mlflow.client

The mlflow.client module provides a Python CRUD interface to MLflow Experiments, Runs, Model Versions, and Registered Models. This is a lower level API that directly translates to MLflow REST API calls. For a higher level API for managing an “active run”, use the mlflow module.

class mlflow.client.MlflowClient(tracking_uri: Optional[str] = None, registry_uri: Optional[str] = None)[source]

Bases: object

Client of an MLflow Tracking Server that creates and manages experiments and runs, and of an MLflow Registry Server that creates and manages registered models and model versions. It’s a thin wrapper around TrackingServiceClient and RegistryClient so there is a unified API but we can keep the implementation of the tracking and registry clients independent from each other.

copy_model_version(src_model_uri, dst_name) → ModelVersion [source]

Copy a model version from one registered model to another as a new model version.

Parameters

src_model_uri – The model URI of the model version to copy. This must be a model registry URI with a “models:/” scheme (e.g., “models:/iris_model@champion”).
dst_name – The name of the registered model to copy the model version to. If a registered model with this name does not exist, it will be created.

Returns

Single mlflow.entities.model_registry.ModelVersion object representing the copied model version.

Example

import mlflow.sklearn
from mlflow import MlflowClient
from mlflow.models import infer_signature
from sklearn.datasets import make_regression
from sklearn.ensemble import RandomForestRegressor


def print_model_version_info(mv):
    print(f"Name: {mv.name}")
    print(f"Version: {mv.version}")
    print(f"Source: {mv.source}")


mlflow.set_tracking_uri("sqlite:///mlruns.db")
X, y = make_regression(n_features=4, n_informative=2, random_state=0, shuffle=False)

# Log a model
with mlflow.start_run() as run:
    params = {"n_estimators": 3, "random_state": 42}
    rfr = RandomForestRegressor(**params).fit(X, y)
    signature = infer_signature(X, rfr.predict(X))
    mlflow.log_params(params)
    mlflow.sklearn.log_model(rfr, artifact_path="sklearn-model", signature=signature)

# Create source model version
client = MlflowClient()
src_name = "RandomForestRegression-staging"
client.create_registered_model(src_name)
src_uri = f"runs:/{run.info.run_id}/sklearn-model"
mv_src = client.create_model_version(src_name, src_uri, run.info.run_id)
print_model_version_info(mv_src)
print("--")

# Copy the source model version into a new registered model
dst_name = "RandomForestRegression-production"
src_model_uri = f"models:/{mv_src.name}/{mv_src.version}"
mv_copy = client.copy_model_version(src_model_uri, dst_name)
print_model_version_info(mv_copy)

Output

Name: RandomForestRegression-staging
Version: 1
Source: runs:/53e08bb38f0c487fa36c5872515ed998/sklearn-model
--
Name: RandomForestRegression-production
Version: 1
Source: models:/RandomForestRegression-staging/1

create_experiment(name: str, artifact_location: Optional[str] = None, tags: Optional[Dict[str, Any]] = None) → str[source]

Create an experiment.

Parameters

name – The experiment name. Must be unique.
artifact_location – The location to store run artifacts. If not provided, the server picks anappropriate default.
tags – A dictionary of key-value pairs that are converted into mlflow.entities.ExperimentTag objects, set as experiment tags upon experiment creation.

Returns

String as an integer ID of the created experiment.

Example

from pathlib import Path
from mlflow import MlflowClient

# Create an experiment with a name that is unique and case sensitive.
client = MlflowClient()
experiment_id = client.create_experiment(
    "Social NLP Experiments",
    artifact_location=Path.cwd().joinpath("mlruns").as_uri(),
    tags={"version": "v1", "priority": "P1"},
)
client.set_experiment_tag(experiment_id, "nlp.framework", "Spark NLP")

# Fetch experiment metadata information
experiment = client.get_experiment(experiment_id)
print(f"Name: {experiment.name}")
print(f"Experiment_id: {experiment.experiment_id}")
print(f"Artifact Location: {experiment.artifact_location}")
print(f"Tags: {experiment.tags}")
print(f"Lifecycle_stage: {experiment.lifecycle_stage}")

Output

Name: Social NLP Experiments
Experiment_id: 1
Artifact Location: file:///.../mlruns
Tags: {'version': 'v1', 'priority': 'P1', 'nlp.framework': 'Spark NLP'}
Lifecycle_stage: active

create_model_version(name: str, source: str, run_id: Optional[str] = None, tags: Optional[Dict[str, Any]] = None, run_link: Optional[str] = None, description: Optional[str] = None, await_creation_for: int = 300) → ModelVersion [source]

Create a new model version from given source.

Parameters

name – Name for the containing registered model.
source – URI indicating the location of the model artifacts. The artifact URI can be run relative (e.g. runs:/<run_id>/<model_artifact_path>), a model registry URI (e.g. models:/<model_name>/<version>), or other URIs supported by the model registry backend (e.g. “s3://my_bucket/my/model”).
run_id – Run ID from MLflow tracking server that generated the model.
tags – A dictionary of key-value pairs that are converted into mlflow.entities.model_registry.ModelVersionTag objects.
run_link – Link to the run from an MLflow tracking server that generated this model.
description – Description of the version.
await_creation_for – Number of seconds to wait for the model version to finish being created and is in READY status. By default, the function waits for five minutes. Specify 0 or None to skip waiting.

Returns

Single mlflow.entities.model_registry.ModelVersion object created by backend.

Example

import mlflow.sklearn
from mlflow.store.artifact.runs_artifact_repo import RunsArtifactRepository
from mlflow import MlflowClient
from mlflow.models import infer_signature
from sklearn.datasets import make_regression
from sklearn.ensemble import RandomForestRegressor

mlflow.set_tracking_uri("sqlite:///mlruns.db")
params = {"n_estimators": 3, "random_state": 42}
name = "RandomForestRegression"
X, y = make_regression(n_features=4, n_informative=2, random_state=0, shuffle=False)
rfr = RandomForestRegressor(**params).fit(X, y)
signature = infer_signature(X, rfr.predict(X))

# Log MLflow entities
with mlflow.start_run() as run:
    mlflow.log_params(params)
    mlflow.sklearn.log_model(rfr, artifact_path="sklearn-model", signature=signature)

# Register model name in the model registry
client = MlflowClient()
client.create_registered_model(name)

# Create a new version of the rfr model under the registered model name
desc = "A new version of the model"
runs_uri = f"runs:/{run.info.run_id}/sklearn-model"
model_src = RunsArtifactRepository.get_underlying_uri(runs_uri)
mv = client.create_model_version(name, model_src, run.info.run_id, description=desc)
print(f"Name: {mv.name}")
print(f"Version: {mv.version}")
print(f"Description: {mv.description}")
print(f"Status: {mv.status}")
print(f"Stage: {mv.current_stage}")

Output

Name: RandomForestRegression
Version: 1
Description: A new version of the model
Status: READY
Stage: None

create_registered_model(name: str, tags: Optional[Dict[str, Any]] = None, description: Optional[str] = None) → RegisteredModel [source]

Create a new registered model in backend store.

Parameters

name – Name of the new model. This is expected to be unique in the backend store.
tags – A dictionary of key-value pairs that are converted into mlflow.entities.model_registry.RegisteredModelTag objects.
description – Description of the model.

Returns

A single object of mlflow.entities.model_registry.RegisteredModel created by backend.

Example

import mlflow
from mlflow import MlflowClient


def print_registered_model_info(rm):
    print(f"name: {rm.name}")
    print(f"tags: {rm.tags}")
    print(f"description: {rm.description}")


name = "SocialMediaTextAnalyzer"
tags = {"nlp.framework": "Spark NLP"}
desc = "This sentiment analysis model classifies the tone-happy, sad, angry."

mlflow.set_tracking_uri("sqlite:///mlruns.db")
client = MlflowClient()
client.create_registered_model(name, tags, desc)
print_registered_model_info(client.get_registered_model(name))

Output

name: SocialMediaTextAnalyzer
tags: {'nlp.framework': 'Spark NLP'}
description: This sentiment analysis model classifies the tone-happy, sad, angry.

create_run(experiment_id: str, start_time: Optional[int] = None, tags: Optional[Dict[str, Any]] = None, run_name: Optional[str] = None) → Run [source]

Create a mlflow.entities.Run object that can be associated with metrics, parameters, artifacts, etc. Unlike mlflow.projects.run(), creates objects but does not run code. Unlike mlflow.start_run(), does not change the “active run” used by mlflow.log_param().

Parameters

experiment_id – The string ID of the experiment to create a run in.
start_time – If not provided, use the current timestamp.
tags – A dictionary of key-value pairs that are converted into mlflow.entities.RunTag objects.
run_name – The name of this run.

Returns

mlflow.entities.Run that was created.

Example

from mlflow import MlflowClient

# Create a run with a tag under the default experiment (whose id is '0').
tags = {"engineering": "ML Platform"}
name = "platform-run-24"
client = MlflowClient()
experiment_id = "0"
run = client.create_run(experiment_id, tags=tags, run_name=name)

# Show newly created run metadata info
print(f"Run tags: {run.data.tags}")
print(f"Experiment id: {run.info.experiment_id}")
print(f"Run id: {run.info.run_id}")
print(f"Run name: {run.info.run_name}")
print(f"lifecycle_stage: {run.info.lifecycle_stage}")
print(f"status: {run.info.status}")

Output

Run tags: {'engineering': 'ML Platform'}
Experiment id: 0
Run id: 65fb9e2198764354bab398105f2e70c1
Run name: platform-run-24
lifecycle_stage: active
status: RUNNING

delete_experiment(experiment_id: str) → None[source]

Delete an experiment from the backend store.

This deletion is a soft-delete, not a permanent deletion. Experiment names can not be reused, unless the deleted experiment is permanently deleted by a database admin.

Parameters: experiment_id – The experiment ID returned from create_experiment.

Example

from mlflow import MlflowClient

# Create an experiment with a name that is unique and case sensitive
client = MlflowClient()
experiment_id = client.create_experiment("New Experiment")
client.delete_experiment(experiment_id)

# Examine the deleted experiment details.
experiment = client.get_experiment(experiment_id)
print(f"Name: {experiment.name}")
print(f"Artifact Location: {experiment.artifact_location}")
print(f"Lifecycle_stage: {experiment.lifecycle_stage}")

Output

Name: New Experiment
Artifact Location: file:///.../mlruns/1
Lifecycle_stage: deleted

delete_model_version(name: str, version: str) → None[source]

Delete model version in backend.

Parameters

name – Name of the containing registered model.
version – Version number of the model version.

