Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
-
# app.py — Thai Sentiment Analysis (
|
| 2 |
-
import os, json, importlib.util, traceback, re, math, tempfile
|
| 3 |
import gradio as gr
|
| 4 |
import torch, pandas as pd
|
| 5 |
import torch.nn.functional as F
|
|
@@ -69,51 +69,48 @@ def _is_substantive_text(s, min_chars=2):
|
|
| 69 |
return True
|
| 70 |
|
| 71 |
def _format_pct(x): return f"{x*100:.2f}%"
|
| 72 |
-
def _to_datetime_safe(s): return pd.to_datetime(s, errors="coerce", infer_datetime_format=True, utc=False)
|
| 73 |
|
| 74 |
-
|
| 75 |
-
|
| 76 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 77 |
|
| 78 |
def detect_columns(df):
|
| 79 |
-
"""ตรวจหา text
|
| 80 |
cols = list(df.columns)
|
| 81 |
low = {c.lower(): c for c in cols}
|
| 82 |
|
| 83 |
# Text column
|
| 84 |
text_col = None
|
| 85 |
for k in LIKELY_TEXT_COLS:
|
| 86 |
-
if k in low:
|
|
|
|
|
|
|
| 87 |
if text_col is None:
|
| 88 |
cand = [c for c in cols if df[c].dtype == object]
|
| 89 |
text_col = cand[0] if cand else cols[0]
|
| 90 |
|
| 91 |
-
#
|
| 92 |
-
|
| 93 |
for c in cols:
|
| 94 |
-
if c
|
| 95 |
-
date_candidates.append(c)
|
| 96 |
continue
|
| 97 |
-
|
| 98 |
-
|
| 99 |
-
date_candidates.append(c)
|
| 100 |
-
date_candidates = list(dict.fromkeys(date_candidates))
|
| 101 |
-
date_col = date_candidates[0] if len(date_candidates) > 0 else None
|
| 102 |
-
|
| 103 |
-
# Shop candidates
|
| 104 |
-
shop_candidates = []
|
| 105 |
-
for c in cols:
|
| 106 |
-
if c.lower() in LIKELY_SHOP_COLS:
|
| 107 |
-
shop_candidates.append(c)
|
| 108 |
continue
|
|
|
|
| 109 |
if df[c].dtype == object:
|
| 110 |
unique_ratio = df[c].nunique() / len(df)
|
| 111 |
-
if 0.01 <= unique_ratio <= 0.5:
|
| 112 |
-
|
| 113 |
-
shop_candidates = list(dict.fromkeys(shop_candidates))
|
| 114 |
-
shop_col = shop_candidates[0] if len(shop_candidates) > 0 else None
|
| 115 |
|
| 116 |
-
|
|
|
|
|
|
|
|
|
|
| 117 |
|
| 118 |
# ================= Core Predict =================
|
| 119 |
def _predict_batch(texts, model_name, batch_size=32):
|
|
@@ -170,58 +167,53 @@ def make_summary_chart(df):
|
|
| 170 |
|
| 171 |
return fig, info
|
| 172 |
|
| 173 |
-
def
|
| 174 |
-
"""
|
| 175 |
-
|
| 176 |
-
# กรองตามวันที่ถ้าต้องการ
|
| 177 |
-
if date_col and days_filter:
|
| 178 |
-
cutoff = pd.Timestamp.now() - pd.Timedelta(days=days_filter)
|
| 179 |
-
df = df[df[date_col] >= cutoff]
|
| 180 |
|
| 181 |
-
#
|
| 182 |
-
|
| 183 |
-
for
|
| 184 |
-
if pd.isna(
|
| 185 |
continue
|
| 186 |
-
|
| 187 |
-
neg = len(
|
| 188 |
-
pos = len(
|
| 189 |
-
total = len(
|
| 190 |
|
| 191 |
-
|
| 192 |
-
"
|
| 193 |
"negative": neg,
|
| 194 |
"positive": pos,
|
| 195 |
"total": total,
