Python BernoulliRBM.n_iter方法代码示例

# 需要导入模块: from sklearn.neural_network import BernoulliRBM [as 别名]
# 或者: from sklearn.neural_network.BernoulliRBM import n_iter [as 别名]
def RBM_SVM(trainfeatures, testfeatures, trainlabels, testlabels):
    # ******************* Scikit-learning RBM + SVM *******************
    print "train RBM+SVM model"

    ##    trainfeatures = (trainfeatures - np.min(trainfeatures, 0)) / (np.max(trainfeatures, 0) + 0.0001)  # 0-1 scaling
    min_max_scaler = preprocessing.MinMaxScaler()
    trainfeatures_fs = min_max_scaler.fit_transform(trainfeatures)
    testfeatures_fs = min_max_scaler.transform(testfeatures)

    # SVM parameters
    clf = svm.SVC(C=5.0, kernel='sigmoid', degree=3, gamma=0.5, coef0=10.0,
                  shrinking=True, probability=False, tol=0.001, cache_size=200,
                  class_weight=None, verbose=False, max_iter=-1, random_state=None)

    # RBM parameters
    rbm = BernoulliRBM(random_state=0, verbose=True)
    rbm.learning_rate = 0.06
    rbm.n_iter = 20

    # Machine learning pipeline
    classifier = Pipeline(steps=[('rbm', rbm), ('svm', clf)])

    # More components tend to give better prediction performance, but larger
    # fitting time
    rbm.n_components = 400
    classifier.fit(trainfeatures_fs, trainlabels)
    results = classifier.predict(testfeatures_fs)

    results = results.ravel()
    testerror = float(len(testlabels)
                      - np.sum(testlabels == results))/float(len(testlabels))
    # print"error rate with SVM  is %.4f" %testerror

    return testerror

# 需要导入模块: from sklearn.neural_network import BernoulliRBM [as 别名]
# 或者: from sklearn.neural_network.BernoulliRBM import n_iter [as 别名]
def Logistic():
    logistic = linear_model.LogisticRegression()
    rbm = BernoulliRBM(random_state=0, verbose=True)
    classifier = Pipeline(steps=[('rbm', rbm), ('logistic', logistic)])
    # RBM parameters obtained after cross-validation
    rbm.learning_rate = 0.01
    rbm.n_iter = 121
    rbm.n_components = 700
    logistic.C= 1.0  
    # Training RBM-Logistic Pipeline
    classifier.fit(data_train,target_train)
    # Training Logistic regression
    logistic_classifier = linear_model.LogisticRegression(C=1.0)
    logistic_classifier.fit(data_train,target_train)    
    print("printing_results")
    print("Logistic regression using RBM features:\n%s\n" % (metrics.classification_report(target_test,classifier.predict(data_test))))
    cm3 = confusion_matrix(target_test,classifier.predict(data_test))
    plt.matshow(cm3)
    plt.title('Confusion Matrix Logistic Regression with RBM Features')
    plt.colorbar()
    plt.ylabel('True Label')
    plt.xlabel('Predicted Label')
    plt.savefig('confusion_matrix3.jpg')
    print("Logistic regression using raw pixel features:\n%s\n" % (metrics.classification_report(target_test,logistic_classifier.predict(data_test))))
    cm4 = confusion_matrix(target_test,logistic_classifier.predict(data_test))
    plt.matshow(cm4)
    plt.title('Confusion Matrix Logistic Regression')
    plt.colorbar()
    plt.ylabel('True Label')
    plt.xlabel('Predicted Label')
    plt.savefig('confusion_matrix4.jpg')
#Logistic()

