DEPLOY: updated all files for manual deploy to huggingface

.dockerignore

@@ -1,17 +1,21 @@
 
+
 #--- ignore select binary files/folders
 bin/images/sample*
 bin/models/*.pth
 bin/models/*.zip
+bin/models/deeplabv3*vhflip30/*.pth
 bin/testing
-
+_ignore
+.vscode
+cicd_workflows
 
 #--- ignore all local data files; preserve/recreate folder structure
-data_host_mount
+data/demo_tiles/*.tiff
 data/tiles
 data/wsi
 
-
-#--- ignore all files within the _ignore folder
-_ignore
-
+#--- ignore all doc files
+docs
+notebooks
+preso

.gitattributes

@@ -1,3 +1,10 @@
+#--- Note:  omdena github does not allow git lfs.  Disable.
+#--- Note:  huggingface does not allow _any_ binaries;  git lfs has to be used
+#bin/models/*.pth filter=lfs diff=lfs merge=lfs -text
+#bin/models/deeplab*vhflip30/model_a* filter=lfs diff=lfs merge=lfs -text
+#bin/images/* filter=lfs diff=lfs merge=lfs -text
+#data/demo_tiles/raw/* filter=lfs diff=lfs merge=lfs -text
+
 *.7z filter=lfs diff=lfs merge=lfs -text
 *.arrow filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
@@ -23,7 +30,6 @@
 *.pth filter=lfs diff=lfs merge=lfs -text
 *.rar filter=lfs diff=lfs merge=lfs -text
 *.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.tar.* filter=lfs diff=lfs merge=lfs -text
 *.tar filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
@@ -33,7 +39,8 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
-*model_a* filter=lfs diff=lfs merge=lfs -text
 *.tiff filter=lfs diff=lfs merge=lfs -text
 data/demo_tiles/raw/*.tiff filter=lfs diff=lfs merge=lfs -text
 bin/models/deeplabv3*vhflip30/model_a* filter=lfs diff=lfs merge=lfs -text
+*model_a* filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -1,13 +1,49 @@
+#--- NOTE:  this .gitignore is specific to the hugspace_docker cicd deploy
+#--- WARN:  omdena github does not support git lfs at all; allows small binary files
+#--- WARN:  huggingface github does not allow _any_ binary files outside of git lfs
+
 #--- specific to task5-deploy
 bin/images/sample*
-bin/models/*/*.pth
-bin/models/*.pth
-bin/models/*.zip
+bin/images/dbl.png
+
+#--- specific to cicd_hugspace_streamlit deploy
+#--- omdena github will not have access to git lfs or the complete model file
+#--- cicd will rebuild the model file
+#.vscode
+#bin/models/deeplabv3*vhflip30/*.pth                      
+#bin/testing
+#data/demo_tiles/raw/*.tiff
+#notebooks
+#.dockerignore
+#Dockerfile
+#main.py
+
+#--- specific to cicd_hugspace_docker deploy
+#--- omdena github will not have access to git lfs or the complete model file
+#--- cicd will rebuild the model file
+.vscode
+bin/models/deeplabv3*vhflip30/*.pth                      
 bin/testing
+data/demo_tiles/raw/*.tiff
+notebooks
+
+
+#--- omdena github does not allow large files or git lfs
+bin/models/*.pth                   
+bin/models/*.zip
+#bin/models/deeplabv3*/model_a*     #--- save partial model files in omdena github
+#data/demo_tiles                    #--- allow demo tiles in the github for use and ref
 data/tiles
 data/wsi
 data_host_mount
+
+preso
+
+*.pth
 _ignore
+*.bkp
+*.dtmp
+*.pptx
 
 
 # Byte-compiled / optimized / DLL files
@@ -26,7 +62,7 @@ dist/
 downloads/
 eggs/
 .eggs/
-lib/
+#lib/
 lib64/
 parts/
 sdist/

README.md

@@ -1,5 +1,5 @@
 ---
-title: Spcdkr Omdenasaudi Liverhccxai
+title: spcDkr omdenaSaudi Liver HCC XAI
 emoji: 🏢
 colorFrom: purple
 colorTo: green

app.py

@@ -2,7 +2,6 @@
     toExecute:  (from root app folder) ... streamlit run app.py
 '''
 import streamlit as st
-#from uix import lit_sidebar as lit_sideBar
 import uix.lit_sidebar as litSideBar
 
 
@@ -11,16 +10,14 @@ st.set_page_config(
             page_title='Omdena Saudi Arabia - Liver HCC Diagnosis with XAI', 
             #page_icon='https://cdn.freebiesupply.com/logos/thumbs/1x/nvidia-logo.png', 
             layout="wide")
-st.header("Omdena Saudi Arabia - Liver HCC Diagnosis with XAI")
+st.header('\
+    Detecting Liver Cancer from Histopathology WSI \
+    using Deep Learning and Explainability (XAI)\
+')
+st.markdown('#### Dr. Shaista Hussain (Saudi Arabia Chapter Lead)')
+st.markdown("##### Iain McKone (Deployment Lead) [LinkedIn](%s)" % "https://linkedin.com/in/iainmckone")
 st.markdown('---')
 
 
 #--- streamlit:  add a sidebar 
 litSideBar.init()
-
-
-#if __name__ == '__main__':
-#    st.run("main:app", host="0.0.0.0", port=49300, reload=True)
-#   streamlit run app.py --server.port 49400 --server.maxUploadSize 2000 
-
-#aryPkg[moduleNames.index(page)].run()

lib/models/mdl_autoenc.py

@@ -0,0 +1,55 @@
+import pandas as pd
+import numpy as np
+from sklearn.decomposition import PCA 
+import lib.utils as libPaths
+import pickle
+
+
+m_kstrFile = __file__
+m_kstrDataPath = libPaths.pth_data
+m_kstrBinModelPath = libPaths.pth_binModels
+m_kstrPcaModelPath = m_kstrBinModelPath + 'pca_unsuperv_colab.pkl'
+m_kstrEncModelPath = m_kstrBinModelPath + 'enc_keras_seq/'
+
+
+#--- Supervised:  autoencoder - Principal Component Analysis
+def load_encFromKeras():
+    from tensorflow import keras
+    mdlAnoms = keras.models.load_model(m_kstrEncModelPath)
+    return mdlAnoms
+
+
+def load_pcaFromPkl():
+    with open(m_kstrPcaModelPath, 'rb') as filPkl:
+        # load using pickle de-serializer
+        mdlAnoms = pickle.load(filPkl)
+    return mdlAnoms
+
+
+def save_encToKeras(mdlAnoms):
+    mdlAnoms.save(m_kstrEncModelPath)
+
+
+
+def predict(pdfScaled):
+    
+    #--- Pre:  Transforming train and test dataframes based on PCA
+    mdlPCA = load_pcaFromPkl()         #--- this is a pre-fit model based on training
+    npaPca = mdlPCA.transform(pdfScaled)
+    print("INFO (" + m_kstrFile + ".predict)  npaPca.shape:  ", npaPca.shape)
+
+
+    #--- predict on unseen data
+    mdlEnc = load_encFromKeras()
+    npaPredict = mdlEnc.predict(npaPca[:,:29])
+    print("INFO (" + m_kstrFile + ".predict)  npaPredict.shape:  ", npaPredict.shape)
+    #--- expected:  297, 29?
+    return npaPredict
+    
+
+""" 
+def train(pdfTrainData):
+    mdlAnoms = PCA()                        #---- TODO:  this is Keras Sequential
+    mdlAnoms.fit(pdfTrainData.values)
+    save_encToKeras(mdlAnoms)
+    return mdlAnoms """

