spotforecast2-safe 0.0.1__py3-none-any.whl → 0.0.2__py3-none-any.whl

spotforecast2_safe/preprocessing/__init__.py

@@ -9,13 +9,8 @@ from .outlier import (
     mark_outliers,
     manual_outlier_removal,
     get_outliers,
-    visualize_outliers_hist,
-    visualize_outliers_plotly_scatter,
-)
-from .time_series_visualization import (
-    visualize_ts_plotly,
-    visualize_ts_comparison,
 )
+
 from .imputation import custom_weights, get_missing_weights, WeightFunction
 from .split import split_abs_train_val_test, split_rel_train_val_test
 from ._differentiator import TimeSeriesDifferentiator
@@ -31,10 +26,6 @@ __all__ = [
     "mark_outliers",
     "manual_outlier_removal",
     "get_outliers",
-    "visualize_outliers_hist",
-    "visualize_outliers_plotly_scatter",
-    "visualize_ts_plotly",
-    "visualize_ts_comparison",
     "custom_weights",
     "get_missing_weights",
     "WeightFunction",

spotforecast2_safe/preprocessing/outlier.py

@@ -1,14 +1,8 @@
-from typing import Optional, Dict, Any
+from typing import Optional, Dict
 
 from sklearn.ensemble import IsolationForest
 import numpy as np
 import pandas as pd
-import matplotlib.pyplot as plt
-
-try:
-    import plotly.graph_objects as go
-except ImportError:
-    go = None
 
 
 def mark_outliers(
@@ -192,244 +186,3 @@ def get_outliers(
             outliers_dict[col] = data.loc[outlier_mask, col]
 
