skfolio 0.0.7__tar.gz → 0.0.9__tar.gz

{skfolio-0.0.7/src/skfolio.egg-info → skfolio-0.0.9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: skfolio
-Version: 0.0.7
+Version: 0.0.9
 Summary: Portfolio optimization built on top of scikit-learn
 Author-email: Hugo Delatte <delatte.hugo@gmail.com>
 Maintainer-email: Hugo Delatte <delatte.hugo@gmail.com>
@@ -78,7 +78,6 @@ Requires-Dist: kaleido; extra == "docs"
 Requires-Dist: sphinx-copybutton; extra == "docs"
 Requires-Dist: numpydoc; extra == "docs"
 Requires-Dist: sphinx-togglebutton; extra == "docs"
-Requires-Dist: jupyterlite-sphinx; extra == "docs"
 Requires-Dist: sphinx-favicon; extra == "docs"
 Requires-Dist: sphinx-prompt; extra == "docs"
 Requires-Dist: sphinxext.opengraph; extra == "docs"
@@ -128,8 +127,10 @@ Requires-Dist: sphinx-favicon; extra == "docs"
 
 
 **skfolio** is a Python library for portfolio optimization built on top of scikit-learn.
-It provides a unified interface and `sklearn` compatible tools to build, tune and
-cross-validate portfolio models. It is distributed under the 3-Clause BSD license.
+It offers a unified interface and tools compatible with scikit-learn to build, fine-tune,
+and cross-validate portfolio models.
+
+It is distributed under the open source 3-Clause BSD license.
 
 .. image:: https://raw.githubusercontent.com/skfolio/skfolio/master/docs/_static/expo.jpg
     :target: https://skfolio.org/auto_examples/
@@ -146,7 +147,7 @@ Important links
 Installation
 ~~~~~~~~~~~~
 
-To install skfolio::
+`skfolio` is available on PyPI and can be installed with::
 
     pip install -U skfolio
 
@@ -155,7 +156,7 @@ To install skfolio::
 Dependencies
 ~~~~~~~~~~~~
 
-skfolio requires:
+`skfolio` requires:
 
 - python (>= |PythonMinVersion|)
 - numpy (>= |NumpyMinVersion|)
@@ -168,30 +169,37 @@ skfolio requires:
 
 Key Concepts
 ~~~~~~~~~~~~
-Since the development of modern portfolio theory by Markowitz (1952), mean-variance optimization (MVO)
-has received considerable attention. Unfortunately it faces a number of shortcomings including high sensitivity to the
-input parameters (expected returns and covariance), weight concentration, high turnover and poor out-of-sample
-performance.
-It is well known that naive allocation (1/N, inverse-vol, ...) tend to outperform MVO out-of-sample (DeMiguel, 2007).
+Since the development of modern portfolio theory by Markowitz (1952), mean-variance
+optimization (MVO) has received considerable attention.
+
+Unfortunately, it faces a number of shortcomings, including high sensitivity to the
+input parameters (expected returns and covariance), weight concentration, high turnover,
+and poor out-of-sample performance.
+
+It is well known that naive allocation (1/N, inverse-vol, etc.) tends to outperform
+MVO out-of-sample (DeMiguel, 2007).
 
-Numerous approaches have been developed to alleviate these shortcomings (shrinkage, bayesian approaches,
-additional constraints, regularization, uncertainty set, higher moments, coherent risk measures,
-left-tail risk optimization, distributionally robust optimization, factor model, risk-parity, hierarchical clustering,
-ensemble methods...)
+Numerous approaches have been developed to alleviate these shortcomings (shrinkage,
+additional constraints, regularization, uncertainty set, higher moments, Bayesian
+approaches, coherent risk measures, left-tail risk optimization, distributionally robust
+optimization, factor model, risk-parity, hierarchical clustering, ensemble methods,
+pre-selection, etc.).
 
-With this large number of methods, added to the fact that they can be composed together there is the need for an
-unified framework to perform model selection, validation and parameter tuning while reducing the risk of data leakage
-and overfitting. This framework is build on scikit-learn's API.
+With this large number of methods, added to the fact that they can be composed together,
+there is a need for a unified framework with a machine learning approach to perform
+model selection, validation, and parameter tuning while reducing the risk of data
+leakage and overfitting.
+
+This framework is built on scikit-learn's API.
 
 Available models
 ~~~~~~~~~~~~~~~~
-The current release contains:
 
