()\n",
"data_config.LOAD_FORECAST = False\n",
"data_processor = DataProcessor(data_config)\n",
"data_processor.set_batch_size(1024)\n",
"\n",
"data_processor.set_train_range((-np.inf, datetime(year=2022, month=11, day=30, tzinfo=pytz.UTC)))\n",
@@ -204,6 +220,13 @@
"trainer.plot_every(10)\n",
"trainer.train(epochs=epochs)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {