tsam 2.1.0__py3-none-any.whl → 2.3.2__py3-none-any.whl

tsam/utils/segmentation.py

@@ -1,119 +1,118 @@
-# -*- coding: utf-8 -*-
-
-import numpy as np
-import pandas as pd
-from sklearn.cluster import AgglomerativeClustering
-from tsam.representations import representations
-
-
-def segmentation(
-    normalizedTypicalPeriods,
-    noSegments,
-    timeStepsPerPeriod,
-    solver,
-    representationMethod=None,
-    representationDict=None,
-    distributionPeriodWise=True,
-):
-    """
-    Agglomerative clustering of adjacent time steps within a set of typical periods in order to further reduce the
-    temporal resolution within typical periods and to further reduce complexity of input data.
-
-    :param normalizedTypicalPeriods: MultiIndex DataFrame containing the typical periods as first index, the time steps
-        within the periods as second index and the attributes as columns.
-    :type normalizedTypicalPeriods: pandas DataFrame
-
-    :param noSegments: Number of segments in which the typical periods shoul be subdivided - equivalent to the number of
-        inner-period clusters.
-    :type noSegments: integer
-
-    :param timeStepsPerPeriod: Number of time steps per period
-    :type timeStepsPerPeriod: integer
-
-    :returns:     - **segmentedNormalizedTypicalPeriods** (pandas DataFrame) --  MultiIndex DataFrame similar to
-                    normalizedTypicalPeriods but with segments instead of time steps. Moreover, two additional index
-                    levels define the length of each segment and the time step index at which each segment starts.
-                  - **predictedSegmentedNormalizedTypicalPeriods** (pandas DataFrame) -- MultiIndex DataFrame with the same
-                    shape of normalizedTypicalPeriods, but with overwritten values derived from segmentation used for
-                    prediction of the original periods and accuracy indicators.
-    """
-    # Initialize lists for predicted and segmented DataFrame
-    segmentedNormalizedTypicalPeriodsList = []
-    predictedSegmentedNormalizedTypicalPeriodsList = []
-    # do for each typical period
-    for i in normalizedTypicalPeriods.index.get_level_values(0).unique():
-        # make numpy array with rows containing the segmenatation candidates (time steps)
-        # and columns as dimensions of the
-        segmentationCandidates = np.asarray(normalizedTypicalPeriods.loc[i, :])
-        # produce adjacency matrix: Each time step is only connected to its preceding and succeeding one
-        adjacencyMatrix = np.eye(timeStepsPerPeriod, k=1) + np.eye(
-            timeStepsPerPeriod, k=-1
-        )
-        # execute clustering of adjacent time steps
-        if noSegments == 1:
-            clusterOrder = np.asarray([0] * len(segmentationCandidates))
-        else:
-            clustering = AgglomerativeClustering(
-                n_clusters=noSegments, linkage="ward", connectivity=adjacencyMatrix
-            )
-            clusterOrder = clustering.fit_predict(segmentationCandidates)
-        # determine the indices where the segments change and the number of time steps in each segment
-        segNo, indices, segmentNoOccur = np.unique(
-            clusterOrder, return_index=True, return_counts=True
-        )
-        clusterOrderUnique = [clusterOrder[index] for index in sorted(indices)]
-        # determine the segments' values
-        clusterCenters, clusterCenterIndices = representations(
-            segmentationCandidates,
-            clusterOrder,
-            default="meanRepresentation",
-            representationMethod=representationMethod,
-            representationDict=representationDict,
-            distributionPeriodWise=distributionPeriodWise,
-            timeStepsPerPeriod=1,
-        )
-        # clusterCenters = meanRepresentation(segmentationCandidates, clusterOrder)
-        # predict each time step of the period by representing it with the corresponding segment's values
-        predictedSegmentedNormalizedTypicalPeriods = (
