def train_svm(params, suffix, train_X, train_Y, test_X, test_Y):
C = params['C']
kernel = params['kernel']
model = SVC(gamma='scale', probability=True, C=C, kernel=kernel)
print("Params C:", C, "kernel:", kernel)
model.fit(train_X, train_Y)
print("Train score", model.score(train_X, train_Y))
test_score = model.score(test_X, test_Y)
print("Test score", test_score)
return test_score, None
def phoneAccelerometerISVM():
print("Loading data...")
data = pd.read_csv("./Train_Phone-Acc-nexus4_1-a.csv")
print("Done!")
# Parse data and make bike vs not-biking classification using an SVM.
# Note: I'm assuming a window width of 500
print("Finding time series windows indexes for each class kind...")
previousClassLabel = str(data.get_value(data.index[0], 'gt'))
pos = 0
y = []
X = []
window = 500
while pos < data.shape[0]:
# Make y label.
if str(data.iloc[pos]['gt']) == 'sit':
y.append(1)
else:
y.append(-1)
# Make X row.
X.append(data.iloc[pos:pos + window]['y'])
# Move to the next window
pos += window
print("Done!")
# Build and fit the SVM.
print("Training SVM on all data accelerometer data...")
X = np.array(X)
y = np.array(y)
#clfs = LinearSVC()
clfs = SVC()
clfs.fit(X, y)
print("Done!")
# print("Predicting accelerometer classes on all data using SVM...")
# ypred = predict(X, clfs.coef_.reshape(len(clfs.coef_.ravel()), 1))
# print("Done!")
# error = calculateTotalAbsoluteError(y, ypred) / y.shape[0]
# print("Accelerometer training error (Means kind of nothing): %f"%error)
# Cross validation
print("Training SVM on accelerometer training only data...")
X_train, X_test, y_train, y_test = train_test_split(X, y, stratify=y, test_size = 0.1) #, random_state = 0
clfs = SVC()
clfs.fit(X_train, y_train)
yhat = clfs.predict(X_test)
print("Abs Error = %f"%( calculateTotalAbsoluteError(yhat, y_test)/len(yhat)))
print("Test data mean accuracy SVM score: %f"%clfs.score(X_test, y_test))
f1_c0 = f1_score(y_test, clfs.predict(X_test), pos_label=1, average='binary')
#print("Test data f1 score for class -1: %f"%(f1_c0))
print("Test data f1 score for class +1: %f" % (f1_c0))
print("Done!")
if Y_label != 'NULL' or random.random() > 0:
if Y_label == event_name:
Y = 1
else:
Y = 0
if i == 0:
X_all = X
Y_all = Y
i = 1
else:
X_all = np.vstack((X_all, X))
Y_all = np.append(Y_all, Y)
i += 1
# print (i)
# print (np.sum(X_all, axis = 1))
# print(X_all, Y_all)
clf = SVC(kernel=chi2_kernel)
# clf = SVC()
clf.fit(X_all, Y_all)
print(clf.score(X_all, Y_all))
print(clf.predict(X_all))
fread.close()
cPickle.dump(clf, open(output_file, "wb"))
print 'SVM trained successfully for event %s!' % (event_name)
trn_embedding = embed(X_trn, triplet_model)
val_embedding = embed(X_val, triplet_model)
# print (X_trn, X_val)
# print (trn_embedding, val_embedding)
# print (triplet_model.get_weights())
clf = SVC(
# class_weight='balanced',
probability=True,
# tol=1e-4,
)
clf.fit(trn_embedding, Y_trn)
print(clf.score(val_embedding, Y_val))
print(clf.predict_proba(val_embedding))
print(roc_auc_score(Y_val, clf.predict(val_embedding)))
print(classification_report(Y_val, clf.predict(val_embedding), digits=4))
all_files = [x[:-8] for x in os.listdir(ALL_FILES)]
X = [
pickle.load(open(os.path.join(FEATURE_PATH, x + ".fkmeans"), "rb"),
encoding='latin1') for x in all_files
]
# Y = [ranks[x.split()[0].strip()] for x in all_files]
proba = clf.predict_proba(embed(np.array(X), triplet_model))
# print(len(proba), len(proba[0]), proba[0])
test_labels = []
for email in emails:
email_id = email.id
prefix_train_pos = 'email_' + str(email_id)
if email_id % 5 != 0:
train_arrays.append(model.docvecs[prefix_train_pos])
train_labels.append(int(email.label))
else:
test_arrays.append(model.docvecs[prefix_train_pos])
test_labels.append(int(email.label))
classifier = SVC()
classifier.fit(numpy.array(train_arrays), numpy.array(train_labels))
print("Overall score is %f." % classifier.score(numpy.array(test_arrays), numpy.array(test_labels)))
corrects = []
wrongs = []
for email in emails:
email_id = email.id
prefix_train_pos = 'email_' + str(email_id)
if email_id % 5 == 0:
prediction = classifier.predict([model.docvecs[prefix_train_pos]])[0]
actual = int(email.label)
if prediction != actual:
wrongs.append((email.id, prediction, actual))
else:
# print(max(classifier.predict_proba([model.docvecs[prefix_train_pos]])[0]), actual)
corrects.append(email.id)
