def feature_action_sensitivity(feature_type='TD4'):
''' 对每个特征，分析其在不移位和移位情况下的协方差 '''
results = []
subjects = ['subject_' + str(i + 1) for i in range(1)]
channel_pos_list = ['S0', # 中心位置
'U1', 'U2', 'D1', 'D2', 'L1', 'L2', 'R1', 'R2'] # 上 下 左 右
pos_num = len(channel_pos_list)
actions = [i+1 for i in range(7)]
action_num = len(actions) # 7 动作类型个数
if feature_type == 'TD4':
feature_list = ['MAV', 'ZC', 'SSC', 'WL']
elif feature_type == 'TD5':
feature_list = ['MAV', 'ZC', 'SSC', 'WL','RMS']
feat_num = len(feature_list) # 4 特征维度
groups = [i+1 for i in range(4)]
group_num = len(groups) # 4 通道数
group_span = group_num*feat_num
# print group_span
action_span = feat_num*group_num # 16
# print groups, channel_num, channel_span, feat_num
train_dir = 'train4_250_100'
results.append(['subject', 'action', 'feature', 'group', 'means_shift', 'std_shift'] )
plsca = PLSCanonical(n_components=2)
# pos = 1
k=0
for pos_idx, pos_name in enumerate(channel_pos_list[1:]):
pos = pos_idx+1
for subject in subjects:
# shift_simulation = np.ones((action_num,action_span,2))
trains, classes = data_load.load_feature_dataset(train_dir, subject, feature_type)
# m = trains.shape[0]
# print trains.shape, classes.shape, m
# print group_span, group_span*2
# sys.exit(0)
# m = trains.shape[0]*2/3
m = trains.shape[0]/2
X_train = trains[:m, group_span*pos: group_span*(pos+1)]
Y_train = trains[:m:, :group_span]
X_test = trains[m:, group_span*pos: group_span*(pos+1)]
Y_test = trains[m:, :group_span]
plsca.fit(X_train, Y_train)
X_train_r, Y_train_r = plsca.transform(X_train, Y_train)
X_test_r, Y_test_r = plsca.transform(X_test, Y_test)
filename=subject+'_'+pos_name
# plot_plsc_figure(X_train_r,Y_train_r,X_test_r, Y_test_r, filename)
plot_plsc_figure_two(X_train_r,Y_train_r,X_test_r, Y_test_r, filename)
def correlation_matching(I_tr, T_tr, I_te, T_te, n_comps):
""" Learns correlation matching (CM) over I_tr and T_tr
and applies it to I_tr, T_tr, I_te, T_te
Parameters
----------
I_tr: np.ndarray [shape=(n_tr, d_I)]
image data matrix for training
T_tr: np.ndarray [shape=(n_tr, d_T)]
text data matrix for training
I_te: np.ndarray [shape=(n_te, d_I)]
image data matrix for testing
T_te: np.ndarray [shape=(n_te, d_T)]
text data matrix for testing
n_comps: int > 0 [scalar]
number of canonical componens to use
Returns
-------
I_tr_cca : np.ndarray [shape=(n_tr, n_comps)]
image data matrix represetned in correlation space
T_tr_cca : np.ndarray [shape=(n_tr, n_comps)]
text data matrix represetned in correlation space
I_te_cca : np.ndarray [shape=(n_te, n_comps)]
image data matrix represetned in correlation space
T_te_cca : np.ndarray [shape=(n_te, n_comps)]
text data matrix represetned in correlation space
"""
# sclale image and text data
I_scaler = StandardScaler()
I_tr = I_scaler.fit_transform(I_tr)
I_te = I_scaler.transform(I_te)
T_scaler = StandardScaler()
T_tr = T_scaler.fit_transform(T_tr)
T_te = T_scaler.transform(T_te)
cca = PLSCanonical(n_components=n_comps, scale=False)
cca.fit(I_tr, T_tr)
I_tr_cca, T_tr_cca = cca.transform(I_tr, T_tr)
I_te_cca, T_te_cca = cca.transform(I_te, T_te)
return I_tr_cca, T_tr_cca, I_te_cca, T_te_cca
def test_pls_canonical_basics():
# Basic checks for PLSCanonical
d = load_linnerud()
X = d.data
Y = d.target
pls = PLSCanonical(n_components=X.shape[1])
pls.fit(X, Y)
assert_matrix_orthogonal(pls.x_weights_)
assert_matrix_orthogonal(pls.y_weights_)
assert_matrix_orthogonal(pls._x_scores)
assert_matrix_orthogonal(pls._y_scores)
# Check X = TP' and Y = UQ'
T = pls._x_scores
P = pls.x_loadings_
U = pls._y_scores
Q = pls.y_loadings_
# Need to scale first
Xc, Yc, x_mean, y_mean, x_std, y_std = _center_scale_xy(X.copy(),
Y.copy(),
scale=True)
assert_array_almost_equal(Xc, np.dot(T, P.T))
assert_array_almost_equal(Yc, np.dot(U, Q.T))
# Check that rotations on training data lead to scores
Xt = pls.transform(X)
assert_array_almost_equal(Xt, pls._x_scores)
Xt, Yt = pls.transform(X, Y)
assert_array_almost_equal(Xt, pls._x_scores)
assert_array_almost_equal(Yt, pls._y_scores)
# Check that inverse_transform works
X_back = pls.inverse_transform(Xt)
assert_array_almost_equal(X_back, X)
_, Y_back = pls.inverse_transform(Xt, Yt)
assert_array_almost_equal(Y_back, Y)
def drawFaces(emb1, emb2, wordRanking, n, reduction="cut"):
"""
Plot Chernoff faces for n most/less interesting words
