app.py

# --- START OF FINAL, POLISHED FILE app.py ---

import gradio as gr
import pandas as pd
import plotly.express as px
import time
import json
from datasets import load_dataset

# --- Constants ---
PARAM_CHOICES = ['< 1B', '1B', '5B', '12B', '32B', '64B', '128B', '256B', '> 500B']
# This hidden textbox will store the slider's state as a JSON string
PARAM_STATE_DEFAULT_JSON = json.dumps([0, len(PARAM_CHOICES) - 1])

TOP_K_CHOICES = list(range(5, 51, 5))
HF_DATASET_ID = "evijit/orgstats_daily_data"
TAG_FILTER_CHOICES = [ "Audio & Speech", "Time series", "Robotics", "Music", "Video", "Images", "Text", "Biomedical", "Sciences" ]
PIPELINE_TAGS = [ 'text-generation', 'text-to-image', 'text-classification', 'text2text-generation', 'audio-to-audio', 'feature-extraction', 'image-classification', 'translation', 'reinforcement-learning', 'fill-mask', 'text-to-speech', 'automatic-speech-recognition', 'image-text-to-text', 'token-classification', 'sentence-similarity', 'question-answering', 'image-feature-extraction', 'summarization', 'zero-shot-image-classification', 'object-detection', 'image-segmentation', 'image-to-image', 'image-to-text', 'audio-classification', 'visual-question-answering', 'text-to-video', 'zero-shot-classification', 'depth-estimation', 'text-ranking', 'image-to-video', 'multiple-choice', 'unconditional-image-generation', 'video-classification', 'text-to-audio', 'time-series-forecasting', 'any-to-any', 'video-text-to-text', 'table-question-answering' ]

# --- Custom HTML, CSS, and JavaScript for the Slider ---
custom_slider_js = """
function createCustomSlider() {{
    const paramChoices = {js_param_choices};
    const slider = document.getElementById('noui-slider-container');
    if (slider.noUiSlider) {{ return; }} // Don't re-create if it already exists

    noUiSlider.create(slider, {{
        start: [0, paramChoices.length - 1],
        connect: true,
        step: 1,
        range: {{ 'min': 0, 'max': paramChoices.length - 1 }},
        pips: {{
            mode: 'values',
            values: Array.from(Array(paramChoices.length).keys()),
            density: 100 / (paramChoices.length - 1),
            format: {{ to: function(value) {{ return paramChoices[value]; }} }}
        }}
    }});

    const paramRangeStateInput = document.querySelector('#param-range-state-js textarea');
    const resetBtn = document.getElementById('reset-params-btn');
    const initialRange = [0, paramChoices.length - 1];

    function update(values) {{
        const intValues = values.map(v => parseInt(v, 10));
        const isDefault = intValues[0] === initialRange[0] && intValues[1] === initialRange[1];
        
        // Show/hide reset button
        resetBtn.style.display = isDefault ? 'none' : 'inline-block';

        // Update hidden state for Python
        const newValue = JSON.stringify(intValues);
        if (paramRangeStateInput.value !== newValue) {{
            paramRangeStateInput.value = newValue;
            const event = new Event('input', {{ bubbles: true }});
            paramRangeStateInput.dispatchEvent(event);
        }}
    }}

    slider.noUiSlider.on('update', update);
    
    // The reset button in the HTML calls this JS function directly
    window.resetSlider = function() {{
        slider.noUiSlider.set(initialRange);
    }}
}}
"""

def load_models_data():
    overall_start_time = time.time()
    print(f"Attempting to load dataset from Hugging Face Hub: {HF_DATASET_ID}")
    try:
        dataset_dict = load_dataset(HF_DATASET_ID)
        df = dataset_dict[list(dataset_dict.keys())[0]].to_pandas()
        if 'params' in df.columns:
            df['params'] = pd.to_numeric(df['params'], errors='coerce').fillna(0)
        else:
            df['params'] = 0
        msg = f"Successfully loaded dataset in {time.time() - overall_start_time:.2f}s."
        print(msg)
        return df, True, msg
    except Exception as e:
        return pd.DataFrame(), False, f"Failed to load dataset. Error: {e}"

def get_param_range_values(param_range_labels):
    min_label, max_label = param_range_labels
    min_val = 0.0 if '<' in min_label else float(min_label.replace('B', ''))
    max_val = float('inf') if '>' in max_label else float(max_label.replace('B', ''))
    return min_val, max_val