Example

import mlflow.sklearn
from mlflow import MlflowClient
from mlflow.models import infer_signature
from sklearn.datasets import make_regression
from sklearn.ensemble import RandomForestRegressor


def print_models_info(mv):
    for m in mv:
        print(f"name: {m.name}")
        print(f"latest version: {m.version}")
        print(f"run_id: {m.run_id}")
        print(f"current_stage: {m.current_stage}")


mlflow.set_tracking_uri("sqlite:///mlruns.db")
X, y = make_regression(n_features=4, n_informative=2, random_state=0, shuffle=False)

# Create two runs and log MLflow entities
with mlflow.start_run() as run1:
    params = {"n_estimators": 3, "random_state": 42}
    rfr = RandomForestRegressor(**params).fit(X, y)
    signature = infer_signature(X, rfr.predict(X))
    mlflow.log_params(params)
    mlflow.sklearn.log_model(rfr, artifact_path="sklearn-model", signature=signature)

with mlflow.start_run() as run2:
    params = {"n_estimators": 6, "random_state": 42}
    rfr = RandomForestRegressor(**params).fit(X, y)
    signature = infer_signature(X, rfr.predict(X))
    mlflow.log_params(params)
    mlflow.sklearn.log_model(rfr, artifact_path="sklearn-model", signature=signature)

# Register model name in the model registry
name = "RandomForestRegression"
client = MlflowClient()
client.create_registered_model(name)

# Create a two versions of the rfr model under the registered model name
for run_id in [run1.info.run_id, run2.info.run_id]:
    model_uri = f"runs:/{run_id}/sklearn-model"
    mv = client.create_model_version(name, model_uri, run_id)
    print(f"model version {mv.version} created")

print("--")

# Fetch latest version; this will be version 2
models = client.get_latest_versions(name, stages=["None"])
print_models_info(models)
print("--")

# Delete the latest model version 2
print(f"Deleting model version {mv.version}")
client.delete_model_version(name, mv.version)
models = client.get_latest_versions(name, stages=["None"])
print_models_info(models)

Output

model version 1 created
model version 2 created
--
name: RandomForestRegression
latest version: 2
run_id: 9881172ef10f4cb08df3ed452c0c362b
current_stage: None
--
Deleting model version 2
name: RandomForestRegression
latest version: 1
run_id: 9165d4f8aa0a4d069550824bdc55caaf
current_stage: None

delete_model_version_tag(name: str, version: Optional[str] = None, key: Optional[str] = None, stage: Optional[str] = None) → None[source]

Delete a tag associated with the model version.

When stage is set, tag will be deleted for latest model version of the stage. Setting both version and stage parameter will result in error.

Parameters

name – Registered model name.
version – Registered model version.
key – Tag key. key is required.
stage – Registered model stage.

Example

import mlflow.sklearn
from mlflow import MlflowClient
from mlflow.models import infer_signature
from sklearn.datasets import make_regression
from sklearn.ensemble import RandomForestRegressor


def print_model_version_info(mv):
    print(f"Name: {mv.name}")
    print(f"Version: {mv.version}")
    print(f"Tags: {mv.tags}")


mlflow.set_tracking_uri("sqlite:///mlruns.db")
params = {"n_estimators": 3, "random_state": 42}
name = "RandomForestRegression"
X, y = make_regression(n_features=4, n_informative=2, random_state=0, shuffle=False)
rfr = RandomForestRegressor(**params).fit(X, y)
signature = infer_signature(X, rfr.predict(X))

# Log MLflow entities
with mlflow.start_run() as run:
    mlflow.log_params(params)
    mlflow.sklearn.log_model(rfr, artifact_path="sklearn-model", signature=signature)
# Register model name in the model registry
client = MlflowClient()
client.create_registered_model(name)

# Create a new version of the rfr model under the registered model name
# and delete a tag
model_uri = f"runs:/{run.info.run_id}/sklearn-model"
tags = {"t": "1", "t1": "2"}
mv = client.create_model_version(name, model_uri, run.info.run_id, tags=tags)
print_model_version_info(mv)
print("--")
# using version to delete tag
client.delete_model_version_tag(name, mv.version, "t")

# using stage to delete tag
client.delete_model_version_tag(name, key="t1", stage=mv.current_stage)
mv = client.get_model_version(name, mv.version)
print_model_version_info(mv)

Output

Name: RandomForestRegression
Version: 1
Tags: {'t': '1', 't1': '2'}
--
Name: RandomForestRegression
Version: 1
Tags: {}

delete_registered_model(name: str)[source]

Delete registered model. Backend raises exception if a registered model with given name does not exist.

Parameters: name – Name of the registered model to delete.

Example

import mlflow
from mlflow import MlflowClient


def print_registered_models_info(r_models):
    print("--")
    for rm in r_models:
        print(f"name: {rm.name}")
        print(f"tags: {rm.tags}")
        print(f"description: {rm.description}")


mlflow.set_tracking_uri("sqlite:///mlruns.db")
client = MlflowClient()

# Register a couple of models with respective names, tags, and descriptions
for name, tags, desc in [
    ("name1", {"t1": "t1"}, "description1"),
    ("name2", {"t2": "t2"}, "description2"),
]:
    client.create_registered_model(name, tags, desc)

# Fetch all registered models
print_registered_models_info(client.search_registered_models())

# Delete one registered model and fetch again
client.delete_registered_model("name1")
print_registered_models_info(client.search_registered_models())

Output

--
name: name1
tags: {'t1': 't1'}
description: description1
name: name2
tags: {'t2': 't2'}
description: description2
--
name: name2
tags: {'t2': 't2'}
description: description2

delete_registered_model_alias(name: str, alias: str) → None[source]

Delete an alias associated with a registered model.

Parameters

name – Registered model name.
alias – Name of the alias.

Example

import mlflow
from mlflow import MlflowClient
from mlflow.models import infer_signature
from sklearn.datasets import make_regression
from sklearn.ensemble import RandomForestRegressor


def print_model_info(rm):
    print("--Model--")
    print("name: {}".format(rm.name))
    print("aliases: {}".format(rm.aliases))


def print_model_version_info(mv):
    print("--Model Version--")
    print("Name: {}".format(mv.name))
    print("Version: {}".format(mv.version))
    print("Aliases: {}".format(mv.aliases))


mlflow.set_tracking_uri("sqlite:///mlruns.db")
params = {"n_estimators": 3, "random_state": 42}
name = "RandomForestRegression"
X, y = make_regression(n_features=4, n_informative=2, random_state=0, shuffle=False)
rfr = RandomForestRegressor(**params).fit(X, y)
signature = infer_signature(X, rfr.predict(X))

# Log MLflow entities
with mlflow.start_run() as run:
    mlflow.log_params(params)
    mlflow.sklearn.log_model(rfr, artifact_path="sklearn-model", signature=signature)

# Register model name in the model registry
client = MlflowClient()
client.create_registered_model(name)
model = client.get_registered_model(name)
print_model_info(model)

# Create a new version of the rfr model under the registered model name
model_uri = "runs:/{}/sklearn-model".format(run.info.run_id)
mv = client.create_model_version(name, model_uri, run.info.run_id)
print_model_version_info(mv)

# Set registered model alias
client.set_registered_model_alias(name, "test-alias", mv.version)
print()
print_model_info(model)
print_model_version_info(mv)

# Delete registered model alias
client.delete_registered_model_alias(name, "test-alias")
print()
print_model_info(model)
print_model_version_info(mv)

Output

--Model--
name: RandomForestRegression
aliases: {}
--Model Version--
Name: RandomForestRegression
Version: 1
Aliases: []

--Model--
name: RandomForestRegression
aliases: {"test-alias": "1"}
--Model Version--
Name: RandomForestRegression
Version: 1
Aliases: ["test-alias"]

--Model--
name: RandomForestRegression
aliases: {}
--Model Version--
Name: RandomForestRegression
Version: 1
Aliases: []

delete_registered_model_tag(name: str, key: str) → None[source]

Delete a tag associated with the registered model.

Parameters

name – Registered model name.
key – Registered model tag key.

Example

import mlflow
from mlflow import MlflowClient


def print_registered_models_info(r_models):
    print("--")
    for rm in r_models:
        print(f"name: {rm.name}")
        print(f"tags: {rm.tags}")


mlflow.set_tracking_uri("sqlite:///mlruns.db")
client = MlflowClient()

# Register a couple of models with respective names and tags
for name, tags in [("name1", {"t1": "t1"}), ("name2", {"t2": "t2"})]:
    client.create_registered_model(name, tags)

# Fetch all registered models
print_registered_models_info(client.search_registered_models())
# Delete a tag from model `name2`
client.delete_registered_model_tag("name2", "t2")
print_registered_models_info(client.search_registered_models())

Output

--
name: name1
tags: {'t1': 't1'}
name: name2
tags: {'t2': 't2'}
--
name: name1
tags: {'t1': 't1'}
name: name2
tags: {}

delete_run(run_id: str) → None[source]

Deletes a run with the given ID.

Parameters: run_id – The unique run id to delete.

Example

from mlflow import MlflowClient

# Create a run under the default experiment (whose id is '0').
client = MlflowClient()
experiment_id = "0"
run = client.create_run(experiment_id)
run_id = run.info.run_id
print(f"run_id: {run_id}; lifecycle_stage: {run.info.lifecycle_stage}")
print("--")
client.delete_run(run_id)
del_run = client.get_run(run_id)
print(f"run_id: {run_id}; lifecycle_stage: {del_run.info.lifecycle_stage}")

Output

run_id: a61c7a1851324f7094e8d5014c58c8c8; lifecycle_stage: active
run_id: a61c7a1851324f7094e8d5014c58c8c8; lifecycle_stage: deleted

delete_tag(run_id: str, key: str) → None[source]

Delete a tag from a run. This is irreversible.

Parameters

run_id – String ID of the run.
key – Name of the tag.

Example

from mlflow import MlflowClient


def print_run_info(run):
    print(f"run_id: {run.info.run_id}")
    print(f"Tags: {run.data.tags}")


# Create a run under the default experiment (whose id is '0').
client = MlflowClient()
tags = {"t1": 1, "t2": 2}
experiment_id = "0"
run = client.create_run(experiment_id, tags=tags)
print_run_info(run)
print("--")

# Delete tag and fetch updated info
client.delete_tag(run.info.run_id, "t1")
run = client.get_run(run.info.run_id)
print_run_info(run)

Output

run_id: b7077267a59a45d78cd9be0de4bc41f5
Tags: {'t2': '2', 't1': '1'}
--
run_id: b7077267a59a45d78cd9be0de4bc41f5
Tags: {'t2': '2'}

download_artifacts(run_id: str, path: str, dst_path: Optional[str] = None) → str[source]

Download an artifact file or directory from a run to a local directory if applicable, and return a local path for it.

Parameters

run_id – The run to download artifacts from.
path – Relative source path to the desired artifact.
dst_path – Absolute path of the local filesystem destination directory to which to download the specified artifacts. This directory must already exist. If unspecified, the artifacts will either be downloaded to a new uniquely-named directory on the local filesystem or will be returned directly in the case of the LocalArtifactRepository.

Returns

Local path of desired artifact.

Example

import os
import mlflow
from mlflow import MlflowClient

features = "rooms, zipcode, median_price, school_rating, transport"
with open("features.txt", "w") as f:
    f.write(features)

# Log artifacts
with mlflow.start_run() as run:
    mlflow.log_artifact("features.txt", artifact_path="features")

# Download artifacts
client = MlflowClient()
local_dir = "/tmp/artifact_downloads"
if not os.path.exists(local_dir):
    os.mkdir(local_dir)
local_path = client.download_artifacts(run.info.run_id, "features", local_dir)
print(f"Artifacts downloaded in: {local_path}")
print(f"Artifacts: {os.listdir(local_path)}")

Output

Artifacts downloaded in: /tmp/artifact_downloads/features
Artifacts: ['features.txt']

get_experiment(experiment_id: str) → Experiment [source]

Retrieve an experiment by experiment_id from the backend store

Parameters: experiment_id – The experiment ID returned from create_experiment.
Returns: mlflow.entities.Experiment

Example

from mlflow import MlflowClient

client = MlflowClient()
exp_id = client.create_experiment("Experiment")
experiment = client.get_experiment(exp_id)

# Show experiment info
print(f"Name: {experiment.name}")
print(f"Experiment ID: {experiment.experiment_id}")
print(f"Artifact Location: {experiment.artifact_location}")
print(f"Lifecycle_stage: {experiment.lifecycle_stage}")

Output

Name: Experiment
Experiment ID: 1
Artifact Location: file:///.../mlruns/1
Lifecycle_stage: active

get_experiment_by_name(name: str) → Optional[Experiment][source]

Retrieve an experiment by experiment name from the backend store

Parameters: name – The experiment name, which is case sensitive.
Returns: An instance of mlflow.entities.Experiment if an experiment with the specified name exists, otherwise None.

