From c826ed63589b632ffc1b204a15e83ccf210df537 Mon Sep 17 00:00:00 2001
From: DIANE <abderrahim.diane@cefe.cnrs.fr>
Date: Wed, 14 Aug 2024 16:10:26 +0200
Subject: [PATCH] -correct csv dialect detector(replacing csv module by
csvclever) -rearranging model creation script -st.cache_data
---
src/Class_Mod/DATA_HANDLING.py | 11 +-
src/Class_Mod/RegModels.py | 3 +-
src/Class_Mod/VarSel.py | 7 +-
src/pages/2-model_creation.py | 836 ++++++++++++++++-----------------
4 files changed, 410 insertions(+), 447 deletions(-)
diff --git a/src/Class_Mod/DATA_HANDLING.py b/src/Class_Mod/DATA_HANDLING.py
index 17e4dcb..7f73676 100644
--- a/src/Class_Mod/DATA_HANDLING.py
+++ b/src/Class_Mod/DATA_HANDLING.py
@@ -3,14 +3,17 @@ from .Evaluation_Metrics import metrics
## try to automatically detect the field separator within the CSV
def find_delimiter(filename):
- sniffer = csv.Sniffer()
- with open(filename) as fp:
- delimiter = sniffer.sniff(fp.read(200)).delimiter
+ import clevercsv
+ with open(filename, newline='') as csvfile:
+ delimiter = clevercsv.Sniffer().sniff(csvfile.read(100)).delimiter
+ # sniffer = csv.Sniffer()
+ # with open(filename) as fp:
+ # delimiter = sniffer.sniff(fp.read(200)).delimiter
return delimiter
def find_col_index(filename):
with open(filename) as fp:
- lines = pd.read_csv(fp, skiprows=3, nrows=3, index_col=False, sep=str(find_delimiter(filename)))
+ lines = pd.read_csv(fp, skiprows=3, nrows=3, index_col=False, sep=find_delimiter(filename))
col_index = 'yes' if lines.iloc[:,0].dtypes != np.float64 else 'no'
return col_index
diff --git a/src/Class_Mod/RegModels.py b/src/Class_Mod/RegModels.py
index 6e4cc01..0063bcc 100644
--- a/src/Class_Mod/RegModels.py
+++ b/src/Class_Mod/RegModels.py
@@ -185,12 +185,13 @@ class TpeIpls(Regmodel):
# ## Modelling
folds = KF_CV().CV(x = x2[0], y = np.array(self._ytrain), n_folds = self._nfolds)
try:
+
Model = PLSRegression(scale = False, n_components = params['n_components'])
yp = KF_CV().cross_val_predictor(model = Model, folds = folds, x = x2[0], y = np.array(self._ytrain))
self._cv_df = KF_CV().metrics_cv(y = np.array(self._ytrain), ypcv = yp, folds =folds)[1]
except ValueError as ve:
+ Model = PLSRegression(scale = False, n_components = 1)
params["n_components"] = 1
- Model = PLSRegression(scale = False, n_components = params['n_components'])
yp = KF_CV().cross_val_predictor(model = Model, folds = folds, x = x2[0], y = np.array(self._ytrain))
self._cv_df = KF_CV().metrics_cv(y = np.array(self._ytrain), ypcv = yp, folds =folds)[1]
# self._cv_df['Average'] = self._cv_df.mean(axis = 1)
diff --git a/src/Class_Mod/VarSel.py b/src/Class_Mod/VarSel.py
index a2d5363..9f60fc4 100644
--- a/src/Class_Mod/VarSel.py
+++ b/src/Class_Mod/VarSel.py
@@ -69,10 +69,11 @@ class TpeIpls:
try:
Model = PLSRegression(scale = self.scale,n_components = params['n_components'])
Model.fit(self.x_train.iloc[:,id], self.y_train)
- except ValueError as ve:
- params["n_components"] = 1
- Model = PLSRegression(scale = self.scale,n_components = params['n_components'])
+ except ValueError as ve:
+ Model = PLSRegression(scale = self.scale,n_components = 1)
Model.fit(self.x_train.iloc[:,id], self.y_train)
+ params['n_components'] = 1
+
## make prediction
yc = Model.predict(self.x_train.iloc[:,id]).ravel()
diff --git a/src/pages/2-model_creation.py b/src/pages/2-model_creation.py
index f89dd4e..a9f995a 100644
--- a/src/pages/2-model_creation.py
+++ b/src/pages/2-model_creation.py
@@ -34,192 +34,227 @@ def delete_dir():
def increment():
st.session_state.counter += 1
# #################################### Methods ##############################################
-@st.cache_data
-def csv_loader(x,y):
- file_name = str(xcal_csv.name) +' and '+ str(ycal_csv.name)
- xfile = pd.read_csv(xcal_csv, decimal='.', sep=sepx, index_col=col, header=0)
- yfile = pd.read_csv(ycal_csv, decimal='.', sep=sepy, index_col=col)
- return xfile, yfile, file_name
+class lw:
+ def __init__(self, Reg_json, pred):
+ self.model_ = Reg_json['model']
+ self.best_hyperparams_ = Reg_json['best_lwplsr_params']
+ self.pred_data_ = [pd.json_normalize(Reg_json[i]) for i in pred]
+
+# @st.cache_data
+# # def tpeipls_(change, n_intervall, n_iter):
+# Reg = TpeIpls(train = [X_train, y_train], test=[X_test, y_test], n_intervall = n_intervall, n_iter=n_iter)
+# # time.sleep(1)
+# # reg_model = Reg.model_
+# # global intervalls
+# # intervalls = Reg.selected_features_.T
+# # intervalls_with_cols = Reg.selected_features_.T
+# # for i in range(intervalls.shape[0]):
+# # for j in range(intervalls.shape[1]):
+# # intervalls_with_cols.iloc[i,j] = spectra.columns[intervalls.iloc[i,j]]
+# # rega = Reg.selected_features_
+# return Reg #, reg_model, intervalls, intervalls_with_cols, rega
+def auto_execute(func):
+ func()
+ return func
-@st.cache_data
-def dx_loader(change):
- with NamedTemporaryFile(delete=False, suffix=".dx") as tmp:
- tmp.write(data_file.read())
- tmp_path = tmp.name
- chem_data, spectra, meta_data, meta_data_st = read_dx(file = tmp_path)
