---
title: ModelData (latest version)
description: API reference for qiskit_noise_learning.data.ModelData in the latest version of qiskit-noise-learning
source: https://quantum.cloud.ibm.com/docs/en/api/qiskit-noise-learning/generated/data-model-data
---

# qiskit\_noise\_learning.data.ModelData

*class* `qiskit_noise_learning.data.ModelData(dataset: Dataset)`

[GitHub](https://github.com/Qiskit/qiskit-noise-learning/tree/stable/0.1/qiskit_noise_learning/data/model_data.py)

Bases: [`LeveledData`](/docs/api/qiskit-noise-learning/generated/data-leveled-data "qiskit_noise_learning.data.leveled_data.LeveledData"), [`Generic`](https://docs.python.org/3/library/typing.html#typing.Generic)\[`ParameterIndex`]

Results from fitting, backed by an xarray Dataset.

The dataset has data variables:

- `parameter_values`: 1D array with dimension `parameter_index`.
- `covariance`: 2D array with dimensions `(parameter_row_index, parameter_col_index)`.

The `parameter_index`, `parameter_row_index`, and `parameter_col_index` coordinates all share the same parameter labels. Additional fit metadata is stored in dataset attrs.

### \_\_init\_\_

`__init__(dataset: Dataset)`

## Methods

|                                                                                                                                                             |                                                                   |
| ----------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------- |
| [`__init__`](#qiskit_noise_learning.data.ModelData.__init__ "qiskit_noise_learning.data.ModelData.__init__")(dataset)                                       |                                                                   |
| [`filter_time`](#qiskit_noise_learning.data.ModelData.filter_time "qiskit_noise_learning.data.ModelData.filter_time")(lb, ub)                               | Filter to data gathered within the time bounds.                   |
| [`from_arrays`](#qiskit_noise_learning.data.ModelData.from_arrays "qiskit_noise_learning.data.ModelData.from_arrays")(parameter\_indices, ...\[, metadata]) | Instantiate from data specified as arrays in standard containers. |

## Attributes

|                                                                                                              |                                              |
| ------------------------------------------------------------------------------------------------------------ | -------------------------------------------- |
| `dataset`                                                                                                    |                                              |
| [`metadata`](#qiskit_noise_learning.data.ModelData.metadata "qiskit_noise_learning.data.ModelData.metadata") | Metadata describing the model parameter fit. |

### from\_arrays

*classmethod* `from_arrays(parameter_indices: list[ParameterIndex], parameter_values: ndarray[float64], covariance: ndarray[float64], time_lbs: ndarray[datetime64], time_ubs: ndarray[datetime64], metadata: dict[str, Any] | None = None) → Self`

Instantiate from data specified as arrays in standard containers.

**Parameters**

- **parameter\_indices** – A list of `ParameterIndex` instances.
- **parameter\_values** – A 1d array of floats indicating parameter values.
- **covariance** – A 2d array of floats indicating the covariances of the parameter values.
- **time\_lbs** – A 1d array of data acquisition time lower bounds for each parameter estimate.
- **time\_ubs** – A 1d array of data acquisition time upper bounds for each parameter estimate.
- **metadata** – Any metadata to attach to the dataset.

### metadata

Type: [`dict`](https://docs.python.org/3/library/stdtypes.html#dict)\[[`str`](https://docs.python.org/3/library/stdtypes.html#str), [`Any`](https://docs.python.org/3/library/typing.html#typing.Any)]

Metadata describing the model parameter fit.

### filter\_time

`filter_time(lb: datetime64, ub: datetime64) → Self`

Filter to data gathered within the time bounds.

**Parameters**

- **lb** – The time lower bound (inclusive).
- **ub** – The time upper bound (inclusive).

**Returns**

The time filtered version of self.