Example

from mlflow import MlflowClient

# Case-sensitive name
client = MlflowClient()
experiment = client.get_experiment_by_name("Default")
# Show experiment info
print(f"Name: {experiment.name}")
print(f"Experiment ID: {experiment.experiment_id}")
print(f"Artifact Location: {experiment.artifact_location}")
print(f"Lifecycle_stage: {experiment.lifecycle_stage}")

Output

Name: Default
Experiment ID: 0
Artifact Location: file:///.../mlruns/0
Lifecycle_stage: active

get_latest_versions(name: str, stages: Optional[List[str]] = None) → List[ModelVersion][source]

Warning

mlflow.tracking.client.MlflowClient.get_latest_versions is deprecated since 2.9.0. Model registry stages will be removed in a future major release. To learn more about the deprecation of model registry stages, see our migration guide here: https://mlflow.org/docs/2.12.1/model-registry.html#migrating-from-stages

Latest version models for each requests stage. If no stages provided, returns the latest version for each stage.

Parameters

name – Name of the registered model from which to get the latest versions.
stages – List of desired stages. If input list is None, return latest versions for for ALL_STAGES.

Returns

List of mlflow.entities.model_registry.ModelVersion objects.

Example

import mlflow.sklearn
from mlflow import MlflowClient
from mlflow.models import infer_signature
from sklearn.datasets import make_regression
from sklearn.ensemble import RandomForestRegressor


def print_models_info(mv):
    for m in mv:
        print(f"name: {m.name}")
        print(f"latest version: {m.version}")
        print(f"run_id: {m.run_id}")
        print(f"current_stage: {m.current_stage}")


mlflow.set_tracking_uri("sqlite:///mlruns.db")
X, y = make_regression(n_features=4, n_informative=2, random_state=0, shuffle=False)
# Create two runs Log MLflow entities
with mlflow.start_run() as run1:
    params = {"n_estimators": 3, "random_state": 42}
    rfr = RandomForestRegressor(**params).fit(X, y)
    signature = infer_signature(X, rfr.predict(X))
    mlflow.log_params(params)
    mlflow.sklearn.log_model(rfr, artifact_path="sklearn-model", signature=signature)
with mlflow.start_run() as run2:
    params = {"n_estimators": 6, "random_state": 42}
    rfr = RandomForestRegressor(**params).fit(X, y)
    signature = infer_signature(X, rfr.predict(X))
    mlflow.log_params(params)
    mlflow.sklearn.log_model(rfr, artifact_path="sklearn-model", signature=signature)
# Register model name in the model registry
name = "RandomForestRegression"
client = MlflowClient()
client.create_registered_model(name)
# Create a two versions of the rfr model under the registered model name
for run_id in [run1.info.run_id, run2.info.run_id]:
    model_uri = f"runs:/{run_id}/sklearn-model"
    mv = client.create_model_version(name, model_uri, run_id)
    print(f"model version {mv.version} created")
# Fetch latest version; this will be version 2
print("--")
print_models_info(client.get_latest_versions(name, stages=["None"]))

Output

model version 1 created
model version 2 created
--
name: RandomForestRegression
latest version: 2
run_id: 31165664be034dc698c52a4bdeb71663
current_stage: None

get_metric_history(run_id: str, key: str) → List[Metric][source]

Return a list of metric objects corresponding to all values logged for a given metric.

Parameters

run_id – Unique identifier for run.
key – Metric name within the run.

Returns

A list of mlflow.entities.Metric entities if logged, else empty list.

Example

from mlflow import MlflowClient


def print_metric_info(history):
    for m in history:
        print(f"name: {m.key}")
        print(f"value: {m.value}")
        print(f"step: {m.step}")
        print(f"timestamp: {m.timestamp}")
        print("--")


# Create a run under the default experiment (whose id is "0"). Since this is low-level
# CRUD operation, the method will create a run. To end the run, you'll have
# to explicitly end it.
client = MlflowClient()
experiment_id = "0"
run = client.create_run(experiment_id)
print(f"run_id: {run.info.run_id}")
print("--")

# Log couple of metrics, update their initial value, and fetch each
# logged metrics' history.
for k, v in [("m1", 1.5), ("m2", 2.5)]:
    client.log_metric(run.info.run_id, k, v, step=0)
    client.log_metric(run.info.run_id, k, v + 1, step=1)
    print_metric_info(client.get_metric_history(run.info.run_id, k))
client.set_terminated(run.info.run_id)

Output

run_id: c360d15714994c388b504fe09ea3c234
--
name: m1
value: 1.5
step: 0
timestamp: 1603423788607
--
name: m1
value: 2.5
step: 1
timestamp: 1603423788608
--
name: m2
value: 2.5
step: 0
timestamp: 1603423788609
--
name: m2
value: 3.5
step: 1
timestamp: 1603423788610
--

get_model_version(name: str, version: str) → ModelVersion [source]

Converts the docstring args and returns to google style.

Parameters

name – Name of the containing registered model.
version – Version number as an integer of the model version.

Returns

A single mlflow.entities.model_registry.ModelVersion object.

Example

import mlflow.sklearn
from mlflow import MlflowClient
from mlflow.models import infer_signature
from sklearn.datasets import make_regression
from sklearn.ensemble import RandomForestRegressor

X, y = make_regression(n_features=4, n_informative=2, random_state=0, shuffle=False)

# Create two runs Log MLflow entities
with mlflow.start_run() as run1:
    params = {"n_estimators": 3, "random_state": 42}
    rfr = RandomForestRegressor(**params).fit(X, y)
    signature = infer_signature(X, rfr.predict(X))
    mlflow.log_params(params)
    mlflow.sklearn.log_model(rfr, artifact_path="sklearn-model", signature=signature)

with mlflow.start_run() as run2:
    params = {"n_estimators": 6, "random_state": 42}
    rfr = RandomForestRegressor(**params).fit(X, y)
    signature = infer_signature(X, rfr.predict(X))
    mlflow.log_params(params)
    mlflow.sklearn.log_model(rfr, artifact_path="sklearn-model", signature=signature)

# Register model name in the model registry
name = "RandomForestRegression"
client = MlflowClient()
client.create_registered_model(name)

# Create a two versions of the rfr model under the registered model name
for run_id in [run1.info.run_id, run2.info.run_id]:
    model_uri = f"runs:/{run_id}/sklearn-model"
    mv = client.create_model_version(name, model_uri, run_id)
    print(f"model version {mv.version} created")
print("--")

# Fetch the last version; this will be version 2
mv = client.get_model_version(name, mv.version)
print(f"Name: {mv.name}")
print(f"Version: {mv.version}")

Output

model version 1 created
model version 2 created
--
Name: RandomForestRegression
Version: 2

get_model_version_by_alias(name: str, alias: str) → ModelVersion [source]

Get the model version instance by name and alias.

Parameters

name – Registered model name.
alias – Name of the alias.

Returns

A single mlflow.entities.model_registry.ModelVersion object.

Example

import mlflow
from mlflow import MlflowClient
from mlflow.models import infer_signature
from sklearn.datasets import make_regression
from sklearn.ensemble import RandomForestRegressor


def print_model_info(rm):
    print("--Model--")
    print("name: {}".format(rm.name))
    print("aliases: {}".format(rm.aliases))


def print_model_version_info(mv):
    print("--Model Version--")
    print("Name: {}".format(mv.name))
    print("Version: {}".format(mv.version))
    print("Aliases: {}".format(mv.aliases))


mlflow.set_tracking_uri("sqlite:///mlruns.db")
params = {"n_estimators": 3, "random_state": 42}
name = "RandomForestRegression"
X, y = make_regression(n_features=4, n_informative=2, random_state=0, shuffle=False)
rfr = RandomForestRegressor(**params).fit(X, y)
signature = infer_signature(X, rfr.predict(X))
# Log MLflow entities
with mlflow.start_run() as run:
    mlflow.log_params(params)
    mlflow.sklearn.log_model(rfr, artifact_path="sklearn-model", signature=signature)
# Register model name in the model registry
client = MlflowClient()
client.create_registered_model(name)
model = client.get_registered_model(name)
print_model_info(model)
# Create a new version of the rfr model under the registered model name
model_uri = "runs:/{}/sklearn-model".format(run.info.run_id)
mv = client.create_model_version(name, model_uri, run.info.run_id)
print_model_version_info(mv)
# Set registered model alias
client.set_registered_model_alias(name, "test-alias", mv.version)
print()
print_model_info(model)
print_model_version_info(mv)
# Get model version by alias
alias_mv = client.get_model_version_by_alias(name, "test-alias")
print()
print_model_version_info(alias_mv)

Output

--Model--
name: RandomForestRegression
aliases: {}
--Model Version--
Name: RandomForestRegression
Version: 1
Aliases: []
--Model--
name: RandomForestRegression
aliases: {"test-alias": "1"}
--Model Version--
Name: RandomForestRegression
Version: 1
Aliases: ["test-alias"]
--Model Version--
Name: RandomForestRegression
Version: 1
Aliases: ["test-alias"]

get_model_version_download_uri(name: str, version: str) → str[source]

Get the download location in Model Registry for this model version.

Parameters

name – Name of the containing registered model.
version – Version number as an integer of the model version.

Returns

A single URI location that allows reads for downloading.

import mlflow.sklearn
from mlflow import MlflowClient
from mlflow.models import infer_signature
from sklearn.datasets import make_regression
from sklearn.ensemble import RandomForestRegressor

mlflow.set_tracking_uri("sqlite:///mlruns.db")
params = {"n_estimators": 3, "random_state": 42}
name = "RandomForestRegression"
X, y = make_regression(n_features=4, n_informative=2, random_state=0, shuffle=False)
rfr = RandomForestRegressor(**params).fit(X, y)
signature = infer_signature(X, rfr.predict(X))

# Log MLflow entities
with mlflow.start_run() as run:
    mlflow.log_params(params)
    mlflow.sklearn.log_model(rfr, artifact_path="sklearn-model", signature=signature)

# Register model name in the model registry
client = MlflowClient()
client.create_registered_model(name)

# Create a new version of the rfr model under the registered model name
model_uri = f"runs:/{run.info.run_id}/sklearn-model"
mv = client.create_model_version(name, model_uri, run.info.run_id)
artifact_uri = client.get_model_version_download_uri(name, mv.version)
print(f"Download URI: {artifact_uri}")

Download URI: runs:/027d7bbe81924c5a82b3e4ce979fcab7/sklearn-model

get_model_version_stages(name: str, version: str) → List[str][source]

Warning

mlflow.tracking.client.MlflowClient.get_model_version_stages is deprecated since 2.9.0. Model registry stages will be removed in a future major release. To learn more about the deprecation of model registry stages, see our migration guide here: https://mlflow.org/docs/2.12.1/model-registry.html#migrating-from-stages

This is a docstring. Here is info.

