Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -1,14 +1,10 @@
|
|
| 1 |
-
# app.py — Thai Sentiment (WangchanBERTa Variants)
|
| 2 |
-
# - Focus on POS/NEG only
|
| 3 |
-
# - Batch + CSV tabs
|
| 4 |
-
# - CSV: auto-detect text/date cols, hide date widgets if no date col
|
| 5 |
-
# - DatePicker fallback to Textbox if component missing
|
| 6 |
-
|
| 7 |
import os, json, importlib.util, traceback, re, math, tempfile, datetime
|
| 8 |
import gradio as gr
|
| 9 |
import torch, pandas as pd
|
| 10 |
import torch.nn.functional as F
|
| 11 |
import plotly.graph_objects as go
|
|
|
|
| 12 |
from huggingface_hub import hf_hub_download
|
| 13 |
from safetensors.torch import load_file
|
| 14 |
from transformers import AutoTokenizer
|
|
@@ -24,28 +20,42 @@ if DEFAULT_MODEL not in AVAILABLE_CHOICES:
|
|
| 24 |
|
| 25 |
NEG_COLOR = "#F87171"
|
| 26 |
POS_COLOR = "#34D399"
|
|
|
|
| 27 |
TEMPLATE = "plotly_white"
|
| 28 |
CACHE = {}
|
| 29 |
|
| 30 |
-
# ================= Date
|
| 31 |
-
|
| 32 |
-
|
| 33 |
-
|
| 34 |
-
|
| 35 |
-
|
| 36 |
-
|
| 37 |
-
|
| 38 |
-
|
| 39 |
|
| 40 |
-
def
|
| 41 |
-
|
| 42 |
-
if
|
| 43 |
-
|
| 44 |
-
|
| 45 |
-
|
| 46 |
-
|
| 47 |
-
|
| 48 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 49 |
|
| 50 |
# ================= Loader =================
|
| 51 |
def _import_models():
|
|
@@ -99,65 +109,226 @@ def _to_datetime_safe(s): return pd.to_datetime(s, errors="coerce", infer_dateti
|
|
| 99 |
|
| 100 |
LIKELY_TEXT_COLS = ["text","review","message","comment","content","sentence","body","ข้อความ","รีวิว"]
|
| 101 |
LIKELY_DATE_COLS = ["date","created_at","time","timestamp","datetime","วันที่","วันเวลา","เวลา"]
|
|
|
|
| 102 |
|
| 103 |
-
def
|
|
|
|
| 104 |
cols = list(df.columns)
|
| 105 |
low = {c.lower(): c for c in cols}
|
|
|
|
|
|
|
| 106 |
text_col = None
|
| 107 |
for k in LIKELY_TEXT_COLS:
|
| 108 |
if k in low: text_col = low[k]; break
|
| 109 |
if text_col is None:
|
| 110 |
cand = [c for c in cols if df[c].dtype == object]
|
| 111 |
text_col = cand[0] if cand else cols[0]
|
|
|
|
|
|
|
| 112 |
date_candidates = []
|
| 113 |
for c in cols:
|
| 114 |
-
if c.lower() in LIKELY_DATE_COLS:
|
|
|
|
|
|
|
| 115 |
sample = df[c].head(50)
|
| 116 |
if _to_datetime_safe(sample).notna().sum() >= max(3, int(len(sample)*0.2)):
|
| 117 |
date_candidates.append(c)
|
| 118 |
date_candidates = list(dict.fromkeys(date_candidates))
|
| 119 |
-
date_col = date_candidates[0] if len(date_candidates)>0 else None
|
| 120 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 121 |
|
| 122 |
# ================= Charts =================
|
| 123 |
-
def
|
|
|
|
| 124 |
total = len(df)
|
| 125 |
-
|
| 126 |
-
|
| 127 |
-
|
| 128 |
-
fig_bar.add_bar(name="positive", x=["positive"], y=[len(pos_df)], marker_color=POS_COLOR)
|
| 129 |
-
fig_bar.update_layout(barmode="group", title="Label counts", template=TEMPLATE)
|
| 130 |
-
labels=["negative","positive"]; values=[len(neg_df), len(pos_df)]
|
| 131 |
-
fig_pie = go.Figure(go.Pie(labels=labels, values=values, hole=0.35,
|
| 132 |
-
marker=dict(colors=[NEG_COLOR, POS_COLOR])))
|
| 133 |
-
fig_pie.update_layout(title="Positive vs Negative", template=TEMPLATE)
|
| 134 |
neg_avg = pd.to_numeric(df["negative(%)"].str.rstrip("%"), errors="coerce").mean()
|
| 135 |
pos_avg = pd.to_numeric(df["positive(%)"].str.rstrip("%"), errors="coerce").mean()
|
| 136 |
-
|
| 137 |
-
|
| 138 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 139 |
|
| 140 |
def _resample_counts(df, date_col, freq):
|
|
|
|
| 141 |
g = df.groupby([pd.Grouper(key=date_col, freq=freq),"label"]).size().unstack(fill_value=0)
|
| 142 |
for c in ["negative","positive"]:
|
| 143 |
if c not in g.columns: g[c]=0
|
| 144 |
return g[["negative","positive"]].sort_index()
|
| 145 |
|
| 146 |
-
def
|
| 147 |
-
|
| 148 |
-
|
| 149 |
-
|
| 150 |
-
if
|
| 151 |
-
|
| 152 |
-
|
| 153 |
-
|
| 154 |
-
fig
|
| 155 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 156 |
return fig
|
| 157 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 158 |
