from huggingface_hub import HfApi import pandas as pd import os 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_AUDIO_FRAME_CLASSIFICATION_MAPPING_NAMES, MODEL_FOR_AUDIO_XVECTOR_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_SEMANTIC_SEGMENTATION_MAPPING_NAMES, MODEL_FOR_IMAGE_CLASSIFICATION_MAPPING_NAMES, MODEL_FOR_CAUSAL_IMAGE_MODELING_MAPPING_NAMES, MODEL_FOR_MASKED_IMAGE_MODELING_MAPPING_NAMES, MODEL_FOR_TABLE_QUESTION_ANSWERING_MAPPING_NAMES, MODEL_FOR_VISUAL_QUESTION_ANSWERING_MAPPING_NAMES, MODEL_FOR_DOCUMENT_QUESTION_ANSWERING_MAPPING_NAMES, MODEL_FOR_BACKBONE_MAPPING_NAMES, MODEL_FOR_ZERO_SHOT_IMAGE_CLASSIFICATION_MAPPING_NAMES, ) audio_models = list(MODEL_FOR_CTC_MAPPING_NAMES.keys()) + list(MODEL_FOR_AUDIO_CLASSIFICATION_MAPPING_NAMES.keys()) + \ list(MODEL_FOR_SPEECH_SEQ_2_SEQ_MAPPING_NAMES.keys()) + list(MODEL_FOR_AUDIO_FRAME_CLASSIFICATION_MAPPING_NAMES.keys()) + \ list(MODEL_FOR_AUDIO_XVECTOR_MAPPING_NAMES.keys()) vision_models = list(MODEL_FOR_VISION_2_SEQ_MAPPING_NAMES.keys()) + list(MODEL_FOR_INSTANCE_SEGMENTATION_MAPPING_NAMES.keys()) + \ list(MODEL_FOR_SEMANTIC_SEGMENTATION_MAPPING_NAMES.keys()) + list(MODEL_FOR_IMAGE_CLASSIFICATION_MAPPING_NAMES.keys()) + \ list(MODEL_FOR_CAUSAL_IMAGE_MODELING_MAPPING_NAMES.keys()) + list(MODEL_FOR_MASKED_IMAGE_MODELING_MAPPING_NAMES.keys()) + \ list(MODEL_FOR_TABLE_QUESTION_ANSWERING_MAPPING_NAMES.keys()) + list(MODEL_FOR_VISUAL_QUESTION_ANSWERING_MAPPING_NAMES.keys()) + \ list(MODEL_FOR_DOCUMENT_QUESTION_ANSWERING_MAPPING_NAMES.keys()) + list(MODEL_FOR_BACKBONE_MAPPING_NAMES.keys()) + \ list(MODEL_FOR_ZERO_SHOT_IMAGE_CLASSIFICATION_MAPPING_NAMES.keys()) today = datetime.date.today() year, week, _ = today.isocalendar() DATASET_REPO_URL = ( "https://huggingface.co/datasets/huggingface/transformers-stats-space-data" ) DATA_FILENAME = f"data_{week}_{year}.csv" DATA_FILE = os.path.join("data", DATA_FILENAME) HF_TOKEN = os.environ.get("HF_TOKEN") print("is none?", HF_TOKEN is None) def retrieve_model_stats(): hf_api = HfApi() all_stats = {} total_downloads = 0 for model_name in list(CONFIG_MAPPING_NAMES.keys()): 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")] ) if len(models) > 0: model_stats["download_per_model"] = int( model_stats["num_downloads"] / len(models) ) else: model_stats["download_per_model"] = model_stats["num_downloads"] 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 = pd.DataFrame.from_dict(sorted_results, orient="index") # give header to model names result = "model_names" + dataframe.to_csv() return result repo = Repository(local_dir="data", clone_from=DATASET_REPO_URL, use_auth_token=HF_TOKEN) if not os.path.isfile(DATA_FILE): st.title("You are the first this week!!! Please wait until the new data is generated and written") result = retrieve_model_stats() 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) 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] ) st.title(f"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), ) ) 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), ) ) st.title("Bottom 20 downloads last 30 days") st.altair_chart(bar_chart, use_container_width=True) # print vision df_vision = dataframe[dataframe["modality"] == "vision"] vision_int_downloads = np.array( [int(x.replace(",", "")) for x in df_vision["num_downloads"].values] ) source = pd.DataFrame( { "Number of total downloads": vision_int_downloads, "Model architecture name": df_vision["model_names"].values, } ) bar_chart = ( alt.Chart(source) .mark_bar() .encode( y="Number of total downloads", x=alt.X("Model architecture name", sort=None), ) ) st.title("Vision downloads last 30 days") st.altair_chart(bar_chart, use_container_width=True) # print audio df_audio = dataframe[dataframe["modality"] == "audio"] audio_int_downloads = np.array( [int(x.replace(",", "")) for x in df_audio["num_downloads"].values] ) source = pd.DataFrame( { "Number of total downloads": audio_int_downloads, "Model architecture name": df_audio["model_names"].values, } ) bar_chart = ( alt.Chart(source) .mark_bar() .encode( y="Number of total downloads", x=alt.X("Model architecture name", sort=None), ) ) st.title("Audio downloads last 30 days") st.altair_chart(bar_chart, use_container_width=True) # print all stats st.title("All stats last 30 days") st.table(dataframe) st.title("Vision stats last 30 days") st.table(dataframe[dataframe["modality"] == "vision"].drop("modality", axis=1)) st.title("Audio stats last 30 days") st.table(dataframe[dataframe["modality"] == "audio"].drop("modality", axis=1))