up

app.py

@@ -1,9 +1,9 @@
-#import streamlit as st
-
 from huggingface_hub import HfApi
-import pandas
+import pandas as pd
 import os
 import streamlit as st
+import altair as alt
+import numpy as np
 import datetime
 from transformers.models.auto.configuration_auto import CONFIG_MAPPING_NAMES
 
@@ -22,7 +22,7 @@ def retrieve_model_stats():
     all_stats = {}
     total_downloads = 0
 
-    for model_name in list(CONFIG_MAPPING_NAMES.keys())[:2]:
+    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}
         models = hf_api.list_models(filter=model_name)
 
@@ -35,15 +35,17 @@ def retrieve_model_stats():
         # save in overall dict
         all_stats[model_name] = model_stats
 
-    for model_name in list(CONFIG_MAPPING_NAMES.keys())[:2]:
+    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")
+    dataframe = pd.DataFrame.from_dict(sorted_results, orient="index")
 
-    return dataframe.to_csv()
+    # give header to model names
+    result = "model_names" + dataframe.to_csv()
+    return result
 
 
 repo = Repository(local_dir="data", clone_from=DATASET_REPO_URL)
@@ -60,10 +62,34 @@ if not os.path.isfile(DATA_FILE):
         print(commit_url)
 
 with open(DATA_FILE, "r") as f:
-    dataframe = pandas.read_csv(DATA_FILE)
-
-print(DATA_FILE)
-print(dataframe)
-
-st.title(f'Transformers model downloads for year {year} and week {week}')
+    dataframe = pd.read_csv(DATA_FILE)
+
+int_downloads = np.array([int(x.replace(",", "")) for x in dataframe["num_downloads"].values])
+
+# 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),
+)
+st.title(f'Top 20 downloads for year {year} and week {week}')
+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),
+)
+st.title(f'Bottom 20 downloads for year {year} and week {week}')
+st.altair_chart(bar_chart, use_container_width=True)
+
+# print all stats
+st.title(f'All downloads for year {year} and week {week}')
 st.table(dataframe)

data

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