app.py

#from Modules_manager.PCA_ import pca_maker

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 *

# graphical delimiter
st.write("---")

# load images for web interface
img_sselect = Image.open("images\sselect.JPG")
img_general = Image.open("images\general.JPG")
img_predict = Image.open("images\predict.JPG")

# TOC menu on the left
with st.sidebar:
    st.markdown("[Sample Selection](#sample-selection)")
    st.markdown("[Model Development](#create-a-model)")
    st.markdown("[Predictions Making](#predict)")


# Page header
with st.container():
    st.subheader("Plateforme d'Analyses Chimiques pour l'Ecologie-PACE :goat:")
    st.title("NIRS Utils")
    st.write("Samples selection (PCA, [UMAP](https://umap-learn.readthedocs.io/en/latest/how_umap_works.html), ...), Predictive Modelling ([Pinard](https://github.com/GBeurier/pinard), [LWPLSR](https://doi.org/10.1002/cem.3209), ...), and Predictions using your data (CSV or DX files) and/or PACE NIRS Database.")
    #st.image(img_general)


################################### Data Loading and Visualization ########################################
container1 = st.container(border=True)
col2, col1 = st.columns([3, 1])


container2 = st.container(border=True)
container2.header("Exploratory Data Analysis-Multivariable Data Analysis", divider='blue')
scores, loadings, pc = st.columns([2, 3, 0.5])
influence, hotelling, qexp = st.columns([2, 2, 1])


with container1:
    col1.header("NIRS Data Loading", divider='blue')
    col2.header("Spectral Data Visualization", divider='blue')

    with col1:
        # loader for csv file containing NIRS spectra
        sselectx_csv = st.file_uploader("Load NIRS Data", type="csv", help=" :mushroom: select a csv matrix with samples as rows and lambdas as columns", key=5)
        if sselectx_csv is not None:
            # Select list for CSV delimiter
            psep = st.selectbox("Select csv separator - _detected_: " + str(find_delimiter('data/'+sselectx_csv.name)), options=[";", ","], index=[";", ","].index(str(find_delimiter('data/'+sselectx_csv.name))), key=9)
            # Select list for CSV header True / False
            phdr = st.selectbox("indexes column in csv? - _detected_: " + str(find_col_index('data/'+sselectx_csv.name)), options=["no", "yes"], index=["no", "yes"].index(str(find_col_index('data/'+sselectx_csv.name))), key=31)
            if phdr == 'yes':
                col = 0
            else:
                col = False
            data_import = pd.read_csv(sselectx_csv, sep=psep, index_col=col)
            st.success("The data have been loaded successfully", icon="✅")
            ## Visualize spectra

    if sselectx_csv is not None: 
        with col2:
            fig, ax = plt.subplots(figsize = (30,7))
            data_import.T.plot(legend=False, ax = ax, color = 'blue')
            ax.set_xlabel('Wavelength/Wavenumber', fontsize=18)
            ax.set_ylabel('Signal', fontsize=18)
            plt.margins(x = 0)
            st.pyplot(fig)
                    
            st.write("Summary")
            info = pd.DataFrame({'N':[data_import.shape[0]],
                                    'Min': [np.min(data_import)],
                                    'Max':[np.max(data_import)],}, index = ['Values']).T
            info.rename_axis('information')
            st.table(data=info)
######################################################################################

############################## Exploratory data analysis ###############################
with container2:
    if sselectx_csv is not None:
        plot_type=['', 'PCA','UMAP', 'NMF']
        cluster_methods = ['', 'Kmeans','UMAP', 'AP']

        with pc:
            type_plot = st.selectbox("Dimensionality reduction techniques: ", options=plot_type, key=37)
            type_cluster = st.selectbox("Clustering techniques: ", options=cluster_methods, key=38)
            # compute UMAP - umap_maker in application_functions.py
            if type_plot == 'PCA':
                model = LinearPCA(data_import, Ncomp=5)
            elif type_plot =='UMAP':
                model = Umap(x = data_import, n_components = 5, n_neighbors = 20 , min_dist = 0)



        if type_plot in ['PCA', 'UMAP']:
            # add 2 select lists to choose which component to plot
            axis1 = pc.selectbox("x-axis", options = model.scores_.columns, index=0)
            axis2 = pc.selectbox("y-axis", options = model.scores_.columns, index=1)
            axis3 = pc.selectbox("z-axis", options = model.scores_.columns, index=2)

            if type_cluster == 'Kmeans':
                 cl = Sk_Kmeans(pd.concat([model.scores_.loc[:,axis1], model.scores_.loc[:,axis2], model.scores_.loc[:,axis3]], axis = 1), max_clusters = 30)

            with scores:
                    t = model.scores_
                    if type_cluster in ['Kmeans','UMAP', 'AP']:
                        st.write('Scree plot')
                        fig2 = px.scatter(cl.inertia_.T, y = 'inertia')
                        st.plotly_chart(fig2)

                        ncluster = st.number_input(min_value=2, max_value=30, value=3, label = 'Select the desired number of clusters')
                        data, colors = cl.fit_optimal(nclusters=ncluster)
                        #fig = px.scatter(data, x=axis1, y=axis2, color= colors)
                        st.write('Scores plot')
                        fig = px.scatter_3d(data, x=axis1, y=axis2, z = axis3, color=colors)

                        
                        
                    else:
                        fig = px.scatter_3d(t, x=axis1, y=axis2, z = axis3)

                    st.plotly_chart(fig)
    
