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

Fixed small summary with model architectures until now

Browse Source
This commit is contained in:
Victor Mylle
2023-11-30 21:53:35 +00:00
parent eba10c8f83
commit 120b6aa5bd
23 changed files with 402 additions and 185 deletions
Download Patch File Download Diff File Expand all files Collapse all files

103
src/data/dataset.py
View File

@@ -15,19 +15,18 @@ class NrvDataset(Dataset):
lstm: bool = False,
):
self.data_config = data_config
self.dataframe = dataframe
self.full_day_skip = full_day_skip
self.lstm = lstm
# reset dataframe index
self.dataframe.reset_index(drop=True, inplace=True)
dataframe.reset_index(drop=True, inplace=True)
self.sequence_length = sequence_length
self.predict_sequence_length = predict_sequence_length
self.samples_to_skip = self.skip_samples()
self.samples_to_skip = self.skip_samples(dataframe=dataframe)
total_indices = set(
range(len(self.dataframe) - self.sequence_length - self.predict_sequence_length)
range(len(dataframe) - self.sequence_length - self.predict_sequence_length)
)
self.valid_indices = sorted(list(total_indices - set(self.samples_to_skip)))
@@ -48,20 +47,28 @@ class NrvDataset(Dataset):
self.forecast_features.append("wind_gen_forecast")
# add time feature to dataframe
time_feature = np.array([0] * len(self.dataframe))
time_feature = np.array([0] * len(dataframe))
if self.data_config.QUARTER:
time_feature += self.dataframe["quarter"]
time_feature += dataframe["quarter"]
if self.data_config.DAY_OF_WEEK:
d_w = self.dataframe["day_of_week"]
d_w = dataframe["day_of_week"]
if self.data_config.QUARTER:
d_w *= 96
time_feature += d_w
self.dataframe["time_feature"] = time_feature
# if not all zero:
if time_feature.any():
self.time_feature = torch.tensor(time_feature).float().reshape(-1)
else:
self.time_feature = None
self.nrv = torch.tensor(dataframe["nrv"].values).float().reshape(-1)
def skip_samples(self):
nan_rows = self.dataframe[self.dataframe.isnull().any(axis=1)]
self.history_features, self.forecast_features = self.preprocess_data(dataframe)
def skip_samples(self, dataframe):
nan_rows = dataframe[dataframe.isnull().any(axis=1)]
nan_indices = nan_rows.index
skip_indices = [
list(
@@ -79,18 +86,22 @@ class NrvDataset(Dataset):
# add indices that are not the start of a day (00:15) to the skip indices (use datetime column)
# get indices of all 00:15 timestamps
if self.full_day_skip:
start_of_day_indices = self.dataframe[
self.dataframe["datetime"].dt.time != pd.Timestamp("00:15:00").time()
start_of_day_indices = dataframe[
dataframe["datetime"].dt.time != pd.Timestamp("00:15:00").time()
].index
skip_indices.extend(start_of_day_indices)
skip_indices = list(set(skip_indices))
return skip_indices
def preprocess_data(self, dataframe):
return torch.tensor(dataframe[self.history_features].values).float(), torch.tensor(dataframe[self.forecast_features].values).float()
def __len__(self):
return len(self.valid_indices)
def _get__all_data(self, idx: int):
def _get_all_data(self, idx: int):
history_df = self.dataframe.iloc[idx : idx + self.sequence_length]
forecast_df = self.dataframe.iloc[
idx + self.sequence_length : idx + self.sequence_length + self.predict_sequence_length
@@ -99,39 +110,47 @@ class NrvDataset(Dataset):
def __getitem__(self, idx):
actual_idx = self.valid_indices[idx]
history_df, forecast_df = self._get__all_data(actual_idx)
# get nrv history features
nrv_features = torch.tensor(history_df[["nrv"]].values).reshape(-1)
nrv_features = self.nrv[actual_idx : actual_idx + self.sequence_length]
# get history featues
history_features = history_df[self.history_features].values
history_features = self.history_features[actual_idx : actual_idx + self.sequence_length, :]
forecast_features = self.forecast_features[actual_idx + self.sequence_length : actual_idx + self.sequence_length + self.predict_sequence_length, :]
# combine the history features to one tensor (first one feature, then the next one, etc.)
history_features = torch.tensor(history_features)
# get forecast features
forecast_features = forecast_df[self.forecast_features].values
forecast_features = torch.tensor(forecast_features)
# add last time feature of the history
time_feature = history_df["time_feature"].iloc[-1]
if self.time_feature is not None:
time_features = self.time_feature[actual_idx : actual_idx + self.sequence_length]
else:
time_features = None
## all features
if not self.lstm:
all_features = torch.cat(
[nrv_features, history_features.reshape(-1), forecast_features.reshape(-1), torch.tensor([time_feature])], dim=0
)
all_features_list = [nrv_features]
if history_features.numel() > 0:
all_features_list.append(history_features.reshape(-1))
if forecast_features.numel() > 0:
all_features_list.append(forecast_features.reshape(-1))
if time_features is not None:
all_features_list.append(torch.tensor([time_features[-1]]))
all_features = torch.cat(all_features_list, dim=0)
else:
time_features = torch.tensor(history_df["time_feature"].values).reshape(-1, 1)
# combine (96, ) and (96, 2) to (96, 3)
all_features = torch.cat(
[nrv_features.unsqueeze(1), time_features], dim=1
)
all_features_list = [nrv_features.unsqueeze(1)]
if self.forecast_features.numel() > 0:
history_forecast_features = self.forecast_features[actual_idx + 1 : actual_idx + self.sequence_length + 1, :]
all_features_list.append(history_forecast_features)
if time_features is not None:
all_features_list.append(time_features.unsqueeze(-1))
all_features = torch.cat(all_features_list, dim=1)
# Target sequence, flattened if necessary
nrv_target = forecast_df["nrv"].values
nrv_target = self.nrv[actual_idx + self.sequence_length : actual_idx + self.sequence_length + self.predict_sequence_length]
# check if nan values are present
if torch.isnan(all_features).any():
@@ -141,16 +160,18 @@ class NrvDataset(Dataset):
# all features and target to float
all_features = all_features.float()
# to tens&éazzaéaz"ezéors
nrv_target = torch.tensor(nrv_target).float()
return all_features, nrv_target, idx
def random_day_autoregressive(self, idx: int):
all_features, nrv_target, _ = self.__getitem__(idx)
# remove the first 96 values of the features (the nrv history)
all_features = all_features[self.sequence_length :]
if not self.lstm:
all_features = all_features[self.sequence_length :]
else:
# last time step
all_features = all_features[-1, :]
all_features = all_features.unsqueeze(0)
return all_features, nrv_target

