ocf-data-sampler 0.5.13__py3-none-any.whl → 0.5.15__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Potentially problematic release.

This version of ocf-data-sampler might be problematic. Click here for more details.

Files changed (10) hide show
  1. ocf_data_sampler/config/model.py +8 -34
  2. ocf_data_sampler/select/dropout.py +30 -32
  3. ocf_data_sampler/torch_datasets/datasets/pvnet_uk.py +7 -7
  4. ocf_data_sampler/torch_datasets/datasets/site.py +7 -7
  5. ocf_data_sampler/torch_datasets/utils/config_normalization_values_to_dicts.py +29 -27
  6. ocf_data_sampler/torch_datasets/utils/time_slice_for_dataset.py +12 -28
  7. {ocf_data_sampler-0.5.13.dist-info → ocf_data_sampler-0.5.15.dist-info}/METADATA +1 -1
  8. {ocf_data_sampler-0.5.13.dist-info → ocf_data_sampler-0.5.15.dist-info}/RECORD +10 -10
  9. {ocf_data_sampler-0.5.13.dist-info → ocf_data_sampler-0.5.15.dist-info}/WHEEL +0 -0
  10. {ocf_data_sampler-0.5.13.dist-info → ocf_data_sampler-0.5.15.dist-info}/top_level.txt +0 -0
ocf_data_sampler/config/model.py CHANGED
@@ -90,7 +90,7 @@ class DropoutMixin(Base):
90
90
  "negative or zero.",
91
91
  )
92
92
 
93
- dropout_fraction: float|list[float] = Field(
93
+ dropout_fraction: float | list[float] = Field(
94
94
  default=0,
95
95
  description="Either a float(Chance of dropout being applied to each sample) or a list of "
96
96
  "floats (probability that dropout of the corresponding timedelta is applied)",
@@ -106,31 +106,22 @@ class DropoutMixin(Base):
106
106
 
107
107
 
108
108
  @field_validator("dropout_fraction")
109
- def dropout_fractions(cls, dropout_frac: float|list[float]) -> float|list[float]:
109
+ def dropout_fractions(cls, dropout_frac: float | list[float]) -> float | list[float]:
110
110
  """Validate 'dropout_frac'."""
111
- from math import isclose
112
- if isinstance(dropout_frac, float):
113
- if not (dropout_frac <= 1):
114
- raise ValueError("Input should be less than or equal to 1")
115
- elif not (dropout_frac >= 0):
116
- raise ValueError("Input should be greater than or equal to 0")
111
+ if isinstance(dropout_frac, float | int):
112
+ if not (0<= dropout_frac <= 1):
113
+ raise ValueError("Dropout fractions must be in range [0, 1]")
117
114
 
118
115
  elif isinstance(dropout_frac, list):
119
116
  if not dropout_frac:
120
117
  raise ValueError("List cannot be empty")
121
118
 
122
- if not all(isinstance(i, float) for i in dropout_frac):
123
- raise ValueError("All elements in the list must be floats")
124
-
125
119
  if not all(0 <= i <= 1 for i in dropout_frac):
126
- raise ValueError("Each float in the list must be between 0 and 1")
127
-
128
- if not isclose(sum(dropout_frac), 1.0, rel_tol=1e-9):
129
- raise ValueError("Sum of all floats in the list must be 1.0")
120
+ raise ValueError("All dropout fractions must be in range [0, 1]")
130
121
 
122
+ if not (0 <= sum(dropout_frac) <= 1):
123
+ raise ValueError("The sum of dropout fractions must be in range [0, 1]")
131
124
 
132
- else:
133
- raise TypeError("Must be either a float or a list of floats")
134
125
  return dropout_frac
135
126
 
136
127
 
@@ -172,23 +163,6 @@ class NormalisationConstantsMixin(Base):
172
163
  """Normalisation constants for multiple channels."""
173
164
  normalisation_constants: dict[str, NormalisationValues]
174
165
 
175
- @property
176
- def channel_means(self) -> dict[str, float]:
177
- """Return the channel means."""
178
- return {
179
- channel: norm_values.mean
180
- for channel, norm_values in self.normalisation_constants.items()
181
- }
182
-
183
-
184
- @property
185
- def channel_stds(self) -> dict[str, float]:
186
- """Return the channel standard deviations."""
187
- return {
188
- channel: norm_values.std
189
- for channel, norm_values in self.normalisation_constants.items()
190
- }
191
-
192
166
 
