Xf_last_runtime3, Xf_last_runtime4, Xf_usermean)) #At this point we have: Xf, yf, tsafir #___LEARNING___ print("encoding finished. predicting..") if tool == "tsafrir": #___TSAFRIR MEAN___ def bound_req(pred, req): if pred < req: return pred else: return req bound_with_reqtime = np.vectorize(bound_req) np_array_to_file(bound_with_reqtime(tsafir, data['time_req']), arguments["<output_folder>"] + "/prediction_tsafrir") elif tool in ["sgd", "passive-aggressive"]: #___ONLINE LEARNING___ from simpy import Environment, simulate, Monitor from swfpy import io if arguments['--verbose'] == True: import logging from simpy.util import start_delayed if arguments['--verbose'] == True: global_logger = logging.getLogger('global') hdlr = logging.FileHandler('predictor.log') formatter = logging.Formatter('%(levelname)s %(message)s') hdlr.setFormatter(formatter) global_logger.addHandler(hdlr)
Xf_last_runtime4, Xf_usermean)) #At this point we have: Xf, yf, tsafir #___LEARNING___ print("encoding finished. predicting..") if tool=="tsafrir": #___TSAFRIR MEAN___ def bound_req(pred,req): if pred<req: return pred else: return req bound_with_reqtime=np.vectorize(bound_req) np_array_to_file(bound_with_reqtime(tsafir,data['time_req']),arguments["<output_folder>"]+"/prediction_tsafrir") elif tool in ["sgd","passive-aggressive"]: #___ONLINE LEARNING___ from simpy import Environment,simulate,Monitor from swfpy import io if arguments['--verbose']==True: import logging from simpy.util import start_delayed if arguments['--verbose']==True: global_logger = logging.getLogger('global') hdlr = logging.FileHandler('predictor.log') formatter = logging.Formatter('%(levelname)s %(message)s') hdlr.setFormatter(formatter) global_logger.addHandler(hdlr)
max_depth=None, min_samples_split=2, min_samples_leaf=1, max_features='auto', bootstrap=True, oob_score=False, n_jobs=3, random_state=None, verbose=0, min_density=None, compute_importances=None) print("learning random forests") forest.fit(Xlearn, ylearn) print("prediction") pred = forest.predict(Xtest) np_array_to_file(pred, "prediction_rf") elif tool == "tsafrir": #___TSAFRIR MEAN___ np_array_to_file(tsafir, "prediction_tsafrir") elif tool == "svr": #___OFFLINE SVR___ print("creating SVR") svr = SVR(kernel='linear', degree=3, gamma=0.0, coef0=0.0, tol=0.001, C=1.0, epsilon=0.1,
if tool=="random_forest": #____OFFLINE RANDOM FORESTS____ start=int(len(Xf)*.7) i=int(len(Xf)*.8) Xlearn=Xf[start:i:1,:] Xtest=Xf[i:len(Xf),:] ylearn=yf[start:i:1] ytest=yf[i:len(yf)] tsafirtest=tsafir[i:len(yf)] forest=RandomForestRegressor(n_estimators=40, criterion='mse', max_depth=None, min_samples_split=2, min_samples_leaf=1, max_features='auto', bootstrap=True, oob_score=False, n_jobs=3, random_state=None, verbose=0, min_density=None, compute_importances=None) print("learning random forests") forest.fit(Xlearn,ylearn) print("prediction") pred=forest.predict(Xtest) np_array_to_file(pred,"prediction_rf") elif tool=="tsafrir": #___TSAFRIR MEAN___ np_array_to_file(tsafir,"prediction_tsafrir") elif tool=="svr": #___OFFLINE SVR___ print("creating SVR") svr=SVR(kernel='linear', degree=3, gamma=0.0, coef0=0.0, tol=0.001, C=1.0, epsilon=0.1, shrinking=True, probability=False, cache_size=200, verbose=False, max_iter=-1, random_state=None) svr.fit(Xlearn,ylearn) pred=svr.predict(Xtest) np_array_to_file(pred,"prediction_rf") elif tool in ["sgd","passive-aggressive"]: #___ONLINE LEARNING___