# ================= Core Predict =================
|
| 159 |
def _predict_batch(texts, model_name, batch_size=32):
|
| 160 |
-
model,tok,cfg=load_model(model_name)
|
|
|
|
| 161 |
for i in range(0,len(texts),batch_size):
|
| 162 |
chunk=texts[i:i+batch_size]
|
| 163 |
enc=tok(chunk,padding=True,truncation=True,
|
|
@@ -168,94 +339,365 @@ def _predict_batch(texts, model_name, batch_size=32):
|
|
| 168 |
for txt,p in zip(chunk,probs):
|
| 169 |
neg,pos=float(p[0]),float(p[1])
|
| 170 |
label="positive" if pos>=neg else "negative"
|
| 171 |
-
results.append({
|
| 172 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 173 |
return results
|
| 174 |
|
| 175 |
-
# =================
|
| 176 |
-
def predict_many(text_block, model_choice):
|
| 177 |
try:
|
| 178 |
-
raw=(text_block or "").splitlines()
|
| 179 |
-
norm=[_norm_text(t) for t in raw]
|
| 180 |
-
|
| 181 |
-
|
| 182 |
-
|
| 183 |
-
|
| 184 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 185 |
|
| 186 |
-
# ================= CSV
|
| 187 |
def on_file_change(file_obj):
|
|
|
|
| 188 |
if file_obj is None:
|
| 189 |
-
return gr.update(choices=[],value=None),
|
| 190 |
-
|
| 191 |
-
|
| 192 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 193 |
try:
|
| 194 |
-
df=pd.read_csv(file_obj.name)
|
| 195 |
-
text_col,date_candidates,date_col=
|
| 196 |
-
|
| 197 |
-
|
| 198 |
-
|
| 199 |
-
|
| 200 |
-
|
| 201 |
-
|
| 202 |
-
|
| 203 |
-
|
| 204 |
-
|
| 205 |
-
|
| 206 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 207 |
|
| 208 |
-
|
| 209 |
-
|
| 210 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 211 |
try:
|
| 212 |
-
df_raw=pd.read_csv(file_obj.name)
|
| 213 |
-
|
| 214 |
-
|
| 215 |
-
|
| 216 |
-
if not
|
| 217 |
-
|
| 218 |
-
|
| 219 |
-
|
| 220 |
-
|
| 221 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 222 |
if dts.notna().any():
|
| 223 |
-
df_time
|
| 224 |
-
|
| 225 |
-
|
| 226 |
-
|
| 227 |
-
|
| 228 |
-
|
| 229 |
-
|
| 230 |
-
|
| 231 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 232 |
|
| 233 |
# ================= Gradio UI =================
|
| 234 |
-
with gr.Blocks(title="Thai Sentiment") as demo:
|
| 235 |
-
gr.Markdown("
|
| 236 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 237 |
|
| 238 |
-
|
| 239 |
-
|
| 240 |
-
|
| 241 |
-
|
| 242 |
-
|
| 243 |
-
|
| 244 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 245 |
with gr.Row():
|
| 246 |
-
|
| 247 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 248 |
with gr.Row():
|
| 249 |
-
|
| 250 |
-
|
| 251 |
-
|
| 252 |
-
|
| 253 |
-
|
| 254 |
-
|
| 255 |
-
|
| 256 |
-
|
|
|
|
|
|
|
| 257 |
|
| 258 |
-
|
| 259 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 260 |
|
| 261 |
-
if __name__=="__main__":
|
|
|
|
|
|
| 1 |
+
# app.py — Thai Sentiment (WangchanBERTa Variants) - ปรับปรุง UI และเพิ่ม Shop Analysis
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
import os, json, importlib.util, traceback, re, math, tempfile, datetime
|
| 3 |
import gradio as gr
|
| 4 |
import torch, pandas as pd
|
| 5 |
import torch.nn.functional as F
|
| 6 |
import plotly.graph_objects as go
|
| 7 |
+
from plotly.subplots import make_subplots
|
| 8 |
from huggingface_hub import hf_hub_download
|
| 9 |
from safetensors.torch import load_file
|
| 10 |
from transformers import AutoTokenizer
|
|
|
|
| 20 |
|
| 21 |
NEG_COLOR = "#F87171"
|
| 22 |
POS_COLOR = "#34D399"
|
| 23 |
+
NEUTRAL_COLOR = "#94A3B8"
|
| 24 |
TEMPLATE = "plotly_white"
|
| 25 |
CACHE = {}
|
| 26 |
|
| 27 |
+
# ================= Date Presets =================
|
| 28 |
+
DATE_PRESETS = {
|
| 29 |
+
"ทั้งหมด": None,
|
| 30 |
+
"7 วันล่าสุด": 7,
|
| 31 |
+
"30 วันล่าสุด": 30,
|
| 32 |
+
"90 วันล่าสุด": 90,
|
| 33 |
+
"เดือนนี้": "current_month",
|
| 34 |
+
"เดือนที่แล้ว": "last_month"
|
| 35 |
+
}
|
| 36 |
|
| 37 |
+
def apply_date_preset(df, date_col, preset_key):
|
| 38 |
+
"""กรองข้อมูลตาม preset ที่เลือก"""
|
| 39 |
+
if preset_key == "ทั้งหมด":
|
| 40 |
+
return df
|
| 41 |
