better dataset

app.py

@@ -1,31 +1,28 @@
-from apscheduler.schedulers.background import BackgroundScheduler
+# from apscheduler.schedulers.background import BackgroundScheduler
 from model_types import MODEL_TYPES, ModelType
-from huggingface_hub import HfApi
+
+# from huggingface_hub import HfApi
 import matplotlib.pyplot as plt
 import bar_chart_race as bcr
 import pandas as pd
 import gradio as gr
-import requests
-import os
 
+# import os
 
-def restart_space():
-    HfApi(token=os.environ.get("HF_TOKEN", None)).restart_space(
-        repo_id="IlyasMoutawwakil/llm-bar-race",
-        token=os.environ.get("HF_TOKEN", None),
-    )
 
+# def restart_space():
+#     HfApi(token=os.environ.get("HF_TOKEN", None)).restart_space(
+#         repo_id="IlyasMoutawwakil/llm-bar-race",
+#         token=os.environ.get("HF_TOKEN", None),
+#     )
 
-if os.path.exists("open-llm-race-dataset.csv"):
-    open_llm_race_dataset = pd.read_csv("open-llm-race-dataset.csv")
-else:
-    open_llm_race_dataset = pd.read_csv(
-        "https://huggingface.co/datasets/IlyasMoutawwakil/open-llm-race-dataset/resolve/main/open-llm-race-dataset.csv"
-    )
 
+open_llm_race_dataset = pd.read_parquet(
+    "https://huggingface.co/datasets/IlyasMoutawwakil/llm-race-dataset/resolve/main/llm-race-dataset.parquet",
+    engine="pyarrow",
+)
 
 # resample for ever model to a daily frequency
-open_llm_race_dataset["date"] = pd.to_datetime(open_llm_race_dataset["date"])
 open_llm_race_dataset = (
     open_llm_race_dataset.set_index("date", drop=True)
     .groupby("model", as_index=False)
@@ -52,25 +49,25 @@ open_llm_race_dataset["type"] = open_llm_race_dataset["model"].apply(
 def get_bar_chart(model_type: str, top_n: int = 10, title: str = ""):
     fig, ax = plt.subplots(figsize=(12, 6))
     ax.set_xlim(0, 100)
-    plt.subplots_adjust(left=0.25)
+    plt.subplots_adjust(left=0.30, right=0.98)
 
     subset = open_llm_race_dataset[open_llm_race_dataset["type"] == model_type]
     subset = subset.pivot(index="date", columns="model", values="score")
     subset.fillna(0, inplace=True)
     fig = bcr.bar_chart_race(
         subset,
+        fig=fig,
         title=title,
         n_bars=top_n,
         fixed_max=True,
+        bar_label_font=10,
+        tick_label_font=10,
         period_length=1000,
         steps_per_period=20,
         end_period_pause=100,
-        bar_texttemplate="{x:.2f}",
         filter_column_colors=True,
-        bar_label_font=10,
-        tick_label_font=10,
-        bar_kwargs={"alpha": 0.2, "ec": "black", "lw": 3},
-        fig=fig,
+        bar_texttemplate="{x:.2f}%",
+        bar_kwargs={"alpha": 0.5, "ec": "black", "lw": 2},
     )
     return gr.HTML(fig)
 
@@ -88,14 +85,7 @@ with demo:
             get_bar_chart(ModelType.IFT.name, title="Instructions Finetuned Models")
         with gr.TabItem(label="RLHF Models"):
             get_bar_chart(ModelType.RL.name, top_n=4, title="RLHF Models")
+        with gr.TabItem(label="Finetuned Models"):
+            get_bar_chart(ModelType.FT.name, title="Finetuned Models")
 
-
-# Restart space every hour
-scheduler = BackgroundScheduler()
-scheduler.add_job(
-    func=restart_space,
-    trigger="interval",
-    seconds=3600,
-)
-scheduler.start()
 demo.queue(concurrency_count=10).launch()

requirements.txt

@@ -1,5 +1,4 @@
 git+https://github.com/dexplo/bar_chart_race.git
 huggingface_hub
-APScheduler
 pandas
 tqdm