-* Optimization estimators:
+* Portfolio Optimization:
     * Naive:
         * Equal-Weighted
         * Inverse-Volatility
-        * Random (dirichlet)
+        * Random (Dirichlet)
     * Convex:
         * Mean-Risk
         * Risk Budgeting
@@ -201,27 +209,27 @@ The current release contains:
         * Hierarchical Risk Parity
         * Hierarchical Equal Risk Contribution
         * Nested Clusters Optimization
-    * Ensemble methods:
+    * Ensemble Methods:
         * Stacking Optimization
 
-* Moment estimators:
-    * Expected Returns:
-        * Empirical
-        * Exponentially Weighted
-        * Equilibrium
-        * Shrinkage (James-Stein, Bayes-Stein, ...)
-    * Covariance:
-        * Empirical
-        * Gerber
-        * Denoising
-        * Denoting
-        * Exponentially Weighted
-        * Ledoit-Wolf
-        * Oracle Approximating Shrinkage
-        * Shrunk Covariance
-        * Graphical lasso CV
-
-* Distance estimator:
+* Expected Returns Estimator:
+    * Empirical
+    * Exponentially Weighted
+    * Equilibrium
+    * Shrinkage
+
+* Covariance Estimator:
+    * Empirical
+    * Gerber
+    * Denoising
+    * Denoting
+    * Exponentially Weighted
+    * Ledoit-Wolf
+    * Oracle Approximating Shrinkage
+    * Shrunk Covariance
+    * Graphical Lasso CV
+
+* Distance Estimator:
     * Pearson Distance
     * Kendall Distance
     * Spearman Distance
@@ -229,12 +237,12 @@ The current release contains:
     * Distance Correlation
     * Variation of Information
 
-* Prior estimators:
+* Prior Estimator:
     * Empirical
     * Black & Litterman
     * Factor Model
 
-* Uncertainty Set estimators:
+* Uncertainty Set Estimator:
     * On Expected Returns:
         * Empirical
         * Circular Bootstrap
@@ -242,18 +250,18 @@ The current release contains:
         * Empirical
         * Circular bootstrap
 
-* Pre-Selection transformers:
+* Pre-Selection Transformer:
     * Non-Dominated Selection
     * Select K Extremes (Best or Worst)
     * Drop Highly Correlated Assets
 
 * Cross-Validation and Model Selection:
-    * Compatible with all `sklearn` methods (KFold, ...)
+    * Compatible with all `sklearn` methods (KFold, etc.)
     * Walk Forward
-    * Combinatorial Purged Cross-validation
+    * Combinatorial Purged Cross-Validation
 
 * Hyper-Parameter Tuning:
-    * Compatible with all `sklearn` methods (GridSearchCV, RandomizedSearchCV, ...)
+    * Compatible with all `sklearn` methods (GridSearchCV, RandomizedSearchCV)
 
 * Risk Measures:
     * Variance
@@ -277,9 +285,24 @@ The current release contains:
     * Skew
     * Kurtosis
 
+* Optimization Features:
+    * Minimize Risk
+    * Maximize Returns
+    * Maximize Utility
+    * Maximize Ratio
+    * Transaction Costs
+    * Management Fees
+    * L1 and L2 Regularization
+    * Weight Constraints
+    * Group Constraints
+    * Budget Constraints
+    * Tracking Error Constraints
+    * Turnover Constraints
+
 Quickstart
 ~~~~~~~~~~
-The code snippets below are designed to introduce ``skfolio``'s functionality so you can start using it quickly.
+The code snippets below are designed to introduce the functionality of `skfolio` so you
+can start using it quickly. It follows the same API as scikit-learn.
 
 Imports
 -------
@@ -591,9 +614,9 @@ Combinatorial Purged Cross-Validation
 Recognition
 ~~~~~~~~~~~
 
