Upload app.py

app.py

@@ -21,24 +21,24 @@ from datasets import load_dataset
 
 #Read data training data.
 
-x1 = pd.read_csv("m12_data_train.csv", index_col = 0, low_memory = False)
+x1 = pd.read_csv("m6_data_train.csv", index_col = 0, low_memory = False)
 
-x2 = pd.read_csv("m24_data_train.csv", index_col = 0, low_memory = False)
+x2 = pd.read_csv("m12_data_train.csv", index_col = 0, low_memory = False)
 
-x3 = pd.read_csv("m36_data_train.csv", index_col = 0, low_memory = False)
+x3 = pd.read_csv("m24_data_train.csv", index_col = 0, low_memory = False)
 
-x4 = pd.read_csv("m60_data_train.csv", index_col = 0, low_memory = False)
+x4 = pd.read_csv("m36_data_train.csv", index_col = 0, low_memory = False)
 
 
 #Read validation data.
 
-x1_valid = pd.read_csv("m12_data_valid.csv", index_col = 0, low_memory = False)
+x1_valid = pd.read_csv("m6_data_valid.csv", index_col = 0, low_memory = False)
 
-x2_valid = pd.read_csv("m24_data_valid.csv", index_col = 0, low_memory = False)
+x2_valid = pd.read_csv("m12_data_valid.csv", index_col = 0, low_memory = False)
 
-x3_valid = pd.read_csv("m36_data_valid.csv", index_col = 0, low_memory = False)
+x3_valid = pd.read_csv("m24_data_valid.csv", index_col = 0, low_memory = False)
 
-x4_valid = pd.read_csv("m60_data_valid.csv", index_col = 0, low_memory = False)
+x4_valid = pd.read_csv("m36_data_valid.csv", index_col = 0, low_memory = False)
 
 
 #Define feature names.
@@ -86,10 +86,10 @@ y4_valid = x4_valid.pop('OUTCOME')
 
 #Assign hyperparameters.
 
-y1_params =  {'objective': 'binary', 'boosting_type': 'gbdt', 'lambda_l1': 9.636570621064845e-06, 'lambda_l2': 0.003747385566704826, 'num_leaves': 8, 'feature_fraction': 0.5227250594804498, 'bagging_fraction': 0.44654591882113764, 'bagging_freq': 4, 'min_child_samples': 72, 'metric': 'binary_logloss', 'verbosity': -1, 'random_state': 31}
-y2_params =  {'objective': 'binary', 'boosting_type': 'gbdt', 'lambda_l1': 8.065104217173182, 'lambda_l2': 0.009368546720767723, 'num_leaves': 15, 'feature_fraction': 0.4640347984930871, 'bagging_fraction': 0.4385618748071607, 'bagging_freq': 3, 'min_child_samples': 66, 'metric': 'binary_logloss', 'verbosity': -1, 'random_state': 31}
-y3_params =  {'objective': 'binary', 'boosting_type': 'gbdt', 'lambda_l1': 1.2748078853140657e-05, 'lambda_l2': 0.6573192301848148, 'num_leaves': 39, 'feature_fraction': 0.7143554798223156, 'bagging_fraction': 0.5791644571313095, 'bagging_freq': 7, 'min_child_samples': 50, 'metric': 'binary_logloss', 'verbosity': -1, 'random_state': 31}
-y4_params =  {'objective': 'binary', 'boosting_type': 'gbdt', 'lambda_l1': 7.088664776651091e-06, 'lambda_l2': 4.1646943899743127e-08, 'num_leaves': 36, 'feature_fraction': 0.436937199531357, 'bagging_fraction': 0.8226045360995117, 'bagging_freq': 4, 'min_child_samples': 68, 'metric': 'binary_logloss', 'verbosity': -1, 'random_state': 31}
+y1_params =  {'objective': 'binary', 'boosting_type': 'gbdt', 'lambda_l1': 2.874728678068222e-05, 'lambda_l2': 0.002100238688192627, 'num_leaves': 39, 'feature_fraction': 0.4504130718946593, 'bagging_fraction': 0.8916461477863318, 'bagging_freq': 7, 'min_child_samples': 45, 'metric': 'binary_logloss', 'verbosity': -1, 'random_state': 31}
+y2_params =  {'objective': 'binary', 'boosting_type': 'gbdt', 'lambda_l1': 0.0002837317278662907, 'lambda_l2': 5.412618023120056e-06, 'num_leaves': 78, 'feature_fraction': 0.4044321534682025, 'bagging_fraction': 0.747678020066352, 'bagging_freq': 6, 'min_child_samples': 44, 'metric': 'binary_logloss', 'verbosity': -1, 'random_state': 31}
+y3_params =  {'objective': 'binary', 'boosting_type': 'gbdt', 'lambda_l1': 0.00016354134178989566, 'lambda_l2': 0.005110516449291205, 'num_leaves': 4, 'feature_fraction': 0.525789668995701, 'bagging_fraction': 0.4203858842031528, 'bagging_freq': 3, 'min_child_samples': 66, 'metric': 'binary_logloss', 'verbosity': -1, 'random_state': 31}
+y4_params =  {'objective': 'binary', 'boosting_type': 'gbdt', 'lambda_l1': 0.00014329772210712767, 'lambda_l2': 0.001638738946438707, 'num_leaves': 2, 'feature_fraction': 0.565882308738563, 'bagging_fraction': 0.47701769327658605, 'bagging_freq': 5, 'min_child_samples': 59, 'metric': 'binary_logloss', 'verbosity': -1, 'random_state': 31}
 
