changes as comments

app.py

@@ -18,7 +18,7 @@ import csv
 def process_file(model_name,inc_slider,progress=Progress(track_tqdm=True)):
     # progress = gr.Progress(track_tqdm=True)
 
-    progress(0, desc="Starting the processing") 
+    progress(0, desc="Pre-Processing...") 
     # with open(file.name, 'r') as f:
     #     content = f.read()
     # saved_test_dataset = "train.txt"
@@ -78,14 +78,15 @@ def process_file(model_name,inc_slider,progress=Progress(track_tqdm=True)):
     # Load the test file and select rows based on indices
     test = pd.read_csv(test_location, sep=',', header=None, engine='python')
     selected_rows_df2 = test.loc[indices]
-    # label=pd.read_csv(label_location, header=None, engine='python')
-    # test_label=label.loc[indices]
-    # test_label.to_csv(parent_location+'highGRschool10/test_label.txt', sep='\t', index=False, header=False, quoting=3, escapechar=' ')
+    label=pd.read_csv(label_location, header=None, engine='python')
+    test_label=label.loc[indices]
+    test_label.to_csv(parent_location+'highGRschool10/test_label.txt', sep='\t', index=False, header=False, quoting=3, escapechar=' ')
     # Save the selected rows to a file
     selected_rows_df2.to_csv('fileHandler/selected_rows.txt', sep='\t', index=False, header=False, quoting=3, escapechar=' ')
     # ✅ Get the first 20% and last 20% of instances for each student ID within selected schools
 
     selected_test_info = test_info.loc[indices]
+    
 
     # # First 20%
     # first_20_percent_indices = selected_test_info.groupby(3).apply(
@@ -113,7 +114,7 @@ def process_file(model_name,inc_slider,progress=Progress(track_tqdm=True)):
     ]
     # Group data by opt_task1 and opt_task2 based on test_info[6]
     opt_task_groups = ['opt_task1' if test_info.loc[idx, 6] == 0 else 'opt_task2' for idx in selected_rows_df2.index]
-    progress(0.2, desc="Files create and saved!! Now Executing models")
+    progress(0.2, desc="Running fine-tuned models...")
     print("finetuned task: ",finetune_task)
     subprocess.run([
         "python", "new_test_saved_finetuned_model.py",
@@ -126,7 +127,7 @@ def process_file(model_name,inc_slider,progress=Progress(track_tqdm=True)):
         "-e",str(1),
         "-b",str(1000)
     ])
-    progress(0.5,desc="Model execution completed!! Now performing analysis on the results")
+    progress(0.5,desc="Saving output files..")
 
     # Load tlb and plb
     with open("fileHandler/tlabels_plabels.pkl", "rb") as f:
@@ -288,7 +289,7 @@ def process_file(model_name,inc_slider,progress=Progress(track_tqdm=True)):
     # Read data from test_info.txt
     with open(test_info_location, "r") as file:
         data = file.readlines()
-
+    selected_data = [data[i] for i in indices if i < len(data)]
     # Assuming test_info[7] is a list with ideal tasks for each instance
     ideal_tasks = test_info[6]  # A list where each element is either 1 or 2
 
@@ -304,7 +305,7 @@ def process_file(model_name,inc_slider,progress=Progress(track_tqdm=True)):
     opt2_ratios = []
     final_total=[]
     opt1_total=[]
-    for i, row in enumerate(data):
+    for i, row in enumerate(selected_data):
         row = row.strip()
         if not row:
             continue
@@ -664,9 +665,9 @@ def process_file(model_name,inc_slider,progress=Progress(track_tqdm=True)):
     Model: {model_name}
     ---------------------------\n
     Time Taken: {result['time_taken_from_start']:.2f} seconds
-    Total Schools in test: {len(unique_schools):.4f}
-    Total number of instances having Schools with HGR : {len(high_indices):.4f}
-    Total number of instances having Schools with LGR: {len(low_indices):.4f}
+    Number of schools sampled: {len(unique_schools)}
+    Total number of instances from HGR schools : {len(high_indices)}
+    Total number of instances from LGR schools: {len(low_indices)}
 
     ROC score of HGR: {high_roc_auc:.4f}
     ROC score of LGR: {low_roc_auc:.4f}
@@ -675,7 +676,7 @@ def process_file(model_name,inc_slider,progress=Progress(track_tqdm=True)):
     ROC-AUC for problems of type ER: {opt_task1_roc_auc:.4f}
     ROC-AUC for problems of type ME: {opt_task2_roc_auc:.4f}
     """
-    progress(0.5,desc="first k '%' sampling")
+    # progress(0.5,desc="first k '%' sampling")
 #     subprocess.run([
 #     "python", "new_test_saved_finetuned_model.py",
 #     "-workspace_name", "ratio_proportion_change3_2223/sch_largest_100-coded",
@@ -694,7 +695,7 @@ def process_file(model_name,inc_slider,progress=Progress(track_tqdm=True)):
     # print(roc_auc_first_k)
 
 
-    progress(0.5,desc="last '%' sampling")
+    # progress(0.5,desc="last '%' sampling")
 #     subprocess.run([
 #     "python", "new_test_saved_finetuned_model.py",
 #     "-workspace_name", "ratio_proportion_change3_2223/sch_largest_100-coded",

fileHandler/result.txt

@@ -1,7 +1,7 @@
-avg_loss: 0.5841353535652161
-total_acc: 69.00702106318957
-precisions: 0.7236623191454734
-recalls: 0.6900702106318957
-f1_scores: 0.6802420656474512
-time_taken_from_start: 2.079533815383911
-auc_score: 0.7457100293916334
+avg_loss: 0.5839772423108419
+total_acc: 69.6584058941728
+precisions: 0.7224570437809088
+recalls: 0.696584058941728
+f1_scores: 0.6872024231270459
+time_taken_from_start: 4.869930028915405
+auc_score: 0.7470103507185207

fileHandler/roc_data.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2483f35aa06ef8983623602f690eb3fe006654c79d448f4f82a913b4862e34e9
-size 9437
+oid sha256:2550042df149bd1483f0ddb2f0af449d7b679115a6f2bcc7c2af6600c20bfead
+size 27485

fileHandler/roc_data2.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0578bbc08b428a1f54707fc3aca6aa1063e045033cb007f8ba3361f1aace43df
-size 28023
+oid sha256:169a215fb6971ef69cb8a703b24f2afe9aae9383becccdbe2aaf9ad4c9abf005
+size 83732

fileHandler/tlabels_plabels.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1aabcfeb64b7645738d0507dd755822b92f2a256a2f0bdee28b2916268078eb
-size 37993
+oid sha256:71046b1d75a84d0f02d04aa725087ba339eb954fc9cf158d4d17331e73bfd48b
+size 113592