Spaces:

AzureModels4AI
/

PeopleModelsDatasets2X

Sleeping

Rename app.py to Pros1.app.py

ffa9aed verified about 2 years ago

7.88 kB

import streamlit as st
from huggingface_hub import HfApi
import asyncio
import os
import plotly.express as px

# Initialize the Hugging Face API
api = HfApi()

# Directory to save the generated HTML files
HTML_DIR = "generated_html_pages"
if not os.path.exists(HTML_DIR):
    os.makedirs(HTML_DIR)

# Default list of Hugging Face usernames - where all the magic begins! 🪄
default_users = {
    "users": [
        "awacke1", "rogerxavier", "jonatasgrosman", "kenshinn", "Csplk", "DavidVivancos",
        "cdminix", "Jaward", "TuringsSolutions", "Severian", "Wauplin",
        "phosseini", "Malikeh1375", "gokaygokay", "MoritzLaurer", "mrm8488",
        "TheBloke", "lhoestq", "xw-eric", "Paul", "Muennighoff",
        "ccdv", "haonan-li", "chansung", "lukaemon", "hails",
        "pharmapsychotic", "KingNish", "merve", "ameerazam08", "ashleykleynhans"
    ]
}

# Asynchronous function to fetch user content - because why wait when you can multitask? 🚀
async def fetch_user_content(username):
    try:
        # Fetch models and datasets - the stars of our show! 🌟
        models = list(await asyncio.to_thread(api.list_models, author=username))  # Convert generator to list
        datasets = list(await asyncio.to_thread(api.list_datasets, author=username))  # Convert generator to list
        
        return {
            "username": username,
            "models": models,
            "datasets": datasets
        }
    except Exception as e:
        # Oops! Something went wrong - blame it on the gremlins! 😈
        return {"username": username, "error": str(e)}

# Fetch all users concurrently - more hands (or threads) make light work! 💪
async def fetch_all_users(usernames):
    tasks = [fetch_user_content(username) for username in usernames]
    return await asyncio.gather(*tasks)

# Generate HTML content for a user and save it to a file - because who doesn't love a good download link? 💾
def generate_html_page(username, models, datasets):
    html_content = f"""
    <html>
    <head>
        <title>{username}'s Hugging Face Content</title>
    </head>
    <body>
        <h1>{username}'s Hugging Face Profile</h1>
        <p><a href="https://huggingface.co/{username}">🔗 Profile Link</a></p>
        <h2>🧠 Models</h2>
        <ul>
    """
    for model in models:
        model_name = model.modelId.split("/")[-1]
        html_content += f'<li><a href="https://huggingface.co/{model.modelId}">{model_name}</a></li>'
    
    html_content += """
        </ul>
        <h2>📚 Datasets</h2>
        <ul>
    """
    for dataset in datasets:
        dataset_name = dataset.id.split("/")[-1]
        html_content += f'<li><a href="https://huggingface.co/datasets/{dataset.id}">{dataset_name}</a></li>'
    
    html_content += """
        </ul>
    </body>
    </html>
    """

    # Save the HTML content to a file
    html_file_path = os.path.join(HTML_DIR, f"{username}.html")
    with open(html_file_path, "w") as html_file:
        html_file.write(html_content)

    return html_file_path

# Cache the HTML file path using Streamlit's caching decorator
@st.cache_data(show_spinner=False)
def get_cached_html_file(username):
    return generate_html_page(username, *get_user_content(username))

# Fetch user content from the API (without caching)
def get_user_content(username):
    user_data = asyncio.run(fetch_user_content(username))
    if "error" in user_data:
        return None, user_data["error"]
    return user_data["models"], user_data["datasets"]

# Streamlit app setup - the nerve center of our operation! 🎛️
st.title("Hugging Face User Content Display - Let's Automate Some Fun! 🎉")

# Convert the default users list to a string - because nobody likes typing out long lists! 📝
default_users_str = "\n".join(default_users["users"])

# Text area with default list of usernames - feel free to add your friends! 👥
usernames = st.text_area("Enter Hugging Face usernames (one per line):", value=default_users_str, height=300)

# Show User Content button - the big red button! (But actually it's blue) 🖱️
if st.button("Show User Content"):
    if usernames:
        username_list = [username.strip() for username in usernames.split('\n') if username.strip()]

        # Collect statistics for Plotly graphs
        stats = {"username": [], "models_count": [], "datasets_count": []}

        st.markdown("### User Content Overview")
        for username in username_list:
            with st.container():
                # Profile link - because everyone deserves their 15 seconds of fame! 🎤
                st.markdown(f"**{username}** [🔗 Profile](https://huggingface.co/{username})")

