openstef 3.4.24__py3-none-any.whl → 3.4.25__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.
- openstef/model/regressors/dazls.py +28 -107
- openstef/pipeline/create_component_forecast.py +2 -19
- {openstef-3.4.24.dist-info → openstef-3.4.25.dist-info}/METADATA +1 -1
- {openstef-3.4.24.dist-info → openstef-3.4.25.dist-info}/RECORD +7 -25
- openstef/data/dazls_model_3.4.7/dazls_stored_3.4.7_adaptation_model.z +0 -0
- openstef/data/dazls_model_3.4.7/dazls_stored_3.4.7_adaptation_model.z.license +0 -3
- openstef/data/dazls_model_3.4.7/dazls_stored_3.4.7_adaptation_model_features.z +0 -0
- openstef/data/dazls_model_3.4.7/dazls_stored_3.4.7_adaptation_model_features.z.license +0 -3
- openstef/data/dazls_model_3.4.7/dazls_stored_3.4.7_adaptation_model_scaler.z +0 -0
- openstef/data/dazls_model_3.4.7/dazls_stored_3.4.7_adaptation_model_scaler.z.license +0 -3
- openstef/data/dazls_model_3.4.7/dazls_stored_3.4.7_domain_model.z +0 -0
- openstef/data/dazls_model_3.4.7/dazls_stored_3.4.7_domain_model.z.license +0 -3
- openstef/data/dazls_model_3.4.7/dazls_stored_3.4.7_domain_model_features.z +0 -2
- openstef/data/dazls_model_3.4.7/dazls_stored_3.4.7_domain_model_features.z.license +0 -3
- openstef/data/dazls_model_3.4.7/dazls_stored_3.4.7_domain_model_scaler.z +0 -0
- openstef/data/dazls_model_3.4.7/dazls_stored_3.4.7_domain_model_scaler.z.license +0 -3
- openstef/data/dazls_model_3.4.7/dazls_stored_3.4.7_model_card.md +0 -14
- openstef/data/dazls_model_3.4.7/dazls_stored_3.4.7_model_card.md.license +0 -3
- openstef/data/dazls_model_3.4.7/dazls_stored_3.4.7_target.z +0 -0
- openstef/data/dazls_model_3.4.7/dazls_stored_3.4.7_target.z.license +0 -3
- openstef/data/dazls_model_3.4.7/dazls_stored_3.4.7_target_scaler.z +0 -0
- openstef/data/dazls_model_3.4.7/dazls_stored_3.4.7_target_scaler.z.license +0 -3
- {openstef-3.4.24.dist-info → openstef-3.4.25.dist-info}/LICENSE +0 -0
- {openstef-3.4.24.dist-info → openstef-3.4.25.dist-info}/WHEEL +0 -0
- {openstef-3.4.24.dist-info → openstef-3.4.25.dist-info}/top_level.txt +0 -0
|
@@ -4,65 +4,41 @@
|
|
|
4
4
|
"""This module defines the DAZL model."""
|
|
5
5
|
import numpy as np
|
|
6
6
|
from sklearn.base import BaseEstimator
|
|
7
|
+
from sklearn.compose import TransformedTargetRegressor
|
|
8
|
+
from sklearn.linear_model import LinearRegression
|
|
7
9
|
from sklearn.metrics import mean_squared_error, r2_score
|
|
8
|
-
from sklearn.
|
|
10
|
+
from sklearn.pipeline import Pipeline
|
|
9
11
|
from sklearn.preprocessing import MinMaxScaler
|
|
10
|
-
from sklearn.utils import shuffle
|
|
11
12
|
|
|
12
13
|
|
|
13
14
|
class Dazls(BaseEstimator):
|
|
14
15
|
"""DAZLS model.
|
|
15
16
|
|
|
16
|
-
The model carries out wind and solar power prediction for unseen target substations using training data from
|
|
17
|
-
|
|
18
|
-
This model has two sub-models:
|
|
19
|
-
|
|
20
|
-
- domain model : a model taking a set of 'input' features of a substation and make an 'initial' prediction.
