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

Added skip in NRVDataset for incomplete samples

Browse Source
This commit is contained in:
Victor Mylle
2023-11-13 15:28:51 +00:00
parent 2f48363292
commit caeba6b841
3 changed files with 59 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
Result-Reports/November_1.md
View File

@@ -2,10 +2,17 @@
## 1. TODOs
- [x] Compare autoregressive vs non-autoregressive
- [ ] Add more input parameters (load forecast)
- [x] Rewrite dataloader for more input parameters (load forecast)
- [ ] Explore more input parameters (load forecast)
- [x] Quantile Regression sampling fix
- [x] Quantile Regression exploration
- [ ] Plots with good scaling (y-axis)
- [x] Plots with good scaling (y-axis)
- [x] Some days in load forecast are missing, remove samples from dataset (Implemented a skip in the NRVDataset)
- [ ] Quantile Regression nakijken
- [ ] Test scores voor 96 values
- [ ] (Optional) Andere modellen (LSTM?)
## 2. Autoregressive vs Non-Autoregressive

42
src/data/dataset.py
View File

@@ -5,29 +5,48 @@ import pandas as pd
class NrvDataset(Dataset):
def __init__(self, dataframe, data_config, sequence_length=96, predict_sequence_length=96):
self.data_config = data_config
self.dataframe = dataframe
# reset dataframe index
self.dataframe.reset_index(drop=True, inplace=True)
self.nrv = torch.tensor(dataframe['nrv'].to_numpy(), dtype=torch.float32)
self.load_forecast = torch.tensor(dataframe['load_forecast'].to_numpy(), dtype=torch.float32)
self.total_load = torch.tensor(dataframe['total_load'].to_numpy(), dtype=torch.float32)
self.sequence_length = sequence_length
self.predict_sequence_length = predict_sequence_length
self.samples_to_skip = self.skip_samples()
total_indices = set(range(len(self.nrv) - self.sequence_length - self.predict_sequence_length))
self.valid_indices = sorted(list(total_indices - set(self.samples_to_skip)))
def skip_samples(self):
nan_rows = self.dataframe[self.dataframe.isnull().any(axis=1)]
nan_indices = nan_rows.index
skip_indices = [list(range(idx-self.sequence_length-self.predict_sequence_length, idx+1)) for idx in nan_indices]
skip_indices = [item for sublist in skip_indices for item in sublist]
skip_indices = list(set(skip_indices))
skip_indices.sort()
return skip_indices
def __len__(self):
return len(self.nrv) - self.sequence_length - self.predict_sequence_length
return len(self.nrv) - self.sequence_length - self.predict_sequence_length - len(self.samples_to_skip)
def __getitem__(self, idx):
actual_idx = self.valid_indices[idx]
features = []
if self.data_config.NRV_HISTORY:
nrv = self.nrv[idx:idx+self.sequence_length]
nrv = self.nrv[actual_idx:actual_idx+self.sequence_length]
features.append(nrv.view(-1))
if self.data_config.LOAD_HISTORY:
load_history = self.load_forecast[idx:idx+self.sequence_length]
load_history = self.total_load[actual_idx:actual_idx+self.sequence_length]
features.append(load_history.view(-1))
if self.data_config.LOAD_FORECAST:
load_forecast = self.load_forecast[idx+self.sequence_length:idx+self.sequence_length+self.predict_sequence_length]
load_forecast = self.load_forecast[actual_idx+self.sequence_length:actual_idx+self.sequence_length+self.predict_sequence_length]
features.append(load_forecast.view(-1))
if not features:
@@ -37,17 +56,24 @@ class NrvDataset(Dataset):
all_features = torch.cat(features, dim=0)
# Target sequence, flattened if necessary
nrv_target = self.nrv[idx+self.sequence_length:idx+self.sequence_length+self.predict_sequence_length].view(-1)
nrv_target = self.nrv[actual_idx+self.sequence_length:actual_idx+self.sequence_length+self.predict_sequence_length].view(-1)
# check if nan values are present
if torch.isnan(all_features).any():
print(f"Found nan values in the features of sample {idx}.")
print(f"Actual index: {actual_idx}")
raise ValueError("There are nan values in the features.")
return all_features, nrv_target
def random_day_autoregressive(self, idx: int):
idx = self.valid_indices[idx]
features = []
# we already have the NRV history with the newly predicted values, so we don't need to include the last 96 values
if self.data_config.LOAD_HISTORY:
load_history = self.load_forecast[idx:idx+self.sequence_length]
load_history = self.total_load[idx:idx+self.sequence_length]
features.append(load_history.view(-1))
if self.data_config.LOAD_FORECAST:

23
src/data/preprocessing.py
View File

@@ -62,16 +62,18 @@ class DataProcessor:
def get_load_forecast(self):
df = pd.read_csv(forecast_data_path, delimiter=';')
df = df.rename(columns={'Day-ahead 6PM forecast': 'load_forecast', 'Datetime': 'datetime'})
df = df[['datetime', 'load_forecast']]
df = df.rename(columns={'Day-ahead 6PM forecast': 'load_forecast', 'Datetime': 'datetime', 'Total Load': 'total_load'})
df = df[['datetime', 'load_forecast', 'total_load']]
df['datetime'] = pd.to_datetime(df['datetime'], utc=True)
# check if there are nan values
# if df.isnull().values.any():
# # print the rows with nan values
# print(df[df.isnull().any(axis=1)])
# raise ValueError("There are nan values in the load forecast data.")
if df.isnull().values.any():
# print the rows with nan values
# print(df[df.isnull().any(axis=1)])
# export to temp csv
df[df.isnull().any(axis=1)].to_csv("temp.csv")
# raise ValueError("There are nan values in the load forecast data.")
df.sort_values(by="datetime", inplace=True)
return df
@@ -94,6 +96,7 @@ class DataProcessor:
if transform:
train_df['nrv'] = self.nrv_scaler.fit_transform(train_df['nrv'].values.reshape(-1, 1)).reshape(-1)
train_df['load_forecast'] = self.load_forecast_scaler.fit_transform(train_df['load_forecast'].values.reshape(-1, 1)).reshape(-1)
train_df['total_load'] = self.load_forecast_scaler.transform(train_df['total_load'].values.reshape(-1, 1)).reshape(-1)
train_dataset = NrvDataset(train_df, data_config=self.data_config, predict_sequence_length=predict_sequence_length)
return self.get_dataloader(train_dataset)
@@ -111,6 +114,7 @@ class DataProcessor:
if transform:
test_df['nrv'] = self.nrv_scaler.transform(test_df['nrv'].values.reshape(-1, 1)).reshape(-1)
test_df['load_forecast'] = self.load_forecast_scaler.transform(test_df['load_forecast'].values.reshape(-1, 1)).reshape(-1)
test_df['total_load'] = self.load_forecast_scaler.transform(test_df['total_load'].values.reshape(-1, 1)).reshape(-1)
test_dataset = NrvDataset(test_df, data_config=self.data_config, predict_sequence_length=predict_sequence_length)
return self.get_dataloader(test_dataset, shuffle=False)
@@ -120,4 +124,9 @@ class DataProcessor:
return self.get_train_dataloader(transform=transform, predict_sequence_length=predict_sequence_length), self.get_test_dataloader(transform=transform, predict_sequence_length=predict_sequence_length)
def inverse_transform(self, tensor: torch.Tensor):
return self.nrv_scaler.inverse_transform(tensor.cpu().numpy()).reshape(-1)
return self.nrv_scaler.inverse_transform(tensor.cpu().numpy()).reshape(-1)
def get_input_size(self):
data_loader = self.get_train_dataloader()
input, _ = next(iter(data_loader))
return input.shape[-1]