Clean up

pyproject.toml

@@ -9,7 +9,6 @@ dependencies = [
     "faiss-cpu>=1.12.0",
     "gradio[mcp]>=5.49.1",
     "gradio-modal>=0.0.4",
-    "loguru>=0.7.3",
     "polars>=1.34.0",
     "sentence-transformers>=5.1.1",
     "spaces>=0.42.1",

requirements.txt

@@ -120,8 +120,6 @@ jsonschema==4.25.1
     # via mcp
 jsonschema-specifications==2025.9.1
     # via jsonschema
-loguru==0.7.3
-    # via iccv2025 (pyproject.toml)
 markdown-it-py==4.0.0
     # via rich
 markupsafe==3.0.3

table.py

@@ -1,52 +1,10 @@
 import datasets
 import polars as pl
-from loguru import logger
-from polars import datatypes as pdt
 
 BASE_REPO_ID = "ai-conferences/ICCV2025"
-PATCH_REPO_ID = "ai-conferences/ICCV2025-patches"
 PAPER_PAGE_REPO_ID = "hysts-bot-data/paper-pages-slim"
 
 
-def get_patch_latest_values(
-    df: pl.DataFrame, all_columns: list[str], id_col: str, timestamp_col: str = "timestamp", delimiter: str = ","
-) -> pl.DataFrame:
-    df = df.sort(timestamp_col)
-
-    list_cols = [
-        col for col, dtype in df.schema.items() if col not in (id_col, timestamp_col) and dtype.base_type() is pdt.List
-    ]
-    df = df.with_columns(
-        [
-            pl.when(pl.col(c).is_not_null()).then(pl.col(c).list.join(delimiter)).otherwise(None).alias(c)
-            for c in list_cols
-        ]
-    )
-
-    update_columns = [col for col in df.columns if col not in (id_col, timestamp_col)]
-    melted = df.unpivot(on=update_columns, index=[timestamp_col, id_col]).drop_nulls()
-
-    latest_rows = (
-        melted.sort(timestamp_col)
-        .group_by([id_col, "variable"])
-        .agg(pl.col("value").last())
-        .pivot("variable", index=id_col, values="value")
-    )
-
-    latest_rows = latest_rows.with_columns(
-        [
-            pl.when(pl.col(c).is_not_null()).then(pl.col(c).str.split(delimiter)).otherwise(None).alias(c)
-            for c in list_cols
-        ]
-    )
-
-    missing_cols = [c for c in all_columns if c not in latest_rows.columns and c != id_col]
-    if missing_cols:
-        latest_rows = latest_rows.with_columns([pl.lit(None).alias(c) for c in missing_cols])
-
-    return latest_rows.select([id_col] + [col for col in all_columns if col != id_col])
-
-
 def format_author_claim_ratio(row: dict) -> str:
     n_linked_authors = row["n_linked_authors"]
     n_authors = row["n_authors"]
@@ -77,28 +35,6 @@ df_orig = (
     .drop(["github_2"])
 )
 
-try:
-    df_patches = (
-        datasets.load_dataset(PATCH_REPO_ID, split="train")
-        .to_polars()
-        .drop("diff")
-        .with_columns(pl.col("timestamp").str.strptime(pl.Datetime, "%+"))
-    )
-    df_patches = get_patch_latest_values(df_patches, df_orig.columns, id_col="paper_id", timestamp_col="timestamp")
-    df_orig = (
-        df_orig.join(df_patches, on="paper_id", how="left")
-        .with_columns(
-            [
-                pl.coalesce([pl.col(col + "_right"), pl.col(col)]).alias(col)
-                for col in df_orig.columns
-                if col != "paper_id"
-            ]
-        )
-        .select(df_orig.columns)
-    )
-except Exception as e:  # noqa: BLE001
-    logger.warning(e)
-
 # format authors
 df_orig = df_orig.with_columns(pl.col("authors").list.join(", ").alias("authors_str"))
 # format links

uv.lock

@@ -894,7 +894,6 @@ dependencies = [
     { name = "faiss-cpu" },
     { name = "gradio", extra = ["mcp"] },
     { name = "gradio-modal" },
-    { name = "loguru" },
     { name = "polars" },
     { name = "sentence-transformers" },
     { name = "spaces" },
@@ -907,7 +906,6 @@ requires-dist = [
     { name = "faiss-cpu", specifier = ">=1.12.0" },
     { name = "gradio", extras = ["mcp"], specifier = ">=5.49.1" },
     { name = "gradio-modal", specifier = ">=0.0.4" },
-    { name = "loguru", specifier = ">=0.7.3" },
     { name = "polars", specifier = ">=1.34.0" },
     { name = "sentence-transformers", specifier = ">=5.1.1" },
     { name = "spaces", specifier = ">=0.42.1" },
@@ -971,19 +969,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/41/45/1a4ed80516f02155c51f51e8cedb3c1902296743db0bbc66608a0db2814f/jsonschema_specifications-2025.9.1-py3-none-any.whl", hash = "sha256:98802fee3a11ee76ecaca44429fda8a41bff98b00a0f2838151b113f210cc6fe", size = 18437, upload-time = "2025-09-08T01:34:57.871Z" },
 ]
 
-[[package]]
-name = "loguru"
-version = "0.7.3"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "colorama", marker = "sys_platform == 'win32'" },
-    { name = "win32-setctime", marker = "sys_platform == 'win32'" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/3a/05/a1dae3dffd1116099471c643b8924f5aa6524411dc6c63fdae648c4f1aca/loguru-0.7.3.tar.gz", hash = "sha256:19480589e77d47b8d85b2c827ad95d49bf31b0dcde16593892eb51dd18706eb6", size = 63559, upload-time = "2024-12-06T11:20:56.608Z" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/0c/29/0348de65b8cc732daa3e33e67806420b2ae89bdce2b04af740289c5c6c8c/loguru-0.7.3-py3-none-any.whl", hash = "sha256:31a33c10c8e1e10422bfd431aeb5d351c7cf7fa671e3c4df004162264b28220c", size = 61595, upload-time = "2024-12-06T11:20:54.538Z" },
-]
-
 [[package]]
 name = "markdown-it-py"
 version = "4.0.0"
@@ -3179,15 +3164,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/fa/a8/5b41e0da817d64113292ab1f8247140aac61cbf6cfd085d6a0fa77f4984f/websockets-15.0.1-py3-none-any.whl", hash = "sha256:f7a866fbc1e97b5c617ee4116daaa09b722101d4a3c170c787450ba409f9736f", size = 169743, upload-time = "2025-03-05T20:03:39.41Z" },
 ]
 
-[[package]]
-name = "win32-setctime"
-version = "1.2.0"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/b3/8f/705086c9d734d3b663af0e9bb3d4de6578d08f46b1b101c2442fd9aecaa2/win32_setctime-1.2.0.tar.gz", hash = "sha256:ae1fdf948f5640aae05c511ade119313fb6a30d7eabe25fef9764dca5873c4c0", size = 4867, upload-time = "2024-12-07T15:28:28.314Z" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/e1/07/c6fe3ad3e685340704d314d765b7912993bcb8dc198f0e7a89382d37974b/win32_setctime-1.2.0-py3-none-any.whl", hash = "sha256:95d644c4e708aba81dc3704a116d8cbc974d70b3bdb8be1d150e36be6e9d1390", size = 4083, upload-time = "2024-12-07T15:28:26.465Z" },
-]
-
 [[package]]
 name = "xxhash"
 version = "3.6.0"