from ValidationUtils import cv_benchmark_model
# %%
# impor data
# specs = pd.read_csv('./luzrawSpectra/nirMatrix.csv') # cut spectra
specs = pd.read_csv("/Users/maxprem/nirPy/calData_full.csv") # full spectra
lab = pd.read_excel("/Users/maxprem/nirGit/nirpy/luzrawSpectra/labData.xlsx")
# input wavenumber to cut spectra
specs = cut_specs(specs, 4100, 5500)
# specs = cut_specs(specs, 4100, 5500)
# %%
X, y, wave_number, ref = importLuzCol(specs, lab, 4)
# split dataset in train and test data
X_train, X_test, y_train, y_test = train_test_split(
X, y, test_size=0.3, random_state=42
)
# %%
# transformation pipeline
# scale y
y_scaler = GlobalStandardScaler()
y_train = y_scaler.fit_transform(y_train)
y_test = y_scaler.transform(y_test)
opt_comp = optimal_n_comp(X, y, n_comp)
opt_model = pls_regression(X, y, opt_comp)
pls_scores(X, y, opt_model)
#specs = pd.read_csv("./luzrawSpectra/nirMatrix.csv") # cut spectra
specs = pd.read_csv("/Users/maxprem/nirPy/calData_full.csv") # full spectra
lab = pd.read_excel("/Users/maxprem/nirGit/nirpy/luzrawSpectra/labData.xlsx")
# input wavenumber to specs = cut_specs(specs, 4100, 5500)
# specs = cut_specs(specs, 4100, 5500)
X, y, wl, ref = importLuzCol(specs, lab, 2)
# splitting dataset
"""to be continued with test set"""
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.2,
random_state=42)
#########################
# scaling and transformingfrom ChemUtils import EmscScaler, GlobalStandardScaler, SavgolFilter
# scale y
y_scaler = GlobalStandardScaler()
y_train = y_scaler.fit_transform(y_train)
y_test = y_scaler.transform(y_test)