193
167
  class Satellite(TimeWindowMixin, DropoutMixin, SpatialWindowMixin, NormalisationConstantsMixin):
194
168
  """Satellite configuration model."""
ocf_data_sampler/select/dropout.py CHANGED
@@ -9,53 +9,51 @@ import pandas as pd
9
9
  import xarray as xr
10
10
 
11
11
 
12
- def apply_sampled_dropout_time(
12
+ def apply_history_dropout(
13
13
  t0: pd.Timestamp,
14
14
  dropout_timedeltas: list[pd.Timedelta],
15
- dropout_frac: float|list[float],
15
+ dropout_frac: float | list[float],
16
16
  da: xr.DataArray,
17
17
  ) -> xr.DataArray:
18
- """Randomly pick a dropout time from a list of timedeltas and apply dropout time to the data.
18
+ """Apply randomly sampled dropout to the historical part of some sequence data.
19
+
20
+ Dropped out data is replaced with NaNs
19
21
 
20
22
  Args:
21
- t0: The forecast init-time
23
+ t0: The forecast init-time.
22
24
  dropout_timedeltas: List of timedeltas relative to t0 to pick from
23
- dropout_frac: Either a probability that dropout will be applied.
24
- This should be between 0 and 1 inclusive.
25
- Or a list of probabilities for each of the corresponding timedeltas
25
+ dropout_frac: The probabilit(ies) that each dropout timedelta will be applied. This should
26
+ be between 0 and 1 inclusive.
26
27
  da: Xarray DataArray with 'time_utc' coordinate
27
28
  """
28
- if isinstance(dropout_frac, list):
29
- # checking if len match
30
- if len(dropout_frac) != len(dropout_timedeltas):
31
- raise ValueError("Lengths of dropout_frac and dropout_timedeltas should match")
29
+ if len(dropout_timedeltas)==0:
30
+ return da
32
31
 
32
+ if isinstance(dropout_frac, float | int):
33
33
 
34
+ if not (0<=dropout_frac<=1):
35
+ raise ValueError("`dropout_frac` must be in range [0, 1]")
34
36
 
37
+ # Create list with equal chance for all dropout timedeltas
38
+ n = len(dropout_timedeltas)
39
+ dropout_frac = [dropout_frac/n for _ in range(n)]
40
+ else:
41
+ if not 0<=sum(dropout_frac)<=1:
42
+ raise ValueError("The sum of `dropout_frac` must be in range [0, 1]")
43
+ if len(dropout_timedeltas)!=len(dropout_frac):
44
+ raise ValueError("`dropout_timedeltas` and `dropout_frac` must have the same length")
35
45
 
36
- dropout_time = t0 + np.random.choice(dropout_timedeltas,p=dropout_frac)
46
+ dropout_frac = [*dropout_frac] # Make copy of the list so we can append to it
37
47
 
38
- return da.where(da.time_utc <= dropout_time)
48
+ dropout_timedeltas = [*dropout_timedeltas] # Make copy of the list so we can append to it
39
49
 
50
+ # Add chance of no dropout
51
+ dropout_frac.append(1-sum(dropout_frac))
52
+ dropout_timedeltas.append(None)
40
53
 
54
+ timedelta_choice = np.random.choice(dropout_timedeltas, p=dropout_frac)
41
55
 
42
- # old logic
56
+ if timedelta_choice is None:
57
+ return da
43
58
  else:
44
- # sample dropout time
45
- if dropout_frac > 0 and len(dropout_timedeltas) == 0:
46
- raise ValueError("To apply dropout, dropout_timedeltas must be provided")
47
-
48
-
49
- if not (0 <= dropout_frac <= 1):
50
- raise ValueError("dropout_frac must be between 0 and 1 inclusive")
51
-
52
- if (len(dropout_timedeltas) == 0) or (np.random.uniform() >= dropout_frac):
53
- dropout_time = None
54
- else:
55
- dropout_time = t0 + np.random.choice(dropout_timedeltas)
56
-
57
- # apply dropout time
58
- if dropout_time is None:
59
- return da
60
- # This replaces the times after the dropout with NaNs
61
- return da.where(da.time_utc <= dropout_time)
59
+ return da.where((da.time_utc <= timedelta_choice + t0) | (da.time_utc> t0))
ocf_data_sampler/torch_datasets/datasets/pvnet_uk.py CHANGED
@@ -137,10 +137,10 @@ class AbstractPVNetUKDataset(Dataset):
137
137
  for nwp_key, da_nwp in dataset_dict["nwp"].items():
138
138
 