     return outliers_dict
-
-
-def visualize_outliers_hist(
-    data: pd.DataFrame,
-    data_original: pd.DataFrame,
-    columns: Optional[list[str]] = None,
-    contamination: float = 0.01,
-    random_state: int = 1234,
-    figsize: tuple[int, int] = (10, 5),
-    bins: int = 50,
-    **kwargs: Any,
-) -> None:
-    """Visualize outliers in DataFrame using stacked histograms.
-
-    Creates a histogram for each specified column, displaying both regular data
-    and detected outliers in different colors. Uses IsolationForest for outlier
-    detection.
-
-    Args:
-        data: The DataFrame with cleaned data (outliers may be NaN).
-        data_original: The original DataFrame before outlier detection.
-        columns: List of column names to visualize. If None, all columns are used.
-            Default: None.
-        contamination: The estimated proportion of outliers in the dataset.
-            Default: 0.01.
-        random_state: Random seed for reproducibility. Default: 1234.
-        figsize: Figure size as (width, height). Default: (10, 5).
-        bins: Number of histogram bins. Default: 50.
-        **kwargs: Additional keyword arguments passed to plt.hist() (e.g., color,
-            alpha, edgecolor, etc.).
-
-    Returns:
-        None. Displays matplotlib figures.
-
-    Raises:
-        ValueError: If data or data_original is empty, or if specified columns
-            don't exist.
-        ImportError: If matplotlib is not installed.
-
-    Examples:
-        >>> import pandas as pd
-        >>> import numpy as np
-        >>> from spotforecast2.preprocessing.outlier import visualize_outliers_hist
-        >>>
-        >>> # Create sample data
-        >>> np.random.seed(42)
-        >>> data_original = pd.DataFrame({
-        ...     'temperature': np.concatenate([
-        ...         np.random.normal(20, 5, 100),
-        ...         [50, 60, 70]  # outliers
-        ...     ]),
-        ...     'humidity': np.concatenate([
-        ...         np.random.normal(60, 10, 100),
-        ...         [95, 98, 99]  # outliers
-        ...     ])
-        ... })
-        >>> data_cleaned = data_original.copy()
-        >>>
-        >>> # Visualize outliers
-        >>> visualize_outliers_hist(
-        ...     data_cleaned,
-        ...     data_original,
-        ...     contamination=0.03,
-        ...     figsize=(12, 5),
-        ...     alpha=0.7
-        ... )
-    """
-    if data.empty or data_original.empty:
-        raise ValueError("Input data is empty")
-
-    columns_to_plot = columns if columns is not None else data.columns
-
-    # Validate columns exist
-    missing_cols = set(columns_to_plot) - set(data.columns)
-    if missing_cols:
-        raise ValueError(f"Columns not found in data: {missing_cols}")
-
-    # Detect outliers
-    outliers = get_outliers(
-        data_original,
-        data_original=data_original,
-        contamination=contamination,
-        random_state=random_state,
-    )
-
-    for col in columns_to_plot:
-        # Get inliers (non-NaN values in cleaned data)
-        inliers = data[col].dropna()
-
-        # Get outlier values
-        outlier_vals = outliers[col]
-
-        # Calculate percentage
-        pct_outliers = (len(outlier_vals) / len(data_original)) * 100
-
-        # Create figure
-        plt.figure(figsize=figsize)
-        plt.hist(
-            [inliers, outlier_vals],
-            bins=bins,
-            stacked=True,
-            color=["lightgrey", "red"],
-            label=["Regular Data", "Outliers"],
-            **kwargs,
-        )
-        plt.grid(True, alpha=0.3)
-        plt.title(f"{col} Distribution with Outliers ({pct_outliers:.2f}%)")
-        plt.xlabel("Value")
-        plt.ylabel("Frequency")
-        plt.legend()
-        plt.tight_layout()
-        plt.show()
-
-
-def visualize_outliers_plotly_scatter(
-    data: pd.DataFrame,
-    data_original: pd.DataFrame,
-    columns: Optional[list[str]] = None,
-    contamination: float = 0.01,
-    random_state: int = 1234,
-    **kwargs: Any,
-) -> None:
-    """Visualize outliers in time series using Plotly scatter plots.