|
|
21
|
-
Input features can be features such as: weather, geospatial, total load, etc.
|
|
22
|
-
These features are always directly related to the components' size in some way.
|
|
23
|
-
|
|
24
|
-
|
|
25
|
-
- adaptation model : a model taking a set of 'meta' features of a substation and refines the domain model's
|
|
26
|
-
prediction. Next to the features, it is trained on the domain model's predictions.
|
|
27
|
-
'Meta' features are features related to the uncertainty of the data, and include:
|
|
28
|
-
variance of the total load, standard deviation of the total load, etc.
|
|
29
|
-
|
|
30
|
-
Any data-driven model can be plugged and used as the base for the domain and the adaptation model.
|
|
31
|
-
|
|
32
|
-
CAUTION : 'Meta' features should be kept out of the domain model, and vice versa input features should be
|
|
33
|
-
kept out the adaptation model.
|
|
34
|
-
|
|
35
|
-
For a full reference, see:
|
|
36
|
-
Teng, S.Y., van Nooten, C. C., van Doorn, J.M., Ottenbros, A., Huijbregts, M., Jansen, J.J.
|
|
37
|
-
Improving Near Real-Time Predictions of Renewable Electricity Production at Substation Level (Submitted)
|
|
38
|
-
|
|
39
|
-
Args:
|
|
40
|
-
- BaseEstimator (object) : a base model that can be used to carry out predictions.
|
|
17
|
+
The model carries out wind and solar power prediction for unseen target substations using training data from other
|
|
18
|
+
substations with known components.
|
|
41
19
|
|
|
42
20
|
"""
|
|
43
21
|
|
|
22
|
+
model_: Pipeline
|
|
23
|
+
|
|
44
24
|
def __init__(self):
|
|
45
25
|
"""Initialize DAZL model."""
|
|
46
26
|
self.__name__ = "DAZLS"
|
|
47
|
-
|
|
48
|
-
|
|
49
|
-
|
|
50
|
-
|
|
51
|
-
|
|
27
|
+
|
|
28
|
+
regressor = TransformedTargetRegressor(
|
|
29
|
+
regressor=LinearRegression(),
|
|
30
|
+
transformer=MinMaxScaler(clip=True),
|
|
31
|
+
)
|
|
32
|
+
|
|
33
|
+
self.model_ = Pipeline(
|
|
34
|
+
[("scaler", MinMaxScaler(clip=True)), ("regressor", regressor)]
|
|
35
|
+
)
|
|
52
36
|
|
|
53
37
|
# The input columns for the domain and adaptation models (with description)
|
|
54
|
-
self.
|
|
38
|
+
self.baseline_input_columns = [
|
|
55
39
|
"radiation", # Weather parameter
|
|
56
40
|
"windspeed_100m", # Weather parameter
|
|
57
|
-
"
|
|
58
|
-
"lat", # Latitude
|
|
59
|
-
"lon", # Longitude
|
|
60
|
-
"hour", # Hour of the day
|
|
61
|
-
"minute", # Minute of the hour
|
|
62
|
-
]
|
|
63
|
-
self.adaptation_model_input_columns = [
|
|
64
|
-
"var_total", # Variance of the total load
|
|
65
|
-
"sem_total", # Standard Error of the Mean of the total load
|
|
41
|
+
"total_load",
|
|
66
42
|
]
|
|
67
43
|
self.target_columns = ["total_wind_part", "total_solar_part"]
|
|
68
44
|
|
|
@@ -76,34 +52,15 @@ class Dazls(BaseEstimator):
|
|
|
76
52
|
Args:
|
|
77
53
|
features: inputs for domain and adaptation model (domain_model_input, adaptation_model_input)
|
|
78
54
|
target: the expected output (y_train)
|
|
79
|
-
|
|
80
55
|
"""
|
|
81
|
-
x,
|
|
82
|
-
features.loc[:, self.