lib/models/mdl_kmeans.py

@@ -0,0 +1,155 @@
+from sklearn.cluster import KMeans
+import lib.utils as libPaths
+import pickle
+import pandas as pd
+
+
+m_kstrFile = __file__
+m_kstrDataPath = libPaths.pth_data
+m_kstrBinModelPath = libPaths.pth_binModels
+
+#m_kstrPcaModelPath = m_kstrBinModelPath + 'pca_kmeans_unsuperv_colab.pkl'
+#m_kstrPcaModelPath = m_kstrBinModelPath + 'pca_kmeans_unsuperv_colab_v1.2.1.pkl'
+m_kstrPcaModelPath_111 = m_kstrBinModelPath + 'claims_pca_v1.1.1_27cols.pkl'            #--- ERROR:  __randomstate_ctor() takes from 0 to 1 positional arguments but 2 were given
+m_kstrPcaModelPath_121 = m_kstrBinModelPath + 'claims_pca_v1.2.1_27cols.pkl'
+m_kstrPcaModelPath_claims_py3816_sk111hp = m_kstrBinModelPath + 'claims_pca_py3816_sk111hp_27cols.pkl'
+m_kstrPcaModelPath = m_kstrPcaModelPath_claims_py3816_sk111hp
+
+#m_kstrKmeansModelPath = m_kstrBinModelPath + 'kmeans_unsuperv_colab.pkl'
+#m_kstrKmeansModelPath = m_kstrBinModelPath + 'kmn_unsuperv_colab_v1.2.1.pkl'
+m_kstrModelPath_111 = m_kstrBinModelPath + 'claims_kmn_v1.1.1_22cols.pkl'            #--- ERROR:  __randomstate_ctor() takes from 0 to 1 positional arguments but 2 were given
+m_kstrModelPath_121 = m_kstrBinModelPath + 'claims_kmn_v1.2.1_22cols.pkl'
+m_kstrModelPath_claims_py3816_sk111hp = m_kstrBinModelPath + 'claims_kmn_py3816_sk111hp_22cols.pkl'
+m_kstrKmeansModelPath = m_kstrModelPath_claims_py3816_sk111hp
+
+m_blnTraceOn = True
+
+
+#--- unsupervised:  Logistic Regession
+def load_pcaFromPkl():
+    with open(m_kstrPcaModelPath, 'rb') as filPkl:
+        mdlAnoms = pickle.load(filPkl)
+    return mdlAnoms
+
+
+#--- unsupervised:  KMeans
+def load_kmeansFromPkl():
+    with open(m_kstrKmeansModelPath, 'rb') as filPkl:
+        mdlAnoms = pickle.load(filPkl)
+    return mdlAnoms
+
+
+def save_pcaToPkl(mdlAnoms):
+    with open(m_kstrPcaModelPath, 'wb') as filPkl:
+        pickle.dump(mdlAnoms, filPkl)
+    return mdlAnoms
+
+
+def save_kmeansToPkl(mdlAnoms):
+    with open(m_kstrKmeansModelPath, 'wb') as filPkl:
+        pickle.dump(mdlAnoms, filPkl)
+    return mdlAnoms
+
+
+
+#--- determine which points can be labelled against which clusters
+def predict(pdfScaled):
+    #--- load a persisted fit kmeans model
+    #--- predict will assign labels onto a similarly scaled data frame 
+
+
+    #--- Note:  reverse chron through the code ...
+    #---        4. KMeans was fit on X-reduced (22 cols)
+    #---        3. X_reduced was a reduced column set of X-scaled (27 -> 22;  Dropped 5 cols:  DeadOrNot; and hotEncoded Gender and Race)
+    #---        2. x_scaled was transformed through stdScaler
+    #---        1. StdScaler was fit on X to produce X-scaled (X has 27 cols)
+    pdfReduced = pdfScaled[['InscClaimAmtReimbursed', 'DeductibleAmtPaid',
+        'AdmittedDays', 'RenalDiseaseIndicator', 'NoOfMonths_PartACov',
+        'NoOfMonths_PartBCov', 'ChronicCond_Alzheimer',
+        'ChronicCond_Heartfailure', 'ChronicCond_KidneyDisease',
+        'ChronicCond_Cancer', 'ChronicCond_ObstrPulmonary',
+        'ChronicCond_Depression', 'ChronicCond_Diabetes',
+        'ChronicCond_IschemicHeart', 'ChronicCond_Osteoporasis',
+        'ChronicCond_rheumatoidarthritis', 'ChronicCond_stroke',
+        'IPAnnualReimbursementAmt', 'IPAnnualDeductibleAmt',
+        'OPAnnualReimbursementAmt', 'OPAnnualDeductibleAmt', 'Age']]
+
+    #--- prefit Kmeans clustering - was fit on trained pdfReduced
+    #--- Note:  if we want to understand how kmeans performs on test/prod data, we need to predict
+    mdlKMeans = load_kmeansFromPkl()
+    #ndaPredict = mdlKMeans.predict(pdfScaled)         #20230208:  ValueError: X has 27 features, but KMeans is expecting 22 features as input.
+    ndaPredict = mdlKMeans.predict(pdfReduced)       #ValueError: X has 22 features, but KMeans is expecting 27 features as input.
+    return ndaPredict
+
+
+#--- feat eng
+def do_featEng(pdfLoaded, blnIsTrain=False, hasGroupByProviderCols=True):
+    print("INFO (mdl_kmeans.doFeatEng):  blnIsTrain, ", blnIsTrain)
+
+    #--- columns_to_remove
+    aryColsToDrop = ['BeneID', 'ClaimID', 'ClaimStartDt','ClaimEndDt','AttendingPhysician',
+                     'OperatingPhysician', 'OtherPhysician', 'ClmDiagnosisCode_1',
+                     'ClmDiagnosisCode_2', 'ClmDiagnosisCode_3', 'ClmDiagnosisCode_4',
+                     'ClmDiagnosisCode_5', 'ClmDiagnosisCode_6', 'ClmDiagnosisCode_7',
+                     'ClmDiagnosisCode_8', 'ClmDiagnosisCode_9', 'ClmDiagnosisCode_10',
+                     'ClmProcedureCode_1', 'ClmProcedureCode_2', 'ClmProcedureCode_3',
+                     'ClmProcedureCode_4', 'ClmProcedureCode_5', 'ClmProcedureCode_6',
+                     'ClmAdmitDiagnosisCode', 'AdmissionDt',
+                     'DischargeDt', 'DiagnosisGroupCode','DOB', 'DOD',
+                     'State', 'County']
+    pdfFeatEng = pdfLoaded.drop(columns=aryColsToDrop, axis=1)
+
+    #--- flag categorical cols
+    pdfFeatEng.Gender = pdfFeatEng.Gender.astype('category')
+    pdfFeatEng.Race = pdfFeatEng.Race.astype('category')
+
+    #--- one-hot-encoding
+    pdfFeatEng = pd.get_dummies(pdfFeatEng, columns=['Gender', 'Race'], drop_first=True)
+    if (blnIsTrain):
+        #--- one-hot encode the potential fraud column (for training data only)
+        try:
+            #print("INFO (claims.doFeatEng):  one-hot encoding potential fraud")
+            pdfFeatEng.loc[pdfFeatEng['PotentialFraud'] == 'Yes', 'PotentialFraud'] = 1
+            pdfFeatEng.loc[pdfFeatEng['PotentialFraud'] == 'No', 'PotentialFraud'] = 0
+        except KeyError:
+            #--- likely column not found; invalid fxn call
+            print("ERROR (claims.doFeatEng):  Potential Fraud col not found")
+
+    pdfFeatEng.loc[pdfFeatEng['RenalDiseaseIndicator'] == 'Y', 'RenalDiseaseIndicator'] = 1 
+    pdfFeatEng['DeductibleAmtPaid'].fillna(0, inplace=True)
+    pdfFeatEng['AdmittedDays'].fillna(0, inplace=True)
+
+    #--- check for correlated cols
+
+    #--- add new features to assist with predictions
+    if (hasGroupByProviderCols):
+        pdfFeatEng['InscClaimReimbursement_ProviderAvg'] = pdfFeatEng.groupby(['Provider'])['InscClaimAmtReimbursed'].transform('mean') 
+        pdfFeatEng['DeductibleAmtPaid_ProviderAvg'] = pdfFeatEng.groupby(['Provider'])['DeductibleAmtPaid'].transform('mean')
+        
+        pdfFeatEng['IPAnnualReimbursementAmt_ProviderAvg'] = pdfFeatEng.groupby(['Provider'])['IPAnnualReimbursementAmt'].transform('mean')
+        pdfFeatEng['IPAnnualDeductibleAmt_ProviderAvg'] = pdfFeatEng.groupby(['Provider'])['IPAnnualDeductibleAmt'].transform('mean')
+
+        pdfFeatEng['OPAnnualReimbursementAmt_ProviderAvg'] = pdfFeatEng.groupby(['Provider'])['OPAnnualReimbursementAmt'].transform('mean')
+        pdfFeatEng['OPAnnualDeductibleAmt_ProviderAvg'] = pdfFeatEng.groupby(['Provider'])['OPAnnualDeductibleAmt'].transform('mean')
+    return pdfFeatEng
+
+
+def fit(pdfScaled):
+    #--- determine the centroids of the kmeans clusters
+    #--- refit kmeans clustering according to the pre-scaled data provided
+    #--- note:  this all assumes that the nature of the data and the number of clusters remain unchanged
+    m_klngNumClusters = 3
+    if (m_blnTraceOn): print("TRACE (" + m_kstrFile + ".fit)  instantiate KMeans ...")
+    mdlKMeans = KMeans(n_clusters=m_klngNumClusters, max_iter=50, random_state=2022)            #--- #clusters was learned from training    
+    
+    if (m_blnTraceOn): print("TRACE (" + m_kstrFile + ".fit)  fitting data (scaled) ...")
+    mdlKMeans.fit(pdfScaled)           #--- fit on test/prod data
+    
+    return mdlKMeans                    #--- this ibject will give us all results based on kmeans
+
+
+def train(pdfTrainData):
+    mdlAnoms = KMeans(n_clusters=3, max_iter=50, random_state=2022)
+    mdlAnoms.fit(pdfTrainData.values)
+    save_kmeansToPkl(mdlAnoms)
+    return mdlAnoms

lib/models/mdl_logR.py

@@ -0,0 +1,41 @@
+from sklearn.linear_model import LogisticRegressionCV
+import lib.utils as libPaths
+import pickle
+
+
+m_kstrFile = __file__
+m_kstrDataPath = libPaths.pth_data
+m_kstrBinModelPath = libPaths.pth_binModels
+m_kstrModelPath = m_kstrBinModelPath + 'lgr_model_colab.pkl'
+
+
+#--- Supervised:  Logistic Regession
+def load_fromPkl():
+    with open(m_kstrModelPath, 'rb') as filPkl:
+        mdlAnoms = pickle.load(filPkl)
+    return mdlAnoms
+
+
+
+def save_toPkl(mdlAnoms):
+    with open(m_kstrModelPath, 'wb') as filPkl:
+        pickle.dump(mdlAnoms, filPkl)
+    return mdlAnoms
+
+
+
+def predict(npaData):
+    #--- input:  numpy.ndarray of feature eng, and scaled data 
+    mdlAnoms = load_fromPkl()
+    npaPredict = mdlAnoms.predict(npaData)
+
+    print("INFO (npaPredict.shape):  ", npaPredict.shape)
+    return npaPredict
+
+
+
+def train(pdfTrainData):
+    mdlAnoms = LogisticRegressionCV()
+    mdlAnoms.fit(pdfTrainData.values)
+    save_toPkl(mdlAnoms)
+    return mdlAnoms