def make_treemap_data(df, count_by, top_k=25, tag_filter=None, pipeline_filter=None, param_range=None, skip_orgs=None):
    if df is None or df.empty: return pd.DataFrame()
    filtered_df = df.copy()
    col_map = { "Audio & Speech": "is_audio_speech", "Music": "has_music", "Robotics": "has_robot", "Biomedical": "is_biomed", "Time series": "has_series", "Sciences": "has_science", "Video": "has_video", "Images": "has_image", "Text": "has_text" }
    if tag_filter and tag_filter in col_map and col_map[tag_filter] in filtered_df.columns:
        filtered_df = filtered_df[filtered_df[col_map[tag_filter]]]
    if pipeline_filter and "pipeline_tag" in filtered_df.columns:
        filtered_df = filtered_df[filtered_df["pipeline_tag"].astype(str) == pipeline_filter]
    if param_range:
        min_params, max_params = get_param_range_values(param_range)
        is_default_range = (param_range[0] == PARAM_CHOICES[0] and param_range[1] == PARAM_CHOICES[-1])
        if not is_default_range and 'params' in filtered_df.columns:
            if min_params is not None: filtered_df = filtered_df[filtered_df['params'] >= min_params]
            if max_params is not None and max_params != float('inf'): filtered_df = filtered_df[filtered_df['params'] < max_params]
    if skip_orgs and len(skip_orgs) > 0 and "organization" in filtered_df.columns:
        filtered_df = filtered_df[~filtered_df["organization"].isin(skip_orgs)]
    if filtered_df.empty: return pd.DataFrame()
    if count_by not in filtered_df.columns: filtered_df[count_by] = 0.0
    filtered_df[count_by] = pd.to_numeric(filtered_df[count_by], errors='coerce').fillna(0.0)
    org_totals = filtered_df.groupby("organization")[count_by].sum().nlargest(top_k, keep='first')
    top_orgs_list = org_totals.index.tolist()
    treemap_data = filtered_df[filtered_df["organization"].isin(top_orgs_list)][["id", "organization", count_by]].copy()
    treemap_data["root"] = "models"
    return treemap_data

def create_treemap(treemap_data, count_by, title=None):
    if treemap_data.empty:
        fig = px.treemap(names=["No data matches filters"], parents=[""], values=[1])
        fig.update_layout(title="No data matches the selected filters", margin=dict(t=50, l=25, r=25, b=25))
        return fig
    fig = px.treemap(treemap_data, path=["root", "organization", "id"], values=count_by, title=title, color_discrete_sequence=px.colors.qualitative.Plotly)
    fig.update_layout(margin=dict(t=50, l=25, r=25, b=25))
    fig.update_traces(textinfo="label+value+percent root", hovertemplate="<b>%{label}</b><br>%{value:,} " + count_by + "<br>%{percentRoot:.2%} of total<extra></extra>")
    return fig

custom_head = """
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/noUiSlider/15.7.1/nouislider.min.css">
<script src="https://cdnjs.cloudflare.com/ajax/libs/noUiSlider/15.7.1/nouislider.min.js"></script>
"""

with gr.Blocks(title="🤗 ModelVerse Explorer", fill_width=True, head=custom_head) as demo:
    models_data_state = gr.State(pd.DataFrame())
    loading_complete_state = gr.State(False)
    
    with gr.Row():
        gr.Markdown("# 🤗 ModelVerse Explorer")

    with gr.Row():
        with gr.Column(scale=1):
            count_by_dropdown = gr.Dropdown(label="Metric", choices=[("Downloads (last 30 days)", "downloads"), ("Downloads (All Time)", "downloadsAllTime"), ("Likes", "likes")], value="downloads")
            filter_choice_radio = gr.Radio(label="Filter Type", choices=["None", "Tag Filter", "Pipeline Filter"], value="None")
            tag_filter_dropdown = gr.Dropdown(label="Select Tag", choices=TAG_FILTER_CHOICES, value=None, visible=False)
            pipeline_filter_dropdown = gr.Dropdown(label="Select Pipeline Tag", choices=PIPELINE_TAGS, value=None, visible=False)
            
            with gr.Group():
                gr.HTML("""
                    <div style="display: flex; justify-content: space-between; align-items: center; margin-bottom: -1rem;">
                        <label class="gradio-label">Parameters</label>
                        <button id="reset-params-btn" onclick="window.resetSlider()" class="gr-button gr-button-sm gr-button-secondary" style="display: none;">🔄 Reset</button>
                    </div>
                """)
                gr.HTML("""
                    <div id="noui-slider-container" style="margin: 2rem 1rem;"></div>
                    <style>
                        .noUi-value { font-size: 12px; color: #777; }
                        .noUi-pips-horizontal { padding: 10px 0; height: 50px; }
                        .noUi-connect { background: #000; }
                        .noUi-handle { border-radius: 50%; width: 22px; height: 22px; right: -11px; top: -8px; box-shadow: none; border: 2px solid #000; background: #FFF; cursor: pointer; }
                        .noUi-handle:focus { outline: none; }
                        .noUi-handle::after, .noUi-handle::before { display: none; }
                    </style>
                """)
                param_range_state_js = gr.Textbox(value=PARAM_STATE_DEFAULT_JSON, visible=False, elem_id="param-range-state-js")
            
            top_k_dropdown = gr.Dropdown(label="Number of Top Organizations", choices=TOP_K_CHOICES, value=25)
            skip_orgs_textbox = gr.Textbox(label="Organizations to Skip (comma-separated)", value="TheBloke,MaziyarPanahi,unsloth,modularai,Gensyn,bartowski")
            generate_plot_button = gr.Button(value="Generate Plot", variant="primary", interactive=False)