|
|
83
|
-
features.loc[:, self.adaptation_model_input_columns],
|
|
56
|
+
x, y = (
|
|
57
|
+
features.loc[:, self.baseline_input_columns],
|
|
84
58
|
target.loc[:, self.target_columns],
|
|
85
59
|
)
|
|
86
|
-
domain_model_input, adaptation_model_input, y_train = shuffle(
|
|
87
|
-
x, x2, y, random_state=999
|
|
88
|
-
) # just shuffling
|
|
89
|
-
|
|
90
|
-
self.domain_model_scaler.fit(domain_model_input)
|
|
91
|
-
self.adaptation_model_scaler.fit(adaptation_model_input)
|
|
92
|
-
self.target_scaler.fit(y_train)
|
|
93
|
-
domain_model_input = self.domain_model_scaler.transform(domain_model_input)
|
|
94
|
-
adaptation_model_input = self.adaptation_model_scaler.transform(
|
|
95
|
-
adaptation_model_input
|
|
96
|
-
)
|
|
97
|
-
y_train = self.target_scaler.transform(y_train)
|
|
98
60
|
|
|
99
|
-
self.
|
|
100
|
-
domain_model_pred = self.domain_model.predict(domain_model_input)
|
|
101
|
-
adaptation_model_input = np.concatenate(
|
|
102
|
-
(adaptation_model_input, domain_model_pred), axis=1
|
|
103
|
-
)
|
|
104
|
-
self.adaptation_model.fit(adaptation_model_input, y_train)
|
|
61
|
+
self.model_.fit(x, y)
|
|
105
62
|
|
|
106
|
-
def predict(self, x: np.array
|
|
63
|
+
def predict(self, x: np.array):
|
|
107
64
|
"""Make a prediction.
|
|
108
65
|
|
|
109
66
|
For the prediction we use the test data x. We use domain_model_input_columns and
|
|
@@ -119,41 +76,10 @@ class Dazls(BaseEstimator):
|
|
|
119
76
|
|
|
120
77
|
Returns:
|
|
121
78
|
prediction: The output prediction after both models.
|
|
122
|
-
|
|
123
79
|
"""
|
|
124
|
-
|
|
125
|
-
x.loc[:, self.domain_model_input_columns],
|
|
126
|
-
x.loc[:, self.adaptation_model_input_columns],
|
|
127
|
-
)
|
|
128
|
-
# Rescale test data for both models (if required)
|
|
129
|
-
domain_model_test_data_scaled = self.domain_model_scaler.transform(
|
|
130
|
-
domain_model_test_data
|
|
131
|
-
)
|
|
132
|
-
adaptation_model_test_data_scaled = self.adaptation_model_scaler.transform(
|
|
133
|
-
adaptation_model_test_data
|
|
134
|
-
)
|
|
135
|
-
# Use the scaled data to make domain_model_prediction
|
|
136
|
-
domain_model_test_data_pred = self.domain_model.predict(
|
|
137
|
-
domain_model_test_data_scaled
|
|
138
|
-
)
|
|
139
|
-
# Use the domain_model_prediction to make adaptation_model_prediction
|
|
140
|
-
adaptation_model_test_data_pred = self.adaptation_model.predict(
|
|
141
|
-
np.concatenate(
|
|
142
|
-
[adaptation_model_test_data_scaled, domain_model_test_data_pred], axis=1
|
|
143
|
-
)
|
|
144
|
-
)
|
|
145
|
-
# Rescale adaptation_model_prediction (if required)
|
|
146
|
-
prediction = self.target_scaler.inverse_transform(
|
|
147
|
-
adaptation_model_test_data_pred
|
|
148
|
-
)
|
|
80
|
+
model_test_data = x.loc[:, self.baseline_input_columns]
|
|
149
81
|
|
|
150
|
-
|
|
151
|
-
prediction_domain = self.target_scaler.inverse_transform(
|
|
152
|
-
domain_model_test_data_pred
|
|
153
|
-
)
|
|
154
|
-
return prediction, prediction_domain
|
|
155
|
-
else:
|
|
156
|
-
return prediction
|
|
82
|
+
return self.model_.predict(model_test_data)
|
|
157
83
|
|
|
158
84
|
def score(self, truth, prediction):
|
|
159
85
|
"""Evaluation of the prediction's output.