lib/models/mdl_svm.py

@@ -0,0 +1,40 @@
+from sklearn.svm import LinearSVC
+import lib.utils as libPaths
+import pickle
+
+
+m_kstrFile = __file__
+m_kstrDataPath = libPaths.pth_data
+m_kstrBinModelPath = libPaths.pth_binModels
+m_kstrModelPath = m_kstrBinModelPath + 'svm_model_colab.pkl'
+
+
+#--- Supervised:  Support Vector Machines
+def load_fromPkl():
+    with open(m_kstrModelPath, 'rb') as filPkl:
+        mdlAnoms = pickle.load(filPkl)
+    return mdlAnoms
+
+
+
+def save_toPkl(mdlAnoms):
+    with open(m_kstrModelPath, 'wb') as filPkl:
+        pickle.dump(mdlAnoms, filPkl)
+    return mdlAnoms
+
+    
+
+def predict(npaData):
+    #--- input:  numpy.ndarray of feature eng, and scaled data 
+    mdlAnoms = load_fromPkl()
+    npaPredict = mdlAnoms.predict(npaData)
+    print("INFO (" + m_kstrFile + ".predict)  npaPredict.shape:  ", npaPredict.shape)
+    return npaPredict
+    
+
+
+def train(pdfTrainData):
+    mdlAnoms = LinearSVC()
+    mdlAnoms.fit(pdfTrainData.values)
+    save_toPkl(mdlAnoms)
+    return mdlAnoms

lib/models/mdl_utils.py

@@ -0,0 +1,256 @@
+import pandas as pd
+import pickle
+import lib.utils as libPaths
+
+m_blnTraceOn = False
+
+#--- load, merge data from file
+m_kstrDataPath = libPaths.pth_data
+m_kstrModelPath = libPaths.pth_model
+m_kstrBinModelPath = libPaths.pth_binModels
+
+#m_kstrScalerPath_claims = m_kstrBinModelPath + 'stdClaims_scaler_colab.pkl'         #--- does not work for scaling claims data;  from v1.0.2; using 1.1.1
+#m_kstrScalerPath_claims2 = m_kstrBinModelPath + 'std_scaler_unsuperv_colab.pkl'     #--- does not work; expects 32 features 
+#m_kstrScalerPath_claims = m_kstrBinModelPath + 'stdClaims_scaler_colab_v1.2.1.pkl'   
+m_kstrScalerPath_claims111 = m_kstrBinModelPath + 'claims_stdScaler_v1.1.1_27cols.pkl'
+m_kstrScalerPath_claims121 = m_kstrBinModelPath + 'claims_stdScaler_v1.2.1_27cols.pkl'
+m_kstrScalerPath_claims_py3816_sk111hp = m_kstrBinModelPath + 'claims_stdScl_py3816_sk111hp_27cols.pkl'
+m_kstrScalerPath_claims = m_kstrScalerPath_claims_py3816_sk111hp
+
+m_kstrScalerPath_providers111 = m_kstrBinModelPath + 'prov_stdScaler_v1.1.1_32cols.pkl'
+m_kstrScalerPath_providers121 = m_kstrBinModelPath + 'prov_stdScaler_v1.2.1_32cols.pkl'
+m_kstrScalerPath_prov_py3816_sk111 = m_kstrBinModelPath + 'prov_stdScl_py3816_sk111_32cols.pkl'
+m_kstrScalerPath_prov_py3816_sk111hp = m_kstrBinModelPath + 'prov_stdScl_py3816_sk111hp_32cols.pkl'
+m_kstrScalerPath_prov = m_kstrScalerPath_prov_py3816_sk111hp
+
+m_kstrScalerPath_providers_superv = m_kstrBinModelPath + 'gbc_scaler.pkl'
+m_kstrScalerPath_providers_train = m_kstrBinModelPath + "stdProvider_scaler.pkl" 
+   
+
+
+def doProviders_stdScaler(pdfFeatEng, blnIsTrain=False, hasGroupByProviderCols=True):
+    print("INFO (claims.do_stdScaler):  blnIsTrain, ", blnIsTrain)
+
+    #--- Note:  prediction runs on X_val
+    '''
+    #--- WARN:  The default value of numeric_only in DataFrameGroupBy.sum is deprecated. 
+    #           In a future version, numeric_only will default to False. Either specify 
+    #           numeric_only or select only columns which should be valid for the function.
+    '''
+
+    #--- WARN:  this code groups all data by provider;  any predictions will also be by provider
+    pdfGroupBy = pdfFeatEng
+    if (hasGroupByProviderCols):
+        pdfGroupBy = pdfFeatEng.groupby(['Provider'], as_index=False).agg('sum')
+    
+    X = pdfGroupBy
+
+    try:
+        X = X.drop(columns=['Provider'], axis=1)        #--- cannot scale;  text
+    except KeyError:
+        #--- likely column not found; invalid fxn call
+        print("ERROR (mdlUtils.doProviders_stdScaler):  Provider col not found")
+
+    try:
+        X = X.drop(columns=['PotentialFraud'], axis=1)  
+    except KeyError:
+        #--- likely column not found; invalid fxn call
+        if (blnIsTrain):  print("ERROR (mdlUtils.doProviders_stdScaler):  Potential Fraud col not found")
+
+
+    #--- apply std scaler
+    #--- WARN:  scaling is also grouped by provider
+    if (m_blnTraceOn):  print("INFO (mdlUtils.doProviders_stdScaler)  cols: ", X.columns)           #--- 32cols
+    X_std = fitProviders_txfStdScaler(X, blnIsTrain)
+    return X_std
+
+
+
+def doClaims_stdScaler(pdfFeatEng, blnIsTrain=False):
+    print("INFO (mdlUtils.doClaims_stdScaler):  blnIsTrain, ", blnIsTrain)
+
+    #--- Note:  prediction runs on X_val
+    '''
+    #--- WARN:  The default value of numeric_only in DataFrameGroupBy.sum is deprecated. 
+    #           In a future version, numeric_only will default to False. Either specify 
+    #           numeric_only or select only columns which should be valid for the function.
+    '''
+
+    #--- WARN:  this code groups all data by provider;  any predictions will also be by provider
+    X = pdfFeatEng
+
+    try:
+        X = X.drop(columns=['Provider'], axis=1)        #--- cannot scale;  text
+    except KeyError:
+        #--- likely column not found; invalid fxn call
+        print("ERROR (mdlUtils.do_stdScaler):  Provider col not found")
+
+    try:
+        X = X.drop(columns=['PotentialFraud'], axis=1)  
+    except KeyError:
+        #--- likely column not found; invalid fxn call
+        if (blnIsTrain):  print("ERROR (mdlUtils.do_stdScaler):  Potential Fraud col not found")
+
+
+    #--- apply std scaler
+    #--- WARN:  scaling is also grouped by provider
+    #print("INFO (mdlUtils.doClaims_stdScaler)  cols: ", X.columns)
+    X_std = fitClaims_txfStdScaler(X, blnIsTrain)
+    return X_std
+
+
+
+def doProviders_stdScaler_toPdf(npaScaled):
+    #--- NOTE:  the list of cols came from doProvider_stdScaler; print(X.columns)
+    aryCols = ['InscClaimAmtReimbursed', 'DeductibleAmtPaid', 'AdmittedDays',
+       'NoOfMonths_PartACov', 'NoOfMonths_PartBCov', 'ChronicCond_Alzheimer',
+       'ChronicCond_Heartfailure', 'ChronicCond_KidneyDisease',
+       'ChronicCond_Cancer', 'ChronicCond_ObstrPulmonary',
+       'ChronicCond_Depression', 'ChronicCond_Diabetes',
+       'ChronicCond_IschemicHeart', 'ChronicCond_Osteoporasis',
+       'ChronicCond_rheumatoidarthritis', 'ChronicCond_stroke',
+       'IPAnnualReimbursementAmt', 'IPAnnualDeductibleAmt',
+       'OPAnnualReimbursementAmt', 'OPAnnualDeductibleAmt', 'Age', 'DeadOrNot',
+       'Gender_2', 'Race_2', 'Race_3', 'Race_5',
+       'ClaimReimbursement_ProviderAvg',
+       'ClaimReimbursement_AttendingPhysician',
+       'ClaimReimbursement_OperatingPhysician',
+       'DeductibleAmtPaid_ProviderAvg', 'DeductibleAmtPaid_AttendingPhysician',
+       'DeductibleAmtPaid_OperatingPhysician']
+
+    #npaScaled = do_stdScaler(pdfFeatEng)
+    pdfScaled = pd.DataFrame(npaScaled, columns=aryCols)
+    return pdfScaled
+
+
+
+def doClaims_stdScaler_toPdf(npaScaled):
+    #--- NOTE:  the list of cols came from doClaims_stdScaler; print(X.columns)
+    aryCols = ['InscClaimAmtReimbursed', 'DeductibleAmtPaid', 'AdmittedDays',
+       'RenalDiseaseIndicator', 'NoOfMonths_PartACov', 'NoOfMonths_PartBCov', 'ChronicCond_Alzheimer',
+       'ChronicCond_Heartfailure', 'ChronicCond_KidneyDisease',
+       'ChronicCond_Cancer', 'ChronicCond_ObstrPulmonary',
+       'ChronicCond_Depression', 'ChronicCond_Diabetes',
+       'ChronicCond_IschemicHeart', 'ChronicCond_Osteoporasis',
+       'ChronicCond_rheumatoidarthritis', 'ChronicCond_stroke',
+       'IPAnnualReimbursementAmt', 'IPAnnualDeductibleAmt',
+       'OPAnnualReimbursementAmt', 'OPAnnualDeductibleAmt', 'Age', 'DeadOrNot',
+       'Gender_2', 'Race_2', 'Race_3', 'Race_5']
+
+    #npaScaled = do_stdScaler(pdfFeatEng)
+    pdfScaled = pd.DataFrame(npaScaled, columns=aryCols)
+    return pdfScaled
+
+
+
+
+def fitClaims_stdScaler(pdfData, blnIsTrain=False):
+    #--- apply scaler
+    #--- WARN:  scaling is not grouped by provider
+    from sklearn.preprocessing import StandardScaler
+
+    #--- note:  this is a numpy.ndarray
+    #--- we need to fit the scaler, and then save as a pkl file
+    #strScalerPath = m_kstrScalerPath_claims
+    strScalerPath = m_kstrScalerPath_claims
+#    strScalerPath = m_kstrBinModelPath + "stdClaims_scaler_colab.pkl"
+    if (m_blnTraceOn):  print("INFO (lib.model.fitClaims_stdScalar):  ", strScalerPath)
+    if (blnIsTrain):
+        scaler = StandardScaler()
+        sclFit = scaler.fit(pdfData)
+        #--- if we train locally;  write out to gbc_scalar.pkl
+        #--- we do not want to overwrite the colab version used for test
+        strScalerPath = m_kstrBinModelPath + "stdClaims_scaler.pkl"
+        if (m_blnTraceOn):  print("INFO (lib.model.fit_stdScalar)  Using local pkl for Train: ", strScalerPath)
+        with open(strScalerPath, 'wb') as filPkl:
+            pickle.dump(sclFit, filPkl)
+    else:
+        #--- we need to load the pkl file
+        import sklearn
+        if (m_blnTraceOn):  print("INFO (lib.model.fit_stdScalar)  Using colab pkl for Test: ", strScalerPath)
+        with open(strScalerPath, 'rb') as filPkl:
+            sclFit = pickle.load(filPkl)
+        if (m_blnTraceOn):  print("TRACE (libModel.fitClaims_stdScalar)  sclFit.type: ", type(sclFit))
+
+        #--- testing
+        scaler = StandardScaler()
+        if (m_blnTraceOn):  print("TRACE (libModel.fitClaims_stdScalar)  StdScaler.version: ", scaler.__getstate__()['_sklearn_version'])
+        if (m_blnTraceOn):  print("TRACE (libModel.fitClaims_stdScalar)  sclFit.version: " , sclFit.__getstate__()['_sklearn_version'])
+        if (m_blnTraceOn):  print("TRACE (libModel.fitClaims_stdScalar)  sklearn.version: " , sklearn.__version__)
+    return sclFit
+
+
+
+def fitProviders_stdScaler(pdfData, blnIsTrain=False):
+    #--- apply scaler
+    #--- WARN:  scaling is also grouped by provider
+    from sklearn.preprocessing import StandardScaler
+
+    #--- note:  this is a numpy.ndarray
+    #--- we need to fit the scaler, and then save as a pkl file
+    #strScalerPath = m_kstrScalerPath_providers
+    #strScalerPath = m_kstrScalerPath_providers_train            
+    strScalerPath = m_kstrScalerPath_prov         
+    print("INFO (libModel.fitProviders_stdScalar):  ", strScalerPath)
+    if (blnIsTrain):
+        scaler = StandardScaler()
+        sclFit = scaler.fit(pdfData)
+        #--- if we train locally;  write out to gbc_scalar.pkl
+        #--- we do not want to overwrite the colab version used for test
+        strScalerPath = m_kstrScalerPath_providers_train       #--- works for provider training
+        if (m_blnTraceOn):  print("TRACE (libModel.fitProviders_stdScalar)  Using local pkl for Train: ", strScalerPath)
+        with open(strScalerPath, 'wb') as filPkl:
+            pickle.dump(sclFit, filPkl)
+    else:
+        #--- we need to load the pkl file
+        if (m_blnTraceOn):  print("TRACE (libModel.fitProviders_stdScalar)  Using colab pkl for Test: ", strScalerPath)
+        with open(strScalerPath, 'rb') as filPkl:
+            sclFit = pickle.load(filPkl)
+        if (m_blnTraceOn):  print("TRACE (libModel.fitProviders_stdScalar)  sclFit.type: ", type(sclFit))
+    return sclFit
+
+
+
+def fitProviders_stdScalerSuperv(pdfData, blnIsTrain=False):
+    #--- apply scaler
+    #--- WARN:  scaling is also grouped by provider
+    from sklearn.preprocessing import StandardScaler
+
+    #--- note:  this is a numpy.ndarray
+    #--- we need to fit the scaler, and then save as a pkl file
+    strScalerPath = m_kstrScalerPath_prov
+    if (m_blnTraceOn):  print("TRACE (libModel.fitProviders_stdScalar):  ", strScalerPath)
+    if (blnIsTrain):
+        scaler = StandardScaler()
+        sclFit = scaler.fit(pdfData)
+        #--- if we train locally;  write out to gbc_scalar.pkl
+        #--- we do not want to overwrite the colab version used for test
+        strScalerPath = m_kstrBinModelPath + "stdProvider_scaler.pkl"
+        if (m_blnTraceOn):  print("TRACE (libModel.fitProviders_stdScalar)  Using local pkl for Train: ", strScalerPath)
+        with open(strScalerPath, 'wb') as filPkl:
+            pickle.dump(sclFit, filPkl)
+    else:
+        #--- we need to load the pkl file
+        if (m_blnTraceOn):  print("TRACE (libModel.fitProviders_stdScalar)  Using colab pkl for Test: ", strScalerPath)
+        with open(strScalerPath, 'rb') as filPkl:
+            sclFit = pickle.load(filPkl)
+        if (m_blnTraceOn):  print("TRACE (libModel.fitProviders_stdScalar)  sclFit.type: ", type(sclFit))
+    return sclFit
+
+
+
+def fitProviders_txfStdScaler(pdfData, blnIsTrain=False):
+    from sklearn.preprocessing import StandardScaler
+    sclFit = fitProviders_stdScaler(pdfData, blnIsTrain)
+    X_std = sclFit.transform(pdfData)
+    return X_std
+
+
+
+def fitClaims_txfStdScaler(pdfData, blnIsTrain=False):
+    from sklearn.preprocessing import StandardScaler
+    sclFit = fitClaims_stdScaler(pdfData, blnIsTrain)
+
+
+    X_std = sclFit.transform(pdfData)
+    return X_std