+
|
| 42 |
+
now = pd.Timestamp.now()
|
| 43 |
+
|
| 44 |
+
if isinstance(DATE_PRESETS[preset_key], int):
|
| 45 |
+
days = DATE_PRESETS[preset_key]
|
| 46 |
+
cutoff = now - pd.Timedelta(days=days)
|
| 47 |
+
return df[df[date_col] >= cutoff]
|
| 48 |
+
|
| 49 |
+
elif DATE_PRESETS[preset_key] == "current_month":
|
| 50 |
+
start = now.replace(day=1, hour=0, minute=0, second=0, microsecond=0)
|
| 51 |
+
return df[df[date_col] >= start]
|
| 52 |
+
|
| 53 |
+
elif DATE_PRESETS[preset_key] == "last_month":
|
| 54 |
+
end_last = now.replace(day=1, hour=0, minute=0, second=0, microsecond=0)
|
| 55 |
+
start_last = (end_last - pd.Timedelta(days=1)).replace(day=1)
|
| 56 |
+
return df[(df[date_col] >= start_last) & (df[date_col] < end_last)]
|
| 57 |
+
|
| 58 |
+
return df
|
| 59 |
|
| 60 |
# ================= Loader =================
|
| 61 |
def _import_models():
|
|
|
|
| 109 |
|
| 110 |
LIKELY_TEXT_COLS = ["text","review","message","comment","content","sentence","body","ข้อความ","รีวิว"]
|
| 111 |
LIKELY_DATE_COLS = ["date","created_at","time","timestamp","datetime","วันที่","วันเวลา","เวลา"]
|
| 112 |
+
LIKELY_SHOP_COLS = ["shop","store","branch","ร้าน","สาขา","ชื่อร้าน"]
|
| 113 |
|
| 114 |
+
def detect_columns(df):
|
| 115 |
+
"""ตรวจหา text, date, shop columns อัตโนมัติ"""
|
| 116 |
cols = list(df.columns)
|
| 117 |
low = {c.lower(): c for c in cols}
|
| 118 |
+
|
| 119 |
+
# Text column
|
| 120 |
text_col = None
|
| 121 |
for k in LIKELY_TEXT_COLS:
|
| 122 |
if k in low: text_col = low[k]; break
|
| 123 |
if text_col is None:
|
| 124 |
cand = [c for c in cols if df[c].dtype == object]
|
| 125 |
text_col = cand[0] if cand else cols[0]
|
| 126 |
+
|
| 127 |
+
# Date candidates
|
| 128 |
date_candidates = []
|
| 129 |
for c in cols:
|
| 130 |
+
if c.lower() in LIKELY_DATE_COLS:
|
| 131 |
+
date_candidates.append(c)
|
| 132 |
+
continue
|
| 133 |
sample = df[c].head(50)
|
| 134 |
if _to_datetime_safe(sample).notna().sum() >= max(3, int(len(sample)*0.2)):
|
| 135 |
date_candidates.append(c)
|
| 136 |
date_candidates = list(dict.fromkeys(date_candidates))
|
| 137 |
+
date_col = date_candidates[0] if len(date_candidates) > 0 else None
|
| 138 |
+
|
| 139 |
+
# Shop candidates
|
| 140 |
+
shop_candidates = []
|
| 141 |
+
for c in cols:
|
| 142 |
+
if c.lower() in LIKELY_SHOP_COLS:
|
| 143 |
+
shop_candidates.append(c)
|
| 144 |
+
continue
|
| 145 |
+
# ตรวจว่ามีค่าซ้ำพอสมควร (เหมือนเป็น categorical)
|
| 146 |
+
if df[c].dtype == object:
|
| 147 |
+
unique_ratio = df[c].nunique() / len(df)
|
| 148 |
+
if 0.01 <= unique_ratio <= 0.5: # 1-50% ของข้อมูลเป็นค่าซ้ำ
|
| 149 |
+
shop_candidates.append(c)
|
| 150 |
+
shop_candidates = list(dict.fromkeys(shop_candidates))
|
| 151 |
+
shop_col = shop_candidates[0] if len(shop_candidates) > 0 else None
|
| 152 |
+
|
| 153 |
+
return text_col, date_candidates, date_col, shop_candidates, shop_col
|
| 154 |
|
| 155 |
# ================= Charts =================
|
| 156 |
+
def make_summary_chart(df, chart_type="pie"):
|
| 157 |
+
"""สร้างกราฟสรุปแบบเดียว (ไม่ซ้ำซ้อน)"""
|
| 158 |
total = len(df)
|
| 159 |
+
neg_count = len(df[df["label"]=="negative"])
|
| 160 |
+
pos_count = len(df[df["label"]=="positive"])
|
| 161 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 162 |
neg_avg = pd.to_numeric(df["negative(%)"].str.rstrip("%"), errors="coerce").mean()
|
| 163 |
pos_avg = pd.to_numeric(df["positive(%)"].str.rstrip("%"), errors="coerce").mean()
|
| 164 |
+
|
| 165 |
+
info = (f"**📊 สรุปผลการวิเคราะห์**\n\n"
|
| 166 |
+
f"- 📝 ทั้งหมด: **{total:,}** รีวิว\n"
|
| 167 |
+
f"- 😞 เชิงลบ: **{neg_count:,}** ({neg_count/total*100:.1f}%)\n"
|
| 168 |
+
f"- 😊 เชิงบวก: **{pos_count:,}** ({pos_count/total*100:.1f}%)\n"
|
| 169 |
+
f"- 📈 ค่าเฉลี่ยความมั่นใจ:\n"
|
| 170 |
+
f" - เชิงลบ: {neg_avg:.2f}%\n"
|
| 171 |
+
f" - เชิงบวก: {pos_avg:.2f}%")
|
| 172 |
+
|
| 173 |
+
if chart_type == "pie":
|
| 174 |
+
fig = go.Figure(go.Pie(
|
| 175 |
+
labels=["😞 เชิงลบ","😊 เชิงบวก"],
|
| 176 |
+
