minimal working example

app.py

@@ -2,7 +2,7 @@ import gradio as gr
 import pandas as pd
 import plotly.express as px
 
-merged_df = pd.read_csv("merged_cloud_data.csv")
+merged_df = pd.read_csv("data/merged_cloud_data.csv")
 
 tdp_fig = px.scatter(
     merged_df,
@@ -30,9 +30,6 @@ cost_fig = px.scatter(
 )
 
 
-color_discrete_map = {"Direct": "#2ca02c", "Indirect": "#1f77b4", "None": "#d62728"}
-
-
 def generate_figure(org_name):
     org_data = data[data["Organization"] == org_name]
     model_counts = (
@@ -55,64 +52,31 @@ def generate_figure(org_name):
 
 
 with gr.Blocks() as demo:
-    gr.Markdown("# Environmental Transparency Explorer Tool 🕵️‍♀️🌎")
+    gr.Markdown("# Cloud Compute ☁️, Energy ⚡ and Cost 💲 - Explorer Tool")
     gr.Markdown(
-        "## Explore the data from 'Misinformation by Omission: The Need for More Environmental Transparency in AI'"
+        "## Explore the data from 'When we pay for cloud compute, what are we really paying for?'"
     )
     with gr.Accordion("Methodology", open=False):
-        gr.Markdown(
-            'We analyzed Epoch AI\'s "Notable AI Models" dataset, which tracks information on “models that were state of the art, highly cited, \
-        or otherwise historically notable” released over time. We selected the time period starting in 2010 as this is the beginning of the modern “deep learning era” \
-        (as defined by Epoch AI), which is representative of the types of AI models currently trained and deployed, including all 754 models from 2010 \
-        to the first quarter of 2025 in our analysis. We examined the level of environmental impact transparency for each model based on key information \
-        from the Epoch AI dataset (e.g., model accessibility, training compute estimation method) as well as from individual model release content \
-        (e.g., paper, model card, announcement).'
-        )
+        gr.Markdown("TODO")
     with gr.Row():
         with gr.Column():
-            gr.Markdown("### All Data")
-            counts = (
-                data.groupby("Year")[["Model", "Environmental Transparency"]]
-                .value_counts()
-                .reset_index()
-            )
-            counts.columns = ["Year", "Model", "Environmental Transparency", "Count"]
-            fig2 = px.bar(
-                counts,
-                x="Year",
-                y="Count",
-                color="Environmental Transparency",
-                color_discrete_map=color_discrete_map,
-                hover_data=["Model"],
-            )
-            fig2.update_layout(xaxis_type="category")
-            fig2.update_xaxes(categoryorder="category ascending")
-
-            plt2 = gr.Plot(fig2)
+            gr.Markdown("### TDP Data")
+            plt1 = gr.Plot(tdp_fig)
     with gr.Row():
         with gr.Column(scale=1):
             org_choice = gr.Dropdown(
                 organizations,
                 value="",
                 label="Organizations",
-                info="Pick an organization to explore their environmental disclosures",
+                info="Pick a characteristic to regenerate plot",
                 interactive=True,
             )
-            gr.Markdown("The 3 transparency categories are:")
-            gr.Markdown(
-                "**Direct Disclosure**: Developers explicitly reported energy or GHG emissions, e.g., using hardware TDP, country average carbon intensity or measurements."
-            )
-            gr.Markdown(
-                "**Indirect Disclosure**: Developers provided training compute data or released their model weights, allowing external estimates of training or inference impacts."
-            )
-            gr.Markdown(
-                "**No Disclosure**: Environmental impact data was not publicly released and estimation approaches (as noted in Indirect Disclosure) were not possible."
-            )
+
         with gr.Column(scale=4):
-            gr.Markdown("### Data by Organization")
+            gr.Markdown("### Cost Data")
             fig = generate_figure(org_choice)
-            plt = gr.Plot(fig)
+            plt = gr.Plot(cost_fig)
 
-    org_choice.select(generate_figure, inputs=[org_choice], outputs=[plt])
+    # org_choice.select(generate_figure, inputs=[org_choice], outputs=[plt])
 
 demo.launch()