lib/models/mdl_xgb.py

@@ -0,0 +1,66 @@
+import pandas as pd
+from sklearn.ensemble import GradientBoostingClassifier
+import lib.utils as libPaths
+import pickle
+import sys
+
+
+m_kstrFile = __file__
+m_kstrDataPath = libPaths.pth_data
+m_kstrBinModelPath = libPaths.pth_binModels
+m_kstrModelPath_gbc = m_kstrBinModelPath + 'gbc_model_colab.pkl'
+m_kstrModelPath_prov111 = m_kstrBinModelPath + 'prov_gbc_v1.1.1_32cols.pkl'            #--- ERROR:  __randomstate_ctor() takes from 0 to 1 positional arguments but 2 were given
+m_kstrModelPath_prov121 = m_kstrBinModelPath + 'prov_gbc_v1.2.1_32cols.pkl'
+m_kstrModelPath_prov_py3816_sk111hp = m_kstrBinModelPath + 'prov_gbc_py3816_sk111hp_32cols.pkl'
+m_kstrModelPath = m_kstrModelPath_prov_py3816_sk111hp
+
+m_blnTraceOn = True
+
+
+
+#--- Supervised:  xg boost;  gradient boosting classifier
+def load_fromPkl():
+    try:
+        with open(m_kstrModelPath, 'rb') as filPkl:
+            mdlAnoms = pickle.load(filPkl)
+        return mdlAnoms
+
+    except:
+        e = sys.exc_info()
+        print("ERROR (mdl_xgb.load_fromPkl_genError):  ", e)    
+
+
+
+def save_toPkl(mdlAnoms):
+    with open(m_kstrModelPath, 'wb') as filPkl:
+        pickle.dump(mdlAnoms, filPkl)
+    return mdlAnoms
+
+
+
+def predict(npaData):
+
+    try:
+        #--- input:  numpy.ndarray of feature eng, and scaled data 
+        mdlAnoms = load_fromPkl()
+        if (m_blnTraceOn):  print("TRACE (mdl_xgb.predict):  data loaded ... ")
+        npaPredict = mdlAnoms.predict(npaData)
+
+    except:
+        e = sys.exc_info()
+        print("ERROR (mdl_xgb.predict_genError1):  ", e)  
+
+
+    #--- AttributeError: 'GradientBoostingClassifier' object has no attribute '_loss'
+    #--- version of scikit-learn?  Monika: ?.?.? ; Iain: 1.2.0
+
+    #print("INFO (type.npaPredict):  ", type(npaPredict))
+    #if (m_blnTraceOn):  print("TRACE (mdl_xgb.predict) npaPredict.shape:  ", npaPredict.shape)
+    return npaPredict
+
+
+def train(pdfTrainData):
+    mdlAnoms = GradientBoostingClassifier()
+    mdlAnoms.fit(pdfTrainData.values)
+    save_toPkl(mdlAnoms)
+    return mdlAnoms

lib/utils.py

@@ -25,6 +25,7 @@ pth_dtaApp = pth_data                                   #--- working folders for
 pth_dtaDemoTiles = pth_data + "demo_tiles/"                   #--- dedicated area for demo data
 pth_dtaTiles = pth_data + "tiles/"
 pth_dtaWsi = pth_data + "wsi/"
+pth_dtaTileSamples = pth_dtaDemoTiles + "raw/sample/"
 
 #--- lib paths
 pth_libModels = pth_lib + "models/"

util_dockerPreRun.sh → scripts/docker/util_docker_preRun.sh

@@ -1,10 +1,10 @@
 #!/bin/bash
 
 #--- Note:  this file is designed to run locally as well as within docker to prep the environment
+#--- Entry:  this script is assumed to run from the /app root folder
+#--- Usage:  ./scripts/docker/util_docker_preRun.sh
+
 #--- for volume initialization; ensure folders are in place; assume:  we are in the /app folder
-mkdir -p data/demo_tiles/raw
-mkdir -p data/tiles/raw data/tiles/pred data/tiles/grad_bg data/tiles/grad_wt data/tiles/grad_vt
-mkdir -p data/wsi/raw
 
 
 <<blockComment 
@@ -12,9 +12,21 @@ mkdir -p data/wsi/raw
 - this is done to ensure that the model can be stored within gitHub
 - the split model is recreated on docker container startup using the cat command
 blockComment
+echo -e "INFO(util_docker_preRun):\t Initializing ..."
+
+strpth_pwd=$(pwd)
+strpth_scriptLoc=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )
+strpth_scrHome="${strpth_scriptLoc}/../"
+strpth_appHome="${strpth_scrHome}../"
+strpth_scrModels="${strpth_scrHome}models/"
+
+echo "strpth_appHome = ${strpth_appHome}"
 