139
139
  # Standardise and convert to NumpyBatch
140
- da_channel_means = self.means_dict["nwp"][nwp_key]
141
- da_channel_stds = self.stds_dict["nwp"][nwp_key]
140
+ channel_means = self.means_dict["nwp"][nwp_key]
141
+ channel_stds = self.stds_dict["nwp"][nwp_key]
142
142
 
143
- da_nwp = (da_nwp - da_channel_means) / da_channel_stds
143
+ da_nwp = (da_nwp - channel_means) / channel_stds
144
144
 
145
145
  nwp_numpy_modalities[nwp_key] = convert_nwp_to_numpy_sample(da_nwp)
146
146
 
@@ -151,17 +151,17 @@ class AbstractPVNetUKDataset(Dataset):
151
151
  da_sat = dataset_dict["sat"]
152
152
 
153
153
  # Standardise and convert to NumpyBatch
154
- da_channel_means = self.means_dict["sat"]
155
- da_channel_stds = self.stds_dict["sat"]
154
+ channel_means = self.means_dict["sat"]
155
+ channel_stds = self.stds_dict["sat"]
156
156
 
157
- da_sat = (da_sat - da_channel_means) / da_channel_stds
157
+ da_sat = (da_sat - channel_means) / channel_stds
158
158
 
159
159
  numpy_modalities.append(convert_satellite_to_numpy_sample(da_sat))
160
160
 
161
161
  if "gsp" in dataset_dict:
162
162
  gsp_config = self.config.input_data.gsp
163
163
  da_gsp = dataset_dict["gsp"]
164
- da_gsp = da_gsp / da_gsp.effective_capacity_mwp
164
+ da_gsp = da_gsp / da_gsp.effective_capacity_mwp.values
165
165
 
166
166
  # Convert to NumpyBatch
167
167
  numpy_modalities.append(
ocf_data_sampler/torch_datasets/datasets/site.py CHANGED
@@ -82,10 +82,10 @@ def process_and_combine_datasets(
82
82
 
83
83
  # Standardise and convert to NumpyBatch
84
84
 
85
- da_channel_means = means_dict["nwp"][nwp_key]
86
- da_channel_stds = stds_dict["nwp"][nwp_key]
85
+ channel_means = means_dict["nwp"][nwp_key]
86
+ channel_stds = stds_dict["nwp"][nwp_key]
87
87
 
88
- da_nwp = (da_nwp - da_channel_means) / da_channel_stds
88
+ da_nwp = (da_nwp - channel_means) / channel_stds
89
89
 
90
90
  nwp_numpy_modalities[nwp_key] = convert_nwp_to_numpy_sample(da_nwp)
91
91
 
@@ -96,16 +96,16 @@ def process_and_combine_datasets(
96
96
  da_sat = dataset_dict["sat"]
97
97
 
98
98
  # Standardise and convert to NumpyBatch
99
- da_channel_means = means_dict["sat"]
100
- da_channel_stds = stds_dict["sat"]
99
+ channel_means = means_dict["sat"]
100
+ channel_stds = stds_dict["sat"]
101
101
 
102
- da_sat = (da_sat - da_channel_means) / da_channel_stds
102
+ da_sat = (da_sat - channel_means) / channel_stds
103
103
 
104
104
  numpy_modalities.append(convert_satellite_to_numpy_sample(da_sat))
105
105
 
106
106
  if "site" in dataset_dict:
107
107
  da_sites = dataset_dict["site"]
108
- da_sites = da_sites / da_sites.capacity_kwp
108
+ da_sites = da_sites / da_sites.capacity_kwp.values
109
109
 
110
110
  # Convert to NumpyBatch
111
111
  numpy_modalities.append(convert_site_to_numpy_sample(da_sites))
ocf_data_sampler/torch_datasets/utils/config_normalization_values_to_dicts.py CHANGED
@@ -1,28 +1,14 @@
1
- """Utility function for converting channel dictionaries to xarray DataArrays."""
1
+ """Utility function for converting normalisation constants in the config to arrays."""
2
2
 
