def __init__(self,
feature_path,
spectrograms_path,
BC_datapath,
Kfold_path,
type,
annotation="Is Eeg Usable For Clinical Purposes"):
""""
annotation="Quality Of Eeg" or "Is Eeg Usable For Clinical Purposes"
"""
self.get_data = preprossingPipeline(BC_datapath=BC_datapath)
self.LDA = None #LDA model
self.PCA = None #PCA model
self.TSNE = None #TSNE model
self.max_windows = 30
self.max_files = 10
self.le = preprocessing.LabelEncoder()
with open(os.path.join(os.getcwd(), Kfold_path), "r") as read_file:
Kfold = json.load(read_file)
trainNames = Kfold[f"train_0"]
testNames = Kfold[f"test_0"]
self.type = type
if type == "Feture_test":
self.X_train, self.Y_train, self.filenames_train, self.train_id = self.get_vectors(
trainNames, feature_path, annotation)
self.X_test, self.Y_test, self.filenames_test, self.test_id = self.get_vectors(
testNames, feature_path, annotation)
self.le.fit(np.append(self.filenames_train, self.filenames_test))
self.X_train = scale_data(self.X_train)
self.X_test = scale_data(self.X_test)
if type == "Spectrograms_test":
self.X_train, self.Y_train, self.filenames_train, self.train_id = self.get_vectors(
trainNames, spectrograms_path, annotation)
self.X_test, self.Y_test, self.filenames_test, self.test_id = self.get_vectors(
testNames, spectrograms_path, annotation)
self.le.fit(np.append(self.filenames_train, self.filenames_test))
self.X_train = scale_data(self.X_train)
self.X_test = scale_data(self.X_test)
if type == "Spectrograms_balance":
self.X_test, self.Y_test, self.filenames_test, self.test_id = self.get_balance(
5, spectrograms_path, annotation)
self.X_train, self.Y_train, self.filenames_train, self.train_id = self.get_balance(
26, spectrograms_path, annotation)
self.le.fit(self.filenames_test)
if type == "Feature_balance":
self.X_test, self.Y_test, self.filenames_test, self.test_id = self.get_balance(
5, feature_path, annotation)
self.X_train, self.Y_train, self.filenames_train, self.train_id = self.get_balance(
26, feature_path, annotation)
self.le.fit(self.filenames_test)
def make_pca(windows, make_spectograms=False):
if make_spectograms:
path_pca = os.path.join(os.getcwd(), 'Villads', 'PCA_spectograms.sav')
else:
path_pca = os.path.join(os.getcwd(), 'Villads',
'PCA_feature_vectors_1.sav')
pca = pickle.load(open(path_pca, 'rb'))
windows = scale_data(windows)
windows = pca.transform(windows)
return windows
def plot_comand(feature_path, path_pca, BC_datapath, newplot=True):
pca = pickle.load(open(path_pca, 'rb'))
get_data = preprossingPipeline(BC_datapath=BC_datapath)
feature_vectors, labels, filenames, window_id = get_data.make_label(
quality=None, is_usable=None, max_files=10, path=feature_path)
while True:
print("What you want to plot, options pca or")
command = input()
if command == "pca":
feature_vectors, labels, filenames, window_id = get_data.make_label(
quality=None, is_usable=None, max_files=10, path=feature_path)
scaled_feature_vectors = scale_data(feature_vectors)
pca_vectors = pca.transform(scaled_feature_vectors)
print("what components ex 0 1")
components = input()
components = components.split(" ")
plot_pca_interactiv(pca_vectors, labels, window_id, components[0],
components[1])
if command == "break":
break
if command == "spec" or command == "EEG":
print("Insert index")
idx = int(input())
if newplot == False:
get_data.plot_window(window_id[idx][0],
window_id[idx][1],
type=command)
else:
data, time, chanels = get_data.plot_window(window_id[idx][0],
window_id[idx][1],
type=command,
plot=True)
data = np.array(data).T
df = pd.DataFrame(data, columns=chanels, index=time)
fig = make_subplots(rows=len(chanels), cols=1)
for i, ch in enumerate(chanels):
fig.add_trace(px.line(df, y=ch, x=df.index),
row=(i + 1),
col=1)
fig = px.line(df, y=chanels[0], x=df.index)
fig.show()
feature_vectors_9_10,labels_9_10,filenames_1,idx_1= C.make_label(max_files=15,quality=[9],is_usable=None,path = path, max_windows=60)
feature_vectors_5,labels_5,filenames_2,idx_2= C.make_label(max_files=15,quality=[5],is_usable=None,path = path, max_windows=60)
fv1, l1, f1, i1 = C.make_label(max_files=70,quality=None,is_usable='Yes',path = path, max_windows=2)
fv2, l2, f2, i2 = C.make_label(max_files=70,quality=None,is_usable='No',path = path, max_windows=2)
fv=np.vstack((feature_vectors_1,feature_vectors_5))
feature_vectors=np.vstack((fv,feature_vectors_9_10))
fv_new = np.vstack((fv1,fv2))
filenames=filenames+filenames_1+filenames_2
labels=labels_1+labels_9_10+labels_5
index = idx+idx_1+idx_2
l = l1+l2
scaled_feature_vector=scale_data(feature_vectors)
scaled_new = scale_data(fv_new)
pca = PCA()
pca.fit(scaled_feature_vector)
pca_fv=pca.transform(scaled_feature_vector)
pca_fv1 = pca.transform(scaled_new)
neigh = KNeighborsClassifier(n_neighbors=3)
neigh.fit(pca_fv, labels)
J = []
for i in range(126):
J.append(np.argmax(neigh.predict_proba(pca_fv1[i:i+1])))
J2 = []
from Villads.PCA_TSNE_classes import scale_data from Visualization.PCA_TSNE_plot import plot_pca import numpy as np from sklearn.discriminant_analysis import LinearDiscriminantAnalysis path='/Users/villadsstokbro/Dokumenter/DTU/KID/3. semester/Fagprojekt/spectograms_all_ch/' C=preprossingPipeline(BC_datapath='/Users/villadsstokbro/Dokumenter/DTU/KID/3. semester/Fagprojekt/BrainCapture/dataEEG',mac=True) feature_vectors_1,labels_1,filenames,idx= C.make_label(max_files=5,quality=None,is_usable='No',path = path,max_windows=10) feature_vectors_9_10,labels_9_10,filenames_1,idx_1= C.make_label(max_files=5,quality=None,is_usable='Yes',path = path) feature_vectors=np.vstack((feature_vectors_1,feature_vectors_9_10)) filenames=filenames+filenames_1 labels=labels_1+labels_9_10 scaled_feature_vectors=scale_data(feature_vectors) pca=PCA() tsne=TSNE() pca.fit(scaled_feature_vectors) pca_vectors=pca.transform(scaled_feature_vectors) tsne_vectors=tsne.fit_transform(scaled_feature_vectors) labels_new=[a[0] for a in idx+idx_1] clf = LinearDiscriminantAnalysis() ld = clf.fit(scaled_feature_vectors,labels) plot_pca(pca_vectors,labels,np.unique(labels)) plot_pca(tsne_vectors,labels,np.unique(labels),model='TSNE') plot_pca(pca_vectors,labels_new,np.unique(labels_new)) plot_pca(tsne_vectors,labels_new,np.unique(labels_new),model='TSNE') plot_pca(ld.transform(scaled_feature_vectors),)
def fit_pca(fv):
scaled_new_fv = scale_data(fv)
pca = PCA()
pca.fit(fv)
pca_fv = pca.transform(fv)
return pca_fv