update

app.py

@@ -8,6 +8,9 @@ from huggingface_hub.utils._errors import EntryNotFoundError, RepositoryNotFound
 from dotenv import load_dotenv
 from matplotlib.colors import LinearSegmentedColormap
 import plotly.express as px
+import plotly.graph_objects as go
+from sklearn.linear_model import LinearRegression
+import numpy as np
 
 load_dotenv()
 webhook_url = os.environ.get("WEBHOOK_URL")
@@ -271,6 +274,29 @@ for folder in get_folders_matching_format('data'):
                 pd.read_excel(final_file_name + '.xlsx', sheet_name=sheet_name))
 
 
+# def create_scaling_plot(all_data, period):
+#     selected_columns = ['Name', 'Parameters Count (B)', 'Average (The lower the better)']
+#     target_data = all_data[period]
+#     new_df = pd.DataFrame()
+#
+#     for size in target_data.keys():
+#         new_df = pd.concat([new_df, target_data[size]['cr'].loc[:, selected_columns]], axis=0)
+#
+#     new_df.rename(columns={
+#         'Parameters Count (B)': 'Params(B)',
+#         'Average (The lower the better)': 'Compression Rate (%)'
+#     }, inplace=True)
+#
+#     fig = px.scatter(new_df,
+#                      x='Params(B)',
+#                      y='Compression Rate (%)',
+#                      title='Compression Rate Scaling Law',
+#                      hover_name='Name'
+#                      )
+#     fig.update_traces(marker=dict(size=12))
+#     return fig
+
+
 def create_scaling_plot(all_data, period):
     selected_columns = ['Name', 'Parameters Count (B)', 'Average (The lower the better)']
     target_data = all_data[period]
@@ -284,12 +310,36 @@ def create_scaling_plot(all_data, period):
         'Average (The lower the better)': 'Compression Rate (%)'
     }, inplace=True)
 
+    # Create scatter plot
     fig = px.scatter(new_df,
                      x='Params(B)',
                      y='Compression Rate (%)',
                      title='Compression Rate Scaling Law',
                      hover_name='Name'
                      )
+
+    # Add logarithmic trendline
+    X = new_df[['Params(B)']].values
+    y = new_df['Compression Rate (%)'].values
+
+    # Perform log transformation on X
+    X_log = np.log(X)
+
+    model = LinearRegression()
+    model.fit(X_log, y)
+
+    # Create trendline data for plot
+    X_plot = np.linspace(X_log.min() - 1, X_log.max() + 0.1, 100)
+    y_plot = model.predict(X_plot.reshape(-1, 1))
+
+    fig.add_trace(go.Scatter(
+        x=np.exp(X_plot),
+        y=y_plot,
+        mode='lines',
+        name='Trend',
+        line=dict(color='#39C5BB')
+    ))
+
     fig.update_traces(marker=dict(size=12))
     return fig