-
-    Creates an interactive time series plot for each specified column, showing
-    regular data as a line and detected outliers as scatter points. Uses
-    IsolationForest for outlier detection.
-
-    Args:
-        data: The DataFrame with cleaned data (outliers may be NaN).
-        data_original: The original DataFrame before outlier detection.
-        columns: List of column names to visualize. If None, all columns are used.
-            Default: None.
-        contamination: The estimated proportion of outliers in the dataset.
-            Default: 0.01.
-        random_state: Random seed for reproducibility. Default: 1234.
-        **kwargs: Additional keyword arguments passed to go.Figure.update_layout()
-            (e.g., template, height, etc.).
-
-    Returns:
-        None. Displays Plotly figures.
-
-    Raises:
-        ValueError: If data or data_original is empty, or if specified columns
-            don't exist.
-        ImportError: If plotly is not installed.
-
-    Examples:
-        >>> import pandas as pd
-        >>> import numpy as np
-        >>> from spotforecast2.preprocessing.outlier import visualize_outliers_plotly_scatter
-        >>>
-        >>> # Create sample time series data
-        >>> np.random.seed(42)
-        >>> dates = pd.date_range('2024-01-01', periods=103, freq='h')
-        >>> data_original = pd.DataFrame({
-        ...     'temperature': np.concatenate([
-        ...         np.random.normal(20, 5, 100),
-        ...         [50, 60, 70]  # outliers
-        ...     ]),
-        ...     'humidity': np.concatenate([
-        ...         np.random.normal(60, 10, 100),
-        ...         [95, 98, 99]  # outliers
-        ...     ])
-        ... }, index=dates)
-        >>> data_cleaned = data_original.copy()
-        >>>
-        >>> # Visualize outliers
-        >>> visualize_outliers_plotly_scatter(
-        ...     data_cleaned,
-        ...     data_original,
-        ...     contamination=0.03,
-        ...     template='plotly_white'
-        ... )
-    """
-    if go is None:
-        raise ImportError(
-            "plotly is required for this function. " "Install with: pip install plotly"
-        )
-
-    if data.empty or data_original.empty:
-        raise ValueError("Input data is empty")
-
-    columns_to_plot = columns if columns is not None else data.columns
-
-    # Validate columns exist
-    missing_cols = set(columns_to_plot) - set(data.columns)
-    if missing_cols:
-        raise ValueError(f"Columns not found in data: {missing_cols}")
-
-    # Detect outliers
-    outliers = get_outliers(
-        data_original,
-        data_original=data_original,
-        contamination=contamination,
-        random_state=random_state,
-    )
-
-    for col in columns_to_plot:
-        fig = go.Figure()
-
-        # Add regular data as line
-        fig.add_trace(
-            go.Scatter(
-                x=data.index,
-                y=data[col],
-                mode="lines",
-                name="Regular Data",
-                line=dict(color="lightgrey"),
-            )
-        )
-
-        # Add outliers as scatter points
-        outlier_vals = outliers[col]
-        if not outlier_vals.empty:
-            fig.add_trace(
-                go.Scatter(
-                    x=outlier_vals.index,
-                    y=outlier_vals,
-                    mode="markers",
-                    name="Outliers",
-                    marker=dict(color="red", size=8, symbol="x"),
-                )
-            )
-
-        # Calculate percentage
-        pct_outliers = (len(outlier_vals) / len(data_original)) * 100
-
-        # Update layout with custom kwargs
-        layout_kwargs = {
-            "title": f"{col} Time Series with Outliers ({pct_outliers:.2f}%)",
-            "xaxis_title": "Time",
-            "yaxis_title": "Value",
-            "template": "plotly_white",
-            "legend": dict(
-                orientation="h", yanchor="bottom", y=1.02, xanchor="right", x=1
-            ),
-        }
-        layout_kwargs.update(kwargs)
-        fig.update_layout(**layout_kwargs)
-        fig.show()