- os.unlink(tmp_path)
- return chem_data, spectra, meta_data, meta_data_st
+# ####################################### page preamble #######################################
+st.title("Calibration Model Development") # page title
+st.markdown("Create a predictive model, then use it for predicting your target variable (chemical data) from NIRS spectra")
+M0, M00 = st.columns([1, .4])
+M0.image("./images/model_creation.png", use_column_width=True) # graphical abstract
-@st.cache_data
-def visualize(change):
-
- if np.array(spectra.columns).dtype.kind in ['i','f']:
- colnames = spectra.columns
- else:
- colnames = np.arange(spectra.shape[1])
- # 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(spectra, y = y, method="kennard_stone", metric="correlation", test_size=0.25, random_state=42)
- # Assign data to training and test sets
- X_train, y_train = pd.DataFrame(spectra.iloc[train_index,:]), y.iloc[train_index]
- X_test, y_test = pd.DataFrame(spectra.iloc[test_index,:]), y.iloc[test_index]
+################################################################# Begin : I- Data loading and preparation ######################################
+files_format = ['csv', 'dx'] # Supported files format
+file = M00.radio('Select files format:', options = files_format,horizontal=True) # Select a file format
+spectra = pd.DataFrame() # preallocate the spectral data block
+y = pd.DataFrame() # preallocate the target(s) data block
+match file:
+ # load csv file
+ case 'csv':
+ with M00:
+ # Load X-block data
+ xcal_csv = st.file_uploader("Select NIRS Data", type="csv", help=" :mushroom: select a csv matrix with samples as rows and lambdas as columns")
+ if xcal_csv:
+ sepx = st.radio("Select separator (X file) - _detected_: " + str(find_delimiter('data/'+xcal_csv.name)),
+ options=[";", ","], index=[";", ","].index(str(find_delimiter('data/'+xcal_csv.name))), key=0,horizontal=True)
+ hdrx = st.radio("samples name (X file)? - _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,horizontal=True)
+ match hdrx:
+ case "yes":
+ col = 0
+ case "no":
+ col = False
+ else:
+ st.warning('Insert your spectral data file here!')
+
+ # Load Y-block data
+ ycal_csv = st.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 ycal_csv:
+ sepy = st.radio("Select separator (Y file) - _detected_: " + str(find_delimiter('data/'+ycal_csv.name)),
+ options=[";", ","], index=[";", ","].index(str(find_delimiter('data/'+ycal_csv.name))), key=2,horizontal=True)
+ hdry = st.radio("samples name (Y file)? - _detected_: " + str(find_col_index('data/'+ycal_csv.name)),
+ options=["no", "yes"], index=["no", "yes"].index(str(find_col_index('data/'+ycal_csv.name))), key=3,horizontal=True)
+
+ match hdry:
+ case "yes":
+ col = 0
+ case "no":
+ col = False
- #### insight on loaded data
- # M0, M000 = st.columns([1, .4])
- fig1, ax1 = plt.subplots( figsize = (12,3))
- spectra.T.plot(legend=False, ax = ax1, linestyle = '--')
- ax1.set_ylabel('Signal intensity')
- ax1.margins(0)
- plt.tight_layout()
- # M0.pyplot(fig1) ######## Loaded graph
- # fig1.savefig("./Report/figures/spectra_plot.png")
+ else:
+ st.warning('Insert your target data file here!')
+
+
+ # AFTER LOADING BOTH X AND Y FILES
+ if xcal_csv and ycal_csv:
+ # create a str instance for storing the hash of both x and y data
+ xy_hash = ''
+ from io import StringIO
+ for i in ["xcal_csv", "ycal_csv"]:
+ stringio = StringIO(eval(f'{i}.getvalue().decode("utf-8")'))
+ xy_hash += str(hash_data(str(stringio)))
+
+ @st.cache_data
+ def csv_loader(change):
+ file_name = str(xcal_csv.name) +' and '+ str(ycal_csv.name)
+ xfile = pd.read_csv(xcal_csv, decimal='.', sep=sepx, index_col=col, header=0)
+ yfile = pd.read_csv(ycal_csv, decimal='.', sep=sepy, index_col=col)
+ xfile.to_csv("./Report/datasets/"+xcal_csv.name,sep = ';', encoding='utf-8', mode='a')
+ yfile.to_csv("./Report/datasets/"+ycal_csv.name,sep = ';', encoding='utf-8', mode='a')
+ return xfile, yfile, file_name
+ xfile, yfile, file_name = csv_loader(change =xy_hash)
+
+
+ if yfile.shape[1]>0 and xfile.shape[1]>0 :
+
+ # prepare x data
+ spectra, meta_data = col_cat(xfile)
+ spectra = pd.DataFrame(spectra).astype(float)
+
+ # prepare y data
+ chem_data, idx = col_cat(yfile)
+ if chem_data.shape[1]>1:
+ yname = M00.selectbox('Select target', options=chem_data.columns)
+ y = chem_data.loc[:,yname]
+ else:
+ y = chem_data.iloc[:,0]
+
+ ### warning
+ if spectra.shape[0] != y.shape[0]:
+ st.warning('X and Y have different sample size')
+ y = pd.DataFrame
+ spectra = pd.DataFrame
- fig2, ax2 = plt.subplots(figsize = (12,3))
- sns.histplot(y, color="deeppink", kde = True,label="y",ax = ax2, fill=True)
- sns.histplot(y_train, color="blue", kde = True,label="y (train)",ax = ax2, fill=True)
- sns.histplot(y_test, color="green", kde = True,label="y (test)",ax = ax2, fill=True)
- ax2.set_xlabel('y')
- plt.legend()
- plt.tight_layout()
+ else:
+ st.error('Error: The data has not been loaded successfully, please consider tuning the decimal and separator !')