8
src/models/linear_regression.py
View File

@@ -1,11 +1,17 @@
import torch
import numpy as np
class LinearRegression(torch.nn.Module):
def __init__(self, inputSize, output_size):
super(LinearRegression, self).__init__()
self.inputSize = inputSize
self.output_size = output_size
self.linear = torch.nn.Linear(inputSize, output_size)
# dimension multiplication without first one
dim = inputSize[1:]
dim = [int(x) for x in dim]
dim = np.prod(dim)
self.linear = torch.nn.Linear(dim, output_size)
def forward(self, x):
x = torch.squeeze(x, -1)

6
src/models/lstm_model.py
View File

@@ -37,9 +37,9 @@ class GRUModel(torch.nn.Module):
def forward(self, x):
# Forward pass through the GRU layers
_, hidden_state = self.gru(x)
x, _ = self.gru(x)
x = x[:, -1, :]
# Use the hidden state from the last time step for the output
output = self.linear(hidden_state[-1])
output = self.linear(x)
return output

2
src/models/non_linear_regression.py
View File

@@ -13,7 +13,7 @@ class NonLinearRegression(torch.nn.Module):
# add linear layers with relu
self.layers = torch.nn.ModuleList()
self.layers.append(torch.nn.Linear(inputSize, hiddenSize))
self.layers.append(torch.nn.Linear(inputSize[-1], hiddenSize))
self.layers.append(torch.nn.Dropout(dropout))
for _ in range(numLayers - 2):
self.layers.append(torch.nn.Linear(hiddenSize, hiddenSize))

4
src/models/time_embedding_layer.py
View File

@@ -10,6 +10,8 @@ class TimeEmbedding(nn.Module):
def forward(self, x):
# Extract the last 'time_features' from the input
if self.time_features == 0:
return x
time_feature = x[..., -1] # Use ellipsis to access the last dimension
# convert to int
time_feature = time_feature.int()
@@ -20,6 +22,8 @@ class TimeEmbedding(nn.Module):
def output_dim(self, input_dim):
if self.time_features == 0:
return input_dim
# Create a list from the input dimension
input_dim_list = list(input_dim)
# Modify the last dimension