 #Training models.
 
@@ -140,7 +140,7 @@ y4_calib_model = y4_calib_model.fit(y4_calib_probs, y4_valid)
 output_y1 = (
     """          
         <br/>
-        <center>The probability of 12-month survival:</center>
+        <center>The probability of 6-month survival:</center>
         <br/>
         <center><h1>{:.2f}%</h1></center>
 """
@@ -149,7 +149,7 @@ output_y1 = (
 output_y2 = (
     """          
         <br/>        
-        <center>The probability of 24-month survival:</center>
+        <center>The probability of 12-month survival:</center>
         <br/>        
         <center><h1>{:.2f}%</h1></center>
 """
@@ -158,7 +158,7 @@ output_y2 = (
 output_y3 = (
     """          
         <br/>        
-        <center>The probability of 36-month survival:</center>
+        <center>The probability of 24-month survival:</center>
         <br/>        
         <center><h1>{:.2f}%</h1></center>
 """
@@ -167,7 +167,7 @@ output_y3 = (
 output_y4 = (
     """          
         <br/>        
-        <center>The probability of 60-month survival:</center>
+        <center>The probability of 36-month survival:</center>
         <br/>        
         <center><h1>{:.2f}%</h1></center>
 """
@@ -297,12 +297,12 @@ def y4_interpret(*args):
     return fig
 
 
-with gr.Blocks(title = "NCDB-LGG") as demo:
+with gr.Blocks(title = "NCDB-GBM") as demo:
         