Returns: A list of valid stages.

Example

import mlflow.sklearn
from mlflow import MlflowClient
from mlflow.models import infer_signature
from sklearn.datasets import make_regression
from sklearn.ensemble import RandomForestRegressor

mlflow.set_tracking_uri("sqlite:///mlruns.db")
params = {"n_estimators": 3, "random_state": 42}
name = "RandomForestRegression"
X, y = make_regression(n_features=4, n_informative=2, random_state=0, shuffle=False)
rfr = RandomForestRegressor(**params).fit(X, y)
signature = infer_signature(X, rfr.predict(X))

# Log MLflow entities
with mlflow.start_run() as run:
    mlflow.log_params(params)
    mlflow.sklearn.log_model(rfr, artifact_path="sklearn-model", signature=signature)

# Register model name in the model registry
client = MlflowClient()
client.create_registered_model(name)

# Create a new version of the rfr model under the registered model name
# fetch valid stages
model_uri = f"runs:/{run.info.run_id}/models/sklearn-model"
mv = client.create_model_version(name, model_uri, run.info.run_id)
stages = client.get_model_version_stages(name, mv.version)
print(f"Model list of valid stages: {stages}")

Output

Model list of valid stages: ['None', 'Staging', 'Production', 'Archived']

get_parent_run(run_id: str) → Optional[Run][source]

Gets the parent run for the given run id if one exists.

Parameters: run_id – Unique identifier for the child run.
Returns: A single mlflow.entities.Run object, if the parent run exists. Otherwise, returns None.

Example

import mlflow
from mlflow import MlflowClient

# Create nested runs
with mlflow.start_run():
    with mlflow.start_run(nested=True) as child_run:
        child_run_id = child_run.info.run_id

client = MlflowClient()
parent_run = client.get_parent_run(child_run_id)

print(f"child_run_id: {child_run_id}")
print(f"parent_run_id: {parent_run.info.run_id}")

Output

child_run_id: 7d175204675e40328e46d9a6a5a7ee6a
parent_run_id: 8979459433a24a52ab3be87a229a9cdf

get_registered_model(name: str) → RegisteredModel [source]

Get a registered model.

Parameters: name – Name of the registered model to get.
Returns: A single mlflow.entities.model_registry.RegisteredModel object.

Example

import mlflow
from mlflow import MlflowClient


def print_model_info(rm):
    print("--")
    print(f"name: {rm.name}")
    print(f"tags: {rm.tags}")
    print(f"description: {rm.description}")


name = "SocialMediaTextAnalyzer"
tags = {"nlp.framework": "Spark NLP"}
desc = "This sentiment analysis model classifies the tone-happy, sad, angry."
mlflow.set_tracking_uri("sqlite:///mlruns.db")
client = MlflowClient()
# Create and fetch the registered model
client.create_registered_model(name, tags, desc)
model = client.get_registered_model(name)
print_model_info(model)

Output

--
name: SocialMediaTextAnalyzer
tags: {'nlp.framework': 'Spark NLP'}
description: This sentiment analysis model classifies the tone-happy, sad, angry.

get_run(run_id: str) → Run [source]

Fetch the run from backend store. The resulting Run contains a collection of run metadata – RunInfo, as well as a collection of run parameters, tags, and metrics – RunData. It also contains a collection of run inputs (experimental), including information about datasets used by the run – RunInputs. In the case where multiple metrics with the same key are logged for the run, the RunData contains the most recently logged value at the largest step for each metric.

Parameters: run_id – Unique identifier for the run.
Returns: A single mlflow.entities.Run object, if the run exists. Otherwise, raises an exception.

Example

import mlflow
from mlflow import MlflowClient

with mlflow.start_run() as run:
    mlflow.log_param("p", 0)

# The run has finished since we have exited the with block
# Fetch the run
client = MlflowClient()
run = client.get_run(run.info.run_id)
print(f"run_id: {run.info.run_id}")
print(f"params: {run.data.params}")
print(f"status: {run.info.status}")

Output

run_id: e36b42c587a1413ead7c3b6764120618
params: {'p': '0'}
status: FINISHED

list_artifacts(run_id: str, path=None) → List[FileInfo][source]

List the artifacts for a run.

Parameters

run_id – The run to list artifacts from.
path – The run’s relative artifact path to list from. By default it is set to None or the root artifact path.

Returns

List of mlflow.entities.FileInfo

Example

from mlflow import MlflowClient


def print_artifact_info(artifact):
    print(f"artifact: {artifact.path}")
    print(f"is_dir: {artifact.is_dir}")
    print(f"size: {artifact.file_size}")


features = "rooms zipcode, median_price, school_rating, transport"
labels = "price"

# Create a run under the default experiment (whose id is '0').
client = MlflowClient()
experiment_id = "0"
run = client.create_run(experiment_id)

# Create some artifacts and log under the above run
for file, content in [("features", features), ("labels", labels)]:
    with open(f"{file}.txt", "w") as f:
        f.write(content)
    client.log_artifact(run.info.run_id, f"{file}.txt")

# Fetch the logged artifacts
artifacts = client.list_artifacts(run.info.run_id)
for artifact in artifacts:
    print_artifact_info(artifact)
client.set_terminated(run.info.run_id)

Output

artifact: features.txt
is_dir: False
size: 53
artifact: labels.txt
is_dir: False
size: 5

load_table(experiment_id: str, artifact_file: str, run_ids: Optional[List[str]] = None, extra_columns: Optional[List[str]] = None) → pandas.DataFrame[source]

Note

Experimental: This function may change or be removed in a future release without warning.

Load a table from MLflow Tracking as a pandas.DataFrame. The table is loaded from the specified artifact_file in the specified run_ids. The extra_columns are columns that are not in the table but are augmented with run information and added to the DataFrame.

Parameters

experiment_id – The experiment ID to load the table from.
artifact_file – The run-relative artifact file path in posixpath format to which table to load (e.g. “dir/file.json”).
run_ids – Optional list of run_ids to load the table from. If no run_ids are specified, the table is loaded from all runs in the current experiment.
extra_columns – Optional list of extra columns to add to the returned DataFrame For example, if extra_columns=[“run_id”], then the returned DataFrame will have a column named run_id.

Returns

pandas.DataFrame containing the loaded table if the artifact exists: or else throw a MlflowException.

Example with passing run_ids

import mlflow
import pandas as pd
from mlflow import MlflowClient

table_dict = {
    "inputs": ["What is MLflow?", "What is Databricks?"],
    "outputs": ["MLflow is ...", "Databricks is ..."],
    "toxicity": [0.0, 0.0],
}
df = pd.DataFrame.from_dict(table_dict)
client = MlflowClient()
run = client.create_run(experiment_id="0")
client.log_table(run.info.run_id, data=df, artifact_file="qabot_eval_results.json")
loaded_table = client.load_table(
    experiment_id="0",
    artifact_file="qabot_eval_results.json",
    run_ids=[
        run.info.run_id,
    ],
    # Append a column containing the associated run ID for each row
    extra_columns=["run_id"],
)

Example with passing no run_ids

# Loads the table with the specified name for all runs in the given
# experiment and joins them together
import mlflow
import pandas as pd
from mlflow import MlflowClient

table_dict = {
    "inputs": ["What is MLflow?", "What is Databricks?"],
    "outputs": ["MLflow is ...", "Databricks is ..."],
    "toxicity": [0.0, 0.0],
}
df = pd.DataFrame.from_dict(table_dict)
client = MlflowClient()
run = client.create_run(experiment_id="0")
client.log_table(run.info.run_id, data=df, artifact_file="qabot_eval_results.json")
loaded_table = client.load_table(
    experiment_id="0",
    artifact_file="qabot_eval_results.json",
    # Append the run ID and the parent run ID to the table
    extra_columns=["run_id"],
)

log_artifact(run_id, local_path, artifact_path=None) → None[source]

Write a local file or directory to the remote artifact_uri.

Parameters

local_path – Path to the file or directory to write.
artifact_path – If provided, the directory in artifact_uri to write to.

Example

import tempfile
from pathlib import Path

from mlflow import MlflowClient

# Create a run under the default experiment (whose id is '0').
client = MlflowClient()
experiment_id = "0"
run = client.create_run(experiment_id)

# log and fetch the artifact
with tempfile.TemporaryDirectory() as tmp_dir:
    path = Path(tmp_dir, "features.txt")
    path.write_text(features)
    client.log_artifact(run.info.run_id, path)

artifacts = client.list_artifacts(run.info.run_id)
for artifact in artifacts:
    print(f"artifact: {artifact.path}")
    print(f"is_dir: {artifact.is_dir}")
client.set_terminated(run.info.run_id)

Output

artifact: features.txt
is_dir: False

log_artifacts(run_id: str, local_dir: str, artifact_path: Optional[str] = None) → None[source]

Write a directory of files to the remote artifact_uri.

Parameters

local_dir – Path to the directory of files to write.
artifact_path – If provided, the directory in artifact_uri to write to.

Example

import json
import tempfile
from pathlib import Path

# Create some artifacts data to preserve
features = "rooms, zipcode, median_price, school_rating, transport"
data = {"state": "TX", "Available": 25, "Type": "Detached"}
with tempfile.TemporaryDirectory() as tmp_dir:
    tmp_dir = Path(tmp_dir)
    with (tmp_dir / "data.json").open("w") as f:
        json.dump(data, f, indent=2)
    with (tmp_dir / "features.json").open("w") as f:
        f.write(features)

    # Create a run under the default experiment (whose id is '0'), and log
    # all files in "data" to root artifact_uri/states
    client = MlflowClient()
    experiment_id = "0"
    run = client.create_run(experiment_id)
    client.log_artifacts(run.info.run_id, tmp_dir, artifact_path="states")

artifacts = client.list_artifacts(run.info.run_id)
for artifact in artifacts:
    print(f"artifact: {artifact.path}")
    print(f"is_dir: {artifact.is_dir}")
client.set_terminated(run.info.run_id)

Output

artifact: states
is_dir: True

log_batch(run_id: str, metrics: Sequence[Metric] = (), params: Sequence[Param] = (), tags: Sequence[RunTag] = (), synchronous: bool = True) → Optional[mlflow.utils.async_logging.run_operations.RunOperations][source]

Log multiple metrics, params, and/or tags.

Parameters

run_id – String ID of the run
metrics – If provided, List of Metric(key, value, timestamp) instances.
params – If provided, List of Param(key, value) instances.
tags – If provided, List of RunTag(key, value) instances.
synchronous – Experimental If True, blocks until the metrics/tags/params are logged successfully. If False, logs the metrics/tags/params asynchronously and returns a future representing the logging operation.

Raises

mlflow.MlflowException – If any errors occur.

Returns

When synchronous=True, returns None. When synchronous=False, returns an mlflow.utils.async_logging.run_operations.RunOperations instance that represents future for logging operation.