From: https://gist.github.com/aflaxman/4043086
:param n: if negative: less interesting
:param reduction:
:return:
"""
s1 = None
s2 = None
if reduction=="cut":
s1 = emb1.getSimMatrix()[0:,0:18]
s2 = emb2.getSimMatrix()[0:,0:18]
elif reduction=="svd":
s1 = TruncatedSVD(n_components=k).fit_transform(emb1.getSimMatrix())
s2 = TruncatedSVD(n_components=k).fit_transform(emb2.getSimMatrix())
elif reduction=="cca": #use orginal embeddings, not similarity matrix for reduction
cca = PLSCanonical(n_components=18)
cca.fit(emb1.m, emb2.m)
s1, s2 = cca.transform(emb1.m, emb2.m)
interesting = list()
name = str(n)+"."+reduction
if n<0: #plot uninteresting words
n *= -1
interesting = [wordRanking[::-1][i] for i in xrange(n)]
else:
interesting = [wordRanking[i] for i in xrange(n)]
fig = plt.figure(figsize=(11,11))
c = 0
for i in range(n):
word = interesting[i]
j = emb1.d[word]
ax = fig.add_subplot(n,2,c+1,aspect='equal')
mpl_cfaces.cface(ax, *s1[j]) #nice for similarity matrix *s1[j][:18]
ax.axis([-1.2,1.2,-1.2,1.2])
ax.set_xticks([])
ax.set_yticks([])
ax.set_title(word)
ax2 = fig.add_subplot(n,2,c+2,aspect='equal')
mpl_cfaces.cface(ax2, *s2[j])
ax2.axis([-1.2,1.2,-1.2,1.2])
ax2.set_xticks([])
ax2.set_yticks([])
ax2.set_title(word)
c += 2
plotname = "plots/"+NAME+".cface_s1s2_"+name+".png"
fig.savefig(plotname)
print("\tSaved Chernoff faces plot in '%s'" % (plotname))
class _PLSCanonicalImpl:
def __init__(self, **hyperparams):
self._hyperparams = hyperparams
self._wrapped_model = Op(**self._hyperparams)
def fit(self, X, y=None):
if y is not None:
self._wrapped_model.fit(X, y)
else:
self._wrapped_model.fit(X)
return self
def transform(self, X):
return self._wrapped_model.transform(X)
def predict(self, X):
return self._wrapped_model.predict(X)
def getCCARanking(self, filter=None):
"""
Compare how far apart words are in projection into common space by CCA
:return:
"""
cca = PLSCanonical(n_components=self.n)
cca.fit(self.emb1.m, self.emb2.m)
m1transformed, m2transformed = cca.transform(self.emb1.m, self.emb2.m)
#get distances between vectors
assert self.emb1.vocab_size == self.emb2.vocab_size
distDict = dict()
for i in xrange(self.emb1.vocab_size):
v1 = m1transformed[i]
v2 = m2transformed[i]
w = self.emb1.rd[i]
distDict[w] = 1-Similarity.euclidean(v1,v2)
ranked = sorted(distDict.iteritems(), key=itemgetter(1), reverse=True)
if filter is not None:
ranked = [(w, s) for (w, s) in distDict.iteritems() if w in filter]
return ranked
def plotClustersCCA(self, filter=None):
"""
Plot clusters in 2dim CCA space: Comparable across embeddings
:return:
"""
if len(self.cluster1) <= 1:
cmap1 = plt.get_cmap('jet', 2)
else:
cmap1 = plt.get_cmap('jet', len(self.cluster1))
cmap1.set_under('gray')
if len(self.cluster2) <= 1:
cmap2 = plt.get_cmap('jet', 2)
else:
cmap2 = plt.get_cmap('jet', len(self.cluster2))
cmap2.set_under('gray')
cca = PLSCanonical(n_components=2)
cca.fit(self.emb1.m, self.emb2.m)
m1transformed, m2transformed = cca.transform(self.emb1.m, self.emb2.m)
labels1 = [self.emb1.rd[i] for i in xrange(self.emb1.vocab_size)]
colors1 = [self.word2cluster1[self.emb1.rd[i]] for i in xrange(self.emb1.vocab_size)]
labels2 = [self.emb2.rd[i] for i in xrange(self.emb2.vocab_size)]
colors2 = [self.word2cluster2[self.emb2.rd[i]] for i in xrange(self.emb2.vocab_size)]
if filter is not None:
print("\tFiltering samples to plot")
filteredIds = [self.emb1.d[w] for w in filter] #get ids for words in filter
m1transformed = m1transformed[filteredIds]
m2transformed = m2transformed[filteredIds]
labels1 = [l for l in labels1 if l in filter]
labels2 = [l for l in labels2 if l in filter]
elif m1transformed.shape[0] > 100: #sample indices to display, otherwise it's too messy
filteredIds = np.random.randint(low=0, high=m1.transformed.shape[0]) #sample filteredIds
m1transformed = m1transformed[filteredIds]
m2transformed = m2transformed[filteredIds]
labels1 = [l for l in labels1 if l in filter]
labels2 = [l for l in labels2 if l in filter]
plotWithLabelsAndColors(m1transformed, labels1, colors=colors1, cmap=cmap1, filename="plots/"+NAME+".cca1.png", dimRed="CCA")
plotWithLabelsAndColors(m2transformed, labels2, colors=colors2, cmap=cmap2, filename="plots/"+NAME+".cca2.png", dimRed="CCA")
plt.xlim(1,np.amax(nComponents))
plt.title('PLS SVD accuracy')
plt.xlabel('Number of components')