152
src/notebooks/training.ipynb
View File

@@ -42,15 +42,15 @@
},
{
"cell_type": "code",
"execution_count": 3,
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"#### Data Processor ####\n",
"data_config = DataConfig()\n",
"data_config.NRV_HISTORY = True\n",
"data_config.LOAD_HISTORY = False\n",
"data_config.LOAD_FORECAST = False\n",
"data_config.LOAD_HISTORY = True\n",
"data_config.LOAD_FORECAST = True\n",
"\n",
"data_config.WIND_FORECAST = False\n",
"data_config.WIND_HISTORY = False\n",
@@ -72,16 +72,32 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 11,
"metadata": {},
"outputs": [],
"outputs": [
{
"ename": "KeyboardInterrupt",
"evalue": "Interrupted by user",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
"\u001b[1;32m/workspaces/Thesis/src/notebooks/training.ipynb Cell 5\u001b[0m line \u001b[0;36m7\n\u001b[1;32m <a href='vscode-notebook-cell://dev-container%2B7b22686f737450617468223a222f686f6d652f766963746f726d796c6c652f53656144726976652f4d79204c69627261726965732f4750552d7365727665722f546865736973222c226c6f63616c446f636b6572223a66616c73652c22636f6e66696746696c65223a7b22246d6964223a312c2270617468223a222f686f6d652f766963746f726d796c6c652f53656144726976652f4d79204c69627261726965732f4750552d7365727665722f5468657369732f2e646576636f6e7461696e65722f646576636f6e7461696e65722e6a736f6e222c22736368656d65223a227673636f64652d66696c65486f7374227d7d@ssh-remote%2Bvictormylle.be/workspaces/Thesis/src/notebooks/training.ipynb#W4sdnNjb2RlLXJlbW90ZQ%3D%3D?line=2'>3</a>\u001b[0m trainer \u001b[39m=\u001b[39m ProbabilisticBaselineTrainer(\n\u001b[1;32m <a href='vscode-notebook-cell://dev-container%2B7b22686f737450617468223a222f686f6d652f766963746f726d796c6c652f53656144726976652f4d79204c69627261726965732f4750552d7365727665722f546865736973222c226c6f63616c446f636b6572223a66616c73652c22636f6e66696746696c65223a7b22246d6964223a312c2270617468223a222f686f6d652f766963746f726d796c6c652f53656144726976652f4d79204c69627261726965732f4750552d7365727665722f5468657369732f2e646576636f6e7461696e65722f646576636f6e7461696e65722e6a736f6e222c22736368656d65223a227673636f64652d66696c65486f7374227d7d@ssh-remote%2Bvictormylle.be/workspaces/Thesis/src/notebooks/training.ipynb#W4sdnNjb2RlLXJlbW90ZQ%3D%3D?line=3'>4</a>\u001b[0m quantiles\u001b[39m=\u001b[39mquantiles, data_processor\u001b[39m=\u001b[39mdata_processor, clearml_helper\u001b[39m=\u001b[39mclearml_helper\n\u001b[1;32m <a href='vscode-notebook-cell://dev-container%2B7b22686f737450617468223a222f686f6d652f766963746f726d796c6c652f53656144726976652f4d79204c69627261726965732f4750552d7365727665722f546865736973222c226c6f63616c446f636b6572223a66616c73652c22636f6e66696746696c65223a7b22246d6964223a312c2270617468223a222f686f6d652f766963746f726d796c6c652f53656144726976652f4d79204c69627261726965732f4750552d7365727665722f5468657369732f2e646576636f6e7461696e65722f646576636f6e7461696e65722e6a736f6e222c22736368656d65223a227673636f64652d66696c65486f7374227d7d@ssh-remote%2Bvictormylle.be/workspaces/Thesis/src/notebooks/training.ipynb#W4sdnNjb2RlLXJlbW90ZQ%3D%3D?line=4'>5</a>\u001b[0m )\n\u001b[1;32m <a href='vscode-notebook-cell://dev-container%2B7b22686f737450617468223a222f686f6d652f766963746f726d796c6c652f53656144726976652f4d79204c69627261726965732f4750552d7365727665722f546865736973222c226c6f63616c446f636b6572223a66616c73652c22636f6e66696746696c65223a7b22246d6964223a312c2270617468223a222f686f6d652f766963746f726d796c6c652f53656144726976652f4d79204c69627261726965732f4750552d7365727665722f5468657369732f2e646576636f6e7461696e65722f646576636f6e7461696e65722e6a736f6e222c22736368656d65223a227673636f64652d66696c65486f7374227d7d@ssh-remote%2Bvictormylle.be/workspaces/Thesis/src/notebooks/training.ipynb#W4sdnNjb2RlLXJlbW90ZQ%3D%3D?line=5'>6</a>\u001b[0m trainer\u001b[39m.\u001b[39madd_metrics_to_track([CRPSLoss()])\n\u001b[0;32m----> <a href='vscode-notebook-cell://dev-container%2B7b22686f737450617468223a222f686f6d652f766963746f726d796c6c652f53656144726976652f4d79204c69627261726965732f4750552d7365727665722f546865736973222c226c6f63616c446f636b6572223a66616c73652c22636f6e66696746696c65223a7b22246d6964223a312c2270617468223a222f686f6d652f766963746f726d796c6c652f53656144726976652f4d79204c69627261726965732f4750552d7365727665722f5468657369732f2e646576636f6e7461696e65722f646576636f6e7461696e65722e6a736f6e222c22736368656d65223a227673636f64652d66696c65486f7374227d7d@ssh-remote%2Bvictormylle.be/workspaces/Thesis/src/notebooks/training.ipynb#W4sdnNjb2RlLXJlbW90ZQ%3D%3D?line=6'>7</a>\u001b[0m trainer\u001b[39m.\u001b[39;49mtrain()\n",
"File \u001b[0;32m/workspaces/Thesis/src/notebooks/../../src/trainers/probabilistic_baseline.py:43\u001b[0m, in \u001b[0;36mProbabilisticBaselineTrainer.train\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 42\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39mtrain\u001b[39m(\u001b[39mself\u001b[39m):\n\u001b[0;32m---> 43\u001b[0m task \u001b[39m=\u001b[39m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49minit_clearml_task()\n\u001b[1;32m 44\u001b[0m \u001b[39mtry\u001b[39;00m:\n\u001b[1;32m 45\u001b[0m time_steps \u001b[39m=\u001b[39m [[] \u001b[39mfor\u001b[39;00m _ \u001b[39min\u001b[39;00m \u001b[39mrange\u001b[39m(\u001b[39m96\u001b[39m)]\n",
"File \u001b[0;32m/workspaces/Thesis/src/notebooks/../../src/trainers/probabilistic_baseline.py:28\u001b[0m, in \u001b[0;36mProbabilisticBaselineTrainer.init_clearml_task\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 25\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mnot\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mclearml_helper:\n\u001b[1;32m 26\u001b[0m \u001b[39mreturn\u001b[39;00m \u001b[39mNone\u001b[39;00m\n\u001b[0;32m---> 28\u001b[0m task_name \u001b[39m=\u001b[39m \u001b[39minput\u001b[39;49m(\u001b[39m\"\u001b[39;49m\u001b[39mEnter a task name: \u001b[39;49m\u001b[39m\"\u001b[39;49m)\n\u001b[1;32m 29\u001b[0m \u001b[39mif\u001b[39;00m task_name \u001b[39m==\u001b[39m \u001b[39m\"\u001b[39m\u001b[39m\"\u001b[39m:\n\u001b[1;32m 30\u001b[0m task_name \u001b[39m=\u001b[39m \u001b[39m\"\u001b[39m\u001b[39mUntitled Task\u001b[39m\u001b[39m\"\u001b[39m\n",