-            pd.DataFrame(clusterCenters, columns=normalizedTypicalPeriods.columns)
-            .reindex(clusterOrder)
-            .reset_index(drop=True)
-        )
-        # represent the period by the segments in the right order only instead of each time step
-        segmentedNormalizedTypicalPeriods = (
-            pd.DataFrame(clusterCenters, columns=normalizedTypicalPeriods.columns)
-            .reindex(clusterOrderUnique)
-            .set_index(np.sort(indices))
-        )
-        # keep additional information on the lengths of the segments in the right order
-        segmentDuration = (
-            pd.DataFrame(segmentNoOccur, columns=["Segment Duration"])
-            .reindex(clusterOrderUnique)
-            .set_index(np.sort(indices))
-        )
-        # create DataFrame with reduced number of segments together with three indices per period:
-        # 1. The segment number
-        # 2. The segment duration
-        # 3. The index of the original time step, at which the segment starts
-        result = segmentedNormalizedTypicalPeriods.set_index(
-            [
-                pd.Index(segNo, name="Segment Step"),
-                segmentDuration["Segment Duration"],
-                pd.Index(np.sort(indices), name="Original Start Step"),
-            ]
-        )
-        # append predicted and segmented DataFrame to list to create a big DataFrame for all periods
-        predictedSegmentedNormalizedTypicalPeriodsList.append(
-            predictedSegmentedNormalizedTypicalPeriods
-        )
-        segmentedNormalizedTypicalPeriodsList.append(result)
-    # create a big DataFrame for all periods for predicted segmented time steps and segments and return
-    predictedSegmentedNormalizedTypicalPeriods = pd.concat(
-        predictedSegmentedNormalizedTypicalPeriodsList,
-        keys=normalizedTypicalPeriods.index.get_level_values(0).unique(),
-    ).rename_axis(["", "TimeStep"])
-    segmentedNormalizedTypicalPeriods = pd.concat(
-        segmentedNormalizedTypicalPeriodsList,
-        keys=normalizedTypicalPeriods.index.get_level_values(0).unique(),
-    )
-    return segmentedNormalizedTypicalPeriods, predictedSegmentedNormalizedTypicalPeriods
+# -*- coding: utf-8 -*-
+
+import numpy as np
+import pandas as pd
+from sklearn.cluster import AgglomerativeClustering
+from tsam.representations import representations
+
+
+def segmentation(
+    normalizedTypicalPeriods,
+    noSegments,
+    timeStepsPerPeriod,
+    representationMethod=None,
+    representationDict=None,
+    distributionPeriodWise=True,
+):
+    """
+    Agglomerative clustering of adjacent time steps within a set of typical periods in order to further reduce the
+    temporal resolution within typical periods and to further reduce complexity of input data.
+
+    :param normalizedTypicalPeriods: MultiIndex DataFrame containing the typical periods as first index, the time steps
+        within the periods as second index and the attributes as columns.
+    :type normalizedTypicalPeriods: pandas DataFrame
+
+    :param noSegments: Number of segments in which the typical periods should be subdivided - equivalent to the number of
+        inner-period clusters.
+    :type noSegments: integer
+
+    :param timeStepsPerPeriod: Number of time steps per period
+    :type timeStepsPerPeriod: integer
+
+    :returns:     - **segmentedNormalizedTypicalPeriods** (pandas DataFrame) --  MultiIndex DataFrame similar to
+                    normalizedTypicalPeriods but with segments instead of time steps. Moreover, two additional index
+                    levels define the length of each segment and the time step index at which each segment starts.
+                  - **predictedSegmentedNormalizedTypicalPeriods** (pandas DataFrame) -- MultiIndex DataFrame with the same
+                    shape of normalizedTypicalPeriods, but with overwritten values derived from segmentation used for
+                    prediction of the original periods and accuracy indicators.
