<a id="skfolio-portfolio-multiperiodportfolio"></a>

# skfolio.portfolio.MultiPeriodPortfolio

<a id="skfolio.portfolio.MultiPeriodPortfolio"></a>

### *class* skfolio.portfolio.MultiPeriodPortfolio(portfolios=None, name=None, tag=None, risk_free_rate=0, annualization_factor=None, fitness_measures=None, compounded=False, sample_weight=None, min_acceptable_return=None, value_at_risk_beta=0.95, entropic_risk_measure_theta=1, entropic_risk_measure_beta=0.95, cvar_beta=0.95, evar_beta=0.95, drawdown_at_risk_beta=0.95, cdar_beta=0.95, edar_beta=0.95, check_observations_order=False, \*\*kwargs)

Multi-Period Portfolio class.

A Multi-Period Portfolio is composed of a list of [`Portfolio`](https://skfolio.org/generated/skfolio.portfolio.Portfolio.html.md#skfolio.portfolio.Portfolio).

* **Parameters:**
  **portfolios** *list[Portfolio], optional*
  : A list of [`Portfolio`](https://skfolio.org/generated/skfolio.portfolio.Portfolio.html.md#skfolio.portfolio.Portfolio). The default (`None`) is to initialize with an
    empty list.

  **name** *str, optional*
  : Name of the multi-period portfolio.
    The default (`None`) is to use the object id.

  **tag** *str, optional*
  : Tag given to the multi-period portfolio.
    Tags are used to manipulate groups of portfolios from a `Population`.

  **fitness_measures** *list[measures], optional*
  : List of fitness measures.
    Fitness measures are used to compute the portfolio fitness which is used to
    compute domination.
    The default (`None`) is to use the list [PerfMeasure.MEAN, RiskMeasure.VARIANCE]

  **annualization_factor** *float, default=252.0*
  : Factor used to annualize the below measures using the square-root rule:
    > * Annualized Mean = Mean \* factor
    > * Annualized Variance = Variance \* factor
    > * Annualized Semi-Variance = Semi-Variance \* factor
    > * Annualized Standard-Deviation = Standard-Deviation \* sqrt(factor)
    > * Annualized Semi-Deviation = Semi-Deviation \* sqrt(factor)
    > * Annualized Sharpe Ratio = Sharpe Ratio \* sqrt(factor)
    > * Annualized Sortino Ratio = Sortino Ratio \* sqrt(factor)

  **risk_free_rate** *float, default=0.0*
  : Risk-free rate. The default value is `0.0`.

  **compounded** *bool, default=False*
  : If this is set to True, cumulative returns are compounded.
    The default is `False`.

  **sample_weight** *ndarray of shape (n_observations,), optional*
  : Sample weights for each observation. If None, equal weights are assumed.

  **min_acceptable_return** *float, optional*
  : The minimum acceptable return used to distinguish “downside” and “upside”
    returns for the computation of lower partial moments:
    > * First Lower Partial Moment
    > * Semi-Variance
    > * Semi-Deviation
    <br/>
    The default (`None`) is to use the mean.

  **value_at_risk_beta** *float, default=0.95*
  : The confidence level of the portfolio VaR (Value At Risk) which represents
    the return on the worst (1-beta)% observations.
    The default value is `0.95`.

  **entropic_risk_measure_theta** *float, default=1.0*
  : The risk aversion level of the portfolio Entropic Risk Measure.
    The default value is `1.0`.

  **entropic_risk_measure_beta** *float, default=0.95*
  : The confidence level of the portfolio Entropic Risk Measure.
    The default value is `0.95`.

  **cvar_beta** *float, default=0.95*
  : The confidence level of the portfolio CVaR (Conditional Value at Risk) which
    represents the expected VaR on the worst (1-beta)% observations.
    The default value is `0.95`.

  **evar_beta** *float, default=0.95*
  : The confidence level of the portfolio EVaR (Entropic Value at Risk).
    The default value is `0.95`.

  **drawdown_at_risk_beta** *float, default=0.95*
  : The confidence level of the portfolio Drawdown at Risk (DaR) which represents
    the drawdown on the worst (1-beta)% observations.
    The default value is `0.95`.

  **cdar_beta** *float, default=0.95*
  : The confidence level of the portfolio CDaR (Conditional Drawdown at Risk) which
    represents the expected drawdown on the worst (1-beta)% observations.
    The default value is `0.95`.