                        
            if type_plot =='PCA':
                with loadings:
                        st.write('Loadings plot')
                        p = model.loadings_
                        pp = pd.concat([p, pd.DataFrame(np.arange(p.shape[0]), index=p.index, columns=['wl'])], axis =1)
                        df1 = pp.melt(id_vars="wl")

                        fig = px.line(df1, x = 'wl', y = 'value', color='variable')
                        fig.update_layout(
                            legend=dict(x=1, y=0,
                                        font=dict(
                                            family="Courier", size=12, color="black"),
                                            bordercolor="Black", borderwidth=2)
                                            )
                        st.plotly_chart(fig)




                with influence:
                        st.write('Influence plot')
                        ax1 = st.selectbox("Component", options=model.scores_.columns, index=3)

                        leverage = model.leverage_
                        residuals = model.residuals
                        fig = px.scatter(x=leverage[ax1], y=residuals[ax1], color = leverage[ax1]*residuals[ax1])
                        st.plotly_chart(fig)

                with hotelling:

                        st.write('T²-Hotelling vs Q residuals plot')
                        ax2 = st.selectbox("Component", options=model.scores_.columns, index=4)

                        t = model.scores_
                        fig = px.scatter(t, x=axis1, y=t.columns[1])
                        st.plotly_chart(fig)

                with qexp:
                        pass

            
            else:
                    st.markdown('Select a dimensionality reduction technique from the dropdown list')


########################################################################################
# Model creation module
container2 = st.container(border=True)

M1, M2, M3 = st.columns([2,2,2])
M4, M5 = st.columns([6,2])
container3 = st.container(border=True)
M7, M8 = st.columns([2,2])

available_regression_algo = ["","SciKitLearn PLSR", "Jchemo Local Weighted PLSR", "Intervalle Selection PLSR"]
with container2:
    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")
    # 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("Choose seed", min_value=1, max_value=1212, 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])
        #############################

        regression_algo = M1.selectbox("Choose the algorithm for regression", options=available_regression_algo, key = 12)
        
        if regression_algo == 'SciKitLearn PLSR':
            # 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 == 'Jchemo Local Weighted PLSR':
            reg_model = model_LWPLSR(xcal_csv, ycal_csv, sep, hdr)
        
        elif regression_algo == "Intervalle Selection PLSR":
             s = M2.number_input(label='Enter the maximum number of intervalls', min_value=1, max_value=6, value="min")
             reg_model = TpeIpls(x_train= X_train, y_train= y_train, x_test=X_test, y_test= y_test,Kfold= 3,scale= True, n_intervall = 3)
             reg_model.tune(n_iter=10)
        
        if regression_algo in ["SciKitLearn PLSR", "Jchemo Local Weighted PLSR", "Intervalle Selection PLSR"]:
             with container3:
                st.header("Model Diagnosis", divider='blue')
                yc = Reg.pred_data_[0]
                ycv = Reg.pred_data_[1]
                yt = Reg.pred_data_[2]
                M7.write('Predicted vs Measured values')
                M7.pyplot(reg_plot([y_train, y_train, y_test],[yc, ycv, yt]))
                M8.write('Residuals plot')
                M8.pyplot(resid_plot([y_train, y_train, y_test],[yc, ycv, yt]))


        # Export the model with pickle or joblib
        if regression_algo != '':
            M1.write("-- Performance metrics --")
            M1.dataframe(Reg.metrics_)
            M1.write("-- Save the model --")
            #model_export = M1.selectbox("Choose way to export", options=["pickle", "joblib"], key=20)
            model_name = M1.text_input('Give it a name')
            if M1.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)
                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]))
        

# graphical delimiter
st.write("---")







#M9, M10, M11 = st.columns([2,2,2])
# Prediction module - TO BE DONE !!!!!
with st.container():
    st.header("Predictions making")
    st.write("---")
    st.write("Predict chemical values from NIRS")
    model_column, space, file_column= st.columns((2, 1, 1))
    NIRS_csv = file_column.file_uploader("Select NIRS Data to predict", type="csv", help=" :mushroom: select a csv matrix with samples as rows and lambdas as columns")
    export_folder = './data/predictions/'
    export_name = 'Predictions_of_'
    if NIRS_csv:
        export_name += str(NIRS_csv.name[:-4])
        qsep = file_column.selectbox("Select csv separator - _detected_: " + str(find_delimiter('data/'+NIRS_csv.name)), options=[";", ","], index=[";", ","].index(str(find_delimiter('data/'+NIRS_csv.name))), key=2)
        qhdr = file_column.selectbox("indexes column in csv? - _detected_: " + str(find_col_index('data/'+NIRS_csv.name)), options=["no", "yes"], index=["no", "yes"].index(str(find_col_index('data/'+NIRS_csv.name))), key=3)

        # Load the model with joblib
        model_column.write("Load your saved predictive model")
        model_name_import = model_column.selectbox('Choose file:', options=os.listdir('data/models/'), key = 21)
        if model_name_import != ' ':
            export_name += '_with_' + str(model_name_import[:-4])
            with open('data/models/'+ model_name_import,'rb') as f:
                model_loaded = joblib.load(f)
            if model_loaded:
                model_column.success("The model has been loaded successfully", icon="✅")
    result = ''

    if st.button("Predict"):
        # use prediction function from application_functions.py to predict chemical values
        result = prediction(NIRS_csv, qsep, qhdr, model_loaded)
        st.write('Predicted values are: ')
        st.dataframe(result.T)
        pd.DataFrame(result).to_csv(export_folder + export_name + '.csv')
        # export to local drive - Download
        download_results(export_folder + export_name + '.csv', export_name + '.csv')
        # create a report with information on the prediction
        ## see https://stackoverflow.com/a/59578663