+
+ # Load .dx file
+ case 'dx':
+ with M00:
+ data_file = st.file_uploader("Select Data", type=".dx", help=" :mushroom: select a dx file")
+ if data_file:
+ file_name = str(data_file.name)
+ ## creating the temp file
+ with NamedTemporaryFile(delete=False, suffix=".dx") as tmp:
+ tmp.write(data_file.read())
+ tmp_path = tmp.name
+ with open(tmp.name, 'r') as dd:
+ dxdata = dd.read()
+ xy_hash = str(dxdata)
+ with open('Report/datasets/'+data_file.name, 'w') as dd:
+ dd.write(dxdata)
+ ## load and parse the temp dx file
+ @st.cache_data
+ def dx_loader(change):
+ chem_data, spectra, meta_data, meta_data_st = read_dx(file = tmp_path)
+ os.unlink(tmp_path)
+ return chem_data, spectra, meta_data, meta_data_st
+ chem_data, spectra, meta_data, meta_data_st = dx_loader(change = hash_data(xy_hash))
+
+ if not spectra.empty:
+ st.success("The data have been loaded successfully", icon="✅")
+ if chem_data.shape[1]>0:
+
+ yname = st.selectbox('Select target', options=chem_data.columns)
+ measured = chem_data.loc[:,yname] > 0
+ y = chem_data.loc[:,yname].loc[measured]
+ spectra = spectra.loc[measured]
+ else:
+ st.warning('Warning: your file includes no target variables to model !', icon="âš ï¸")
- # M0.pyplot(fig2)
- # fig2.savefig("./Report/figures/Histogram.png")
-
- # M000.write('Loaded data summary')
- # M000.write(pd.DataFrame([desc_stats(y_train),desc_stats(y_test),desc_stats(y)], index =['train', 'test', 'total'] ).round(2))
- stats=pd.DataFrame([desc_stats(y_train),desc_stats(y_test),desc_stats(y)], index =['train', 'test', 'total'] ).round(2)
-
- return X_train, X_test,y_train, y_test, colnames, train_index, test_index, stats, fig1, fig2
+ else :
+ st.warning('Load your file here!')
-@st.cache_data
-def pls_(change):
- Reg = Plsr(train = [X_train, y_train], test = [X_test, y_test], n_iter=200)
- reg_model = Reg.model_
- rega = Reg.selected_features_
- return Reg, reg_model, rega
+################################################### END : I- Data loading and preparation ####################################################
-@st.cache_data
-def tpeipls_(change, n_intervall, n_iter):
- Reg = TpeIpls(train = [X_train, y_train], test=[X_test, y_test], n_intervall = n_intervall, n_iter=n_iter)
- time.sleep(1)
- reg_model = Reg.model_
- intervalls = Reg.selected_features_.T
- intervalls_with_cols = Reg.selected_features_.T
- for i in range(intervalls.shape[0]):
- for j in range(intervalls.shape[1]):
- intervalls_with_cols.iloc[i,j] = spectra.columns[intervalls.iloc[i,j]]
- rega = Reg.selected_features_
- return Reg, reg_model, intervalls, intervalls_with_cols, rega
-# ####################################### page preamble #######################################
-st.title("Calibration Model Development") # page title
-st.markdown("Create a predictive model, then use it for predicting your target variable (chemical data) from NIRS spectra")
-M0, M00 = st.columns([1, .4])
-M0.image("./images/model_creation.png", use_column_width=True) # graphical abstract
-####################################### I- Data preparation
-files_format = ['.csv', '.dx'] # Supported files format
-file = M00.radio('Select files format:', options = files_format,horizontal=True) # Select a file format
-spectra = pd.DataFrame() # preallocate the spectral data block
-y = pd.DataFrame() # preallocate the target(s) data block
-match file:
- ## load .csv file
- case '.csv':
- # Load X-block data
- xcal_csv = M00.file_uploader("Select NIRS Data", type="csv", help=" :mushroom: select a csv matrix with samples as rows and lambdas as columns")
- if xcal_csv:
- sepx = M00.radio("Select separator (X file) - _detected_: " + str(find_delimiter('data/'+xcal_csv.name)),
- options=[";", ","], index=[";", ","].index(str(find_delimiter('data/'+xcal_csv.name))), key=0,horizontal=True)
- hdrx = M00.radio("samples name (X file)? - _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,horizontal=True)
- match hdrx:
- case "yes":
- col = 0
- case "no":
- col = False
- else:
- M00.warning('Insert your spectral data file here!')
-
- # Load Y-block data
- ycal_csv = M00.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 ycal_csv:
- sepy = M00.radio("Select separator (Y file) - _detected_: " + str(find_delimiter('data/'+ycal_csv.name)),
- options=[";", ","], index=[";", ","].index(str(find_delimiter('data/'+ycal_csv.name))), key=2,horizontal=True)
- hdry = M00.radio("samples name (Y file)? - _detected_: " + str(find_col_index('data/'+ycal_csv.name)),
- options=["no", "yes"], index=["no", "yes"].index(str(find_col_index('data/'+ycal_csv.name))), key=3,horizontal=True)
-
- match hdry:
- case "yes":
- col = 0
- case "no":
- col = False
- else:
- M00.warning('Insert your target data file here!')
+################################################### BEGIN : visualize and split the data ####################################################
+st.header("I - Data visualization", divider='blue')
+if not spectra.empty and not y.empty:
+ @st.cache_data
+ def visualize(change):
- if xcal_csv and ycal_csv:
- xfile, yfile, file_name = csv_loader(x = hash_data(xcal_csv.name+str(xcal_csv.size)), y =hash_data(ycal_csv.name+str(ycal_csv.size)))
-
- if yfile.shape[1]>0 and xfile.shape[1]>0 :
- spectra, meta_data = col_cat(xfile)
- chem_data, idx = col_cat(yfile)
- if chem_data.shape[1]>1:
- yname = M00.selectbox('Select target', options=chem_data.columns)
- y = chem_data.loc[:,yname]
- else:
- y = chem_data.iloc[:,0]
-
+ if np.array(spectra.columns).dtype.kind in ['i','f']:
+ colnames = spectra.columns
+ else:
+ colnames = np.arange(spectra.shape[1])
- spectra = pd.DataFrame(spectra).astype(float)
- # if not meta_data.empty :
- # st.write(meta_data)
- if spectra.shape[0] != y.shape[0]:
- M00.warning('X and Y have different sample size')
- y = pd.DataFrame
- spectra = pd.DataFrame
+ # 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(spectra, y = y, method="kennard_stone", metric="correlation", test_size=0.25, random_state=42)
- else:
- M00.error('Error: The data has not been loaded successfully, please consider tuning the decimal and separator !')
-
- ## Load .dx file
- case '.dx':
- data_file = M00.file_uploader("Select Data", type=".dx", help=" :mushroom: select a dx file")
- if not data_file:
- M00.warning('Load your file here!')
