Squashed commit of the following:

commit 5716cb6 Author: Molier <[email protected]> Date: Thu Aug 15 17:48:13 2024 +0200 chore: Update dependencies: pandera... commit 75cacb9 Author: Molier <[email protected]> Date: Tue Aug 13 16:51:31 2024 +0200 Refactor capacity input model, add default threshold, update cap analysis logic - Refactored the capacity input model in the `models.py` file to include a default value for the `threshold` field. The `threshold` field now has a default value of 2.5 and must be greater than or equal to 0. - Updated the `main.py` file to import the `pandera.typing` module for type annotations. - Modified the `find_peaks_with_surroundings` method in the `CapacityAnalysis` class to skip peaks that are within a certain time window of previously found peaks. - Made other minor code improvements and optimizations. commit b61c3fb Author: Molier <[email protected]> Date: Tue Aug 13 12:18:04 2024 +0200 chore: Add basic type checking for Python analysis, small doc refac and removal obs file commit fe9e685 Author: Molier <[email protected]> Date: Tue Aug 13 12:05:01 2024 +0200 chore: remove pre-commit comment(no strict mypy) commit a099d9a Author: Jan Pecinovsky <=> Date: Tue Aug 13 10:10:52 2024 +0000 add threshold to capacity input commit 8934a0e Author: Jan Pecinovsky <[email protected]> Date: Fri Aug 2 08:22:39 2024 +0000 version bump commit 990fef5 Author: Jan Pecinovsky <[email protected]> Date: Fri Aug 2 08:19:29 2024 +0000 Validators on Timeseries data to convert NaN to None for JSON output. commit a1fafd7 Author: Jan Pecinovsky <[email protected]> Date: Fri Jul 26 19:53:34 2024 +0200 0.0.14. Capacity Analysis. Refactoring. Poetry Package Manager. (#9) * Allow the case where not all participants have offtake, injection or a key * readmes updated * added capacity analysis with demo nb * python compat removal >3.10 * key validation to 3 decimal values * added poetry as package manager and updated the requirements and dev requirements * review * imports * samples * add seaborn requirement-dev * remove rounding from output * Capacity analysis typechanges to make it more pure and only use inout outputmodels in the demo * feat: Add PeakDetail model to capacity module * chore: Ruff import removal * chore: Update pre-commit hooks with pyupgrade v3.16.0 refactoring to upgrade to python311 * feat: added a test you can run for all the notebooks. (#8) * chore: Update pre-commit hooks with pyupgrade v3.16.0 refactoring to upgrade to python311 * chore: made requirements more human readable * feat: Update dependencies for entsoe-py and energyid * chore: Add test suite for notebook execution --------- Co-authored-by: Jan Pecinovsky <[email protected]> * Version Bump --------- Co-authored-by: Molier <[email protected]> Co-authored-by: Oscar <[email protected]>
EnergieID · Aug 27, 2024 · 5b7ce61 · 5b7ce61
1 parent f1f8857
commit 5b7ce61
Show file tree

Hide file tree

Showing 10 changed files with 1,191 additions and 500 deletions.
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -1,7 +1,7 @@
 repos:
   - repo: https://github.com/astral-sh/ruff-pre-commit
     # Ruff version.
-    rev: v0.5.5
+    rev: v0.6.2
     hooks:
       # Run the linter.
       - id: ruff
@@ -12,7 +12,13 @@ repos:
         types_or: [python, pyi, jupyter]
 
   - repo: https://github.com/asottile/pyupgrade
-    rev: v3.16.0
+    rev: v3.17.0
     hooks:
       - id: pyupgrade
         args: [--py311-plus]
+
+  # - repo: https://github.com/pre-commit/mirrors-mypy
+  #   rev: "" # Use the sha / tag you want to point at
+  #   hooks:
+  #     - id: mypy
+  #       args: [--strict, --ignore-missing-imports]
diff --git a/.vscode/settings.json b/.vscode/settings.json
@@ -0,0 +1,3 @@
+{
+    "python.analysis.typeCheckingMode": "basic"
+}
diff --git a/openenergyid/__init__.py b/openenergyid/__init__.py
@@ -1,6 +1,6 @@
 """Open Energy ID Python SDK."""
 
