def br_caller(df, method, params, expected, expected_baseline):
df = norm(df, [[580, 600]])
result, result_baseline = remove_baseline(df, method, params=params)
np.testing.assert_array_almost_equal(expected,
np.array(result['wvl'].iloc[5, 0:5]))
np.testing.assert_array_almost_equal(
expected_baseline, np.array(result_baseline['wvl'].iloc[5, 0:5]))
def test_norm():
df = pd.read_csv(get_path('test_data.csv'), header=[0, 1])
result = norm.norm(df, [[580, 590], [590, 600]], col_var='wvl')
np.testing.assert_almost_equal(result['wvl'].iloc[0, :].sum(), 2.0)
import numpy as np
import pandas as pd
from libpyhat.examples import get_path
from libpyhat.transform.norm import norm
from libpyhat.regression.regression import regression
np.random.seed(1)
df = pd.read_csv(get_path('test_data.csv'), header=[0, 1])
df = norm(df, [[580, 600]])
x = df['wvl']
y = df[('comp', 'SiO2')]
def test_PLS():
regress = regression(method=['PLS'],
params=[{
'n_components': 3,
'scale': False
}])
regress.fit(x, y)
prediction = np.squeeze(regress.predict(x))
rmse = np.sqrt(np.average((prediction - y)**2))
expected = 9.568890617713505
np.testing.assert_almost_equal(rmse, expected)
regress.calc_Qres_Lev(x)
Qres_expected = [
0.04055878, 0.04188589, 0.04159104, 0.04374264, 0.04080776, 0.04072383,
0.04057845, 0.04053754, 0.04056575, 0.04077855
]
np.testing.assert_array_almost_equal(regress.Q_res[0:10], Qres_expected)
def norm(self, ranges, col_var):
self.df = norm.norm(self.df, ranges, col_var=col_var)
import numpy as np
import pandas as pd
from libpyhat.examples import get_path
import libpyhat.clustering.cluster as cluster
import libpyhat.transform.norm as norm
np.random.seed(1)
df = pd.read_csv(get_path('test_data.csv'), header=[0, 1])
df = norm.norm(df, [[585, 600]])
def test_spectral():
kws = {
'n_clusters': 3,
'n_init': 10,
'affinity': 'rbf',
'gamma': 1.0,
'n_neighbors': 5,
'degree': 3,
'coef0': 1,
'n_jobs': 1,
'random_state': 1
}
result = cluster.cluster(df, 'wvl', 'Spectral', [], kws)
clusters = np.squeeze(np.array(result['Spectral']))
cluster_count = [
np.count_nonzero(clusters == 1),
np.count_nonzero(clusters == 2),
np.count_nonzero(clusters == 3)
]
cluster_count.sort()
assert cluster_count == [8, 32, 63]
import numpy as np
import pandas as pd
from libpyhat.examples import get_path
from libpyhat.transform import cal_tran, norm
from libpyhat.transform.caltran_utils import prepare_data
np.random.seed(1)
data1 = pd.read_csv(get_path('caltran_test1.csv'),header=[0,1])
data2 = pd.read_csv(get_path('caltran_test2.csv'),header=[0,1])
data1, data2 = prepare_data(data1,data2,'Target','Target')
#normalize the data for numerical stability
data1 = norm.norm(data1,[[240,250]])
data2 = norm.norm(data2,[[240,250]])
def cal_tran_helper(data1,data2,params, expected, single_spect = False):
ct = cal_tran.cal_tran(params)
ct.derive_transform(data1['wvl'], data2['wvl'])
if single_spect:
result = ct.apply_transform(data1['wvl'].iloc[0,:])
else:
result = ct.apply_transform(data1['wvl'])
if len(result.shape)>1:
np.testing.assert_array_almost_equal(np.array(result,dtype=float)[:, 4], expected)
else:
np.testing.assert_array_almost_equal(np.array(result,dtype=float)[4], expected)
def test_no_transform():
params = {'method':'None'}
ct = cal_tran.cal_tran(params)
