class MyPLS():
def __init__(self,
n_components=2,
scale=True,
max_iter=500,
tol=1e-06,
copy=True):
self.pls = PLSRegression(n_components, scale, max_iter, tol, copy)
def fit(self, X, Y):
self.pls.fit(X, Y)
return self.pls
def predict(self, X, copy=True):
return self.pls.predict(X, copy).flatten()
def score(self, X, Y, sample_weight=None):
return self.pls.score(X, Y, sample_weight)
def get_params(self, deep=True):
return self.pls.get_params(deep)
def set_params(self, **parameters):
self.pls.set_params(**parameters)
return self
@property
def intercept_(self):
return 0
@property
def coeff_(self):
return self.pls.coef_
def PLSReg_loop(X, y, params, number_rnd):
row = 0
results = pd.DataFrame(columns=[
'n_components', 'max_iter', 'random_state', 'r2_test', 'r2_train'
])
n_components = params['n_components']
max_iter = params['max_iter']
random_states = np.random.randint(0, 10000, number_rnd)
x_load = []
y_load = []
for n in n_components:
for m in max_iter:
x_loc = []
y_loc = []
for r in random_states:
print(
'PARAMS n_components: {}, max_iter: {}, random_state: {}'.
format(n, m, r))
plsr = PLSRegression()
plsr.set_params(**{'n_components': n, 'max_iter': m})
X_train, X_test, y_train, y_test = train_test_split(
X, y, test_size=0.2, random_state=r)
#plsr.fit(X_train, y_train)
#x_loc += [plsr.x_loadings_]
#y_loc += [plsr.y_loadings_]
r2_test = 0. #plsr.score(X_test, y_test)
r2_train = 0. #plsr.score(X_train, y_train)
results.loc[row] = [n, m, r, r2_test, r2_train]
row += 1
x_load += [np.array(x_loc)]
y_load += [np.array(y_loc)]
x_load = np.array(x_load)
y_load = np.array(y_load)
results.to_csv(params['name'] + '_results')
with open(params['name'] + '_x_load', 'wb') as f:
pickle.dump(x_load, f)
with open(params['name'] + '_y_load', 'wb') as f:
pickle.dump(y_load, f)
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])
if result_sim >= 0.85:
sim_count += 1
print("Data " + str(i + 1) + " : " + str(result_sim))
accuracy = float(sim_count) / float(len(y_score))
print("Accuracy: " + str(accuracy))
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])
print("similarity of test example " + str(index) + " = " + str(result))
if (1 - math.fabs(result)) <= tol:
sim_count += 1
print "Count of correct prediction = ", sim_count
acc = float(sim_count) / float(len(y_score))