Example

import time

from mlflow import MlflowClient
from mlflow.entities import Metric, Param, RunTag


def print_run_info(r):
    print(f"run_id: {r.info.run_id}")
    print(f"params: {r.data.params}")
    print(f"metrics: {r.data.metrics}")
    print(f"tags: {r.data.tags}")
    print(f"status: {r.info.status}")


# Create MLflow entities and a run under the default experiment (whose id is '0').
timestamp = int(time.time() * 1000)
metrics = [Metric("m", 1.5, timestamp, 1)]
params = [Param("p", "p")]
tags = [RunTag("t", "t")]
experiment_id = "0"
client = MlflowClient()
run = client.create_run(experiment_id)

# Log entities, terminate the run, and fetch run status
client.log_batch(run.info.run_id, metrics=metrics, params=params, tags=tags)
client.set_terminated(run.info.run_id)
run = client.get_run(run.info.run_id)
print_run_info(run)

# To log metric in async fashion
client.log_metric(run.info.run_id, "m", 1.5, synchronous=False)

Output

run_id: ef0247fa3205410595acc0f30f620871
params: {'p': 'p'}
metrics: {'m': 1.5}
tags: {'t': 't'}
status: FINISHED

log_dict(run_id: str, dictionary: Dict[str, Any], artifact_file: str) → None[source]

Log a JSON/YAML-serializable object (e.g. dict) as an artifact. The serialization format (JSON or YAML) is automatically inferred from the extension of artifact_file. If the file extension doesn’t exist or match any of [“.json”, “.yml”, “.yaml”], JSON format is used.

Parameters

run_id – String ID of the run.
dictionary – Dictionary to log.
artifact_file – The run-relative artifact file path in posixpath format to which the dictionary is saved (e.g. “dir/data.json”).

Example

from mlflow import MlflowClient

client = MlflowClient()
run = client.create_run(experiment_id="0")
run_id = run.info.run_id

dictionary = {"k": "v"}

# Log a dictionary as a JSON file under the run's root artifact directory
client.log_dict(run_id, dictionary, "data.json")

# Log a dictionary as a YAML file in a subdirectory of the run's root artifact directory
client.log_dict(run_id, dictionary, "dir/data.yml")

# If the file extension doesn't exist or match any of [".json", ".yaml", ".yml"],
# JSON format is used.
mlflow.log_dict(run_id, dictionary, "data")
mlflow.log_dict(run_id, dictionary, "data.txt")

log_figure(run_id: str, figure: Union[matplotlib.figure.Figure, plotly.graph_objects.Figure], artifact_file: str, *, save_kwargs: Optional[Dict[str, Any]] = None) → None[source]

Log a figure as an artifact. The following figure objects are supported:

Parameters

run_id – String ID of the run.
figure – Figure to log.
artifact_file – The run-relative artifact file path in posixpath format to which the figure is saved (e.g. “dir/file.png”).
save_kwargs – Additional keyword arguments passed to the method that saves the figure.

Matplotlib Example

import mlflow
import matplotlib.pyplot as plt

fig, ax = plt.subplots()
ax.plot([0, 1], [2, 3])

run = client.create_run(experiment_id="0")
client.log_figure(run.info.run_id, fig, "figure.png")

Plotly Example

import mlflow
from plotly import graph_objects as go

fig = go.Figure(go.Scatter(x=[0, 1], y=[2, 3]))

run = client.create_run(experiment_id="0")
client.log_figure(run.info.run_id, fig, "figure.html")

log_image(run_id: str, image: Union[numpy.ndarray, PIL.Image.Image, mlflow.Image], artifact_file: Optional[str] = None, key: Optional[str] = None, step: Optional[int] = None, timestamp: Optional[int] = None) → None[source]

Logs an image in MLflow, supporting two use cases:

Time-stepped image logging:
Ideal for tracking changes or progressions through iterative processes (e.g., during model training phases).
- Usage: log_image(image, key=key, step=step, timestamp=timestamp)
Artifact file image logging:
Best suited for static image logging where the image is saved directly as a file artifact.
- Usage: log_image(image, artifact_file)

The following image formats are supported:

mlflow.Image: An MLflow wrapper around PIL image for convenient image logging.

Numpy array support

data types:
- bool (useful for logging image masks)
- integer [0, 255]
- unsigned integer [0, 255]
- float [0.0, 1.0]
Warning
- Out-of-range integer values will raise ValueError.
- Out-of-range float values will raise ValueError.
shape (H: height, W: width):
- H x W (Grayscale)
- H x W x 1 (Grayscale)
- H x W x 3 (an RGB channel order is assumed)
- H x W x 4 (an RGBA channel order is assumed)

Parameters

run_id – String ID of run.
image – The image object to be logged.
artifact_file – Specifies the path, in POSIX format, where the image will be stored as an artifact relative to the run’s root directory (for example, “dir/image.png”). This parameter is kept for backward compatibility and should not be used together with key, step, or timestamp.
key – Image name for time-stepped image logging. This string may only contain alphanumerics, underscores (_), dashes (-), periods (.), spaces ( ), and slashes (/).
step – Integer training step (iteration) at which the image was saved. Defaults to 0.
timestamp – Time when this image was saved. Defaults to the current system time.

Time-stepped image logging numpy example

import mlflow
import numpy as np

image = np.random.randint(0, 256, size=(100, 100, 3), dtype=np.uint8)
with mlflow.start_run() as run:
    client = mlflow.MlflowClient()
    client.log_image(run.info.run_id, image, key="dogs", step=3)

Time-stepped image logging pillow example

import mlflow
from PIL import Image

image = Image.new("RGB", (100, 100))
with mlflow.start_run() as run:
    client = mlflow.MlflowClient()
    client.log_image(run.info.run_id, image, key="dogs", step=3)

Time-stepped image logging with mlflow.Image example

import mlflow
from PIL import Image

# Saving an image to retrieve later.
Image.new("RGB", (100, 100)).save("image.png")

image = mlflow.Image("image.png")
with mlflow.start_run() as run:
    client = mlflow.MlflowClient()
    client.log_image(run.info.run_id, image, key="dogs", step=3)

Legacy artifact file image logging numpy example

import mlflow
import numpy as np

image = np.random.randint(0, 256, size=(100, 100, 3), dtype=np.uint8)
with mlflow.start_run() as run:
    client = mlflow.MlflowClient()
    client.log_image(run.info.run_id, image, "image.png")

Legacy artifact file image logging pillow example

import mlflow
from PIL import Image

image = Image.new("RGB", (100, 100))
with mlflow.start_run() as run:
    client = mlflow.MlflowClient()
    client.log_image(run.info.run_id, image, "image.png")

log_inputs(run_id: str, datasets: Optional[Sequence[DatasetInput]] = None) → None[source]

Log one or more dataset inputs to a run.

Parameters

run_id – String ID of the run.
datasets – List of mlflow.entities.DatasetInput instances to log.

Raises

mlflow.MlflowException – If any errors occur.

log_metric(run_id: str, key: str, value: float, timestamp: Optional[int] = None, step: Optional[int] = None, synchronous: bool = True) → Optional[mlflow.utils.async_logging.run_operations.RunOperations][source]

Log a metric against the run ID.

Parameters

run_id – The run id to which the metric should be logged.
key – Metric name. This string may only contain alphanumerics, underscores (_), dashes (-), periods (.), spaces ( ), and slashes (/). All backend stores will support keys up to length 250, but some may support larger keys.
value – Metric value. Note that some special values such as +/- Infinity may be replaced by other values depending on the store. For example, the SQLAlchemy store replaces +/- Inf with max / min float values. All backend stores will support values up to length 5000, but some may support larger values.
timestamp – Time when this metric was calculated. Defaults to the current system time.
step – Integer training step (iteration) at which was the metric calculated. Defaults to 0.
synchronous – Experimental If True, blocks until the metric is logged successfully. If False, logs the metric asynchronously and returns a future representing the logging operation.

Returns

When synchronous=True, returns None. When synchronous=False, returns an mlflow.utils.async_logging.run_operations.RunOperations instance that represents future for logging operation.

Example

from mlflow import MlflowClient


def print_run_info(r):
    print(f"run_id: {r.info.run_id}")
    print(f"metrics: {r.data.metrics}")
    print(f"status: {r.info.status}")


# Create a run under the default experiment (whose id is '0').
# Since these are low-level CRUD operations, this method will create a run.
# To end the run, you'll have to explicitly end it.
client = MlflowClient()
experiment_id = "0"
run = client.create_run(experiment_id)
print_run_info(run)
print("--")

# Log the metric. Unlike mlflow.log_metric this method
# does not start a run if one does not exist. It will log
# the metric for the run id in the backend store.
client.log_metric(run.info.run_id, "m", 1.5)
client.set_terminated(run.info.run_id)
run = client.get_run(run.info.run_id)
print_run_info(run)

# To log metric in async fashion
client.log_metric(run.info.run_id, "m", 1.5, synchronous=False)

Output

run_id: 95e79843cb2c463187043d9065185e24
metrics: {}
status: RUNNING
--
run_id: 95e79843cb2c463187043d9065185e24
metrics: {'m': 1.5}
status: FINISHED

log_param(run_id: str, key: str, value: Any, synchronous: Optional[bool] = True) → Any[source]

Log a parameter (e.g. model hyperparameter) against the run ID.

Parameters

run_id – The run id to which the param should be logged.
key – Parameter name. This string may only contain alphanumerics, underscores (_), dashes (-), periods (.), spaces ( ), and slashes (/). All backend stores support keys up to length 250, but some may support larger keys.
value – Parameter value, but will be string-ified if not. All built-in backend stores support values up to length 6000, but some may support larger values.
synchronous – Experimental If True, blocks until the parameter is logged successfully. If False, logs the parameter asynchronously and returns a future representing the logging operation.

Returns

When synchronous=True, returns parameter value. When synchronous=False, returns an mlflow.utils.async_logging.run_operations.RunOperations instance that represents future for logging operation.

Example

from mlflow import MlflowClient


def print_run_info(r):
    print(f"run_id: {r.info.run_id}")
    print(f"params: {r.data.params}")
    print(f"status: {r.info.status}")


# Create a run under the default experiment (whose id is '0').
# Since these are low-level CRUD operations, this method will create a run.
# To end the run, you'll have to explicitly end it.
client = MlflowClient()
experiment_id = "0"
run = client.create_run(experiment_id)
print_run_info(run)
print("--")
# Log the parameter. Unlike mlflow.log_param this method
# does not start a run if one does not exist. It will log
# the parameter in the backend store
p_value = client.log_param(run.info.run_id, "p", 1)
assert p_value == 1
client.set_terminated(run.info.run_id)
run = client.get_run(run.info.run_id)
print_run_info(run)

Output

run_id: e649e49c7b504be48ee3ae33c0e76c93
params: {}
status: RUNNING
--
run_id: e649e49c7b504be48ee3ae33c0e76c93
params: {'p': '1'}
status: FINISHED

log_table(run_id: str, data: Union[Dict[str, Any], pandas.DataFrame], artifact_file: str) → None[source]

Note

Experimental: This function may change or be removed in a future release without warning.

Log a table to MLflow Tracking as a JSON artifact. If the artifact_file already exists in the run, the data would be appended to the existing artifact_file.

Parameters

run_id – String ID of the run.
data – Dictionary or pandas.DataFrame to log.
artifact_file – The run-relative artifact file path in posixpath format to which the table is saved (e.g. “dir/file.json”).