  **edar_beta** *float, default=0.95*
  : The confidence level of the portfolio EDaR (Entropic Drawdown at Risk).
    The default value is `0.95`.

  **check_observations_order** *bool, default=False*
  : If this is set to True, and if the list of portfolios is not chronologically
    sorted, an error is raised. The chronological order is determined by comparing
    the first and last observations of each portfolio.
    The default is `False`.
* **Attributes:**
  [`n_observations`](#skfolio.portfolio.MultiPeriodPortfolio.n_observations) *float*
  : Number of observations.

  **mean** *float*
  : Mean of the portfolio returns.

  **annualized_mean** *float*
  : Mean annualized by $mean \times annualization\_factor$

  **mean_absolute_deviation** *float*
  : Mean Absolute Deviation. The deviation is the difference between the
    return and a minimum acceptable return (`min_acceptable_return`).

  **first_lower_partial_moment** *float*
  : First Lower Partial Moment. The First Lower Partial Moment is the mean of the
    returns below a minimum acceptable return (`min_acceptable_return`).

  **variance** *float*
  : Variance (Second Moment)

  **annualized_variance** *float*
  : Variance annualized by $variance \times annualization\_factor$

  **semi_variance** *float*
  : Semi-variance (Second Lower Partial Moment).
    The semi-variance is the variance of the returns below a minimum acceptable
    return (`min_acceptable_return`).

  **annualized_semi_variance** *float*
  : Semi-variance annualized by
    $semi\_variance \times annualization\_factor$

  **standard_deviation** *float*
  : Standard Deviation (Square Root of the Second Moment).

  **annualized_standard_deviation** *float*
  : Standard Deviation annualized by
    $standard\_deviation \times \sqrt{annualization\_factor}$

  **semi_deviation** *float*
  : Semi-deviation (Square Root of the Second Lower Partial Moment).
    The Semi Standard Deviation is the Standard Deviation of the returns below a
    minimum acceptable return (`min_acceptable_return`).

  **annualized_semi_deviation** *float*
  : Semi-deviation annualized by
    $semi\_deviation \times \sqrt{annualization\_factor}$

  **skew** *float*
  : Skew. The Skew is a measure of the lopsidedness of the distribution.
    A symmetric distribution have a Skew of zero.
    Higher Skew corresponds to longer right tail.

  **kurtosis** *float*
  : Kurtosis. It is a measure of the heaviness of the tail of the distribution.
    Higher Kurtosis corresponds to greater extremity of deviations (fat tails).

  **fourth_central_moment** *float*
  : Fourth Central Moment.

  **fourth_lower_partial_moment** *float*
  : Fourth Lower Partial Moment. It is a measure of the heaviness of the downside
    tail of the returns below a minimum acceptable return (`min_acceptable_return`).
    Higher Fourth Lower Partial Moment corresponds to greater extremity of downside
    deviations (downside fat tail).

  **worst_realization** *float*
  : Worst Realization which is the worst return.

  **value_at_risk** *float*
  : Historical VaR (Value at Risk).
    The VaR is the maximum loss at a given confidence level (`value_at_risk_beta`).

  **cvar** *float*
  : Historical CVaR (Conditional Value at Risk). The CVaR (or Tail VaR) represents
    the mean shortfall at a specified confidence level (`cvar_beta`).

  **entropic_risk_measure** *float*
  : Historical Entropic Risk Measure. It is a risk measure which depends on the
    risk aversion defined by the investor (`entropic_risk_measure_theta`) through
    the exponential utility function at a given confidence level
    (`entropic_risk_measure_beta`).

  **evar** *float*
  : Historical EVaR (Entropic Value at Risk). It is a coherent risk measure which
    is an upper bound for the VaR and the CVaR, obtained from the Chernoff
    inequality at a given confidence level (`evar_beta`). The EVaR can be
    represented by using the concept of relative entropy.

  **drawdown_at_risk** *float*
  : Historical Drawdown at Risk. It is the maximum drawdown at a given
    confidence level (`drawdown_at_risk_beta`).

  **cdar** *float*
  : Historical CDaR (Conditional Drawdown at Risk) at a given confidence level
    (`cdar_beta`).

  **max_drawdown** *float*
  : Maximum Drawdown.

  **average_drawdown** *float*
  : Average Drawdown.

  **edar** *float*
  : EDaR (Entropic Drawdown at Risk). It is a coherent risk measure which is an
    upper bound for the Drawdown at Risk and the CDaR, obtained from the Chernoff
    inequality at a given confidence level (`edar_beta`). The EDaR can be
    represented by using the concept of relative entropy.