values=[neg_count, pos_count],
|
| 177 |
+
hole=0.4,
|
| 178 |
+
marker=dict(colors=[NEG_COLOR, POS_COLOR]),
|
| 179 |
+
textinfo='label+percent',
|
| 180 |
+
textfont_size=14
|
| 181 |
+
))
|
| 182 |
+
fig.update_layout(
|
| 183 |
+
title="สัดส่วนรีวิวเชิงบวก vs เชิงลบ",
|
| 184 |
+
template=TEMPLATE,
|
| 185 |
+
height=400
|
| 186 |
+
)
|
| 187 |
+
else: # bar
|
| 188 |
+
fig = go.Figure()
|
| 189 |
+
fig.add_bar(
|
| 190 |
+
x=["เชิงลบ","เชิงบวก"],
|
| 191 |
+
y=[neg_count, pos_count],
|
| 192 |
+
marker_color=[NEG_COLOR, POS_COLOR],
|
| 193 |
+
text=[neg_count, pos_count],
|
| 194 |
+
textposition='auto'
|
| 195 |
+
)
|
| 196 |
+
fig.update_layout(
|
| 197 |
+
title="จำนวนรีวิวแยกตามความรู้สึก",
|
| 198 |
+
template=TEMPLATE,
|
| 199 |
+
yaxis_title="จำนวน (รีวิว)",
|
| 200 |
+
height=400
|
| 201 |
+
)
|
| 202 |
+
|
| 203 |
+
return fig, info
|
| 204 |
|
| 205 |
def _resample_counts(df, date_col, freq):
|
| 206 |
+
"""รวมข้อมูลตามช่วงเวลา"""
|
| 207 |
g = df.groupby([pd.Grouper(key=date_col, freq=freq),"label"]).size().unstack(fill_value=0)
|
| 208 |
for c in ["negative","positive"]:
|
| 209 |
if c not in g.columns: g[c]=0
|
| 210 |
return g[["negative","positive"]].sort_index()
|
| 211 |
|
| 212 |
+
def make_time_chart(df, date_col, freq, use_smooth):
|
| 213 |
+
"""กราฟแนวโน้มตามเวลา"""
|
| 214 |
+
ts = _resample_counts(df, date_col, freq)
|
| 215 |
+
|
| 216 |
+
if use_smooth:
|
| 217 |
+
window = 7 if freq=="D" else (4 if freq=="W" else 3)
|
| 218 |
+
ts = ts.rolling(window, min_periods=1).mean()
|
| 219 |
+
|
| 220 |
+
fig = go.Figure()
|
| 221 |
+
fig.add_scatter(
|
| 222 |
+
x=ts.index, y=ts["negative"],
|
| 223 |
+
mode="lines+markers",
|
| 224 |
+
name="😞 เชิงลบ",
|
| 225 |
+
line=dict(color=NEG_COLOR, width=2),
|
| 226 |
+
marker=dict(size=6)
|
| 227 |
+
)
|
| 228 |
+
fig.add_scatter(
|
| 229 |
+
x=ts.index, y=ts["positive"],
|
| 230 |
+
mode="lines+markers",
|
| 231 |
+
name="😊 เชิงบวก",
|
| 232 |
+
line=dict(color=POS_COLOR, width=2),
|
| 233 |
+
marker=dict(size=6)
|
| 234 |
+
)
|
| 235 |
+
|
| 236 |
+
freq_map = {"D": "รายวัน", "W": "รายสัปดาห์", "M": "รายเดือน"}
|
| 237 |
+
smooth_text = " (ปรับให้เรียบแล้ว)" if use_smooth else ""
|
| 238 |
+
|
| 239 |
+
fig.update_layout(
|
| 240 |
+
title=f"📈 แนวโน้มรีวิวตามเวลา ({freq_map[freq]}){smooth_text}",
|
| 241 |
+
template=TEMPLATE,
|
| 242 |
+
xaxis_title="วันที่",
|
| 243 |
+
yaxis_title="จำนวนรีวิว",
|
| 244 |
+
hovermode='x unified',
|
| 245 |
+
height=450
|
| 246 |
+
)
|
| 247 |
+
|
| 248 |
return fig
|
| 249 |
|
| 250 |
+
def make_shop_analysis(df, shop_col, date_col=None, freq="D"):
|
| 251 |
+
"""วิเคราะห์แยกตามร้าน/สาขา"""
|
| 252 |
+
|
| 253 |
+
# 1. สรุปภาพรวมแต่ละร้าน
|
| 254 |
+
shop_summary = []
|
| 255 |
+
for shop in df[shop_col].unique():
|
| 256 |
+
if pd.isna(shop):
|
| 257 |
+
continue
|
| 258 |
+
shop_df = df[df[shop_col] == shop]
|
| 259 |
+
neg = len(shop_df[shop_df["label"]=="negative"])
|
| 260 |
+
pos = len(shop_df[shop_df["label"]=="positive"])
|
| 261 |
+
total = len(shop_df)
|
| 262 |
+
pos_ratio = pos / total * 100 if total > 0 else 0
|
| 263 |
+
|
| 264 |
+
shop_summary.append({
|
| 265 |
+
"ร้าน/สาขา": shop,
|
| 266 |
+
"รีวิวทั้งหมด": total,
|
| 267 |
+
"😞 เชิงลบ": neg,
|
| 268 |
+
"😊 เชิงบวก": pos,
|
| 269 |
+
"% เชิงบวก": f"{pos_ratio:.1f}%"
|
| 270 |
+
})
|
| 271 |
+
|
| 272 |
+
summary_df = pd.DataFrame(shop_summary).sort_values("รีวิวทั้งหมด", ascending=False)
|
| 273 |
+
|
| 274 |
+
# 2. กราฟเปรียบเทียบร้าน
|
| 275 |
+
fig_compare = go.Figure()
|
| 276 |
+
|
| 277 |
+
shops = summary_df["ร้าน/สาขา"].tolist()
|
| 278 |
+
negs = summary_df["😞 เชิงลบ"].tolist()
|
| 279 |
+
poss = summary_df["😊 เชิงบวก"].tolist()
|
| 280 |
+
|
| 281 |
+
fig_compare.add_bar(name="😞 เชิงลบ", x=shops, y=negs, marker_color=NEG_COLOR)
|
| 282 |
+
fig_compare.add_bar(name="😊 เชิงบวก", x=shops, y=poss, marker_color=POS_COLOR)
|
| 283 |
+
|
| 284 |
+
fig_compare.update_layout(
|
| 285 |
+
title="🏪 เปรียบเทียบรีวิวแต่ละร้าน/สาขา",
|
| 286 |
+
barmode='stack',
