learner-py
The learner-py package implements transfer learning methods for low-rank
matrix estimation. These methods leverage similarity in the latent row
and column spaces between the source and target populations to improve
estimation in the target population. The methods include the LatEnt
spAce-based tRaNsfer lEaRning (LEARNER) method and the direct projection
LEARNER (D-LEARNER) method described by McGrath et
al. (2024).
Installation
You can install the released version of learner-py from
PyPi with:
pip install learner-py
LEARNER Method
We can apply the LEARNER method via the learner function.
This method allows for flexible patterns of heterogeneity across the
source and target populations. It consequently requires specifying the
tuning parameters lambda_1 and lambda_2 which control the degree of
transfer learning between the populations. These values can be selected
based on cross-validation via the cv.learner function. For example, we
can specify candidate values of 1, 10, and 100 for lambda_1 and
lambda_2 and select the optimal values based on cross-validation as
follows:
res_cv = pylearner.cv_learner(
Y_source=dat_highsim["Y_source"],
Y_target=dat_highsim["Y_target"],
lambda1_all=[1, 10, 100],
lambda2_all=[1, 10, 100],
step_size=0.003
)
print(res_cv['lambda_1_min']) #100
print(res_cv["lambda_2_min"]) #1
Example
We illustrate an example of how learner can be used. We first load the
package.
import learner-py as pylearner
In this illustration, we will use one of the toy data sets in the
package (dat_highsim) that has a high degree of similarity between the
latent spaces of the source and target populations. The object
dat_highsim is a list which contains the observed source population
data matrix Y_source and the target population data matrix Y_target.
Since the data was simulated, the true values of the matrices are
included in dat_highsim as Theta_source and Theta_target.
LEARNER Method
We can apply the LEARNER method via the learner function.
This method allows for flexible patterns of heterogeneity across the
source and target populations. It consequently requires specifying the
tuning parameters lambda_1 and lambda_2 which control the degree of
transfer learning between the populations. These values can be selected
based on cross-validation via the cv.learner function. For example, we
can specify candidate values of 1, 10, and 100 for lambda_1 and
lambda_2 and select the optimal values based on cross-validation as
follows:
res_cv = pylearner.cv_learner(
Y_source=dat_highsim["Y_source"],
Y_target=dat_highsim["Y_target"],
lambda1_all=[1, 10, 100],
lambda2_all=[1, 10, 100],
step_size=0.003
)
print(res_cv['lambda_1_min']) #100
print(res_cv["lambda_2_min"]) #1
Next, we apply the learner function with these values of lambda1
and lambda2:
res_learner <- learner(Y_source = dat_highsim$Y_source,
Y_target = dat_highsim$Y_target,
lambda1 = 100, lambda2 = 1,
step_size = 0.003)
The LEARNER estimate is given by the learner_estimate component in the
output of the learner function, e.g.,
print(res_learner['learner_estimate'][0:4, 0:4])
[[ 0.14688887 -1.63414688 1.18573076 0.00809396]
[ 0.10877659 -0.2439277 -1.0061737 -0.05811972]
[-0.62130277 1.04206753 -0.69077759 0.90570933]
[ 1.58115883 -3.0000149 0.39780804 -2.12428512]]
D-LEARNER Method
We can apply the D-LEARNER method via the dlearner function. This
method makes stronger assumptions on the heterogeneity across the source
and target populations. It consequently does not rely on choosing tuning
parameters. The dlearner function can be applied as follows:
res_dlearner = pylearner.dlearner(Y_source=dat_highsim["Y_source"],
Y_target=dat_highsim["Y_target"])
print(res_dlearner['dlearner_estimate'][0:4, 0:4])
[[ 0.0959171 -1.72143637 1.15500149 0.00547827]
[ 0.10771367 -0.3224348 -1.03557177 -0.10819564]
[-0.72372751 0.86634922 -0.43528206 1.10580219]
[ 1.63476957 -2.91985925 0.04876288 -2.35750409]]
1 maintainer
Metadata
1 maintainer
Release files for learner-py 1.0.4
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Built distributions (wheels)
Total release size: 68.1 MB
Release files / learner_py-1.0.4-cp313-cp313-win_amd64.whl
| Download URL | learner_py-1.0.4-cp313-cp313-win_amd64.whl |
|---|---|
| Size | 237.9 kB |
| Tags | CPython 3.13 Windows x86-64 |
|
SHA-256 checksum How to use checksums |
33f4dc469bab8b34154209b6234598add766340cd8bb3f8c6fba129201f21638
|
|
BLAKE2b-256 checksum How to use checksums |
11fc2f8a79d11be38bc10ac9db62d45b2be4357280197e8da017106a9107d6fc
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 7, 2025.