     gr.Markdown(
         """
     <br/>
-    <center><h1>LGG Survival Outcomes</h1></center>
+    <center><h1>GBM Survival Outcomes</h1></center>
     <center><h2>Prediction Tool</h2></center>
     <center><i>The publication describing the details of this predictive tool will be posted here upon the acceptance of publication.</i><center>
         """
@@ -324,44 +324,44 @@ with gr.Blocks(title = "NCDB-LGG") as demo:
             <th>Brier Score</th>
           </tr>
           <tr>
-            <td>12-Month Mortality</td>
+            <td>6-Month Mortality</td>
             <td>LightGBM</td>
-            <td>0.758 (0.745 - 0.771)</td>
-            <td>0.836 (0.825 - 0.847)</td>
-            <td>0.821 (0.810 - 0.832)</td>
-            <td>0.649 (0.635 - 0.663)</td>
-            <td>0.889 (0.865 - 0.890)</td>
-            <td>0.101 (0.092 - 0.110)</td>             
+            <td>0.694 (0.686 - 0.702)</td>
+            <td>0.810 (0.803 - 0.817)</td>
+            <td>0.772 (0.765 - 0.779)</td>
+            <td>0.719 (0.711 - 0.727)</td>
+            <td>0.831 (0.824 - 0.838)</td>
+            <td>0.152 (0.146 - 0.158)</td>             
           </tr>
           <tr>
-            <td>24-Month Mortality</td>
+            <td>12-Month Mortality</td>
             <td>LightGBM</td>
-            <td>0.771 (0.758 - 0.784)</td>
-            <td>0.844 (0.833 - 0.855)</td>
-            <td>0.822 (0.811 - 0.833)</td>
-            <td>0.783 (0.771 - 0.795)</td>
-            <td>0.892 (0.873 - 0.894)</td>
-            <td>0.123 (0.113 - 0.133)</td>             
+            <td>0.700 (0.692 - 0.708)</td>
+            <td>0.742 (0.735 - 0.749)</td>
+            <td>0.720 (0.712 - 0.728)</td>
+            <td>0.821 (0.815 - 0.827)</td>
+            <td>0.808 (0.792 - 0.807)</td>
+            <td>0.183 (0.176 - 0.190)</td>             
           </tr>
           <tr>
-            <td>36-Month Mortality</td>
+            <td>24-Month Mortality</td>
             <td>LightGBM</td>
-            <td>0.771 (0.758 - 0.784)</td>
-            <td>0.825 (0.813 - 0.837)</td>
-            <td>0.803 (0.791 - 0.815)</td>
-            <td>0.834 (0.823 - 0.845)</td>
-            <td>0.884 (0.865 - 0.886)</td>
-            <td>0.139 (0.128 - 0.150)</td>             
+            <td>0.742 (0.735 - 0.749)</td>
+            <td>0.555 (0.547 - 0.563)</td>
+            <td>0.702 (0.694 - 0.710)</td>
+            <td>0.897 (0.892 - 0.902)</td>
+            <td>0.725 (0.706 - 0.728)</td>
+            <td>0.153 (0.147 - 0.159)</td>             
           </tr>                        
           <tr>
-            <td>60-Month Mortality</td>
+            <td>36-Month Mortality</td>
             <td>LightGBM</td>
-            <td>0.789 (0.775 - 0.803)</td>
-            <td>0.819 (0.806 - 0.832)</td>
-            <td>0.802 (0.789 - 0.815)</td>
-            <td>0.905 (0.895 - 0.915)</td>
-            <td>0.870 (0.864 - 0.887)</td>
-            <td>0.142 (0.130 - 0.154)</td>             
+            <td>0.705 (0.697 - 0.713)</td>
+            <td>0.576 (0.568 - 0.584)</td>
+            <td>0.689 (0.681 - 0.697)</td>
+            <td>0.937 (0.933 - 0.941)</td>
+            <td>0.707 (0.687 - 0.713)</td>
+            <td>0.103 (0.098 - 0.108)</td>             
           </tr>        
         </table>
         </div>
@@ -387,6 +387,7 @@ with gr.Blocks(title = "NCDB-LGG") as demo:
             Facility_Location = gr.Dropdown(label = "Facility Location", choices = ['South Atlantic', 'East North Central', 'Middle Atlantic', 'East North Central', 'Middle Atlantic', 'Pacific', 'West South Central', 'West North Central', 'East South Central', 'New England', 'Mountain', 'Unknown or Other'], type = 'index', value = 'South Atlantic')
 
             CharlsonDeyo_Score = gr.Dropdown(label = "Charlson-Deyo Score", choices = ['0', '1', '2', 'Greater than 3'], type = 'index', value = '0')
+            
             Karnofsky_Performance_Scale = gr.Dropdown(label = "Karnofsky Performance Scale", choices = ['KPS 0-20', 'KPS 21-40', 'KPS 41-60', 'KPS 61-80', 'KPS 81-100', 'Unknown'], type = 'index', value = 'KPS 81-100')
             