- else :
- file_name = str(data_file.name)
- chem_data, spectra, meta_data, meta_data_st = dx_loader(change = hash_data(str(data_file.size)))
- if not spectra.empty:
- M00.success("The data have been loaded successfully", icon="✅")
- if chem_data.shape[1]>0:
- yname = M00.selectbox('Select target', options=chem_data.columns)
- measured = chem_data.loc[:,yname] > 0
- y = chem_data.loc[:,yname].loc[measured]
- spectra = spectra.loc[measured]
- else:
- M00.warning('Warning: your file includes no target variables to model !', icon="âš ï¸")
+ # Assign data to training and test sets
+ X_train, y_train = pd.DataFrame(spectra.iloc[train_index,:]), y.iloc[train_index]
+ X_test, y_test = pd.DataFrame(spectra.iloc[test_index,:]), y.iloc[test_index]
-# visualize and split the data
-st.header("I - Data visualization", divider='blue')
-if not spectra.empty and not y.empty:
- X_train, X_test,y_train, y_test, colnames, train_index, test_index, stats, fig1, fig2= visualize(hash_data(y+np.median(spectra)))
+ #### insight on loaded data
+ # M0, M000 = st.columns([1, .4])
+ fig1, ax1 = plt.subplots( figsize = (12,3))
+ spectra.T.plot(legend=False, ax = ax1, linestyle = '-', linewidth = 0.6)
+ ax1.set_ylabel('Signal intensity')
+ ax1.margins(0)
+ plt.tight_layout()
+
+ fig2, ax2 = plt.subplots(figsize = (12,3))
+ sns.histplot(y, color="deeppink", kde = True,label="y",ax = ax2, fill=True)
+ sns.histplot(y_train, color="blue", kde = True,label="y (train)",ax = ax2, fill=True)
+ sns.histplot(y_test, color="green", kde = True,label="y (test)",ax = ax2, fill=True)
+ ax2.set_xlabel('y')
+ plt.legend()
+ plt.tight_layout()
+ stats=pd.DataFrame([desc_stats(y_train), desc_stats(y_test), desc_stats(y)], index =['train', 'test', 'total'] ).round(2)
+
+ return X_train, X_test,y_train, y_test, colnames, train_index, test_index, stats, fig1, fig2
+ X_train, X_test,y_train, y_test, colnames, train_index, test_index, stats, fig1, fig2= visualize(change = hash_data(y+np.median(spectra)))
+
M0, M000 = st.columns([1, .4])
- M0.pyplot(fig1) ######## Loaded graph
- fig1.savefig("./Report/figures/spectra_plot.png")
- M0.pyplot(fig2)
- fig2.savefig("./Report/figures/Histogram.png")
- M000.write('Loaded data summary')
- M000.write(stats)
-
- ####################################### Model creation ###################################################
+ with M0:
+ st.pyplot(fig1) ######## Loaded graph
+ st.pyplot(fig2)
+ fig1.savefig("./Report/figures/spectra_plot.png")
+ fig2.savefig("./Report/figures/Histogram.png")
+ with M000:
+ st.write('Loaded data summary')
+ st.write(stats)
+
+################################################### END : visualize and split the data #######################################################
+
+
+
+
+
+
+########################################################## BEGIN : Create Model ####################################################
regression_algo = None # initialize the selected regression algorithm
Reg = None # initialize the regression model object
intervalls_with_cols = pd.DataFrame()
@@ -245,139 +280,171 @@ if not (spectra.empty and y.empty):
folds = KF_CV.CV(X_train, y_train, nb_folds)# split train data into nb_folds for cross_validation
- # Model creation
- match regression_algo:
- case "":
- M20.warning('Choose a modelling algorithm from the dropdown list !')
-
- case "PLS":
- Reg, reg_model, rega = pls_(change =st.session_state.counter)
-
- case 'LW-PLS':
- M20.write(f'K-Fold for Cross-Validation (K = {str(nb_folds)})')
- info = M20.info('Starting LWPLSR model creation... Please wait a few minutes.')
- # export data to csv for Julia train/test
- data_to_work_with = ['x_train_np', 'y_train_np', 'x_test_np', 'y_test_np']
- x_train_np, y_train_np, x_test_np, y_test_np = X_train.to_numpy(), y_train.to_numpy(), X_test.to_numpy(), y_test.to_numpy()
- # Cross-Validation calculation
-
- d = {}
- for i in range(nb_folds):
- d["xtr_fold{0}".format(i+1)], d["ytr_fold{0}".format(i+1)], d["xte_fold{0}".format(i+1)], d["yte_fold{0}".format(i+1)] = np.delete(x_train_np, folds[list(folds)[i]], axis=0), np.delete(y_train_np, folds[list(folds)[i]], axis=0), x_train_np[folds[list(folds)[i]]], y_train_np[folds[list(folds)[i]]]
- data_to_work_with.append("xtr_fold{0}".format(i+1))
- data_to_work_with.append("ytr_fold{0}".format(i+1))
- data_to_work_with.append("xte_fold{0}".format(i+1))
- data_to_work_with.append("yte_fold{0}".format(i+1))
- # check best pre-treatment with a global PLSR model
- preReg = Plsr(train = [X_train, y_train], test = [X_test, y_test], n_iter=20)
- temp_path = Path('temp/')
- with open(temp_path / "lwplsr_preTreatments.json", "w+") as outfile:
- json.dump(preReg.best_hyperparams_, outfile)
- # export Xtrain, Xtest, Ytrain, Ytest and all CV folds to temp folder as csv files
- for i in data_to_work_with:
- if 'fold' in i:
- j = d[i]
- else:
- j = globals()[i]
- np.savetxt(temp_path / str(i + ".csv"), j, delimiter=",")
- # run Julia Jchemo as subprocess
- import subprocess
- subprocess_path = Path("Class_Mod/")
- subprocess.run([f"{sys.executable}", subprocess_path / "LWPLSR_Call.py"])
- # retrieve json results from Julia JChemo
- try:
- with open(temp_path / "lwplsr_outputs.json", "r") as outfile:
- Reg_json = json.load(outfile)
- # delete csv files
- for i in data_to_work_with: os.unlink(temp_path / str(i + ".csv"))
- # # delete json file after import
- os.unlink(temp_path / "lwplsr_outputs.json")
- os.unlink(temp_path / "lwplsr_preTreatments.json")
- # format result data into Reg object
- pred = ['pred_data_train', 'pred_data_test']### keys of the dict
- for i in range(nb_folds):
- pred.append("CV" + str(i+1)) ### add cv folds keys to pred
-
- Reg = type('obj', (object,), {'model_' : Reg_json['model'], 'best_hyperparams_' : Reg_json['best_lwplsr_params'],
- 'pred_data_' : [pd.json_normalize(Reg_json[i]) for i in pred]})
- reg_model = Reg.model_
- Reg.CV_results_ = pd.DataFrame()
- Reg.cv_data_ = {'YpredCV' : {}, 'idxCV' : {}}
- # # set indexes to Reg.pred_data (train, test, folds idx)
- for i in range(len(pred)):
- Reg.pred_data_[i] = Reg.pred_data_[i].T.reset_index().drop(columns = ['index'])
- if i == 0: # data_train
- # Reg.pred_data_[i] = np.array(Reg.pred_data_[i])
- Reg.pred_data_[i].index = list(y_train.index)
- Reg.pred_data_[i] = Reg.pred_data_[i].iloc[:,0]
- elif i == 1: # data_test
- # Reg.pred_data_[i] = np.array(Reg.pred_data_[i])
- Reg.pred_data_[i].index = list(y_test.index)
- Reg.pred_data_[i] = Reg.pred_data_[i].iloc[:,0]
- else:
- # CVi
- Reg.pred_data_[i].index = folds[list(folds)[i-2]]
- # Reg.CV_results_ = pd.concat([Reg.CV_results_, Reg.pred_data_[i]])
- Reg.cv_data_['YpredCV']['Fold' + str(i-1)] = np.array(Reg.pred_data_[i]).reshape(-1)
- Reg.cv_data_['idxCV']['Fold' + str(i-1)] = np.array(folds[list(folds)[i-2]]).reshape(-1)
-
- Reg.CV_results_= KF_CV.metrics_cv(y = y_train, ypcv = Reg.cv_data_['YpredCV'], folds = folds)[1]
- #### cross validation results print
- Reg.best_hyperparams_print = Reg.best_hyperparams_
- ## plots
- Reg.cv_data_ = KF_CV().meas_pred_eq(y = np.array(y_train), ypcv= Reg.cv_data_['YpredCV'], folds=folds)
- Reg.pretreated_spectra_ = preReg.pretreated_spectra_
+ # Model creation-M20 columns
+ with M20:
+ if regression_algo:
+ info = st.info('The model is being created. This may take a few minutes.')
+ if regression_algo == 'TPE-iPLS':# if model type is ipls then ask for the number of iterations and intervalls
+ s = st.number_input(label='Enter the maximum number of intervals', min_value=1, max_value=6)
+ it = st.number_input(label='Enter the number of iterations', min_value=2, max_value=500, value=2)
+
+ if regression_algo: # if a regression method is selected then create the model
+ @st.cache_data
+ def RequestingModelCreation(change, regression_algo):
+ match regression_algo:
+ case 'PLS':
+ Reg = Plsr(train = [X_train, y_train], test = [X_test, y_test], n_iter=5)
+ reg_model = Reg.model_
+ rega = Reg.selected_features_
+ case 'LW-PLS':
+ # export data to csv for Julia train/test
+ global x_train_np, y_train_np, x_test_np, y_test_np
+ data_to_work_with = ['x_train_np', 'y_train_np', 'x_test_np', 'y_test_np']
+ x_train_np, y_train_np, x_test_np, y_test_np = X_train.to_numpy(), y_train.to_numpy(), X_test.to_numpy(), y_test.to_numpy()
+ # Cross-Validation calculation
+
+ d = {}
+ for i in range(nb_folds):
+ d["xtr_fold{0}".format(i+1)], d["ytr_fold{0}".format(i+1)], d["xte_fold{0}".format(i+1)], d["yte_fold{0}".format(i+1)] = np.delete(x_train_np, folds[list(folds)[i]], axis=0), np.delete(y_train_np, folds[list(folds)[i]], axis=0), x_train_np[folds[list(folds)[i]]], y_train_np[folds[list(folds)[i]]]
+ data_to_work_with.append("xtr_fold{0}".format(i+1))
+ data_to_work_with.append("ytr_fold{0}".format(i+1))
+ data_to_work_with.append("xte_fold{0}".format(i+1))
+ data_to_work_with.append("yte_fold{0}".format(i+1))
+ # check best pre-treatment with a global PLSR model
+ preReg = Plsr(train = [X_train, y_train], test = [X_test, y_test], n_iter=20)
+ temp_path = Path('temp/')
+ with open(temp_path / "lwplsr_preTreatments.json", "w+") as outfile:
+ json.dump(preReg.best_hyperparams_, outfile)
+ # export Xtrain, Xtest, Ytrain, Ytest and all CV folds to temp folder as csv files
+ for i in data_to_work_with:
+ if 'fold' in i:
+ j = d[i]
+ else:
+ j = globals()[i]
+ # st.write(j)