plt.ylabel('accuracy')
plt.legend (['LR','LDA','GNB','Linear SVM','rbf SVM'],loc='lower right')
plt.grid(True)
if (0):
#%% PLS Cannonical
nComponents = np.arange(1,nClasses+1)
plsCanScores = np.zeros((5,np.alen(nComponents)))
for i,n in enumerate(nComponents):
plscan = PLSCanonical(n_components=n)
plscan.fit(Xtrain,Ytrain)
XtrainT = plscan.transform(Xtrain)
XtestT = plscan.transform(Xtest)
plsCanScores[:,i] = util.classify(XtrainT,XtestT,labelsTrain,labelsTest)
plscan = PLSCanonical(n_components=2)
plscan.fit(Xtrain,Ytrain)
xt = plscan.transform(Xtrain)
fig = plt.figure()
util.plotData(fig,xt,labelsTrain,classColors)
plt.title('First 2 components of projected data')
#%% Plot accuracies for PLSSVD
plt.figure()
for i in range (5):
vec_c.append(i)
if j < len_train:
l_p.append(vec_p)
l_c.append(vec_c)
else:
l_p_t.append(vec_p)
l_c_t.append(vec_c)
j += 1
sorted_p = np.asarray(l_p)
sorted_c = np.asarray(l_c) #Convert the input to an array
plc = PLSCanonical()
plc.fit_transform(sorted_c, sorted_p)
sorted_c, sorted_p = plc.transform(sorted_c, sorted_p)
sorted_c_test = np.asarray(l_c_t)
sorted_p_test = np.asarray(l_p_t)
sorted_c_test, sorted_p_test = plc.transform(sorted_c_test, sorted_p_test)
plr = PLSRegression()
plr.fit(sorted_c, sorted_p)
params = plr.get_params()
plr.set_params(**params)
y_score = plr.predict(sorted_c_test)
sim_count = 0
print("Test Similarity: ")
for i in range(len(y_score)):
result_sim = 1 - spatial.distance.cosine(y_score[i], sorted_p_test[i])
# set negative connectivities to 0
edge_data = np.apply_along_axis(
lambda x: [0 if element < 0 else element for element in x], 1,
edge_data)
# re-split data (3 ways) for CCA
X1_train = edge_data[:140, :]
X2_train = edge_data[140:280, :]
X2_remain = edge_data[280:, :]
#cca = CCA(n_components =2)
#cca.fit(X1_train, X2_train)
cca = PLSCanonical(n_components=100)
cca.fit(X1_train, X2_train)
block_1_transformed, block_2_transformed = cca.transform(X1_train,
X2_train,
copy=False)
block_3_transformed = np.dot(X2_remain, cca.y_rotations_)
edge_data_transformed = np.vstack(
(block_1_transformed, block_2_transformed, block_3_transformed))
# initialise the classifier
clf = svm.SVC(kernel='precomputed')
# optional shuffle
perm = np.random.permutation(n_subjects)
#print perm
#print n_subjects
labels = labels[perm]
edge_data_transformed = edge_data_transformed[perm, :]
plt.xlim(1, np.amax(nComponents))
plt.title('PLS SVD accuracy')
plt.xlabel('Number of components')
plt.ylabel('accuracy')
plt.legend(['LR', 'LDA', 'GNB', 'Linear SVM', 'rbf SVM'],
loc='lower right')
plt.grid(True)
if (0):
#%% PLS Cannonical
nComponents = np.arange(1, nClasses + 1)
plsCanScores = np.zeros((5, np.alen(nComponents)))
for i, n in enumerate(nComponents):
plscan = PLSCanonical(n_components=n)
plscan.fit(Xtrain, Ytrain)
XtrainT = plscan.transform(Xtrain)
XtestT = plscan.transform(Xtest)
plsCanScores[:, i] = util.classify(XtrainT, XtestT, labelsTrain,
labelsTest)
plscan = PLSCanonical(n_components=2)
plscan.fit(Xtrain, Ytrain)
xt = plscan.transform(Xtrain)
fig = plt.figure()
util.plotData(fig, xt, labelsTrain, classColors)
plt.title('First 2 components of projected data')
#%% Plot accuracies for PLSSVD
plt.figure()
for i in range(5):
plt.plot(nComponents, plsCanScores[i, :], lw=3)
def pls_decomposition(videos, audios, n_components=256):
plsca = PLSCanonical(n_components=n_components)
plsca.fit(audios, videos)
videos_c, audios_c = plsca.transform(videos, audios)
return videos_c, audios_c
for e in temp1[:]:
temp4.append(e)
for e in temp2[:]:
temp4.append(e)
if len(temp4) == 600 and len(temp3) == 300:
x_n.append(temp4)
y_n.append(temp3)
npx = np.asarray(x, dtype=np.float64)
npy = np.asarray(y, dtype=np.float64)
npxn = np.asarray(x_n, dtype=np.float64)
npyn = np.asarray(y_n, dtype=np.float64)
cca = PLSCanonical(n_components=2)
cca.fit_transform(npx, npy)
npx, npy = cca.transform(npx, npy)
npxn, npyn = cca.transform(npxn, npyn)
pls.fit(npx, npy)
params = pls.get_params(deep=True)
print(params)
pls.set_params(**params)
y_score = pls.predict(npxn)
sim_count = 0
tol = 0.1
for index in range(len(y_score)):
sub_result = np.subtract(y_score, npyn)
result = 1 - spatial.distance.cosine(y_score[index], npyn[index])
def training_lda_TD4_inter(my_clfs, trains_S0, trains_shift, classes, **kw):
print 'training_lda_TD4_inter.........'