# 需要导入模块: from sklearn.neural_network import BernoulliRBM [as 别名]
# 或者: from sklearn.neural_network.BernoulliRBM import n_iter [as 别名]
def SGD():
    SGD = linear_model.SGDClassifier(loss='hinge',penalty='l2',random_state=42,n_jobs=-1,epsilon=0.001)
    rbm = BernoulliRBM(random_state=0, verbose=True)
    classifier = Pipeline(steps=[('rbm', rbm), ('SGD', SGD)])
    # RBM parameters obtained after cross-validation
    rbm.learning_rate = 0.01
    rbm.n_iter = 15
    rbm.n_components = 50
    SGD.alpha=0.0001
    SGD.C=1 
    # Training SGD
    SGD_classifier = linear_model.SGDClassifier(loss='hinge',penalty='l2',random_state=42,n_jobs=-1,alpha=0.0001, epsilon=0.001)
    SGD_classifier.fit(data_train,target_train)
    # Training RBM-SGD Pipeline    
    classifier.fit(data_train,target_train)
    print("printing_results")
    
    print("SGD using RBM features:\n%s\n" % (metrics.classification_report(target_test,classifier.predict(data_test))))
    cm = confusion_matrix(target_test,classifier.predict(data_test))
    plt.matshow(cm)
    plt.title('Confusion Matrix SVM with SDG with RBM Features')
    plt.colorbar()
    plt.ylabel('True Label')
    plt.xlabel('Predicted Label')
    plt.savefig('confusion_matrix1.jpg')
    print("SGD using raw pixel features:\n%s\n" % (metrics.classification_report(target_test,SGD_classifier.predict(data_test))))
    cm1 = confusion_matrix(target_test,SGD_classifier.predict(data_test))
    plt.matshow(cm1)
    plt.title('Confusion Matrix SVM with SDG Raw Features')
    plt.colorbar()
    plt.ylabel('True Label')
    plt.xlabel('Predicted Label')
    plt.savefig('confusion_matrix2.jpg')

# 需要导入模块: from sklearn.neural_network import BernoulliRBM [as 别名]
# 或者: from sklearn.neural_network.BernoulliRBM import n_iter [as 别名]
def build_classifier(clf_name):

    clf = None
    parameters = {}

    if clf_name == "svm":
        clf = svm.SVC(kernel='linear', C=10)
        parameters = {}

    elif clf_name == "knn":
        clf = neighbors.KNeighborsClassifier(n_neighbors=5, weights='uniform', algorithm='brute', leaf_size=30,
                                             metric='cosine', metric_params=None)

    elif clf_name == "rmb":
        logistic = linear_model.LogisticRegression()
        rbm = BernoulliRBM(random_state=0, verbose=True)
        rbm.learning_rate = 0.01
        rbm.n_iter = 20
        rbm.n_components = 100
        logistic.C = 6000
        clf = Pipeline(steps=[('rbm', rbm), ('logistic', logistic)])
        #parameters = {'clf__C': (1, 10)}

    elif clf_name == "tsne":
        clf = TSNE(n_components=2, init='random', metric='cosine')

    return clf, parameters

# 需要导入模块: from sklearn.neural_network import BernoulliRBM [as 别名]
# 或者: from sklearn.neural_network.BernoulliRBM import n_iter [as 别名]
def runRBM(arr, clsfr):#iters, lrn_rate, logistic_c_val, logistic_c_val2, n_comp, filename):
    global file_dir, nEvents, solutionFile
    iters = int(arr[0]*10)
    lrn_rate = arr[1]
    logistic_c_val = arr[2]*1000.0
    logistic_c_val2 = arr[3]*100.0
    n_comp = int(arr[4]*100)
    filename = 'rbm_iter'+str(iters)+'_logc'+str(log_c_val)+'_logcc'+str(log_c_val2)+'_lrn'+str(learn_rate)+'_nc'+str(n_comp)# low
    logistic = linear_model.LogisticRegression()
    rbm = BernoulliRBM(random_state=0, verbose=True)
    
    classifier = Pipeline(steps=[('rbm', rbm), ('logistic', logistic)])

    ###############################################################################
    # Training

