v1.3.1

Minor patch release compatible with Tune Insight v1.3.1 and v1.3.0. Install with

pip install tuneinsight==1.3.1

To also install data science tools such as jupyter, install the full release:

pip install tuneinsight[full]==1.3.1

(If you are using zsh, you may need to escape the brackets as tuneinsight\[full\]).

This is a minor release intended for compatibility with fixes in v1.3.1., and is fully compatible with v1.3.0.

v1.3.0

Release compatible with Tune Insight v1.3.0. Install with

pip install tuneinsight==1.3.0

To also install data science tools such as jupyter, install the full release:

pip install tuneinsight[full]==1.3.0

(If you are using zsh, you may need to escape the brackets as tuneinsight\[full\]).

This release includes quality-of-life improvements and bug fixes, aiming to improve the usability of the SDK:

• We have improved error messages and warnings for some common issues (e.g. errors with .login).
• The cryptolib has been trimmed down and is now much lighter, reducing the size of the package.

In addition, we have decided to deprecate model-as-a-service and fully encrypted regression in the SDK. Use HybridFL instead.

v1.2.3

Release compatible with Tune Insight v1.2.3. Install with

pip install tuneinsight==1.2.3

To also install data science tools such as jupyter, install the full release:

pip install tuneinsight[full]==1.2.3

(If you are using zsh, you may need to escape the brackets as tuneinsight\[full\]).

This release includes fairly significant updates to the API for compatibility with new features. Notable changes:

1. Screening

This release includes API updates for compatibility with new features (including data preparation and cross-standard queries). Changes to the SDK itself are very minor.

v1.2.0

Release compatible with Tune Insight v1.2.0. Install with

pip install tuneinsight==1.2.0

To also install data science tools such as jupyter, install the full release:

pip install tuneinsight[full]==1.2.0

(If you are using zsh, you may need to escape the brackets as tuneinsight\[full\]).

This release includes API updates for compatibility with new features. Notable changes include:

1. Privacy risk analysis on projects (Project.display_privacy_warnings).
2. Many bug fixes, pertaining to loading computations from the backend and compound preprocessing.
3. Small improvements to the cryptolib that make it lighter.

v1.1.4

Release compatible with Tune Insight v1.1.4. Install with

pip install tuneinsight==1.1.4

To also install data science tools such as jupyter, install the full release:

pip install tuneinsight[full]==1.1.4

(If you are using zsh, you may need to escape the brackets as tuneinsight\[full\]).

This release mostly includes API updates for compatibility with new features added in the solution. Two notable SDK-only changes:

1. Basic support for Cross-standard queries (TIQL).
2. Improved plotting of Kaplan-Meier survival curves.

v1.1.3

Release compatible with Tune Insight v1.1.2. Install with

pip install tuneinsight==1.1.3

To also install data science tools such as jupyter, install the full release:

pip install tuneinsight[full]==1.1.3

(If you are using zsh, you may need to escape the brackets as tuneinsight\[full\]).

This release brings very few changes since many features were brought in the intermediate release v1.1.2. The most notable change is a fix to a bug where the cryptolib could not be loaded when running a Linux image with Docker on Mac OS.

v1.1.2

SDK-only release compatible with Tune Insight v1.1.{0,1}. Install with

pip install tuneinsight==1.1.2

This version marks some dependencies (mostly related to jupyter) as optional. The above will not include these dependencies and is recommended for production environments. Users who intend to use the SDK in notebooks should do the full install:

pip install tuneinsight[full]==1.1.2

(If you are using zsh, you may need to escape the brackets as tuneinsight\[full\]).

This release also updates some of the dependencies of the SDK, in particular python-keycloak. It also includes upcoming features (of v1.2) that might not be supported by your instance, but should be backwards compatible.

v1.1.0

Compatible with Tune Insight v1.1.0. Install with

pip install tuneinsight==1.1.0

This version mirrors the major version change for the Tune Insight solution. Changes to the SDK are minor. New features include:

• Better usability by non-editor users (a bug previously made such users unable to run projects).
• Ability to check what a user is allowed to do (capabilities) from the SDK with client.can.
• Projects can now be (un)archived.
• Units can be specified to filter records such that they use the appropriate units for a numerical value.

v1.0.1

Compatible with Tune Insight v1.0.1. Install with

pip install tuneinsight==1.0.1

This is a minor patch version that mostly includes UI changes, and this SDK release is intended for consistency. It is (99%) compatible with v1.0.0., but includes additional features supported by the API but intended for the SDK.

v1.0.0

Compatible with Tune Insight v1.0.0. Install with

pip install tuneinsight==1.0.0

This version includes major (mostly backwards-compatible) changes, conforming to the changes in the Tune Insight solution to v1.0.0. New features available in the solution and mirrored in the SDK include:

• The Feasibility, Distribution and FilteredAggregation computations, which all extend aggregations for specialized use cases.
• Automated dataset schema inference.
• Policies at a datasource level.
• Differentially private statistics.
• Confidence intervals and post-processing for differentially private survival curves.
• Screening operations for datasets.
• Privacy budgets can be scoped at a datasource level.

The following new features were added to the SDK specifically:

• Support for remote datasources (for non-contributing nodes).
• A human-readable display of available project actions.

This release also includes many smaller changes aiming to improve the user experience, such as improved error messages.