spotforecast2_safe-0.0.2.dist-info/METADATA

@@ -0,0 +1,107 @@
+Metadata-Version: 2.3
+Name: spotforecast2-safe
+Version: 0.0.2
+Summary: spotforecast2-safe (Core): Safety-critical time series forecasting for production
+Author: bartzbeielstein
+Author-email: bartzbeielstein <32470350+bartzbeielstein@users.noreply.github.com>
+Requires-Dist: astral>=3.2
+Requires-Dist: feature-engine>=1.9.3
+Requires-Dist: flake8>=7.3.0
+Requires-Dist: holidays>=0.90
+Requires-Dist: lightgbm>=4.6.0
+Requires-Dist: numba>=0.63.1
+Requires-Dist: pandas>=3.0.0
+Requires-Dist: pyarrow>=23.0.0
+Requires-Dist: scikit-learn>=1.8.0
+Requires-Dist: tqdm>=4.67.2
+Requires-Dist: pytest>=9.0.2 ; extra == 'dev'
+Requires-Dist: pytest-cov>=6.0.0 ; extra == 'dev'
+Requires-Dist: black>=24.1.0 ; extra == 'dev'
+Requires-Dist: isort>=5.13.0 ; extra == 'dev'
+Requires-Dist: ruff>=0.3.0 ; extra == 'dev'
+Requires-Dist: mkdocs>=1.6.1 ; extra == 'dev'
+Requires-Dist: mkdocs-material>=9.7.1 ; extra == 'dev'
+Requires-Dist: mkdocstrings>=1.0.2 ; extra == 'dev'
+Requires-Dist: mkdocstrings-python>=2.0.1 ; extra == 'dev'
+Requires-Dist: safety>=3.0.0 ; extra == 'dev'
+Requires-Dist: bandit>=1.8.0 ; extra == 'dev'
+Requires-Python: >=3.13
+Project-URL: Documentation, https://sequential-parameter-optimization.github.io/spotforecast2-safe/
+Project-URL: Repository, https://github.com/sequential-parameter-optimization/spotforecast2-safe
+Project-URL: Issues, https://github.com/sequential-parameter-optimization/spotforecast2-safe/issues
+Provides-Extra: dev
+Description-Content-Type: text/markdown
+
+<div align="left">
+  <img src="logo/spotlogo.png" alt="spotforecast2-safe Logo" width="300">
+</div>
+
+# spotforecast2-safe (Core)
+
+[![Python Version](https://img.shields.io/badge/python-3.13%2B-blue)](https://www.python.org/downloads/)
+[![EU AI Act](https://img.shields.io/badge/EU%20AI%20Act-Ready-success)](MODEL_CARD.md)
+[![Dependencies](https://img.shields.io/badge/dependencies-minimal-blue)](pyproject.toml)
+[![Audit](https://img.shields.io/badge/audit-whitebox-brightgreen)](MODEL_CARD.md)
+[![License](https://img.shields.io/github/license/sequential-parameter-optimization/spotforecast2-safe)](LICENSE)
+
+**Testing & Quality**
+
+[![Build Status](https://img.shields.io/github/actions/workflow/status/sequential-parameter-optimization/spotforecast2-safe/ci.yml?branch=main&label=Tests)](https://github.com/sequential-parameter-optimization/spotforecast2-safe/actions/workflows/ci.yml)
+[![Documentation](https://img.shields.io/badge/docs-passing-brightgreen)](https://sequential-parameter-optimization.github.io/spotforecast2-safe/)
+[![Reliability](https://img.shields.io/badge/robustness-fail--safe-orange)](MODEL_CARD.md)
+
+**Status**
+
+[![Maintenance](https://img.shields.io/badge/maintenance-active-green)](https://github.com/sequential-parameter-optimization/spotforecast2-safe)
+[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
+
+
+
+## Safety-Critical Design Goals
+
+`spotforecast2-safe` is a specialized Python library designed to **facilitate** time series forecasting in safety-critical production environments and embedded systems. 
+
+Unlike standard machine and dep learning libraries, it follows a strict **"Safety-First"** architecture by design. **However, users must independently verify that these features meet their specific regulatory requirements:**
+
+- **Zero Dead Code**: We aim to minimize the attack surface by excluding visualization and training logic.
+- **Deterministic Logic**: The algorithms are designed to be purely mathematical and deterministic.
+- **Fail-Safe Operation**: The system is designed to favor explicit errors over silent failures when encountering invalid data.
+- **EU AI Act Support**: The architecture supports transparency and data governance, helping users build compliant high-risk AI components.
+
+For a detailed technical overview of our safety mechanisms, see our **[MODEL_CARD.md](MODEL_CARD.md)**.
+
+## ⚠️ Disclaimer & Liability
+
+**IMPORTANT**: This software is provided "as is" and any express or implied warranties, including, but not limited to, the implied warranties of merchantability and fitness for a particular purpose are disclaimed. 
+
+In no event shall the authors, copyright holders, or contributors be liable for any direct, indirect, incidental, special, exemplary, or consequential damages (including, but not limited to, procurement of substitute goods or services; loss of use, data, or profits; or business interruption) however caused and on any theory of liability, whether in contract, strict liability, or tort (including negligence or otherwise) arising in any way out of the use of this software, even if advised of the possibility of such damage.
+
+**The use of this software in safety-critical systems is at the sole risk of the user.**
+
+## Attributions
+
+Parts of the code are ported from `skforecast` to reduce external dependencies.
+Many thanks to the [skforecast team](https://skforecast.org/0.20.0/more/about-skforecast.html) for their great work!
+
+## Documentation
+
+ Documentation (API) is available at: [https://sequential-parameter-optimization.github.io/spotforecast2-safe/](https://sequential-parameter-optimization.github.io/spotforecast2-safe/)
+
+## License
+
+`spotforecast2-safe` software: [BSD-3-Clause License](LICENSE)
+
+
+# References
+
+## spotforecast2
+
+The "full" version of `spotforecast2-safe`, which is named `spotforecast`, is available at: [https://sequential-parameter-optimization.github.io/spotforecast2/](https://sequential-parameter-optimization.github.io/spotforecast2/)
+
+## skforecast 
+
+* Amat Rodrigo, J., & Escobar Ortiz, J. (2026). skforecast (Version 0.20.0) [Computer software]. https://doi.org/10.5281/zenodo.8382788 
+
+## spotoptim
+
+* [spotoptim documentation](https://sequential-parameter-optimization.github.io/spotoptim/)