+    """
+    # Initialize lists for predicted and segmented DataFrame
+    segmentedNormalizedTypicalPeriodsList = []
+    predictedSegmentedNormalizedTypicalPeriodsList = []
+    # do for each typical period
+    for i in normalizedTypicalPeriods.index.get_level_values(0).unique():
+        # make numpy array with rows containing the segmenatation candidates (time steps)
+        # and columns as dimensions of the
+        segmentationCandidates = np.asarray(normalizedTypicalPeriods.loc[i, :])
+        # produce adjacency matrix: Each time step is only connected to its preceding and succeeding one
+        adjacencyMatrix = np.eye(timeStepsPerPeriod, k=1) + np.eye(
+            timeStepsPerPeriod, k=-1
+        )
+        # execute clustering of adjacent time steps
+        if noSegments == 1:
+            clusterOrder = np.asarray([0] * len(segmentationCandidates))
+        else:
+            clustering = AgglomerativeClustering(
+                n_clusters=noSegments, linkage="ward", connectivity=adjacencyMatrix
+            )
+            clusterOrder = clustering.fit_predict(segmentationCandidates)
+        # determine the indices where the segments change and the number of time steps in each segment
+        segNo, indices, segmentNoOccur = np.unique(
+            clusterOrder, return_index=True, return_counts=True
+        )
+        clusterOrderUnique = [clusterOrder[index] for index in sorted(indices)]
+        # determine the segments' values
+        clusterCenters, clusterCenterIndices = representations(
+            segmentationCandidates,
+            clusterOrder,
+            default="meanRepresentation",
+            representationMethod=representationMethod,
+            representationDict=representationDict,
+            distributionPeriodWise=distributionPeriodWise,
+            timeStepsPerPeriod=1,
+        )
+        # clusterCenters = meanRepresentation(segmentationCandidates, clusterOrder)
+        # predict each time step of the period by representing it with the corresponding segment's values
+        predictedSegmentedNormalizedTypicalPeriods = (
+            pd.DataFrame(clusterCenters, columns=normalizedTypicalPeriods.columns)
+            .reindex(clusterOrder)
+            .reset_index(drop=True)
+        )
+        # represent the period by the segments in the right order only instead of each time step
+        segmentedNormalizedTypicalPeriods = (
+            pd.DataFrame(clusterCenters, columns=normalizedTypicalPeriods.columns)
+            .reindex(clusterOrderUnique)
+            .set_index(np.sort(indices))
+        )
+        # keep additional information on the lengths of the segments in the right order
+        segmentDuration = (
+            pd.DataFrame(segmentNoOccur, columns=["Segment Duration"])
+            .reindex(clusterOrderUnique)
+            .set_index(np.sort(indices))
+        )
+        # create DataFrame with reduced number of segments together with three indices per period:
+        # 1. The segment number
+        # 2. The segment duration
+        # 3. The index of the original time step, at which the segment starts
+        result = segmentedNormalizedTypicalPeriods.set_index(
+            [
+                pd.Index(segNo, name="Segment Step"),
+                segmentDuration["Segment Duration"],
+                pd.Index(np.sort(indices), name="Original Start Step"),
+            ]
+        )
+        # append predicted and segmented DataFrame to list to create a big DataFrame for all periods
+        predictedSegmentedNormalizedTypicalPeriodsList.append(
+            predictedSegmentedNormalizedTypicalPeriods
+        )
+        segmentedNormalizedTypicalPeriodsList.append(result)
+    # create a big DataFrame for all periods for predicted segmented time steps and segments and return
+    predictedSegmentedNormalizedTypicalPeriods = pd.concat(
+        predictedSegmentedNormalizedTypicalPeriodsList,
+        keys=normalizedTypicalPeriods.index.get_level_values(0).unique(),
+    ).rename_axis(["", "TimeStep"])
+    segmentedNormalizedTypicalPeriods = pd.concat(
+        segmentedNormalizedTypicalPeriodsList,
+        keys=normalizedTypicalPeriods.index.get_level_values(0).unique(),
+    )
+    return segmentedNormalizedTypicalPeriods, predictedSegmentedNormalizedTypicalPeriods

{tsam-2.1.0.dist-info → tsam-2.3.2.dist-info}/LICENSE.txt

@@ -1,21 +1,21 @@
-MIT License
-
-Copyright (c) 2017 Leander Kotzur (FZJ IEK-3), Maximilian Hoffmann (FZJ IEK-3), Peter Markewitz (FZJ IEK-3), Martin Robinius (FZJ IEK-3), Detlef Stolten (FZJ IEK-3)
-
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this software and associated documentation files (the "Software"), to deal
-in the Software without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Software, and to permit persons to whom the Software is
-furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in all
-copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+MIT License
+
+Copyright (c) 2017 Leander Kotzur (FZJ IEK-3), Maximilian Hoffmann (FZJ IEK-3), Peter Markewitz (FZJ IEK-3), Martin Robinius (FZJ IEK-3), Detlef Stolten (FZJ IEK-3)
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 SOFTWARE.