File size: 4,217 Bytes
efc839c 9fe9439 297b2e5 f4eea62 9fe9439 f4eea62 efc839c f4eea62 efc839c f4eea62 efc839c f4eea62 efc839c 297b2e5 efc839c f4eea62 efc839c 297b2e5 efc839c 921abd0 |
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 |
import pandas as pd
import gradio as gr
CSV_PATH = "./judged-fast-accurate-downsampled.csv"
def load_csv_from_path(path: str):
try:
df = pd.read_csv(path)
return df, ""
except Exception as e:
return None, f"Failed to read CSV at {path}: {e}"
def filter_rows(df, mode, similar, text_filter, max_rows):
if df is None:
return "No data loaded. Click Reload.", "", None
if df.empty:
return "No data in CSV.", "", None
# Expected columns from judged-fast-accurate CSV
required = [
"frame_idx",
"t_sec",
"truth_text",
"fast_text",
"fast_similar",
"fast_score",
"fast_reason",
"accurate_text",
"accurate_similar",
"accurate_score",
"accurate_reason",
]
missing = [c for c in required if c not in df.columns]
if missing:
return f"Missing columns: {missing}", "", None
df["fast_similar"] = df["fast_similar"].astype(str)
df["accurate_similar"] = df["accurate_similar"].astype(str)
if mode != "both":
if mode == "fast":
df = df[df["fast_text"].notna()]
else:
df = df[df["accurate_text"].notna()]
if similar != "all":
val = "True" if similar == "true" else "False"
df = df[(df["fast_similar"] == val) | (df["accurate_similar"] == val)]
if text_filter:
t = text_filter.lower()
cols = [
"truth_text",
"fast_text",
"fast_reason",
"accurate_text",
"accurate_reason",
]
mask = df[cols].fillna("").apply(lambda x: x.str.lower().str.contains(t))
df = df[mask.any(axis=1)]
df = df.copy()
# Pretty display columns
df["fast"] = (
"similar=" + df["fast_similar"].fillna("")
+ " score=" + df["fast_score"].fillna("").astype(str)
+ " | " + df["fast_text"].fillna("")
+ " | reason: " + df["fast_reason"].fillna("")
)
df["accurate"] = (
"similar=" + df["accurate_similar"].fillna("")
+ " score=" + df["accurate_score"].fillna("").astype(str)
+ " | " + df["accurate_text"].fillna("")
+ " | reason: " + df["accurate_reason"].fillna("")
)
display_cols = ["frame_idx", "t_sec", "truth_text", "fast", "accurate"]
subset = df[display_cols].head(max_rows)
summary = (
f"Rows: {len(df)} | "
f"fast similar: {sum(df['fast_similar']=='True')} | "
f"accurate similar: {sum(df['accurate_similar']=='True')}"
)
return "", summary, subset
def run_all(path, mode, similar, text_filter, max_rows):
df, err = load_csv_from_path(path)
if err:
return err, "", None
return filter_rows(df, mode, similar, text_filter, max_rows)
with gr.Blocks() as demo:
gr.Markdown("# OCR Judge Viewer")
with gr.Row():
path_in = gr.Textbox(value=CSV_PATH, label="CSV path", interactive=True)
reload_btn = gr.Button("Reload")
mode = gr.Dropdown(["both", "fast", "accurate"], value="both", label="Mode")
similar = gr.Dropdown(["all", "true", "false"], value="all", label="similar flag")
text_filter = gr.Textbox(label="Search text", placeholder="search in truth/reasons")
max_rows = gr.Slider(10, 500, value=100, step=10, label="Max rows")
err_box = gr.Markdown()
summary_box = gr.Markdown()
table = gr.Dataframe(wrap=True)
reload_btn.click(run_all, [path_in, mode, similar, text_filter, max_rows], [err_box, summary_box, table])
mode.change(run_all, [path_in, mode, similar, text_filter, max_rows], [err_box, summary_box, table])
similar.change(run_all, [path_in, mode, similar, text_filter, max_rows], [err_box, summary_box, table])
text_filter.change(run_all, [path_in, mode, similar, text_filter, max_rows], [err_box, summary_box, table])
max_rows.change(run_all, [path_in, mode, similar, text_filter, max_rows], [err_box, summary_box, table])
demo.load(run_all, [path_in, mode, similar, text_filter, max_rows], [err_box, summary_box, table])
if __name__ == "__main__":
demo.queue().launch(server_name="0.0.0.0", server_port=7860, ssr_mode=False, show_error=True)
|