Spaces:
Running
Running
File size: 8,559 Bytes
32dbb08 5dd7582 61542b8 32dbb08 61542b8 32dbb08 5dd7582 32dbb08 6a05116 06e8556 32dbb08 ce5dc65 32dbb08 ce5dc65 32dbb08 985478d cd60bd0 c57e76c 32dbb08 61542b8 5dd7582 e46e945 32dbb08 06e8556 5dd7582 06e8556 5dd7582 06e8556 5dd7582 06e8556 32dbb08 5dd7582 32dbb08 5dd7582 32dbb08 5dd7582 32dbb08 06e8556 32dbb08 06e8556 32dbb08 e46e945 32dbb08 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 |
import json
import gzip
import gradio as gr
from gradio_leaderboard import Leaderboard, ColumnFilter, SelectColumns
import pandas as pd
from apscheduler.schedulers.background import BackgroundScheduler
from huggingface_hub import snapshot_download
from io import StringIO
from src.about import (
CITATION_BUTTON_LABEL,
CITATION_BUTTON_TEXT,
EVALUATION_QUEUE_TEXT,
INTRODUCTION_TEXT,
LLM_BENCHMARKS_TEXT,
TITLE,
)
from src.display.css_html_js import custom_css
from src.display.utils import (
BENCHMARK_COLS,
BENCHMARK_COLS_MULTIMODAL,
BENCHMARK_COLS_MIB_SUBGRAPH,
BENCHMARK_COLS_MIB_CAUSALGRAPH,
COLS,
COLS_MIB_SUBGRAPH,
COLS_MIB_CAUSALGRAPH,
COLS_MULTIMODAL,
EVAL_COLS,
EVAL_TYPES,
AutoEvalColumn,
AutoEvalColumn_mib_subgraph,
AutoEvalColumn_mib_causalgraph,
fields,
)
from src.envs import API, EVAL_REQUESTS_PATH, QUEUE_REPO, REPO_ID, TOKEN, RESULTS_REPO_MIB_SUBGRAPH, EVAL_RESULTS_MIB_SUBGRAPH_PATH, RESULTS_REPO_MIB_CAUSALGRAPH, EVAL_RESULTS_MIB_CAUSALGRAPH_PATH
from src.populate import get_evaluation_queue_df, get_leaderboard_df, get_leaderboard_df_mib_subgraph, get_leaderboard_df_mib_causalgraph
from src.submission.submit import add_new_eval
def restart_space():
API.restart_space(repo_id=REPO_ID)
### Space initialisation
try:
print(EVAL_REQUESTS_PATH)
snapshot_download(
repo_id=QUEUE_REPO, local_dir=EVAL_REQUESTS_PATH, repo_type="dataset", tqdm_class=None, etag_timeout=30, token=TOKEN
)
except Exception:
restart_space()
try:
print(RESULTS_REPO_MIB_SUBGRAPH)
snapshot_download(
repo_id=RESULTS_REPO_MIB_SUBGRAPH, local_dir=EVAL_RESULTS_MIB_SUBGRAPH_PATH, repo_type="dataset", tqdm_class=None, etag_timeout=30, token=TOKEN
)
except Exception:
restart_space()
try:
print(RESULTS_REPO_MIB_CAUSALGRAPH)
snapshot_download(
repo_id=RESULTS_REPO_MIB_CAUSALGRAPH, local_dir=EVAL_RESULTS_MIB_CAUSALGRAPH_PATH, repo_type="dataset", tqdm_class=None, etag_timeout=30, token=TOKEN
)
except Exception:
restart_space()
LEADERBOARD_DF_MIB_SUBGRAPH = get_leaderboard_df_mib_subgraph(EVAL_RESULTS_MIB_SUBGRAPH_PATH, EVAL_REQUESTS_PATH, COLS_MIB_SUBGRAPH, BENCHMARK_COLS_MIB_SUBGRAPH)
LEADERBOARD_DF_MIB_CAUSALGRAPH = get_leaderboard_df_mib_causalgraph(EVAL_RESULTS_MIB_CAUSALGRAPH_PATH, EVAL_REQUESTS_PATH, COLS_MIB_CAUSALGRAPH, BENCHMARK_COLS_MIB_CAUSALGRAPH)
# LEADERBOARD_DF = get_leaderboard_df(EVAL_RESULTS_PATH, EVAL_REQUESTS_PATH, COLS, BENCHMARK_COLS)
# LEADERBOARD_DF_MULTIMODAL = get_leaderboard_df(EVAL_RESULTS_PATH, EVAL_REQUESTS_PATH, COLS_MULTIMODAL, BENCHMARK_COLS_MULTIMODAL)
(
finished_eval_queue_df,
running_eval_queue_df,
pending_eval_queue_df,
) = get_evaluation_queue_df(EVAL_REQUESTS_PATH, EVAL_COLS)
def init_leaderboard_mib_subgraph(dataframe, track):
print(f"init_leaderboard_mib: dataframe head before loc is {dataframe.head()}\n")
if dataframe is None or dataframe.empty:
raise ValueError("Leaderboard DataFrame is empty or None.")