|
| 287 |
+
template=TEMPLATE,
|
| 288 |
+
xaxis_title="ร้าน/สาขา",
|
| 289 |
+
yaxis_title="จำนวนรีวิว",
|
| 290 |
+
height=450
|
| 291 |
+
)
|
| 292 |
+
|
| 293 |
+
# 3. กราฟแนวโน้มตามเวลาแยกร้าน (ถ้ามี date_col)
|
| 294 |
+
fig_trend = None
|
| 295 |
+
if date_col and date_col in df.columns:
|
| 296 |
+
fig_trend = go.Figure()
|
| 297 |
+
|
| 298 |
+
for shop in shops[:5]: # แสดงแค่ 5 ร้านแรก
|
| 299 |
+
shop_df = df[df[shop_col] == shop].copy()
|
| 300 |
+
if len(shop_df) == 0:
|
| 301 |
+
continue
|
| 302 |
+
|
| 303 |
+
# คำนวณ positive ratio ตามเวลา
|
| 304 |
+
shop_df['pos_score'] = (shop_df['label'] == 'positive').astype(int)
|
| 305 |
+
ts = shop_df.groupby(pd.Grouper(key=date_col, freq=freq))['pos_score'].mean() * 100
|
| 306 |
+
|
| 307 |
+
fig_trend.add_scatter(
|
| 308 |
+
x=ts.index,
|
| 309 |
+
y=ts.values,
|
| 310 |
+
mode='lines+markers',
|
| 311 |
+
name=shop,
|
| 312 |
+
line=dict(width=2),
|
| 313 |
+
marker=dict(size=5)
|
| 314 |
+
)
|
| 315 |
+
|
| 316 |
+
freq_map = {"D": "รายวัน", "W": "รายสัปดาห์", "M": "รายเดือน"}
|
| 317 |
+
fig_trend.update_layout(
|
| 318 |
+
title=f"📊 แนวโน้ม % รีวิวเชิงบวกแยกตามร้าน ({freq_map[freq]})",
|
| 319 |
+
template=TEMPLATE,
|
| 320 |
+
xaxis_title="วันที่",
|
| 321 |
+
yaxis_title="% รีวิวเชิงบวก",
|
| 322 |
+
hovermode='x unified',
|
| 323 |
+
height=450
|
| 324 |
+
)
|
| 325 |
+
|
| 326 |
+
return summary_df, fig_compare, fig_trend
|
| 327 |
+
|
| 328 |
# ================= Core Predict =================
|
| 329 |
def _predict_batch(texts, model_name, batch_size=32):
|
| 330 |
+
model,tok,cfg=load_model(model_name)
|
| 331 |
+
results=[]
|
| 332 |
for i in range(0,len(texts),batch_size):
|
| 333 |
chunk=texts[i:i+batch_size]
|
| 334 |
enc=tok(chunk,padding=True,truncation=True,
|
|
|
|
| 339 |
for txt,p in zip(chunk,probs):
|
| 340 |
neg,pos=float(p[0]),float(p[1])
|
| 341 |
label="positive" if pos>=neg else "negative"
|
| 342 |
+
results.append({
|
| 343 |
+
"review":txt,
|
| 344 |
+
"negative(%)":_format_pct(neg),
|
| 345 |
+
"positive(%)":_format_pct(pos),
|
| 346 |
+
"label":label
|
| 347 |
+
})
|
| 348 |
return results
|
| 349 |
|
| 350 |
+
# ================= Tab 1: วิเคราะห์หลายรีวิว =================
|
| 351 |
+
def predict_many(text_block, model_choice, chart_type):
|
| 352 |
try:
|
| 353 |
+
raw = (text_block or "").splitlines()
|
| 354 |
+
norm = [_norm_text(t) for t in raw]
|
| 355 |
+
clean = [t for t in norm if _is_substantive_text(t)]
|
| 356 |
+
|
| 357 |
+
if not clean:
|
| 358 |
+
return pd.DataFrame(), go.Figure(), "❌ ไม่พบข้อความที่สามารถวิเคราะห์ได้\n\nกรุณาป้อนข้อความที่มีความยาวอย่างน้อย 2 ตัวอักษร"
|
| 359 |
+
|
| 360 |
+
results = _predict_batch(clean, model_choice)
|
| 361 |
+
df = pd.DataFrame(results)
|
| 362 |
+
|
| 363 |
+
fig, info = make_summary_chart(df, chart_type)
|
| 364 |
+
|
| 365 |
+
return df, fig, info
|
| 366 |
+
|
| 367 |
+
except Exception as e:
|
| 368 |
+
return pd.DataFrame(), go.Figure(), f"❌ เกิดข้อผิดพลาด:\n\n{traceback.format_exc()}"
|
| 369 |
|
| 370 |
+
# ================= Tab 2: อัปโหลด CSV =================
|
| 371 |
def on_file_change(file_obj):
|
| 372 |
+
"""เมื่ออัปโหลดไฟล์ - ตรวจหา columns อัตโนมัติ"""
|
| 373 |
if file_obj is None:
|
| 374 |
+
return (gr.update(choices=[],value=None),
|
| 375 |
+
gr.update(choices=[],value=None),
|
| 376 |
+
gr.update(choices=[],value=None),
|
| 377 |
+
gr.update(visible=False),
|
| 378 |
+
gr.update(visible=False),
|
| 379 |
+
gr.update(visible=False),
|
| 380 |
+
gr.update(visible=False),
|
| 381 |
+
"⚠️ กรุณาอัปโหลดไฟล์ CSV")
|
| 382 |
+
|
| 383 |
try:
|
| 384 |
+
df = pd.read_csv(file_obj.name)
|
| 385 |
+
text_col, date_candidates, date_col, shop_candidates, shop_col = detect_columns(df)
|
| 386 |
+
|
| 387 |
+
has_date = date_col is not None
|
| 388 |
+
has_shop = shop_col is not None
|
| 389 |
+
|
| 390 |
+
note = f"✅ **ตรวจพบคอลัมน์:**\n"
|
| 391 |
+
note += f"- 📝 ข้อความ: **{text_col}**\n"
|
| 392 |
+
|
| 393 |
+
if has_date:
|
| 394 |
+