|
|
@@ -164,7 +90,6 @@ class Dazls(BaseEstimator):
|
|
|
164
90
|
|
|
165
91
|
Returns:
|
|
166
92
|
RMSE and R2 scores
|
|
167
|
-
|
|
168
93
|
"""
|
|
169
94
|
rmse = (mean_squared_error(truth, prediction)) ** 0.5
|
|
170
95
|
r2_score_value = r2_score(truth, prediction)
|
|
@@ -175,17 +100,13 @@ class Dazls(BaseEstimator):
|
|
|
175
100
|
|
|
176
101
|
Returns:
|
|
177
102
|
Summary represented by a string
|
|
178
|
-
|
|
179
103
|
"""
|
|
180
104
|
summary_str = (
|
|
181
105
|
f"{self.__name__} model summary:\n\n"
|
|
182
|
-
f"
|
|
183
|
-
f"\tInput columns: {self.
|
|
184
|
-
f"\tScaler: {self.
|
|
185
|
-
f"
|
|
186
|
-
f"\tInput columns: {self.adaptation_model_input_columns} \n"
|
|
187
|
-
f"\tScaler: {self.adaptation_model_scaler} \n\n"
|
|
188
|
-
f"Target columns: {self.target_columns}"
|
|
106
|
+
f"Model: {self.model_} \n"
|
|
107
|
+
f"\tInput columns: {self.baseline_input_columns} \n"
|
|
108
|
+
f"\tScaler: {self.model_['scaler']} \n\n"
|
|
109
|
+
f"\tRegressor: {self.model_['regressor']} \n\n"
|
|
189
110
|
)
|
|
190
111
|
|
|
191
112
|
return summary_str
|
|
@@ -18,7 +18,7 @@ from openstef.settings import Settings
|
|
|
18
18
|
|
|
19
19
|
# Set the path for the Dazls stored model
|
|
20
20
|
DAZLS_STORED = str(
|
|
21
|
-
PROJECT_ROOT / "openstef" / "data" / "dazls_model_3.4.
|
|
21
|
+
PROJECT_ROOT / "openstef" / "data" / "dazls_model_3.4.24" / "dazls_stored_3.4.24_"
|
|
22
22
|
)
|
|
23
23
|
|
|
24
24
|
|
|
@@ -113,24 +113,7 @@ def create_components_forecast_pipeline(
|
|
|
113
113
|
# Save and load the model as .sav file (or as .z file)
|
|
114
114
|
# For the code contact: korte.termijn.prognoses@alliander.com
|
|
115
115
|
dazls_model = Dazls()
|
|
116
|
-
dazls_model.
|
|
117
|
-
dazls_model.domain_model_scaler = joblib.load(
|
|
118
|
-
DAZLS_STORED + "domain_model_scaler.z"
|
|
119
|
-
)
|
|
120
|
-
dazls_model.domain_model_input_columns = joblib.load(
|
|
121
|
-
DAZLS_STORED + "domain_model_features.z"
|
|
122
|
-
)
|
|
123
|
-
|
|
124
|
-
dazls_model.adaptation_model = joblib.load(DAZLS_STORED + "adaptation_model.z")
|
|
125
|
-
dazls_model.adaptation_model_scaler = joblib.load(
|
|
126
|
-
DAZLS_STORED + "adaptation_model_scaler.z"
|
|
127
|
-
)
|
|
128
|
-
dazls_model.adaptation_model_input_columns = joblib.load(
|
|
129
|
-
DAZLS_STORED + "adaptation_model_features.z"
|
|
130
|
-
)
|
|
131
|
-
|
|
132
|
-