 #--- recreate single model file from its parts, stored within a specific model version folder
-./bin/models/util_joinModel.sh './bin/models/deeplabv3*vhflip30/model_a*' ./bin/models/model.pth
+strpth_binModels="${strpth_appHome}bin/models/"
+echo "strpth_binModels = ${strpth_binModels}"
+#$("'${strpth_scrModels}util_joinModel.sh' '${strpth_binModels}deeplabv3*vhflip30/model_a*' '${strpth_binModels}model.pth'")
+eval "'${strpth_scrModels}/util_joinModel.sh' '${strpth_binModels}/deeplabv3*vhflip30/model_a*' '${strpth_binModels}/model.pth'"
 
 #--- run streamlit/fastapi
-./util_startLocal_streamlitFastApi.sh
+eval "'${strpth_scrHome}/streamlitFastApi/util_local_runStreamlitFastApi.sh'"

scripts/docker/util_local_buildDockerDemo.sh

@@ -0,0 +1,85 @@
+#!/bin/bash
+
+#--- Note:  this file is designed to run locally to build the docker image
+#--- Entry:  this script is assumed to run from the /app root folder
+#--- Usage:  ./scripts/docker/util_local_buildDockerDemo.sh
+#--- Assume:  any associated containers are not running
+
+<<blockComment 
+    util_local_buildDockerDemo -> img_stm_omdenasaudi_hcc:demo -> ctr_stm_omdenasaudi_hcc:demo
+blockComment
+
+
+#--- initialize/configuration
+echo "TRACE:  Initializing ..."
+kstr_defDkrHubId="kidcoconut73"
+kstr_defDkrImageName="img_stm_omdenasaudi_hcc"
+kstr_defDkrTagVersion="0.1.2"
+kstr_defDkrTagStage="demo"
+
+strpth_pwd=$(pwd)
+strpth_scriptLoc=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )
+strpth_scrHome="${strpth_scriptLoc}/../"
+strpth_appHome="${strpth_scrHome}/../"
+
+#--- declarations
+echo "TRACE:  Declarations ..."
+
+#strUtl_scriptLoc="$(utl_getScriptLoc)"
+source ${strpth_scrHome}/util.sh
+
+#kstr_dkrImg="kidcoconut73/img_stm_omdenasaudi_hcc:demo"
+#kstr_dkrCtr="kidcoconut73/ctr_stm_omdenasaudi_hcc:demo"
+kstr_dkrHubImg="${kstr_defDkrHubId}/${kstr_defDkrImageName}:${kstr_defDkrTagStage}"
+kstr_dkrImg="${kstr_defDkrImageName}:${kstr_defDkrTagVersion}"
+kstr_dkrCtr="${kstr_dkrImg/img_/ctr_}"          #--- bash replace one occurrence
+
+
+
+function utl_trace_config {
+    #echo ""
+    local kbln_enableLog=true
+    utl_logInfo $kbln_enableLog 0 "(utl_trace_config) ... echo configuration"
+
+    utl_trace_var "strpth_pwd" $strpth_pwd
+    utl_trace_var "strpth_scriptLoc" $strpth_scriptLoc
+    echo ""
+    utl_trace_var "kstr_defDkrHubId" $kstr_defDkrHubId
+    utl_trace_var "kstr_defDkrImageName" $kstr_defDkrImageName
+    utl_trace_var "kstr_defDkrTagVersion" $kstr_defDkrTagVersion
+    utl_trace_var "kstr_defDkrTagStage" $kstr_defDkrTagStage
+    echo ""
+    utl_trace_var "kstr_dkrHubImg" $kstr_dkrHubImg
+    utl_trace_var "kstr_dkrImg" $kstr_dkrImg
+    utl_trace_var "kstr_dkrCtr" $kstr_dkrCtr
+    echo ""
+}
+
+#echo -e "\nTRACE:  Echo config ..."
+utl_trace_config
+
+
+#--- to build/rebuild the image;  make sure you stop and remove the container if you are replacing/upgrading;  or change the version tag# from 0.1
+#--- stop the container if it is running
+#--- delete container if it exists
+echo -e "\nTRACE:  Stop and remove container if it exists ..."
+docker stop $kstr_dkrCtr
+docker rm $kstr_dkrCtr
+
+#--- build the docker image
+echo -e "\nTRACE:  Build the docker image ..."
+docker build -t $kstr_dkrImg .
+
+
+#--- to tag the image prior to push to DockerHub;  docker login and then register user/image:tag
+#--- to push this image to DockerHub, example based on the repo:  kidcoconut73/img_stm_omdenasaudi_hcc
+#    docker tag img_omdenasaudi_hcc:0.1 kidcoconut73/img_stm_omdenasaudi_hcc:demo
+#    docker tag img_omdenasaudi_hcc:0.1 kidcoconut73/img_stm_omdenasaudi_hcc:0.1
+#--- tag the image
+echo -e "\nTRACE:  Tag the image ..."
+docker tag ${kstr_dkrImg} $kstr_dkrHubImg
+docker tag ${kstr_dkrImg} "${kstr_defDkrHubId}/${kstr_defDkrImageName}:${kstr_defDkrTagVersion}"
+
+
+#--- push the image to dockerHub
+docker push kidcoconut73/img_stm_omdenasaudi_hcc:demo

scripts/docker/util_local_runDockerDemo.sh

@@ -0,0 +1,33 @@
+#!/bin/bash
+
+#--- Note:  this file is designed to run locally to launch docker
+#--- Entry:  this script is assumed to run from the /app root folder
+#--- Usage:  ./scripts/util_local_runDockerDemo.sh
+#--- Assume:  docker image has been built;  container is not running
+
+<<blockComment 
+    util_local_runDockerDemo -> Dockerfile -> util_dockerPreRun -> util_local_runStreamlitFastApi
+blockComment
+
+
+#--- initialize/config
+kstr_defDkrHubId="kidcoconut73"
+kstr_defDkrImageName="img_stm_omdenasaudi_hcc"
+kstr_defDkrCtrName=${kstr_defDkrImageName/img_/ctr_}
+kstr_defDkrTagVersion="0.1.2"
+kstr_defDkrTagStage="demo"
+
+kstr_dkrImg="${kstr_defDkrImageName}:${kstr_defDkrTagVersion}"
+kstr_dkrCtr="${kstr_defDkrImageName/img_/ctr_}"          #--- bash replace one occurrence
+
+#--- stop the container if it is running
+docker stop $kstr_dkrCtr
+
+#--- delete container if it exists
+docker rm $kstr_dkrCtr
+
+#--- to run the container from the image;  specific port mapping (-p) vs any available port mapping (-P)
+#    docker run -p 49400:39400 -p 49500:39500 --name ctr_stmOmdenaSaudiHcc -v ./data:/app/data img_stm_omdenasaudi_hcc:0.1
+
+#--- run docker demo locally
+docker run -p 49400:39400 -p 49500:39500 --name $kstr_dkrCtr -v ./data:/app/data $kstr_dkrImg

scripts/huggingface/util_local_readyDeploy_toHugSpace_streamlit.sh

@@ -0,0 +1,88 @@
+#!/bin/bash
+
+#--- Note:  this file is designed to run locally to ready the deploy branch for hugspace
+#--- Entry:  this script is assumed to run from the /app root folder
+#--- Usage:  ./scripts/util_local_readyDeploy_toHugSpace_streamlit.sh
+
+<<blockComment 
+    bash:   util_local_readyDeploy_toHugSpace_streamlit -> git
+    git:    local/task-5-deployment -> omdena/deploy_hugspace_streamlit -> hugspace/main
+blockComment
+
+
+#--- initialize/configuration
+echo "TRACE:  Initializing ..."
+kstr_hugspaceId="kidcoconut"
+
+
+#--- git checkout deploy_hugspace_streamlit
+#--- git merge task-5-deployment
+#--- delete all unnecessary files
+<<deadCode
+    kstr_defDkrHubId="kidcoconut73"
+    kstr_defDkrImageName="img_stm_omdenasaudi_hcc"
+    kstr_defDkrTagVersion="0.1.2"
+    kstr_defDkrTagStage="demo"
+    strpth_pwd=$(pwd)
+    strpth_scriptLoc=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )
+
+
+    #--- declarations
+    echo "TRACE:  Declarations ..."
+
+    #strUtl_scriptLoc="$(utl_getScriptLoc)"
+    source ${strpth_scriptLoc}/util.sh
+
+    #kstr_dkrImg="kidcoconut73/img_stm_omdenasaudi_hcc:demo"
+    #kstr_dkrCtr="kidcoconut73/ctr_stm_omdenasaudi_hcc:demo"
+    kstr_dkrHubImg="${kstr_defDkrHubId}/${kstr_defDkrImageName}:${kstr_defDkrTagStage}"
+    kstr_dkrImg="${kstr_defDkrImageName}:${kstr_defDkrTagVersion}"
+    kstr_dkrCtr="${kstr_dkrImg/img_/ctr_}"          #--- bash replace one occurrence
+
+
+
+    function utl_trace_config () {
+        echo ""
+        utl_trace_var "strpth_pwd" $strpth_pwd
+        utl_trace_var "strpth_scriptLoc" $strpth_scriptLoc
+        echo ""
+        utl_trace_var "kstr_defDkrHubId" $kstr_defDkrHubId
+        utl_trace_var "kstr_defDkrImageName" $kstr_defDkrImageName
+        utl_trace_var "kstr_defDkrTagVersion" $kstr_defDkrTagVersion
+        utl_trace_var "kstr_defDkrTagStage" $kstr_defDkrTagStage
+        echo ""
+        utl_trace_var "kstr_dkrHubImg" $kstr_dkrHubImg
+        utl_trace_var "kstr_dkrImg" $kstr_dkrImg
+        utl_trace_var "kstr_dkrCtr" $kstr_dkrCtr
+        echo ""
+    }
+
+    echo -e "\nTRACE:  Echo config ...\n"
+    utl_trace_config
+
+
+    #--- to build/rebuild the image;  make sure you stop and remove the container if you are replacing/upgrading;  or change the version tag# from 0.1
+    #--- stop the container if it is running
+    #--- delete container if it exists
+    echo -e "\nTRACE:  Stop and remove container if it exists ..."
+    docker stop $kstr_dkrCtr
+    docker rm $kstr_dkrCtr
+
+    #--- build the docker image
+    echo -e "\nTRACE:  Build the docker image ..."
+    docker build -t $kstr_dkrImg .
+
+
+    #--- to tag the image prior to push to DockerHub;  docker login and then register user/image:tag
+    #--- to push this image to DockerHub, example based on the repo:  kidcoconut73/img_stm_omdenasaudi_hcc
+    #    docker tag img_omdenasaudi_hcc:0.1 kidcoconut73/img_stm_omdenasaudi_hcc:demo
+    #    docker tag img_omdenasaudi_hcc:0.1 kidcoconut73/img_stm_omdenasaudi_hcc:0.1
+    #--- tag the image
+    echo -e "\nTRACE:  Tag the image ..."
+    docker tag ${kstr_dkrImg} $kstr_dkrHubImg
+    docker tag ${kstr_dkrImg} "${kstr_defDkrHubId}/${kstr_defDkrImageName}:${kstr_defDkrTagVersion}"
+
+
+    #--- push the image to dockerHub
+    #    docker push kidcoconut73/img_stm_omdenasaudi_hcc:demo
+deadCode