note += f"- 📅 วันที่: **{date_col}**\n"
|
| 395 |
+
else:
|
| 396 |
+
note += f"- 📅 วันที่: _ไม่พบ_\n"
|
| 397 |
+
|
| 398 |
+
if has_shop:
|
| 399 |
+
note += f"- 🏪 ร้าน/สาขา: **{shop_col}** (พบ {df[shop_col].nunique()} ร้าน)\n"
|
| 400 |
+
else:
|
| 401 |
+
note += f"- 🏪 ร้าน/สาขา: _ไม่พบ_\n"
|
| 402 |
+
|
| 403 |
+
note += f"\n_หากไม่ถูกต้อง สามารถเลือกใหม่ได้จากเมนูด้านบน_"
|
| 404 |
+
|
| 405 |
+
return (gr.update(choices=list(df.columns), value=text_col),
|
| 406 |
+
gr.update(choices=date_candidates if date_candidates else ["ไม่มี"], value=date_col),
|
| 407 |
+
gr.update(choices=shop_candidates if shop_candidates else ["ไม่มี"], value=shop_col),
|
| 408 |
+
gr.update(visible=has_date),
|
| 409 |
+
gr.update(visible=has_date),
|
| 410 |
+
gr.update(visible=has_shop),
|
| 411 |
+
gr.update(visible=has_shop),
|
| 412 |
+
note)
|
| 413 |
+
|
| 414 |
+
except Exception as e:
|
| 415 |
+
return (gr.update(choices=[],value=None),
|
| 416 |
+
gr.update(choices=[],value=None),
|
| 417 |
+
gr.update(choices=[],value=None),
|
| 418 |
+
gr.update(visible=False),
|
| 419 |
+
gr.update(visible=False),
|
| 420 |
+
gr.update(visible=False),
|
| 421 |
+
gr.update(visible=False),
|
| 422 |
+
f"❌ ไม่สามารถอ่านไฟล์ได้:\n{str(e)}")
|
| 423 |
|
| 424 |
+
def predict_csv(file_obj, model_choice, text_col, date_col, shop_col,
|
| 425 |
+
date_preset, freq, use_smooth, chart_type):
|
| 426 |
+
"""วิเคราะห์รีวิวจากไฟล์ CSV"""
|
| 427 |
+
if file_obj is None:
|
| 428 |
+
return (pd.DataFrame(), go.Figure(), go.Figure(),
|
| 429 |
+
gr.update(visible=False), gr.update(visible=False),
|
| 430 |
+
pd.DataFrame(), gr.update(visible=False),
|
| 431 |
+
"❌ กรุณาอัปโหลดไฟล์ CSV", None)
|
| 432 |
+
|
| 433 |
try:
|
| 434 |
+
df_raw = pd.read_csv(file_obj.name)
|
| 435 |
+
cols = list(df_raw.columns)
|
| 436 |
+
|
| 437 |
+
# ตรวจสอบ text column
|
| 438 |
+
if text_col not in cols:
|
| 439 |
+
text_col, _, _, _, _ = detect_columns(df_raw)
|
| 440 |
+
|
| 441 |
+
# ดึงข้อความและทำนาย
|
| 442 |
+
texts = [_norm_text(v) for v in df_raw[text_col].tolist()]
|
| 443 |
+
texts = [t for t in texts if _is_substantive_text(t)]
|
| 444 |
+
|
| 445 |
+
if not texts:
|
| 446 |
+
return (pd.DataFrame(), go.Figure(), go.Figure(),
|
| 447 |
+
gr.update(visible=False), gr.update(visible=False),
|
| 448 |
+
pd.DataFrame(), gr.update(visible=False),
|
| 449 |
+
"❌ ไม่พบข้อความที่สามารถวิเคราะห์ได้ในไฟล์", None)
|
| 450 |
+
|
| 451 |
+
results = _predict_batch(texts, model_choice)
|
| 452 |
+
df_out = pd.DataFrame(results)
|
| 453 |
+
|
| 454 |
+
# กราฟสรุปหลัก
|
| 455 |
+
fig_main, info = make_summary_chart(df_out, chart_type)
|
| 456 |
+
|
| 457 |
+
# กราฟตามเวลา
|
| 458 |
+
fig_time = go.Figure()
|
| 459 |
+
show_time = False
|
| 460 |
+
|
| 461 |
+
if date_col and date_col in cols and date_col != "ไม่มี":
|
| 462 |
+
dts = _to_datetime_safe(df_raw[date_col])
|
| 463 |
if dts.notna().any():
|
| 464 |
+
df_time = df_out.copy()
|
| 465 |
+
df_time["__dt__"] = dts
|
| 466 |
+
df_time = df_time.dropna(subset=["__dt__"])
|
| 467 |
+
|
| 468 |
+
# ใช้ date preset
|
| 469 |
+
df_time = apply_date_preset(df_time, "__dt__", date_preset)
|
| 470 |
+
|
| 471 |
+
if len(df_time) > 0:
|
| 472 |
+
fig_time = make_time_chart(df_time, "__dt__", freq, use_smooth)
|
| 473 |
+
show_time = True
|
| 474 |
+
|
| 475 |
+
# วิเคราะห์ตาม Shop
|
| 476 |
+
shop_summary_df = pd.DataFrame()
|
| 477 |
+
fig_shop = go.Figure()
|
| 478 |
+
fig_shop_trend = None
|
| 479 |
+
show_shop = False
|
| 480 |
+
|
| 481 |
+
if shop_col and shop_col in cols and shop_col != "ไม่มี":
|
| 482 |
+
df_with_shop = df_out.copy()
|
| 483 |
+
df_with_shop[shop_col] = df_raw[shop_col]
|
| 484 |
+
|
| 485 |
+
# ถ้ามี date ด้วย ให้ใส่เข้าไป
|
| 486 |
+
if date_col and date_col in cols and date_col != "ไม่มี":
|
| 487 |
+
dts = _to_datetime_safe(df_raw[date_col])
|
| 488 |
+
if dts.notna().any():
|
| 489 |
+
df_with_shop["__dt__"] = dts
|
| 490 |
+
df_with_shop = df_with_shop.dropna(subset=["__dt__"])
|
| 491 |
+