    # Hyper-parameters. These were set by cross-validation,
    # using a GridSearchCV. Here we are not performing cross-validation to
    # save time.
    rbm.learning_rate = lrn_rate #0.10#0.06
    rbm.n_iter = iters #20
    # More components tend to give better prediction performance, but larger
    # fitting time
    rbm.n_components = n_comp # 250
    logistic.C = logistic_c_val #6000.0

    # Training RBM-Logistic Pipeline
    classifier.fit(sigtr[train_input].values, sigtr['Label'].values)

    # Training Logistic regression
    logistic_classifier = linear_model.LogisticRegression(C=logistic_c_val2)#100.0
    logistic_classifier.fit(sigtr[train_input].values, sigtr['Label'].values)

    ###############################################################################
    # Evaluation
    if clsfr == 0:
        clsnn_pred=classifier.predict(sigtest[train_input].values)
        solnFile('clsnn_'+filename,clsnn_pred,sigtest['EventId'].values)#,bkgtest)
        ams_score = ams.AMS_metric(solutionFile, file_dir+filename+'.out', nEvents)
        print ams_score
        logfile.write(filename+': ' + str(ams_score)+'\n')
    
    elif clsfr == 1:
        log_cls_pred = logistic_classifier.predict(sigtest[train_input].values)
        solnFile('lognn_'+filename,log_cls_pred,sigtest['EventId'].values)#,bkgtest)
        ams_score = ams.AMS_metric(solutionFile, file_dir+'lognn_'+filename+'.out', nEvents)
        print ams_score
        logfile.write('lognn ' + filename+': ' + str(ams_score)+'\n')
    else:
        logistic_classifier_tx = linear_model.LogisticRegression(C=logistic_c_val2)
        logistic_classifier_tx.fit_transform(sigtr[train_input].values, sigtr['Label'].values)
        log_cls_tx_pred = logistic_classifier_tx.predict(sigtest[train_input].values)
        solnFile('lognntx_'+filename,log_cls_tx_pred,sigtest['EventId'].values)#,bkgtest)
        ams_score = ams.AMS_metric(solutionFile, file_dir+filename+'.out', nEvents)
        print ams_score
        logfile.write('lognntx '+ filename+': ' + str(ams_score)+'\n')

    return -1.0*float(ams_score)

# 需要导入模块: from sklearn.neural_network import BernoulliRBM [as 别名]
# 或者: from sklearn.neural_network.BernoulliRBM import n_iter [as 别名]
def train_rbm(X, n_components=100, n_iter=10):
    X = X.astype(np.float64)
    X = (X - np.min(X, 0)) / (np.max(X, 0) + 0.0001)  # scale to [0..1]
    rbm = BernoulliRBM(random_state=0, verbose=True)
    rbm.learning_rate = 0.06
    rbm.n_iter = n_iter
    rbm.n_components = n_components
    rbm.fit(X)
    return rbm

# 需要导入模块: from sklearn.neural_network import BernoulliRBM [as 别名]
# 或者: from sklearn.neural_network.BernoulliRBM import n_iter [as 别名]
def rbm_dbn_train_and_predict(train_set_x,train_set_y,test_set_x,test_set_y):
    dbn = DBN(epochs=200,learn_rates=0.01)
    rbm = BernoulliRBM(random_state=0, verbose=True)
    rbm.learning_rate = 0.06
    rbm.n_iter = 20
    rbm.n_components = 100
    classifier = Pipeline(steps=[('rbm', rbm), ('dbn', dbn)])
    classifier.fit(train_set_x,train_set_y)
    PRED = classifier.predict(test_set_x)
    return PRED   

