added for low

.gitignore

@@ -2,3 +2,4 @@ train_info.txt
 train.txt
 train_label.txt
 ratio_proportion_change3_2223/sch_largest_100-coded/logs/
+ratio_proportion_change3_2223/sch_largest_100-coded/finetuning/

app.py

@@ -23,10 +23,23 @@ def process_file(model_name,inc_slider,progress=Progress(track_tqdm=True)):
     # shutil.copyfile(file.name, saved_test_dataset)
     # shutil.copyfile(label.name, saved_test_label)
     # shutil.copyfile(info.name, saved_train_info)
-
-
+    parent_location="ratio_proportion_change3_2223/sch_largest_100-coded/finetuning/"
+    if(model_name=="High Graduated Schools"):
+        finetune_task="highGRschool10"
+        test_info_location=parent_location+"highGRschool10/test_info.txt"
+        test_location=parent_location+"highGRschool10/test.txt"
+    elif(model_name== "Low Graduated Schools" ):
+        finetune_task="lowGRschoolAll"
+        test_info_location=parent_location+"lowGRschoolAll/test_info.txt"
+        test_location=parent_location+"lowGRschoolAll/test.txt"
+    elif(model_name=="Full Set"):
+        test_info_location=parent_location+"highGRschool10/test_info.txt"
+        test_location=parent_location+"highGRschool10/test.txt"
+        finetune_task="highGRschool10"
+    else:
+        finetune_task=None
     # Load the test_info file and the graduation rate file
-    test_info = pd.read_csv('train_info.txt', sep=',', header=None, engine='python')
+    test_info = pd.read_csv(test_info_location, sep=',', header=None, engine='python')
     grad_rate_data = pd.DataFrame(pd.read_pickle('school_grduation_rate.pkl'),columns=['school_number','grad_rate'])  # Load the grad_rate data
 
     # Step 1: Extract unique school numbers from test_info
@@ -53,7 +66,7 @@ def process_file(model_name,inc_slider,progress=Progress(track_tqdm=True)):
     indices = test_info[test_info[0].isin(random_schools)].index.tolist()
 
     # Load the test file and select rows based on indices
-    test = pd.read_csv('train.txt', sep=',', header=None, engine='python')
+    test = pd.read_csv(test_location, sep=',', header=None, engine='python')
     selected_rows_df2 = test.loc[indices]
 
     # Save the selected rows to a file
@@ -61,14 +74,7 @@ def process_file(model_name,inc_slider,progress=Progress(track_tqdm=True)):
 
    
     # For demonstration purposes, we'll just return the content with the selected model name
-    if(model_name=="High Graduated Schools"):
-        finetune_task="highGRschool10"
-    elif(model_name== "Low Graduated Schools" ):
-        finetune_task="highGRschool10"
-    elif(model_name=="Full Set"):
-        finetune_task="highGRschool10"
-    else:
-        finetune_task=None
+
     # print(checkpoint)
     progress(0.1, desc="Files created and saved")
     # if (inc_val<5):
@@ -81,7 +87,7 @@ def process_file(model_name,inc_slider,progress=Progress(track_tqdm=True)):
     subprocess.run([
         "python", "new_test_saved_finetuned_model.py",
         "-workspace_name", "ratio_proportion_change3_2223/sch_largest_100-coded",
-        "-finetune_task", "highGRschool10",
+        "-finetune_task", finetune_task,
         "-test_dataset_path","../../../../selected_rows.txt",
         # "-test_label_path","../../../../train_label.txt",
         "-finetuned_bert_classifier_checkpoint", 

result.txt

@@ -1,7 +1,7 @@
-avg_loss: 0.5730699896812439
-total_acc: 69.52861952861953
-precisions: 0.7336375047795977
-recalls: 0.6952861952861953
-f1_scores: 0.6858177547541179
-time_taken_from_start: 16.031665802001953
-auc_score: 0.7738852057033876
+avg_loss: 0.5569005310535431
+total_acc: 74.30213464696223
+precisions: 0.7660032941165892
+recalls: 0.7430213464696224
+f1_scores: 0.7359098644855878
+time_taken_from_start: 41.834863901138306
+auc_score: 0.7675472675472674

roc_data.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c4af99c21a2122f6f4c4773439bbb77976243559acf78cd9b771f24d3ae9bdc
-size 5930
+oid sha256:c022a6b5eaa8a1a3c8cb6f10578afc01f92a1f9800ec4ebe1ab78b22b3ddd988
+size 10685