File size: 3,883 Bytes
fd38574 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 |
# Import packages
from dash import Dash, html, dcc, callback, Input, Output
import pandas as pd
import pickle
import plotly.express as px
from graphs.model_market_share import create_plotly_stacked_area_chart
from graphs.model_characteristics import create_plotly_language_concentration_chart
# Incorporate data
df = pd.read_csv('https://raw.githubusercontent.com/plotly/datasets/master/gapminder2007.csv')
# Initialize the app
app = Dash()
# Load all pickle files in data_frames/ as loop
with open('data_frames/model_topk_df.pkl', 'rb') as f:
model_topk_df = pickle.load(f)
with open('data_frames/model_gini_df.pkl', 'rb') as f:
model_gini_df = pickle.load(f)
with open('data_frames/model_hhi_df.pkl', 'rb') as f:
model_hhi_df = pickle.load(f)
with open('data_frames/language_concentration_df.pkl', 'rb') as f:
language_concentration_df = pickle.load(f)
with open('data_frames/download_license_cumsum_df.pkl', 'rb') as f:
license_concentration_df = pickle.load(f)
TEMP_MODEL_EVENTS = {
# "Yolo World Mirror": "2024-03-01",
"Llama 3": "2024-04-17",
"Stable Cascade": "2024-02-02",
"Stable Diffusion 3": "2024-05-30",
# "embed/upscale": "2023-03-24",
"DeepSeek-R1": "2025-01-20",
"Gemma-3 12B QAT": "2025-04-15", # gemma-3-12b-it-qat-4bit
# "Qwen": "2025-03-05",
# "Flux RedFlux": "2025-04-12",
# "DeepSeek-V3": "2025-03-24",
# "bloom": "2022-05-19",
"DALLE2-PyTorch": "2022-06-25",
"Stable Diffusion": "2022-08-10",
"CLIP ViT": "2021-01-05",
"YOLOv8": "2023-04-26",
"Sentence Transformer MiniLM v2": "2021-08-30",
}
PALETTE_0 = [
"#335C67",
"#FFF3B0",
"#E09F3E",
"#9E2A2B",
"#540B0E"
]
fig = create_plotly_stacked_area_chart(
model_topk_df, model_gini_df, model_hhi_df, TEMP_MODEL_EVENTS, PALETTE_0
)
LANG_SEGMENT_ORDER = [
'Monolingual: EN', 'Monolingual: HR', 'Monolingual: M/LR',
'Multilingual: HR', 'Multilingual', 'Unknown',
]
fig2 = create_plotly_language_concentration_chart(
language_concentration_df, 'time', 'metric', 'value', LANG_SEGMENT_ORDER, PALETTE_0
)
LICENSE_SEGMENT_ORDER = [
"Open Use", "Open Use (Acceptable Use Policy)", "Open Use (Non-Commercial Only)", "Attribution",
"Acceptable Use Policy", "Non-Commercial Only", "Undocumented", "Undocumented (Acceptable Use Policy)",
]
fig3 = create_plotly_language_concentration_chart(
license_concentration_df, 'period', 'status', 'percent', LICENSE_SEGMENT_ORDER, PALETTE_0
)
# Make global font family
fig.update_layout(font_family="Inter")
fig2.update_layout(font_family="Inter")
fig3.update_layout(font_family="Inter")
# App layout
app.layout = html.Div(
[
html.Div(children='Visualizing the Open Model Ecosystem', style={'fontSize': 28, 'fontWeight': 'bold', 'marginBottom': 10}),
html.Div(children='An interactive dashboard to explore trends in open models on Hugging Face', style={'fontSize': 16, 'marginBottom': 20}),
html.Hr(),
dcc.Tabs([
dcc.Tab(label='Model Market Share', children=[
dcc.Graph(figure=fig, id='stacked-area-chart'),
]),
dcc.Tab(label='Model Characteristics', children=[
dcc.Graph(id='language-concentration-chart'),
html.Div([
dcc.Dropdown(['Language Concentration', 'Architecture', 'License', 'Method'], 'Language Concentration', id='dropdown'),
]),
]),
])
],
style={'fontFamily': 'Inter'}
)
# On dropdown change, update graph
@app.callback(
Output('language-concentration-chart', 'figure'),
[Input('dropdown', 'value')]
)
def update_graph(selected_metric):
if selected_metric == 'Language Concentration':
return fig2
elif selected_metric == 'License':
return fig3
# Run the app
if __name__ == '__main__':
app.run(debug=True)
|