-We would like to thanks all contributors behind our direct dependencies like
-scikit-learn and cvxpy but also the contributors of the following packages that
-were a source of inspiration:
+We would like to thank all contributors behind our direct dependencies, such as
+scikit-learn and cvxpy, but also the contributors of the following packages that were a
+source of inspiration:
 
     * PyPortfolioOpt
     * Riskfolio-Lib
@@ -606,11 +629,11 @@ were a source of inspiration:
 Citation
 ~~~~~~~~
 
-If you use skfolio in a scientific publication, we would appreciate citations:
+If you use `skfolio` in a scientific publication, we would appreciate citations:
 
 Bibtex entry::
 
-    @misc{riskfolio,
+    @misc{skfolio,
           author = {Hugo Delatte},
           title = {skfolio},
           year  = {2023},

{skfolio-0.0.7 → skfolio-0.0.9}/README.rst

@@ -41,8 +41,10 @@
 
 
 **skfolio** is a Python library for portfolio optimization built on top of scikit-learn.
-It provides a unified interface and `sklearn` compatible tools to build, tune and
-cross-validate portfolio models. It is distributed under the 3-Clause BSD license.
+It offers a unified interface and tools compatible with scikit-learn to build, fine-tune,
+and cross-validate portfolio models.
+
+It is distributed under the open source 3-Clause BSD license.
 
 .. image:: https://raw.githubusercontent.com/skfolio/skfolio/master/docs/_static/expo.jpg
     :target: https://skfolio.org/auto_examples/
@@ -59,7 +61,7 @@ Important links
 Installation
 ~~~~~~~~~~~~
 
-To install skfolio::
+`skfolio` is available on PyPI and can be installed with::
 
     pip install -U skfolio
 
@@ -68,7 +70,7 @@ To install skfolio::
 Dependencies
 ~~~~~~~~~~~~
 
-skfolio requires:
+`skfolio` requires:
 
 - python (>= |PythonMinVersion|)
 - numpy (>= |NumpyMinVersion|)
@@ -81,30 +83,37 @@ skfolio requires:
 
 Key Concepts
 ~~~~~~~~~~~~
-Since the development of modern portfolio theory by Markowitz (1952), mean-variance optimization (MVO)
-has received considerable attention. Unfortunately it faces a number of shortcomings including high sensitivity to the
-input parameters (expected returns and covariance), weight concentration, high turnover and poor out-of-sample
-performance.
-It is well known that naive allocation (1/N, inverse-vol, ...) tend to outperform MVO out-of-sample (DeMiguel, 2007).
+Since the development of modern portfolio theory by Markowitz (1952), mean-variance
+optimization (MVO) has received considerable attention.
+
+Unfortunately, it faces a number of shortcomings, including high sensitivity to the
+input parameters (expected returns and covariance), weight concentration, high turnover,
+and poor out-of-sample performance.
+
+It is well known that naive allocation (1/N, inverse-vol, etc.) tends to outperform
+MVO out-of-sample (DeMiguel, 2007).
 
-Numerous approaches have been developed to alleviate these shortcomings (shrinkage, bayesian approaches,
-additional constraints, regularization, uncertainty set, higher moments, coherent risk measures,
-left-tail risk optimization, distributionally robust optimization, factor model, risk-parity, hierarchical clustering,
-ensemble methods...)
+Numerous approaches have been developed to alleviate these shortcomings (shrinkage,
+additional constraints, regularization, uncertainty set, higher moments, Bayesian
+approaches, coherent risk measures, left-tail risk optimization, distributionally robust
+optimization, factor model, risk-parity, hierarchical clustering, ensemble methods,
+pre-selection, etc.).
 