Dictionary Example

import mlflow
from mlflow import MlflowClient

table_dict = {
    "inputs": ["What is MLflow?", "What is Databricks?"],
    "outputs": ["MLflow is ...", "Databricks is ..."],
    "toxicity": [0.0, 0.0],
}
with mlflow.start_run() as run:
    client = MlflowClient()
    client.log_table(
        run.info.run_id, data=table_dict, artifact_file="qabot_eval_results.json"
    )

Pandas DF Example

import mlflow
import pandas as pd
from mlflow import MlflowClient

table_dict = {
    "inputs": ["What is MLflow?", "What is Databricks?"],
    "outputs": ["MLflow is ...", "Databricks is ..."],
    "toxicity": [0.0, 0.0],
}
df = pd.DataFrame.from_dict(table_dict)
with mlflow.start_run() as run:
    client = MlflowClient()
    client.log_table(run.info.run_id, data=df, artifact_file="qabot_eval_results.json")

Image Column Example

import mlflow
import pandas as pd
from mlflow import MlflowClient

image = mlflow.Image([[1, 2, 3]])
table_dict = {
    "inputs": ["Show me a dog", "Show me a cat"],
    "outputs": [image, image],
}
df = pd.DataFrame.from_dict(table_dict)
with mlflow.start_run() as run:
    client = MlflowClient()
    client.log_table(run.info.run_id, data=df, artifact_file="image_gen.json")

log_text(run_id: str, text: str, artifact_file: str) → None[source]

Log text as an artifact.

Parameters

run_id – String ID of the run.
text – String containing text to log.
artifact_file – The run-relative artifact file path in posixpath format to which the text is saved (e.g. “dir/file.txt”).

Example

from mlflow import MlflowClient

client = MlflowClient()
run = client.create_run(experiment_id="0")

# Log text to a file under the run's root artifact directory
client.log_text(run.info.run_id, "text1", "file1.txt")

# Log text in a subdirectory of the run's root artifact directory
client.log_text(run.info.run_id, "text2", "dir/file2.txt")

# Log HTML text
client.log_text(run.info.run_id, "<h1>header</h1>", "index.html")

rename_experiment(experiment_id: str, new_name: str) → None[source]

Update an experiment’s name. The new name must be unique.

Parameters: experiment_id – The experiment ID returned from create_experiment.

Example

from mlflow import MlflowClient


def print_experiment_info(experiment):
    print(f"Name: {experiment.name}")
    print(f"Experiment_id: {experiment.experiment_id}")
    print(f"Lifecycle_stage: {experiment.lifecycle_stage}")


# Create an experiment with a name that is unique and case sensitive
client = MlflowClient()
experiment_id = client.create_experiment("Social NLP Experiments")

# Fetch experiment metadata information
experiment = client.get_experiment(experiment_id)
print_experiment_info(experiment)
print("--")

# Rename and fetch experiment metadata information
client.rename_experiment(experiment_id, "Social Media NLP Experiments")
experiment = client.get_experiment(experiment_id)
print_experiment_info(experiment)

Output

Name: Social NLP Experiments
Experiment_id: 1
Lifecycle_stage: active
--
Name: Social Media NLP Experiments
Experiment_id: 1
Lifecycle_stage: active

rename_registered_model(name: str, new_name: str) → RegisteredModel [source]

Update registered model name.

Parameters

name – Name of the registered model to update.
new_name – New proposed name for the registered model.

Returns

A single updated mlflow.entities.model_registry.RegisteredModel object.

Example

import mlflow
from mlflow import MlflowClient


def print_registered_model_info(rm):
    print(f"name: {rm.name}")
    print(f"tags: {rm.tags}")
    print(f"description: {rm.description}")


name = "SocialTextAnalyzer"
tags = {"nlp.framework": "Spark NLP"}
desc = "This sentiment analysis model classifies the tone-happy, sad, angry."

# create a new registered model name
mlflow.set_tracking_uri("sqlite:///mlruns.db")
client = MlflowClient()
client.create_registered_model(name, tags, desc)
print_registered_model_info(client.get_registered_model(name))
print("--")

# rename the model
new_name = "SocialMediaTextAnalyzer"
client.rename_registered_model(name, new_name)
print_registered_model_info(client.get_registered_model(new_name))

Output

name: SocialTextAnalyzer
tags: {'nlp.framework': 'Spark NLP'}
description: This sentiment analysis model classifies the tone-happy, sad, angry.
--
name: SocialMediaTextAnalyzer
tags: {'nlp.framework': 'Spark NLP'}
description: This sentiment analysis model classifies the tone-happy, sad, angry.

restore_experiment(experiment_id: str) → None[source]

Restore a deleted experiment unless permanently deleted.

Parameters: experiment_id – The experiment ID returned from create_experiment.

Example

from mlflow import MlflowClient


def print_experiment_info(experiment):
    print(f"Name: {experiment.name}")
    print(f"Experiment Id: {experiment.experiment_id}")
    print(f"Lifecycle_stage: {experiment.lifecycle_stage}")


# Create and delete an experiment
client = MlflowClient()
experiment_id = client.create_experiment("New Experiment")
client.delete_experiment(experiment_id)

# Examine the deleted experiment details.
experiment = client.get_experiment(experiment_id)
print_experiment_info(experiment)
print("--")

# Restore the experiment and fetch its info
client.restore_experiment(experiment_id)
experiment = client.get_experiment(experiment_id)
print_experiment_info(experiment)

Output

Name: New Experiment
Experiment Id: 1
Lifecycle_stage: deleted
--
Name: New Experiment
Experiment Id: 1
Lifecycle_stage: active

restore_run(run_id: str) → None[source]

Restores a deleted run with the given ID.

Parameters: run_id – The unique run id to restore.

Example

from mlflow import MlflowClient

# Create a run under the default experiment (whose id is '0').
client = MlflowClient()
experiment_id = "0"
run = client.create_run(experiment_id)
run_id = run.info.run_id
print(f"run_id: {run_id}; lifecycle_stage: {run.info.lifecycle_stage}")
client.delete_run(run_id)
del_run = client.get_run(run_id)
print(f"run_id: {run_id}; lifecycle_stage: {del_run.info.lifecycle_stage}")
client.restore_run(run_id)
rest_run = client.get_run(run_id)
print(f"run_id: {run_id}; lifecycle_stage: {rest_run.info.lifecycle_stage}")

Output

run_id: 7bc59754d7e74534a7917d62f2873ac0; lifecycle_stage: active
run_id: 7bc59754d7e74534a7917d62f2873ac0; lifecycle_stage: deleted
run_id: 7bc59754d7e74534a7917d62f2873ac0; lifecycle_stage: active

search_experiments(view_type: int = 1, max_results: Optional[int] = 1000, filter_string: Optional[str] = None, order_by: Optional[List[str]] = None, page_token=None) → PagedList[Experiment][source]

Search for experiments that match the specified search query.

Parameters

view_type – One of enum values ACTIVE_ONLY, DELETED_ONLY, or ALL defined in mlflow.entities.ViewType.
max_results – Maximum number of experiments desired. Certain server backend may apply its own limit.
filter_string –
Filter query string (e.g., "name = 'my_experiment'"), defaults to searching for all experiments. The following identifiers, comparators, and logical operators are supported.
Identifiers
- name: Experiment name
- creation_time: Experiment creation time
- last_update_time: Experiment last update time
- tags.<tag_key>: Experiment tag. If tag_key contains spaces, it must be wrapped with backticks (e.g., "tags.`extra key`").
Comparators for string attributes and tags
- =: Equal to
- !=: Not equal to
- LIKE: Case-sensitive pattern match
- ILIKE: Case-insensitive pattern match
Comparators for numeric attributes
- =: Equal to
- !=: Not equal to
- <: Less than
- <=: Less than or equal to
- >: Greater than
- >=: Greater than or equal to
Logical operators
- AND: Combines two sub-queries and returns True if both of them are True.
order_by –
List of columns to order by. The order_by column can contain an optional DESC or ASC value (e.g., "name DESC"). The default ordering is ASC, so "name" is equivalent to "name ASC". If unspecified, defaults to ["last_update_time DESC"], which lists experiments updated most recently first. The following fields are supported:
- experiment_id: Experiment ID
- name: Experiment name
- creation_time: Experiment creation time
- last_update_time: Experiment last update time
page_token – Token specifying the next page of results. It should be obtained from a search_experiments call.

Returns

A PagedList of Experiment objects. The pagination token for the next page can be obtained via the token attribute of the object.

Example

import mlflow


def assert_experiment_names_equal(experiments, expected_names):
    actual_names = [e.name for e in experiments if e.name != "Default"]
    assert actual_names == expected_names, (actual_names, expected_names)


mlflow.set_tracking_uri("sqlite:///:memory:")
client = mlflow.MlflowClient()

# Create experiments
for name, tags in [
    ("a", None),
    ("b", None),
    ("ab", {"k": "v"}),
    ("bb", {"k": "V"}),
]:
    client.create_experiment(name, tags=tags)

# Search for experiments with name "a"
experiments = client.search_experiments(filter_string="name = 'a'")
assert_experiment_names_equal(experiments, ["a"])

# Search for experiments with name starting with "a"
experiments = client.search_experiments(filter_string="name LIKE 'a%'")
assert_experiment_names_equal(experiments, ["ab", "a"])

# Search for experiments with tag key "k" and value ending with "v" or "V"
experiments = client.search_experiments(filter_string="tags.k ILIKE '%v'")
assert_experiment_names_equal(experiments, ["bb", "ab"])

# Search for experiments with name ending with "b" and tag {"k": "v"}
experiments = client.search_experiments(filter_string="name LIKE '%b' AND tags.k = 'v'")
assert_experiment_names_equal(experiments, ["ab"])

# Sort experiments by name in ascending order
experiments = client.search_experiments(order_by=["name"])
assert_experiment_names_equal(experiments, ["a", "ab", "b", "bb"])

# Sort experiments by ID in descending order
experiments = client.search_experiments(order_by=["experiment_id DESC"])
assert_experiment_names_equal(experiments, ["bb", "ab", "b", "a"])

search_model_versions(filter_string: Optional[str] = None, max_results: int = 10000, order_by: Optional[List[str]] = None, page_token: Optional[str] = None) → PagedList[ModelVersion][source]

Search for model versions in backend that satisfy the filter criteria.

Parameters

filter_string –
Filter query string (e.g., "name = 'a_model_name' and tag.key = 'value1'"), defaults to searching for all model versions. The following identifiers, comparators, and logical operators are supported.
Identifiers
- name: model name.
- source_path: model version source path.
- run_id: The id of the mlflow run that generates the model version.
- tags.<tag_key>: model version tag. If tag_key contains spaces, it must be wrapped with backticks (e.g., "tags.`extra key`").
Comparators
- =: Equal to.
- !=: Not equal to.
- LIKE: Case-sensitive pattern match.
- ILIKE: Case-insensitive pattern match.
- IN: In a value list. Only run_id identifier supports IN comparator.
Logical operators
- AND: Combines two sub-queries and returns True if both of them are True.
max_results – Maximum number of model versions desired.
order_by – List of column names with ASC|DESC annotation, to be used for ordering matching search results.
page_token – Token specifying the next page of results. It should be obtained from a search_model_versions call.

Returns

A PagedList of mlflow.entities.model_registry.ModelVersion objects that satisfy the search expressions. The pagination token for the next page can be obtained via the token attribute of the object.