dazls_model.target_columns = joblib.load(DAZLS_STORED + "target.z")
|
|
133
|
-
dazls_model.target_scaler = joblib.load(DAZLS_STORED + "target_scaler.z")
|
|
116
|
+
dazls_model.model_ = joblib.load(DAZLS_STORED + "baseline_model.z")
|
|
134
117
|
|
|
135
118
|
logger.info("DAZLS model loaded", dazls_model=str(dazls_model))
|
|
136
119
|
|
|
@@ -8,24 +8,6 @@ openstef/data/dutch_holidays_2020-2022.csv,sha256=pS-CjE0igYXd-2dG-MlqyvR2fgYgXk
|
|
|
8
8
|
openstef/data/dutch_holidays_2020-2022.csv.license,sha256=AxxHusqwIXU5RHl5ZMU65LyXmgtbj6QlcnFaOEN4kEE,145
|
|
9
9
|
openstef/data/pv_single_coefs.csv,sha256=jadIEYdHvl1lnV_06X_FASkJZ6C3Hecs5xZnH1gPMvI,24779
|
|
10
10
|
openstef/data/pv_single_coefs.csv.license,sha256=AxxHusqwIXU5RHl5ZMU65LyXmgtbj6QlcnFaOEN4kEE,145
|
|
11
|
-
openstef/data/dazls_model_3.4.7/dazls_stored_3.4.7_adaptation_model.z,sha256=BRtD0Wr9DmMJypYxdWOY2xHFe_tg0-Jz9nnlInvswHM,29609700
|
|
12
|
-
openstef/data/dazls_model_3.4.7/dazls_stored_3.4.7_adaptation_model.z.license,sha256=AxxHusqwIXU5RHl5ZMU65LyXmgtbj6QlcnFaOEN4kEE,145
|
|
13
|
-
openstef/data/dazls_model_3.4.7/dazls_stored_3.4.7_adaptation_model_features.z,sha256=J9mF1mqfVwrZoyzJ8VoWPehKIoGtRakfe1a1m5lZt5I,88
|
|
14
|
-
openstef/data/dazls_model_3.4.7/dazls_stored_3.4.7_adaptation_model_features.z.license,sha256=AxxHusqwIXU5RHl5ZMU65LyXmgtbj6QlcnFaOEN4kEE,145
|
|
15
|
-
openstef/data/dazls_model_3.4.7/dazls_stored_3.4.7_adaptation_model_scaler.z,sha256=qukM4z9nZBi_70-1Y5RXpB2tEOwt8oI3KlDVkhnpnVM,879
|
|
16
|
-
openstef/data/dazls_model_3.4.7/dazls_stored_3.4.7_adaptation_model_scaler.z.license,sha256=AxxHusqwIXU5RHl5ZMU65LyXmgtbj6QlcnFaOEN4kEE,145
|
|
17
|
-
openstef/data/dazls_model_3.4.7/dazls_stored_3.4.7_domain_model.z,sha256=Sissl8ax7pm7Y3zWeoE350GTC3-Dl6iAEQl5_zbZe7g,32608923
|
|
18
|
-
openstef/data/dazls_model_3.4.7/dazls_stored_3.4.7_domain_model.z.license,sha256=AxxHusqwIXU5RHl5ZMU65LyXmgtbj6QlcnFaOEN4kEE,145
|
|
19
|
-
openstef/data/dazls_model_3.4.7/dazls_stored_3.4.7_domain_model_features.z,sha256=UUwyRZcUl4S884R86bL-8g9llaDHINmW5-WRoMJF0Do,123
|
|
20
|
-
openstef/data/dazls_model_3.4.7/dazls_stored_3.4.7_domain_model_features.z.license,sha256=AxxHusqwIXU5RHl5ZMU65LyXmgtbj6QlcnFaOEN4kEE,145
|
|
21
|
-
openstef/data/dazls_model_3.4.7/dazls_stored_3.4.7_domain_model_scaler.z,sha256=MddERJN1LmFrgSgzEnIxrpvbL8-dn4iLsyCMXBQDs8o,1173
|
|
22
|
-
openstef/data/dazls_model_3.4.7/dazls_stored_3.4.7_domain_model_scaler.z.license,sha256=AxxHusqwIXU5RHl5ZMU65LyXmgtbj6QlcnFaOEN4kEE,145