"File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/ipykernel/kernelbase.py:1251\u001b[0m, in \u001b[0;36mKernel.raw_input\u001b[0;34m(self, prompt)\u001b[0m\n\u001b[1;32m 1249\u001b[0m msg \u001b[39m=\u001b[39m \u001b[39m\"\u001b[39m\u001b[39mraw_input was called, but this frontend does not support input requests.\u001b[39m\u001b[39m\"\u001b[39m\n\u001b[1;32m 1250\u001b[0m \u001b[39mraise\u001b[39;00m StdinNotImplementedError(msg)\n\u001b[0;32m-> 1251\u001b[0m \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_input_request(\n\u001b[1;32m 1252\u001b[0m \u001b[39mstr\u001b[39;49m(prompt),\n\u001b[1;32m 1253\u001b[0m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_parent_ident[\u001b[39m\"\u001b[39;49m\u001b[39mshell\u001b[39;49m\u001b[39m\"\u001b[39;49m],\n\u001b[1;32m 1254\u001b[0m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mget_parent(\u001b[39m\"\u001b[39;49m\u001b[39mshell\u001b[39;49m\u001b[39m\"\u001b[39;49m),\n\u001b[1;32m 1255\u001b[0m password\u001b[39m=\u001b[39;49m\u001b[39mFalse\u001b[39;49;00m,\n\u001b[1;32m 1256\u001b[0m )\n",
"File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/ipykernel/kernelbase.py:1295\u001b[0m, in \u001b[0;36mKernel._input_request\u001b[0;34m(self, prompt, ident, parent, password)\u001b[0m\n\u001b[1;32m 1292\u001b[0m \u001b[39mexcept\u001b[39;00m \u001b[39mKeyboardInterrupt\u001b[39;00m:\n\u001b[1;32m 1293\u001b[0m \u001b[39m# re-raise KeyboardInterrupt, to truncate traceback\u001b[39;00m\n\u001b[1;32m 1294\u001b[0m msg \u001b[39m=\u001b[39m \u001b[39m\"\u001b[39m\u001b[39mInterrupted by user\u001b[39m\u001b[39m\"\u001b[39m\n\u001b[0;32m-> 1295\u001b[0m \u001b[39mraise\u001b[39;00m \u001b[39mKeyboardInterrupt\u001b[39;00m(msg) \u001b[39mfrom\u001b[39;00m \u001b[39mNone\u001b[39;00m\n\u001b[1;32m 1296\u001b[0m \u001b[39mexcept\u001b[39;00m \u001b[39mException\u001b[39;00m:\n\u001b[1;32m 1297\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mlog\u001b[39m.\u001b[39mwarning(\u001b[39m\"\u001b[39m\u001b[39mInvalid Message:\u001b[39m\u001b[39m\"\u001b[39m, exc_info\u001b[39m=\u001b[39m\u001b[39mTrue\u001b[39;00m)\n",
"\u001b[0;31mKeyboardInterrupt\u001b[0m: Interrupted by user"
]
}
],
"source": [
"data_processor.set_full_day_skip(True)\n",
"quantiles = [0.01, 0.05, 0.1, 0.15, 0.4, 0.5, 0.6, 0.85, 0.9, 0.95, 0.99]\n",
"quantiles = [0.01, 0.05, 0.1, 0.15, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.85, 0.9, 0.95, 0.99]\n",
"trainer = ProbabilisticBaselineTrainer(\n",
" quantiles=quantiles, data_processor=data_processor, clearml_helper=clearml_helper\n",
")\n",
"trainer.add_metrics_to_track([CRPSLoss(quantiles=quantiles)])\n",
"trainer.add_metrics_to_track([CRPSLoss()])\n",
"trainer.train()"
]
},
@@ -100,7 +116,7 @@
"source": [
"#### Hyperparameters ####\n",
"inputDim = data_processor.get_input_size()\n",
"learningRate = 0.00005\n",
"learningRate = 0.0001\n",
"epochs = 150\n",
"\n",
"# model = LinearRegression(inputDim, 96)\n",
@@ -133,8 +149,8 @@
"learningRate = 0.0003\n",
"epochs = 50\n",
"\n",
"# model = LinearRegression(inputDim, 1)\n",
"model = NonLinearRegression(inputDim, 1, hiddenSize=1024, numLayers=5)\n",
"model = LinearRegression(inputDim, 1)\n",
"# model = NonLinearRegression(inputDim, 1, hiddenSize=1024, numLayers=5)\n",
"optimizer = torch.optim.Adam(model.parameters(), lr=learningRate)\n",
"\n",
"#### Data Processor ####\n",
@@ -167,13 +183,15 @@
},
{
"cell_type": "code",
"execution_count": 4,
"execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"ClearML Task: created new task id=1182d39a984b478c9301aafb4a81ff1b\n",
"ClearML results page: http://192.168.1.182:8080/projects/2e46d4af6f1e4c399cf9f5aa30bc8795/experiments/1182d39a984b478c9301aafb4a81ff1b/output/log\n",
"96\n"
]
},
@@ -181,72 +199,66 @@
"name": "stderr",
"output_type": "stream",
"text": [
"/workspaces/Thesis/src/notebooks/../../src/trainers/quantile_trainer.py:68: UserWarning: 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",
" quantiles_tensor = torch.tensor(quantiles)\n",
"/workspaces/Thesis/src/notebooks/../../src/losses/pinball_loss.py:8: UserWarning: 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",
" self.quantiles_tensor = torch.tensor(quantiles, dtype=torch.float32)\n",
"InsecureRequestWarning: Certificate verification is disabled! Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#ssl-warnings\n"
"Connecting multiple input models with the same name: `checkpoint`. This might result in the wrong model being used when executing remotely\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"ClearML Task: created new task id=4652507a84f5435fb6bd98c645d15f24\n",
"ClearML results page: http://192.168.1.182:8080/projects/2e46d4af6f1e4c399cf9f5aa30bc8795/experiments/4652507a84f5435fb6bd98c645d15f24/output/log\n",
"2023-11-26 22:15:47,860 - clearml.Task - INFO - Storing jupyter notebook directly as code\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Switching to remote execution, output log page http://192.168.1.182:8080/projects/2e46d4af6f1e4c399cf9f5aa30bc8795/experiments/4652507a84f5435fb6bd98c645d15f24/output/log\n"
]
},
{
"ename": "",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31mThe Kernel crashed while executing code in the the current cell or a previous cell. Please review the code in the cell(s) to identify a possible cause of the failure. Click <a href='https://aka.ms/vscodeJupyterKernelCrash'>here</a> for more info. View Jupyter <a href='command:jupyter.viewOutput'>log</a> for further details."
"Early stopping triggered\n"