start_time = time.time()
log_fold = root_path + '/result/' + kw['log_fold']
new_fold(log_fold)
chan_len = kw['chan_len']
action_num = kw['action_num']
print "----training " + kw[
'feature_type'] + " inter, training by position O, testing by electrode shift "
cv = 5
results = []
results.append(['Feat', 'Algorithm', 'Channel_Pos', 'Accuracy', 'std'])
log_file = 'feat_' + kw['feature_type'] + '_inter'
clf = sklearn.lda.LDA(solver='svd',
shrinkage=None,
priors=None,
n_components=None,
store_covariance=False,
tol=0.0001)
data_num = trains_S0.shape[0] / action_num
# print data_num
scores = sklearn.cross_validation.cross_val_score(clf,
trains_S0,
classes,
cv=cv)
results.append(
['feat_TD4_cv_' + str(cv), 'lda', 'S0',
scores.mean(),
scores.std()])
kf = KFold(data_num, n_folds=cv)
for idx, channel_pos in enumerate(kw['pos_list']):
X_test = trains_shift[:, idx * chan_len:idx * chan_len + chan_len]
y_test = classes
iteration = cv
scores = np.zeros((iteration, ))
cca_scores = np.zeros((iteration, ))
iteration -= 1
for train_idx, test_idx in kf:
train_idx_all = np.array([], np.int)
test_idx_all = np.array([], np.int)
for action_idx in range(action_num):
train_idx_all = np.concatenate(
(train_idx_all, train_idx * action_idx), axis=0)
test_idx_all = np.concatenate(
(test_idx_all, test_idx * action_idx), axis=0)
# X_train, y_train = trains_S0[train_idx_all], classes[train_idx_all]
X_train, y_train = trains_S0, classes
X_train_shift, y_train_shift = X_test[train_idx_all], classes[
train_idx_all]
X_train_all = np.concatenate((X_train, X_train_shift), axis=0)
y_train_all = np.concatenate((y_train, y_train_shift), axis=0)
sys.exit(0)
score_inter = clf.fit(X_train_all,
y_train_all).score(X_test, y_test)
scores[iteration] = score_inter.mean()
# print X_train.shape, y_train.shape
if channel_pos != 'S0':
# plsca = joblib.load(transform_fold+'/cca_transform_'+kw['subject']+'_'+channel_pos+'.model')
plsca = PLSCanonical(n_components=14)
# print X_test.shape, X_train.shape
# sys.exit(0)
plsca.fit(X_test[train_idx], X_train)
X_test_cca, X_train_cca = plsca.transform(X_test, X_train)
cca_score = clf.fit(X_train_cca,
y_train).score(X_test_cca, y_test)
cca_scores[iteration] = cca_score.mean()
iteration -= 1
# print scores
# print cca_scores
# sys.exit(0)
results.append(
['feat_TD4', 'lda', channel_pos,
np.mean(scores),
np.std(scores)])
results.append([
'feat_TD4', 'lda_cca', channel_pos,
np.mean(cca_scores),
np.std(cca_scores)
])
log_result(results, log_fold + '/' + log_file + '_' + str(kw['num']), 2)
print '----Log Fold:', log_fold, ', log_file: ', log_file + '_' + channel_pos + '_' + str(
kw['num'])
print '----training TD4 time elapsed:', time.time() - start_time
X_test = X[n // 2:]
Y_test = Y[n // 2:]
print("Corr(X)")
print(np.round(np.corrcoef(X.T), 2))
print("Corr(Y)")
print(np.round(np.corrcoef(Y.T), 2))
# #############################################################################
# Canonical (symmetric) PLS
# Transform data
# ~~~~~~~~~~~~~~
plsca = PLSCanonical(n_components=2)
plsca.fit(X_train, Y_train)
X_train_r, Y_train_r = plsca.transform(X_train, Y_train)
X_test_r, Y_test_r = plsca.transform(X_test, Y_test)
# Scatter plot of scores
# ~~~~~~~~~~~~~~~~~~~~~~
# 1) On diagonal plot X vs Y scores on each components
plt.figure(figsize=(12, 8))
plt.subplot(221)
plt.plot(X_train_r[:, 0], Y_train_r[:, 0], "ob", label="train")
plt.plot(X_test_r[:, 0], Y_test_r[:, 0], "or", label="test")
plt.xlabel("x scores")
plt.ylabel("y scores")
plt.title('Comp. 1: X vs Y (test corr = %.2f)' %
np.corrcoef(X_test_r[:, 0], Y_test_r[:, 0])[0, 1])
plt.xticks(())
plt.yticks(())
from sklearn import datasets
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.cross_decomposition import PLSCanonical
from sklearn.neighbors import KNeighborsClassifier
import math
from mlxtend.feature_selection import SequentialFeatureSelector as SFS
dataSet = datasets.load_digits()
data = dataSet["data"]
target = dataSet["target"]
plsca = PLSCanonical(n_components=2)
plsca.fit(data, target)
X_train_r, Y_train_r = plsca.transform(data, target)
knn = math.sqrt(len(X_train_r))
knn = KNeighborsClassifier(n_neighbors=int(knn))
Y_train_r = [int(Y_train_r[i]) for i in range(0, len(Y_train_r))]
k = knn.fit(X_train_r, Y_train_r)
print(k.score(X_train_r, Y_train_r))
knn = KNeighborsClassifier(n_neighbors=4)
sfs = SFS(knn,
k_features=3,
forward=True,
floating=False,
verbose=2,
def training_lda_TD4_intra(my_clfs, trains, classes, **kw):
start_time = time.time()
if (kw.has_key('log_fold')):
log_fold = root_path + '/result/' + kw['log_fold']
new_fold(log_fold)
chan_len = kw['chan_len']
action_num = kw['action_num']
cv = 3
results = []
results.append([
'Feat', 'Algorithm', 'n_components', 'Channel_Pos', 'Accuracy', 'std'
])
log_file = 'feat_' + kw['feature_type'] + '_intra'
clf = sklearn.lda.LDA(solver='svd',
shrinkage=None,
priors=None,
n_components=None,
store_covariance=False,
tol=0.0001)
data_num = trains.shape[0] / action_num
scores = sklearn.cross_validation.cross_val_score(clf,
trains,
classes,
cv=cv)
results.append([
'feat_TD4_cv_' + str(cv), 'lda', 'ALL', 0,
scores.mean(),
scores.std()
])
# 组内训练策略 9组数据
print '组内训练.............'
for idx, channel_pos in enumerate(kw['pos_list']):
# print '----training TD4 intra , channel_pos: ', channel_pos,'......'
trains_intra = trains[:, idx * chan_len:idx * chan_len + chan_len]
scores = sklearn.cross_validation.cross_val_score(clf,
trains_intra,
classes,
cv=cv)
results.append([
'feat_TD4_cv_' + str(cv), 'lda', 0, channel_pos,
scores.mean(),
scores.std()
])
# 中心训练策略
print '中心训练策略.............'