# 需要导入模块: from sklearn.neural_network import BernoulliRBM [as 别名]
# 或者: from sklearn.neural_network.BernoulliRBM import n_iter [as 别名]
def rbm_logistic_train_and_predict(train_set_x,train_set_y,test_set_x,test_set_y):
    logistic = linear_model.LogisticRegression(C=6000)
    rbm = BernoulliRBM(random_state=0, verbose=True)
    rbm.learning_rate = 0.06
    rbm.n_iter = 20
    rbm.n_components = 100
    classifier = Pipeline(steps=[('rbm', rbm), ('logistic', logistic)])
    classifier.fit(train_set_x,train_set_y)
    PRED = classifier.predict(test_set_x)
    return PRED

# 需要导入模块: from sklearn.neural_network import BernoulliRBM [as 别名]
# 或者: from sklearn.neural_network.BernoulliRBM import n_iter [as 别名]
def rbm_knn_train_and_predict(train_set_x,train_set_y,test_set_x,test_set_y):
    knn = KNeighborsClassifier(n_neighbors=5)
    rbm = BernoulliRBM(random_state=0, verbose=True)
    rbm.learning_rate = 0.06
    rbm.n_iter = 20
    rbm.n_components = 100
    classifier = Pipeline(steps=[('rbm', rbm), ('knn', knn)])
    classifier.fit(train_set_x,train_set_y)
    PRED = classifier.predict(test_set_x)
    return PRED

# 需要导入模块: from sklearn.neural_network import BernoulliRBM [as 别名]
# 或者: from sklearn.neural_network.BernoulliRBM import n_iter [as 别名]
def run_auto():
    X = load_data('gender/male')
    X = X.astype(np.float32) / 256
    rbm = BernoulliRBM(random_state=0, verbose=True)
    rbm.learning_rate = 0.06
    rbm.n_iter = 20
    rbm.n_components = 2000
    rbm.fit(X)
    cimgs = [comp.reshape(100, 100) for comp in rbm.components_]
    smartshow(cimgs[:12])
    return rbm

# 需要导入模块: from sklearn.neural_network import BernoulliRBM [as 别名]
# 或者: from sklearn.neural_network.BernoulliRBM import n_iter [as 别名]
    def getNeuralModel(self,X,Y):

            logistic = linear_model.LogisticRegression()
            rbm = BernoulliRBM(verbose=True)

            classifier = linear_model.LogisticRegression(penalty='l2', tol=.0001)#Pipeline(steps = [('rbm', rbm),('logistic',logistic)])
            rbm.learning_rate = 0.0001
            rbm.n_iter = 1000
            rbm.n_components = 1000

            classifier.fit(X, Y)

            return classifier

# 需要导入模块: from sklearn.neural_network import BernoulliRBM [as 别名]
# 或者: from sklearn.neural_network.BernoulliRBM import n_iter [as 别名]
def Logistic_cross_vaildation():
    logistic = linear_model.LogisticRegression()
    #cross-validation for logistic regression with RBM
    rbm = BernoulliRBM(random_state=0, verbose=True)
    classifier = Pipeline(steps=[('rbm', rbm), ('logistic', logistic)])   
    rbm.n_iter=100
    cv = cross_validation.StratifiedKFold(output, 3)
    score_func = metrics.f1_score
    parameters = { "rbm__learning_rate": [0.1, 0.01, 0.001,0.0001],"rbm__n_components":[100,200,300,400,500,600,700,800],"logistic__C":[1,100,1000,5000]}
    grid_search = GridSearchCV(classifier,parameters,score_func=score_func,cv=cv)
    grid_search.fit(input,output)
    print "Best %s: %0.3f" % (score_func.__name__, grid_search.best_score_)
    print "Best parameters set:"
    best_parameters = grid_search.best_estimator_.get_params()
    for param_name in sorted(parameters.keys()):
        print "\t%s: %r" % (param_name, best_parameters[param_name])