3
- import xarray as xr
3
+ import numpy as np
4
4
 
5
5
  from ocf_data_sampler.config import Configuration
6
6
 
7
7
 
8
- def channel_dict_to_dataarray(channel_dict: dict[str, float]) -> xr.DataArray:
9
- """Converts a dictionary of channel values to a DataArray.
10
-
11
- Args:
12
- channel_dict: Dictionary mapping channel names (str) to their values (float).
13
-
14
- Returns:
15
- xr.DataArray: A 1D DataArray with channels as coordinates.
16
- """
17
- return xr.DataArray(
18
- list(channel_dict.values()),
19
- coords={"channel": list(channel_dict.keys())},
20
- )
21
-
22
8
  def config_normalization_values_to_dicts(
23
9
  config: Configuration,
24
- ) -> tuple[dict[str, xr.DataArray | dict[str, xr.DataArray]]]:
25
- """Construct DataArrays of mean and std values from the config normalisation constants.
10
+ ) -> tuple[dict[str, np.ndarray | dict[str, np.ndarray]]]:
11
+ """Construct numpy arrays of mean and std values from the config normalisation constants.
26
12
 
27
13
  Args:
28
14
  config: Data configuration.
@@ -40,18 +26,34 @@ def config_normalization_values_to_dicts(
40
26
  stds_dict["nwp"] = {}
41
27
 
42
28
  for nwp_key in config.input_data.nwp:
43
- # Standardise and convert to NumpyBatch
29
+ nwp_config = config.input_data.nwp[nwp_key]
44
30
 
45
- means_dict["nwp"][nwp_key] = channel_dict_to_dataarray(
46
- config.input_data.nwp[nwp_key].channel_means,
47
- )
48
- stds_dict["nwp"][nwp_key] = channel_dict_to_dataarray(
49
- config.input_data.nwp[nwp_key].channel_stds,
50
- )
31
+ means_list = []
32
+ stds_list = []
33
+
34
+ for channel in list(nwp_config.channels):
35
+ # These accumulated channels are diffed and renamed
36
+ if channel in nwp_config.accum_channels:
37
+ channel =f"diff_{channel}"
38
+
39
+ means_list.append(nwp_config.normalisation_constants[channel].mean)
40
+ stds_list.append(nwp_config.normalisation_constants[channel].std)
41
+
42
+ means_dict["nwp"][nwp_key] = np.array(means_list)[None, :, None, None]
43
+ stds_dict["nwp"][nwp_key] = np.array(stds_list)[None, :, None, None]
51
44
 
52
45
  if config.input_data.satellite is not None:
46
+ sat_config = config.input_data.satellite
47
+
48
+ means_list = []
49
+ stds_list = []
50
+
51
+ for channel in list(config.input_data.satellite.channels):
52
+ means_list.append(sat_config.normalisation_constants[channel].mean)
53
+ stds_list.append(sat_config.normalisation_constants[channel].std)
53
54
 
54
- means_dict["sat"] = channel_dict_to_dataarray(config.input_data.satellite.channel_means)
55
- stds_dict["sat"] = channel_dict_to_dataarray(config.input_data.satellite.channel_stds)
55
+ # Convert to array and expand dimensions so we can normalise the 4D sat and NWP sources
56
+ means_dict["sat"] = np.array(means_list)[None, :, None, None]
57
+ stds_dict["sat"] = np.array(stds_list)[None, :, None, None]
56
58
 
57
59
  return means_dict, stds_dict
ocf_data_sampler/torch_datasets/utils/time_slice_for_dataset.py CHANGED
@@ -1,10 +1,9 @@
1
1
  """Slice datasets by time."""
2
2
 
3
3
  import pandas as pd
4
- import xarray as xr
5
4
 
6
5
  from ocf_data_sampler.config import Configuration
7
- from ocf_data_sampler.select.dropout import apply_sampled_dropout_time
6
+ from ocf_data_sampler.select.dropout import apply_history_dropout
8
7
  from ocf_data_sampler.select.select_time_slice import select_time_slice, select_time_slice_nwp
9
8
  from ocf_data_sampler.utils import minutes
10
9
 