df_with_shop = apply_date_preset(df_with_shop, "__dt__", date_preset)
|
| 492 |
+
|
| 493 |
+
shop_summary_df, fig_shop, fig_shop_trend = make_shop_analysis(
|
| 494 |
+
df_with_shop, shop_col, "__dt__", freq
|
| 495 |
+
)
|
| 496 |
+
else:
|
| 497 |
+
shop_summary_df, fig_shop, _ = make_shop_analysis(df_with_shop, shop_col)
|
| 498 |
+
else:
|
| 499 |
+
shop_summary_df, fig_shop, _ = make_shop_analysis(df_with_shop, shop_col)
|
| 500 |
+
|
| 501 |
+
show_shop = True
|
| 502 |
+
|
| 503 |
+
# บันทึกไฟล์
|
| 504 |
+
fd, path = tempfile.mkstemp(suffix=".csv")
|
| 505 |
+
os.close(fd)
|
| 506 |
+
df_out.to_csv(path, index=False, encoding="utf-8-sig")
|
| 507 |
+
|
| 508 |
+
return (df_out, fig_main, fig_time,
|
| 509 |
+
gr.update(visible=show_time, value=fig_time),
|
| 510 |
+
gr.update(visible=show_shop, value=fig_shop),
|
| 511 |
+
shop_summary_df,
|
| 512 |
+
gr.update(visible=show_shop and fig_shop_trend is not None, value=fig_shop_trend),
|
| 513 |
+
info, path)
|
| 514 |
+
|
| 515 |
+
except Exception as e:
|
| 516 |
+
return (pd.DataFrame(), go.Figure(), go.Figure(),
|
| 517 |
+
gr.update(visible=False), gr.update(visible=False),
|
| 518 |
+
pd.DataFrame(), gr.update(visible=False),
|
| 519 |
+
f"❌ เกิดข้อผิดพลาด:\n\n{traceback.format_exc()}", None)
|
| 520 |
|
| 521 |
# ================= Gradio UI =================
|
| 522 |
+
with gr.Blocks(title="Thai Sentiment Analysis", theme=gr.themes.Soft()) as demo:
|
| 523 |
+
gr.Markdown("""
|
| 524 |
+
# 🇹🇭 Thai Sentiment Analysis
|
| 525 |
+
### วิเคราะห์ความรู้สึกรีวิวภาษาไทย (เชิงบวก/เชิงลบ)
|
| 526 |
+
""")
|
| 527 |
+
|
| 528 |
+
model_radio = gr.Radio(
|
| 529 |
+
choices=AVAILABLE_CHOICES,
|
| 530 |
+
value=DEFAULT_MODEL,
|
| 531 |
+
label="🤖 เลือกโมเดล",
|
| 532 |
+
info="แนะนำ: WCB สำหรับความเร็ว, WCB_4Layer_BiLSTM สำหรับความแม่นยำ"
|
| 533 |
+
)
|
| 534 |
|
| 535 |
+
# =================== Tab 1: วิเคราะห์หลายรีวิว ===================
|
| 536 |
+
with gr.Tab("📝 วิเคราะห์หลายรีวิว"):
|
| 537 |
+
gr.Markdown("""
|
| 538 |
+
**วิธีใช้:** ป้อนรีวิวหลายรายการ (แต่ละบรรทัด = 1 รีวิว) แล้วกด "เริ่มวิเคราะห์"
|
| 539 |
+
|
| 540 |
+
**ตัวอย่าง:**
|
| 541 |
+
```
|
| 542 |
+
อาหารอร่อยมาก บริการดีค่ะ
|
| 543 |
+
ของแพงไป รสชาติก็ธรรมดา
|
| 544 |
+
บรรยากาศดี แต่รอนาน
|
| 545 |
+
```
|
| 546 |
+
""")
|
| 547 |
+
|
| 548 |
+
text_input = gr.Textbox(
|
| 549 |
+
lines=10,
|
| 550 |
+
label="📄 ข้อความรีวิว (บรรทัดละ 1 รีวิว)",
|
| 551 |
+
placeholder="ป้อนรีวิวที่ต้องการวิเคราะห์...\nแต่ละบรรทัด = 1 รีวิว"
|
| 552 |
+
)
|
| 553 |
+
|
| 554 |
with gr.Row():
|
| 555 |
+
chart_type_1 = gr.Radio(
|
| 556 |
+
choices=["pie", "bar"],
|
| 557 |
+
value="pie",
|
| 558 |
+
label="📊 รูปแบบกราฟ",
|
| 559 |
+
info="Pie = วงกลม, Bar = แท่ง"
|
| 560 |
+
)
|
| 561 |
+
predict_btn_1 = gr.Button("🚀 เริ่มวิเคราะห์", variant="primary", size="lg")
|
| 562 |
+
|
| 563 |
+
result_df_1 = gr.Dataframe(label="📋 ผลการวิเคราะห์ทั้งหมด")
|
| 564 |
+
|
| 565 |
with gr.Row():
|
| 566 |
+
with gr.Column(scale=1):
|
| 567 |
+
result_chart_1 = gr.Plot(label="📊 กราฟสรุป")
|
| 568 |
+
with gr.Column(scale=1):
|
| 569 |
+
result_info_1 = gr.Markdown()
|
| 570 |
+
|
| 571 |
+
predict_btn_1.click(
|
| 572 |
+
predict_many,
|
| 573 |
+
[text_input, model_radio, chart_type_1],
|
| 574 |
+
[result_df_1, result_chart_1, result_info_1]
|
| 575 |
+
)
|
| 576 |
|
| 577 |
+
# =================== Tab 2: อัปโหลด CSV ===================
|
| 578 |
+
with gr.Tab("📤 อัปโหลด CSV"):
|
| 579 |
+
gr.Markdown("""
|
| 580 |
+
**วิธีใช้:** อัปโหลดไฟล์ CSV ที่มีคอลัมน์รีวิว (และอาจมีวันที่/ร้านด้วย)
|
| 581 |
+
|
| 582 |
+
**คอลัมน์ที่ต้องมี:**
|
| 583 |
+
- ✅ คอลัมน์ข้อความรีวิว (เช่น "text", "review", "รีวิว")
|
| 584 |
+
- ⭐ คอลัมน์วันที่ (optional - สำหรับวิเคราะห์แนวโน้ม)
|
| 585 |
+
- ⭐ คอลัมน์ร้าน/สาขา (optional - สำหรับเปรียบเทียบร้าน)
|
| 586 |
+
""")
|
| 587 |
+
|
| 588 |
+
with gr.Row():
|
| 589 |
+
file_input = gr.File(
|
| 590 |
+
file_types=[".csv"],
|
| 591 |
+
label="📁 อัปโหลดไฟล์ CSV"
|
| 592 |
+
)
|
| 593 |
+
|
| 594 |
+