{spotforecast2_safe-0.0.1.dist-info → spotforecast2_safe-0.0.2.dist-info}/RECORD

@@ -5,39 +5,25 @@ spotforecast2_safe/data/fetch_data.py,sha256=q2_f_GGjNWX2sb6aVlCKfOLShcdBTGkyx7r
 spotforecast2_safe/exceptions.py,sha256=GaEIZMrdx0in3laIxwpB3KcFOovim6KznZt-oE4MfU8,20516
 spotforecast2_safe/forecaster/__init__.py,sha256=BbCOS2ouKcPC9VzcdprllVyqlZIyAWXCOvUAiInxDi4,140
 spotforecast2_safe/forecaster/base.py,sha256=_Asa5yCGz4zaMpqcjAuxPy9nnH4P387T24RnYM0dPc8,16755
-spotforecast2_safe/forecaster/metrics.py,sha256=MiZs9MAvT5JjPEGEks1uWR0nFuzYucCWuu4bMV_4HPQ,19316
 spotforecast2_safe/forecaster/recursive/__init__.py,sha256=YNVxLReLEwSFDasmjXXMSKJqNL_Y4lVEZ696UksjVVE,184
 spotforecast2_safe/forecaster/recursive/_forecaster_equivalent_date.py,sha256=PEu9aCW0UT_gdA0PzGEMijXSQW1Yz1Af57ieRyyjYtI,48252
 spotforecast2_safe/forecaster/recursive/_forecaster_recursive.py,sha256=uMVNqLTjGytVxq1jgUDhVbot9yvzqQvtucstKuIMAxY,44256
 spotforecast2_safe/forecaster/recursive/_warnings.py,sha256=BtZ3UoycywjEQ0ceXe4TL1WEdFcLAi1EnDMvZXHw_U8,325
 spotforecast2_safe/forecaster/utils.py,sha256=uc7jusIzhjVRTH-8kRip6BPiILr-nARUDWUwNaWtPws,38159
-spotforecast2_safe/model_selection/__init__.py,sha256=uP60TkgDzs_x5V60rnKanc12S9-yXx2ZLsXsXdqAYEA,208
-spotforecast2_safe/model_selection/bayesian_search.py,sha256=94zYTFjlhG5FuMxeR4H1R_s5cAyTrYVYZPE1cBod4L8,17447
-spotforecast2_safe/model_selection/grid_search.py,sha256=kK2cS6sZg3nUBEJEPtAkuqxO_AJrh2wwVuRIvMwywOo,11038
-spotforecast2_safe/model_selection/random_search.py,sha256=ZaLZo7ibOZUC40JB8ycgLQv3rGWoiSOx3K-FFr1eGUk,6282
-spotforecast2_safe/model_selection/split_base.py,sha256=zpIl8CnWhM526GkIT2XlSJ5cQQZTjt2F-E97ycK0sT4,15002
-spotforecast2_safe/model_selection/split_one_step.py,sha256=tc3oOkbXxLUXd3mwjo2NVVW3PgbOR7slSQnRxinxAsc,9412
-spotforecast2_safe/model_selection/split_ts_cv.py,sha256=pV0eCqTLipC7aBezAvz15zuAJ8dNAPXT0VwpYGKF3_s,29977
-spotforecast2_safe/model_selection/utils_common.py,sha256=AujMGU4G3nncQ8Ym_eXPu6IbXCcYq3vgitAEWaRS4kE,31819
-spotforecast2_safe/model_selection/utils_metrics.py,sha256=mMVKh03-yAvRjEnZlbg3CsktXNcHo7yiTkI5VMg5wQk,3842
-spotforecast2_safe/model_selection/validation.py,sha256=9IU76Hymh6WPqcEunZwOIvYF72LJ-D5HFHfX8GWaht4,30063
-spotforecast2_safe/preprocessing/__init__.py,sha256=UkwleNM-ue_YbaCLcYywW-qLqd8SFJ08-qKuv4tbaDs,1212
+spotforecast2_safe/preprocessing/__init__.py,sha256=xbRMD0zEr3hhxfXD-7sOjtdJDdG6LWeOe6-pumkPCU0,918
 spotforecast2_safe/preprocessing/_binner.py,sha256=2bWGMh_Ytyphxb_5j2VlIT8w3tx24GZs_g53o0Nb390,13848
 spotforecast2_safe/preprocessing/_common.py,sha256=aP8EIYIg3iBXnijXByHedGEdcubXu-ciRtEgqdDfO_8,3141