@@ -52,7 +51,7 @@ def slice_datasets_by_time(
52
51
  )
53
52
 
54
53
  # Apply the randomly sampled dropout
55
- sliced_datasets_dict["sat"] = apply_sampled_dropout_time(
54
+ sliced_datasets_dict["sat"] = apply_history_dropout(
56
55
  t0,
57
56
  dropout_timedeltas=minutes(sat_config.dropout_timedeltas_minutes),
58
57
  dropout_frac=sat_config.dropout_fraction,
@@ -62,59 +61,44 @@ def slice_datasets_by_time(
62
61
  if "gsp" in datasets_dict:
63
62
  gsp_config = config.input_data.gsp
64
63
 
65
- da_gsp_past = select_time_slice(
64
+ da_gsp = select_time_slice(
66
65
  datasets_dict["gsp"],
67
66
  t0,
68
67
  time_resolution=minutes(gsp_config.time_resolution_minutes),
69
68
  interval_start=minutes(gsp_config.interval_start_minutes),
70
- interval_end=minutes(0),
69
+ interval_end=minutes(gsp_config.interval_end_minutes),
71
70
  )
72
71
 
73
72
  # Dropout on the past GSP, but not the future GSP
74
- da_gsp_past = apply_sampled_dropout_time(
73
+ da_gsp = apply_history_dropout(
75
74
  t0,
76
75
  dropout_timedeltas=minutes(gsp_config.dropout_timedeltas_minutes),
77
76
  dropout_frac=gsp_config.dropout_fraction,
78
- da=da_gsp_past,
79
- )
80
-
81
- da_gsp_future = select_time_slice(
82
- datasets_dict["gsp"],
83
- t0,
84
- time_resolution=minutes(gsp_config.time_resolution_minutes),
85
- interval_start=minutes(gsp_config.time_resolution_minutes),
86
- interval_end=minutes(gsp_config.interval_end_minutes),
77
+ da=da_gsp,
87
78
  )
88
79
 
89
- sliced_datasets_dict["gsp"] = xr.concat([da_gsp_past, da_gsp_future], dim="time_utc")
80
+ sliced_datasets_dict["gsp"] = da_gsp
90
81
 
91
82
  if "site" in datasets_dict:
92
83
  site_config = config.input_data.site
93
84
 
94
- da_site_past = select_time_slice(
85
+ da_site = select_time_slice(
95
86
  datasets_dict["site"],
96
87
  t0,
97
88
  time_resolution=minutes(site_config.time_resolution_minutes),
98
89
  interval_start=minutes(site_config.interval_start_minutes),
99
- interval_end=minutes(0),
90
+ interval_end=minutes(site_config.interval_end_minutes),
100
91
  )
101
92
 
102
93
  # Apply the randomly sampled dropout on the past site not the future
103
- da_site_past = apply_sampled_dropout_time(
94
+ da_site = apply_history_dropout(
104
95
  t0,
105
96
  dropout_timedeltas=minutes(site_config.dropout_timedeltas_minutes),
106
97
  dropout_frac=site_config.dropout_fraction,
107
- da=da_site_past,
98
+ da=da_site,
108
99
  )
109
100
 
110
- da_site_future = select_time_slice(
111
- datasets_dict["site"],
112
- t0,
113
- time_resolution=minutes(site_config.time_resolution_minutes),
114
- interval_start=minutes(site_config.time_resolution_minutes),
115
- interval_end=minutes(site_config.interval_end_minutes),
116
- )
101
+ sliced_datasets_dict["site"] = da_site
117
102
 
118
- sliced_datasets_dict["site"] = xr.concat([da_site_past, da_site_future], dim="time_utc")
119
103
 