Example

import mlflow
from mlflow import MlflowClient

client = MlflowClient()

# Get all versions of the model filtered by name
model_name = "CordobaWeatherForecastModel"
filter_string = f"name='{model_name}'"
results = client.search_model_versions(filter_string)
print("-" * 80)
for res in results:
    print(f"name={res.name}; run_id={res.run_id}; version={res.version}")

# Get the version of the model filtered by run_id
run_id = "e14afa2f47a040728060c1699968fd43"
filter_string = f"run_id='{run_id}'"
results = client.search_model_versions(filter_string)
print("-" * 80)
for res in results:
    print(f"name={res.name}; run_id={res.run_id}; version={res.version}")

Output

------------------------------------------------------------------------------------
name=CordobaWeatherForecastModel; run_id=eaef868ee3d14d10b4299c4c81ba8814; version=1
name=CordobaWeatherForecastModel; run_id=e14afa2f47a040728060c1699968fd43; version=2
------------------------------------------------------------------------------------
name=CordobaWeatherForecastModel; run_id=e14afa2f47a040728060c1699968fd43; version=2

search_registered_models(filter_string: Optional[str] = None, max_results: int = 100, order_by: Optional[List[str]] = None, page_token: Optional[str] = None) → PagedList[RegisteredModel][source]

Search for registered models in backend that satisfy the filter criteria.

Parameters

filter_string –
Filter query string (e.g., “name = ‘a_model_name’ and tag.key = ‘value1’”), defaults to searching for all registered models. The following identifiers, comparators, and logical operators are supported.
Identifiers
- name: registered model name.
- tags.<tag_key>: registered model tag. If tag_key contains spaces, it must be wrapped with backticks (e.g., “tags.`extra key`”).
Comparators
- =: Equal to.
- !=: Not equal to.
- LIKE: Case-sensitive pattern match.
- ILIKE: Case-insensitive pattern match.
Logical operators
- AND: Combines two sub-queries and returns True if both of them are True.
max_results – Maximum number of registered models desired.
order_by – List of column names with ASC|DESC annotation, to be used for ordering matching search results.
page_token – Token specifying the next page of results. It should be obtained from a search_registered_models call.

Returns

A PagedList of mlflow.entities.model_registry.RegisteredModel objects that satisfy the search expressions. The pagination token for the next page can be obtained via the token attribute of the object.

Example

import mlflow
from mlflow import MlflowClient

client = MlflowClient()

# Get search results filtered by the registered model name
model_name = "CordobaWeatherForecastModel"
filter_string = f"name='{model_name}'"
results = client.search_registered_models(filter_string=filter_string)
print("-" * 80)
for res in results:
    for mv in res.latest_versions:
        print(f"name={mv.name}; run_id={mv.run_id}; version={mv.version}")

# Get search results filtered by the registered model name that matches
# prefix pattern
filter_string = "name LIKE 'Boston%'"
results = client.search_registered_models(filter_string=filter_string)
print("-" * 80)
for res in results:
    for mv in res.latest_versions:
        print(f"name={mv.name}; run_id={mv.run_id}; version={mv.version}")

# Get all registered models and order them by ascending order of the names
results = client.search_registered_models(order_by=["name ASC"])
print("-" * 80)
for res in results:
    for mv in res.latest_versions:
        print(f"name={mv.name}; run_id={mv.run_id}; version={mv.version}")

Output

------------------------------------------------------------------------------------
name=CordobaWeatherForecastModel; run_id=eaef868ee3d14d10b4299c4c81ba8814; version=1
name=CordobaWeatherForecastModel; run_id=e14afa2f47a040728060c1699968fd43; version=2
------------------------------------------------------------------------------------
name=BostonWeatherForecastModel; run_id=ddc51b9407a54b2bb795c8d680e63ff6; version=1
name=BostonWeatherForecastModel; run_id=48ac94350fba40639a993e1b3d4c185d; version=2
-----------------------------------------------------------------------------------
name=AzureWeatherForecastModel; run_id=5fcec6c4f1c947fc9295fef3fa21e52d; version=1
name=AzureWeatherForecastModel; run_id=8198cb997692417abcdeb62e99052260; version=3
name=BostonWeatherForecastModel; run_id=ddc51b9407a54b2bb795c8d680e63ff6; version=1
name=BostonWeatherForecastModel; run_id=48ac94350fba40639a993e1b3d4c185d; version=2
name=CordobaWeatherForecastModel; run_id=eaef868ee3d14d10b4299c4c81ba8814; version=1
name=CordobaWeatherForecastModel; run_id=e14afa2f47a040728060c1699968fd43; version=2

search_runs(experiment_ids: List[str], filter_string: str = '', run_view_type: int = 1, max_results: int = 1000, order_by: Optional[List[str]] = None, page_token: Optional[str] = None) → PagedList[Run][source]

Search for Runs that fit the specified criteria.

Parameters

experiment_ids – List of experiment IDs, or a single int or string id.
filter_string – Filter query string, defaults to searching all runs.
run_view_type – one of enum values ACTIVE_ONLY, DELETED_ONLY, or ALL runs defined in mlflow.entities.ViewType.
max_results – Maximum number of runs desired.
order_by – List of columns to order by (e.g., “metrics.rmse”). The order_by column can contain an optional DESC or ASC value. The default is ASC. The default ordering is to sort by start_time DESC, then run_id.
page_token – Token specifying the next page of results. It should be obtained from a search_runs call.

Returns

A PagedList of Run objects that satisfy the search expressions. If the underlying tracking store supports pagination, the token for the next page may be obtained via the token attribute of the returned object.

Example

import mlflow
from mlflow import MlflowClient
from mlflow.entities import ViewType


def print_run_info(runs):
    for r in runs:
        print(f"run_id: {r.info.run_id}")
        print(f"lifecycle_stage: {r.info.lifecycle_stage}")
        print(f"metrics: {r.data.metrics}")
        # Exclude mlflow system tags
        tags = {k: v for k, v in r.data.tags.items() if not k.startswith("mlflow.")}
        print(f"tags: {tags}")


# Create an experiment and log two runs with metrics and tags under the experiment
experiment_id = mlflow.create_experiment("Social NLP Experiments")
with mlflow.start_run(experiment_id=experiment_id) as run:
    mlflow.log_metric("m", 1.55)
    mlflow.set_tag("s.release", "1.1.0-RC")
with mlflow.start_run(experiment_id=experiment_id):
    mlflow.log_metric("m", 2.50)
    mlflow.set_tag("s.release", "1.2.0-GA")
# Search all runs under experiment id and order them by
# descending value of the metric 'm'
client = MlflowClient()
runs = client.search_runs(experiment_id, order_by=["metrics.m DESC"])
print_run_info(runs)
print("--")
# Delete the first run
client.delete_run(run_id=run.info.run_id)
# Search only deleted runs under the experiment id and use a case insensitive pattern
# in the filter_string for the tag.
filter_string = "tags.s.release ILIKE '%rc%'"
runs = client.search_runs(
    experiment_id, run_view_type=ViewType.DELETED_ONLY, filter_string=filter_string
)
print_run_info(runs)

Output

run_id: 0efb2a68833d4ee7860a964fad31cb3f
lifecycle_stage: active
metrics: {'m': 2.5}
tags: {'s.release': '1.2.0-GA'}
run_id: 7ab027fd72ee4527a5ec5eafebb923b8
lifecycle_stage: active
metrics: {'m': 1.55}
tags: {'s.release': '1.1.0-RC'}
--
run_id: 7ab027fd72ee4527a5ec5eafebb923b8
lifecycle_stage: deleted
metrics: {'m': 1.55}
tags: {'s.release': '1.1.0-RC'}

set_experiment_tag(experiment_id: str, key: str, value: Any) → None[source]

Set a tag on the experiment with the specified ID. Value is converted to a string.

Parameters

experiment_id – String ID of the experiment.
key – Name of the tag.
value – Tag value (converted to a string).

from mlflow import MlflowClient

# Create an experiment and set its tag
client = MlflowClient()
experiment_id = client.create_experiment("Social Media NLP Experiments")
client.set_experiment_tag(experiment_id, "nlp.framework", "Spark NLP")

# Fetch experiment metadata information
experiment = client.get_experiment(experiment_id)
print(f"Name: {experiment.name}")
print(f"Tags: {experiment.tags}")

Name: Social Media NLP Experiments
Tags: {'nlp.framework': 'Spark NLP'}

set_model_version_tag(name: str, version: Optional[str] = None, key: Optional[str] = None, value: Optional[Any] = None, stage: Optional[str] = None) → None[source]

Set a tag for the model version. When stage is set, tag will be set for latest model version of the stage. Setting both version and stage parameter will result in error.

Parameters

name – Registered model name.
version – Registered model version.
key – Tag key to log. key is required.
value – Tag value to log. value is required.
stage – Registered model stage.

Example

import mlflow.sklearn
from mlflow import MlflowClient
from mlflow.models import infer_signature
from sklearn.datasets import make_regression
from sklearn.ensemble import RandomForestRegressor


def print_model_version_info(mv):
    print(f"Name: {mv.name}")
    print(f"Version: {mv.version}")
    print(f"Tags: {mv.tags}")


mlflow.set_tracking_uri("sqlite:///mlruns.db")
params = {"n_estimators": 3, "random_state": 42}
name = "RandomForestRegression"
X, y = make_regression(n_features=4, n_informative=2, random_state=0, shuffle=False)
rfr = RandomForestRegressor(**params).fit(X, y)
signature = infer_signature(X, rfr.predict(X))

# Log MLflow entities
with mlflow.start_run() as run:
    mlflow.log_params(params)
    mlflow.sklearn.log_model(rfr, artifact_path="sklearn-model", signature=signature)

# Register model name in the model registry
client = MlflowClient()
client.create_registered_model(name)

# Create a new version of the rfr model under the registered model name
# and set a tag
model_uri = f"runs:/{run.info.run_id}/sklearn-model"
mv = client.create_model_version(name, model_uri, run.info.run_id)
print_model_version_info(mv)
print("--")

# Tag using model version
client.set_model_version_tag(name, mv.version, "t", "1")

# Tag using model stage
client.set_model_version_tag(name, key="t1", value="1", stage=mv.current_stage)
mv = client.get_model_version(name, mv.version)
print_model_version_info(mv)

Output

Name: RandomForestRegression
Version: 1
Tags: {}
--
Name: RandomForestRegression
Version: 1
Tags: {'t': '1', 't1': '1'}

set_registered_model_alias(name: str, alias: str, version: str) → None[source]

Set a registered model alias pointing to a model version.

Parameters

name – Registered model name.
alias – Name of the alias. Note that aliases of the format v<number>, such as v9 and v42, are reserved and cannot be set.
version – Registered model version number.

Example

import mlflow
from mlflow import MlflowClient
from mlflow.models import infer_signature
from sklearn.datasets import make_regression
from sklearn.ensemble import RandomForestRegressor


def print_model_info(rm):
    print("--Model--")
    print("name: {}".format(rm.name))
    print("aliases: {}".format(rm.aliases))


def print_model_version_info(mv):
    print("--Model Version--")
    print("Name: {}".format(mv.name))
    print("Version: {}".format(mv.version))
    print("Aliases: {}".format(mv.aliases))


mlflow.set_tracking_uri("sqlite:///mlruns.db")
params = {"n_estimators": 3, "random_state": 42}
name = "RandomForestRegression"
X, y = make_regression(n_features=4, n_informative=2, random_state=0, shuffle=False)
rfr = RandomForestRegressor(**params).fit(X, y)
signature = infer_signature(X, rfr.predict(X))

# Log MLflow entities
with mlflow.start_run() as run:
    mlflow.log_params(params)
    mlflow.sklearn.log_model(rfr, artifact_path="sklearn-model", signature=signature)

# Register model name in the model registry
client = MlflowClient()
client.create_registered_model(name)
model = client.get_registered_model(name)
print_model_info(model)

# Create a new version of the rfr model under the registered model name
model_uri = "runs:/{}/sklearn-model".format(run.info.run_id)
mv = client.create_model_version(name, model_uri, run.info.run_id)
print_model_version_info(mv)

# Set registered model alias
client.set_registered_model_alias(name, "test-alias", mv.version)
print()
print_model_info(model)
print_model_version_info(mv)

Output

--Model--
name: RandomForestRegression
aliases: {}

--Model Version--
Name: RandomForestRegression
Version: 1
Aliases: []

--Model--
name: RandomForestRegression
aliases: {"test-alias": "1"}

--Model Version--
Name: RandomForestRegression
Version: 1
Aliases: ["test-alias"]

set_registered_model_tag(name, key, value) → None[source]

Set a tag for the registered model.