{bin → scripts}/models/util_joinModel.sh

@@ -13,14 +13,25 @@ blkHeader
 #none
 
 
-#---    initialization
+#--- initialize/configuration
 #---    $1:  first arg;  source pattern match;  eg './bin/models/deeplabv3*vhflip30/model_a*';  Note that this is wildcarded so must be in quotes
 #---    $n:  last arg; dest model file;  eg. ./bin/models/model.pth
+echo -e "INFO(util_joinModel):\t Initializing ..."
 strPth_patternMatch=$1
+if [ -z "$strPth_patternMatch" ]; then
+    echo "WARN: no args provided.  Exiting script."
+    exit
+fi
+
 strPth_filMatch=( $strPth_patternMatch )        #--- expand the pattern match; get the first value of the pattern match
 strPth_parentFld=$(dirname $strPth_filMatch)    #--- get the parent dir of the first file match
 strPth_mdlFile=${@: -1}                         #--- Note:  this gets the last arg;  otherwise the 2nd arg would be an iteration of the 1st arg wildcard
 
+strpth_pwd=$(pwd)
+strpth_scriptLoc=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )
+strpth_scrHome="${strpth_scriptLoc}/../"
+strpth_appHome="${strpth_scrHome}/../"
+
 #echo "TRACE:  strPth_patternMatch= $strPth_patternMatch"
 #echo "TRACE:  strPth_filMatch= $strPth_filMatch"
 #echo "TRACE:  strPth_parentFld= $strPth_parentFld"
@@ -29,4 +40,6 @@ strPth_mdlFile=${@: -1}                         #--- Note:  this gets the last a
 #--- reconstitute model
 #--- Note:  cat command does not work with single-quote literals; do not reapply single quotes
 #echo "cat ${strPth_patternMatch} > ${strPth_mdlFile}"
+echo -e "INFO:\t Joining model binary ..."
 cat ${strPth_patternMatch} > ${strPth_mdlFile}
+echo -e "INFO:\t Done ...\n"

{bin → scripts}/models/util_splitModel.sh

@@ -13,13 +13,24 @@ blkHeader
 #none
 
 
-#---    initialization
+#---    initialization/configuration
 #---    $1:  first arg; the source model file; eg ./bin/models/model.pth
 #---    $n:  last arg; dest model path;  eg. ./test_model_folder
 strPth_mdlFile=$1
 strPth_mdlFolder=$2
 strPrefix='/model_'
 
+if [ -z "$strPth_mdlFile" ] || [ -z "$strPth_mdlFolder" ]; then
+    echo "WARN: no args provided.  Exiting script."
+    exit
+fi
+
+strpth_pwd=$(pwd)
+strpth_scriptLoc=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )
+strpth_scrHome="${strpth_scriptLoc}/../"
+#strpth_ignHome="${strpth_scrHome}/../"
+strpth_appHome="${strpth_scrHome}/../"
+
 #echo "TRACE:  strPth_mdlFile= $strPth_mdlFile"
 echo "TRACE:  strPth_mdlFolder= $strPth_mdlFolder"
 
@@ -29,3 +40,5 @@ mkdir -p $strPth_mdlFolder
 #--- split the model into smaller chunks
 echo "split -b 10M $strPth_mdlFile $strPth_mdlFolder$strPrefix"
 split -b 10M $strPth_mdlFile $strPth_mdlFolder$strPrefix
+
+echo -e "INFO:\t Done ...\n"

util_startLocal_streamlitFastApi.sh → scripts/streamlitFastApi/util_local_runStreamlitFastApi.sh

@@ -1,21 +1,25 @@
 #!/bin/bash
 
 #--- Note:  this file is designed to run locally and within docker to prep the environment
+#--- Entry:  this script is assumed to run from the /app root folder
+#--- Usage:  ./scripts/util_local_runStreamlitFastApi.sh
+echo -e "INFO(util_local_runStreamlitFastApi):\t Initializing ..."
+
 #--- for volume initialization; ensure folders are in place; assume:  we are in the /app folder
-#mkdir -p data/demo_tiles/raw
-#mkdir -p data/tiles/raw data/tiles/pred data/tiles/grad_bg data/tiles/grad_wt data/tiles/grad_vt
-#mkdir -p data/wsi/raw
+mkdir -p data/demo_tiles/raw
+mkdir -p data/tiles/raw data/tiles/pred data/tiles/grad_bg data/tiles/grad_wt data/tiles/grad_vt
+mkdir -p data/wsi/raw
 
 #--- for streamlit;  external 49400;  internal 39400
 echo "INFO:  starting streamlit ..."
-streamlit run app.py --server.port=49400 --server.maxUploadSize=2000 &
+streamlit run app.py --server.port=39400 --server.maxUploadSize=2000 &
 
 #--- for fastapi;  external 49500;  internal 39500
 echo "INFO:  starting fastapi ..."
-uvicorn main:app --reload --workers 1 --host 0.0.0.0 --port 49500 &
+uvicorn main:app --reload --workers 1 --host 0.0.0.0 --port 39500 &
 
 #--- wait for any process to exit
 wait -n
 
 #--- Exit with status of process that exited first
-exit $?
+exit $?