|
| 196 |
"pos_pct": pos/total*100 if total > 0 else 0
|
| 197 |
})
|
| 198 |
|
| 199 |
-
|
| 200 |
|
| 201 |
# กราฟแท่ง Stacked
|
| 202 |
fig = go.Figure()
|
| 203 |
fig.add_bar(
|
| 204 |
name="😞 เชิงลบ",
|
| 205 |
-
x=
|
| 206 |
-
y=
|
| 207 |
-
marker_color=NEG_COLOR
|
|
|
|
|
|
|
| 208 |
)
|
| 209 |
fig.add_bar(
|
| 210 |
name="😊 เชิงบวก",
|
| 211 |
-
x=
|
| 212 |
-
y=
|
| 213 |
-
marker_color=POS_COLOR
|
|
|
|
|
|
|
| 214 |
)
|
| 215 |
|
| 216 |
-
title = "🏪 รีวิวแต่ละร้าน/สาขา"
|
| 217 |
-
if days_filter:
|
| 218 |
-
title += f" ({days_filter} วันล่าสุด)"
|
| 219 |
-
|
| 220 |
fig.update_layout(
|
| 221 |
-
title=
|
| 222 |
barmode='stack',
|
| 223 |
template=TEMPLATE,
|
| 224 |
-
xaxis_title="
|
| 225 |
yaxis_title="จำนวนรีวิว",
|
| 226 |
height=450,
|
| 227 |
showlegend=True
|
|
@@ -229,11 +221,11 @@ def make_shop_chart(df, shop_col, date_col=None, days_filter=None):
|
|
| 229 |
|
| 230 |
# ตารางสรุป
|
| 231 |
summary_df = pd.DataFrame({
|
| 232 |
-
"
|
| 233 |
-
"รีวิวทั้งหมด":
|
| 234 |
-
"😞 เชิงลบ":
|
| 235 |
-
"😊 เชิงบวก":
|
| 236 |
-
"% เชิงบวก":
|
| 237 |
})
|
| 238 |
|
| 239 |
return fig, summary_df
|
|
@@ -264,47 +256,46 @@ def on_file_change(file_obj):
|
|
| 264 |
if file_obj is None:
|
| 265 |
return (gr.update(choices=[], value=None),
|
| 266 |
gr.update(choices=[], value=None),
|
| 267 |
-
gr.update(
|
| 268 |
gr.update(visible=False),
|
| 269 |
"⚠️ กรุณาอัปโหลดไฟล์ CSV")
|
| 270 |
|
| 271 |
try:
|
| 272 |
df = pd.read_csv(file_obj.name)
|
| 273 |
-
text_col,
|
| 274 |
-
|
| 275 |
-
has_shop = shop_col is not None
|
| 276 |
|
| 277 |
-
|
| 278 |
-
note += f"- 📝 ข้อความ: **{text_col}**\n"
|
| 279 |
|
| 280 |
-
|
| 281 |
-
|
| 282 |
|
| 283 |
-
if
|
| 284 |
-
note += f"
|
| 285 |
else:
|
| 286 |
-
note += f"
|
| 287 |
|
| 288 |
-
note +=
|
| 289 |
|
| 290 |
return (gr.update(choices=list(df.columns), value=text_col),
|
| 291 |
-
gr.update(choices=
|
| 292 |
-
|
| 293 |
-
gr.update(visible=
|
|
|
|
| 294 |
note)
|
| 295 |
|
| 296 |
except Exception as e:
|
| 297 |
return (gr.update(choices=[], value=None),
|
| 298 |
gr.update(choices=[], value=None),
|
| 299 |
-
gr.update(
|
| 300 |
gr.update(visible=False),
|
| 301 |
f"❌ ไม่สามารถอ่านไฟล์ได้: {str(e)}")
|
| 302 |
|
| 303 |
-
def predict_csv(file_obj, model_choice, text_col,
|
| 304 |
"""วิเคราะห์ CSV"""
|
| 305 |
if file_obj is None:
|
| 306 |
return (pd.DataFrame(), go.Figure(),
|
| 307 |
-
gr.update(visible=False),
|
|
|
|
| 308 |
"❌ กรุณาอัปโหลดไฟล์", None)
|
| 309 |
|
| 310 |
try:
|
|
@@ -314,7 +305,7 @@ def predict_csv(file_obj, model_choice, text_col, date_col, shop_col, days_filte
|
|
| 314 |
|
| 315 |
# ตรวจสอบ text column
|
| 316 |