Transparency logRelease files / learner_py-1.0.4-cp313-cp313-macosx_10_13_x86_64.whl
| Download URL | learner_py-1.0.4-cp313-cp313-macosx_10_13_x86_64.whl |
|---|---|
| Size | 346.9 kB |
| Tags | CPython 3.13 macOS 10.13+ x86-64 |
|
SHA-256 checksum How to use checksums |
24bf1417bc02cf50c12439cc45855e88c15df9cbcac30891082230a0dff30475
|
|
BLAKE2b-256 checksum How to use checksums |
de2b85871c6cc9ecbc6c2ad9db504e4c77cc27450909b051201815c152e3e522
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 7, 2025.
Transparency logRelease files / learner_py-1.0.4-cp312-cp312-win_amd64.whl
| Download URL | learner_py-1.0.4-cp312-cp312-win_amd64.whl |
|---|---|
| Size | 237.8 kB |
| Tags | CPython 3.12 Windows x86-64 |
|
SHA-256 checksum How to use checksums |
5462a8032b77d10e720e0952142fad0dce2e231d3aa15817237d255136fe813e
|
|
BLAKE2b-256 checksum How to use checksums |
6e453210d7df31388b3e0f533ec0eb3f25537c7fcf6d8d949b0bee464ee6f38d
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 7, 2025.
Transparency logRelease files / learner_py-1.0.4-cp312-cp312-macosx_10_13_x86_64.whl
| Download URL | learner_py-1.0.4-cp312-cp312-macosx_10_13_x86_64.whl |
|---|---|
| Size | 346.8 kB |
| Tags | CPython 3.12 macOS 10.13+ x86-64 |
|
SHA-256 checksum How to use checksums |
70a007b4678feea30344b03d7d4e90d135334ae4901e4263c828942310faeeda
|
|
BLAKE2b-256 checksum How to use checksums |
41f0cc988b52f6704ab9808627c06ce9c6d213ccab92dd0c7b7bfc3a81759700
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 7, 2025.
Transparency logRelease files / learner_py-1.0.4-cp311-cp311-win_amd64.whl
| Download URL | learner_py-1.0.4-cp311-cp311-win_amd64.whl |
|---|---|
| Size | 236.9 kB |
| Tags | CPython 3.11 Windows x86-64 |
|
SHA-256 checksum How to use checksums |
7283544a7387c41361234bca8c9aae3857f8ef046a20587a1f1715fe92f463f3
|
|
BLAKE2b-256 checksum How to use checksums |
f04d581038179282a864e59a62f25eed666cffee30c6f66bdaf825ad9c4b07ba
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 7, 2025.
Transparency logRelease files / learner_py-1.0.4-cp311-cp311-musllinux_1_2_x86_64.whl
| Download URL | learner_py-1.0.4-cp311-cp311-musllinux_1_2_x86_64.whl |
|---|---|
| Size | 11.4 MB |
| Tags | CPython 3.11 Linux musl 1.2+ x86-64 |
|
SHA-256 checksum How to use checksums |
5e8152081c471fa69f24b269f96d3dc2997200d59d52be58d5a8f8fd06b56e11
|
|
BLAKE2b-256 checksum How to use checksums |
ccdee7db1fbf99645f23ee77aa8b03c22b3012d8ca72ae3457e05b9e5eb33db0
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 7, 2025.
Transparency logRelease files / learner_py-1.0.4-cp311-cp311-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl
| Download URL | learner_py-1.0.4-cp311-cp311-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl |
|---|---|
| Size | 10.4 MB |
| Tags | CPython 3.11 Linux glibc 2.24+ x86-64 Linux glibc 2.28+ x86-64 |
|
SHA-256 checksum How to use checksums |
529f882dce6670b88eae451eddacbcd90589d44e58d57f17ba5749cc9d9efbd6
|
|
BLAKE2b-256 checksum How to use checksums |
528ec55a7dddf52967a10e58299e8c56414bf716367e805fa2b314e8825334e0
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 7, 2025.
Transparency logRelease files / learner_py-1.0.4-cp311-cp311-macosx_10_9_x86_64.whl
| Download URL | learner_py-1.0.4-cp311-cp311-macosx_10_9_x86_64.whl |
|---|---|
| Size | 346.5 kB |
| Tags | CPython 3.11 macOS 10.9+ x86-64 |
|
SHA-256 checksum How to use checksums |
84ed7ad8d21a5759d703a9a344535cd16951778f059979c81788cfd235a752fb
|
|
BLAKE2b-256 checksum How to use checksums |
34f0aca27ae5cb64432e1a048a82f7c1dfc82f4e6554731060762e66b609e84a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 7, 2025.
Transparency logRelease files / learner_py-1.0.4-cp310-cp310-win_amd64.whl
| Download URL | learner_py-1.0.4-cp310-cp310-win_amd64.whl |
|---|---|
| Size | 236.5 kB |
| Tags | CPython 3.10 Windows x86-64 |
|
SHA-256 checksum How to use checksums |
3f6fa3f191a00a39e0a4ab3fbebf03fba118a25995ac0eb3cece2b7305040fc0
|
|
BLAKE2b-256 checksum How to use checksums |
0975ab5763b90e9936175b49b6c6135e53dd53bdff6a290adb86b1e55a5bed7b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 7, 2025.