trains_intra_S0 = trains[:, 0:chan_len]
for idx, channel_pos in enumerate(kw['pos_list']):
if channel_pos == 'S0':
continue
tests_shift = trains[:, idx * chan_len:idx * chan_len + chan_len]
# if channel_pos == 'L2':
# print idx*chan_len, idx*chan_len+chan_len, tests_shift.shape, trains.shape
# sys.exit(0)
scores = clf.fit(trains_intra_S0, classes).score(tests_shift, classes)
results.append([
'feat_TD4_cv_' + str(cv), 'lda', 0,
'train S0' + ' test ' + channel_pos,
scores.mean(),
scores.std()
])
# 组训练策略（不同于组内训练策略） 5-fold
print '组训练策略.............'
trains_intra_S0 = trains[:, 0:chan_len]
kf = KFold(data_num, n_folds=cv)
for idx, channel_pos in enumerate(kw['pos_list']):
if channel_pos == 'S0':
continue
itera = cv
scores = np.zeros((itera, ))
# stds = np.zeros( (itera,) )
itera -= 1
trains_shift = trains[:, idx * chan_len:idx * chan_len + chan_len]
for train_idx, test_idx in kf:
train_idx_all = np.array([], np.int)
test_idx_all = np.array([], np.int)
for action_idx in range(action_num):
train_idx_all = np.concatenate(
(train_idx_all, train_idx * (action_idx + 1)), axis=0)
test_idx_all = np.concatenate(
(test_idx_all, test_idx * (action_idx + 1)), axis=0)
X_train = np.concatenate(
(trains_intra_S0[train_idx_all], trains_shift[train_idx_all]),
axis=0)
y_train = np.concatenate(
(classes[train_idx_all], classes[train_idx_all]), axis=0)
X_test = trains_shift[test_idx_all]
y_test = classes[test_idx_all]
# X_test = trains_shift
# y_test = classes
score = clf.fit(X_train, y_train).score(X_test, y_test)
scores[itera] = score.mean()
itera -= 1
# print scores
results.append([
'feat_TD4_cv_' + str(cv), 'lda', 0, 'S0 + ' + channel_pos,
np.mean(scores),
np.std(scores)
])
# 基于CCA的训练策略 5-fold 交叉验证
print 'CCA训练策略.............'
trains_S0 = trains[:, 0:chan_len]
n_components_list = [6, 8, 10, 12, 14, 16] # 子空间维数
# n_components_list = [12,14,16]
kf = KFold(data_num, n_folds=cv)
for n_components in n_components_list:
for idx, channel_pos in enumerate(kw['pos_list']):
if channel_pos == 'S0':
continue
itera = cv
scores = np.zeros((itera, ))
stds = np.zeros((itera, ))
itera -= 1
trains_shift = trains[:, idx * chan_len:idx * chan_len + chan_len]
for train_idx, test_idx in kf:
train_idx_all = np.array([], np.int)
test_idx_all = np.array([], np.int)
for action_idx in range(action_num):
train_idx_all = np.concatenate(
(train_idx_all, train_idx * (action_idx + 1)), axis=0)
test_idx_all = np.concatenate(
(test_idx_all, test_idx * (action_idx + 1)), axis=0)
# print train_idx_all.shape, train_idx_all, test_idx_all.shape, test_idx_all
# plsca.fit(trains_shift[train_idx_all], trains_S0[train_idx_all])
plsca = PLSCanonical(n_components=n_components)
plsca.fit(trains_shift, trains_S0)
trains_shift_cca, trains_S0_cca = plsca.transform(
trains_shift, trains_S0)
X_trains = np.concatenate(
(trains_S0_cca, trains_shift_cca[train_idx_all]), axis=0)
y_trains = np.concatenate((classes, classes[train_idx_all]),
axis=0)
score = clf.fit(X_trains,
y_trains).score(trains_shift_cca[test_idx_all],
classes[test_idx_all])
scores[itera] = score.mean()
# stds[itera] = score.std()
itera -= 1
results.append([
'feat_TD4_cv_' + str(cv), 'lda_cca', n_components,
'S0 + ' + channel_pos,
np.mean(scores),
np.std(scores)
])
log_result(results,
log_fold + '/' + log_file + '_action_1-' + str(action_num), 2)
print '----Log Fold:', log_fold, ', log_file: ', log_file + '_action_1-' + str(
action_num)
print '----training TD4 time elapsed:', time.time() - start_time
plt.gca().set_aspect('equal', adjustable='box')
plt.legend(['Cell volume', 'Age', 'Both'])
#NB: Strong colinearity between Age and Volume
# Transition rate prediction using PLS
X = dfc_g1[['vol_sm', 'Age', 'gr_sm']] # Design matrix
y = dfc_g1['G1S_logistic'] # Response var
# Drop NaN rows
I = np.isnan(dfc_g1['gr_sm'])
X = X.loc[~I].copy()
y = y[~I]
pls_model = PLSCanonical()
pls_model.fit(scale(X), y)
X_c, y_c = pls_model.transform(scale(X), y)
# Multiple linearregression on birth size and growth rate
df['bvol'] = df['Birth volume']
df['exp_gr'] = df['Exponential growth rate']
df['g1_len'] = df['G1 length']