+ np.savetxt(temp_path / str(i + ".csv"), j, delimiter=",")
+ # run Julia Jchemo as subprocess
+ import subprocess
+ subprocess_path = Path("Class_Mod/")
+ subprocess.run([f"{sys.executable}", subprocess_path / "LWPLSR_Call.py"])
+ # retrieve json results from Julia JChemo
+ try:
+ with open(temp_path / "lwplsr_outputs.json", "r") as outfile:
+ Reg_json = json.load(outfile)
+ # delete csv files
+ for i in data_to_work_with: os.unlink(temp_path / str(i + ".csv"))
+ # delete json file after import
+ os.unlink(temp_path / "lwplsr_outputs.json")
+ os.unlink(temp_path / "lwplsr_preTreatments.json")
+ # format result data into Reg object
+ pred = ['pred_data_train', 'pred_data_test']### keys of the dict
+ for i in range(nb_folds):
+ pred.append("CV" + str(i+1)) ### add cv folds keys to pred
+ # global Reg
+ # Reg = type('obj', (object,), {'model_' : Reg_json['model'], 'best_hyperparams_' : Reg_json['best_lwplsr_params'],
+ # 'pred_data_' : [pd.json_normalize(Reg_json[i]) for i in pred]})
+ # global Reg
+ Reg = lw(Reg_json=Reg_json, pred = pred)
+ reg_model = Reg.model_
+ Reg.CV_results_ = pd.DataFrame()
+ Reg.cv_data_ = {'YpredCV' : {}, 'idxCV' : {}}
+ # set indexes to Reg.pred_data (train, test, folds idx)
+ for i in range(len(pred)):
+ Reg.pred_data_[i] = Reg.pred_data_[i].T.reset_index().drop(columns = ['index'])
+ if i == 0: # data_train
+ # Reg.pred_data_[i] = np.array(Reg.pred_data_[i])
+ Reg.pred_data_[i].index = list(y_train.index)
+ Reg.pred_data_[i] = Reg.pred_data_[i].iloc[:,0]
+ elif i == 1: # data_test
+ # Reg.pred_data_[i] = np.array(Reg.pred_data_[i])
+ Reg.pred_data_[i].index = list(y_test.index)
+ Reg.pred_data_[i] = Reg.pred_data_[i].iloc[:,0]
+ else:
+ # CVi
+ Reg.pred_data_[i].index = folds[list(folds)[i-2]]
+ # Reg.CV_results_ = pd.concat([Reg.CV_results_, Reg.pred_data_[i]])
+ Reg.cv_data_['YpredCV']['Fold' + str(i-1)] = np.array(Reg.pred_data_[i]).reshape(-1)
+ Reg.cv_data_['idxCV']['Fold' + str(i-1)] = np.array(folds[list(folds)[i-2]]).reshape(-1)
+
+ Reg.CV_results_= KF_CV.metrics_cv(y = y_train, ypcv = Reg.cv_data_['YpredCV'], folds = folds)[1]
+ #### cross validation results print
+ Reg.best_hyperparams_print = Reg.best_hyperparams_
+ ## plots
+ Reg.cv_data_ = KF_CV().meas_pred_eq(y = np.array(y_train), ypcv= Reg.cv_data_['YpredCV'], folds=folds)
+ Reg.pretreated_spectra_ = preReg.pretreated_spectra_
+
+ Reg.best_hyperparams_print = {**preReg.best_hyperparams_, **Reg.best_hyperparams_}
+ Reg.best_hyperparams_ = {**preReg.best_hyperparams_, **Reg.best_hyperparams_}
+
+ Reg.__hash__ = hash_data(Reg.best_hyperparams_print)
+ except FileNotFoundError as e:
+ Reg = None
+ for i in data_to_work_with: os.unlink(temp_path / str(i + ".csv"))
+ Reg.__hash__ = 0
+ case 'TPE-iPLS':
+ Reg = TpeIpls(train = [X_train, y_train], test=[X_test, y_test], n_intervall = s, n_iter=it)
+ reg_model = Reg.model_
+
+ intervalls = Reg.selected_features_.T
+ intervalls_with_cols = Reg.selected_features_.T
+
+ for i in range(intervalls.shape[0]):
+ for j in range(intervalls.shape[1]):
+ intervalls_with_cols.iloc[i,j] = spectra.columns[intervalls.iloc[i,j]]
+ rega = Reg.selected_features_
+
+ st.session_state.intervalls = Reg.selected_features_.T
+ st.session_state.intervalls_with_cols =intervalls_with_cols
+ return Reg
+ Reg = RequestingModelCreation(change =st.session_state.counter, regression_algo = regression_algo)
+ else:
+ st.warning('Choose a modelling algorithm from the dropdown list !')
- Reg.best_hyperparams_print = {**preReg.best_hyperparams_, **Reg.best_hyperparams_}
- Reg.best_hyperparams_ = {**preReg.best_hyperparams_, **Reg.best_hyperparams_}
- info.empty()
- M20.success('Model created!')
- except FileNotFoundError as e:
- # Display error message on the interface if modeling is wrong
- info.empty()
- M20.warning('- ERROR during model creation -')
- Reg = None
- for i in data_to_work_with: os.unlink(temp_path / str(i + ".csv"))
-
- case 'TPE-iPLS':
- s = M20.number_input(label='Enter the maximum number of intervals', min_value=1, max_value=6)
- it = M20.number_input(label='Enter the number of iterations', min_value=50, max_value=500, value=50)
- progress_text = "The model is being created. Please wait."
- Reg, reg_model, intervalls, intervalls_with_cols, rega = tpeipls_(change = st.session_state.counter, n_intervall= s, n_iter = it)
-
- # pro = M1.info("The model is being created. Please wait!")
- # pro.empty()
- M20.info("The model has successfully been created!")
-
+ if regression_algo:
+ info.empty()
+ if Reg:
+ st.success('Success! Your model has been created and is ready to use.')
+ else:
+ st.error("Error: Model creation failed. Please try again.")
