class PCAMODEL(object):
n_components = None
trainX = None
trainY = None
testX = None
model = None
def __init__(self, n='mle', X = None, Y = None):
self.n_components = n
self.trainX = X
self.trainY = Y
def build_model(self):
self.model = PCA(self.n_components)
self.model.fit(self.trainX)
def reduce_dim(self, data):
return self.model.transform(data)
def PDBpca(pdblist_file, npcs=5,refPDB_file=None): # read pdblist file and fit each structure to refPDB pdbdata, miscs, rmsds = pynumpdb.readPDBlist(pdblist_file,refPDB_file) # run PCA #v,P,PC = pynumpdb._pca.pca_train(pdbdata,npcs,do_norm=0) pca = PCA() pca.fit(pdbdata) v = pca.explained_variance_ P = pca.components_ PC = pca.transform(pdbdata) print v print P print len(PC),len(PC[0]) #print PC.T return v,P,PC
import pylab as pl
from scikits.learn.decomposition import PCA, FastICA
###############################################################################
# Generate sample data
S = np.random.standard_t(1.5, size=(2, 10000))
S[0] *= 2.
# Mix data
A = [[1, 1], [0, 2]] # Mixing matrix
X = np.dot(A, S) # Generate observations
pca = PCA()
S_pca_ = pca.fit(X.T).transform(X.T).T
ica = FastICA()
S_ica_ = ica.fit(X).transform(X) # Estimate the sources
S_ica_ /= S_ica_.std(axis=1)[:, np.newaxis]
###############################################################################
# Plot results
def plot_samples(S, axis_list=None):
pl.scatter(S[0], S[1], s=2, marker='o', linewidths=0, zorder=10)
if axis_list is not None:
colors = [(0, 0.6, 0), (0.6, 0, 0)]
for color, axis in zip(colors, axis_list):
#!/usr/bin/env python
import os, numpy
from scikits.learn.decomposition import PCA
from ift6266h12.utils.ift6266h12_io import load_train_input, load_test_input, load_valid_input
dest_path = '/data/lisa/data/UTLC/pca'
trainset = load_train_input('sylvester', normalize=True)
testset = load_test_input('sylvester', normalize=True)
validset = load_valid_input('sylvester', normalize=True)
pca = PCA(32)
pca.fit(trainset)
numpy.save(os.path.join(dest_path, 'sylvester_train_x_pca32.npy'),
pca.transform(trainset))
numpy.save(os.path.join(dest_path, 'sylvester_valid_x_pca32.npy'),
pca.transform(validset))
numpy.save(os.path.join(dest_path, 'sylvester_test_x_pca32.npy'),
pca.transform(testset))
import pylab as pl
from scikits.learn import datasets
from scikits.learn.decomposition import PCA
from scikits.learn.lda import LDA
iris = datasets.load_iris()
X = iris.data
y = iris.target
target_names = iris.target_names
print target_names
pca = PCA(n_components=2)
X_r = pca.fit(X).transform(X)
lda = LDA(n_components=2)
X_r2 = lda.fit(X, y).transform(X)
# Percentage of variance explained for each components
print 'explained variance ratio (first two components):', \
pca.explained_variance_ratio_
pl.figure()
for c, i, target_name in zip("rgb", [0, 1, 2], target_names):
pl.scatter(X_r[y == i, 0], X_r[y == i, 1], c=c, label=target_name)
pl.legend()
pl.title('PCA of IRIS dataset')
pl.figure()
print __doc__
import pylab as pl
from scikits.learn import datasets
from scikits.learn.decomposition import PCA
from scikits.learn.lda import LDA
iris = datasets.load_iris()
X = iris.data
y = iris.target
target_names = iris.target_names
pca = PCA(n_components=2)
X_r = pca.fit(X).transform(X)
lda = LDA(n_components=2)
X_r2 = lda.fit(X, y).transform(X)
# Percentage of variance explained for each components
print 'explained variance ratio (first two components):', \
pca.explained_variance_ratio_
pl.figure()
for c, i, target_name in zip("rgb", [0, 1, 2], target_names):
pl.scatter(X_r[y == i, 0], X_r[y == i, 1], c=c, label=target_name)
pl.legend()
pl.title('PCA of IRIS dataset')
pl.figure()
import pylab as pl
from scikits.learn.decomposition import PCA, FastICA
###############################################################################
# Generate sample data
S = np.random.standard_t(1.5, size=(10000, 2))
S[0] *= 2.
# Mix data
A = np.array([[1, 1], [0, 2]]) # Mixing matrix
X = np.dot(S, A.T) # Generate observations
pca = PCA()
S_pca_ = pca.fit(X).transform(X)
ica = FastICA()
S_ica_ = ica.fit(X).transform(X) # Estimate the sources
S_ica_ /= S_ica_.std(axis=0)
###############################################################################
# Plot results
def plot_samples(S, axis_list=None):
pl.scatter(S[:,0], S[:,1], s=2, marker='o', linewidths=0, zorder=10)
if axis_list is not None:
colors = [(0, 0.6, 0), (0.6, 0, 0)]
for color, axis in zip(colors, axis_list):
import pylab as pl
from scikits.learn.decomposition import PCA, FastICA
###############################################################################
# Generate sample data
S = np.random.standard_t(1.5, size=(2, 10000))
S[0] *= 2.
# Mix data
A = [[1, 1], [0, 2]] # Mixing matrix
X = np.dot(A, S) # Generate observations
pca = PCA()
S_pca_ = pca.fit(X.T).transform(X.T).T
ica = FastICA()
S_ica_ = ica.fit(X).transform(X) # Estimate the sources
S_ica_ /= S_ica_.std(axis=1)[:, np.newaxis]
###############################################################################
# Plot results
def plot_samples(S, axis_list=None):
pl.scatter(S[0], S[1], s=2, marker='o', linewidths=0, zorder=10)
if axis_list is not None:
colors = [(0, 0.6, 0), (0.6, 0, 0)]
for color, axis in zip(colors, axis_list):
