Update utils.py

utils.py

@@ -12,12 +12,12 @@ SUBJECTS = ["Biology", "Business", "Chemistry", "Computer Science", "Economics",
             "Health", "History", "Law", "Math", "Philosophy", "Physics", "Psychology", "Other"]
 
 MODEL_INFO = [
-    "Models", "Data Source", "Model Size(B)",
+    "Models", "Data Source",
     "Overall",
     "Biology", "Business", "Chemistry", "Computer Science", "Economics", "Engineering",
     "Health", "History", "Law", "Math", "Philosophy", "Physics", "Psychology", "Other"]
 
-DATA_TITLE_TYPE = ['markdown', 'markdown', 'markdown', 'number', 'number', 'number', 'number', 'number', 'number',
+DATA_TITLE_TYPE = ['markdown', 'markdown', 'number', 'number', 'number', 'number', 'number', 'number',
                    'number', 'number', 'number', 'number', 'number', 'number', 'number',
                    'number', 'number']
 
@@ -102,9 +102,9 @@ def get_df():
     repo = Repository(local_dir=SUBMISSION_NAME, clone_from=SUBMISSION_URL, use_auth_token=HF_TOKEN)
     repo.git_pull()
     df = pd.read_csv(CSV_DIR)
+    df['Model Size(B)'] = df['Model Size(B)'].apply(process_model_size)
     df = df.sort_values(by=['Overall'], ascending=False)
-    # print("df[COLUMN_NAMES]", df.values.tolist())
-    return df[COLUMN_NAMES]
+    return df
 
 
 def add_new_eval(
@@ -150,7 +150,7 @@ def search_and_filter_models(df, query, min_size, max_size):
     
     df = df[(df['Model Size(B)'] >= min_size) & (df['Model Size(B)'] <= max_size)]
     
-    return df
+    return df[COLUMN_NAMES]
 
 
 def search_models(df, query):
@@ -163,5 +163,14 @@ def get_size_range(df):
     sizes = df['Model Size(B)'].dropna()
     if len(sizes) > 0:
         return float(sizes.min()), float(sizes.max())
-    return 0, 500 
+    return 0, 600 
+
+
+def process_model_size(size):
+    if size == 'unk':
+        return 1000.0
+    try:
+        return float(size)
+    except ValueError:
+        return 1000.0