]
}
],
"source": [
"task = clearml_helper.get_task(task_name=\"Autoregressive Quantile Regression + Quarter + Load Forecast + Load History\")\n",
"data_config = task.connect(data_config, name=\"data_features\")\n",
"\n",
"#### Hyperparameters ####\n",
"data_processor.set_output_size(1)\n",
"inputDim = data_processor.get_input_size()\n",
"learningRate = 0.0001\n",
"epochs = 100\n",
"epochs = 300\n",
"\n",
"# quantiles = torch.tensor([0.01, 0.05, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 0.95, 0.99]).to(\"cuda\")\n",
"quantiles = torch.tensor(\n",
" [0.01, 0.05, 0.1, 0.15, 0.3, 0.4, 0.5, 0.6, 0.7, 0.85, 0.9, 0.95, 0.99]\n",
").to(\"cuda\")\n",
"quantiles = task.get_parameter(\"general/quantiles\", cast=True)\n",
"if quantiles is None:\n",
" quantiles = [0.01, 0.05, 0.1, 0.15, 0.3, 0.4, 0.5, 0.6, 0.7, 0.85, 0.9, 0.95, 0.99]\n",
" task.set_parameter(\"general/quantiles\", quantiles)\n",
"else:\n",
" if isinstance(quantiles, str):\n",
" quantiles = eval(quantiles)\n",
"\n",
"# model = LinearRegression(inputDim, len(quantiles))\n",
"time_embedding = TimeEmbedding(data_processor.get_time_feature_size(), 4)\n",
"non_linear_regression_model = NonLinearRegression(time_embedding.output_dim(inputDim), len(quantiles), hiddenSize=1024, numLayers=5)\n",
"model_parameters = {\n",
" \"learning_rate\": 0.0001,\n",
" \"hidden_size\": 512,\n",
" \"num_layers\": 3,\n",
" \"dropout\": 0.2,\n",
" \"time_feature_embedding\": 2,\n",
"}\n",
"\n",
"model_parameters = task.connect(model_parameters, name=\"model_parameters\")\n",
"\n",
"time_embedding = TimeEmbedding(data_processor.get_time_feature_size(), model_parameters[\"time_feature_embedding\"])\n",
"# linear_regression = LinearRegression(time_embedding.output_dim(inputDim), len(quantiles))\n",
"non_linear_regression_model = NonLinearRegression(time_embedding.output_dim(inputDim), len(quantiles), hiddenSize=model_parameters[\"hidden_size\"], numLayers=model_parameters[\"num_layers\"], dropout=model_parameters[\"dropout\"])\n",
"model = nn.Sequential(time_embedding, non_linear_regression_model)\n",
"optimizer = torch.optim.Adam(model.parameters(), lr=learningRate)\n",
"optimizer = torch.optim.Adam(model.parameters(), lr=model_parameters[\"learning_rate\"])\n",
"\n",
"#### Trainer ####\n",
"trainer = AutoRegressiveQuantileTrainer(\n",
" model,\n",
" inputDim,\n",
" optimizer,\n",
" data_processor,\n",
" quantiles,\n",
" \"cuda\",\n",
" debug=True,\n",
" clearml_helper=clearml_helper,\n",
" debug=False,\n",
")\n",
"trainer.add_metrics_to_track(\n",
" [PinballLoss(quantiles), MSELoss(), L1Loss(), CRPSLoss(quantiles)]\n",
" [PinballLoss(quantiles), MSELoss(), L1Loss(), CRPSLoss()]\n",
")\n",
"trainer.early_stopping(patience=10)\n",
"trainer.plot_every(5)\n",
"trainer.train(epochs=epochs, remotely=True)"
"trainer.train(task=task, epochs=epochs, remotely=False)"
]
},
{
@@ -258,49 +270,9 @@
},
{
"cell_type": "code",
"execution_count": 3,
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/workspaces/Thesis/src/notebooks/../../src/trainers/quantile_trainer.py:335: UserWarning: 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",
" quantiles_tensor = torch.tensor(quantiles)\n",
"/workspaces/Thesis/src/notebooks/../../src/losses/pinball_loss.py:22: UserWarning: 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",
" self.quantiles_tensor = torch.tensor(quantiles, dtype=torch.float32)\n",
"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=0c748cf6ec0f4c748cc35be78ae4c6c1\n",
"ClearML results page: http://192.168.1.182:8080/projects/2e46d4af6f1e4c399cf9f5aa30bc8795/experiments/0c748cf6ec0f4c748cc35be78ae4c6c1/output/log\n",
"2023-11-26 16:15:07,490 - clearml.Task - INFO - Storing jupyter notebook directly as code\n",
"2023-11-26 16:15:09,255 - clearml.model - WARNING - 500 model found when searching for `file:///workspaces/Thesis/src/notebooks/checkpoint.pt`\n",
"2023-11-26 16:15:09,256 - clearml.model - WARNING - Selected model `Autoregressive Quantile Regression (quarter + day of week)` (id=bc0cb0d7fc614e2e8b0edf5b85348646)\n",
"2023-11-26 16:15:09,265 - clearml.frameworks - INFO - Found existing registered model id=bc0cb0d7fc614e2e8b0edf5b85348646 [/workspaces/Thesis/src/notebooks/checkpoint.pt] reusing it.\n",
"2023-11-26 16:15:09,958 - clearml.Task - INFO - Completed model upload to http://192.168.1.182:8081/Thesis/NrvForecast/Untitled%20Task.0c748cf6ec0f4c748cc35be78ae4c6c1/models/checkpoint.pt\n",
"2023-11-26 16:15:10,998 - clearml.Task - INFO - Completed model upload to http://192.168.1.182:8081/Thesis/NrvForecast/Untitled%20Task.0c748cf6ec0f4c748cc35be78ae4c6c1/models/checkpoint.pt\n",
"2023-11-26 16:15:12,118 - clearml.Task - INFO - Completed model upload to http://192.168.1.182:8081/Thesis/NrvForecast/Untitled%20Task.0c748cf6ec0f4c748cc35be78ae4c6c1/models/checkpoint.pt\n",
"2023-11-26 16:15:13,152 - clearml.Task - INFO - Completed model upload to http://192.168.1.182:8081/Thesis/NrvForecast/Untitled%20Task.0c748cf6ec0f4c748cc35be78ae4c6c1/models/checkpoint.pt\n",
"2023-11-26 16:15:14,540 - clearml.Task - INFO - Completed model upload to http://192.168.1.182:8081/Thesis/NrvForecast/Untitled%20Task.0c748cf6ec0f4c748cc35be78ae4c6c1/models/checkpoint.pt\n",
"Early stopping triggered\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/workspaces/Thesis/src/notebooks/../../src/trainers/quantile_trainer.py:366: UserWarning:\n",
"\n",
"Creating a tensor from a list of numpy.ndarrays is extremely slow. Please consider converting the list to a single numpy.ndarray with numpy.array() before converting to a tensor. (Triggered internally at /opt/conda/conda-bld/pytorch_1682343967769/work/torch/csrc/utils/tensor_new.cpp:245.)\n",
"\n"
]
}
],
"outputs": [],
"source": [
"### Data Processor ###\n",
"data_processor.set_full_day_skip(True)\n",

