Update installation, fix some warning move to src layout (#93)

- I have transitioned from setup.py to pyproject.toml . #89 - Changed the layout from flat to source. [See here for advantages](https://packaging.python.org/en/latest/discussions/src-layout-vs-flat-layout/) - Updated the installation description in the README.md - Fixed a couple of deprecation and future warnings, reported in #91 --------- Co-authored-by: Julian Belina <[email protected]>
FZJ-IEK3-VSA · Oct 15, 2024 · c46fbd3 · c46fbd3
1 parent fc0a9d4
commit c46fbd3
Show file tree

Hide file tree

Showing 25 changed files with 171 additions and 133 deletions.
diff --git a/.github/workflows/daily_tests.yml b/.github/workflows/daily_tests.yml
@@ -34,11 +34,7 @@ jobs:
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
-        pip install pytest
-        pip install pytest-cov
-        pip install codecov
-        pip install -r requirements.txt
-        pip install --no-cache-dir -e .
+        pip install --no-cache-dir -e .[dev]
         
     - name: Test with pytest
       working-directory: ./test/

diff --git a/.github/workflows/test_on_push_and_pull.yml b/.github/workflows/test_on_push_and_pull.yml
@@ -29,11 +29,7 @@ jobs:
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
-        pip install pytest
-        pip install pytest-cov
-        pip install codecov
-        pip install -r requirements.txt
-        pip install --no-cache-dir -e .
+        pip install --no-cache-dir -e .[dev]
         
     - name: Test with pytest
       working-directory: ./test/
@@ -58,11 +54,7 @@ jobs:
     - name: Install dependencies
       run: |
         python -m pip install numpy==${{matrix.python-numpy-version.numpy}} --upgrade pip
-        pip install pytest
-        pip install pytest-cov
-        pip install codecov
-        pip install -r requirements.txt
-        pip install --no-cache-dir -e .
+        pip install --no-cache-dir -e .[dev]
         
     - name: Test with pytest
       working-directory: ./test/

diff --git a/.readthedocs.yml b/.readthedocs.yml
@@ -11,5 +11,6 @@ build:
 
 python:
   install:
+  - requirements: requirements.txt
   - requirements: requirements_dev.txt
   system_packages: false
diff --git a/README.md b/README.md
@@ -19,28 +19,50 @@ The documentation of the tsam code can be found [**here**](https://tsam.readthed
 
 
 ## Installation
+It is recommended to install tsam within its own environment. If you are no familiar with python environments, plaese consider to read some [external documentation](https://realpython.com/python-virtual-environments-a-primer/). In the following we assume you have a [mamba](https://mamba.readthedocs.io/en/latest/installation/mamba-installation.html) or [conda](https://www.anaconda.com/) installation.  All conda and mamba command are interchangeable.
+
+### Direct Installations from Package Manager Repositories
+
+If you want to prevent any possible dependency conflicts create a new environment using the following command:
+
+	mamba create -n tsam_env python pip
+
+Activate an existing or the newly create environment afterward
+
+	mamba activate tsam_env
+
 Directly install via pip from pypi as follows:
 
 	pip install tsam
 
-of install from conda forge with the following command:
+or install from conda forge with the following command:
 
 	conda install tsam -c conda-forge
 
+### Local Installation for Development
 Alternatively, clone a local copy of the repository to your computer
 
 	git clone https://github.com/FZJ-IEK3-VSA/tsam.git
-	
-Then install tsam via pip as follow
-	
+
+Change the directory of your shell into the root folder of the repository
+
 	cd tsam
-	pip install . 
-
-Or install directly via python as 
 
-	python setup.py install
+For development, it is recommended to install tsam into its own environment using conda e.g.
+
+	conda env create --file=requirement.yml
+
+Afterward activate the environment
+
+	conda activate tsam_env
+
+Then install tsam via pip as follows
+
+
+	pip install -e .[dev]
 
-In order to use the k-medoids clustering, make sure that you have installed a MILP solver. As default [HiGHS](https://github.com/ERGO-Code/HiGHS) is used. Nevertheless, in case you have access to a license we recommend commercial solvers (e.g. Gurobi or CPLEX) since they have a better performance.
+### Installation of MILP Solver for k-medoids	
+In order to use the k-medoids clustering, make sure that you have installed a MILP solver. As default [HiGHS](https://github.com/ERGO-Code/HiGHS) is installed and used. Nevertheless, in case you have access to a license we recommend commercial solvers (e.g. Gurobi or CPLEX) since they have a better performance.
 