|
|
23
|
-
openstef/data/dazls_model_3.4.7/dazls_stored_3.4.7_model_card.md,sha256=HwYMHaYLqIZbxKbZEDVstp30P0VENLRdlVQJnmFxFqo,534
|
|
24
|
-
openstef/data/dazls_model_3.4.7/dazls_stored_3.4.7_model_card.md.license,sha256=AxxHusqwIXU5RHl5ZMU65LyXmgtbj6QlcnFaOEN4kEE,145
|
|
25
|
-
openstef/data/dazls_model_3.4.7/dazls_stored_3.4.7_target.z,sha256=7GkwwyQPJosqmGa0LslpfYIf8qgLDMW9Krx8CM_YO10,40
|
|
26
|
-
openstef/data/dazls_model_3.4.7/dazls_stored_3.4.7_target.z.license,sha256=AxxHusqwIXU5RHl5ZMU65LyXmgtbj6QlcnFaOEN4kEE,145
|
|
27
|
-
openstef/data/dazls_model_3.4.7/dazls_stored_3.4.7_target_scaler.z,sha256=HFldCZItBFxDkFrtg36RS-zyrHHGKOILXya-_hmluYM,686
|
|
28
|
-
openstef/data/dazls_model_3.4.7/dazls_stored_3.4.7_target_scaler.z.license,sha256=AxxHusqwIXU5RHl5ZMU65LyXmgtbj6QlcnFaOEN4kEE,145
|
|
29
11
|
openstef/data_classes/__init__.py,sha256=bIyGTSA4V5VoOLTwdaiJJAnozmpSzvQooVYlsf8H4eU,163
|
|
30
12
|
openstef/data_classes/data_prep.py,sha256=gRSL7UiHvZis8m8z7VoTCZc0Ccffhef5_hmSyApnqK0,3417
|
|
31
13
|
openstef/data_classes/model_specifications.py,sha256=Uod1W3QzhRqVLb6zvXwxh9wRL3EHCzSvX0oDNd28cFk,1197
|
|
@@ -60,7 +42,7 @@ openstef/model/metamodels/missing_values_handler.py,sha256=veyvYZHhKvlYZxaUpxRQ7
|
|
|
60
42
|
openstef/model/regressors/__init__.py,sha256=bIyGTSA4V5VoOLTwdaiJJAnozmpSzvQooVYlsf8H4eU,163
|
|
61
43
|
openstef/model/regressors/arima.py,sha256=wt7FVykjSvljpl7vjtliq61SiyjQ7KKtw8PF9x0xf04,7587
|
|
62
44
|
openstef/model/regressors/custom_regressor.py,sha256=Hsmxahc9nfSWD0aEZ6cm4pxW2noQ8B1SujS17_fmxcU,1768
|
|
63
|
-
openstef/model/regressors/dazls.py,sha256=
|
|
45
|
+
openstef/model/regressors/dazls.py,sha256=dQMx11kfMZCl4K61n8Dug2CyBhjlmiw3-ilv7KmowqM,3990
|
|
64
46
|
openstef/model/regressors/lgbm.py,sha256=zCdn1euEdSFxYJzH8XqQFFnb6R4JVUnmineKjX_Gy-g,800
|
|
65
47
|
openstef/model/regressors/linear.py,sha256=uOvZMLGZH_9nXfmS5honCMfyVeyGXP1Cza9A_BdXlVw,3665
|
|
66
48
|
openstef/model/regressors/linear_quantile.py,sha256=N-cia8aba39Th6BzOdtcESLuxhY9YtSGaOYIc6STgag,7830
|
|
@@ -75,7 +57,7 @@ openstef/monitoring/performance_meter.py,sha256=6aCGjJFXFq-7qwaJyBkF3MLqjgVK6FMF
|
|
|
75
57
|
openstef/monitoring/teams.py,sha256=A-tlZeuAgolxFHjgT3gGjraxzW2dmuB-UAOz4xgYNIQ,6668
|
|
76
58
|
openstef/pipeline/__init__.py,sha256=bIyGTSA4V5VoOLTwdaiJJAnozmpSzvQooVYlsf8H4eU,163
|
|
77
59
|