             Laterality = gr.Dropdown(label = "Laterality", choices = ['Right', 'Left', 'Bilateral', 'Midline', 'Unknown'], type = 'index', value = 'Right')
@@ -399,10 +400,6 @@ with gr.Blocks(title = "NCDB-LGG") as demo:
             
             Tumor_Size = gr.Dropdown(label = "Tumor Size", choices = ['< 2 cm', '2 - 3.9 cm', '4 - 5.9 cm', '6 - 7.9 cm', '8 - 9.9 cm', '10 - 11.9 cm', '12 - 13.9 cm', '14 - 15.9 cm', '16 - 17.9 cm', '18 - 19.9 cm', '> 20 cm', 'Unknown'], type = 'index', value = '< 2 cm')
             
-            Histology = gr.Dropdown(label = "Histology", choices = ['Astrocytoma', 'Oligodendroglioma', 'Oligoastrocytoma'], type = 'index', value = 'Astrocytoma')
-            
-            Grade = gr.Dropdown(label = "Grade", choices = ['Grade II', 'Grade III'], type = 'index', value = 'Grade II')
-            
             CoDeletion_1p19q = gr.Dropdown(label = "1p19q Co-Deletion", choices = ['No', 'Yes', 'Unknown'], type = 'index', value = 'No')
             
             MGMT_Methylation = gr.Dropdown(label = "MGMT Methylation", choices = ['Unmethylated', 'Methylated', 'Unknown'], type = 'index', value = 'Unmethylated')
@@ -425,7 +422,7 @@ with gr.Blocks(title = "NCDB-LGG") as demo:
                 
                 gr.Markdown(
                     """
-                    <center> <h2>12-Month Survival</h2> </center>
+                    <center> <h2>6-Month Survival</h2> </center>
                     <br/>
                     <center> This model uses the LightGBM algorithm.</center>
                     <br/>
@@ -469,7 +466,7 @@ with gr.Blocks(title = "NCDB-LGG") as demo:
             with gr.Box():
                 gr.Markdown(
                     """
-                    <center> <h2>24-Month Survival</h2> </center>
+                    <center> <h2>12-Month Survival</h2> </center>
                     <br/>
                     <center> This model uses the LightGBM algorithm.</center>
                     <br/>
@@ -514,7 +511,7 @@ with gr.Blocks(title = "NCDB-LGG") as demo:
                 
                 gr.Markdown(
                     """
-                    <center> <h2>36-Month Survival</h2> </center>
+                    <center> <h2>24-Month Survival</h2> </center>
                     <br/>
                     <center> This model uses the LightGBM algorithm.</center>
                     <br/>
@@ -559,7 +556,7 @@ with gr.Blocks(title = "NCDB-LGG") as demo:
                 
                 gr.Markdown(
                     """
-                    <center> <h2>60-Month Survival</h2> </center>
+                    <center> <h2>36-Month Survival</h2> </center>
                     <br/>
                     <center> This model uses the LightGBM algorithm.</center>
                     <br/>
@@ -603,49 +600,49 @@ with gr.Blocks(title = "NCDB-LGG") as demo:
            
                 y1_predict_btn.click(
                     y1_predict,
-                    inputs = [Facility_Type,Facility_Location,Age,Sex,Race,Hispanic_Ethnicity,Primary_Payor,CharlsonDeyo_Score,Histology,Tumor_Localization,Laterality,Diagnostic_Biopsy,Grade,Ki67_Labeling_Index,Karnofsky_Performance_Scale,MGMT_Methylation,Focality,Tumor_Size,Chemotherapy,Immunotherapy,CoDeletion_1p19q,Resective_Surgery,Extent_of_Resection,Radiation_Treatment],
+                    inputs = [Facility_Type,Facility_Location,Age,Sex,Race,Hispanic_Ethnicity,Primary_Payor,CharlsonDeyo_ScoreTumor_Localization,Laterality,Diagnostic_Biopsy,Ki67_Labeling_Index,Karnofsky_Performance_Scale,MGMT_Methylation,Focality,Tumor_Size,Chemotherapy,Immunotherapy,CoDeletion_1p19q,Resective_Surgery,Extent_of_Resection,Radiation_Treatment],
                     outputs = [label1]
                 )
 