model = smf.ols('g1_len ~ exp_gr + bvol', data=df).fit()
model.summary()
print model.pvalues
# Delete S/G2 after first time point
g1s_marked = []
for c in collated_filtered:
c = c[c['Phase'] != 'Daughter G1'].copy()
g1 = c[c['Phase'] == 'G1']
g1['G1S_mark'] = 0
def plot_compare_cross_decomposition():
# Dataset based latent variables model
n = 500
# 2 latents vars:
l1 = np.random.normal(size=n)
l2 = np.random.normal(size=n)
latents = np.array([l1, l1, l2, l2]).T
X = latents + np.random.normal(size=4 * n).reshape((n, 4))
Y = latents + np.random.normal(size=4 * n).reshape((n, 4))
X_train = X[:n // 2]
Y_train = Y[:n // 2]
X_test = X[n // 2:]
Y_test = Y[n // 2:]
print("Corr(X)")
print(np.round(np.corrcoef(X.T), 2))
print("Corr(Y)")
print(np.round(np.corrcoef(Y.T), 2))
# #############################################################################
# Canonical (symmetric) PLS
# Transform data
# ~~~~~~~~~~~~~~
plsca = PLSCanonical(n_components=2)
plsca.fit(X_train, Y_train)
X_train_r, Y_train_r = plsca.transform(X_train, Y_train)
X_test_r, Y_test_r = plsca.transform(X_test, Y_test)
# Scatter plot of scores
# ~~~~~~~~~~~~~~~~~~~~~~
# 1) On diagonal plot X vs Y scores on each components
plt.figure(figsize=(12, 8))
plt.subplot(221)
plt.scatter(X_train_r[:, 0],
Y_train_r[:, 0],
label="train",
marker="o",
s=25)
plt.scatter(X_test_r[:, 0], Y_test_r[:, 0], label="test", marker="o", s=25)
plt.xlabel("x scores")
plt.ylabel("y scores")
plt.title('Comp. 1: X vs Y (test corr = %.2f)' %
np.corrcoef(X_test_r[:, 0], Y_test_r[:, 0])[0, 1])
plt.xticks(())
plt.yticks(())
plt.legend(loc="best")
plt.subplot(224)
plt.scatter(X_train_r[:, 1],
Y_train_r[:, 1],
label="train",
marker="o",
s=25)
plt.scatter(X_test_r[:, 1], Y_test_r[:, 1], label="test", marker="o", s=25)
plt.xlabel("x scores")
plt.ylabel("y scores")
plt.title('Comp. 2: X vs Y (test corr = %.2f)' %
np.corrcoef(X_test_r[:, 1], Y_test_r[:, 1])[0, 1])
plt.xticks(())
plt.yticks(())
plt.legend(loc="best")
# 2) Off diagonal plot components 1 vs 2 for X and Y
plt.subplot(222)
plt.scatter(X_train_r[:, 0],
X_train_r[:, 1],
label="train",
marker="*",
s=50)
plt.scatter(X_test_r[:, 0], X_test_r[:, 1], label="test", marker="*", s=50)
plt.xlabel("X comp. 1")
plt.ylabel("X comp. 2")
plt.title('X comp. 1 vs X comp. 2 (test corr = %.2f)' %
np.corrcoef(X_test_r[:, 0], X_test_r[:, 1])[0, 1])
plt.legend(loc="best")
plt.xticks(())
plt.yticks(())
plt.subplot(223)
plt.scatter(Y_train_r[:, 0],
Y_train_r[:, 1],
label="train",
marker="*",
s=50)
plt.scatter(Y_test_r[:, 0], Y_test_r[:, 1], label="test", marker="*", s=50)
plt.xlabel("Y comp. 1")
plt.ylabel("Y comp. 2")
plt.title('Y comp. 1 vs Y comp. 2 , (test corr = %.2f)' %
np.corrcoef(Y_test_r[:, 0], Y_test_r[:, 1])[0, 1])
plt.legend(loc="best")
plt.xticks(())
plt.yticks(())
plt.show()
# #############################################################################
# PLS regression, with multivariate response, a.k.a. PLS2
n = 1000
q = 3
p = 10
X = np.random.normal(size=n * p).reshape((n, p))
B = np.array([[1, 2] + [0] * (p - 2)] * q).T
# each Yj = 1*X1 + 2*X2 + noize
Y = np.dot(X, B) + np.random.normal(size=n * q).reshape((n, q)) + 5
pls2 = PLSRegression(n_components=3)
pls2.fit(X, Y)
print("True B (such that: Y = XB + Err)")
print(B)
# compare pls2.coef_ with B
print("Estimated B")
print(np.round(pls2.coef_, 1))
pls2.predict(X)
# PLS regression, with univariate response, a.k.a. PLS1
n = 1000
p = 10
X = np.random.normal(size=n * p).reshape((n, p))
y = X[:, 0] + 2 * X[:, 1] + np.random.normal(size=n * 1) + 5
pls1 = PLSRegression(n_components=3)
pls1.fit(X, y)
# note that the number of components exceeds 1 (the dimension of y)
print("Estimated betas")
print(np.round(pls1.coef_, 1))
# #############################################################################
# CCA (PLS mode B with symmetric deflation)
cca = CCA(n_components=2)
cca.fit(X_train, Y_train)
X_train_r, Y_train_r = cca.transform(X_train, Y_train)
X_test_r, Y_test_r = cca.transform(X_test, Y_test)
def training_lda_TD4_inter(my_clfs, trains_S0, trains_shift, classes, **kw):
print 'training_lda_TD4_inter.........'