  **ulcer_index** *float*
  : Ulcer Index

  **gini_mean_difference** *float*
  : Gini Mean Difference (GMD). It is the expected absolute difference between two
    realizations. The GMD is a superior measure of variability  for non-normal
    distribution than the variance. It can be used to form necessary conditions
    for second-degree stochastic dominance, while the variance cannot.

  **mean_absolute_deviation_ratio** *float*
  : Mean Absolute Deviation ratio.
    It is the excess mean (mean - risk_free_rate) divided by the MaD.

  **first_lower_partial_moment_ratio** *float*
  : First Lower Partial Moment ratio.
    It is the excess mean (mean - risk_free_rate) divided by the First Lower
    Partial Moment.

  **sharpe_ratio** *float*
  : Sharpe ratio.
    It is the excess mean (mean - risk_free_rate) divided by the standard-deviation.

  **annualized_sharpe_ratio** *float*
  : Sharpe ratio annualized by
    $sharpe\_ratio \times \sqrt{annualization\_factor}$.

  **sortino_ratio** *float*
  : Sortino ratio.
    It is the excess mean (mean - risk_free_rate) divided by the semi
    standard-deviation.

  **annualized_sortino_ratio** *float*
  : Sortino ratio annualized by
    $sortino\_ratio \times \sqrt{annualization\_factor}$.

  **value_at_risk_ratio** *float*
  : VaR ratio.
    It is the excess mean (mean - risk_free_rate) divided by the Value at Risk
    (VaR).

  **cvar_ratio** *float*
  : CVaR ratio.
    It is the excess mean (mean - risk_free_rate) divided by the Conditional Value
    at Risk (CVaR).

  **entropic_risk_measure_ratio** *float*
  : Entropic risk measure ratio.
    It is the excess mean (mean - risk_free_rate) divided by the Entropic risk
    measure.

  **evar_ratio** *float*
  : EVaR ratio.
    It is the excess mean (mean - risk_free_rate) divided by the EVaR (Entropic
    Value at Risk).

  **worst_realization_ratio** *float*
  : Worst Realization ratio.
    It is the excess mean (mean - risk_free_rate) divided by the Worst Realization
    (worst return).

  **drawdown_at_risk_ratio** *float*
  : Drawdown at Risk ratio.
    It is the excess mean (mean - risk_free_rate) divided by the drawdown at
    risk.

  **cdar_ratio** *float*
  : CDaR ratio.
    It is the excess mean (mean - risk_free_rate) divided by the CDaR (conditional
    drawdown at risk).

  **calmar_ratio** *float*
  : Calmar ratio.
    It is the excess mean (mean - risk_free_rate) divided by the Maximum Drawdown.

  **average_drawdown_ratio** *float*
  : Average Drawdown ratio.
    It is the excess mean (mean - risk_free_rate) divided by the Average Drawdown.

  **edar_ratio** *float*
  : EDaR ratio.
    It is the excess mean (mean - risk_free_rate) divided by the EDaR (Entropic
    Drawdown at Risk).

  **ulcer_index_ratio** *float*
  : Ulcer Index ratio.
    It is the excess mean (mean - risk_free_rate) divided by the Ulcer Index.

  **gini_mean_difference_ratio** *float*
  : Gini Mean Difference ratio.
    It is the excess mean (mean - risk_free_rate) divided by the Gini Mean
    Difference.