                 y2_predict_btn.click(
                     y2_predict,
-                    inputs = [Facility_Type,Facility_Location,Age,Sex,Race,Hispanic_Ethnicity,Primary_Payor,CharlsonDeyo_Score,Histology,Tumor_Localization,Laterality,Diagnostic_Biopsy,Grade,Ki67_Labeling_Index,Karnofsky_Performance_Scale,MGMT_Methylation,Focality,Tumor_Size,Chemotherapy,Immunotherapy,CoDeletion_1p19q,Resective_Surgery,Extent_of_Resection,Radiation_Treatment],
+                    inputs = [Facility_Type,Facility_Location,Age,Sex,Race,Hispanic_Ethnicity,Primary_Payor,CharlsonDeyo_ScoreTumor_Localization,Laterality,Diagnostic_BiopsyKi67_Labeling_Index,Karnofsky_Performance_Scale,MGMT_Methylation,Focality,Tumor_Size,Chemotherapy,Immunotherapy,CoDeletion_1p19q,Resective_Surgery,Extent_of_Resection,Radiation_Treatment],
                     outputs = [label2]
                 )
                 
                 y3_predict_btn.click(
                     y3_predict,
-                    inputs = [Facility_Type,Facility_Location,Age,Sex,Race,Hispanic_Ethnicity,Primary_Payor,CharlsonDeyo_Score,Histology,Tumor_Localization,Laterality,Diagnostic_Biopsy,Grade,Ki67_Labeling_Index,Karnofsky_Performance_Scale,MGMT_Methylation,Focality,Tumor_Size,Chemotherapy,Immunotherapy,CoDeletion_1p19q,Resective_Surgery,Extent_of_Resection,Radiation_Treatment],
+                    inputs = [Facility_Type,Facility_Location,Age,Sex,Race,Hispanic_Ethnicity,Primary_Payor,CharlsonDeyo_ScoreTumor_Localization,Laterality,Diagnostic_BiopsyKi67_Labeling_Index,Karnofsky_Performance_Scale,MGMT_Methylation,Focality,Tumor_Size,Chemotherapy,Immunotherapy,CoDeletion_1p19q,Resective_Surgery,Extent_of_Resection,Radiation_Treatment],
                     outputs = [label3]
                 )
 
                 y4_predict_btn.click(
                     y4_predict,
-                    inputs = [Facility_Type,Facility_Location,Age,Sex,Race,Hispanic_Ethnicity,Primary_Payor,CharlsonDeyo_Score,Histology,Tumor_Localization,Laterality,Diagnostic_Biopsy,Grade,Ki67_Labeling_Index,Karnofsky_Performance_Scale,MGMT_Methylation,Focality,Tumor_Size,Chemotherapy,Immunotherapy,CoDeletion_1p19q,Resective_Surgery,Extent_of_Resection,Radiation_Treatment],
+                    inputs = [Facility_Type,Facility_Location,Age,Sex,Race,Hispanic_Ethnicity,Primary_Payor,CharlsonDeyo_ScoreTumor_Localization,Laterality,Diagnostic_BiopsyKi67_Labeling_Index,Karnofsky_Performance_Scale,MGMT_Methylation,Focality,Tumor_Size,Chemotherapy,Immunotherapy,CoDeletion_1p19q,Resective_Surgery,Extent_of_Resection,Radiation_Treatment],
                     outputs = [label4]
                 )
 