start_time = time.time()
log_fold = root_path + '/result/' + kw['log_fold']
new_fold(log_fold)
chan_len = kw['chan_len']
action_num = kw['action_num']
print "----training "+kw['feature_type']+" inter, training by position O, testing by electrode shift "
cv = 5
results = []
results.append(['Feat', 'Algorithm','Channel_Pos', 'Accuracy', 'std'])
log_file = 'feat_'+kw['feature_type']+'_inter'
clf = sklearn.lda.LDA(solver='svd', shrinkage=None, priors=None,
n_components=None, store_covariance=False,
tol=0.0001)
data_num = trains_S0.shape[0]/action_num
# print data_num
scores = sklearn.cross_validation.cross_val_score(
clf, trains_S0, classes, cv=cv)
results.append(['feat_TD4_cv_'+str(cv), 'lda', 'S0',
scores.mean(), scores.std()])
kf = KFold(data_num, n_folds=cv)
for idx, channel_pos in enumerate(kw['pos_list']):
X_test = trains_shift[:,idx*chan_len:idx*chan_len+chan_len]
y_test = classes
iteration = cv
scores = np.zeros((iteration,))
cca_scores = np.zeros((iteration,))
iteration -= 1
for train_idx, test_idx in kf:
train_idx_all = np.array([], np.int)
test_idx_all = np.array([], np.int)
for action_idx in range(action_num):
train_idx_all = np.concatenate( (train_idx_all, train_idx*action_idx), axis=0)
test_idx_all = np.concatenate( (test_idx_all, test_idx*action_idx), axis=0)
# X_train, y_train = trains_S0[train_idx_all], classes[train_idx_all]
X_train, y_train = trains_S0, classes
X_train_shift, y_train_shift = X_test[train_idx_all], classes[train_idx_all]
X_train_all = np.concatenate( (X_train, X_train_shift), axis=0)
y_train_all = np.concatenate( (y_train, y_train_shift), axis=0)
sys.exit(0)
score_inter = clf.fit(X_train_all, y_train_all).score(X_test, y_test)
scores[iteration] = score_inter.mean()
# print X_train.shape, y_train.shape
if channel_pos != 'S0':
# plsca = joblib.load(transform_fold+'/cca_transform_'+kw['subject']+'_'+channel_pos+'.model')
plsca = PLSCanonical(n_components=14)
# print X_test.shape, X_train.shape
# sys.exit(0)
plsca.fit(X_test[train_idx], X_train)
X_test_cca, X_train_cca = plsca.transform(X_test, X_train)
cca_score = clf.fit(X_train_cca, y_train).score(X_test_cca, y_test)
cca_scores[iteration] = cca_score.mean()
iteration -= 1
# print scores
# print cca_scores
# sys.exit(0)
results.append(['feat_TD4', 'lda',
channel_pos, np.mean(scores), np.std(scores)])
results.append(['feat_TD4', 'lda_cca',
channel_pos, np.mean(cca_scores), np.std(cca_scores)])
log_result(results, log_fold + '/' + log_file + '_' + str(kw['num']), 2)
print '----Log Fold:', log_fold, ', log_file: ', log_file + '_' + channel_pos + '_' + str(kw['num'])
print '----training TD4 time elapsed:', time.time() - start_time
# mean_shift = 0
# std_shift = 0
# for i in range(2, 10):
# mean_shift += results[i][4]
# std_shift += results[i][5]
# mean_shift /= 9
# std_shift /= 9
# results.append(['feat_TD4','lda(svd;tol=0.0001)', 'Shift_means', '1.0', mean_shift, std_shift])
# mean_all = 0
# std_all = 0
# for i in range(1, 10):
# mean_all += results[i][4]
# std_all += results[i][5]
# mean_all /= 9
# std_all /= 9
def training_lda_TD4_intra(my_clfs, trains, classes, **kw):
start_time = time.time()
if(kw.has_key('log_fold')):
log_fold = root_path + '/result/' + kw['log_fold']
new_fold(log_fold)
chan_len = kw['chan_len']
action_num = kw['action_num']
cv = 3
results = []
results.append(
['Feat', 'Algorithm','n_components', 'Channel_Pos', 'Accuracy', 'std'])
log_file = 'feat_'+kw['feature_type']+'_intra'
clf = sklearn.lda.LDA(solver='svd', shrinkage=None, priors=None,
n_components=None, store_covariance=False,
tol=0.0001)
data_num = trains.shape[0]/action_num
scores = sklearn.cross_validation.cross_val_score(clf, trains, classes, cv=cv)
results.append(['feat_TD4_cv_'+str(cv), 'lda', 'ALL', 0, scores.mean(), scores.std()])
# 组内训练策略 9组数据
print '组内训练.............'
for idx, channel_pos in enumerate(kw['pos_list']):
# print '----training TD4 intra , channel_pos: ', channel_pos,'......'
trains_intra = trains[:,idx*chan_len: idx*chan_len+chan_len]
scores = sklearn.cross_validation.cross_val_score(
clf, trains_intra, classes, cv=cv)
results.append(['feat_TD4_cv_'+str(cv), 'lda', 0, channel_pos, scores.mean(), scores.std()])
# 中心训练策略
print '中心训练策略.............'
trains_intra_S0 = trains[:,0:chan_len]
for idx, channel_pos in enumerate(kw['pos_list']):
if channel_pos == 'S0':
continue
tests_shift = trains[:,idx*chan_len: idx*chan_len+chan_len]
# if channel_pos == 'L2':
# print idx*chan_len, idx*chan_len+chan_len, tests_shift.shape, trains.shape
# sys.exit(0)
scores = clf.fit(trains_intra_S0, classes).score(tests_shift, classes)
results.append(['feat_TD4_cv_'+str(cv), 'lda', 0, 'train S0' + ' test ' + channel_pos, scores.mean(), scores.std()])
# 组训练策略（不同于组内训练策略） 5-fold
print '组训练策略.............'
trains_intra_S0 = trains[:,0:chan_len]
kf = KFold(data_num, n_folds=cv)
for idx, channel_pos in enumerate(kw['pos_list']):
if channel_pos == 'S0':
continue
itera = cv
scores = np.zeros( (itera,) )
# stds = np.zeros( (itera,) )
itera -= 1
trains_shift = trains[:,idx*chan_len: idx*chan_len+chan_len]
for train_idx, test_idx in kf:
train_idx_all = np.array([], np.int)
test_idx_all = np.array([], np.int)
for action_idx in range(action_num):
train_idx_all = np.concatenate( (train_idx_all, train_idx*(action_idx+1)), axis=0)
test_idx_all = np.concatenate( (test_idx_all, test_idx*(action_idx+1)), axis=0)
X_train = np.concatenate( (trains_intra_S0[train_idx_all], trains_shift[train_idx_all]), axis=0)
y_train = np.concatenate( (classes[train_idx_all], classes[train_idx_all]), axis=0)
X_test = trains_shift[test_idx_all]
y_test = classes[test_idx_all]
# X_test = trains_shift
# y_test = classes
score = clf.fit(X_train, y_train).score(X_test, y_test)
scores[itera] = score.mean()
itera -= 1
# print scores
results.append(['feat_TD4_cv_'+str(cv), 'lda', 0, 'S0 + '+channel_pos, np.mean(scores), np.std(scores)])
# 基于CCA的训练策略 5-fold 交叉验证
print 'CCA训练策略.............'
