Question

我正在开发机器学习（使用Python版本2.7.13），我使用Hyperopt来处理数据并获得经过良好处理的数据的百分比。我想制作交叉验证多核，但这样做需要花费更多时间而不是单核。我正在使用带有atributte n_jobs的loblib来使它成为多核的。代码就是这个：

import numpy as np
from sklearn.svm import SVC
from sklearn.svm import SVR
from sklearn.neighbors import KNeighborsClassifier
from joblib import Parallel, delayed
import time
from sklearn.cross_validation import cross_val_score
from sklearn.neighbors import KNeighborsClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.neural_network import MLPClassifier
from sklearn.naive_bayes import GaussianNB
import matplotlib.pyplot as plt
from hyperopt import fmin, tpe, hp, STATUS_OK, Trials
import arff
import os
from weka.core.converters import Loader
from sklearn import preprocessing
from weka.classifiers import Classifier, Evaluation
import weka.core.jvm as jvm
timetot=time.time()


#TAKES DE DATA ARFF FILE FROM THE DIRECTORY AND CONVERTS IT TO BINARY, IN ORDER TO BE ABLE TO BE PROCESSED
########################################################
script_dir = os.getcwd()
rel_path = "data\\iris.arff"
iris_file = os.path.join(os.getcwd(), rel_path)
dataset = arff.load(open(iris_file, 'rb'))
#dataset = arff.load(open('C:\data\iris.arff', 'rb'))
mi_y = np.array(dataset['data'])
data = mi_y[:,0:mi_y.shape[1]-1]
data = np.array(mi_y[:,0:mi_y.shape[1]-1])


datos= data
datosunicos=np.unique(datos)
datosunicos=datosunicos.tolist()
unicos_datos = list(range(len(datosunicos)))

for j in range(len(datos[0])):
    for i in range(len(datos)):
#         print(datosunicos)
#         print(datos[i,j])
         posa = datosunicos.index(datos[i,j])


         datos[i,j] = unicos_datos[posa]

data = datos.astype(np.float64)

#datosBinarios=MultiLabelBinarizer().fit_transform(data)

#y = mi_y
#y = mi_y[:,mi_y.shape[1]-1:mi_y.shape[1]]
y = mi_y[:,mi_y.shape[1]-1]
unicos = np.unique(y)
unicos = unicos.tolist()
unicos_numericos = list(range(len(unicos)))

bar = y
for i in range(len(bar)):
     pos = unicos.index(bar[i])
     bar[i] = unicos_numericos[pos]

y = bar.astype(np.int32)

X = data
#Xbuena = X.astype(np.float)
counter = 0
###########################################################






def hyperopt_train_test(params):
    from sklearn.preprocessing import normalize
    from sklearn.preprocessing import scale

    X_ = X[:]

    if 'normalize' in params:
        if params['normalize'] == 1:
            X_ = normalize(X_)
    del params['normalize']

    if 'scale' in params:
        if params['scale'] == 1:
            X_ = scale(X_)
    del params['scale']

# CHOOSE THE ALGORITHM TO BE USED TO PROCESS THE DATA AND CROSSVALIDATE **HERE IS WHERE I ASSIGN THE CORES WITH N_JOBS=-1
##########################################################
#    clf = SVC(**params)
#    clk =KNeighborsClassifier(**params)
#    clnb=GaussianNB(**params)

    clrf=RandomForestClassifier(**params)
#    clmlp=MLPClassifier(**params)
    #clf = SVR(**params)

    return cross_val_score(clrf, X_, y, cv=10,n_jobs=-1).mean()
##########################################################

#DEFINE THE SEARCH SPACES FOR EACH ALGORITHM
space4svm = {
    'C': hp.uniform('C', 0, 20),
    'kernel': hp.choice('kernel', ['linear', 'sigmoid', 'poly', 'rbf']),
#    'kernel': hp.choice('kernel', ['linear']),
    #'epsilon': hp.choice('epsilon', [0.1]),
    'gamma': hp.uniform('gamma', 0, 20),
    'scale': hp.choice('scale', [0, 1]),
    'normalize': hp.choice('normalize', [0, 1])
}
space4KNN= {
        'n_neighbors': hp.choice('n_neighbors',[1,2,3,4,5]),
        'scale': hp.choice('scale', [0, 1]),
        'normalize': hp.choice('normalize', [0, 1])
        }
space4NB= {
        'scale': hp.choice('scale', [0, 1]),
        'normalize': hp.choice('normalize', [0, 1])
        }
space4RF= {
        'n_estimators': hp.choice('n_estimators',np.arange(10, 30, dtype=int)),
        'max_features': hp.uniform('max_features',0.25, 1),
        'scale': hp.choice('scale', [0, 1]),
        'normalize': hp.choice('normalize', [0, 1])
        }
space4MLP= {
        'momentum': hp.uniform('momentum',0,0.05),
        'scale': hp.choice('scale', [0, 1]),
        'normalize': hp.choice('normalize', [0, 1])
        }



def f(params):
    acc = hyperopt_train_test(params)
    global counter
    counter = counter + 1
    print counter, acc
    return {'loss': -acc, 'status': STATUS_OK}

#HERE IS WHERE I WANT TO MAKE IT MULTICORE , WHEN IT CALLS FMIN FUNCTION
if __name__ == '__main__':
    trials = Trials()
    best = fmin(f,space4RF, algo=tpe.suggest, max_evals=100, trials=trials)
    print 'best:'
    print best



    #CHOOSE THE PARAMETERS DEPENDING ON THE ALGORITHM TO USE
    #############################################################
    #parameters = ['C', 'kernel', 'gamma', 'scale', 'normalize']
    #parameters = ['n_neighbors', 'scale', 'normalize']
    #parameters = [ 'scale', 'normalize']
    parameters = ['n_estimators','max_features', 'scale', 'normalize']
    #parameters = ['momentum','scale', 'normalize']
    #############################################################


    cols = len(parameters)
    f, axes = plt.subplots(nrows=1, ncols=cols, figsize=(20,5))
    cmap = plt.cm.jet
    for i, val in enumerate(parameters):
        xs = np.array([t['misc']['vals'][val] for t in trials.trials]).ravel()
        ys = [-t['result']['loss'] for t in trials.trials]
        #xs, ys = zip(\*sorted(zip(xs, ys)))
        #xs, ys = zipped.sort(\*sorted(zip(xs, ys)))
        axes[i].scatter(xs, ys, s=20, linewidth=0.01, alpha=0.25, c=cmap(float(i)/len(parameters)))
        axes[i].set_title(val)
        axes[i].set_ylim([0.9, 1.0])


#PRINTS TOTAL TIME
print("TIEMPO TOTAL:")
print(time.time()-timetot)

我得到了96秒的处理能力，一个核心，296个核心处理。

非常感谢你的帮助。

使用Joblib多核并行化的时间比单核更多

0 个答案: