up

app.py

@@ -1,10 +1,38 @@
 import streamlit as st
-import pandas as pd
-import numpy as np
 
-df = pd.DataFrame(
-    np.random.randn(10, 5),
-    columns=('col %d' % i for i in range(5))
-)
+from huggingface_hub import HfApi
+import pandas
+from transformers.models.auto.configuration_auto import CONFIG_MAPPING_NAMES
 
-st.table(df)
+hf_api = HfApi()
+all_stats = {}
+total_downloads = 0
+
+for model_name in list(CONFIG_MAPPING_NAMES.keys())[:2]:
+    model_stats = {"num_downloads": 0, "%_of_all_downloads": 0, "num_models": 0, "download_per_model": 0}
+    models = hf_api.list_models(filter=model_name)
+
+    model_stats["num_models"] = len(models)
+    model_stats["num_downloads"] = sum([m.downloads for m in models if hasattr(m, "downloads")])
+    if len(models) > 0:
+        model_stats["download_per_model"] = round(model_stats["num_downloads"] / len(models), 2)
+    total_downloads += model_stats["num_downloads"]
+
+    # save in overall dict
+    all_stats[model_name] = model_stats
+
+
+for model_name in list(CONFIG_MAPPING_NAMES.keys()):
+    all_stats[model_name]["%_of_all_downloads"] = round(all_stats[model_name]["num_downloads"] / total_downloads, 5) * 100  # noqa: E501
+    downloads = all_stats[model_name]["num_downloads"]
+    all_stats[model_name]["num_downloads"] = f"{downloads:,}"
+
+
+sorted_results = dict(reversed(sorted(all_stats.items(), key=lambda d: d[1]["%_of_all_downloads"])))
+dataframe = pandas.DataFrame.from_dict(sorted_results, orient="index")
+result = dataframe.to_string()
+
+with open("result.txt", "w") as f:
+    f.write(result)
+
+st.table(dataframe)