detect_note = gr.Markdown("⬆️ อัปโหลดไฟล์เพื่อเริ่มต้น")
|
| 595 |
+
|
| 596 |
+
with gr.Row():
|
| 597 |
+
text_col_dd = gr.Dropdown(
|
| 598 |
+
label="📝 คอลัมน์ข้อความรีวิว",
|
| 599 |
+
info="เลือกคอลัมน์ที่มีเนื้อหารีวิว"
|
| 600 |
+
)
|
| 601 |
+
date_col_dd = gr.Dropdown(
|
| 602 |
+
label="📅 คอลัมน์วันที่ (ถ้าไม่มีเว้นว่าง)",
|
| 603 |
+
info="สำหรับวิเคราะห์แนวโน้มตามเวลา"
|
| 604 |
+
)
|
| 605 |
+
shop_col_dd = gr.Dropdown(
|
| 606 |
+
label="🏪 คอลัมน์ร้าน/สาขา (ถ้าไม่มีเว้นว่าง)",
|
| 607 |
+
info="สำหรับเปรียบเทียบแต่ละร้าน"
|
| 608 |
+
)
|
| 609 |
+
|
| 610 |
+
gr.Markdown("### ⚙️ ตั้งค่าการวิเคราะห์")
|
| 611 |
+
|
| 612 |
+
with gr.Row():
|
| 613 |
+
date_preset = gr.Radio(
|
| 614 |
+
choices=list(DATE_PRESETS.keys()),
|
| 615 |
+
value="ทั้งหมด",
|
| 616 |
+
label="📆 ช่วงเวลาที่ต้องการวิเคราะห์",
|
| 617 |
+
visible=False
|
| 618 |
+
)
|
| 619 |
+
|
| 620 |
+
freq = gr.Radio(
|
| 621 |
+
choices=[("รายวัน", "D"), ("รายสัปดาห์", "W"), ("รายเดือน", "M")],
|
| 622 |
+
value="D",
|
| 623 |
+
label="📊 ความละเอียดของกราฟ",
|
| 624 |
+
visible=False
|
| 625 |
+
)
|
| 626 |
+
|
| 627 |
+
with gr.Row():
|
| 628 |
+
use_smooth = gr.Checkbox(
|
| 629 |
+
value=True,
|
| 630 |
+
label="✨ ปรับกราฟให้เรียบ (Moving Average)",
|
| 631 |
+
info="ช่วยให้เห็นแนวโน้มชัดเจนขึ้น",
|
| 632 |
+
visible=False
|
| 633 |
+
)
|
| 634 |
+
|
| 635 |
+
chart_type_2 = gr.Radio(
|
| 636 |
+
choices=[("วงกลม", "pie"), ("แท่ง", "bar")],
|
| 637 |
+
value="pie",
|
| 638 |
+
label="📊 รูปแบบกราฟสรุป"
|
| 639 |
+
)
|
| 640 |
+
|
| 641 |
+
shop_analysis_row = gr.Row(visible=False)
|
| 642 |
+
shop_trend_row = gr.Row(visible=False)
|
| 643 |
+
|
| 644 |
+
predict_btn_2 = gr.Button("🚀 เริ่มวิเคราะห์ CSV", variant="primary", size="lg")
|
| 645 |
+
|
| 646 |
+
gr.Markdown("### 📊 ผลการวิเคราะห์")
|
| 647 |
+
|
| 648 |
+
result_df_2 = gr.Dataframe(label="📋 ผลการวิเคราะห์ทั้งหมด")
|
| 649 |
+
|
| 650 |
+
with gr.Row():
|
| 651 |
+
with gr.Column(scale=1):
|
| 652 |
+
result_chart_2 = gr.Plot(label="📊 กราฟสรุปภาพรวม")
|
| 653 |
+
with gr.Column(scale=1):
|
| 654 |
+
result_info_2 = gr.Markdown()
|
| 655 |
+
|
| 656 |
+
result_time = gr.Plot(label="📈 กราฟแนวโน้มตามเวลา", visible=False)
|
| 657 |
+
|
| 658 |
+
with shop_analysis_row:
|
| 659 |
+
gr.Markdown("### 🏪 วิเคราะห์แยกตามร้าน/สาขา")
|
| 660 |
+
|
| 661 |
+
shop_summary = gr.Dataframe(label="📊 สรุปแต่ละร้าน")
|
| 662 |
+
result_shop = gr.Plot(label="🏪 เปรียบเทียบรีวิวแต่ละร้าน", visible=False)
|
| 663 |
+
|
| 664 |
+
with shop_trend_row:
|
| 665 |
+
result_shop_trend = gr.Plot(label="📈 แนวโน้ม % เชิงบวกแยกตามร้าน", visible=False)
|
| 666 |
+
|
| 667 |
+
download_file = gr.File(label="💾 ดาวน์โหลดผลลัพธ์ (CSV)")
|
| 668 |
+
|
| 669 |
+
# Event handlers
|
| 670 |
+
file_input.change(
|
| 671 |
+
on_file_change,
|
| 672 |
+
[file_input],
|
| 673 |
+
[text_col_dd, date_col_dd, shop_col_dd,
|
| 674 |
+
date_preset, freq, use_smooth,
|
| 675 |
+
shop_analysis_row, detect_note]
|
| 676 |
+
)
|
| 677 |
+
|
| 678 |
+
predict_btn_2.click(
|
| 679 |
+
predict_csv,
|
| 680 |
+
[file_input, model_radio, text_col_dd, date_col_dd, shop_col_dd,
|
| 681 |
+
date_preset, freq, use_smooth, chart_type_2],
|
| 682 |
+
[result_df_2, result_chart_2, result_time,
|
| 683 |
+
result_time, result_shop,
|
| 684 |
+
shop_summary, result_shop_trend,
|
| 685 |
+
result_info_2, download_file]
|
| 686 |
+
)
|
| 687 |
+
|
| 688 |
+
gr.Markdown("""
|
| 689 |
+
---
|
| 690 |
+
### 💡 เกี่ยวกับโมเดล
|
| 691 |
+
|
| 692 |
+
**WangchanBERTa Variants** - โมเดล BERT ภาษาไทยที่ได้รับการฝึกสำหรับงานวิเคราะห์ความรู้สึก
|
| 693 |
+
|
| 694 |
+
- **WCB**: เร็ว เหมาะกับงานทั่วไป
|
| 695 |
+
- **WCB_BiLSTM**: เพิ่มความแม่นยำด้วย BiLSTM
|
| 696 |
+
- **WCB_CNN_BiLSTM**: ใช้ CNN + BiLSTM เพิ่มประสิทธิภาพ
|
| 697 |
+
- **WCB_4Layer_BiLSTM**: แม่นยำสูงสุด แต่ช้ากว่า
|
| 698 |
+
|
| 699 |
+
📌 **หมายเหตุ:** โมเดลวิเคราะห์เฉพาะ **เชิงบวก/เชิงลบ** เท่านั้น (ไม่มี neutral)
|
| 700 |
+
""")
|
| 701 |
|
| 702 |
+
if __name__ == "__main__":
|
| 703 |
+
demo.launch()
|