                 y1_interpret_btn.click(
                     y1_interpret,
-                    inputs = [Facility_Type,Facility_Location,Age,Sex,Race,Hispanic_Ethnicity,Primary_Payor,CharlsonDeyo_Score,Histology,Tumor_Localization,Laterality,Diagnostic_Biopsy,Grade,Ki67_Labeling_Index,Karnofsky_Performance_Scale,MGMT_Methylation,Focality,Tumor_Size,Chemotherapy,Immunotherapy,CoDeletion_1p19q,Resective_Surgery,Extent_of_Resection,Radiation_Treatment],
+                    inputs = [Facility_Type,Facility_Location,Age,Sex,Race,Hispanic_Ethnicity,Primary_Payor,CharlsonDeyo_ScoreTumor_Localization,Laterality,Diagnostic_BiopsyKi67_Labeling_Index,Karnofsky_Performance_Scale,MGMT_Methylation,Focality,Tumor_Size,Chemotherapy,Immunotherapy,CoDeletion_1p19q,Resective_Surgery,Extent_of_Resection,Radiation_Treatment],
                     outputs = [plot1],
                 )
                 
                 y2_interpret_btn.click(
                     y2_interpret,
-                    inputs = [Facility_Type,Facility_Location,Age,Sex,Race,Hispanic_Ethnicity,Primary_Payor,CharlsonDeyo_Score,Histology,Tumor_Localization,Laterality,Diagnostic_Biopsy,Grade,Ki67_Labeling_Index,Karnofsky_Performance_Scale,MGMT_Methylation,Focality,Tumor_Size,Chemotherapy,Immunotherapy,CoDeletion_1p19q,Resective_Surgery,Extent_of_Resection,Radiation_Treatment],
+                    inputs = [Facility_Type,Facility_Location,Age,Sex,Race,Hispanic_Ethnicity,Primary_Payor,CharlsonDeyo_ScoreTumor_Localization,Laterality,Diagnostic_BiopsyKi67_Labeling_Index,Karnofsky_Performance_Scale,MGMT_Methylation,Focality,Tumor_Size,Chemotherapy,Immunotherapy,CoDeletion_1p19q,Resective_Surgery,Extent_of_Resection,Radiation_Treatment],
                     outputs = [plot2],
                 )
 
                 y3_interpret_btn.click(
                     y3_interpret,
-                    inputs = [Facility_Type,Facility_Location,Age,Sex,Race,Hispanic_Ethnicity,Primary_Payor,CharlsonDeyo_Score,Histology,Tumor_Localization,Laterality,Diagnostic_Biopsy,Grade,Ki67_Labeling_Index,Karnofsky_Performance_Scale,MGMT_Methylation,Focality,Tumor_Size,Chemotherapy,Immunotherapy,CoDeletion_1p19q,Resective_Surgery,Extent_of_Resection,Radiation_Treatment],
+                    inputs = [Facility_Type,Facility_Location,Age,Sex,Race,Hispanic_Ethnicity,Primary_Payor,CharlsonDeyo_ScoreTumor_Localization,Laterality,Diagnostic_BiopsyKi67_Labeling_Index,Karnofsky_Performance_Scale,MGMT_Methylation,Focality,Tumor_Size,Chemotherapy,Immunotherapy,CoDeletion_1p19q,Resective_Surgery,Extent_of_Resection,Radiation_Treatment],
                   outputs = [plot3],
                 )
 
                 y4_interpret_btn.click(
                     y4_interpret,
-                    inputs = [Facility_Type,Facility_Location,Age,Sex,Race,Hispanic_Ethnicity,Primary_Payor,CharlsonDeyo_Score,Histology,Tumor_Localization,Laterality,Diagnostic_Biopsy,Grade,Ki67_Labeling_Index,Karnofsky_Performance_Scale,MGMT_Methylation,Focality,Tumor_Size,Chemotherapy,Immunotherapy,CoDeletion_1p19q,Resective_Surgery,Extent_of_Resection,Radiation_Treatment],
+                    inputs = [Facility_Type,Facility_Location,Age,Sex,Race,Hispanic_Ethnicity,Primary_Payor,CharlsonDeyo_ScoreTumor_Localization,Laterality,Diagnostic_BiopsyKi67_Labeling_Index,Karnofsky_Performance_Scale,MGMT_Methylation,Focality,Tumor_Size,Chemotherapy,Immunotherapy,CoDeletion_1p19q,Resective_Surgery,Extent_of_Resection,Radiation_Treatment],
                   outputs = [plot4],
                 )