openstef/pipeline/create_basecase_forecast.py,sha256=YkpiqohETTAETb4GiVlK_btw5dpixJy2LmFZdm10iaI,4623
|
|
78
|
-
openstef/pipeline/create_component_forecast.py,sha256=
|
|
60
|
+
openstef/pipeline/create_component_forecast.py,sha256=XlE9oo37qwmZPE2Dgg19CDfFPRKgrLuyW069pS035UQ,5668
|
|
79
61
|
openstef/pipeline/create_forecast.py,sha256=F09civdIumNQwJq2hraea5QTQx7DgvEliXKs4Y3f8Mc,5689
|
|
80
62
|
openstef/pipeline/optimize_hyperparameters.py,sha256=3SLkcLR7XC4IeN48C-XT_lxlfCqW_D0NoMpZcrB9UUM,11045
|
|
81
63
|
openstef/pipeline/train_create_forecast_backtest.py,sha256=-kZqCWal5zYLL0k0Sapks1zTmU5unNAooVPaPos1_7E,6050
|
|
@@ -101,8 +83,8 @@ openstef/tasks/utils/predictionjobloop.py,sha256=Ysy3zF5lzPMz_asYDKeF5m0qgVT3tCt
|
|
|
101
83
|
openstef/tasks/utils/taskcontext.py,sha256=L9K14ycwgVxbIVUjH2DIn_QWbnu-OfxcGtQ1K9T6sus,5630
|
|
102
84
|
openstef/validation/__init__.py,sha256=bIyGTSA4V5VoOLTwdaiJJAnozmpSzvQooVYlsf8H4eU,163
|
|
103
85
|
openstef/validation/validation.py,sha256=628xaDbAm8B4AYtFOAn8_SXLjejNfULGCfX3hVf_mU0,11119
|
|
104
|
-
openstef-3.4.
|
|
105
|
-
openstef-3.4.
|
|
106
|
-
openstef-3.4.
|
|
107
|
-
openstef-3.4.
|
|
108
|
-
openstef-3.4.
|
|
86
|
+
openstef-3.4.25.dist-info/LICENSE,sha256=7Pm2fWFFHHUG5lDHed1vl5CjzxObIXQglnYsEdtjo_k,14907
|
|
87
|
+
openstef-3.4.25.dist-info/METADATA,sha256=RahtAo0FrqIzmTJhj7dvqCRL53PlDod_bUGASwLxnKU,7394
|
|
88
|
+
openstef-3.4.25.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
|
|
89
|
+
openstef-3.4.25.dist-info/top_level.txt,sha256=kD0H4PqrQoncZ957FvqwfBxa89kTrun4Z_RAPs_HhLs,9
|
|
90
|
+
openstef-3.4.25.dist-info/RECORD,,
|
|
Binary file
|
|
Binary file
|
|
Binary file
|
|
Binary file
|
|
Binary file
|
|
@@ -1,14 +0,0 @@
|
|
|
1
|
-
"
|
|
2
|
-
# Model details : dazls_model_test_eval
|
|
3
|
-
|
|
4
|
-
## Description
|
|
5
|
-
**Model Name**: dazls_model_test_eval
|
|
6
|
-
**Author**: KTP, Alliander
|
|
7
|
-
**Model type**: Energy splitting model
|
|
8
|
-
**Model Architecture**: KNeighestNeighbours
|
|
9
|
-
**Date**: 2024-01-31
|
|
10
|
-
|
|
11
|
-
## Intended use
|
|
12
|
-
This is a DAZLs model aimed at determining the energy splits for substations.
|
|
13
|
-
Each of these splits are determined based on a set of features that are available in production,
|
|
14
|
-
and in this case have their origin in the Dutch energy grid.
|
|
Binary file
|
|
Binary file
|
|
File without changes
|
|
File without changes
|
|
File without changes
|