Python KernelDensity.fit方法代码示例

# 需要导入模块: from sklearn.neighbors.kde import KernelDensity [as 别名]
# 或者: from sklearn.neighbors.kde.KernelDensity import fit [as 别名]
def estimate_distribution(samples, h=0.1, n_points=100):
	kde = KernelDensity(bandwidth=h)
	samples = samples[:, np.newaxis]
	kde.fit(samples)
	xs = np.linspace(-1.0, 1.0, n_points)
	ys = [np.exp(kde.score([x])) for x in xs]
	return xs, ys

# 需要导入模块: from sklearn.neighbors.kde import KernelDensity [as 别名]
# 或者: from sklearn.neighbors.kde.KernelDensity import fit [as 别名]
class OneClassKDE(BaseClassifier):
    _fit_params = ["bandwidth"]
    _predict_params = []
    def __init__(self, *args, **kwargs):
        self.bandwidth = kwargs["bandwidth"]
        self.perc_keep = kwargs["perc_keep"]
    
    def fit(self, data, **kwargs):
        #self.train_data = data
        self.kde = KernelDensity(kernel='gaussian', bandwidth=self.bandwidth)
        
        idx = numpy.random.randint(2, size=len(data)).astype(numpy.bool)
        print idx
        
        
        self.kde.fit(data[idx, :])
        self.training_score = self.kde.score_samples(data[~idx, :])
        self.direct_thresh = numpy.percentile(self.training_score, 100-self.perc_keep)
        
        print 'training', self.training_score.min(), self.training_score.mean(), self.training_score.max(), self.direct_thresh
        
        print self.direct_thresh
    
    def predict(self, data):
        score = self.kde.score_samples(data)
        self.score = score
        res = (score < self.direct_thresh)
        print 'test', self.score.min(), self.score.mean(), self.score.max()
        print res.sum(), "of", len(self.score), 'outliers'
        
        return res.astype(numpy.uint8)*-2+1
    
    def decision_function(self, data=None):
        return self.score

# 需要导入模块: from sklearn.neighbors.kde import KernelDensity [as 别名]
# 或者: from sklearn.neighbors.kde.KernelDensity import fit [as 别名]
def _importance_preprocess_uni(states, rewards, gradients, p_tar, p_gen):
    res = _create_episode_info()

    flat_states = [s for traj in states for s in traj]
    # TODO Pass in as args?
    kde = KernelDensity(kernel='gaussian', bandwidth=0.25)
    kde.fit(flat_states)

    for ss, rs, gs, ps, qs in izip(states, rewards, gradients, p_tar, p_gen):

        state_probs = kde.score_samples(ss)
        traj_p = np.cumsum(ps)  # + np.mean(state_probs)
        traj_q = np.cumsum(qs) + state_probs
        traj_grads = np.cumsum(gs, axis=0)
        r_acc = np.cumsum(rs[::-1])[::-1]
        r_grad = (r_acc * traj_grads.T).T

        res.r_grads.extend(r_grad)
        res.traj_p_tar.extend(traj_p)
        res.traj_p_gen.extend(traj_q)
        res.traj_grads.extend(traj_grads)
        res.traj_r.extend(r_acc)

        # Used for estimating fisher
        res.act_grads.extend(gs)
        res.state_act_p_tar.extend(traj_p)
        res.state_act_p_gen.extend(traj_q)

    return res

# 需要导入模块: from sklearn.neighbors.kde import KernelDensity [as 别名]
# 或者: from sklearn.neighbors.kde.KernelDensity import fit [as 别名]
def createfeatmat(N):
    grid = getgridcoords(N).T
    featmat = np.zeros((len(vals), N ** 2))
    for i in range(len(vals)):
        m = np.array([vals[i][0], vals[i][1]]).T
        k = KernelDensity(bandwidth=0.5 / (N - 1), kernel="gaussian")
        k.fit(m)
        featmat[i, :] = k.score_samples(grid)
    return featmat

# 需要导入模块: from sklearn.neighbors.kde import KernelDensity [as 别名]
# 或者: from sklearn.neighbors.kde.KernelDensity import fit [as 别名]
def kde_sklearn(x, x_grid, bandwidth=0.2, **kwargs):
    """Kernel Density Estimation with Scikit-learn"""
    kde_skl = KernelDensity(bandwidth=bandwidth, **kwargs)
    kde_skl.fit(x[:, np.newaxis])
    # score_samples() returns the log-likelihood of the samples
    log_pdf = kde_skl.score_samples(x_grid[:, np.newaxis])
    
    N = np.trapz(np.exp(log_pdf), x_grid)

    return np.exp(log_pdf)/N

# 需要导入模块: from sklearn.neighbors.kde import KernelDensity [as 别名]
# 或者: from sklearn.neighbors.kde.KernelDensity import fit [as 别名]
def estimate_distribution(samples, h=0.1, n_points=100):
	kde = KernelDensity(bandwidth=h)
	min_xs = min(samples)
	max_xs = max(samples)
	samples = samples[:, np.newaxis]
	kde.fit(samples)
	xs = np.linspace(min_xs, max_xs, n_points)
	ys = np.exp(kde.score_samples(xs[:, np.newaxis]))
	print xs.shape, ys.shape, sum(ys)
	return xs, ys

