ml_main.py 文件源码

def one_set(A, y, cv, final_model, names, feature_names, results_dir, train_func=None, predict_func=None, baseline=None):

    log.info("Starting {} analysis.".format(results_dir))

    #create storage directory
    if not os.path.exists(results_dir):
        os.makedirs(results_dir)

    fpr_array, tpr_array, thresh_array, oob_estimates = validation.compute_cv(cv, final_model, A, y, train_func, predict_func)

    log.info("Building storage record.")

    result = validation.create_record(final_model, y, cv, names, fpr_array, tpr_array, thresh_array, oob_estimates)

    try:
        #if logistic regression get feature weights
        if 'logitreg' in final_model.named_steps:
            logitreg = final_model.named_steps['logitreg']
            logit_out = {}
            logit_out['lambda'] = (1.0/logitreg.Cs_).tolist();
            logit_out['lambda_best'] = (1.0/logitreg.C_).tolist()[0];

            #now get the empty
            valid_idx = final_model.named_steps['empty'].get_important_indicies()
            ordered = zip(valid_idx, logitreg.coef_.ravel())
            ordered = sorted(ordered, key=lambda o: -np.abs(o[1]))
            out_dict = []
            max_value = np.abs(ordered[0][1])
            for idx, value in ordered:

                if max_value*1.e-6>np.abs(value):
                    break;

                out_dict.append({'name' : feature_names[idx], 'value' : value })

            logit_out['type'] = 'LogisticRegressionCV'   
            logit_out['nnz'] = len(out_dict)
            logit_out['weights'] = out_dict   
            logit_out['offset'] = logitreg.intercept_[0]

            #store the result
            result['model'] = logit_out
    except:
        tb = traceback.format_exc()
        log.error(tb)

    log.info('Created results.')

    path = validation.store_record(result, results_dir, 'full_time', False)

    log.info('Stored results to directory %s.' % (str(path)))

    log.info("Finished!")