120
104
  return sliced_datasets_dict
{ocf_data_sampler-0.5.13.dist-info → ocf_data_sampler-0.5.15.dist-info}/METADATA RENAMED
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: ocf-data-sampler
3
- Version: 0.5.13
3
+ Version: 0.5.15
4
4
  Author: James Fulton, Peter Dudfield
5
5
  Author-email: Open Climate Fix team <info@openclimatefix.org>
6
6
  License: MIT License
{ocf_data_sampler-0.5.13.dist-info → ocf_data_sampler-0.5.15.dist-info}/RECORD RENAMED
@@ -2,7 +2,7 @@ ocf_data_sampler/__init__.py,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,
2
2
  ocf_data_sampler/utils.py,sha256=CTJf9bjHjO8vOJebUtXiMpvgwUpF7gEOjjaoE77fhTk,1177
3
3
  ocf_data_sampler/config/__init__.py,sha256=O29mbH0XG2gIY1g3BaveGCnpBO2SFqdu-qzJ7a6evl0,223
4
4
  ocf_data_sampler/config/load.py,sha256=LL-7wemI8o4KPkx35j-wQ3HjsMvDgqXr7G46IcASfnU,632
5
- ocf_data_sampler/config/model.py,sha256=Jss8UDJAaQIBDr9megX2pERoT0ocFmwLNFC8pCWN6VA,12386
5
+ ocf_data_sampler/config/model.py,sha256=5ou8BZgQ9h-xyJEqHdspPKZgZO9Vr6opjSphUys7yE8,11505
6
6
  ocf_data_sampler/config/save.py,sha256=m8SPw5rXjkMm1rByjh3pK5StdBi4e8ysnn3jQopdRaI,1064
7
7
  ocf_data_sampler/data/uk_gsp_locations_20220314.csv,sha256=RSh7DRh55E3n8lVAaWXGTaXXHevZZtI58td4d4DhGos,10415772
8
8
  ocf_data_sampler/data/uk_gsp_locations_20250109.csv,sha256=XZISFatnbpO9j8LwaxNKFzQSjs6hcHFsV8a9uDDpy2E,9055334
@@ -32,7 +32,7 @@ ocf_data_sampler/numpy_sample/satellite.py,sha256=RaYzYIcB1AmDrKeiqSpn4QVfBH-QMe
32
32
  ocf_data_sampler/numpy_sample/site.py,sha256=4S19bzCN5lswVUrmWRfwpVsBPUE7bi0OIdxsD9wgvhU,982
33
33
  ocf_data_sampler/numpy_sample/sun_position.py,sha256=5tt-zNm6aRuZMsxZPaAxyg7HeikswfZCeHWXTHuO2K0,1555
34
34
  ocf_data_sampler/select/__init__.py,sha256=mK7Wu_-j9IXGTYrOuDf5yDDuU5a306b0iGKTAooNg_s,210
35
- ocf_data_sampler/select/dropout.py,sha256=BYpv8L771faPOyN7SdIJ5cwkpDve-ohClj95jjsHmjg,1973
35
+ ocf_data_sampler/select/dropout.py,sha256=i5NDP6oQnZBkQRJW-aXVrPXawktVKQz5VMexe5Ww51g,2021
36
36
  ocf_data_sampler/select/fill_time_periods.py,sha256=TlGxp1xiAqnhdWfLy0pv3FuZc00dtimjWdLzr4JoTGA,865
37
37
  ocf_data_sampler/select/find_contiguous_time_periods.py,sha256=etkr6LuB7zxkfzWJ6SgHiULdRuFzFlq5bOUNd257Qx4,11545
38
38
  ocf_data_sampler/select/geospatial.py,sha256=rvMy_e--3tm-KAy9pU6b9-UMBQqH2sXykr3N_4SHYy4,6528
@@ -40,23 +40,23 @@ ocf_data_sampler/select/location.py,sha256=Qp0di-Pgq8WLjN9IBcTVTaRM3lckhr4ZVzaDR
40
40
  ocf_data_sampler/select/select_spatial_slice.py,sha256=Ym_YJjZqeMPC5Bw_xMi7Re2-uCbUagm2KXhnAnstTHo,7200
41
41
  ocf_data_sampler/select/select_time_slice.py,sha256=HeHbwZ0CP03x0-LaJtpbSdtpLufwVTR73p6wH6O_PS8,5513
42
42
  ocf_data_sampler/torch_datasets/datasets/__init__.py,sha256=o0SsEXXZ6k9iL__5_RN1Sf60lw_eqK91P3UFEHAD2k0,102
43
- ocf_data_sampler/torch_datasets/datasets/pvnet_uk.py,sha256=1uwcbEKakXsqr_ZcSjpzf3esP5tA_YVlYgtj9vBjtdM,12115
44