### Methods

| [`append`](#skfolio.portfolio.MultiPeriodPortfolio.append)(portfolio)                                 | Append a Portfolio to the Portfolio list.                                     |
|----------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------|
| [`clear`](#skfolio.portfolio.MultiPeriodPortfolio.clear)()                                           | Clear all measures, fitness, cumulative returns and drawdowns in slots.       |
| [`contribution`](#skfolio.portfolio.MultiPeriodPortfolio.contribution)(measure[, spacing, to_df])           | Compute the contribution of each asset to a given measure for each portfolio. |
| [`copy`](#skfolio.portfolio.MultiPeriodPortfolio.copy)()                                            | Copy the Portfolio attributes without its measures values.                    |
| [`dominates`](#skfolio.portfolio.MultiPeriodPortfolio.dominates)(other[, idx])                           | Portfolio domination.                                                         |
| [`get_measure`](#skfolio.portfolio.MultiPeriodPortfolio.get_measure)(measure)                              | Returns the value of a given measure.                                         |
| [`plot_composition`](#skfolio.portfolio.MultiPeriodPortfolio.plot_composition)()                                | Plot the Portfolio composition.                                               |
| [`plot_contribution`](#skfolio.portfolio.MultiPeriodPortfolio.plot_contribution)(measure[, spacing])             | Plot the contribution of each asset to a given measure.                       |
| [`plot_cumulative_returns`](#skfolio.portfolio.MultiPeriodPortfolio.plot_cumulative_returns)([log_scale, idx])         | Plot the Portfolio cumulative returns.                                        |
| [`plot_drawdowns`](#skfolio.portfolio.MultiPeriodPortfolio.plot_drawdowns)([idx])                             | Plot the Portfolio drawdowns.                                                 |
| [`plot_long_short_exposure`](#skfolio.portfolio.MultiPeriodPortfolio.plot_long_short_exposure)()                        | Plot long, short, net and gross exposure per observation.                     |
| [`plot_returns`](#skfolio.portfolio.MultiPeriodPortfolio.plot_returns)([idx])                               | Plot the Portfolio returns.                                                   |
| [`plot_returns_distribution`](#skfolio.portfolio.MultiPeriodPortfolio.plot_returns_distribution)([percentile_cutoff])    | Plot the Portfolio returns distribution using Gaussian KDE.                   |
| [`plot_rolling_measure`](#skfolio.portfolio.MultiPeriodPortfolio.plot_rolling_measure)([measure, window])           | Plot the measure over a rolling window.                                       |
| [`plot_weights_per_observation`](#skfolio.portfolio.MultiPeriodPortfolio.plot_weights_per_observation)()                    | Plot portfolio weights per observation as a stacked-area chart.               |
| [`predicted_attribution`](#skfolio.portfolio.MultiPeriodPortfolio.predicted_attribution)(factor_model[, ...])        | Ex-ante (predicted) factor attribution for the last portfolio.                |
| [`realized_attribution`](#skfolio.portfolio.MultiPeriodPortfolio.realized_attribution)(factor_model[, ...])         | Realized (ex-post) factor attribution aggregated over all periods.            |
| [`rolling_measure`](#skfolio.portfolio.MultiPeriodPortfolio.rolling_measure)([measure, window])                | Compute the measure over a rolling window.                                    |
| [`rolling_realized_attribution`](#skfolio.portfolio.MultiPeriodPortfolio.rolling_realized_attribution)(factor_model[, ...]) | Rolling realized (ex-post) factor attribution over all periods.               |
| [`summary`](#skfolio.portfolio.MultiPeriodPortfolio.summary)([formatted])                              | Portfolio summary of all its measures.                                        |

<a id="skfolio.portfolio.MultiPeriodPortfolio.annualization_factor"></a>

#### *property* annualization_factor

Portfolio annualization factor.

<a id="skfolio.portfolio.MultiPeriodPortfolio.annualized_factor"></a>

#### *property* annualized_factor

Deprecated alias for `annualization_factor`.

<a id="skfolio.portfolio.MultiPeriodPortfolio.append"></a>

#### append(portfolio)

Append a Portfolio to the Portfolio list.

* **Parameters:**
  **portfolio** *Portfolio*
  : The Portfolio to append.

<a id="skfolio.portfolio.MultiPeriodPortfolio.assets"></a>

#### *property* assets

List of assets names in each Portfolio.

<a id="skfolio.portfolio.MultiPeriodPortfolio.clear"></a>

#### clear()

Clear all measures, fitness, cumulative returns and drawdowns in slots.

<a id="skfolio.portfolio.MultiPeriodPortfolio.composition"></a>

#### *property* composition

DataFrame of the Portfolio composition.

<a id="skfolio.portfolio.MultiPeriodPortfolio.contribution"></a>

#### contribution(measure, spacing=None, to_df=True)

Compute the contribution of each asset to a given measure for each
portfolio.

* **Parameters:**
  **measure** *Measure*
  : The measure used for the contribution computation.

  **spacing** *float, optional*
  : Spacing “h” of the finite difference:
    $contribution(wi)= \frac{measure(wi-h) - measure(wi+h)}{2h}$

  **to_df** *bool, default=False*
  : If this is set to True, a DataFrame with asset names in index and portfolio
    names in columns is returned, otherwise a list of numpy array is returned.
    When a DataFrame is returned, the assets with zero weights are removed.
* **Returns:**
  **values** *list of numpy array of shape (n_assets,) for each portfolio or a DataFrame*
  : The measure contribution of each asset for each portfolio.