# 需要导入模块: from sklearn.neural_network import BernoulliRBM [as 别名]
# 或者: from sklearn.neural_network.BernoulliRBM import n_iter [as 别名]
def SGD_cross_validation():
    SGD = linear_model.SGDClassifier(loss='hinge',penalty='l2',random_state=42,n_jobs=-1,epsilon=0.001)
    # cross-validaiotn for SGD classifier
    rbm = BernoulliRBM(random_state=0, verbose=True)
    classifier = Pipeline(steps=[('rbm', rbm), ('SGD', SGD)])  
    rbm.n_iter=100
    cv = cross_validation.StratifiedKFold(output, 3)
    score_func = metrics.f1_score
    parameters = { "rbm__learning_rate": [0.1, 0.01, 0.001,0.0001],"rbm__n_components":[100,200,300,400,500,600,700,800],"SGD__alpha":[0.1,0.01,0.001,0.0001], "SGD__C":[1,100,1000,10000]}
    grid_search = GridSearchCV(classifier,parameters,score_func=score_func,cv=cv)
    grid_search.fit(input,output)
    print "Best %s: %0.3f" % (score_func.__name__, grid_search.best_score_)
    print "Best parameters set:"
    best_parameters = grid_search.best_estimator_.get_params()
    for param_name in sorted(parameters.keys()):
        print "\t%s: %r" % (param_name, best_parameters[param_name])

# 需要导入模块: from sklearn.neural_network import BernoulliRBM [as 别名]
# 或者: from sklearn.neural_network.BernoulliRBM import n_iter [as 别名]
def neural_net():
    digits = datasets.load_digits()
    X = np.asarray(digits.data, 'float32')
    sidelength = int(np.sqrt(X.shape[1]))
    X,Y = nudge_dataset(X,digits.target,dimen=(sidelength,sidelength))
    #Scale the data to be between zero and 1 at all pixels:
    X = (X - np.min(X,axis=0))/(np.max(X,axis=0)+0.0001)

    #Split the data set into a training and testing set:
    X_train,X_test,Y_train,Y_test = train_test_split(X,Y,test_size=0.2,random_state=0)

    #Models we will use
    logistic = linear_model.LogisticRegression()
    rbm = BernoulliRBM(random_state=0, verbose=True)
    #The classifier
    classifier = Pipeline(steps=[('rbm', rbm), ('logistic', logistic)])

    ###############################################################################
    # Training

    # Hyper-parameters. These were set by cross-validation,
    # using a GridSearchCV. Here we are not performing cross-validation to
    # save time.
    rbm.learning_rate = 0.06
    rbm.n_iter = 20
    # More components tend to give better prediction performance, but larger
    # fitting time
    rbm.n_components = 100
    logistic.C = 6000.0

    # Training RBM-Logistic Pipeline
    classifier.fit(X_train, Y_train)

    # Training Logistic regression
    #logistic_classifier = linear_model.LogisticRegression(C=100.0)
    #logistic_classifier.fit(X_train, Y_train)

    ###############################################################################
    # Evaluation
    print ""
    print("Logistic regression using RBM features:\n%s\n" % (
        metrics.classification_report(
            Y_test,
            classifier.predict(X_test))))
    
    #Predict a few individual cases:
    print classifier.predict(X_test[:5,:]),Y_test[:5]

# 需要导入模块: from sklearn.neural_network import BernoulliRBM [as 别名]
# 或者: from sklearn.neural_network.BernoulliRBM import n_iter [as 别名]
def estimate_n_components():
    X = load_data('gender/male')
    X = X.astype(np.float32) / 256
    n_comp_list = [100, 200, 300, 400, 500, 600, 700, 800, 900, 1000, 1100, 1200]
    scores = []
    for n_comps in n_comp_list:
        rbm = BernoulliRBM(random_state=0, verbose=True)
        rbm.learning_rate = 0.06
        rbm.n_iter = 50
        rbm.n_components = 100
        rbm.fit(X)
        score = rbm.score_samples(X).mean()
        scores.append(score)
    plt.figure()
    plt.plot(n_comp_list, scores)
    plt.show()
    return n_comp_list, scores