2
src/trainers/autoregressive_trainer.py
View File

@@ -15,6 +15,7 @@ class AutoRegressiveTrainer(Trainer):
def __init__(
self,
model: torch.nn.Module,
input_dim: tuple,
optimizer: torch.optim.Optimizer,
criterion: torch.nn.Module,
data_processor: DataProcessor,
@@ -23,6 +24,7 @@ class AutoRegressiveTrainer(Trainer):
):
super().__init__(
model=model,
input_dim=input_dim,
optimizer=optimizer,
criterion=criterion,
data_processor=data_processor,

10
src/trainers/probabilistic_baseline.py
View File

@@ -48,7 +48,7 @@ class ProbabilisticBaselineTrainer(Trainer):
predict_sequence_length=96
)
for inputs, _ in train_loader:
for inputs, _, _ in train_loader:
for i in range(96):
time_steps[i].extend(inputs[:, i].numpy())
@@ -80,7 +80,7 @@ class ProbabilisticBaselineTrainer(Trainer):
raise
def log_final_metrics(self, task, dataloader, quantile_values, train: bool = True):
metric = CRPSLoss(self.quantiles)
metric = CRPSLoss()
crps_values = []
crps_inversed_values = []
@@ -147,6 +147,9 @@ class ProbabilisticBaselineTrainer(Trainer):
def plot_quantiles(self, quantile_values):
fig = go.Figure()
# inverse transform quantile_values
quantile_values = self.data_processor.inverse_transform(quantile_values)
for i, q in enumerate(self.quantiles):
values_for_quantile = quantile_values[:, i]
fig.add_trace(
@@ -159,7 +162,8 @@ class ProbabilisticBaselineTrainer(Trainer):
)
fig.update_layout(title="Quantile Values")
fig.update_yaxes(range=[-1, 1])
fig.update_layout(height=600)
return fig

46
src/trainers/quantile_trainer.py
View File

@@ -60,6 +60,7 @@ class AutoRegressiveQuantileTrainer(AutoRegressiveTrainer):
def __init__(
self,
model: torch.nn.Module,
input_dim: tuple,
optimizer: torch.optim.Optimizer,
data_processor: DataProcessor,
quantiles: list,
@@ -72,6 +73,7 @@ class AutoRegressiveQuantileTrainer(AutoRegressiveTrainer):
criterion = PinballLoss(quantiles=quantiles)
super().__init__(
model=model,
input_dim=input_dim,
optimizer=optimizer,
criterion=criterion,
data_processor=data_processor,
@@ -192,7 +194,10 @@ class AutoRegressiveQuantileTrainer(AutoRegressiveTrainer):
prev_features = prev_features.to(self.device)
targets = targets.to(self.device)
initial_sequence = prev_features[:, :96]
if len(list(prev_features.shape)) == 2:
initial_sequence = prev_features[:, :96]
else:
initial_sequence = prev_features[:, :, 0]
target_full = targets[:, 0].unsqueeze(1) # (batch_size, 1)
with torch.no_grad():
@@ -206,22 +211,37 @@ class AutoRegressiveQuantileTrainer(AutoRegressiveTrainer):
predictions_full = new_predictions_full.unsqueeze(1)
for i in range(sequence_length - 1):
new_features = torch.cat(
(prev_features[:, 1:96], samples), dim=1
) # (batch_size, 96)
if len(list(prev_features.shape)) == 2:
new_features = torch.cat(
(prev_features[:, 1:96], samples), dim=1
) # (batch_size, 96)
new_features = new_features.float()
new_features = new_features.float()
other_features, new_targets = dataset.get_batch_autoregressive(
np.array(idx_batch) + i + 1
) # (batch_size, new_features)
other_features, new_targets = dataset.get_batch_autoregressive(
np.array(idx_batch) + i + 1
) # (batch_size, new_features)
if other_features is not None:
prev_features = torch.cat(
(new_features.to(self.device), other_features.to(self.device)), dim=1
) # (batch_size, 96 + new_features)
else:
prev_features = new_features
if other_features is not None:
prev_features = torch.cat(
(new_features.to(self.device), other_features.to(self.device)), dim=1
) # (batch_size, 96 + new_features)
else:
prev_features = new_features
other_features, new_targets = dataset.get_batch_autoregressive(
np.array(idx_batch) + i + 1
) # (batch_size, 1, new_features)
# change the other_features nrv based on the samples
other_features[:, 0, 0] = samples.squeeze(-1)
# make sure on same device
other_features = other_features.to(self.device)
prev_features = prev_features.to(self.device)
prev_features = torch.cat(
(prev_features[:, 1:, :], other_features), dim=1
) # (batch_size, 96, new_features)
target_full = torch.cat(
(target_full, new_targets.to(self.device)), dim=1

6
src/trainers/trainer.py
View File

@@ -6,18 +6,20 @@ import plotly.graph_objects as go
import numpy as np
from plotly.subplots import make_subplots
from clearml.config import running_remotely
from torchinfo import summary
class Trainer:
def __init__(
self,
model: torch.nn.Module,
input_dim: tuple,
optimizer: torch.optim.Optimizer,
criterion: torch.nn.Module,
data_processor: DataProcessor,
device: torch.device,
debug: bool = True,
):
self.input_dim = input_dim
self.model = model
self.optimizer = optimizer
self.criterion = criterion
@@ -70,6 +72,8 @@ class Trainer:
task.add_tags(self.optimizer.__class__.__name__)
task.add_tags(self.__class__.__name__)
task.set_configuration_object("model", str(summary(self.model, self.input_dim)))
self.optimizer.name = self.optimizer.__class__.__name__
self.criterion.name = self.criterion.__class__.__name__