scripts/util.sh

@@ -0,0 +1,148 @@
+#!/bin/bash
+
+#--- Note:  this file acts as a bash function library
+
+
+<<blockComment 
+    Name:       
+    Usage:      
+    PreReqs:    
+blockComment
+
+
+
+#--- declarations
+<<blockComment
+function utl_trace_config (aryConfigVars) {
+    for each strConfig in aryConfigVars
+    trace_var("kstr_defDkrHubId")
+    #echo "TRACE:  kstr_defDkrHubId = ${kstr_defDkrHubId}"
+    echo "TRACE:  kstr_defDkrImageName = ${kstr_defDkrImageName}"
+    echo "TRACE:  kstr_defDkrTagVersion = ${kstr_defDkrTagVersion}"
+    echo "TRACE:  kstr_defDkrTagStage = ${kstr_defDkrTagStage}"
+    echo "TRACE:  kstr_dkrImg = ${kstr_dkrImg}"
+    echo "TRACE:  kstr_dkrCtr = ${kstr_dkrCtr}"
+}
+blockComment
+
+
+function utl_strRepeat {
+    #--- Usage1:  utl_strRepeat <repeatVal> <repeatCount> <returnVar> 
+    local strRptVal="${1:-null}"       #--- value to repeat
+    local intRptCount="${2:-1}"        #--- repeat count; num times to repeat text
+    local varReturn="${3:-output}"     #--- output var
+    local strTemp                      #--- temp variable
+    printf -v strTemp '%*s' "$intRptCount"
+    printf -v "$varReturn" '%s' "${strTemp// /$strRptVal}"
+}
+
+
+function utl_valIsEmpty {
+    #--- Usage1:    utl_valIsEmpty <val> | "<val>"
+    #--- Usage2:    returnVal=$(utl_valIsEmpty <val> | "<val>")
+    local strTestVal="${1:-null}"      #--- test value
+    local __blnReturn=NULL             #--- output var
+    
+    #echo -e "TRACE: \t $1\n"
+#    if [ ! -z "$strTestVal" -a "$strTestVal" != " " -a "$strTestVal" != "" ]; then      #--- check for empty string
+    if [ ! -z "$strTestVal" ]; then
+        __blnReturn=false
+        if [ "$strTestVal" == " " ] || [ "$strTestVal" == "" ]; then
+            __blnReturn=true            
+        else  
+            if [ "$strTestVal" == null ] || [ "$strTestVal" == NULL ] || [ "$strTestVal" == Null ]; then   
+                    __blnReturn=true
+            fi
+        fi
+    else
+        __blnReturn=true
+    fi
+    echo "$__blnReturn"
+}
+
+
+function utl_varIsEmpty {
+    local strTestVar="${1:-null}"      #--- test variable
+    local __blnReturn=false            #--- output var
+    
+    if [ -z "$strTestVar" ]; then      #--- check for empty string
+        __blnReturn=true
+    fi
+    echo "$__blnReturn"
+}
+
+
+function utl_getScriptLoc {
+    local __blnReturn=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )
+    echo "$__blnReturn"
+}
+
+
+function utl_logMsg {
+    #--- format: <date/time> \ t <logType> <logLevel> \t <preMsg> \t <Msg> \t <postMsg> \t <varName> \t <varValue>
+    local blnLogOn="${1:-true}"        #--- true: log, false:  do not log 
+    local strLogType="${2:-LOG}"       #--- INFO, ERR, WARN, TRACE, TRMOD, TRFXN, EXCPT, DEBUG
+    local strLogLevel="${3:-0}"        #--- Depth of log (tab indent) 
+    local strMsgPrefix="${4:-null}"    #--- 
+    local strMsg="${5:-null}"          #--- 
+    local strMsgPostfix="${6:-null}"   #---     
+    local strVarName="${7:-null}"      #--- 
+    local strVarVal="${8:-null}"       #--- 
+
+    #local blnIsEmpty=$(utl_valIsEmpty $strMsg)
+    #echo -e "TRACE: blnIsEmpty=$blnIsEmpty \t $strMsg \t $(blnEmpty==false) \t $(blnEmpty=='false')"
+    if $(utl_valIsEmpty $strMsgPrefix); then strMsgPrefix=""; else strMsgPrefix="$strMsgPrefix \t"; fi
+    if $(utl_valIsEmpty $strMsg); then strMsg=""; else strMsg="$strMsg \t"; fi
+    if $(utl_valIsEmpty $strMsgPostfix); then strMsgPostfix=""; else strMsgPostfix="$strMsgPostfix \t"; fi
+    if $(utl_valIsEmpty $strVarName); then strVarName=""; else strVarName="$strVarName = "; fi
+    if $(utl_valIsEmpty $strVarVal); then strVarVal=""; else strVarVal="$strVarVal"; fi
+
+    local intTabLevel="$strLogLevel"
+    #echo "TRACE (utl_logMsg):  $strLogLevel"
+    utl_strRepeat "\t" $intTabLevel strTabLevel
+    #echo "TRACE (utl_logMsg):  $strTabLevel"
+
+    if $(utl_valIsEmpty $strLogLevel); then strLogLevel="\b"; strTabLevel=""; fi
+    if [ "$strLogLevel" -eq "0" ]; then strLogLevel="\b"; strTabLevel=""; fi
+
+    #if $($strLogLevel==0); then strLogLevel=""; strTabLevel=""; fi
+
+    if [ "$blnLogOn" ]; then 
+        echo -e "$strTabLevel $strLogType $strLogLevel: \t $strMsgPrefix $strMsg $strMsgPostfix $strVarName $strVarVal"
+    fi
+}
+
+
+function utl_logTrace {
+    #--- format: <date/time> \ t <logType> <logLevel> \t <preMsg> \t <Msg> \t <postMsg> \t <varName> \t <varValue>
+    local blnLogOn="${1:-true}"        #--- true: log, false:  do not log 
+    local strLogType="TRACE"           #--- INFO, ERR, WARN, TRACE, TRMOD, TRFXN, EXCPT, DEBUG
+    local strLogLevel="${2:-0}"        #--- Depth of log (tab indent) 
+    local strMsg="${3:-null}"          #--- 
+
+    utl_logMsg $blnLogOn "$strLogType" "$strLogLevel" null "$strMsg" null null null
+}
+
+function utl_logInfo {
+    #--- format: <date/time> \ t <logType> <logLevel> \t <preMsg> \t <Msg> \t <postMsg> \t <varName> \t <varValue>
+    local blnLogOn="${1:-true}"        #--- true: log, false:  do not log 
+    local strLogType="INFO"           #--- INFO, ERR, WARN, TRACE, TRMOD, TRFXN, EXCPT, DEBUG
+    local strLogLevel="${2:-0}"        #--- Depth of log (tab indent) 
+    local strMsg="${3:-null}"          #--- 
+
+    utl_logMsg $blnLogOn "$strLogType" "$strLogLevel" null "$strMsg" null null null
+}
+
+
+function utl_trace_var {
+    local strVarName="${1:-null}"      #--- 
+    local strVarVal="${2:-null}"       #--- 
+    #echo "\t(util.utl_trace_var) TRACE: \t strVarName = ${strVarName}"
+
+    #kstr_tracePtn="TRACE:  <var> = \${<var>}"
+    #str_tracePtn="${kstr_tracePtn//<var>/"$strVarName"}"          #--- bash replace all occurrences
+    #echo ${str_tracePtn}
+    #echo "TRACE (utl_trace_var):  $strVarName = $strVarVal"
+    #utl_logMsg true "TRACE" 0 "msgPrefix" "msg" "msgPostfix" $strVarName $strVarVal
+    utl_logMsg true "TRACE" 0 null null null $strVarName $strVarVal
+}

uix/lit_sidebar.py

@@ -5,12 +5,14 @@ from uix import lit_packages
 from uix.pages import lit_home, lit_about, lit_diagnosis
 from uix.pages import lit_qaConfigCheck
 
+m_kblnTraceOn=False
+
 
 #--- alt define sidebar pages
 m_aryPages = {
     "Home":                         lit_home,           #--- TODO:  update
-    "Diagnosis:  One Tile":         lit_diagnosis,
-    #"QA:  File Check":              lit_qaConfigCheck,         
+    "Diagnosis:  Single Tile":      lit_diagnosis,
+    #"QA:  File Check":             lit_qaConfigCheck,         
     "About":                        lit_about
 }
 
@@ -26,71 +28,16 @@ def init():
     with st.sidebar:
         kstrUrl_image = "bin/images/logo_omdena_saudi.png"
         st.sidebar.image(kstrUrl_image, width=200)
-        #st.sidebar.markdown('Omdena Saudi - Liver HCC Diagnosis with XAI') 
- 
 
-    #--- init checkboxes
-    strKey = st.sidebar.radio("", list(m_aryPages.keys()))
+    #--- get radio selection
+    strKey = st.sidebar.radio("rdoPageSel", list(m_aryPages.keys()), label_visibility="hidden")
     pagSel = m_aryPages[strKey]
     writePage(pagSel)
 
 
-
-def init_selectBox():
-    #--- init module array of page names, and descr
-    init_modDescrAry()
-
-    # Display the sidebar with a menu of apps
-    kstrMsg = """
-            __Claims Anomaly Views__
-            """
-    with st.sidebar:
-        st.markdown('---')
-        st.markdown(kstrMsg)
-        page = st.selectbox('Select:', m_aryModNames, format_func=fmt_modName) 
-
-    #--- display sidebar footer
-    with st.sidebar:
-        st.markdown('---')
-        st.write('Developed by Chavarria, McKone, Sharma')
-        st.write('Contact at iain.mckone@gmail.com')
-    
-    # Run the chosen app
-    m_aryMods[m_aryModNames.index(page)].run()
-
-
-
-def init_modDescrAry():
-    #--- init global array of page names, and descr
-    #--- note:  you need to specify global scope for fxns to access module-level variables 
-    global m_aryMods
-    global m_aryDescr
-
-    m_aryMods = []
-    m_aryDescr = []
-    for modName in m_aryModNames:
-        modTemp = importlib.import_module('.'+modName,'uix')
-        m_aryMods.append(modTemp)
-
-        #--- If the module has a description attribute use that in the 
-        #--- select box otherwise use the module name
-        try:
-            m_aryDescr.append(modTemp.description)
-        except:
-            m_aryDescr.append(modName)
-
-
-
-#--- display the app descriptions instead of the module names in the selctbox
-def fmt_modName(strName):
-    global m_aryModNames
-    global m_aryDescr
-    return m_aryDescr[m_aryModNames.index(strName)]
-
-
-
 def writePage(uixFile):  
     #--- writes out the page for the selected combo
-  
+
     # _reload_module(page)
     uixFile.run()
+

uix/pages/lit_about.py

@@ -10,13 +10,17 @@ def run():
     #st.experimental_memo.clear()            #--- try to clear cache each time this page is hit
     #st.cache_data.clear()
 
-    st.markdown('### About')
-    st.markdown('### Omdena Saudi:  Liver HCC Diagnosis with XAI')
-    st.markdown('#### Chapter Lead:  Dr. Shai')
-
+    #st.markdown('### About')
+    #st.markdown('### Omdena Saudi Arabia')
+    #st.markdown('### Detecting Liver Cancer from Histopathology WSI Using Deep Learning and Explainability')
+    #st.markdown('#### Dr. Shaista Hussain (Saudi Arabia Chapter Lead)')
+    #st.markdown('##### Deployment Lead:  Iain McKone')
+    st.markdown('##### Project Url:  https://github.com/OmdenaAI/saudi-arabia-histopathology-detection')
+    '''
     st.markdown(
         """
             About page
         """,
             unsafe_allow_html=True,
-        )
+        )
+    '''

uix/pages/lit_diagnosis.py

@@ -18,7 +18,7 @@ from pytorch_grad_cam.utils.image import show_cam_on_image
 import lib.utils as libUtils
 
 import sys
-import os
+import os, random, io
 
 description = "Diagnosis"
 m_kblnTraceOn = True                                  #--- enable/disable module level tracing
@@ -42,6 +42,25 @@ backbone_model_name = DEFAULT_BACKBONE_MODEL
 
 
 
+def image_toBytesIO(image: Image) -> bytes:
+  #--- BytesIO is a file-like buffer stored in memory
+  imgByteArr = io.BytesIO()
+
+  #--- image.save expects a file-like as a argument
+  image.save(imgByteArr, format=image.format)
+
+  return imgByteArr
+
+
+def image_toByteArray(image: Image) -> bytes:
+  #--- convert image to bytesIO 
+  imgByteArr = image_toBytesIO(image)
+
+  #--- Turn the BytesIO object back into a bytes object
+  imgByteArr = imgByteArr.getvalue()
+  return imgByteArr
+
+
 def run():
     #--- note:  in python, you need to specify global scope for fxns to access module-level variables 
     global m_kbln_TraceOn
@@ -50,36 +69,59 @@ def run():
 