-With this large number of methods, added to the fact that they can be composed together there is the need for an
-unified framework to perform model selection, validation and parameter tuning while reducing the risk of data leakage
-and overfitting. This framework is build on scikit-learn's API.
+With this large number of methods, added to the fact that they can be composed together,
+there is a need for a unified framework with a machine learning approach to perform
+model selection, validation, and parameter tuning while reducing the risk of data
+leakage and overfitting.
+
+This framework is built on scikit-learn's API.
 
 Available models
 ~~~~~~~~~~~~~~~~
-The current release contains:
 
-* Optimization estimators:
+* Portfolio Optimization:
     * Naive:
         * Equal-Weighted
         * Inverse-Volatility
-        * Random (dirichlet)
+        * Random (Dirichlet)
     * Convex:
         * Mean-Risk
         * Risk Budgeting
@@ -114,27 +123,27 @@ The current release contains:
         * Hierarchical Risk Parity
         * Hierarchical Equal Risk Contribution
         * Nested Clusters Optimization
-    * Ensemble methods:
+    * Ensemble Methods:
         * Stacking Optimization
 
-* Moment estimators:
-    * Expected Returns:
-        * Empirical
-        * Exponentially Weighted
-        * Equilibrium
-        * Shrinkage (James-Stein, Bayes-Stein, ...)
-    * Covariance:
-        * Empirical
-        * Gerber
-        * Denoising
-        * Denoting
-        * Exponentially Weighted
-        * Ledoit-Wolf
-        * Oracle Approximating Shrinkage
-        * Shrunk Covariance
-        * Graphical lasso CV
-
-* Distance estimator:
+* Expected Returns Estimator:
+    * Empirical
+    * Exponentially Weighted
+    * Equilibrium
+    * Shrinkage
+
+* Covariance Estimator:
+    * Empirical
+    * Gerber
+    * Denoising
+    * Denoting
+    * Exponentially Weighted
+    * Ledoit-Wolf
+    * Oracle Approximating Shrinkage
+    * Shrunk Covariance
+    * Graphical Lasso CV
+
+* Distance Estimator:
     * Pearson Distance
     * Kendall Distance
     * Spearman Distance
@@ -142,12 +151,12 @@ The current release contains:
     * Distance Correlation
     * Variation of Information
 
-* Prior estimators:
+* Prior Estimator:
     * Empirical
     * Black & Litterman
     * Factor Model
 
-* Uncertainty Set estimators:
+* Uncertainty Set Estimator:
     * On Expected Returns:
         * Empirical
         * Circular Bootstrap
@@ -155,18 +164,18 @@ The current release contains:
         * Empirical
         * Circular bootstrap
 
-* Pre-Selection transformers:
+* Pre-Selection Transformer:
     * Non-Dominated Selection
     * Select K Extremes (Best or Worst)
     * Drop Highly Correlated Assets
 
 * Cross-Validation and Model Selection:
-    * Compatible with all `sklearn` methods (KFold, ...)
+    * Compatible with all `sklearn` methods (KFold, etc.)
     * Walk Forward
-    * Combinatorial Purged Cross-validation
+    * Combinatorial Purged Cross-Validation
 
 * Hyper-Parameter Tuning:
-    * Compatible with all `sklearn` methods (GridSearchCV, RandomizedSearchCV, ...)
+    * Compatible with all `sklearn` methods (GridSearchCV, RandomizedSearchCV)
 
 * Risk Measures:
     * Variance
@@ -190,9 +199,24 @@ The current release contains:
     * Skew
     * Kurtosis
 
+* Optimization Features:
+    * Minimize Risk
+    * Maximize Returns
+    * Maximize Utility
+    * Maximize Ratio
+    * Transaction Costs
+    * Management Fees
+    * L1 and L2 Regularization
+    * Weight Constraints
+    * Group Constraints
+    * Budget Constraints
+    * Tracking Error Constraints
+    * Turnover Constraints
+
 Quickstart
 ~~~~~~~~~~
-The code snippets below are designed to introduce ``skfolio``'s functionality so you can start using it quickly.
+The code snippets below are designed to introduce the functionality of `skfolio` so you
+can start using it quickly. It follows the same API as scikit-learn.
 