+
+ if regression_algo:
+ if regression_algo == 'TPE-iPLS':
+ intervalls = st.session_state.intervalls
+ intervalls_with_cols = st.session_state.intervalls_with_cols
-if Reg:
- if st.button('re-model the data', key=4, help=None, type="primary", use_container_width=True):
- increment()
-
- M1, M2 = st.columns([2 ,4])
- M1.write('-- Spectral preprocessing info --')
- M1.write(Reg.best_hyperparams_print)
- with open("data/params/Preprocessing.json", "w") as outfile:
- json.dump(Reg.best_hyperparams_, outfile)
+if Reg:
+ if st.button('re-model the data', key=4, help=None, type="primary", use_container_width=True):# remodel feature for re-tuning the model
+ increment()
+ # fitted values and predicted values
yc = Reg.pred_data_[0]
yt = Reg.pred_data_[1]
- # ##########
- M1.write("-- Model performance --")
- if regression_algo != reg_algo[2]:
- M1.dataframe(metrics(c = [y_train, yc], t = [y_test, yt], method='regression').scores_)
- else:
- M1.dataframe(metrics(t = [y_test, yt], method='regression').scores_)
+
+ M1, M2 = st.columns([2 ,4])
+ with M1:
+ # Show and export the preprocessing methods
+ st.write('-- Spectral preprocessing info --')
+ st.write(Reg.best_hyperparams_print)
+ with open("data/params/Preprocessing.json", "w") as outfile:
+ json.dump(Reg.best_hyperparams_, outfile)
+
+ # Show the model performance table
+ st.write("-- Model performance --")
+ if regression_algo != reg_algo[2]:
+ model_per=pd.DataFrame(metrics(c = [y_train, yc], t = [y_test, yt], method='regression').scores_)
+ else:
+ model_per=pd.DataFrame(metrics(c = [y_train, yc], t = [y_test, yt], method='regression').scores_)
+ st.dataframe(model_per)
- model_per=pd.DataFrame(metrics(c = [y_train, yc], t = [y_test, yt], method='regression').scores_)
- # M1.dataframe(model_per) # duplicate with line 371
+
+ # M1.dataframe(model_per) # duplicate with line 371
@st.cache_data
- def prep_important(change,regression_algo):
+ def prep_important(change, regression_algo, model_hash):
fig, (ax1, ax2) = plt.subplots(2,1, figsize = (12, 4), sharex=True)
ax1.plot(colnames, np.mean(X_train, axis = 0), color = 'black', label = 'Average spectrum (Raw)')
# if regression_algo != reg_algo[2]:
@@ -409,51 +476,53 @@ if Reg:
ax2.legend()
return fig
+ fig = prep_important(change = st.session_state.counter, regression_algo = regression_algo, model_hash = str(Reg.__hash__))
+
+ with M2:## Visualize raw,preprocessed spectra, and selected intervalls(in case of ipls)
+ if not intervalls_with_cols.empty:
+ st.write('-- Important Spectral regions used for model creation --')
+ st.table(intervalls_with_cols)
+ st.write('-- Visualization of the spectral regions used for model creation --')
+ fig.savefig("./Report/figures/Variable_importance.png")
+ st.pyplot(fig)
- fig = prep_important(change = st.session_state.counter, regression_algo = regression_algo)
- if not intervalls_with_cols.empty:
- M2.write('-- Important Spectral regions used for model creation --')
- M2.table(intervalls_with_cols)
-
- M2.write('-- Visualization of the spectral regions used for model creation --')
- fig.savefig("./Report/figures/Variable_importance.png")
- M2.pyplot(fig)
+ if Reg: # Display CV results
+ numbers_dict = {1: "One", 2: "Two",3: "Three",4: "Four",5: "Five",
+ 6: "Six",7: "Seven",8: "Eight",9: "Nine",10: "Ten"}
+ st.header(f" {numbers_dict[nb_folds]}-Fold Cross-Validation results")
- ################# CV results ############
+ cv1, cv2 = st.columns([2,2])
+ with cv2:
+ st.write('-- Cross-Validation Summary--')
+ st.write(Reg.CV_results_.style.map(lambda _: "background-color: #cecece;", subset=(Reg.CV_results_.index.drop(['sd', 'mean', 'cv']), slice(None))))
+ # st.write(Reg.CV_results_)
+ cv_results=pd.DataFrame(Reg.CV_results_)# CV table
- if Reg:
- # fig, (ax1, ax2) = plt.subplots(2,1, figsize = (12, 6))
- # fig = make_subplots(rows=3, cols=1, shared_xaxes=True, vertical_spacing=0.02)
+ st.write('-- Out-of-Fold Predictions Visualization (All in one) --')
+ fig1 = px.scatter(Reg.cv_data_[0], x ='Measured', y = 'Predicted' , trendline='ols', color='Folds', symbol="Folds",
+ color_discrete_sequence=px.colors.qualitative.G10)
+ fig1.add_shape(type='line', x0 = .95 * min(Reg.cv_data_[0].loc[:,'Measured']), x1 = 1.05 * max(Reg.cv_data_[0].loc[:,'Measured']),
+ y0 = .95 * min(Reg.cv_data_[0].loc[:,'Measured']), y1 = 1.05 * max(Reg.cv_data_[0].loc[:,'Measured']), line = dict(color='black', dash = "dash"))
+ fig1.update_traces(marker_size=7, showlegend=False)
+ st.plotly_chart(fig1, use_container_width=True)
+ fig0 = px.scatter(Reg.cv_data_[0], x ='Measured', y = 'Predicted' , trendline='ols', color='Folds', symbol="Folds", facet_col = 'Folds',facet_col_wrap=1,
+ color_discrete_sequence=px.colors.qualitative.G10, text='index', width=800, height=1000)
+ fig0.update_traces(marker_size=8, showlegend=False)
+ fig0.write_image("./Report/figures/meas_vs_pred_cv_onebyone.png")
- st.header("Cross-Validation results")
- cv1, cv2 = st.columns([2,2])
- ############
- cv2.write('-- Cross-Validation Summary--')
- cv2.write(Reg.CV_results_)
- cv_results=pd.DataFrame(Reg.CV_results_)
- cv2.write('-- Out-of-Fold Predictions Visualization (All in one) --')
+ with cv1:
+ st.write('-- Out-of-Fold Predictions Visualization (Separate plots) --')
+ st.plotly_chart(fig0, use_container_width=True)
+ fig1.write_image("./Report/figures/meas_vs_pred_cv_all.png")
- fig1 = px.scatter(Reg.cv_data_[0], x ='Measured', y = 'Predicted' , trendline='ols', color='Folds', symbol="Folds",
- color_discrete_sequence=px.colors.qualitative.G10)
- fig1.add_shape(type='line', x0 = .95 * min(Reg.cv_data_[0].loc[:,'Measured']), x1 = 1.05 * max(Reg.cv_data_[0].loc[:,'Measured']),
- y0 = .95 * min(Reg.cv_data_[0].loc[:,'Measured']), y1 = 1.05 * max(Reg.cv_data_[0].loc[:,'Measured']), line = dict(color='black', dash = "dash"))
- fig1.update_traces(marker_size=7, showlegend=False)
- cv2.plotly_chart(fig1, use_container_width=True)
- fig0 = px.scatter(Reg.cv_data_[0], x ='Measured', y = 'Predicted' , trendline='ols', color='Folds', symbol="Folds", facet_col = 'Folds',facet_col_wrap=1,
- color_discrete_sequence=px.colors.qualitative.G10, text='index', width=800, height=1000)
- fig0.update_traces(marker_size=8, showlegend=False)
- fig0.write_image("./Report/figures/meas_vs_pred_cv_onebyone.png")
- cv1.write('-- Out-of-Fold Predictions Visualization (Separate plots) --')
