merging dfs

app.py

@@ -3,13 +3,15 @@ import pandas as pd
 from huggingface_hub import list_models
 import plotly.express as px
 
-def get_plots(task_data):
+def get_plots(task):
     #TO DO : hover text with energy efficiency number, parameters
-    task_df= pd.read_csv(task_data)
-    task_df['Total GPU Energy (Wh)'] = task_df['total_gpu_energy']*1000
-    task_df = task_df.sort_values(by=['Total GPU Energy (Wh)'])
-    task_df['energy_star'] = pd.cut(task_df['Total GPU Energy (Wh)'], 3, labels=["⭐⭐⭐", "⭐⭐", "⭐"])
-    fig = px.scatter(task_df, x="model", y='Total GPU Energy (Wh)', height= 500, width= 800, color = 'energy_star', color_discrete_map={"⭐": 'red', "⭐⭐": "yellow", "⭐⭐⭐": "green"})
+    task_df= pd.read_csv('data/energy/'+task)
+    params_df = pd.read_csv('data/params/'+task)
+    all_df = pd.merge(task_df, params_df, on='Link'))
+    all_df['Total GPU Energy (Wh)'] = all_df['total_gpu_energy']*1000
+    all_df = task_df.sort_values(by=['Total GPU Energy (Wh)'])
+    all_df['energy_star'] = pd.cut(all_df['Total GPU Energy (Wh)'], 3, labels=["⭐⭐⭐", "⭐⭐", "⭐"])
+    fig = px.scatter(all_df, x="model", y='Total GPU Energy (Wh)', height= 500, width= 800, color = 'energy_star', color_discrete_map={"⭐": 'red', "⭐⭐": "yellow", "⭐⭐⭐": "green"})
     #fig.update_traces(mode="markers+lines", hovertemplate=None)
     fig.update_layout(hovermode="y")
     return fig
@@ -20,10 +22,6 @@ def get_model_names(task_data):
     model_names = task_df[['model']]
     return model_names
 
-def get_params(param_data):
-    param_df= pd.read_csv(param_data)
-    model_params = {}
-
 
 demo = gr.Blocks()
 
@@ -37,36 +35,36 @@ with demo:
         with gr.TabItem("Text Generation 💬"):
             with gr.Row():
                 with gr.Column():
-                    plot = gr.Plot(get_plots('data/energy/text_generation.csv'))
+                    plot = gr.Plot(get_plots('text_generation.csv'))
                 with gr.Column():
-                    table = gr.Dataframe(get_model_names('data/energy/text_generation.csv'))
+                    table = gr.Dataframe(get_model_names('text_generation.csv'))
 
         with gr.TabItem("Image Generation 📷"):
             with gr.Row():
                 with gr.Column():
-                    plot = gr.Plot(get_plots('data/energy/image_generation.csv'))
+                    plot = gr.Plot(get_plots('image_generation.csv'))
                 with gr.Column():
-                    table = gr.Dataframe(get_model_names('data/energy/image_generation.csv'))
+                    table = gr.Dataframe(get_model_names('image_generation.csv'))
 
         with gr.TabItem("Text Classification 🎭"):
             with gr.Row():
                 with gr.Column():
-                    plot = gr.Plot(get_plots('data/energy/text_classification.csv'))
+                    plot = gr.Plot(get_plots('text_classification.csv'))
                 with gr.Column():
-                    table = gr.Dataframe(get_model_names('data/energy/text_classification.csv'))
+                    table = gr.Dataframe(get_model_names('text_classification.csv'))
 
         with gr.TabItem("Image Classification 🖼️"):
             with gr.Row():
                 with gr.Column():
-                    plot = gr.Plot(get_plots('data/energy/image_classification.csv'))
+                    plot = gr.Plot(get_plots('image_classification.csv'))
                 with gr.Column():
-                    table = gr.Dataframe(get_model_names('data/energy/image_classification.csv'))
+                    table = gr.Dataframe(get_model_names('image_classification.csv'))
 
         with gr.TabItem("Extractive QA ❔"):
             with gr.Row():
                 with gr.Column():
-                    plot = gr.Plot(get_plots('data/energy/question_answering.csv'))
+                    plot = gr.Plot(get_plots('question_answering.csv'))
                 with gr.Column():
-                    table = gr.Dataframe(get_model_names('data/energy/question_answering.csv'))
+                    table = gr.Dataframe(get_model_names('question_answering.csv'))
 
 demo.launch()