up

app.py

@@ -5,14 +5,32 @@ import streamlit as st
 import altair as alt
 import numpy as np
 import datetime
+from huggingface_hub import Repository
+
 from transformers.models.auto.configuration_auto import CONFIG_MAPPING_NAMES
+from transformers.models.auto.modeling_auto import (
+    MODEL_FOR_CTC_MAPPING_NAMES,
+    MODEL_FOR_AUDIO_CLASSIFICATION_MAPPING_NAMES,
+    MODEL_FOR_SPEECH_SEQ_2_SEQ_MAPPING_NAMES,
+    MODEL_FOR_VISION_2_SEQ_MAPPING_NAMES,
+    MODEL_FOR_INSTANCE_SEGMENTATION_MAPPING_NAMES,
+    MODEL_FOR_VIDEO_CLASSIFICATION_MAPPING_NAMES,
+    MODEL_FOR_SEMANTIC_SEGMENTATION_MAPPING_NAMES,
+    MODEL_FOR_IMAGE_CLASSIFICATION_MAPPING_NAMES,
+    MODEL_FOR_CAUSAL_IMAGE_MODELING_MAPPING_NAMES,
+    MODEL_FOR_MASKED_IMAGE_MODELING_MAPPING_NAMES,
+)
 
-from huggingface_hub import Repository
+audio_models = MODEL_FOR_CTC_MAPPING_NAMES.keys() + MODEL_FOR_AUDIO_CLASSIFICATION_MAPPING_NAMES.keys() + MODEL_FOR_SPEECH_SEQ_2_SEQ_MAPPING_NAMES.keys()
+
+vision_models = MODEL_FOR_VISION_2_SEQ_MAPPING_NAMES.keys() + MODEL_FOR_INSTANCE_SEGMENTATION_MAPPING_NAMES.keys() + MODEL_FOR_VIDEO_CLASSIFICATION_MAPPING_NAMES.keys() + MODEL_FOR_SEMANTIC_SEGMENTATION_MAPPING_NAMES.keys() + MODEL_FOR_IMAGE_CLASSIFICATION_MAPPING_NAMES.keys() + MODEL_FOR_CAUSAL_IMAGE_MODELING_MAPPING_NAMES.keys() + MODEL_FOR_MASKED_IMAGE_MODELING_MAPPING_NAMES.keys()
 
 today = datetime.date.today()
 year, week, _ = today.isocalendar()
 
-DATASET_REPO_URL = "https://huggingface.co/datasets/patrickvonplaten/model-archs-downloads-space-data"
+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)
 
@@ -23,24 +41,45 @@ def retrieve_model_stats():
     total_downloads = 0
 
     for model_name in list(CONFIG_MAPPING_NAMES.keys()):
-        model_stats = {"num_downloads": 0, "%_of_all_downloads": 0, "num_models": 0, "download_per_model": 0}
+        if model_name in audio_models:
+            modality = "audio"
+        elif model_name in vision_models:
+            modality = "vision"
+        else:
+            modality = "text"
+
+        model_stats = {
+            "num_downloads": 0,
+            "%_of_all_downloads": 0,
+            "num_models": 0,
+            "download_per_model": 0,
+            "modality": modality,
+        }
         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")])
+        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)
+            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
+        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"])))
+    sorted_results = dict(
+        reversed(sorted(all_stats.items(), key=lambda d: d[1]["%_of_all_downloads"]))
+    )
     dataframe = pd.DataFrame.from_dict(sorted_results, orient="index")
 
     # give header to model names
@@ -64,29 +103,43 @@ if not os.path.isfile(DATA_FILE):
 with open(DATA_FILE, "r") as f:
     dataframe = pd.read_csv(DATA_FILE)
 
-int_downloads = np.array([int(x.replace(",", "")) for x in dataframe["num_downloads"].values])
+int_downloads = np.array(
+    [int(x.replace(",", "")) for x in dataframe["num_downloads"].values]
+)
 
 st.title(f"Transformers stats for year {year} and week {week}")
 # print top 20 downloads
-source = pd.DataFrame({
-    'Number of total downloads': int_downloads[:20],
-    'Model architecture name': dataframe["model_names"].values[:20],
-})
-bar_chart = alt.Chart(source).mark_bar().encode(
-    y="Number of total downloads",
-    x=alt.X("Model architecture name", sort=None),
+source = pd.DataFrame(
+    {
+        "Number of total downloads": int_downloads[:20],
+        "Model architecture name": dataframe["model_names"].values[:20],
+    }
+)
+bar_chart = (
+    alt.Chart(source)
+    .mark_bar()
+    .encode(
+        y="Number of total downloads",
+        x=alt.X("Model architecture name", sort=None),
+    )
 )
 st.title("Top 20 downloads last 30 days")
 st.altair_chart(bar_chart, use_container_width=True)
 
 # print bottom 20 downloads
-source = pd.DataFrame({
-    'Number of total downloads': int_downloads[-20:],
-    'Model architecture name': dataframe["model_names"].values[-20:],
-})
-bar_chart = alt.Chart(source).mark_bar().encode(
-    y="Number of total downloads",
-    x=alt.X("Model architecture name", sort=None),
+source = pd.DataFrame(
+    {
+        "Number of total downloads": int_downloads[-20:],
+        "Model architecture name": dataframe["model_names"].values[-20:],
+    }
+)
+bar_chart = (
+    alt.Chart(source)
+    .mark_bar()
+    .encode(
+        y="Number of total downloads",
+        x=alt.X("Model architecture name", sort=None),
+    )
 )
 st.title("Bottom 20 downloads last 30 days")
 st.altair_chart(bar_chart, use_container_width=True)