AutoPrognosis - A system for automating the design of predictive modeling pipelines tailored for clinical prognosis.

<div align="center">

<!-- [](https://github.com/vanderschaarlab/autoprognosis/actions/workflows/test_R.yml) -->

</div>

:key: Features

• :rocket: Automatically learns ensembles of pipelines for classification, regression or survival analysis tasks.
• :cyclone: Easy to extend pluginable architecture.
• :fire: Interpretability and uncertainty quantification tools.
• :adhesive_bandage: Data imputation using HyperImpute.
• :zap: Build demonstrators using Streamlit.
• :notebook: Python and R tutorials available.
• :book: Read the docs

Note : The R bindings have been tested using R version 4.2 and Python 3.8.

:rocket: Installation

Using pip

The library can be installed from PyPI using

$ pip install autoprognosis

or from source, using

$ pip install .

Redis (Optional, but recommended)

AutoPrognosis can use Redis as a backend to improve the performance and quality of the searches.

For that, install the redis-server package following the steps described on the official site.

Environment variables

The library can be configured from a set of environment variables.

| Variable | Description | |----------------|-----------------------------------------------------------------| | N_OPT_JOBS | Number of cores to use for hyperparameter search. Default : 1 | | N_LEARNER_JOBS | Number of cores to use by inidividual learners. Default: all cpus | | REDIS_HOST | IP address for the Redis database. Default 127.0.0.1 | | REDIS_PORT | Redis port. Default: 6379 |

Example: export N_OPT_JOBS = 2 to use 2 cores for hyperparam search.

:boom: Sample Usage

Advanced Python tutorials can be found in the Python tutorials section.

R examples can be found in the R tutorials section.

List the available classifiers

from autoprognosis.plugins.prediction.classifiers import Classifiers
print(Classifiers().list_available())

Create a study for classifiers

from sklearn.datasets import load_breast_cancer

from autoprognosis.studies.classifiers import ClassifierStudy
from autoprognosis.utils.serialization import load_model_from_file
from autoprognosis.utils.tester import evaluate_estimator


X, Y = load_breast_cancer(return_X_y=True, as_frame=True)

df = X.copy()
df["target"] = Y

study_name = "example"

study = ClassifierStudy(
    study_name=study_name,
    dataset=df,  # pandas DataFrame
    target="target",  # the label column in the dataset
)
model = study.fit()

# Predict the probabilities of each class using the model
model.predict_proba(X)

(Advanced) Customize the study for classifiers

from pathlib import Path

from sklearn.datasets import load_breast_cancer

from autoprognosis.studies.classifiers import ClassifierStudy
from autoprognosis.utils.serialization import load_model_from_file
from autoprognosis.utils.tester import evaluate_estimator


X, Y = load_breast_cancer(return_X_y=True, as_frame=True)

df = X.copy()
df["target"] = Y

workspace = Path("workspace")
study_name = "example"

study = ClassifierStudy(
    study_name=study_name,
    dataset=df,  # pandas DataFrame
    target="target",  # the label column in the dataset
    num_iter=100,  # how many trials to do for each candidate
    timeout=60,  # seconds
    classifiers=["logistic_regression", "lda", "qda"],
    workspace=workspace,
)

study.run()

output = workspace / study_name / "model.p"
model = load_model_from_file(output)

# <model> contains the optimal architecture, but the model is not trained yet. You need to call fit() to use it.
# This way, we can further benchmark the selected model on the training set.
metrics = evaluate_estimator(model, X, Y)

print(f"model {model.name()} -> {metrics['str']}")

# Train the model
model.fit(X, Y)

# Predict the probabilities of each class using the model
model.predict_proba(X)

List the available regressors

from autoprognosis.plugins.prediction.regression import Regression
print(Regression().list_available())

Create a Regression study

# third party
import pandas as pd

# autoprognosis absolute
from autoprognosis.utils.serialization import load_model_from_file
from autoprognosis.utils.tester import evaluate_regression
from autoprognosis.studies.regression import RegressionStudy

# Load dataset
df = pd.read_csv(
    "https://archive.ics.uci.edu/ml/machine-learning-databases/00291/airfoil_self_noise.dat",
    header=None,
    sep="\\t",
)
last_col = df.columns[-1]
y = df[last_col]
X = df.drop(columns=[last_col])

df = X.copy()
df["target"] = y

# Search the model
study_name="regression_example"
study = RegressionStudy(
    study_name=study_name,
    dataset=df,  # pandas DataFrame
    target="target",  # the label column in the dataset
)
model = study.fit()

# Predict using the model
model.predict(X)

Advanced Customize the Regression study

# stdlib
from pathlib import Path

# third party
import pandas as pd

# autoprognosis absolute
from autoprognosis.utils.serialization import load_model_from_file
from autoprognosis.utils.tester import evaluate_regression
from autoprognosis.studies.regression import RegressionStudy

# Load dataset
df = pd.read_csv(
    "https://archive.ics.uci.edu/ml/machine-learning-databases/00291/airfoil_self_noise.dat",
    header=None,
    sep="\\t",
)
last_col = df.columns[-1]
y = df[last_col]
X = df.drop(columns=[last_col])

df = X.copy()
df["target"] = y

# Search the model
workspace = Path("workspace")
workspace.mkdir(parents=True, exist_ok=True)

study_name="regression_example"
study = RegressionStudy(
    study_name=study_name,
    dataset=df,  # pandas DataFrame
    target="target",  # the label column in the dataset
    num_iter=10,  # how many trials to do for each candidate. Default: 50
    num_study_iter=2,  # how many outer iterations to do. Default: 5
    timeout=50,  # timeout for optimization for each classfier. Default: 600 seconds
    regressors=["linear_regression", "xgboost_regressor"],
    workspace=workspace,
)

study.run()

# Test the model
output = workspace / study_name / "model.p"

model = load_model_from_file(output)
# <model> contains the optimal architecture, but the model is not trained yet. You need to call fit() to use it.
# This way, we can further benchmark the selected model on the training set.

metrics = evaluate_regression(model, X, y)

print(f"Model {model.name()} score: {metrics['str']}")

# Train the model
model.fit(X, y)


# Predict using the model
model.predict(X)

List available survival analysis estimators

from autoprognosis.plugins.prediction.risk_estimation import RiskEstimation
print(RiskEstimation().list_available())

Create a Survival analysis study

# third party
import numpy as np
from pycox import datasets

# autoprognosis absolute
from autoprognosis.studies.risk_estimation import RiskEstimationStudy
from autoprognosis.utils.serialization import load_model_from_file
from autoprognosis.utils.tester import evaluate_survival_estimator

df = datasets.gbsg.read_df()
df = df[df["duration"] > 0]

X = df.drop(columns = ["duration"])
T = df["duration"]
Y = df["event"]

eval_time_horizons = np.linspace(T.min(), T.max(), 5)[1:-1]

study_name = "example_risks"

study = RiskEstimationStudy(
    study_name=study_name,
    dataset=df,
    target="event",
    time_to_event="duration",
    time_horizons=eval_time_horizons,
)

model = study.fit()

# Predict using the model
model.predict(X, eval_time_horizons)

Advanced Cust