trains_S0 = trains[:,0:chan_len]
n_components_list = [6, 8, 10, 12, 14, 16] # 子空间维数
# n_components_list = [12,14,16]
kf = KFold(data_num, n_folds=cv)
for n_components in n_components_list:
for idx, channel_pos in enumerate(kw['pos_list']):
if channel_pos == 'S0':
continue
itera = cv
scores = np.zeros( (itera,) )
stds = np.zeros( (itera,) )
itera -= 1
trains_shift = trains[:,idx*chan_len: idx*chan_len+chan_len]
for train_idx, test_idx in kf:
train_idx_all = np.array([], np.int)
test_idx_all = np.array([], np.int)
for action_idx in range(action_num):
train_idx_all = np.concatenate( (train_idx_all, train_idx*(action_idx+1)), axis=0)
test_idx_all = np.concatenate( (test_idx_all, test_idx*(action_idx+1)), axis=0)
# print train_idx_all.shape, train_idx_all, test_idx_all.shape, test_idx_all
# plsca.fit(trains_shift[train_idx_all], trains_S0[train_idx_all])
plsca = PLSCanonical(n_components=n_components)
plsca.fit(trains_shift, trains_S0)
trains_shift_cca, trains_S0_cca = plsca.transform(trains_shift, trains_S0)
X_trains = np.concatenate( (trains_S0_cca, trains_shift_cca[train_idx_all]), axis=0)
y_trains = np.concatenate( (classes, classes[train_idx_all]), axis=0)
score = clf.fit(X_trains, y_trains).score(trains_shift_cca[test_idx_all], classes[test_idx_all])
scores[itera] = score.mean()
# stds[itera] = score.std()
itera -= 1
results.append(['feat_TD4_cv_'+str(cv), 'lda_cca', n_components, 'S0 + '+channel_pos, np.mean(scores), np.std(scores)])
log_result(results, log_fold + '/' + log_file + '_action_1-'+str(action_num), 2)
print '----Log Fold:', log_fold, ', log_file: ', log_file + '_action_1-'+str(action_num)
print '----training TD4 time elapsed:', time.time() - start_time
xt,yt = plssvd.fit_transform(dataTrain,Ytrain)
fig = plt.figure()
util.plotData(fig,xt,labelsTrain,classColors)
u = plssvd.x_weights_
plt.quiver(u[0,0],u[1,0],color='k',edgecolor='k',lw=1,scale=0.1,figure=fig)
plt.quiver(-u[1,0],u[0,0],color='k',edgecolor='k',lw=1,scale=0.4,figure=fig)
#%% PLS mode-A
lda = LDA()
nComponents = np.arange(1,nClasses+1)
plsCanScores = np.zeros((2,np.alen(nComponents)))
for i,n in enumerate(nComponents):
plscan = PLSCanonical(n_components=n)
plscan.fit(dataTrain,Ytrain)
dataTrainT = plscan.transform(dataTrain)
dataTestT = plscan.transform(dataTest)
plsCanScores[:,i] = util.classify(dataTrainT,dataTestT,labelsTrain,labelsTest)
fig = plt.figure()
util.plotAccuracy(fig,nComponents,plsCanScores)
plt.title('PLS Canonical accuracy',figure=fig)
plscan = PLSCanonical(n_components=2)
xt,yt = plscan.fit_transform(dataTrain,Ytrain)
fig = plt.figure()
util.plotData(fig,xt,labelsTrain,classColors)
u = plscan.x_weights_
plt.quiver(u[0,0],u[1,0],color='k',edgecolor='k',lw=1,scale=0.1,figure=fig)
plt.quiver(-u[1,0],u[0,0],color='k',edgecolor='k',lw=1,scale=0.4,figure=fig)
X_test = X[n // 2:]
Y_test = Y[n // 2:]
print("Corr(X)")
print(np.round(np.corrcoef(X.T), 2))
print("Corr(Y)")
print(np.round(np.corrcoef(Y.T), 2))
# #############################################################################
# Canonical (symmetric) PLS
# Transform data
# ~~~~~~~~~~~~~~
plsca = PLSCanonical(n_components=2)
plsca.fit(X_train, Y_train)
X_train_r, Y_train_r = plsca.transform(X_train, Y_train)
X_test_r, Y_test_r = plsca.transform(X_test, Y_test)
# Scatter plot of scores
# ~~~~~~~~~~~~~~~~~~~~~~
# 1) On diagonal plot X vs Y scores on each components
plt.figure(figsize=(12, 8))
plt.subplot(221)
plt.scatter(X_train_r[:, 0],
Y_train_r[:, 0],
label="train",
marker="o",
c="b",
s=25)
plt.scatter(X_test_r[:, 0],
Y_test_r[:, 0],
y_train = y[:n / 2]
x_test = x[n / 2:]
y_test = y[n / 2:]
print("corr(x)")
print(np.round(np.corrcoef(x.T), 2))
print("corr(y)")
print(np.round(np.corrcoef(y.T), 2))
#################################################################
# Canonical (symmetric) PLS
# transform the data
plsca = PLSCanonical(n_components=2)
plsca.fit(x_train, y_train)
x_train_r, y_train_r = plsca.transform(x_train, y_train)
x_test_r, y_test_r = plsca.transform(x_test, y_test)
# Scatter plot of scores
# ~~~~~~~~~~~~~~~~~~~~~~
# 1) On diagonal plot x vs y scores on each components
plt.figure(figsize=(12, 8))
plt.subplot(221)
plt.plot(x_train_r[:, 0], y_train_r[:, 0], "ob", label="train")
plt.plot(x_test_r[:, 0], y_test_r[:, 0], "or", label="test")
plt.xlabel("x scores")
plt.ylabel("y scores")
plt.title('Comp. 1: x vs y (test corr = %.2f)' %
np.corrcoef(x_test_r[:, 0], y_test_r[:, 0])[0, 1])
plt.xticks(())
plt.yticks(())