if text_col not in cols:
|
| 317 |
-
text_col, _, _
|
| 318 |
|
| 319 |
# ดึงข้อความ
|
| 320 |
texts = [_norm_text(v) for v in df_raw[text_col].tolist()]
|
|
@@ -323,7 +314,8 @@ def predict_csv(file_obj, model_choice, text_col, date_col, shop_col, days_filte
|
|
| 323 |
|
| 324 |
if not texts_clean:
|
| 325 |
return (pd.DataFrame(), go.Figure(),
|
| 326 |
-
gr.update(visible=False),
|
|
|
|
| 327 |
"❌ ไม่พบข้อความที่วิเคราะห์ได้", None)
|
| 328 |
|
| 329 |
# ทำนาย
|
|
@@ -334,41 +326,26 @@ def predict_csv(file_obj, model_choice, text_col, date_col, shop_col, days_filte
|
|
| 334 |
fig_main, info = make_summary_chart(df_out)
|
| 335 |
|
| 336 |
if skipped > 0:
|
| 337 |
-
info += f"\n\n⚠️ ข้ามแถวว่าง: {skipped} แถว"
|
| 338 |
|
| 339 |
-
#
|
| 340 |
-
|
| 341 |
-
|
| 342 |
-
|
| 343 |
|
| 344 |
-
if
|
| 345 |
# เตรียมข้อมูล
|
| 346 |
-
|
| 347 |
-
|
| 348 |
|
| 349 |
-
#
|
| 350 |
-
|
| 351 |
-
dts = _to_datetime_safe(df_raw[date_col])
|
| 352 |
-
df_shop[date_col] = dts.iloc[:len(df_out)]
|
| 353 |
-
df_shop = df_shop.dropna(subset=[date_col])
|
| 354 |
-
|
| 355 |
-
# แปลง days_filter
|
| 356 |
-
days = None
|
| 357 |
-
if days_filter == "7 วันล่าสุด":
|
| 358 |
-
days = 7
|
| 359 |
-
elif days_filter == "15 วันล่าสุด":
|
| 360 |
-
days = 15
|
| 361 |
-
elif days_filter == "30 วันล่าสุด":
|
| 362 |
-
days = 30
|
| 363 |
-
|
| 364 |
-
fig_shop, shop_summary = make_shop_chart(df_shop, shop_col, date_col, days)
|
| 365 |
-
|
| 366 |
-
if days:
|
| 367 |
-
info += f"\n\n📅 แสดงข้อมูล: {days_filter}"
|
| 368 |
-
else:
|
| 369 |
-
fig_shop, shop_summary = make_shop_chart(df_shop, shop_col)
|
| 370 |
|
| 371 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 372 |
|
| 373 |
# บันทึกไฟล์
|
| 374 |
fd, path = tempfile.mkstemp(suffix=".csv")
|
|
@@ -376,13 +353,14 @@ def predict_csv(file_obj, model_choice, text_col, date_col, shop_col, days_filte
|
|
| 376 |
df_out.to_csv(path, index=False, encoding="utf-8-sig")
|
| 377 |
|
| 378 |
return (df_out, fig_main,
|
| 379 |
-
gr.update(visible=
|
| 380 |
-
|
| 381 |
info, path)
|
| 382 |
|
| 383 |
except Exception as e:
|
| 384 |
return (pd.DataFrame(), go.Figure(),
|
| 385 |
-
gr.update(visible=False),
|
|
|
|
| 386 |
f"❌ เกิดข้อผิดพลาด:\n{traceback.format_exc()}", None)
|
| 387 |
|
| 388 |
# ================= Gradio UI =================
|
|
@@ -399,14 +377,23 @@ with gr.Blocks(title="Thai Sentiment Analysis", theme=gr.themes.Soft()) as demo:
|
|
| 399 |
info="WCB = เร็ว | WCB_BiLSTM = แม่นยำสูงสุด (แนะนำ)"
|
| 400 |
)
|
| 401 |
|
| 402 |
-
# =================== Tab 1 ===================
|
| 403 |
with gr.Tab("📝 วิเคราะห์ข้อความ"):
|
| 404 |
-
gr.Markdown("
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 405 |