<a id="skfolio.portfolio.MultiPeriodPortfolio.copy"></a>

#### copy()

Copy the Portfolio attributes without its measures values.

<a id="skfolio.portfolio.MultiPeriodPortfolio.cumulative_returns"></a>

#### cumulative_returns

Portfolio cumulative returns array.
Non-compounded (arithmetic) cumulative returns start at 0.
Compounded (geometric) cumulative returns are expressed as a wealth index,
starting at 1.0 (i.e., the value of $1 invested).

<a id="skfolio.portfolio.MultiPeriodPortfolio.cumulative_returns_df"></a>

#### *property* cumulative_returns_df

Portfolio cumulative returns Series.
Non-compounded (arithmetic) cumulative returns start at 0.
Compounded (geometric) cumulative returns are expressed as a wealth index,
starting at 1.0 (i.e., the value of $1 invested).

<a id="skfolio.portfolio.MultiPeriodPortfolio.dominates"></a>

#### dominates(other, idx=None)

Portfolio domination.

Returns true if each objective of the current portfolio fitness is not
strictly worse than the corresponding objective of the other portfolio fitness
and at least one objective is strictly better.

* **Parameters:**
  **other** *BasePortfolio*
  : The other portfolio.

  **idx** *slice | array, optional*
  : Indexes or slice indicating on which objectives the domination is performed.
    The default (`None`) is to use all objectives.
* **Returns:**
  **value** *bool*
  : Returns True if the Portfolio dominates the other one.

<a id="skfolio.portfolio.MultiPeriodPortfolio.drawdowns"></a>

#### drawdowns

Portfolio drawdowns array.

<a id="skfolio.portfolio.MultiPeriodPortfolio.drawdowns_df"></a>

#### *property* drawdowns_df

Portfolio drawdowns Series.

<a id="skfolio.portfolio.MultiPeriodPortfolio.ending_weights_dict"></a>

#### *property* ending_weights_dict

Map each Portfolio name to its weights at the end of its observation window.

For each Portfolio, the nested dictionary contains its `ending_weights_dict`,
as determined by that Portfolio’s `weight_drift` setting. Failed portfolios map
every asset to NaN. In a sequential evaluation, the next optimization uses the
last successful ending weights as `previous_weights`.

<a id="skfolio.portfolio.MultiPeriodPortfolio.failed_portfolios"></a>

#### *property* failed_portfolios

Return the list of `FailedPortfolio` in the multi-period portfolio.

<a id="skfolio.portfolio.MultiPeriodPortfolio.fallback_portfolios"></a>

#### *property* fallback_portfolios

Return the list of portfolios in the multi-period portfolio that used a
fallback (i.e., have a non-None `fallback_chain`). This includes
`FailedPortfolio` instances when fallbacks were attempted.

<a id="skfolio.portfolio.MultiPeriodPortfolio.fitness"></a>

#### fitness

Portfolio fitness.

<a id="skfolio.portfolio.MultiPeriodPortfolio.fitness_measures"></a>

#### *property* fitness_measures

Portfolio fitness measures.

<a id="skfolio.portfolio.MultiPeriodPortfolio.get_measure"></a>

#### get_measure(measure)

Returns the value of a given measure.

* **Parameters:**
  **measure** *PerfMeasure | RiskMeasure | ExtraRiskMeasure | RatioMeasure*
  : The input measure.
* **Returns:**
  **value** *float*
  : The measure value.

<a id="skfolio.portfolio.MultiPeriodPortfolio.long_short_exposure"></a>

#### *property* long_short_exposure

DataFrame of long, short, net and gross exposure per observation.

The long exposure is the sum of positive weights. The short exposure is the
sum of negative weights. Net exposure is the sum of all weights and gross
exposure is the sum of absolute weights.

<a id="skfolio.portfolio.MultiPeriodPortfolio.measures_df"></a>

#### *property* measures_df

DataFrame of all measures.

<a id="skfolio.portfolio.MultiPeriodPortfolio.n_failed_portfolios"></a>

#### *property* n_failed_portfolios

Number of `FailedPortfolio` in the multi-period portfolio.

<a id="skfolio.portfolio.MultiPeriodPortfolio.n_fallback_portfolios"></a>

#### *property* n_fallback_portfolios

Number of portfolios in the multi-period portfolio with a fallback.

<a id="skfolio.portfolio.MultiPeriodPortfolio.n_observations"></a>

#### *property* n_observations

Number of observations.