Transparency logRelease files / learner_py-1.0.4-cp310-cp310-musllinux_1_2_x86_64.whl
| Download URL | learner_py-1.0.4-cp310-cp310-musllinux_1_2_x86_64.whl |
|---|---|
| Size | 11.4 MB |
| Tags | CPython 3.10 Linux musl 1.2+ x86-64 |
|
SHA-256 checksum How to use checksums |
d1a8e6b41bcf7381144ab731763d574f8839123ea79c1c82fc78630ca1f4a4ec
|
|
BLAKE2b-256 checksum How to use checksums |
7c990043d9e7da603b9c3c3dc800047b41e1e8798544eeebf689aaac026d8bec
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 7, 2025.
Transparency logRelease files / learner_py-1.0.4-cp310-cp310-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl
| Download URL | learner_py-1.0.4-cp310-cp310-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl |
|---|---|
| Size | 10.3 MB |
| Tags | CPython 3.10 Linux glibc 2.24+ x86-64 Linux glibc 2.28+ x86-64 |
|
SHA-256 checksum How to use checksums |
1db85c07688291e9af6ef7d8027eda2402dfbcac569ce70e08de2f62d868e999
|
|
BLAKE2b-256 checksum How to use checksums |
6342577dd7bc88b75d23f4dae10a21465b2a8253b2f191ae4a24f4547128e442
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 7, 2025.
Transparency logRelease files / learner_py-1.0.4-cp310-cp310-macosx_10_9_x86_64.whl
| Download URL | learner_py-1.0.4-cp310-cp310-macosx_10_9_x86_64.whl |
|---|---|
| Size | 345.0 kB |
| Tags | CPython 3.10 macOS 10.9+ x86-64 |
|
SHA-256 checksum How to use checksums |
215e298991373d9bd18dd8950babf6b8b04a5d44e709431e24fbf2b156d592b9
|
|
BLAKE2b-256 checksum How to use checksums |
d008d05e16b85fec4ca1289090c7ed80722dbf823218ebc32eba6f9958660f5e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 7, 2025.
Transparency logRelease files / learner_py-1.0.4-cp39-cp39-win_amd64.whl
| Download URL | learner_py-1.0.4-cp39-cp39-win_amd64.whl |
|---|---|
| Size | 236.5 kB |
| Tags | CPython 3.9 Windows x86-64 |
|
SHA-256 checksum How to use checksums |
7b963aec5770b8295c5fdd7f9cd878c3c9d0f89ed426f250475dbade075e77b5
|
|
BLAKE2b-256 checksum How to use checksums |
91a362e2b2745a07e3806c6e2a837c8e8a50bd31c78606c706f193bfc5c9614a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 7, 2025.
Transparency logRelease files / learner_py-1.0.4-cp39-cp39-musllinux_1_2_x86_64.whl
| Download URL | learner_py-1.0.4-cp39-cp39-musllinux_1_2_x86_64.whl |
|---|---|
| Size | 11.4 MB |
| Tags | CPython 3.9 Linux musl 1.2+ x86-64 |
|
SHA-256 checksum How to use checksums |
5865722aa5ef25eadfbb9ca9b2418a4b61507f83bce26812edc7a02c59321e9b
|
|
BLAKE2b-256 checksum How to use checksums |
9ea3ccb33eeaed2a9126717b39844909725142531d660fd87ee0337ee6ca844a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 7, 2025.
Transparency logRelease files / learner_py-1.0.4-cp39-cp39-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl
| Download URL | learner_py-1.0.4-cp39-cp39-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl |
|---|---|
| Size | 10.3 MB |
| Tags | CPython 3.9 Linux glibc 2.24+ x86-64 Linux glibc 2.28+ x86-64 |
|
SHA-256 checksum How to use checksums |
b97bc4b4cf4ec1f8bfe254214e04ff04e814a3b0a2ec2fc39d3d98fed69cdec1
|
|
BLAKE2b-256 checksum How to use checksums |
43f22d1a29f1bd7f618f4f2f29e0bd8ed16e5b8277cee01615d91114ff8038d8
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 7, 2025.
Transparency logRelease files / learner_py-1.0.4-cp39-cp39-macosx_10_9_x86_64.whl
| Download URL | learner_py-1.0.4-cp39-cp39-macosx_10_9_x86_64.whl |
|---|---|
| Size | 345.1 kB |
| Tags | CPython 3.9 macOS 10.9+ x86-64 |
|
SHA-256 checksum How to use checksums |
899f0ee9b20cfaff7e1259c3978e22b382c52ac8f0b7583b84001233de6ab9f5
|
|
BLAKE2b-256 checksum How to use checksums |
fc8fc56e7a7c1840bb73c04c1edc6db8c880435e63964d3fbe485c219bfbe685
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 7, 2025.
Transparency log