 Imports
 -------
@@ -504,9 +528,9 @@ Combinatorial Purged Cross-Validation
 Recognition
 ~~~~~~~~~~~
 
-We would like to thanks all contributors behind our direct dependencies like
-scikit-learn and cvxpy but also the contributors of the following packages that
-were a source of inspiration:
+We would like to thank all contributors behind our direct dependencies, such as
+scikit-learn and cvxpy, but also the contributors of the following packages that were a
+source of inspiration:
 
     * PyPortfolioOpt
     * Riskfolio-Lib
@@ -519,11 +543,11 @@ were a source of inspiration:
 Citation
 ~~~~~~~~
 
-If you use skfolio in a scientific publication, we would appreciate citations:
+If you use `skfolio` in a scientific publication, we would appreciate citations:
 
 Bibtex entry::
 
-    @misc{riskfolio,
+    @misc{skfolio,
           author = {Hugo Delatte},
           title = {skfolio},
           year  = {2023},

{skfolio-0.0.7 → skfolio-0.0.9}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "skfolio"
-version = "0.0.7"
+version = "0.0.9"
 maintainers = [
     { name = "Hugo Delatte", email = "delatte.hugo@gmail.com" },
 ]
@@ -75,7 +75,6 @@ docs = [
     "sphinx-copybutton",
     "numpydoc",
     "sphinx-togglebutton",
-    "jupyterlite-sphinx",
     "sphinx-favicon",
     "sphinx-prompt",
     "sphinxext.opengraph",

{skfolio-0.0.7 → skfolio-0.0.9}/src/skfolio/model_selection/_combinatorial.py

@@ -44,7 +44,7 @@ class CombinatorialPurgedCV(BaseCombinatorialCV):
     Provides train/test indices to split time series data samples based on
     Combinatorial Purged Cross-Validation [1]_.
 
-    Compared to `KFold` which split the data into `k` folds with `1` fold for the test
+    Compared to `KFold`, which splits the data into `k` folds with `1` fold for the test
     set and `k - 1` folds for the training set, `CombinatorialPurgedCV` uses `k - p`
     folds for the training set with `p > 1` being the number of test folds.
 
@@ -57,7 +57,7 @@ class CombinatorialPurgedCV(BaseCombinatorialCV):
     overlapped in time with those labels included in the testing set.
 
     Embargoing consist of removing from the training set all observations that
-    immediately follow an observation in the testing set since financial features
+    immediately follow an observation in the testing set, since financial features
     often incorporate series that exhibit serial correlation (like ARMA processes).
 
     Parameters

{skfolio-0.0.7 → skfolio-0.0.9}/src/skfolio/optimization/_base.py

@@ -16,7 +16,7 @@ from skfolio.portfolio import Portfolio
 
 
 class BaseOptimization(skb.BaseEstimator, ABC):
-    """Base class for all optimization estimators in skfolio.
+    """Base class for all portfolio optimizations in skfolio.
 
     portfolio_params :  dict, optional
         Portfolio parameters passed to the portfolio evaluated by the `predict` and

{skfolio-0.0.7 → skfolio-0.0.9}/src/skfolio/optimization/cluster/_nco.py

@@ -40,12 +40,12 @@ class NestedClustersOptimization(BaseOptimization):
     .. note ::
 
         The original paper uses KMeans as the clustering algorithm, minimum Variance for
-        the inner-estimator and equal-weight for the outer-estimator. Here we generalize
-        it to all `sklearn` and `skfolio` clustering algorithm (HierarchicalClustering,
-        KMeans, ...), all optimization estimators (Mean-Variance, HRP, ...)
-        and risk measures (Variance, CVaR,...).
+        the inner-estimator and equal-weighted for the outer-estimator. Here we
+        generalize it to all `sklearn` and `skfolio` clustering algorithms
+        (HierarchicalClustering, KMeans, etc.), all portfolio optimizations
+        (Mean-Variance, HRP, etc.) and risk measures (Variance, CVaR, etc.).
         To avoid data leakage at the outer-estimator, we use out-of-sample estimates to
-        fit the outer optimization.
+        fit the outer estimator.
 