Parameters

name – Registered model name.
key – Tag key to log.
value – Tag value log.

Example

import mlflow
from mlflow import MlflowClient


def print_model_info(rm):
    print("--")
    print("name: {}".format(rm.name))
    print("tags: {}".format(rm.tags))


name = "SocialMediaTextAnalyzer"
tags = {"nlp.framework1": "Spark NLP"}
mlflow.set_tracking_uri("sqlite:///mlruns.db")
client = MlflowClient()

# Create registered model, set an additional tag, and fetch
# update model info
client.create_registered_model(name, tags, desc)
model = client.get_registered_model(name)
print_model_info(model)
client.set_registered_model_tag(name, "nlp.framework2", "VADER")
model = client.get_registered_model(name)
print_model_info(model)

Output

--
name: SocialMediaTextAnalyzer
tags: {'nlp.framework1': 'Spark NLP'}
--
name: SocialMediaTextAnalyzer
tags: {'nlp.framework1': 'Spark NLP', 'nlp.framework2': 'VADER'}

set_tag(run_id: str, key: str, value: Any, synchronous: bool = True) → Optional[mlflow.utils.async_logging.run_operations.RunOperations][source]

Set a tag on the run with the specified ID. Value is converted to a string.

Parameters

run_id – String ID of the run.
key – Tag name. This string may only contain alphanumerics, underscores (_), dashes (-), periods (.), spaces ( ), and slashes (/). All backend stores will support keys up to length 250, but some may support larger keys.
value – Tag value, but will be string-ified if not. All backend stores will support values up to length 5000, but some may support larger values.
synchronous – Experimental If True, blocks until the tag is logged successfully. If False, logs the tag asynchronously and returns a future representing the logging operation.

Returns

When synchronous=True, returns None. When synchronous=False, returns an mlflow.utils.async_logging.run_operations.RunOperations instance that represents future for logging operation.

Example

from mlflow import MlflowClient


def print_run_info(run):
    print(f"run_id: {run.info.run_id}")
    print(f"Tags: {run.data.tags}")


# Create a run under the default experiment (whose id is '0').
client = MlflowClient()
experiment_id = "0"
run = client.create_run(experiment_id)
print_run_info(run)
print("--")
# Set a tag and fetch updated run info
client.set_tag(run.info.run_id, "nlp.framework", "Spark NLP")
run = client.get_run(run.info.run_id)
print_run_info(run)

Output

run_id: 4f226eb5758145e9b28f78514b59a03b
Tags: {}
--
run_id: 4f226eb5758145e9b28f78514b59a03b
Tags: {'nlp.framework': 'Spark NLP'}

set_terminated(run_id: str, status: Optional[str] = None, end_time: Optional[int] = None) → None[source]

Set a run’s status to terminated.

Parameters

status – A string value of mlflow.entities.RunStatus. Defaults to “FINISHED”.
end_time – If not provided, defaults to the current time.

from mlflow import MlflowClient


def print_run_info(r):
    print(f"run_id: {r.info.run_id}")
    print(f"status: {r.info.status}")


# Create a run under the default experiment (whose id is '0').
# Since this is low-level CRUD operation, this method will create a run.
# To end the run, you'll have to explicitly terminate it.
client = MlflowClient()
experiment_id = "0"
run = client.create_run(experiment_id)
print_run_info(run)
print("--")

# Terminate the run and fetch updated status. By default,
# the status is set to "FINISHED". Other values you can
# set are "KILLED", "FAILED", "RUNNING", or "SCHEDULED".
client.set_terminated(run.info.run_id, status="KILLED")
run = client.get_run(run.info.run_id)
print_run_info(run)

run_id: 575fb62af83f469e84806aee24945973
status: RUNNING
--
run_id: 575fb62af83f469e84806aee24945973
status: KILLED

property tracking_uri

transition_model_version_stage(name: str, version: str, stage: str, archive_existing_versions: bool = False) → ModelVersion [source]

Warning

mlflow.tracking.client.MlflowClient.transition_model_version_stage is deprecated since 2.9.0. Model registry stages will be removed in a future major release. To learn more about the deprecation of model registry stages, see our migration guide here: https://mlflow.org/docs/2.12.1/model-registry.html#migrating-from-stages

Update model version stage.

Parameters

name – Registered model name.
version – Registered model version.
stage – New desired stage for this model version.
archive_existing_versions – If this flag is set to True, all existing model versions in the stage will be automatically moved to the “archived” stage. Only valid when stage is "staging" or "production" otherwise an error will be raised.

Returns

A single mlflow.entities.model_registry.ModelVersion object.

Example

import mlflow.sklearn
from mlflow import MlflowClient
from mlflow.models import infer_signature
from sklearn.datasets import make_regression
from sklearn.ensemble import RandomForestRegressor


def print_model_version_info(mv):
    print(f"Name: {mv.name}")
    print(f"Version: {mv.version}")
    print(f"Description: {mv.description}")
    print(f"Stage: {mv.current_stage}")


mlflow.set_tracking_uri("sqlite:///mlruns.db")
params = {"n_estimators": 3, "random_state": 42}
name = "RandomForestRegression"
desc = "A new version of the model using ensemble trees"
X, y = make_regression(n_features=4, n_informative=2, random_state=0, shuffle=False)
rfr = RandomForestRegressor(**params).fit(X, y)
signature = infer_signature(X, rfr.predict(X))

# Log MLflow entities
with mlflow.start_run() as run:
    mlflow.log_params(params)
    mlflow.sklearn.log_model(rfr, artifact_path="sklearn-model", signature=signature)

# Register model name in the model registry
client = MlflowClient()
client.create_registered_model(name)

# Create a new version of the rfr model under the registered model name
model_uri = f"runs:/{run.info.run_id}/sklearn-model"
mv = client.create_model_version(name, model_uri, run.info.run_id, description=desc)
print_model_version_info(mv)
print("--")
# transition model version from None -> staging
mv = client.transition_model_version_stage(name, mv.version, "staging")
print_model_version_info(mv)

Output

Name: RandomForestRegression
Version: 1
Description: A new version of the model using ensemble trees
Stage: None
--
Name: RandomForestRegression
Version: 1
Description: A new version of the model using ensemble trees
Stage: Staging

update_model_version(name: str, version: str, description: Optional[str] = None) → ModelVersion [source]

Update metadata associated with a model version in backend.

Parameters

name – Name of the containing registered model.
version – Version number of the model version.
description – New description.

Returns

A single mlflow.entities.model_registry.ModelVersion object.

Example

import mlflow.sklearn
from mlflow import MlflowClient
from mlflow.models import infer_signature
from sklearn.datasets import make_regression
from sklearn.ensemble import RandomForestRegressor


def print_model_version_info(mv):
    print(f"Name: {mv.name}")
    print(f"Version: {mv.version}")
    print(f"Description: {mv.description}")


mlflow.set_tracking_uri("sqlite:///mlruns.db")
params = {"n_estimators": 3, "random_state": 42}
name = "RandomForestRegression"
X, y = make_regression(n_features=4, n_informative=2, random_state=0, shuffle=False)
rfr = RandomForestRegressor(**params).fit(X, y)
signature = infer_signature(X, rfr.predict(X))

# Log MLflow entities
with mlflow.start_run() as run:
    mlflow.log_params(params)
    mlflow.sklearn.log_model(rfr, artifact_path="sklearn-model", signature=signature)

# Register model name in the model registry
client = MlflowClient()
client.create_registered_model(name)
# Create a new version of the rfr model under the registered model name
model_uri = f"runs:/{run.info.run_id}/sklearn-model"
mv = client.create_model_version(name, model_uri, run.info.run_id)
print_model_version_info(mv)
print("--")
# Update model version's description
desc = "A new version of the model using ensemble trees"
mv = client.update_model_version(name, mv.version, desc)
print_model_version_info(mv)

Output

Name: RandomForestRegression
Version: 1
Description: None
--
Name: RandomForestRegression
Version: 1
Description: A new version of the model using ensemble trees

update_registered_model(name: str, description: Optional[str] = None) → RegisteredModel [source]

Updates metadata for RegisteredModel entity. Input field description should be non-None. Backend raises exception if a registered model with given name does not exist.

Parameters

name – Name of the registered model to update.
description – (Optional) New description.

Returns

A single updated mlflow.entities.model_registry.RegisteredModel object.

Example

def print_registered_model_info(rm):
    print(f"name: {rm.name}")
    print(f"tags: {rm.tags}")
    print(f"description: {rm.description}")


name = "SocialMediaTextAnalyzer"
tags = {"nlp.framework": "Spark NLP"}
desc = "This sentiment analysis model classifies the tone-happy, sad, angry."

mlflow.set_tracking_uri("sqlite:///mlruns.db")
client = MlflowClient()
client.create_registered_model(name, tags, desc)
print_registered_model_info(client.get_registered_model(name))
print("--")

# Update the model's description
desc = "This sentiment analysis model classifies tweets' tone: happy, sad, angry."
client.update_registered_model(name, desc)
print_registered_model_info(client.get_registered_model(name))

Output

name: SocialMediaTextAnalyzer
tags: {'nlp.framework': 'Spark NLP'}
description: This sentiment analysis model classifies the tone-happy, sad, angry.
--
name: SocialMediaTextAnalyzer
tags: {'nlp.framework': 'Spark NLP'}
description: This sentiment analysis model classifies tweets' tone: happy, sad, angry.

update_run(run_id: str, status: Optional[str] = None, name: Optional[str] = None) → None[source]

Update a run with the specified ID to a new status or name.

Parameters

run_id – The ID of the Run to update.
status – The new status of the run to set, if specified. At least one of status or name should be specified.
name – The new name of the run to set, if specified. At least one of name or status should be specified.

Example

from mlflow import MlflowClient


def print_run_info(run):
    print(f"run_id: {run.info.run_id}")
    print(f"run_name: {run.info.run_name}")
    print(f"status: {run.info.status}")


# Create a run under the default experiment (whose id is '0').
client = MlflowClient()
experiment_id = "0"
run = client.create_run(experiment_id)
print_run_info(run)
print("--")

# Update run and fetch info
client.update_run(run.info.run_id, "FINISHED", "new_name")
run = client.get_run(run.info.run_id)
print_run_info(run)

Output

run_id: 1cf6bf8bf6484dd8a598bd43be367b20
run_name: judicious-hog-915
status: RUNNING
--
run_id: 1cf6bf8bf6484dd8a598bd43be367b20
run_name: new_name
status: FINISHED