|
| 406 |
text_input = gr.Textbox(
|
| 407 |
lines=8,
|
| 408 |
label="📄 ข้อความรีวิว",
|
| 409 |
-
placeholder="ป้อนรีวิว แต่ละบรรทัด = 1
|
| 410 |
)
|
| 411 |
|
| 412 |
predict_btn_1 = gr.Button("🚀 เริ่มวิเคราะห์", variant="primary", size="lg")
|
|
@@ -425,53 +412,64 @@ with gr.Blocks(title="Thai Sentiment Analysis", theme=gr.themes.Soft()) as demo:
|
|
| 425 |
[result_df_1, result_chart_1, result_info_1]
|
| 426 |
)
|
| 427 |
|
| 428 |
-
# =================== Tab 2 ===================
|
| 429 |
-
with gr.Tab("📤
|
| 430 |
-
gr.Markdown("
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 431 |
|
| 432 |
file_input = gr.File(file_types=[".csv"], label="📁 อัปโหลดไฟล์ CSV")
|
| 433 |
|
| 434 |
detect_note = gr.Markdown("⬆️ อัปโหลดไฟล์เพื่อเริ่มต้น")
|
| 435 |
|
| 436 |
with gr.Row():
|
| 437 |
-
text_col_dd = gr.Dropdown(
|
| 438 |
-
|
| 439 |
-
|
| 440 |
-
|
| 441 |
-
|
| 442 |
-
|
| 443 |
-
|
| 444 |
-
|
| 445 |
-
info="ใช้กรองข้อมูลเฉพาะกราฟร้าน (ถ้ามีวันที่)",
|
| 446 |
-
visible=False
|
| 447 |
-
)
|
| 448 |
|
| 449 |
predict_btn_2 = gr.Button("🚀 เริ่มวิเคราะห์", variant="primary", size="lg")
|
| 450 |
|
| 451 |
-
|
|
|
|
|
|
|
| 452 |
|
| 453 |
with gr.Row():
|
| 454 |
with gr.Column(scale=1):
|
| 455 |
-
result_chart_2 = gr.Plot(label="📊
|
| 456 |
with gr.Column(scale=1):
|
| 457 |
result_info_2 = gr.Markdown()
|
| 458 |
|
| 459 |
-
|
| 460 |
-
|
| 461 |
|
| 462 |
-
download_file = gr.File(label="💾 ดาวน์โหลดผลลัพธ์")
|
| 463 |
|
| 464 |
# Events
|
| 465 |
file_input.change(
|
| 466 |
on_file_change,
|
| 467 |
[file_input],
|
| 468 |
-
[text_col_dd,
|
| 469 |
)
|
| 470 |
|
| 471 |
predict_btn_2.click(
|
| 472 |
predict_csv,
|
| 473 |
-
[file_input, model_radio, text_col_dd,
|
| 474 |
-
[result_df_2, result_chart_2,
|
| 475 |
)
|
| 476 |
|
| 477 |
gr.Markdown("""
|
|
|
|
| 1 |
+
# app.py — Thai Sentiment Analysis (ยืดหยุ่น + ง่าย)
|
| 2 |
+
import os, json, importlib.util, traceback, re, math, tempfile
|
| 3 |
import gradio as gr
|
| 4 |
import torch, pandas as pd
|
| 5 |
import torch.nn.functional as F
|
|
|
|
| 69 |
return True
|
| 70 |
|
| 71 |
def _format_pct(x): return f"{x*100:.2f}%"
|
|
|
|
| 72 |
|
| 73 |
+
# คำที่น่าจะเป็นคอลัมน์ข้อความ
|
| 74 |
+
LIKELY_TEXT_COLS = ["text","review","message","comment","content","sentence","body",
|
| 75 |
+
"ข้อความ","รีวิว","ความคิดเห็น"]
|
| 76 |
+
|
| 77 |
+
# คำที่น่าจะเป็นคอลัมน์หมวดหมู่ (ร้าน/product/category)
|
| 78 |
+
LIKELY_GROUP_COLS = ["shop","store","branch","category","product","brand","type","group",
|
| 79 |
+
"ร้าน","สาขา","ชื่อร้าน","หมวดหมู่","ประเภท","แบรนด์"]
|
| 80 |
|
| 81 |
def detect_columns(df):
|
| 82 |
+
"""ตรวจหา text และ group columns อัตโนมัติ"""