-__version__ = "0.1.15"
+__version__ = "0.1.16"
 
 from .enums import Granularity
 from .models import TimeDataFrame, TimeSeries

diff --git a/openenergyid/capacity/main.py b/openenergyid/capacity/main.py
@@ -1,7 +1,9 @@
 """Main module for capacity analysis."""
 
 import datetime as dt
+import typing
 import pandas as pd
+import pandera.typing as pdt
 
 
 class CapacityAnalysis:
@@ -21,7 +23,7 @@ class CapacityAnalysis:
 
     def __init__(
         self,
-        data: pd.Series,
+        data: pdt.Series,
         threshold: float = 2.5,
         window: str = "MS",  # Default to month start
         x_padding: int = 4,
@@ -50,11 +52,12 @@ def find_peaks(self) -> pd.Series:
         """
         # Group by the specified window (default is month start)
         grouped = self.data.groupby(pd.Grouper(freq=self.window))
+
         # Find the index (timestamp) of the maximum value in each group
         peak_indices = grouped.idxmax()
+
         # Get the corresponding peak values
         peaks = self.data.loc[peak_indices][self.data > self.threshold]
-
         return peaks
 
     def find_peaks_with_surroundings(
@@ -69,12 +72,20 @@ def find_peaks_with_surroundings(
         Returns:
             List[tuple[dt.datetime,float,pd.Series]]: A list of tuples containing peak time, peak value, and surrounding data.
         """
-        peaks = self.data.sort_values(ascending=False).head(num_peaks)
+        peaks = self.data.nlargest(num_peaks * 2)
         peaks = peaks[peaks > self.threshold]
         if peaks.empty:
             return []
+
         result = []
+        window_size = dt.timedelta(minutes=15 * (2 * self.x_padding + 1))
+
         for peak_time, peak_value in peaks.items():
+            peak_time = typing.cast(pd.Timestamp, peak_time)
+
+            if any(abs(peak_time - prev_peak[0]) < window_size for prev_peak in result):
+                continue
+
             start_time = peak_time - dt.timedelta(minutes=15 * self.x_padding)
             end_time = peak_time + dt.timedelta(minutes=15 * (self.x_padding + 1))
             surrounding_data = self.data[start_time:end_time]
@@ -86,5 +97,6 @@ def find_peaks_with_surroundings(
                     surrounding_data,
                 ]
             )
-
+            if len(result) == num_peaks:
+                break
         return result
diff --git a/openenergyid/capacity/models.py b/openenergyid/capacity/models.py
@@ -10,6 +10,7 @@ class CapacityInput(BaseModel):
 
     timezone: str = Field(alias="timeZone")
     series: TimeSeries
+    threshold: float = Field(default=2.5, ge=0)
 
 
 class PeakDetail(BaseModel):

diff --git a/openenergyid/models.py b/openenergyid/models.py
@@ -63,7 +63,19 @@ def from_json(cls, string: str | None = None, path: str | None = None, **kwargs)
 
 
 class TimeSeries(TimeSeriesBase):
-    """Time series data with a single column."""
+    """
+    Represents a time series data.
+    Attributes:
+        name (str | None): The name of the time series.
+        data (list[float | None]): The data points of the time series.
+    Methods:
+        replace_nan_with_none(cls, data: list[float]) -> list[float | None]:
+            Replace NaN values with None.
+        from_pandas(cls, data: pd.Series) -> Self:
+            Create a TimeSeries object from a Pandas Series.
+        to_pandas(self, timezone: str = "UTC") -> pd.Series:
+            Convert the TimeSeries object to a Pandas Series.
+    """
 
     name: str | None = None
     data: list[float | None]