     #--- page settings
     if (m_kblnTraceOn):  print("TRACE1 (litDiagnosis.run):  Initialize Page Settings ...")
-    st.header("Single Tile Diagnosis")
+    #st.header("Single Tile Diagnosis")
+    st.markdown("#### Single Tile Diagnosis")
+
+    #--- allow the user to select a random sample
+    imgUploaded = None
+    if st.button("Random Sample"):
+        #--- get a random sample file
+        strPth_sample = libUtils.pth_dtaTileSamples
+        strFil_sample = random.choice(os.listdir(strPth_sample))
+        strFullPth_sample = os.path.join(strPth_sample, strFil_sample)
+
+        print("INFO (litDiagnosis.run):  sample file selected ... ", strFullPth_sample)
+
+        #--- display;  convert file image to bytesIO
+        imgSample = Image.open(strFullPth_sample)
+        imgSample = image_toBytesIO(imgSample)
+        imgUploaded = imgSample
+        imgUploaded.name = strFil_sample
+        imgUploaded.type = os.path.splitext(strFil_sample)[1]
 
 
     #--- provide file drag/drop capability
     m_blnDisableDragDrop = False
-    if(not m_blnDisableDragDrop): 
+    #if(not m_blnDisableDragDrop): 
         #btnSave = st.button("Save")
-        imgDropped = st.file_uploader("Upload a single Tile", type=["png", "jpg", "tif", "tiff", "img"])
-        m_blnDisableDragDrop = (imgDropped is None)
+    imgDropped = st.file_uploader("Upload a single Tile", 
+                type=["png", "jpg", "tif", "tiff", "img"], 
+                accept_multiple_files=False )
+    #m_blnDisableDragDrop = (imgDropped is None)
+    #--- <class 'streamlit.runtime.uploaded_file_manager.UploadedFile'>
+    if (imgDropped is not None):
+        imgUploaded = imgDropped
 
 
-    #if (True):
+    if (imgUploaded is None):
+        if (m_kblnTraceOn):  print("ERROR (litDiagnosis.run):  imgUploaded is None ...")
+    else:
         try:
-
+            #--- display uploaded file details
+            if (m_kblnTraceOn):  print("TRACE1 (litDiagnosis.run):  Print uploaded file details ...")
+            st.write("FileName:", "&nbsp;&ensp;&emsp;", imgUploaded.name)
+            st.write("FileType:", "&nbsp;&emsp;&emsp;", imgUploaded.type)
+            
             #--- show:  
             #if (m_kblnTraceOn):  print("TRACE (litDiagnosis.run):  load WSI ...")
-            if (m_blnDisableDragDrop):
+            #if (m_blnDisableDragDrop):
                 #--- load wsi 
-                print("")
-            else:
-                #--- display uploaded file details
-                if (m_kblnTraceOn):  print("TRACE1 (litDiagnosis.run):  Print upload file details ...")
-                st.write(
-                    "FileName:", "&nbsp;&ensp;&emsp;", imgDropped.name, "\n",
-                    "FileType:", "&nbsp;&emsp;&emsp;", imgDropped.type, "\n"
-                )
+            #    print("")
+            #else:
 
                 #--- display diagnosis results ... format (vertical)
-                #showDiagnosis_vert(imgDropped)
-                showDiagnosis_horiz(imgDropped)
+                #showDiagnosis_vert(imgUploaded)
+            showDiagnosis_horiz(imgUploaded)
 
         except TypeError as e:
             print("ERROR (litDiagnosis.run_typeError1):  ", e)
@@ -110,23 +152,24 @@ def showImg_wsi(img):
 
 
 def readyModel_getPreds(imgDropped):
-    print("TRACE:  save raw tile ...")
+    print("TRACE:  readyModel_getPreds ...")
+    print("INFO:  save raw tile ...")
     strPth_tilRaw = save_tilRaw(imgDropped)
     
     #--- ready the model
-    print("TRACE:  ready base model ...")
+    print("INFO:  ready base model ...")
     mdlBase = readyBaseModel()
-    print("TRACE:  ready model with weights ...")
+    print("INFO:  ready model with weights ...")
     mdlWeights = readyModelWithWeights(mdlBase)
-    print("TRACE:  ready model with xai ...")
+    print("INFO:  ready model with xai ...")
     mdlXai = readyModelWithXAI(mdlWeights)
 
     #--- get the XAI weighted prediction
-    print("TRACE:  get xai weighted pred ...")
+    print("INFO:  get xai weighted pred ...")
     output_pred, tns_batch = predXai_tile(mdlXai, strPth_tilRaw)
 
     #--- get the GRADCAM predictions
-    print("TRACE:  get GRADCAM preds ...")
+    print("INFO:  get GRADCAM preds ...")
     cam_img_bg, cam_img_wt, cam_img_vt = predGradCam_tile(output_pred, mdlXai, tns_batch)
 
     print("TRACE:  return readyModel_getPreds ...")
@@ -164,11 +207,16 @@ def showCol_rawTil(colRaw, strPth_tilRaw):
     print("TRACE3:  showCol_rawTil ...")
     colRaw.image(strPth_tilRaw, width=400, use_column_width=True)
 
-
+#--- Dark blue -> Background
+#   Brown -> Whole tumor
+#   Green/Aqua -> Viable tumor
 def showCol_predTil(colPred, xai_pred, strPth_tilRaw):
     kstrPth_tilePred = "data/tiles/pred/"
     strFilName = os.path.basename(strPth_tilRaw)
     strFil_tilePred = kstrPth_tilePred + strFilName
+    
+    #--- make sure the dir exists
+    ensureDirExists(kstrPth_tilePred)
 
     print("TRACE3:  showCol_predTil2 ... ", strFil_tilePred)
     argmax_mask = torch.argmax(xai_pred, dim=0)
@@ -217,10 +265,28 @@ def showDiagnosis_vert(imgDropped):
         colImage.image(lstImages[imgIdx], width=400, use_column_width=True)
 
 
+def ensureDirExists(strPth):
+    blnExists = os.path.exists(strPth)
+    if not blnExists:
+        os.makedirs(strPth)
+    print("TRACE:  creating dir ... ", strPth)
+
+
 def save_tilRaw(imgDropped):
+    print("TRACE:  save_tilRaw ...")
     #--- copy the uploaded raw Tile to data/tiles/raw
     kstrPth_tileRaw = "data/tiles/raw/"
     strFil_tileRaw = kstrPth_tileRaw + imgDropped.name
+    print("TRACE:  save_tilRaw.file ... ", strFil_tileRaw)
+
+    #--- make sure the dir exists
+    ensureDirExists(kstrPth_tileRaw)
+
+    #--- check if the file already exists; delete
+    if (os.path.isfile(strFil_tileRaw)):
+        print("WARN:  save_tilRaw.file exists;  delete ... ", strFil_tileRaw)
+        os.remove(strFil_tileRaw)
+
     with open(strFil_tileRaw,"wb") as filUpload: 
         filUpload.write(imgDropped.getbuffer()) 
     print("TRACE:  uploaded file saved to ", strFil_tileRaw)        

uix/pages/lit_home.py

@@ -7,21 +7,60 @@ def run():
     print("\nINFO (lit_home.run)  loading ", description, " page ...") 
 
 
-    st.markdown('### Home')
-    st.markdown('### Omdena Saudi:  Liver HCC Diagnosis with XAI')
-    st.markdown('#### Chapter Lead:  Dr. Shai')
+    #st.markdown('### Home')
+    #st.markdown('### Omdena Saudi Arabia')
+    #st.markdown('### Detecting Liver Cancer from Histopathology WSI Using Deep Learning and Explainability')
+    st.markdown('#### Background ')
     st.markdown('\
-        <background> \
-         ')
-    
-    st.markdown('\
-        <basis> \
-         ')
-    
+        Hepatocellular Carcinoma (HCC) is a primary liver malignancy, with \
+        alarming global impact. It is the 4th most common cause of cancer \
+        mortality worldwide, and the 6th most common malignancy overall. \
+        \
+        A patient\'s prognosis increases markedly with the speed of diagnosis \
+        and treatment, however the rates of occurrence are increasing at an \
+        alarming rate which will commensurately challenge the medical \
+        community. \
+        \
+        There are already several tools and technologies available to assist \
+        pathologists, however the current approach is ultimately constrained by \
+        a number of factors including:  the rising demand, a limited supply \
+        of skilled specialists, the time required to grow/replenish this talent \
+        pool, and human factors which influence quality, accuracy, consistency, \
+        and speed (timeliness). \
+        ')
+
+    st.markdown('#### Claim ')
     st.markdown('\
-        <claim> \
-         ')
+        It is the desire of this project team to increase the prognosis of \
+        hepatocellular cancer patients.\
+        \
+        Machine Learning techniques, specifically Deep Learning and \
+        Explainability (XAI) show promise in mimic\'ing the role of the \
+        pathologist.  \
+        \
+        MLOps promises to establish a baseline for performance\
+        and a basis for continuous process improvement.  This could greatly \
+        reduce human factor elements while accelerating the times and \
+        increasing the volumes of response.\
+        \
+        As a minimum, an ML application can serve as a supplement to the\
+        pathologist, a teaching aide, a verification tool, or as a framework\
+        for community collaboration and the advancement of quality diagnosis.\
+    ')
 
+    st.markdown('#### Objectives ')
+    st.markdown('\
+        A key objective of this project is to produce a deployed app that will\
+        enable pathologists to upload a digital liver histopathology slide\
+        image and then receive an output that classifies the segment as\
+        malignant (or not). \
+        \
+        The utilization of Machine Learning and Explainability Techniques \
+        to the traditional process of Liver Histopathology and HCC Diagnosis \
+        could serve to greatly reduce the time to diagnosis and treatment. \
+        \
+    ')
+    '''
     st.markdown(
         """
 
@@ -29,4 +68,9 @@ def run():
         
         """,
             unsafe_allow_html=True,
-        )
+        )
+    <style>
+        # MainMenu {visibility: hidden;}
+        footer {visibility: hidden;}
+    </style>
+    '''