<a id="skfolio.portfolio.MultiPeriodPortfolio.plot_composition"></a>

#### plot_composition()

Plot the Portfolio composition.

* **Returns:**
  **plot** *Figure*
  : Returns the plot Figure object.

<a id="skfolio.portfolio.MultiPeriodPortfolio.plot_contribution"></a>

#### plot_contribution(measure, spacing=None)

Plot the contribution of each asset to a given measure.

* **Parameters:**
  **measure** *Measure*
  : The measure used for the contribution computation.

  **spacing** *float, optional*
  : Spacing “h” of the finite difference:
    $contribution(wi)= \frac{measure(wi-h) - measure(wi+h)}{2h}$
* **Returns:**
  **plot** *Figure*
  : The plotly Figure of assets contribution to the measure.

<a id="skfolio.portfolio.MultiPeriodPortfolio.plot_cumulative_returns"></a>

#### plot_cumulative_returns(log_scale=False, idx=None)

Plot the Portfolio cumulative returns.
Non-compounded (arithmetic) cumulative returns start at 0.
Compounded (geometric) cumulative returns are expressed as a wealth index,
starting at 1.0 (i.e., the value of $1 invested).

* **Parameters:**
  **log_scale** *bool, default=False*
  : If this is set to True, the cumulative returns are displayed with a
    logarithm scale on the y-axis. The cumulative returns must be compounded
    otherwise an exception is raised.

  **idx** *slice | array, optional*
  : Indexes or slice of the observations to plot.
    The default (`None`) is to plot all observations.
* **Returns:**
  **plot** *Figure*
  : Returns the plot Figure object.

<a id="skfolio.portfolio.MultiPeriodPortfolio.plot_drawdowns"></a>

#### plot_drawdowns(idx=None)

Plot the Portfolio drawdowns.

* **Parameters:**
  **idx** *slice | array, optional*
  : Indexes or slice of the observations to plot.
    The default (`None`) is to plot all observations.
* **Returns:**
  **plot** *Figure*
  : Returns the plot Figure object.

<a id="skfolio.portfolio.MultiPeriodPortfolio.plot_long_short_exposure"></a>

#### plot_long_short_exposure()

Plot long, short, net and gross exposure per observation.

* **Returns:**
  **plot** *Figure*
  : Returns the plot Figure object.

<a id="skfolio.portfolio.MultiPeriodPortfolio.plot_returns"></a>

#### plot_returns(idx=None)

Plot the Portfolio returns.

* **Parameters:**
  **idx** *slice | array, optional*
  : Indexes or slice of the observations to plot.
    The default (`None`) is to plot all observations.
* **Returns:**
  **plot** *Figure*
  : Returns the plot Figure object

<a id="skfolio.portfolio.MultiPeriodPortfolio.plot_returns_distribution"></a>

#### plot_returns_distribution(percentile_cutoff=None)

Plot the Portfolio returns distribution using Gaussian KDE.

* **Parameters:**
  **percentile_cutoff** *float, default=None*
  : Percentile cutoff for tail truncation (percentile), in percent.
    If a float p is provided, the distribution support is truncated at the p-th
    and (100 - p)-th percentiles.
    If None, no truncation is applied (uses full min/max of returns).
* **Returns:**
  **plot** *Figure*
  : Returns the plot Figure object

<a id="skfolio.portfolio.MultiPeriodPortfolio.plot_rolling_measure"></a>

#### plot_rolling_measure(measure=Sharpe Ratio, window=30)

Plot the measure over a rolling window.

* **Parameters:**
  **measure** *Measure, default = RatioMeasure.SHARPE_RATIO*
  : The measure.

  **window** *int, default=30*
  : The window size.
* **Returns:**
  **plot** *Figure*
  : Returns the plot Figure object

<a id="skfolio.portfolio.MultiPeriodPortfolio.plot_weights_per_observation"></a>

#### plot_weights_per_observation()

Plot portfolio weights per observation as a stacked-area chart.

This shows the composition of the portfolio over time, with each asset’s weight
stacked to illustrate how allocations shift.

* **Returns:**
  **plot** *Figure*
  : Returns the plot Figure object.

<a id="skfolio.portfolio.MultiPeriodPortfolio.portfolios"></a>

#### *property* portfolios

List of portfolios composing the mutli-period portfolio.

