up

app.py

@@ -1,38 +1,68 @@
-import streamlit as st
+#import streamlit as st
 
 from huggingface_hub import HfApi
 import pandas
+import os
+import streamlit as st
+import datetime
 from transformers.models.auto.configuration_auto import CONFIG_MAPPING_NAMES
 
-hf_api = HfApi()
-all_stats = {}
-total_downloads = 0
+from huggingface_hub import Repository
+
+today = datetime.date.today()
+year, week, _ = today.isocalendar()
+
+DATASET_REPO_URL = "https://huggingface.co/datasets/patrickvonplaten/model-archs-downloads-space-data"
+DATA_FILENAME = f"data_{week}_{year}.csv"
+DATA_FILE = os.path.join("data", DATA_FILENAME)
+
+
+def retrieve_model_stats():
+    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())[:2]:
+        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")
 
-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)
+    return dataframe.to_csv()
 
-    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
+repo = Repository(local_dir="data", clone_from=DATASET_REPO_URL)
 
+if not os.path.isfile(DATA_FILE):
+    print("Create datafile...")
+    result = retrieve_model_stats()
 
-for model_name in list(CONFIG_MAPPING_NAMES.keys())[:2]:
-    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:,}"
+    if not os.path.isfile(DATA_FILE):
+        with open(DATA_FILE, "w") as f:
+            f.write(result)
 
+        commit_url = repo.push_to_hub()
+        print(commit_url)
 
-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(DATA_FILE, "r") as f:
+    dataframe = pandas.read_csv(DATA_FILE)
 
-with open("result.txt", "w") as f:
-    f.write(result)
+print(DATA_FILE)
+print(dataframe)
 
 st.table(dataframe)

data

@@ -0,0 +1 @@
+Subproject commit bd0b98ff44210308e4a142bd71bd805fbd330f34

requirements.txt

@@ -1 +1,2 @@
 transformers
+huggingface_hub