Update app.py

app.py

@@ -37,15 +37,27 @@ def make_link(mname):
     display_name = parts[1] if len(parts) > 1 else mname
     return f'[{display_name}](https://huggingface.co/{mname})'
 
-def get_plots(task):
-    # Read CSV using the first column as index so that only the useful columns remain.
+def read_csv_file(task):
+    """
+    Reads a CSV from the data/energy folder using the first column as the index
+    and strips any extraneous whitespace from the column names.
+    """
     df = pd.read_csv('data/energy/' + task, index_col=0)
+    df.columns = df.columns.str.strip()  # remove any extra whitespace
+    return df
+
+def get_plots(task):
+    df = read_csv_file(task)
+    # Convert the numeric columns
     df['total_gpu_energy'] = pd.to_numeric(df['total_gpu_energy'], errors='coerce')
     df['energy_score'] = pd.to_numeric(df['energy_score'], errors='coerce').astype(int)
+    # Create a short model name for display on the y-axis.
     df['Display Model'] = df['model'].apply(lambda m: m.split('/')[-1])
     
+    # Define a discrete color mapping for energy scores.
     color_map = {1: "red", 2: "orange", 3: "yellow", 4: "lightgreen", 5: "green"}
     
+    # Build the scatter plot.
     fig = px.scatter(
         df,
         x="total_gpu_energy",
@@ -73,7 +85,7 @@ def get_plots(task):
 def get_all_plots():
     all_df = pd.DataFrame()
     for task in tasks:
-        df = pd.read_csv('data/energy/' + task, index_col=0)
+        df = read_csv_file(task)
         df['total_gpu_energy'] = pd.to_numeric(df['total_gpu_energy'], errors='coerce')
         df['energy_score'] = pd.to_numeric(df['energy_score'], errors='coerce').astype(int)
         df['Display Model'] = df['model'].apply(lambda m: m.split('/')[-1])
@@ -108,13 +120,13 @@ def get_all_plots():
 
 def get_model_names(task):
     """
-    For a given task, load the energy CSV and return a dataframe with the following columns:
+    For a given task, load the energy CSV and return a DataFrame with the following columns:
       - Model (a markdown link)
       - GPU Energy (Wh) formatted to 4 decimal places
       - Score (a star rating based on energy_score)
-    For text_generation.csv only, also add the "Class" column if present.
+    For text_generation.csv only, also include the "Class" column if present.
     """
-    df = pd.read_csv('data/energy/' + task, index_col=0)
+    df = read_csv_file(task)
     df['total_gpu_energy'] = pd.to_numeric(df['total_gpu_energy'], errors='coerce')
     df['energy_score'] = pd.to_numeric(df['energy_score'], errors='coerce').astype(int)
     df['GPU Energy (Wh)'] = df['total_gpu_energy'].apply(lambda x: f"{x:.4f}")
@@ -127,19 +139,19 @@ def get_model_names(task):
     else:
         df = df[['Model', 'GPU Energy (Wh)', 'Score']]
         
-    # Now sort by the numeric value in total_gpu_energy.
+    # Sort by the numeric GPU energy value.
     df = df.sort_values(by='total_gpu_energy')
     return df
 
 def get_all_model_names():
     """
-    Combine data from all tasks and return a leaderboard table with:
+    Combine data from all tasks and return a leaderboard DataFrame with:
       - Model, GPU Energy (Wh), Score.
     Duplicate models are dropped.
     """
     all_df = pd.DataFrame()
     for task in tasks:
-        df = pd.read_csv('data/energy/' + task, index_col=0)
+        df = read_csv_file(task)
         df['total_gpu_energy'] = pd.to_numeric(df['total_gpu_energy'], errors='coerce')
         df['energy_score'] = pd.to_numeric(df['energy_score'], errors='coerce').astype(int)
         df['GPU Energy (Wh)'] = df['total_gpu_energy'].apply(lambda x: f"{x:.4f}")