|
| 83 |
cols = list(df.columns)
|
| 84 |
low = {c.lower(): c for c in cols}
|
| 85 |
|
| 86 |
# Text column
|
| 87 |
text_col = None
|
| 88 |
for k in LIKELY_TEXT_COLS:
|
| 89 |
+
if k in low:
|
| 90 |
+
text_col = low[k]
|
| 91 |
+
break
|
| 92 |
if text_col is None:
|
| 93 |
cand = [c for c in cols if df[c].dtype == object]
|
| 94 |
text_col = cand[0] if cand else cols[0]
|
| 95 |
|
| 96 |
+
# Group candidates (ร้าน/หมวดหมู่)
|
| 97 |
+
group_candidates = []
|
| 98 |
for c in cols:
|
| 99 |
+
if c == text_col: # ข้ามคอลัมน์ที่เป็น text
|
|
|
|
| 100 |
continue
|
| 101 |
+
if c.lower() in LIKELY_GROUP_COLS:
|
| 102 |
+
group_candidates.append(c)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 103 |
continue
|
| 104 |
+
# ตรวจว่ามีค่าซ้ำพอสมควร (categorical)
|
| 105 |
if df[c].dtype == object:
|
| 106 |
unique_ratio = df[c].nunique() / len(df)
|
| 107 |
+
if 0.01 <= unique_ratio <= 0.5: # 1-50% ของข้อมูลเป็นค่าซ้ำ
|
| 108 |
+
group_candidates.append(c)
|
|
|
|
|
|
|
| 109 |
|
| 110 |
+
group_candidates = list(dict.fromkeys(group_candidates))
|
| 111 |
+
group_col = group_candidates[0] if len(group_candidates) > 0 else None
|
| 112 |
+
|
| 113 |
+
return text_col, group_candidates, group_col
|
| 114 |
|
| 115 |
# ================= Core Predict =================
|
| 116 |
def _predict_batch(texts, model_name, batch_size=32):
|
|
|
|
| 167 |
|
| 168 |
return fig, info
|
| 169 |
|
| 170 |
+
def make_group_chart(df, group_col):
|
| 171 |
+
"""กราฟแสดงรีวิวแยกตามกลุ่ม (ร้าน/หมวดหมู่/etc)"""
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 172 |
|
| 173 |
+
# สรุปแต่ละกลุ่ม
|
| 174 |
+
group_data = []
|
| 175 |
+
for group in df[group_col].unique():
|
| 176 |
+
if pd.isna(group):
|
| 177 |
continue
|
| 178 |
+
group_df = df[df[group_col] == group]
|
| 179 |
+
neg = len(group_df[group_df["label"]=="negative"])
|
| 180 |
+
pos = len(group_df[group_df["label"]=="positive"])
|
| 181 |
+
total = len(group_df)
|
| 182 |
|
| 183 |
+
group_data.append({
|
| 184 |
+
"group": str(group),
|
| 185 |
"negative": neg,
|
| 186 |
"positive": pos,
|
| 187 |
"total": total,
|
| 188 |
"pos_pct": pos/total*100 if total > 0 else 0
|
| 189 |
})
|
| 190 |
|
| 191 |
+
group_df = pd.DataFrame(group_data).sort_values("total", ascending=False)
|
| 192 |
|
| 193 |
# กราฟแท่ง Stacked
|
| 194 |
fig = go.Figure()
|
| 195 |
fig.add_bar(
|
| 196 |
name="😞 เชิงลบ",
|
| 197 |
+
x=group_df["group"],
|
| 198 |
+
y=group_df["negative"],
|
| 199 |
+
marker_color=NEG_COLOR,
|
| 200 |
+
text=group_df["negative"],
|
| 201 |
+
textposition='inside'
|
| 202 |
)
|
| 203 |
fig.add_bar(
|
| 204 |
name="😊 เชิงบวก",
|
| 205 |
+
x=group_df["group"],
|
| 206 |
+
