def train_classifiers(data_files, valid_runs_dict_uiuc, valid_runs_dict_whasc):
'''
Produces test data and tests whether projecting matrices into the tangent space finds the correct discriminative connection.
Parameters:
data_files (list of pairs (filename,data)): the input data
valid_runs_dict_uiuc (dictionary): dictionary containing valid runs for each patient
valid_runs_dict_whasc (dictionary): dictionary containing valid runs for each patient
Returns:
accDict (dictionary): mean accuracy on each file's data
simDict (dictionary): mean cosine similarity of classifier coefficients for each file
matDict (dictionary): mean confusion matrix for each file
corrDict (dictionary): before and after projection correlations
spearDict (dictionary): before and after projection spearman correlations
'''
accDict = {}
simDict = {}
matDict = {}
corrDict = {}
spearDict = {}
simArr = []
for fname, data in data_files:
# get time series data to make covariance matrices
X = np.array([sample['TimeSeries'] for sample in data['samples']
]) # if data_selector(sample)])
y = np.array([
get_label_8(sample['Group'], sample['Location'])
for sample in data['samples']
]) # if data_selector(sample)])
# gsr seems to produce a rank deficient covariance matrix, so oas regularization is necessary
covest = Covariances()
ts = TangentSpace()
#sym = to_symm_mat(0,33)
#diag = to_upper_tri(1)
svc = SVC(kernel='linear')
clf_riem = make_pipeline(covest, ts, svc)
rf = RandomForestClassifier(200)
clf_rf = make_pipeline(covest, ts, rf)
covest2 = Correlations()
svc2 = SVC(kernel='linear')
get_tri_inds = to_upper_tri(0)
clf_cov = make_pipeline(covest2, get_tri_inds, svc2)
#Check clustering
#to_TS = make_pipeline(covest,ts)
#X_in_TS = to_TS.transform(X)
#kmeans = KMeans(n_clusters=4,random_state=0).fit(X_in_TS)
# Monte Carlo, in theory should run this len(y)^2 times, but I need to save my poor computer's memory.
accRiemList = []
accCovList = []
accRfList = []
coeffArr = []
matRiemList = []
corrArrBefore = []
corrArrAfter = []
spearArrBefore = []
spearArrAfter = []
rs = StratifiedShuffleSplit(n_splits=100, test_size=.3)
for i, (train_inds, test_inds) in enumerate(rs.split(X, y)):
X_train, X_test, y_train, y_test = X[train_inds], X[test_inds], y[
train_inds], y[test_inds]
X_train_cov, X_test_cov, y_train_cov, y_test_cov = X_train.copy(
), X_test.copy(), y_train.copy(), y_test.copy()
clf_riem.fit(X_train, y_train)
clf_rf.fit(X_train, y_train)
clf_cov.fit(X_train_cov, y_train_cov)
#get riemann svm coefficients
coeffArr.append(clf_riem[2].coef_)
#compare correlation
corr_coeffs_before = np.corrcoef(np.vstack(
[x[np.triu_indices(33)].flatten() for x in X_train]),
rowvar=False)
corrArrBefore.append(np.linalg.norm(corr_coeffs_before))
#spearman correlation
spearman_coeffs_before, _ = scipy.stats.spearmanr(np.vstack(
[x[np.triu_indices(33)].flatten() for x in X_train]),
axis=0)
spearArrBefore.append(np.linalg.norm(spearman_coeffs_before))
ref = ts.reference_
covs = covest.transform(X_train)
mapped = ts.transform(covs)
corr_coeffs_after = np.corrcoef(mapped, rowvar=False)
spearman_coeffs_after = scipy.stats.spearmanr(mapped, axis=0)
corrArrAfter.append(np.linalg.norm(corr_coeffs_after))
spearArrAfter.append(np.linalg.norm(spearman_coeffs_after))
y_pred = clf_riem.predict(X_test)
y_pred_cov = clf_cov.predict(X_test_cov)
y_pred_rf = clf_rf.predict(X_test)
# save accuracy
accRiemList.append(accuracy_score(y_pred, y_test))
accCovList.append(accuracy_score(y_pred_cov, y_test_cov))
accRfList.append(accuracy_score(y_pred_rf, y_test))
# confusion matrix
mat = confusion_matrix(y_test,
y_pred,
normalize='true',
labels=[0, 1, 2, 3, 4, 5, 6, 7])
matRiemList.append(mat)
for z in range(0, len(coeffArr[0])):
class_z_coeffs = [x[z] for x in coeffArr]
cos_sim = cosine_similarity(class_z_coeffs)
upperTri = cos_sim[np.triu_indices(cos_sim.shape[0], 1)]
cos_avg = np.mean(upperTri.flatten())
simArr.append(cos_avg)
avgMatRiem = sum(matRiemList) / len(matRiemList)
simDict.update({fname: simArr})
matDict.update({fname: avgMatRiem})
riemAcc = np.mean(accRiemList)
covAcc = np.mean(accCovList)
rfAcc = np.mean(accRfList)
accDict.update(
{'raw_data': {
'riem': riemAcc,
'rf': rfAcc,
'cov': covAcc
}})
corrDict.update({
'raw_data': {
'before': np.mean(corrArrBefore),
'after': np.mean(corrArrAfter)
}
})
spearDict.update({
'raw_data': {
'before': np.mean(spearArrBefore),
'after': np.mean(spearArrAfter)
}
})
print("Mean Accuracy w/ Riemann on data " + fname + ": " +
str(riemAcc))
print("Mean Accuracy w/ Cov on data " + fname + ": " + str(covAcc))
print("Mean Accuracy w/ RF on data " + fname + ": " + str(rfAcc))
print("----------------")
return accDict, corrDict, spearDict, matDict, simDict
subject = name.split('_')
data = loadmat(f_name)
data_IS = data[list(data.keys())[-1]]
data_tensor = [data_IS[0][0]]
for j in range(len(data_IS)):
if j == 0:
k = 1
else:
k = 0
for i in range(k, len(data_IS[j])):
temp = [data_IS[j][i]]
data_tensor = np.concatenate((data_tensor, temp), axis=0)
cov = Covariances(estimator='lwf')
ts = TangentSpace()
cov.fit(data_tensor, label)
cov_train = cov.transform(data_tensor)
ts.fit(cov_train, label)
ts_train = ts.transform(cov_train)
ts_shape = (np.shape(ts_train))
pca = PCA()
ann = MLPClassifier(max_iter=5000)
clf = BaggingClassifier(base_estimator=ann, bootstrap=True)
pipe = Pipeline(steps=[('pca', pca), ('clf', clf)])
param_grid = {
'pca__n_components': [20, 30, 40, 50, 60, 70, 80, 90, 100],
'clf__base_estimator__hidden_layer_sizes':
[(10), (20), (30), (40), (50), (60), (70), (80), (90), (100), (110),
(120), (130), (140), (150), (160), (170), (180)],
'clf__n_estimators': [
10, 20, 30, 40, 50, 60, 70, 80, 90, 100, 110, 120, 130, 140, 150,
160, 170, 180
