Python StandardScaler.astype方法代碼示例

# 需要導入模塊: from sklearn.preprocessing import StandardScaler [as 別名]
# 或者: from sklearn.preprocessing.StandardScaler import astype [as 別名]
#
# Generate sample data for the DBSCAN test 
# 
# Lifted from http://scikit-learn.org/stable/auto_examples/cluster/plot_dbscan.html#example-cluster-plot-dbscan-py
#

import numpy as np

from sklearn.cluster import DBSCAN
from sklearn import metrics
from sklearn.datasets.samples_generator import make_blobs
from sklearn.preprocessing import StandardScaler

centers = [[1, 1], [-1, -1], [1, -1]]
X, labels_true = make_blobs(n_samples=750, centers=centers, cluster_std=0.4,
    random_state=0)

X = StandardScaler().fit_transform(X)
X = X.astype(np.float64)
db = DBSCAN(eps=0.3, min_samples=10, metric='l2', algorithm='brute').fit(X)
core_samples_mask = np.zeros_like(db.labels_, dtype=bool)
core_samples_mask[db.core_sample_indices_] = True
labels = db.labels_

with open('dbscan.csv', 'w') as fscanout:
    with open('dbscan_labels.csv', 'w') as fscanlabout:
        for i in range(750):
            fscanout.write(",".join([str(x) for x in X[i,:]]) + "\n")
            fscanlabout.write(str(labels[i]) + "\n")

# 需要導入模塊: from sklearn.preprocessing import StandardScaler [as 別名]
# 或者: from sklearn.preprocessing.StandardScaler import astype [as 別名]
	def cluster(self):

		cluster_file = open("cluster.txt", "w")

		print(self.data.shape)

		X = self.data

		X = StandardScaler().fit_transform(X)

		db = DBSCAN(eps=10, min_samples=2).fit(X)
		labels = db.labels_

		print(labels)

		# Number of clusters in labels, ignoring noise if present.
		n_clusters_ = len(set(labels)) - (1 if -1 in labels else 0)


		index = []
		fitness = []
		mean = []

		print("number of estimated clusters : %d" % n_clusters_ )
		cluster_file.write("number of estimated clusters : %d" % n_clusters_ + "\n")

		for k in range(n_clusters_):
			my_members = (labels == k)

			for i in range(len(X)):
				if my_members[i]:
					index += [i]
					if self.pure_data != None:
						num = 0
						if i % 2 == 0:
							num = int(i/2)
							fitness += [self.pure_data[num].fitness.values] 
						else :
							num = int((i-1)/2)
							fitness += [self.pure_data[num].fitness.values]

			
			if fitness != []:
				for i in range(len(fitness[0])):
					mean += [statistics.mean([ind[i] for ind in fitness])]

			cluster_file.write("index:"+ "\n")
			cluster_file.write(str(index) + "\n")
			cluster_file.write("fitness:"+ "\n")
			cluster_file.write(str(fitness)+ "\n")
			cluster_file.write("mean fitness:"+ "\n")
			cluster_file.write(str(mean)+ "\n")
			cluster_file.write("members:"+ "\n")
			cluster_file.write(str(X[my_members])+ "\n")

			print(index)
			print("members:")
			print(X[my_members])
			print("fitness:"+ "\n")
			print(str(fitness)+ "\n")

			index = []
			fitness = []
			mean = []

		mds = MDS(n_components=2)

		pos = mds.fit_transform(X.astype(np.float64))

		import matplotlib.pyplot as plt

		colors = list('bgrcmykbgrcmykbgrcmykbgrcmyk')

		plt.figure(2)

		for i in range(len(pos[:,0])):

			plt.plot(pos[i, 0], pos[i, 1], 'o', markerfacecolor=colors[labels[i]], markeredgecolor='k')



		import matplotlib.pyplot as plt
		from itertools import cycle

		plt.figure(1)
		plt.title("number of estimated clusters : %d" % n_clusters_)
		colors = list('bgrcmykbgrcmykbgrcmykbgrcmyk')
		colors_cluster = [colors[labels[i]] for i in range(len(X))]
		k = [i for i in range(len(X))]
		for j in range(9):
			plt.subplot(330 + j)
			plt.ylabel(label[j])
			#plt.ylim(limits[j][0], limits[j][1])
			plt.bar(k, X[:][j], color=colors_cluster)
		plt.show()

# 需要導入模塊: from sklearn.preprocessing import StandardScaler [as 別名]
# 或者: from sklearn.preprocessing.StandardScaler import astype [as 別名]
import numpy as np

#from sklearn.cluster import DBSCAN
#from sklearn import metrics
from sklearn.datasets.samples_generator import make_blobs
from sklearn.preprocessing import StandardScaler


##############################################################################
# Generate sample data
centers = [[1, 1], [-1, -1], [1, -1]]
X, labels_true = make_blobs(n_samples=750, centers=centers, cluster_std=0.4,
                            random_state=0)

X = StandardScaler().fit_transform(X)
X = X.astype(np.float32)

##############################################################################
# Compute DBSCAN
import dbscan
labels = np.array(dbscan.dbscan(X, "sparse").run(0.3, 10))
core_samples_mask = np.zeros_like(labels, dtype=bool)
# core_samples_mask[db.core_sample_indices_] = True

# Number of clusters in labels, ignoring noise if present.
n_clusters_ = len(set(labels)) - (1 if -1 in labels else 0)

print('Estimated number of clusters: %d' % n_clusters_)

##############################################################################
# Plot result

# 需要導入模塊: from sklearn.preprocessing import StandardScaler [as 別名]
# 或者: from sklearn.preprocessing.StandardScaler import astype [as 別名]
path = '/Users/zhangweijian01/Downloads/data.csv'
ori_data = pd.read_csv(path, header=0, sep='\t')
y_data = ori_data['Y']
x_data = ori_data.ix[:, 3:]
x_data = x_data.fillna(x_data.mean())
y_data = y_data.fillna(y_data.mean())

# to handle missing values
imp = Imputer(missing_values='NaN', strategy='median', axis=0)
imp.fit(x_data)
data_imp = imp.transform(x_data)
x_scaler = data_imp

# scalar
x_scaler = StandardScaler().fit_transform(data_imp)
x_scaler = x_scaler.astype(np.float64, copy=False)

for i in range(0, len(x_scaler)):
    for j in range(0, len(x_scaler[i])):
        x_scaler[i][j] = float('%.4f' % (x_scaler[i][j]))

# sava preprocessed data to file
np.savetxt("newdata2.csv", x_scaler, delimiter=",")

f = open('newdata1.csv', 'w')
for i in range(0, len(x_scaler)):
    line = str(y_data[i])
    for j in range(0, len(x_scaler[i])):
        line = line + ',' + str(x_scaler[i][j])
    line += '\n'
    f.write(line)