2-model_creation.py

from Packages import *
st.set_page_config(page_title="NIRS Utils", page_icon=":goat:", layout="wide")
from Modules import *
from Class_Mod.DATA_HANDLING import *

st.session_state["interface"] = st.session_state.get('interface')
if st.session_state["interface"] == 'simple':
    hide_pages("Predictions")
def nn(x):
    return x is not None
########################################################################################
reg_algo = ["","Full-PLS", "Locally Weighted PLS", "Interval-PLS"]

# page Design
st.header("Calibration Model Development", divider='blue')
st.write("Create a predictive model, then use it for predicting your target variable(chemical values) from NIRS spectra")
M1, M2, M3 = st.columns([2,2,2])
M4, M5 = st.columns([6,2])
st.write("---")
st.header("Model Diagnosis", divider='blue')

M7, M8 = st.columns([2,2])
M7.write('Predicted vs Measured values')
M8.write('Residuals plot')
M9, M10 = st.columns([2,2])
M9.write("-- Save the model --")




# CSV files loader
xcal_csv = M3.file_uploader("Select NIRS Data", type="csv", help=" :mushroom: select a csv matrix with samples as rows and lambdas as columns")
ycal_csv = M3.file_uploader("Select corresponding Chemical Data", type="csv", help=" :mushroom: select a csv matrix with samples as rows and chemical values as a column")


if xcal_csv is not None and ycal_csv is not None:
        # Select list for CSV delimiter
        sep = M3.selectbox("Select csv separator - _detected_: " + str(find_delimiter('data/'+xcal_csv.name)), options=[";", ","], index=[";", ","].index(str(find_delimiter('data/'+xcal_csv.name))), key=0)
        # Select list for CSV header True / False
        hdr = M3.selectbox("indexes column in csv? - _detected_: " + str(find_col_index('data/'+xcal_csv.name)), options=["no", "yes"], index=["no", "yes"].index(str(find_col_index('data/'+xcal_csv.name))), key=1)
        if hdr == 'yes':
            col = 0
        else:
            col = False
        rd_seed = M1.slider("Customize Train-test split", min_value=1, max_value=100, value=42, format="%i")
        x, y = utils.load_csv(xcal_csv, ycal_csv, autoremove_na=True, sep=sep, x_hdr=0, y_hdr=0, x_index_col=col, y_index_col=col)
        # Split data into training and test sets using the kennard_stone method and correlation metric, 25% of data is used for testing
        train_index, test_index = train_test_split_idx(x, y=y, method="kennard_stone", metric="correlation", test_size=0.25, random_state=rd_seed)
        # Assign data to training and test sets
        X_train, y_train, X_test, y_test = pd.DataFrame(x[train_index]), pd.DataFrame(y[train_index]), pd.DataFrame(x[test_index]), pd.DataFrame(y[test_index])
        y_train = y_train.iloc[:,0]
        y_test = y_test.iloc[:,0]



        ############################# Regression modelling ##########################################
        regression_algo = M1.selectbox("Choose the algorithm for regression", options=reg_algo, key = 12)
        if regression_algo == reg_algo[1]:
            # Train model with model function from application_functions.py
            Reg = PinardPlsr(x_train = X_train, x_test = X_test,y_train = y_train, y_test = y_test)
            reg_model = Reg.model_
            #M2.dataframe(Pin.pred_data_)

        elif regression_algo == reg_algo[2]:
            reg_model = model_LWPLSR(xcal_csv, ycal_csv, sep, hdr)

        elif regression_algo == reg_algo[3]:
            s = M2.number_input(label='Enter the maximum number of intervalls', min_value=1, max_value=6, value=3)
            it = M2.number_input(label='Enter the number of iterations', min_value=50, max_value=1000, value=100)
            progress_text = "The model is being created. Please wait."
            
            Reg = TpeIpls(x_train = X_train, x_test=X_test, y_train = y_train, y_test = y_test, scale = False, Kfold = 3, n_intervall = s)
            pro = M1.progress(0, text="The model is being created. Please wait!")
            rega = Reg.BandSelect(n_iter=it)
            pro.empty()
            M1.progress(100, text = "The model has successfully been  created!")
            
            time.sleep(1)
            reg_model = Reg.model_
            M2.table(rega[0])
        
        ################# Model analysis ############

        if regression_algo in reg_algo[1:]:
            yc = Reg.pred_data_[0]
            ycv = Reg.pred_data_[1]
            yt = Reg.pred_data_[2]
            
            
            M1.write("-- Performance metrics --")
            M1.dataframe(Reg.metrics_)

            M7.pyplot(reg_plot([y_train, y_train, y_test],[yc, ycv, yt]))
            M8.pyplot(resid_plot([y_train, y_train, y_test],[yc, ycv, yt]))
            
            
            #model_export = M1.selectbox("Choose way to export", options=["pickle", "joblib"], key=20)
            model_name = M9.text_input('Give it a name')
            if M9.button('Export Model'):
                #export_package = __import__(model_export)
                with open('data/models/model_' + model_name + '_on_' + xcal_csv.name + '_and_' + ycal_csv.name + '_data_' + '.pkl','wb') as f:
                    joblib.dump(reg_model, f)
                
                if regression_algo == reg_algo[3]:
                    rega[1].sort()
                    pd.DataFrame(rega[1]).to_csv('data/models/model_' + model_name + '_on_' + xcal_csv.name + '_and_' + ycal_csv.name + '_data_''Wavelengths_index.csv', sep = ';')
                st.write('Model Exported')
                

                # create a report with information on the model
                ## see https://stackoverflow.com/a/59578663
        #M4.pyplot(reg_plot(meas==(ycal_csv,ycal_csv,ycal_csv], pred=[ycal_csv,ycal_csv,ycal_csv]))


                if st.session_state['interface'] == 'simple':
                    st.page_link('pages\\3-prediction.py', label = 'Keep on keepin\' on to predict your values !')