y=group_df["positive"],
|
| 207 |
+
marker_color=POS_COLOR,
|
| 208 |
+
text=group_df["positive"],
|
| 209 |
+
textposition='inside'
|
| 210 |
)
|
| 211 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 212 |
fig.update_layout(
|
| 213 |
+
title=f"📊 รีวิวแยกตามกลุ่ม",
|
| 214 |
barmode='stack',
|
| 215 |
template=TEMPLATE,
|
| 216 |
+
xaxis_title="",
|
| 217 |
yaxis_title="จำนวนรีวิว",
|
| 218 |
height=450,
|
| 219 |
showlegend=True
|
|
|
|
| 221 |
|
| 222 |
# ตารางสรุป
|
| 223 |
summary_df = pd.DataFrame({
|
| 224 |
+
"กลุ่ม": group_df["group"],
|
| 225 |
+
"รีวิวทั้งหมด": group_df["total"],
|
| 226 |
+
"😞 เชิงลบ": group_df["negative"],
|
| 227 |
+
"😊 เชิงบวก": group_df["positive"],
|
| 228 |
+
"% เชิงบวก": group_df["pos_pct"].apply(lambda x: f"{x:.1f}%")
|
| 229 |
})
|
| 230 |
|
| 231 |
return fig, summary_df
|
|
|
|
| 256 |
if file_obj is None:
|
| 257 |
return (gr.update(choices=[], value=None),
|
| 258 |
gr.update(choices=[], value=None),
|
| 259 |
+
gr.update(visible=False),
|
| 260 |
gr.update(visible=False),
|
| 261 |
"⚠️ กรุณาอัปโหลดไฟล์ CSV")
|
| 262 |
|
| 263 |
try:
|
| 264 |
df = pd.read_csv(file_obj.name)
|
| 265 |
+
text_col, group_candidates, group_col = detect_columns(df)
|
|
|
|
|
|
|
| 266 |
|
| 267 |
+
has_group = group_col is not None
|
|
|
|
| 268 |
|
| 269 |
+
note = f"✅ **ตรวจพบคอลัมน์**\n\n"
|
| 270 |
+
note += f"📝 **ข้อความรีวิว:** {text_col}\n\n"
|
| 271 |
|
| 272 |
+
if has_group:
|
| 273 |
+
note += f"📊 **กลุ่ม/หมวดหมู่:** {group_col} ({df[group_col].nunique()} กลุ่ม)\n\n"
|
| 274 |
else:
|
| 275 |
+
note += f"📊 **กลุ่ม/หมวดหมู่:** _ไม่พบ_\n\n"
|
| 276 |
|
| 277 |
+
note += "_หากต้องการเปลี่ยน สามารถเลือกคอลัมน์ใหม่ได้ด้านบน_"
|
| 278 |
|
| 279 |
return (gr.update(choices=list(df.columns), value=text_col),
|
| 280 |
+
gr.update(choices=group_candidates if group_candidates else ["ไม่มี"],
|
| 281 |
+
value=group_col if group_col else "ไม่มี"),
|
| 282 |
+
gr.update(visible=has_group),
|
| 283 |
+
gr.update(visible=has_group),
|
| 284 |
note)
|
| 285 |
|
| 286 |
except Exception as e:
|
| 287 |
return (gr.update(choices=[], value=None),
|
| 288 |
gr.update(choices=[], value=None),
|
| 289 |
+
gr.update(visible=False),
|
| 290 |
gr.update(visible=False),
|
| 291 |
f"❌ ไม่สามารถอ่านไฟล์ได้: {str(e)}")
|
| 292 |
|
| 293 |
+
def predict_csv(file_obj, model_choice, text_col, group_col):
|
| 294 |
"""วิเคราะห์ CSV"""
|
| 295 |
if file_obj is None:
|
| 296 |
return (pd.DataFrame(), go.Figure(),
|
| 297 |
+
gr.update(visible=False),
|
| 298 |
+
gr.update(visible=False),
|
| 299 |
"❌ กรุณาอัปโหลดไฟล์", None)
|
| 300 |
|
| 301 |
try:
|
|
|
|
| 305 |
|
| 306 |
# ตรวจสอบ text column
|
| 307 |
if text_col not in cols:
|
| 308 |
+
text_col, _, _ = detect_columns(df_raw)
|
| 309 |
|
| 310 |
# ดึงข้อความ
|
| 311 |
texts = [_norm_text(v) for v in df_raw[text_col].tolist()]
|
|
|
|
| 314 |
|
| 315 |
if not texts_clean:
|
| 316 |
return (pd.DataFrame(), go.Figure(),
|
| 317 |
+
gr.update(visible=False),
|
| 318 |
+
gr.update(visible=False),
|
| 319 |
"❌ ไม่พบข้อความที่วิเคราะห์ได้", None)
|
| 320 |
|
| 321 |
# ทำนาย
|
|
|
|
| 326 |
fig_main, info = make_summary_chart(df_out)
|
| 327 |
|
| 328 |
if skipped > 0:
|
| 329 |
+
info += f"\n\n⚠️ ข้ามแถวว่าง: {skipped} แถว (ใช้ {len(texts_clean)}/{total_rows} แถว)"
|
| 330 |
|
| 331 |
+
# วิเคราะห์ตามกลุ่ม (ถ้ามี)
|
| 332 |
+
fig_group = go.Figure()
|
| 333 |
+
group_summary = pd.DataFrame()
|
| 334 |
+
show_group = False
|
| 335 |
|
| 336 |
+
if group_col and group_col in cols and group_col != "ไม่มี":
|
| 337 |
# เตรียมข้อมูล
|
| 338 |
+
df_group = df_out.copy()
|
| 339 |
+
df_group[group_col] = df_raw[group_col].iloc[:len(df_out)]
|
| 340 |
|
| 341 |
+
# ลบแถวที่ไม่มีข้อมูลกลุ่ม
|
| 342 |
+
df_group = df_group.dropna(subset=[group_col])
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 343 |
|
| 344 |
+
if len(df_group) > 0:
|
| 345 |
+
fig_group, group_summary = make_group_chart(df_group, group_col)
|
| 346 |
+
show_group = True
|
| 347 |
+
|
| 348 |
+
info += f"\n\n📊 **วิเคราะห์เพิ่มเติม:** แยกตาม '{group_col}'"
|
| 349 |
|
| 350 |
# บันทึกไฟล์
|
| 351 |
fd, path = tempfile.mkstemp(suffix=".csv")
|
|
|
|
| 353 |
df_out.to_csv(path, index=False, encoding="utf-8-sig")
|
| 354 |
|
| 355 |
return (df_out, fig_main,
|
| 356 |
+
gr.update(visible=show_group, value=fig_group),
|
| 357 |
+
gr.update(visible=show_group, value=group_summary),
|
| 358 |
info, path)
|
| 359 |
|
| 360 |
except Exception as e:
|
| 361 |
return (pd.DataFrame(), go.Figure(),
|
| 362 |
+
gr.update(visible=False),
|
| 363 |
+
gr.update(visible=False),
|
| 364 |
f"❌ เกิดข้อผิดพลาด:\n{traceback.format_exc()}", None)
|
| 365 |
|
| 366 |
# ================= Gradio UI =================
|
|
|
|
| 377 |
info="WCB = เร็ว | WCB_BiLSTM = แม่นยำสูงสุด (แนะนำ)"
|
| 378 |
)
|
| 379 |
|
| 380 |
+
# =================== Tab 1: วิเคราะห์ข้อความ ===================
|
| 381 |
with gr.Tab("📝 วิเคราะห์ข้อความ"):
|
| 382 |
+
gr.Markdown("""
|
| 383 |
+
**วิธีใช้:** ป้อนรีวิวหลายรายการ (แต่ละบรรทัด = 1 รีวิว)
|
| 384 |
+
|
| 385 |
+
**ตัวอย่าง:**
|
| 386 |
+
```
|
| 387 |
+
อาหารอร่อยมาก บริการดี
|
| 388 |
+
ของแพง รสชาติธรรมดา
|
| 389 |
+
บรรยากาศดี แนะนำเลย
|
| 390 |
+
```
|
| 391 |
+
""")
|
| 392 |
|
| 393 |
text_input = gr.Textbox(
|
| 394 |
lines=8,
|
| 395 |
label="📄 ข้อความรีวิว",
|
| 396 |
+
placeholder="ป้อนรีวิว แต่ละบรรทัด = 1 รีวิว..."
