Python Job.params["thetas"]方法代码示例

# 需要导入模块: from disco.core import Job [as 别名]
# 或者: from disco.core.Job import params["thetas"] [as 别名]
def predict(dataset, fitmodel_url, save_results=True, show=False):
    """
    Function starts a job that makes predictions to input data with a given model

    Parameters
    ----------
    input - dataset object with input urls and other parameters
    fitmodel_url - model created in fit phase
    save_results - save results to ddfs
    show - show info about job execution

    Returns
    -------
    Urls with predictions on ddfs
    """
    from disco.worker.pipeline.worker import Worker, Stage
    from disco.core import Job, result_iterator

    if dataset.params["y_map"] == []:
        raise Exception("Logistic regression requires a target label mapping parameter.")
    if "logreg_fitmodel" not in fitmodel_url:
        raise Exception("Incorrect fit model.")

    job = Job(worker=Worker(save_results=save_results))
    # job parallelizes execution of mappers
    job.pipeline = [
        ("split", Stage("map", input_chain=dataset.params["input_chain"], init=simple_init, process=map_predict))]

    job.params = dataset.params  # job parameters (dataset object)
    job.params["thetas"] = [v for k, v in result_iterator(fitmodel_url["logreg_fitmodel"]) if k == "thetas"][
        0]  # thetas are loaded from ddfs

    job.run(name="logreg_predict", input=dataset.params["data_tag"])
    results = job.wait(show=show)
    return results

# 需要导入模块: from disco.core import Job [as 别名]
# 或者: from disco.core.Job import params["thetas"] [as 别名]
def fit(dataset, alpha=1e-8, max_iterations=10, save_results=True, show=False):
    """
    Function starts a job for calculation of theta parameters

    Parameters
    ----------
    input - dataset object with input urls and other parameters
    alpha - convergence value
    max_iterations - define maximum number of iterations
    save_results - save results to ddfs
    show - show info about job execution

    Returns
    -------
    Urls of fit model results on ddfs
    """
    from disco.worker.pipeline.worker import Worker, Stage
    from disco.core import Job, result_iterator
    import numpy as np

    if dataset.params["y_map"] == []:
        raise Exception("Logistic regression requires a target label mapping parameter.")
    try:
        alpha = float(alpha)
        max_iterations = int(max_iterations)
        if max_iterations < 1:
            raise Exception("Parameter max_iterations should be greater than 0.")
    except ValueError:
        raise Exception("Parameters should be numerical.")

    # initialize thetas to 0 and add intercept term
    thetas = np.zeros(len(dataset.params["X_indices"]) + 1)

    J = [0]  # J cost function values for every iteration
    for i in range(max_iterations):
        job = Job(worker=Worker(save_results=save_results))
        # job parallelizes mappers and joins them with one reducer
        job.pipeline = [
            ("split", Stage("map", input_chain=dataset.params["input_chain"], init=simple_init, process=map_fit)),
            ('group_all', Stage("reduce", init=simple_init, process=reduce_fit, combine=True))]

        job.params = dataset.params  # job parameters (dataset object)
        job.params["thetas"] = thetas  # every iteration set new thetas
        job.run(name="logreg_fit_iter_%d" % (i + 1), input=dataset.params["data_tag"])

        fitmodel_url = job.wait(show=show)
        for k, v in result_iterator(fitmodel_url):
            if k == "J":  #
                J.append(v)  # save value of J cost function
            else:
                thetas = v  # save new thetas
        if np.abs(J[-2] - J[-1]) < alpha:  # check for convergence
            if show:
                print("Converged at iteration %d" % (i + 1))
            break

    return {"logreg_fitmodel": fitmodel_url}  # return results url

# 需要导入模块: from disco.core import Job [as 别名]
# 或者: from disco.core.Job import params["thetas"] [as 别名]
def predict(dataset, fitmodel_url, save_results=True, show=False):
    from disco.worker.pipeline.worker import Worker, Stage
    from disco.core import Job, result_iterator

    if "linreg_fitmodel" not in fitmodel_url:
        raise Exception("Incorrect fit model.")

    job = Job(worker=Worker(save_results=save_results))
    job.pipeline = [
        ("split", Stage("map", input_chain=dataset.params["input_chain"], init=simple_init, process=map_predict))]
    job.params = dataset.params
    job.params["thetas"] = [v for _, v in result_iterator(fitmodel_url["linreg_fitmodel"])][0]

    job.run(name="linreg_predict", input=dataset.params["data_tag"])
    return job.wait(show=show)