 ### Developer installation
 

diff --git a/pyproject.toml b/pyproject.toml
@@ -0,0 +1,53 @@
+[build-system]
+requires = ["setuptools>=64.0.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+
+[project]
+name = "tsam"
+version = "2.3.6"
+description = "Time series aggregation module (tsam) to create typical periods"
+authors = [
+    { name = "Leander Kotzur", email = "[email protected]" },
+    { name = "Maximilian Hoffmann", email = "[email protected]" },
+]
+maintainers = [
+  {name = "Julian Belina", email = "[email protected]"}
+]
+license = { file = "LICENSE.txt" }
+keywords = ["clustering", "optimization"]
+requires-python = ">=3.9,<3.13"
+readme = "README.md"
+classifiers=[
+        "Development Status :: 4 - Beta",
+        "Intended Audience :: End Users/Desktop",
+        "Intended Audience :: Science/Research",
+        "License :: OSI Approved :: MIT License",
+        "Natural Language :: English",
+        "Operating System :: OS Independent",
+        "Programming Language :: Python",
+        "Programming Language :: Python :: 2",
+        "Programming Language :: Python :: 3",
+        "Topic :: Scientific/Engineering :: Mathematics",
+        "Topic :: Software Development :: Libraries :: Python Modules",
+    ]
+dynamic = ["dependencies", "optional-dependencies"]
+
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.setuptools.dynamic]
+dependencies = {file = ["requirements.txt"]}
+optional-dependencies = {dev = { file = ["requirements_dev.txt"] }}
+
+
+#Configureation options
+# https://docs.pytest.org/en/7.1.x/reference/reference.html#configuration-options
+
+[tool.pytest.ini_options]
+testpaths = ["test"] # Sets the path where to look for tests
+pythonpath =["test"] # Sets the path which should be prepended to pythonpath relative to the root folder
+console_output_style = "count"
+
+
diff --git a/requirements.yml b/requirements.yml
@@ -1,8 +1,6 @@
-name: tsam
+name: tsam_env
 channels:
   - conda-forge
 dependencies:
   - python>=3.9,<3.13
   - pip
-  - pip:
-    - -r requirements.txt
diff --git a/requirements_dev.txt b/requirements_dev.txt
@@ -1,8 +1,7 @@
--r requirements.txt
-
 # Testing
 pytest
 pytest-cov
+codecov
 
 # Documentation
 sphinx

diff --git a/requirements_dev.yml b/requirements_dev.yml
diff --git a/setup.py b/setup.py
diff --git a/tsam/__init__.py → src/tsam/__init__.py b/tsam/__init__.py → src/tsam/__init__.py
diff --git a/tsam/hyperparametertuning.py → src/tsam/hyperparametertuning.py b/tsam/hyperparametertuning.py → src/tsam/hyperparametertuning.py
diff --git a/tsam/periodAggregation.py → src/tsam/periodAggregation.py b/tsam/periodAggregation.py → src/tsam/periodAggregation.py
diff --git a/tsam/representations.py → src/tsam/representations.py b/tsam/representations.py → src/tsam/representations.py
diff --git a/tsam/timeseriesaggregation.py → src/tsam/timeseriesaggregation.py b/tsam/timeseriesaggregation.py → src/tsam/timeseriesaggregation.py
diff --git a/tsam/utils/__init__.py → src/tsam/utils/__init__.py b/tsam/utils/__init__.py → src/tsam/utils/__init__.py
diff --git a/tsam/utils/durationRepresentation.py → src/tsam/utils/durationRepresentation.py b/tsam/utils/durationRepresentation.py → src/tsam/utils/durationRepresentation.py
@@ -57,17 +57,18 @@ def durationRepresentation(
                 # get all the values of a certain attribute and cluster
                 candidateValues = candidates.loc[indice[0], a]
                 # sort all values
-                sortedAttr = candidateValues.stack(future_stack=True,).sort_values()
+                sortedAttr = candidateValues.stack(
+                    future_stack=True,
+                ).sort_values()
                 # reindex and arrange such that every sorted segment gets represented by its mean
                 sortedAttr.index = pd.MultiIndex.from_tuples(clean_index)
                 representationValues = sortedAttr.unstack(level=0).mean(axis=1)
                 # respect max and min of the attributes
                 if representMinMax:
                     representationValues.loc[0] = sortedAttr.values[0]
-                    representationValues.loc[
-                        representationValues.index[-1]
-                    ] = sortedAttr.values[-1]
-
+                    representationValues.loc[representationValues.index[-1]] = (
+                        sortedAttr.values[-1]
+                    )
 