                # Generate HTML page and provide download link - because who wouldn't want a custom webpage? 🌐
                models, datasets = get_user_content(username)
                if models is None:
                    st.warning(f"{username}: {datasets} - Looks like the AI needs a coffee break ☕")
                else:
                    html_file_path = get_cached_html_file(username)
                    st.markdown(f"[📄 Download {username}'s HTML Page]({html_file_path})")

                    # Add to statistics for Plotly graphs
                    stats["username"].append(username)
                    stats["models_count"].append(len(models))
                    stats["datasets_count"].append(len(datasets))

                    # Models section with expander - 🧠 because AI models are brainy! 🧠
                    with st.expander(f"🧠 Models ({len(models)})", expanded=False):
                        if models:
                            for model in models:
                                model_name = model.modelId.split("/")[-1]
                                st.markdown(f"- [{model_name}](https://huggingface.co/{model.modelId})")
                        else:
                            st.markdown("No models found. Did you check under the rug? 🕵️‍♂️")

                    # Datasets section with expander - 📚 because data is the foundation of AI! 📚
                    with st.expander(f"📚 Datasets ({len(datasets)})", expanded=False):
                        if datasets:
                            for dataset in datasets:
                                dataset_name = dataset.id.split("/")[-1]
                                st.markdown(f"- [{dataset_name}](https://huggingface.co/datasets/{dataset.id})")
                        else:
                            st.markdown("No datasets found. Maybe they’re still baking in the oven? 🍪")

                st.markdown("---")

        # Plotly graphs to visualize the number of models and datasets each user has
        if stats["username"]:
            st.markdown("### User Content Statistics")

            # Plotting the number of models per user
            fig_models = px.bar(x=stats["username"], y=stats["models_count"], labels={'x':'Username', 'y':'Number of Models'}, title="Number of Models per User")
            st.plotly_chart(fig_models)

            # Plotting the number of datasets per user
            fig_datasets = px.bar(x=stats["username"], y=stats["datasets_count"], labels={'x':'Username', 'y':'Number of Datasets'}, title="Number of Datasets per User")
            st.plotly_chart(fig_datasets)

    else:
        st.warning("Please enter at least one username. Don't be shy! 😅")

# Sidebar instructions - just in case you get lost! 🗺️
st.sidebar.markdown("""
## How to use:
1. The text area is pre-filled with a list of Hugging Face usernames. You can edit this list or add more usernames.
2. Click 'Show User Content'.
3. View the user's models and datasets along with a link to their Hugging Face profile.
4. Download an HTML page for each user to use the absolute links offline!
5. Check out the statistics visualizations at the end!
""")

	import streamlit as st
	from huggingface_hub import HfApi
	import asyncio
	import os
	import plotly.express as px

	# Initialize the Hugging Face API
	api = HfApi()

	# Directory to save the generated HTML files
	HTML_DIR = "generated_html_pages"
	if not os.path.exists(HTML_DIR):
	os.makedirs(HTML_DIR)

	# Default list of Hugging Face usernames - where all the magic begins! 🪄
	default_users = {
	"users": [
	"awacke1", "rogerxavier", "jonatasgrosman", "kenshinn", "Csplk", "DavidVivancos",
	"cdminix", "Jaward", "TuringsSolutions", "Severian", "Wauplin",
	"phosseini", "Malikeh1375", "gokaygokay", "MoritzLaurer", "mrm8488",
	"TheBloke", "lhoestq", "xw-eric", "Paul", "Muennighoff",
	"ccdv", "haonan-li", "chansung", "lukaemon", "hails",
	"pharmapsychotic", "KingNish", "merve", "ameerazam08", "ashleykleynhans"
	]
	}

	# Asynchronous function to fetch user content - because why wait when you can multitask? 🚀
	async def fetch_user_content(username):
	try:
	# Fetch models and datasets - the stars of our show! 🌟
	models = list(await asyncio.to_thread(api.list_models, author=username)) # Convert generator to list
	datasets = list(await asyncio.to_thread(api.list_datasets, author=username)) # Convert generator to list

	return {
	"username": username,
	"models": models,
	"datasets": datasets
	}
	except Exception as e:
	# Oops! Something went wrong - blame it on the gremlins! 😈
	return {"username": username, "error": str(e)}

	# Fetch all users concurrently - more hands (or threads) make light work! 💪
	async def fetch_all_users(usernames):
	tasks = [fetch_user_content(username) for username in usernames]
	return await asyncio.gather(*tasks)