 spotforecast2_safe/preprocessing/_differentiator.py,sha256=otka_TO1edM3zgp16zOjeSKxa61arbmPPsr96_GfgLI,4646
 spotforecast2_safe/preprocessing/_rolling.py,sha256=eYBOH2QRDbue8MYtitcOFLQS0PMdNi6v9I0nu07XexY,9057
 spotforecast2_safe/preprocessing/curate_data.py,sha256=4VV8aYwShyrUc9lqWVx_ckIH-moK0B8ONEMb2i463ag,9603
 spotforecast2_safe/preprocessing/imputation.py,sha256=wXHXcIwWb7_XqW9JdBjaRA7NxWhbKWoQyW5z0KkPLd8,5201
-spotforecast2_safe/preprocessing/outlier.py,sha256=SubBnZTXyJM01zSdll__4iCUA5dDwxF5rIXgMe5iOFQ,15144
+spotforecast2_safe/preprocessing/outlier.py,sha256=uXb9QIYmYM4h3e7tZkdGUF1rVl-Df3E__g9IcDCiuE0,6996
 spotforecast2_safe/preprocessing/split.py,sha256=mzzt5ltUZdVzfWtBBTQjp8E2MyqVdWUFtz7nN11urbU,5011
-spotforecast2_safe/preprocessing/time_series_visualization.py,sha256=KBneOjJVE_uajm5v-28GdYhf6vkMCBUreGfl1GQlJAA,27706
 spotforecast2_safe/processing/__init__.py,sha256=IJ5jTWRvI7V6MCtFpKL1j7tY9VUXwqPiDtfghmfI6Lg,294
 spotforecast2_safe/processing/agg_predict.py,sha256=4iFGm5leCefnBROcBCfwNrOZ7qFC43NIXZ9TxH6QhrA,2471
 spotforecast2_safe/processing/n2n_predict.py,sha256=S4TjuAaKZWjHg9thxVSPr0wneZYeAEJ4jiCoiJ-3d_U,15369
 spotforecast2_safe/processing/n2n_predict_with_covariates.py,sha256=IDoEMOAOOacagJRbNJb1ki64bozNJBprUP9PQyGGe_E,41379
 spotforecast2_safe/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-spotforecast2_safe/stats/__init__.py,sha256=9KVh7ZQD_48AJ0bTNQyYWMT2mBaOrX26W-iA3r-IppE,166
-spotforecast2_safe/stats/autocorrelation.py,sha256=5T-GydM5EfBaLU1iM7F8A9bdc__u_0I9zEonQpT-dos,6854
 spotforecast2_safe/utils/__init__.py,sha256=BSzSzgm10C3h_0qQKSlEtTBtzHD-qjbG9L599Ulx_9c,1043
 spotforecast2_safe/utils/convert_to_utc.py,sha256=hz8mJUHK9jDLUiN5LdNX5l3KZuOKlklyycB4zFdB9Ng,1405
 spotforecast2_safe/utils/data_transform.py,sha256=PhLeZoimM0TLfp34Fp56dQrxlCYNWGVU8h8RZHdZSlo,7294
@@ -46,6 +32,6 @@ spotforecast2_safe/utils/generate_holiday.py,sha256=SHaPvPMt-abis95cChHf5ObyPwCT
 spotforecast2_safe/utils/validation.py,sha256=YfFn4OW-SJeJDioY0opkhY9ISGnZ075KIXdfxlSKlyw,21623
 spotforecast2_safe/weather/__init__.py,sha256=1Jco88pl0deNESgNATin83Nf5i9c58pxN7G-vNiOiu0,120
 spotforecast2_safe/weather/weather_client.py,sha256=Ec_ywug6uoa71MfXM8RNbXEvtBtBzr-SUS5xq_HKtZE,9837
-spotforecast2_safe-0.0.1.dist-info/WHEEL,sha256=iHtWm8nRfs0VRdCYVXocAWFW8ppjHL-uTJkAdZJKOBM,80
-spotforecast2_safe-0.0.1.dist-info/METADATA,sha256=plPc6Nuae8Gt9rv5C-NbjzRv2qJuNfcgQ5amPuedvYw,4073
-spotforecast2_safe-0.0.1.dist-info/RECORD,,
+spotforecast2_safe-0.0.2.dist-info/WHEEL,sha256=iHtWm8nRfs0VRdCYVXocAWFW8ppjHL-uTJkAdZJKOBM,80
+spotforecast2_safe-0.0.2.dist-info/METADATA,sha256=saUC8IP6_mxcusND1eyyKk-MPYrz7j-FTpPaSZPkkVs,5779
+spotforecast2_safe-0.0.2.dist-info/RECORD,,