                 # get the order of the representation values such that euclidean distance to the candidates is minimized
                 order = candidateValues.mean().sort_values().index
@@ -97,8 +98,12 @@ def durationRepresentation(
             # concat centroid values and cluster weights for all clusters
             meansAndWeights = pd.concat(
                 [
-                    pd.DataFrame(np.array(meanVals)).stack(future_stack=True,),
-                    pd.DataFrame(np.array(clusterLengths)).stack(future_stack=True,),
+                    pd.DataFrame(np.array(meanVals)).stack(
+                        future_stack=True,
+                    ),
+                    pd.DataFrame(np.array(clusterLengths)).stack(
+                        future_stack=True,
+                    ),
                 ],
                 axis=1,
             )
@@ -107,7 +112,14 @@ def durationRepresentation(
             # save order of the sorted centroid values across all clusters
             order = meansAndWeightsSorted.index
             # sort all values of the original time series
-            sortedAttr = candidates.loc[:, a].stack(future_stack=True,).sort_values().values
+            sortedAttr = (
+                candidates.loc[:, a]
+                .stack(
+                    future_stack=True,
+                )
+                .sort_values()
+                .values
+            )
             # take mean of sections of the original duration curve according to the cluster and its weight the
             # respective section is assigned to
             representationValues = []
@@ -124,8 +136,7 @@ def durationRepresentation(
                     keepSum=True,
                 )
 
-
-            # transform all representation values to a data frame and arrange it 
+            # transform all representation values to a data frame and arrange it
             # according to the order of the sorted
             # centroid values
             representationValues = pd.DataFrame(np.array(representationValues))
@@ -139,9 +150,9 @@ def durationRepresentation(
     return clusterCenters
 
 
-
-def _representMinMax(representationValues, sortedAttr, meansAndWeightsSorted, 
-                     keepSum=True):
+def _representMinMax(
+    representationValues, sortedAttr, meansAndWeightsSorted, keepSum=True
+):
     """
     Represents the the min and max values of the original time series in the
     duration curve representation such that the min and max values of the
@@ -164,8 +175,8 @@ def _representMinMax(representationValues, sortedAttr, meansAndWeightsSorted,
     if np.any(np.array(representationValues) < 0):
         raise ValueError("Negative values in the duration curve representation")
 
-    # first retrieve the change of the values to the min and max values 
-    # of the original time series and their duration in the original 
+    # first retrieve the change of the values to the min and max values
+    # of the original time series and their duration in the original
     # time series
     delta_max = sortedAttr.max() - representationValues[-1]
     appearance_max = meansAndWeightsSorted[1].iloc[-1]
@@ -174,31 +185,36 @@ def _representMinMax(representationValues, sortedAttr, meansAndWeightsSorted,
 
     if delta_min == 0 and delta_max == 0:
         return representationValues
-    
+
     if keepSum:
 
-        # now anticipate the shift of the sum of the time series 
+        # now anticipate the shift of the sum of the time series
         # due to the change of the min and max values
         # of the duration curve
         delta_sum = delta_max * appearance_max + delta_min * appearance_min
-        # and derive how much the other values have to be changed to preserve 
+        # and derive how much the other values have to be changed to preserve
         # the mean of the duration curve
-        correction_factor = - delta_sum / (meansAndWeightsSorted[1].iloc[1:-1] 
-                                            * representationValues[1:-1]).sum()
-
+        correction_factor = (
+            -delta_sum
+            / (meansAndWeightsSorted[1].iloc[1:-1] * representationValues[1:-1]).sum()
+        )
+
         if correction_factor < -1 or correction_factor > 1:
-            warnings.warn("The cluster is to small to preserve the sum of the duration curve and additionally the min and max values of the original cluster members. The min max values of the cluster are not preserved. This does not necessarily mean that the min and max values of the original time series are not preserved.")
+            warnings.warn(
+                "The cluster is too small to preserve the sum of the duration curve and additionally the min and max values of the original cluster members. The min max values of the cluster are not preserved. This does not necessarily mean that the min and max values of the original time series are not preserved."
+            )
             return representationValues
 
-        # correct the values of the duration curve such 
+        # correct the values of the duration curve such
         # that the mean of the duration curve is preserved
         # since the min and max values are changed
-        representationValues[1:-1] = np.multiply(representationValues[1:-1], (
-            1+ correction_factor))
-
-    # change the values of the duration curve such that the min and max 
+        representationValues[1:-1] = np.multiply(
+            representationValues[1:-1], (1 + correction_factor)
+        )
+
+    # change the values of the duration curve such that the min and max
     # values are preserved
     representationValues[-1] += delta_max
     representationValues[0] += delta_min
-    
+
     return representationValues
diff --git a/tsam/utils/k_maxoids.py → src/tsam/utils/k_maxoids.py b/tsam/utils/k_maxoids.py → src/tsam/utils/k_maxoids.py
diff --git a/tsam/utils/k_medoids_contiguity.py → src/tsam/utils/k_medoids_contiguity.py b/tsam/utils/k_medoids_contiguity.py → src/tsam/utils/k_medoids_contiguity.py
diff --git a/tsam/utils/k_medoids_exact.py → src/tsam/utils/k_medoids_exact.py b/tsam/utils/k_medoids_exact.py → src/tsam/utils/k_medoids_exact.py
diff --git a/tsam/utils/segmentation.py → src/tsam/utils/segmentation.py b/tsam/utils/segmentation.py → src/tsam/utils/segmentation.py