	# Generate HTML content for a user and save it to a file - because who doesn't love a good download link? 💾
	def generate_html_page(username, models, datasets):
	html_content = f"""
	<html>
	<head>
	<title>{username}'s Hugging Face Content</title>
	</head>
	<body>
	<h1>{username}'s Hugging Face Profile</h1>
	<p><a href="https://huggingface.co/{username}">🔗 Profile Link</a></p>
	<h2>🧠 Models</h2>
	<ul>
	"""
	for model in models:
	model_name = model.modelId.split("/")[-1]
	html_content += f'<li><a href="https://huggingface.co/{model.modelId}">{model_name}</a></li>'

	html_content += """
	</ul>
	<h2>📚 Datasets</h2>
	<ul>
	"""
	for dataset in datasets:
	dataset_name = dataset.id.split("/")[-1]
	html_content += f'<li><a href="https://huggingface.co/datasets/{dataset.id}">{dataset_name}</a></li>'

	html_content += """
	</ul>
	</body>
	</html>
	"""

	# Save the HTML content to a file
	html_file_path = os.path.join(HTML_DIR, f"{username}.html")
	with open(html_file_path, "w") as html_file:
	html_file.write(html_content)

	return html_file_path

	# Cache the HTML file path using Streamlit's caching decorator
	@st.cache_data(show_spinner=False)
	def get_cached_html_file(username):
	return generate_html_page(username, *get_user_content(username))

	# Fetch user content from the API (without caching)
	def get_user_content(username):
	user_data = asyncio.run(fetch_user_content(username))
	if "error" in user_data:
	return None, user_data["error"]
	return user_data["models"], user_data["datasets"]

	# Streamlit app setup - the nerve center of our operation! 🎛️
	st.title("Hugging Face User Content Display - Let's Automate Some Fun! 🎉")

	# Convert the default users list to a string - because nobody likes typing out long lists! 📝
	default_users_str = "\n".join(default_users["users"])

	# Text area with default list of usernames - feel free to add your friends! 👥
	usernames = st.text_area("Enter Hugging Face usernames (one per line):", value=default_users_str, height=300)

	# Show User Content button - the big red button! (But actually it's blue) 🖱️
	if st.button("Show User Content"):
	if usernames:
	username_list = [username.strip() for username in usernames.split('\n') if username.strip()]

	# Collect statistics for Plotly graphs
	stats = {"username": [], "models_count": [], "datasets_count": []}

	st.markdown("### User Content Overview")
	for username in username_list:
	with st.container():
	# Profile link - because everyone deserves their 15 seconds of fame! 🎤
	st.markdown(f"{username} [🔗 Profile](https://huggingface.co/{username})")

	# Generate HTML page and provide download link - because who wouldn't want a custom webpage? 🌐
	models, datasets = get_user_content(username)
	if models is None:
	st.warning(f"{username}: {datasets} - Looks like the AI needs a coffee break ☕")
	else:
	html_file_path = get_cached_html_file(username)
	st.markdown(f"[📄 Download {username}'s HTML Page]({html_file_path})")

	# Add to statistics for Plotly graphs
	stats["username"].append(username)
	stats["models_count"].append(len(models))
	stats["datasets_count"].append(len(datasets))

	# Models section with expander - 🧠 because AI models are brainy! 🧠
	with st.expander(f"🧠 Models ({len(models)})", expanded=False):
	if models:
	for model in models:
	model_name = model.modelId.split("/")[-1]
	st.markdown(f"- [{model_name}](https://huggingface.co/{model.modelId})")
	else:
	st.markdown("No models found. Did you check under the rug? 🕵️‍♂️")

	# Datasets section with expander - 📚 because data is the foundation of AI! 📚
	with st.expander(f"📚 Datasets ({len(datasets)})", expanded=False):
	if datasets:
	for dataset in datasets:
	dataset_name = dataset.id.split("/")[-1]
	st.markdown(f"- [{dataset_name}](https://huggingface.co/datasets/{dataset.id})")
	else:
	st.markdown("No datasets found. Maybe they’re still baking in the oven? 🍪")

	st.markdown("---")

	# Plotly graphs to visualize the number of models and datasets each user has
	if stats["username"]:
	st.markdown("### User Content Statistics")

	# Plotting the number of models per user
	fig_models = px.bar(x=stats["username"], y=stats["models_count"], labels={'x':'Username', 'y':'Number of Models'}, title="Number of Models per User")
	st.plotly_chart(fig_models)

	# Plotting the number of datasets per user
	fig_datasets = px.bar(x=stats["username"], y=stats["datasets_count"], labels={'x':'Username', 'y':'Number of Datasets'}, title="Number of Datasets per User")
	st.plotly_chart(fig_datasets)

	else:
	st.warning("Please enter at least one username. Don't be shy! 😅")

	# Sidebar instructions - just in case you get lost! 🗺️
	st.sidebar.markdown("""
	## How to use:
	1. The text area is pre-filled with a list of Hugging Face usernames. You can edit this list or add more usernames.
	2. Click 'Show User Content'.
	3. View the user's models and datasets along with a link to their Hugging Face profile.
	4. Download an HTML page for each user to use the absolute links offline!
	5. Check out the statistics visualizations at the end!
	""")