<a id="skfolio.portfolio.MultiPeriodPortfolio.predicted_attribution"></a>

#### predicted_attribution(factor_model, compute_asset_breakdowns=True)

Ex-ante (predicted) factor attribution for the last portfolio.

Returns the predicted attribution for the most recent (last) portfolio in the
walk-forward sequence, which represents the current allocation.

The last portfolio’s weights are aligned to `factor_model.asset_names`: assets
not in the portfolio receive zero weight, and assets not in the factor model
raise an error.

Predicted attribution uses the factor model’s latest forecast estimates
(`loading_matrix`, `factor_covariance`, `idio_covariance`, `factor_mu`,
`idio_mu`), so no observation alignment is performed.

The annualization scaling uses `self.annualization_factor`.

See [`predicted_factor_attribution`](https://skfolio.org/generated/skfolio.attribution.predicted_factor_attribution.html.md#skfolio.attribution.predicted_factor_attribution)
for the full mathematical description.

* **Parameters:**
  **factor_model** *FactorModel*
  : Factor model whose latest forecast estimates are used. Every asset
    held by the last portfolio must appear in `factor_model.asset_names`.

  **compute_asset_breakdowns** *bool, default=True*
  : If `True`, compute per-asset systematic/idiosyncratic decomposition. Set to
    `False` for faster computation when only portfolio-level results are needed.
* **Returns:**
  **attribution** *Attribution*
  : Component-level, factor-level, and optionally asset-level attribution
    results for the last portfolio.
* **Raises:**
  ValueError
  : If the multi-period portfolio is empty, the last portfolio is a
    [`FailedPortfolio`](https://skfolio.org/generated/skfolio.portfolio.FailedPortfolio.html.md#skfolio.portfolio.FailedPortfolio), or it holds assets not covered by the factor model.

<a id="skfolio.portfolio.MultiPeriodPortfolio.previous_weights_dict"></a>

#### *property* previous_weights_dict

Dictionary mapping Portfolio name to its previous asset weight allocation.

<a id="skfolio.portfolio.MultiPeriodPortfolio.realized_attribution"></a>

#### realized_attribution(factor_model, compute_asset_breakdowns=True, compute_uncertainty=True)

Realized (ex-post) factor attribution aggregated over all periods.

Builds a time-varying weight matrix from the non-failed child portfolios and
computes a single realized attribution over the full walk-forward observation
window.

Each child portfolio’s static weight vector is broadcast across its
observations. Failed portfolios are skipped (their observations and returns are
excluded).

Weights are aligned to `factor_model.asset_names`: assets not in a given
portfolio receive zero weight, and assets not in the factor model raise an
error.

Realized attribution is computed on the overlapping observation window between
the multi-period portfolio and the factor model. Portfolio observations outside
the factor model window, commonly caused by factor-model warmup or exposure lag,
are excluded. Missing portfolio observations inside the overlapping window raise
`ValueError`. Time-varying exposures follow the as-of indexing convention
described in
[`realized_factor_attribution`](https://skfolio.org/generated/skfolio.attribution.realized_factor_attribution.html.md#skfolio.attribution.realized_factor_attribution):
when `exposure_lag > 0`, exposures known at observation $t-\ell$ are
aligned with returns at observation $t$.

The annualization scaling uses `self.annualization_factor`.

See [`realized_factor_attribution`](https://skfolio.org/generated/skfolio.attribution.realized_factor_attribution.html.md#skfolio.attribution.realized_factor_attribution) for
the full mathematical description.

* **Parameters:**
  **factor_model** *FactorModel*
  : Factor model containing time-varying fields (`factor_returns`, `exposures`,
    `idio_returns`) that overlap with the observation periods of non-failed
    child portfolios. Every asset held by any child portfolio must appear in
    `factor_model.asset_names`.

  **compute_asset_breakdowns** *bool, default=True*
  : If `True`, compute per-asset systematic/idiosyncratic attribution. Set to
    `False` for faster computation when only portfolio-level results are needed.

  **compute_uncertainty** *bool, default=True*
  : If `True`, compute attribution uncertainty (standard errors on the factor
    and idiosyncratic mean-return split).
* **Returns:**
  **attribution** *Attribution*
  : Component-level, factor-level, and optionally asset-level attribution
    results aggregated over all non-failed periods.
* **Raises:**
  ValueError
  : If the multi-period portfolio is empty, all child portfolios are failed, any
    child portfolio holds assets not covered by the factor model, no portfolio
    observations overlap with the factor model, or portfolio observations are
    missing inside the overlapping window.