     Parameters
     ----------

{skfolio-0.0.7 → skfolio-0.0.9}/src/skfolio/optimization/cluster/hierarchical/_base.py

@@ -93,7 +93,7 @@ class BaseHierarchicalOptimization(BaseOptimization, ABC):
         allowed. If a float is provided, it is applied to each asset. `None` is
         equivalent to `+np.Inf` (no upper bound). If a dictionary is provided, its
         (key/value) pair must be the (asset name/asset maximum weight) and the input `X`
-        of the `fit` methods must be a DataFrame with the assets names in columns. When
+        of the `fit` method must be a DataFrame with the assets names in columns. When
         using a dictionary, assets values that are not provided are assigned a minimum
         weight of `1.0`. The default is 1.0 (each asset is below 100%).
 
@@ -112,7 +112,7 @@ class BaseHierarchicalOptimization(BaseOptimization, ABC):
 
         with :math:`c_{i}` the transaction cost of asset i, :math:`w_{i}` its weight
         and :math:`w\_prev_{i}` its previous weight (defined in `previous_weights`).
-        The float :math:`total\_cost` is used in the portfolio expected return:
+        The float :math:`total\_cost` is impacting the portfolio expected return in the optimization:
 
         .. math:: expected\_return = \mu^{T} \cdot w - total\_cost
 
@@ -121,7 +121,7 @@ class BaseHierarchicalOptimization(BaseOptimization, ABC):
 
         If a float is provided, it is applied to each asset.
         If a dictionary is provided, its (key/value) pair must be the
-        (asset name/asset cost) and the input `X` of the `fit` methods must be a
+        (asset name/asset cost) and the input `X` of the `fit` method must be a
         DataFrame with the assets names in columns.
         The default value is `0.0`.
 
@@ -130,7 +130,7 @@ class BaseHierarchicalOptimization(BaseOptimization, ABC):
             Based on the above formula, the periodicity of the transaction costs
             needs to be homogenous to the periodicity of :math:`\mu`. For example, if
             the input `X` is composed of **daily** returns, the `transaction_costs` need
-            to be expressed in **daily** costs.
+            to be expressed as **daily** costs.
             (See :ref:`sphx_glr_auto_examples_1_mean_risk_plot_6_transaction_costs.py`)
 
     management_fees : float | dict[str, float] | array-like of shape (n_assets, ), default=0.0
@@ -140,7 +140,7 @@ class BaseHierarchicalOptimization(BaseOptimization, ABC):
         .. math:: total\_fee = \sum_{i=1}^{N} f_{i} \times w_{i}
 
         with :math:`f_{i}` the management fee of asset i and :math:`w_{i}` its weight.
-        The float :math:`total\_fee` is used in the portfolio expected return:
+        The float :math:`total\_fee` is impacting the portfolio expected return in the optimization:
 
         .. math:: expected\_return = \mu^{T} \cdot w - total\_fee
 
@@ -149,7 +149,7 @@ class BaseHierarchicalOptimization(BaseOptimization, ABC):
 
         If a float is provided, it is applied to each asset.
         If a dictionary is provided, its (key/value) pair must be the
-        (asset name/asset fee) and the input `X` of the `fit` methods must be a
+        (asset name/asset fee) and the input `X` of the `fit` method must be a
         DataFrame with the assets names in columns.
         The default value is `0.0`.
 
@@ -172,7 +172,7 @@ class BaseHierarchicalOptimization(BaseOptimization, ABC):
         Previous weights of the assets. Previous weights are used to compute the
         portfolio total cost. If a float is provided, it is applied to each asset.
         If a dictionary is provided, its (key/value) pair must be the
-        (asset name/asset previous weight) and the input `X` of the `fit` methods must
+        (asset name/asset previous weight) and the input `X` of the `fit` method must
         be a DataFrame with the assets names in columns.
         The default (`None`) means no previous weights.