45
src/training_scripts/autoregressive_quantiles.py
View File

@@ -17,19 +17,18 @@ from src.models.time_embedding_layer import TimeEmbedding
#### ClearML ####
clearml_helper = ClearMLHelper(project_name="Thesis/NrvForecast")
task = clearml_helper.get_task(task_name="Autoregressive Quantile Regression")
task = clearml_helper.get_task(task_name="Autoregressive Quantile Regression: GRU + Quarter + Load Forecast")
#### Data Processor ####
data_config = DataConfig()
data_config.NRV_HISTORY = True
data_config.LOAD_HISTORY = True
data_config.LOAD_FORECAST = True
data_config.QUARTER = True
data_config.DAY_OF_WEEK = True
data_config.DAY_OF_WEEK = False
# data_config = task.connect(data_config, name="data_features")
data_config = task.connect(data_config, name="data_features")
data_processor = DataProcessor(data_config, path="", lstm=True)
data_processor.set_batch_size(512)
@@ -39,37 +38,49 @@ data_processor.set_full_day_skip(False)
#### Hyperparameters ####
data_processor.set_output_size(1)
inputDim = data_processor.get_input_size()
learningRate = 0.001
epochs = 100
print("Input dim: ", inputDim)
epochs = 400
# add parameters to clearml
quantiles = task.get_parameter("general/quantiles", cast=True)
# make sure it is a list
if quantiles is None:
quantiles = [0.01, 0.05, 0.1, 0.15, 0.3, 0.4, 0.5, 0.6, 0.7, 0.85, 0.9, 0.95, 0.99]
task.set_parameter("general/quantiles", quantiles)
else:
# if string, convert to list "[0.01, 0.05, 0.1, 0.15, 0.3, 0.4, 0.5, 0.6, 0.7, 0.85, 0.9, 0.95, 0.99]""
if isinstance(quantiles, str):
quantiles = eval(quantiles)
model_parameters = {
"learning_rate": 0.0001,
"hidden_size": 512,
"num_layers": 2,
"dropout": 0.2,
"time_feature_embedding": 4,
}
model_parameters = task.connect(model_parameters, name="model_parameters")
time_embedding = TimeEmbedding(data_processor.get_time_feature_size(), model_parameters["time_feature_embedding"])
lstm_model = GRUModel(time_embedding.output_dim(inputDim), len(quantiles), hidden_size=model_parameters["hidden_size"], num_layers=model_parameters["num_layers"], dropout=model_parameters["dropout"])
# model = LinearRegression(inputDim, len(quantiles))
time_embedding = TimeEmbedding(data_processor.get_time_feature_size(), 4)
# non_linear_regression_model = NonLinearRegression(time_embedding.output_dim(inputDim), len(quantiles), hiddenSize=1024, numLayers=5)
lstm_model = GRUModel(time_embedding.output_dim(inputDim), len(quantiles), hidden_size=512, num_layers=2)
model = nn.Sequential(time_embedding, lstm_model)
optimizer = torch.optim.Adam(model.parameters(), lr=learningRate)
optimizer = torch.optim.Adam(model.parameters(), lr=model_parameters["learning_rate"])
#### Trainer ####
trainer = AutoRegressiveQuantileTrainer(
model,
inputDim,
optimizer,
data_processor,
quantiles,
"cuda",
debug=True,
debug=False,
)
trainer.add_metrics_to_track(
[PinballLoss(quantiles), MSELoss(), L1Loss(), CRPSLoss()]
)
trainer.early_stopping(patience=10)
trainer.plot_every(100)
trainer.train(task=task, epochs=epochs, remotely=True)
trainer.early_stopping(patience=30)
trainer.plot_every(5)
trainer.train(task=task, epochs=epochs, remotely=True)

32
src/training_scripts/hyperparameter_optimizer.py
View File

@@ -60,11 +60,16 @@ quantile_lists = [
quantiles_range = DiscreteParameterRange("general/quantiles", values=quantile_lists)
#### Data Config ####
quarter_range = DiscreteParameterRange("data_features/quarter", values=[True, False])
day_of_week_range = DiscreteParameterRange("data_features/day_of_week", values=[True, False])
quarter_range = DiscreteParameterRange("data_features/quarter", values=[True])
day_of_week_range = DiscreteParameterRange("data_features/day_of_week", values=[True])
load_forecast_range = DiscreteParameterRange("data_features/load_forecast", values=[True, False])
load_history_range = DiscreteParameterRange("data_features/load_history", values=[True, False])
load_forecast_range = DiscreteParameterRange("data_features/load_forecast", values=[True])
learning_rate = DiscreteParameterRange("model_parameters/learning_rate", values=[0.00001, 0.00005, 0.0001, 0.0005, 0.001])
hidden_size = DiscreteParameterRange("model_parameters/hidden_size", values=[64, 128, 256, 512, 1024, 2048])
num_layers = DiscreteParameterRange("model_parameters/num_layers", values=[1, 2, 3, 4, 5, 6])
dropout = DiscreteParameterRange("model_parameters/dropout", values=[0.0, 0.1, 0.2, 0.3, 0.4, 0.5])
time_feature_embedding = DiscreteParameterRange("model_parameters/time_feature_embedding", values=[1,2,3,4,5,6])
### OPTIMIZER OBJECT ###
optimizer = HyperParameterOptimizer(
@@ -75,24 +80,27 @@ optimizer = HyperParameterOptimizer(
execution_queue=execution_queue,
max_number_of_concurrent_tasks=1,
optimizer_class=aSearchStrategy,
max_iteration_per_job=50,
max_iteration_per_job=300,
# save_top_k_tasks_only=3,
pool_period_min=0.2,
total_max_jobs=15,
pool_period_min=1,
total_max_jobs=40,
hyper_parameters=[
quantiles_range,
quarter_range,
day_of_week_range,
load_forecast_range,
load_history_range
learning_rate,
hidden_size,
num_layers,
dropout,
time_feature_embedding
]
)
task.execute_remotely(queue_name="hypertuning", exit_process=True)
optimizer.set_report_period(0.2)
optimizer.set_report_period(1)
def job_complete_callback(
job_id, # type: str
@@ -106,9 +114,9 @@ def job_complete_callback(
print('WOOT WOOT we broke the record! Objective reached {}'.format(objective_value))
optimizer.start(job_complete_callback=job_complete_callback)
optimizer.set_time_limit(in_minutes=120.0)
optimizer.set_time_limit(in_minutes=120.0*8)
optimizer.wait()
top_exp = optimizer.get_top_experiments(top_k=3)
top_exp = optimizer.get_top_experiments(top_k=5)
print([t.id for t in top_exp])
# make sure background optimization stopped
optimizer.stop()