- ocf_data_sampler/torch_datasets/datasets/site.py,sha256=Z7pyuR3VHEJf8egxnZvpsdgBv7fMg2pSc61ORAuqOwQ,15607
43
+ ocf_data_sampler/torch_datasets/datasets/pvnet_uk.py,sha256=wVx4QKHqak2FbxtryAxsVe6wpYM2n_YKgIKpiVs6gpE,12098
44
+ ocf_data_sampler/torch_datasets/datasets/site.py,sha256=ivdSB_YpAqL8-Q1m_uKTGU2YlNQ1bZXdwialT_UpGuo,15590
45
45
  ocf_data_sampler/torch_datasets/sample/__init__.py,sha256=GL84vdZl_SjHDGVyh9Uekx2XhPYuZ0dnO3l6f6KXnHI,100
46
46
  ocf_data_sampler/torch_datasets/sample/base.py,sha256=cQ1oIyhdmlotejZK8B3Cw6MNvpdnBPD8G_o2h7Ye4Vc,2206
47
47
  ocf_data_sampler/torch_datasets/sample/site.py,sha256=40NwNTqjL1WVhPdwe02zDHHfDLG2u_bvCfRCtGAtFc0,1466
48
48
  ocf_data_sampler/torch_datasets/sample/uk_regional.py,sha256=Xx5cBYUyaM6PGUWQ76MHT9hwj6IJ7WAOxbpmYFbJGhc,10483
49
49
  ocf_data_sampler/torch_datasets/utils/__init__.py,sha256=TNSYuSSmFgjsvvJxtoDrH645Z64CHsNUUQ0iayTccP4,416
50
50
  ocf_data_sampler/torch_datasets/utils/add_alterate_coordinate_projections.py,sha256=w6Q4TyxNyl7PKAbhqiXvqOpnqIjwmOUcGREIvPNGYlQ,2666
51
- ocf_data_sampler/torch_datasets/utils/config_normalization_values_to_dicts.py,sha256=jS3DkAwOF1W3AQnvsdkBJ1C8Unm93kQbS8hgTCtFv2A,1743
51
+ ocf_data_sampler/torch_datasets/utils/config_normalization_values_to_dicts.py,sha256=SGt1H2nXcaj44ND14-gHzvA7dkLfgjTacCq7rOkRGwg,1991
52
52
  ocf_data_sampler/torch_datasets/utils/merge_and_fill_utils.py,sha256=we7BTxRH7B7jKayDT7YfNyfI3zZClz2Bk-HXKQIokgU,956
53
53
  ocf_data_sampler/torch_datasets/utils/spatial_slice_for_dataset.py,sha256=Hvz0wHSWMYYamf2oHNiGlzJcM4cAH6pL_7ZEvIBL2dE,1882
54
- ocf_data_sampler/torch_datasets/utils/time_slice_for_dataset.py,sha256=8E4a5v9dqr-sZOyBruuO-tjLPBbjtpYtdFY5z23aqnU,4365
54
+ ocf_data_sampler/torch_datasets/utils/time_slice_for_dataset.py,sha256=Q_-kCTtUieyEDpSElY1xwJct7Vsw0LAn5MbYSg2O6vg,3621
55
55
  ocf_data_sampler/torch_datasets/utils/valid_time_periods.py,sha256=xcy75cVxl0WrglnX5YUAFjXXlO2GwEBHWyqo8TDuiOA,4714
56
56
  ocf_data_sampler/torch_datasets/utils/validation_utils.py,sha256=YqmT-lExWlI8_ul3l0EP73Ik002fStr_bhsZh9mQqEU,4735
57
57
  scripts/download_gsp_location_data.py,sha256=rRDXMoqX-RYY4jPdxhdlxJGhWdl6r245F5UARgKV6P4,3121
58
58
  scripts/refactor_site.py,sha256=skzvsPP0Cn9yTKndzkilyNcGz4DZ88ctvCJ0XrBdc2A,3135
59
- ocf_data_sampler-0.5.13.dist-info/METADATA,sha256=1PrPyQawUd1CYnPf2z6ZCn16aLFKr-7OIKTVlaBIELI,12817
60
- ocf_data_sampler-0.5.13.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
61
- ocf_data_sampler-0.5.13.dist-info/top_level.txt,sha256=deUxqmsONNAGZDNbsntbXH7BRA1MqWaUeAJrCo6q_xA,25
62
- ocf_data_sampler-0.5.13.dist-info/RECORD,,
59
+ ocf_data_sampler-0.5.15.dist-info/METADATA,sha256=AcLJpUOG6smk3WDSZkj3K8cjhvSg9z0lPoEKM16B6q8,12817
60
+ ocf_data_sampler-0.5.15.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
61
+ ocf_data_sampler-0.5.15.dist-info/top_level.txt,sha256=deUxqmsONNAGZDNbsntbXH7BRA1MqWaUeAJrCo6q_xA,25
62
+ ocf_data_sampler-0.5.15.dist-info/RECORD,,