|
| 397 |
)
|
| 398 |
|
| 399 |
predict_btn_1 = gr.Button("🚀 เริ่มวิเคราะห์", variant="primary", size="lg")
|
|
|
|
| 412 |
[result_df_1, result_chart_1, result_info_1]
|
| 413 |
)
|
| 414 |
|
| 415 |
+
# =================== Tab 2: อัปโหลด CSV ===================
|
| 416 |
+
with gr.Tab("📤 วิเคราะห์ไฟล์ CSV"):
|
| 417 |
+
gr.Markdown("""
|
| 418 |
+
**วิธีใช้:** อัปโหลดไฟล์ CSV ที่มีคอลัมน์รีวิว
|
| 419 |
+
|
| 420 |
+
**ระบบจะตรวจหาอัตโนมัติ:**
|
| 421 |
+
- 📝 คอลัมน์ข้อความรีวิว
|
| 422 |
+
- 📊 คอลัมน์กลุ่ม/หมวดหมู่ (เช่น ร้าน, สาขา, ประเภทสินค้า, แบรนด์)
|
| 423 |
+
|
| 424 |
+
**ใช้ได้กับหลายสถานการณ์:**
|
| 425 |
+
- เปรียบเทียบร้านค้า/สาขา
|
| 426 |
+
- วิเคราะห์ตาม product category
|
| 427 |
+
- แยกตามแบรนด์/ประเภทสินค้า
|
| 428 |
+
- หรือข้อมูล categorical อื่นๆ
|
| 429 |
+
""")
|
| 430 |
|
| 431 |
file_input = gr.File(file_types=[".csv"], label="📁 อัปโหลดไฟล์ CSV")
|
| 432 |
|
| 433 |
detect_note = gr.Markdown("⬆️ อัปโหลดไฟล์เพื่อเริ่มต้น")
|
| 434 |
|
| 435 |
with gr.Row():
|
| 436 |
+
text_col_dd = gr.Dropdown(
|
| 437 |
+
label="📝 คอลัมน์ข้อความรีวิว",
|
| 438 |
+
info="เลือกคอลัมน์ที่มีเนื้อหารีวิว"
|
| 439 |
+
)
|
| 440 |
+
group_col_dd = gr.Dropdown(
|
| 441 |
+
label="📊 คอลัมน์กลุ่ม/หมวดหมู่ (ถ้ามี)",
|
| 442 |
+
info="เช่น ร้าน, สาขา, ประเภทสินค้า, แบรนด์"
|
| 443 |
+
)
|
|
|
|
|
|
|
|
|
|
| 444 |
|
| 445 |
predict_btn_2 = gr.Button("🚀 เริ่มวิเคราะห์", variant="primary", size="lg")
|
| 446 |
|
| 447 |
+
gr.Markdown("### 📊 ผลการวิเคราะห์")
|
| 448 |
+
|
| 449 |
+
result_df_2 = gr.Dataframe(label="📋 รายละเอียดทุกรีวิว")
|
| 450 |
|
| 451 |
with gr.Row():
|
| 452 |
with gr.Column(scale=1):
|
| 453 |
+
result_chart_2 = gr.Plot(label="📊 สรุปภาพรวม")
|
| 454 |
with gr.Column(scale=1):
|
| 455 |
result_info_2 = gr.Markdown()
|
| 456 |
|
| 457 |
+
result_group = gr.Plot(label="📊 เปรียบเทียบแต่ละกลุ่ม", visible=False)
|
| 458 |
+
group_summary = gr.Dataframe(label="📋 สรุปแต่ละกลุ่ม", visible=False)
|
| 459 |
|
| 460 |
+
download_file = gr.File(label="💾 ดาวน์โหลดผลลัพธ์ (CSV)")
|
| 461 |
|
| 462 |
# Events
|
| 463 |
file_input.change(
|
| 464 |
on_file_change,
|
| 465 |
[file_input],
|
| 466 |
+
[text_col_dd, group_col_dd, result_group, group_summary, detect_note]
|
| 467 |
)
|
| 468 |
|
| 469 |
predict_btn_2.click(
|
| 470 |
predict_csv,
|
| 471 |
+
[file_input, model_radio, text_col_dd, group_col_dd],
|
| 472 |
+
[result_df_2, result_chart_2, result_group, group_summary, result_info_2, download_file]
|
| 473 |
)
|
| 474 |
|
| 475 |
gr.Markdown("""
|