<a id="skfolio.portfolio.MultiPeriodPortfolio.returns_df"></a>

#### *property* returns_df

Portfolio returns DataFrame.

<a id="skfolio.portfolio.MultiPeriodPortfolio.rolling_measure"></a>

#### rolling_measure(measure=Sharpe Ratio, window=30)

Compute the measure over a rolling window.

* **Parameters:**
  **measure** *Measure, default=RatioMeasure.SHARPE_RATIO*
  : The measure. The default measure is the Sharpe Ratio.

  **window** *int, default=30*
  : The window size. The default value is `30` observations.
* **Returns:**
  **series** *pandas Series*
  : The rolling measure Series.

<a id="skfolio.portfolio.MultiPeriodPortfolio.rolling_realized_attribution"></a>

#### rolling_realized_attribution(factor_model, window_size=60, step=21, compute_asset_breakdowns=True, compute_asset_factor_contribs=False, compute_uncertainty=True)

Rolling realized (ex-post) factor attribution over all periods.

Builds a time-varying weight matrix from the non-failed child portfolios and
computes rolling realized attribution over the full walk-forward observation
window.

Each child portfolio’s static weight vector is broadcast across its
observations. Failed portfolios are skipped.

Rolling realized attribution is computed on the overlapping observation window
between the multi-period portfolio and the factor model. Portfolio observations
outside the factor model window, commonly caused by factor-model warmup or
exposure lag, are excluded. Missing portfolio observations inside the
overlapping window raise `ValueError`. Time-varying exposures follow the as-of
indexing convention described in
[`rolling_realized_factor_attribution`](https://skfolio.org/generated/skfolio.attribution.rolling_realized_factor_attribution.html.md#skfolio.attribution.rolling_realized_factor_attribution).

See [`rolling_realized_factor_attribution`](https://skfolio.org/generated/skfolio.attribution.rolling_realized_factor_attribution.html.md#skfolio.attribution.rolling_realized_factor_attribution)
for the full mathematical description.

* **Parameters:**
  **factor_model** *FactorModel*
  : Factor model containing time-varying fields that overlap with the
    observation periods of non-failed child portfolios.

  **window_size** *int, default=60*
  : Number of effective return periods in each rolling window.

  **step** *int, default=21*
  : Number of observations to advance between consecutive windows. The default
    of 21 produces approximately monthly output for daily data.

  **compute_asset_breakdowns** *bool, default=True*
  : If `True`, compute per-asset attribution for each window.

  **compute_asset_factor_contribs** *bool, default=False*
  : If `True`, compute asset-factor matrix for each window.

  **compute_uncertainty** *bool, default=True*
  : If `True`, compute per-window attribution uncertainty.
* **Returns:**
  **attribution** *Attribution*
  : Rolling attribution results with an additional leading dimension for the
    number of windows.
* **Raises:**
  ValueError
  : If the multi-period portfolio is empty, all child portfolios are failed, any
    child portfolio holds assets not covered by the factor model, no portfolio
    observations overlap with the factor model, or `window_size` exceeds the
    number of overlapping observations.

<a id="skfolio.portfolio.MultiPeriodPortfolio.sample_weight"></a>

#### *property* sample_weight

Observations sample weights.

<a id="skfolio.portfolio.MultiPeriodPortfolio.summary"></a>

#### summary(formatted=True)

Portfolio summary of all its measures.

* **Parameters:**
  **formatted** *bool, default=True*
  : If this is set to True, the measures are formatted into rounded string with
    units.
* **Returns:**
  **summary** *series*
  : Portfolio summary of all its measures.

<a id="skfolio.portfolio.MultiPeriodPortfolio.turnover"></a>

#### *property* turnover

Turnover of each Portfolio, indexed by its first observation.

In a sequentially evaluated path, `previous_weights` come from the last
successful Portfolio. With `weight_drift=False`, they are its target weights,
so each value measures target turnover. With `weight_drift=True`, they include
the intervening drift, so each value measures executed turnover. Failed
portfolios have a NaN value. Empty portfolios are omitted because they have
no observation to use as a rebalancing date.

<a id="skfolio.portfolio.MultiPeriodPortfolio.weights_dict"></a>

#### *property* weights_dict

Dictionary mapping each Portfolio name to its asset weight allocation.

<a id="skfolio.portfolio.MultiPeriodPortfolio.weights_per_observation"></a>

#### *property* weights_per_observation

DataFrame of the Portfolio weights per observation.