|
|
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 |
|
|
|
|
|
|
|
|
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() |
|
|
|
|
|
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) |
|
|
|