# filter for correct track
# dataframe = dataframe.loc[dataframe["Track"] == track]
print(f"init_leaderboard_mib: dataframe head after loc is {dataframe.head()}\n")
return Leaderboard(
value=dataframe,
datatype=[c.type for c in fields(AutoEvalColumn_mib_subgraph)],
select_columns=SelectColumns(
default_selection=[c.name for c in fields(AutoEvalColumn_mib_subgraph) if c.displayed_by_default],
cant_deselect=[c.name for c in fields(AutoEvalColumn_mib_subgraph) if c.never_hidden],
label="Select Columns to Display:",
),
search_columns=["Method"], # Changed from AutoEvalColumn_mib_subgraph.model.name to "Method"
hide_columns=[c.name for c in fields(AutoEvalColumn_mib_subgraph) if c.hidden],
bool_checkboxgroup_label="Hide models",
interactive=False,
)
def init_leaderboard_mib_causalgraph(dataframe, track):
print(f"init_leaderboard_mib: dataframe head before loc is {dataframe.head()}\n")
if dataframe is None or dataframe.empty:
raise ValueError("Leaderboard DataFrame is empty or None.")
# filter for correct track
# dataframe = dataframe.loc[dataframe["Track"] == track]
print(f"init_leaderboard_mib: dataframe head after loc is {dataframe.head()}\n")
return Leaderboard(
value=dataframe,
datatype=[c.type for c in fields(AutoEvalColumn_mib_causalgraph)],
select_columns=SelectColumns(
default_selection=[c.name for c in fields(AutoEvalColumn_mib_causalgraph) if c.displayed_by_default],
cant_deselect=[c.name for c in fields(AutoEvalColumn_mib_causalgraph) if c.never_hidden],
label="Select Columns to Display:",
),
search_columns=["Method"], # Changed from AutoEvalColumn_mib_causalgraph.model.name to "Method"
hide_columns=[c.name for c in fields(AutoEvalColumn_mib_causalgraph) if c.hidden],
bool_checkboxgroup_label="Hide models",
interactive=False,
)
def init_leaderboard(dataframe, track):
if dataframe is None or dataframe.empty:
raise ValueError("Leaderboard DataFrame is empty or None.")
# filter for correct track
dataframe = dataframe.loc[dataframe["Track"] == track]
# print(f"\n\n\n dataframe is {dataframe}\n\n\n")
return Leaderboard(
value=dataframe,
datatype=[c.type for c in fields(AutoEvalColumn)],
select_columns=SelectColumns(
default_selection=[c.name for c in fields(AutoEvalColumn) if c.displayed_by_default],
cant_deselect=[c.name for c in fields(AutoEvalColumn) if c.never_hidden],
label="Select Columns to Display:",
),
search_columns=[AutoEvalColumn.model.name],
hide_columns=[c.name for c in fields(AutoEvalColumn) if c.hidden],
bool_checkboxgroup_label="Hide models",
interactive=False,
)
def process_json(temp_file):
if temp_file is None:
return {}
# Handle file upload
try:
file_path = temp_file.name
if file_path.endswith('.gz'):
with gzip.open(file_path, 'rt') as f:
data = json.load(f)
else:
with open(file_path, 'r') as f:
data = json.load(f)
except Exception as e:
raise gr.Error(f"Error processing file: {str(e)}")
gr.Markdown("Upload successful!")
return data
demo = gr.Blocks(css=custom_css)
with demo:
gr.HTML(TITLE)
gr.Markdown(INTRODUCTION_TEXT, elem_classes="markdown-text")
with gr.Tabs(elem_classes="tab-buttons") as tabs:
# with gr.TabItem("Strict", elem_id="strict-benchmark-tab-table", id=0):
# leaderboard = init_leaderboard(LEADERBOARD_DF, "strict")
# with gr.TabItem("Strict-small", elem_id="strict-small-benchmark-tab-table", id=1):
# leaderboard = init_leaderboard(LEADERBOARD_DF, "strict-small")
# with gr.TabItem("Multimodal", elem_id="multimodal-benchmark-tab-table", id=2):
# leaderboard = init_leaderboard(LEADERBOARD_DF_MULTIMODAL, "multimodal")
# with gr.TabItem("📝 About", elem_id="llm-benchmark-tab-table", id=4):
# gr.Markdown(LLM_BENCHMARKS_TEXT, elem_classes="markdown-text")
# with gr.TabItem("👶 Submit", elem_id="llm-benchmark-tab-table", id=5):
# with gr.Column():
# with gr.Row():
# gr.Markdown(EVALUATION_QUEUE_TEXT, elem_classes="markdown-text")
with gr.TabItem("Subgraph", elem_id="subgraph", id=0):
leaderboard = init_leaderboard_mib_subgraph(LEADERBOARD_DF_MIB_SUBGRAPH, "Subgraph")
with gr.TabItem("Causal Graph", elem_id="causalgraph", id=1):
leaderboard = init_leaderboard_mib_causalgraph(LEADERBOARD_DF_MIB_CAUSALGRAPH, "Causal Graph")
# with gr.Row():
# with gr.Accordion("📙 Citation", open=False):
# citation_button = gr.Textbox(
# value=CITATION_BUTTON_TEXT,
# label=CITATION_BUTTON_LABEL,
# lines=20,
# elem_id="citation-button",
# show_copy_button=True,
# )
scheduler = BackgroundScheduler()
scheduler.add_job(restart_space, "interval", seconds=1800)
scheduler.start()
demo.launch(share=True, ssr_mode=False)
|