diff --git a/poetry.lock b/poetry.lock
diff --git a/pyproject.toml b/pyproject.toml
@@ -66,3 +66,4 @@ seaborn = "^0.13.2"
 pytest = "^8.3.2"
 entsoe-py = "^0.6.8"
 energyid = "^0.0.17"
+snakeviz = "^2.2.0"
diff --git a/requirements-dev.txt b/requirements-dev.txt
@@ -5,18 +5,18 @@ argon2-cffi==23.1.0
 arrow==1.3.0 
 asttokens==2.4.1 
 async-lru==2.0.4 
-attrs==23.2.0 
-babel==2.15.0 
+attrs==24.2.0 
+babel==2.16.0 
 beautifulsoup4==4.12.3 
 bleach==6.1.0 
 certifi==2024.7.4 
-cffi==1.16.0 
+cffi==1.17.0 
 charset-normalizer==3.3.2 
 colorama==0.4.6 
 comm==0.2.2 
 contourpy==1.2.1 
 cycler==0.12.1 
-debugpy==1.8.2 
+debugpy==1.8.5 
 decorator==5.1.1 
 defusedxml==0.7.1 
 energyid==0.0.17 
@@ -57,15 +57,15 @@ jupyterlab==4.2.4
 kiwisolver==1.4.5 
 markupsafe==2.1.5 
 matplotlib-inline==0.1.7 
-matplotlib==3.9.1 
+matplotlib==3.9.2 
 mistune==3.0.2 
 nbclient==0.10.0 
 nbconvert==7.16.4 
 nbformat==5.10.4 
 nest-asyncio==1.6.0 
 notebook-shim==0.2.4 
 notebook==7.2.1 
-numpy==2.0.0 
+numpy==2.0.1 
 overrides==7.7.0 
 packaging==24.1 
 pandas==2.2.2 
@@ -79,7 +79,7 @@ prometheus-client==0.20.0
 prompt-toolkit==3.0.47 
 psutil==6.0.0 
 ptyprocess==0.7.0 
-pure-eval==0.2.2 
+pure-eval==0.2.3 
 pycparser==2.22 
 pygments==2.18.0 
 pyparsing==3.1.2 
@@ -89,21 +89,22 @@ python-json-logger==2.0.7
 pytz==2024.1 
 pywin32==306 
 pywinpty==2.0.13 
-pyyaml==6.0.1 
-pyzmq==26.0.3 
+pyyaml==6.0.2 
+pyzmq==26.1.0 
 qtconsole==5.5.2 
 qtpy==2.4.1 
 referencing==0.35.1 
 requests==2.32.3 
 rfc3339-validator==0.1.4 
 rfc3986-validator==0.1.1 
-rpds-py==0.19.0 
+rpds-py==0.20.0 
 seaborn==0.13.2 
 send2trash==1.8.3 
-setuptools==71.0.3 
+setuptools==72.2.0 
 six==1.16.0 
+snakeviz==2.2.0 
 sniffio==1.3.1 
-soupsieve==2.5 
+soupsieve==2.6 
 stack-data==0.6.3 
 terminado==0.18.1 
 tinycss2==1.3.0 
@@ -116,7 +117,7 @@ tzdata==2024.1
 uri-template==1.3.0 
 urllib3==2.2.2 
 wcwidth==0.2.13 
-webcolors==24.6.0 
+webcolors==24.8.0 
 webencodings==0.5.1 
 websocket-client==1.8.0 
 widgetsnbextension==4.0.11 
diff --git a/requirements.txt b/requirements.txt
@@ -1,7 +1,10 @@
 annotated-types==0.7.0 
-numpy==2.0.0 
+multimethod==1.10 
+mypy-extensions==1.0.0 
+numpy==2.0.1 
 packaging==24.1 
 pandas==2.2.2 
+pandera==0.20.3 
 patsy==0.5.6 
 pydantic-core==2.20.1 
 pydantic==2.8.2