- cv1.plotly_chart(fig0, use_container_width=True)
- fig1.write_image("./Report/figures/meas_vs_pred_cv_all.png")
+ ################################################### BEGIN : Model Diagnosis ####################################################
st.header("III - Model Diagnosis", divider='blue')
-
if Reg:
# signal preprocessing results preparation for latex report
prep_para = Reg.best_hyperparams_
@@ -467,7 +536,7 @@ if Reg:
elif Reg.best_hyperparams_[i] > 1:
prep_para[i] = f"{Reg.best_hyperparams_[i]}nd"
- ### reg plot and residuals plot
+ # reg plot and residuals plot
if regression_algo != reg_algo[2]:
regression_plot = reg_plot([y_train, y_test],[yc, yt], train_idx = train_index, test_idx = test_index)
residual_plot = resid_plot([y_train, y_test], [yc, yt], train_idx=train_index, test_idx=test_index)
@@ -476,130 +545,19 @@ if Reg:
residual_plot = resid_plot([y_train, y_test], [yc, yt], train_idx=train_index, test_idx=test_index)
M7, M8 = st.columns([2,2])
+ with M7:
+ st.write('Predicted vs Measured values')
+ st.pyplot(regression_plot)
+ regression_plot.savefig('./Report/figures/measured_vs_predicted.png')
- M7.write('Predicted vs Measured values')
- M8.write('Residuals plot')
-
- M7.pyplot(regression_plot)
- M8.pyplot(residual_plot)
+ with M8:
+ st.write('Residuals plot')
+ st.pyplot(residual_plot)
+ residual_plot.savefig('./Report/figures/residuals_plot.png')
+
+################################################### END : Model Diagnosis #######################################################
+st.write('Download the Analysis Results')
- residual_plot.savefig('./Report/figures/residuals_plot.png')
- regression_plot.savefig('./Report/figures/measured_vs_predicted.png')
-#########################################
-if Reg:
- st.header('Download Analysis Results', divider='blue')
- def export_model():
- path = 'data/models/model_'
- match file:
- case '.csv':
- #export_package = __import__(model_export)
- with open(path + model_name + date_time + '_created_on_' + xcal_csv.name[:xcal_csv.name.find(".")] +""+
- '_and_' + ycal_csv.name[:ycal_csv.name.find(".")] + '_data_' + '.pkl','wb') as f:
- joblib.dump(reg_model, f)
- if regression_algo == reg_algo[3]:
- Reg.selected_features_.T.to_csv(path + model_name + date_time + '_on_' + xcal_csv.name[:xcal_csv.name.find(".")]
- + '_and_' + ycal_csv.name[:ycal_csv.name.find(".")] + '_data_'+'Wavelengths_index.csv', sep = ';')
-
- case '.dx':
- #export_package = __import__(model_export)
- with open(path + model_name + '_on_'+ data_file.name[:data_file.name.find(".")] + '_data_' + '.pkl','wb') as f:
- joblib.dump(reg_model, f)
- if regression_algo == reg_algo[3]:
- Reg.selected_features_.T.to_csv(path +data_file.name[:data_file.name.find(".")]+ model_name + date_time+ '_on_' + '_data_'+'Wavelengths_index.csv', sep = ';')
-
-
-
-
-
- def export_report():
- match regression_algo:
- case 'PLS':
- latex_report = report.report('Predictive model development', file_name, stats, list(Reg.best_hyperparams_.values()), regression_algo, model_per, cv_results)
-
- case 'LW-PLS':
- latex_report = report.report('Predictive model development', file_name, stats,
- list({key: Reg.best_hyperparams_[key] for key in ['deriv', 'normalization', 'polyorder', 'window_length'] if key in Reg.best_hyperparams_}.values()), regression_algo, model_per, cv_results)
-
- case 'TPE-iPLS':
- latex_report = report.report('Predictive model development', file_name, stats,
- list({key: Reg.best_hyperparams_[key] for key in ['deriv', 'normalization', 'polyorder', 'window_length'] if key in Reg.best_hyperparams_}.values()), regression_algo, model_per, cv_results)
-
- case _:
- st.warning('Data processing has not been performed or finished yet!', icon = "âš ï¸")
-
- report.compile_latex()
-
-
-
- M9, M10 = st.columns([1,1])
- M10.info('The results are automatically converted into LaTeX code, a strong typesetting system noted for its remarkable document formatting.\
- The comprehensive capabilities of LaTeX ensure that your data and findings are cleanly and properly presented,\
- swith accurate formatting and organizing.')
- # M9.write("-- Save the model --")
- model_name = M9.text_input("Please provide a name for the created model: ",value = 'UNNAMED' , placeholder = 'model name')
-
- items_download = M9.selectbox('To proceed, please choose the file or files you want to download from the list below:',
- options = ['','Model', 'Report', 'Both Model & Report'], index=0, format_func=lambda x: x if x else "<Select>",
- key=None, help=None, on_change=None, args=None, kwargs=None, placeholder="Choose an option", disabled=False, label_visibility="visible")
-
-
- ## Save model and download report
-
- # st.session_state.a = "Please wait while your LaTeX report is being compiled..."
- date_time = datetime.datetime.strftime(datetime.date.today(), '_%Y_%m_%d_')
- # match items_download:
- # case '':
-
- if items_download:
- if M9.button('Download', type="primary"):
- match items_download:
- case '':
- M9.warning('Please select an item from the dropdown list!')
- case 'Model':
- export_model()
- case 'Report':
- # M9.info("Please wait while your LaTeX report is being compiled...")
- export_report()
- case 'Both Model & Report':
- export_model()
- export_report()
- M9.success('The selected item has been exported successfully!')
-
-
-if Reg:
-
- if st.session_state['interface'] == 'simple':
- pages_folder = Path("pages/")
- show_pages(
- [Page("app.py", "Home"),
- Page(str(pages_folder / "4-inputs.py"), "Inputs"),
- Page(str(pages_folder / "1-samples_selection.py"), "Samples Selection"),
- Page(str(pages_folder / "2-model_creation.py"), "Models Creation"),
- Page(str(pages_folder / "3-prediction.py"), "Predictions"),
- ]
- )
- st.page_link('pages\\3-prediction.py', label = 'Keep on keepin\' on to predict your values !')
-
-
-##### for outliers removal
- # data_df = pd.DataFrame(
- # {
- # "widgets": ["st.selectbox", "st.number_input", "st.text_area", "st.button"],
- # "favorite": [True, False, False, True],
- # }
- # )
- # st.data_editor(
- # data_df,
- # column_config={
- # "favorite": st.column_config.CheckboxColumn(
- # "Your favorite",
- # help="Select your widgets",
- # default=False,
- # )
- # },
- # disabled=["widgets"],
- # hide_index=True,
- # )
\ No newline at end of file
--
GitLab