        with gr.Column(scale=3):
            plot_output = gr.Plot()
            status_message_md = gr.Markdown("Initializing...")
            data_info_md = gr.Markdown("")

    def _update_button_interactivity(is_loaded_flag): return gr.update(interactive=is_loaded_flag)
    loading_complete_state.change(fn=_update_button_interactivity, inputs=loading_complete_state, outputs=generate_plot_button)

    def _toggle_filters_visibility(choice): return gr.update(visible=choice == "Tag Filter"), gr.update(visible=choice == "Pipeline Filter")
    filter_choice_radio.change(fn=_toggle_filters_visibility, inputs=filter_choice_radio, outputs=[tag_filter_dropdown, pipeline_filter_dropdown])

    def ui_load_data_controller(progress=gr.Progress()):
        progress(0, desc=f"Loading dataset '{HF_DATASET_ID}'...")
        try:
            current_df, load_success_flag, status_msg_from_load = load_models_data()
            if load_success_flag:
                progress(0.9, desc="Processing data...")
                date_display = "Pre-processed (date unavailable)"
                if 'data_download_timestamp' in current_df.columns and pd.notna(current_df['data_download_timestamp'].iloc[0]):
                    ts = pd.to_datetime(current_df['data_download_timestamp'].iloc[0], utc=True)
                    date_display = ts.strftime('%B %d, %Y, %H:%M:%S %Z')
                param_count = (current_df['params'] > 0).sum() if 'params' in current_df.columns else 0
                data_info_text = f"### Data Information\n- Source: `{HF_DATASET_ID}`\n- Status: {status_msg_from_load}\n- Total models loaded: {len(current_df):,}\n- Models with parameter counts: {param_count:,}\n- Data as of: {date_display}\n"
                status_msg_ui = "Data loaded. Ready to generate plot."
            else:
                data_info_text = f"### Data Load Failed\n- {status_msg_from_load}"
                status_msg_ui = status_msg_from_load
        except Exception as e:
            status_msg_ui, data_info_text, load_success_flag = f"An unexpected error occurred: {str(e)}", f"### Critical Error\n- {status_msg_ui}", False
        return current_df, load_success_flag, data_info_text, status_msg_ui

    def ui_generate_plot_controller(metric_choice, filter_type, tag_choice, pipeline_choice, 
                                   param_range_json, k_orgs, skip_orgs_input, df_current_models, progress=gr.Progress()):
        if df_current_models is None or df_current_models.empty:
            return create_treemap(pd.DataFrame(), metric_choice, "Error: Model Data Not Loaded"), "Model data is not loaded."
        
        progress(0.1, desc="Preparing data...")
        tag_to_use = tag_choice if filter_type == "Tag Filter" else None
        pipeline_to_use = pipeline_choice if filter_type == "Pipeline Filter" else None
        orgs_to_skip = [org.strip() for org in skip_orgs_input.split(',') if org.strip()]
        
        param_range_indices = json.loads(param_range_json)
        min_label = PARAM_CHOICES[int(param_range_indices[0])]
        max_label = PARAM_CHOICES[int(param_range_indices[1])]
        param_labels_for_filtering = [min_label, max_label]
        
        treemap_df = make_treemap_data(df_current_models, metric_choice, k_orgs, tag_to_use, pipeline_to_use, param_labels_for_filtering, orgs_to_skip)
        
        progress(0.7, desc="Generating plot...")
        title_labels = {"downloads": "Downloads (last 30 days)", "downloadsAllTime": "Downloads (All Time)", "likes": "Likes"}
        chart_title = f"HuggingFace Models - {title_labels.get(metric_choice, metric_choice)} by Organization"
        plotly_fig = create_treemap(treemap_df, metric_choice, chart_title)
        
        if treemap_df.empty:
            plot_stats_md = "No data matches the selected filters. Please try different options."
        else:
            total_items_in_plot = len(treemap_df['id'].unique())
            total_value_in_plot = treemap_df[metric_choice].sum()
            plot_stats_md = f"## Plot Statistics\n- **Models shown**: {total_items_in_plot:,}\n- **Total {metric_choice}**: {int(total_value_in_plot):,}"
        return plotly_fig, plot_stats_md

    final_js = custom_slider_js.format(js_param_choices=json.dumps(PARAM_CHOICES))
    demo.load(
        fn=ui_load_data_controller, 
        inputs=[], 
        outputs=[models_data_state, loading_complete_state, data_info_md, status_message_md],
        js=f"() => {{ {final_js} }}"
    )

    generate_plot_button.click(
        fn=ui_generate_plot_controller,
        inputs=[count_by_dropdown, filter_choice_radio, tag_filter_dropdown, pipeline_filter_dropdown,
                param_range_state_js, top_k_dropdown, skip_orgs_textbox, models_data_state],
        outputs=[plot_output, status_message_md]
    )

if __name__ == "__main__":
    print(f"Application starting...")
    demo.queue().launch(ssr_mode=False)

# --- END OF FINAL, POLISHED FILE app.py ---