# 需要导入模块: from sklearn.neighbors.kde import KernelDensity [as 别名]
# 或者: from sklearn.neighbors.kde.KernelDensity import fit [as 别名]
class OneClassKDE(BaseClassifier):
    _fit_params = ["bandwidth"]
    def __init__(self, *args, **kwargs):
        self.bandwidth = kwargs["bandwidth"]
    
    def fit(self, data, **kwargs):
        #self.train_data = data
        self.kde = KernelDensity(kernel='gaussian', bandwidth=self.bandwidth)
        self.kde.fit(data)
        self.training_score = self.kde.score_samples(data)
        self.direct_thresh = numpy.percentile(self.training_score, 10)
    
    def predict(self, data):
        score = self.kde.score_samples(data)
        self.score = score
        return (score < self.direct_thresh).astype(numpy.int32)*-2+1
    
    def decision_function(self, data):
        return self.score

# 需要导入模块: from sklearn.neighbors.kde import KernelDensity [as 别名]
# 或者: from sklearn.neighbors.kde.KernelDensity import fit [as 别名]
 def nmultitype_conf_matrix(self,tipos,nfolds):
     cadena = ""
     for t in tipos:
         cadena += t
     if not os.path.exists("models/nmultitype_conf_matrix" + self.bd +"ts"+cadena+"Promedio"+str(nfolds)+".p") or True:
         #Creamos la matriz de matrices donde guardaremos los resultados parciales
         matrices = [None] * nfolds * nfolds
         #Creamos/Recuperamos el modelo Node2Vec
         n2v = node2vec(self.bd,self.port,self.user,self.pss,self.label,1000,20,6,self.mode,[],1)
         n2v.learn("normal",0,False,0)
         #Creamos los arrays X e Y, anadiendo
         X = []
         Y = []
         #Creamos un array de comunes que son los nodos que son a la vez de ambos tipos
         comunes = list()
         for tipo in tipos:
             for n in n2v.n_types[tipo]:
                 if n in n2v.w2v:
                     X.append(n2v.w2v[n])
                     if n in n2v.n_types[tipos[0]] and  n in n2v.n_types[tipos[1]]:
                         comunes.append(n2v.w2v[n])
                     Y.append(tipo)
         #Creamos los k folds estratificados    
         X = np.array(X)
         Y = np.array(Y)
         skf = StratifiedKFold(Y, n_folds=nfolds)
         it = 0
         kdes = []
         for train_index, test_index in skf:
             print "k-fold para kde"
             X_train, X_test = X[train_index], X[test_index]
             Y_train, Y_test = Y[train_index], Y[test_index]
             Y_test = Y_test.astype('|S64')
             #Creamos la funcion de densidad de probabilidad de cada tipo
             for t in tipos:
                 print "Creando KDE para el tipo "+t
                 tempX = []
                 for idx,n in enumerate(Y_train):
                     if n == t:
                         tempX.append(X_train[idx])
                 #Calculating KDE with the train set
                 #use grid search cross-validation to optimize the bandwidth
                 #params = {'bandwidth': np.logspace(-1, 1, 10)}
                 #grid = GridSearchCV(neighbors.KernelDensity(), params)
                 #grid.fit(tempX)
                 #print("best bandwidth: {0}".format(grid.best_estimator_.bandwidth))
                 # use the best estimator to compute the kernel density estimate
                 #kde = grid.best_estimator_
                 kde = KernelDensity(kernel='gaussian', bandwidth=0.1)
                 kde.fit(tempX)
                 kdes.append(kde)
                 print "Terminado KDE para el tipo "+t
             #Dividimos el conjunto de test en tipo1, tipo2 y tipo1+2
             cont = 0
             for idx,x in enumerate(X_test):
                 total = 0
                 x = np.array(x)
                 if any((x == a).all() for a in comunes):
                     Y_test[idx] = str(tipos[0]+"+"+tipos[1])
                     cont += 1
             print "Numero de elementos con doble tipo:"+str(cont)
             #Creamos k-folds estratificados para el arbol de decision
             skf = StratifiedKFold(Y_test, n_folds=nfolds)
             for train_index, test_index in skf:
                 print "k-fold para decission tree"
                 X_train1, X_test1 = X_test[train_index], X_test[test_index]
                 Y_train1, Y_test1 = Y_test[train_index], Y_test[test_index]
                 clf = DecisionTreeClassifier(random_state=0)
                 print X_train1[0]
                 clf.fit(X_train1,Y_train1)
                 export_graphviz(clf);
                 Y_pred1 = clf.predict(X_test1)
                 matriz = metrics.confusion_matrix(Y_test1, Y_pred1,[tipos[0],tipos[1],tipos[0]+"+"+tipos[1]])
                 matrices[it] = np.array(matriz)
                 print matrices[it]
                 it += 1
         f = open( "models/nmultitype_conf_matrix" + self.bd +"ts"+cadena+"Promedio"+str(nfolds)+".p", "w" )
         pickle.dump(matrices,f)
     else:
         f = open( "models/nmultitype_conf_matrix" + self.bd +"ts"+cadena+"Promedio"+str(nfolds)+".p", "r" )
         matrices = pickle.load(f)
     total = matrices[0]
     for m in matrices[1:]:
         total += m
     print total
     matriz_promedio = total 
     matriz_promedio = matriz_promedio.astype('float')
     #print matrices
     #print matriz_promedio
     matriz_promedio = matriz_promedio / len(matrices)
     #print matriz_promedio
     #calculando porcentajes a partir del promedio de frecuencias
     for i in range(0,len(matriz_promedio)):
         suma = 0
         for j in range(0,len(matriz_promedio)): 
             suma += matriz_promedio[i][j]
             matriz_promedio[i][j] = float(matriz_promedio[i][j])
         for j in range(0,len(matriz_promedio)):                
             if suma > 0:
                 matriz_promedio[i][j] = round(float(matriz_promedio[i][j] * 100) / float(suma),2)
#.........这里部分代码省略.........