Update app.py

app.py

@@ -1,9 +1,9 @@
 # app.py — Thai Sentiment (WangchanBERTa Variants)
 # - No Single tab
 # - No aspect analysis (focus on POS/NEG)
-# - CSV tab: date pickers appear ONLY if a date column exists
+# - CSV tab: date pickers appear ONLY if a date column exists (use DatePicker)
 # - Predict buttons right below inputs
-import os, json, importlib.util, traceback, re, math, tempfile
+import os, json, importlib.util, traceback, re, math, tempfile, datetime
 import gradio as gr
 import torch, pandas as pd
 import torch.nn.functional as F
@@ -86,6 +86,19 @@ def _format_pct(x: float) -> str:
 def _to_datetime_safe(s):
     return pd.to_datetime(s, errors="coerce", infer_datetime_format=True, utc=False)
 
+def _normalize_datepicker_value(v):
+    """รับค่าจาก gr.DatePicker (datetime.date หรือ str หรือ None) → pandas.Timestamp หรือ None"""
+    if v is None or (isinstance(v, float) and math.isnan(v)):
+        return None
+    if isinstance(v, datetime.date):
+        return pd.Timestamp(v)
+    # เผื่อบางเวอร์ชันส่ง str 'YYYY-MM-DD'
+    try:
+        ts = pd.to_datetime(v, errors="coerce")
+        return ts if pd.notna(ts) else None
+    except Exception:
+        return None
+
 LIKELY_TEXT_COLS = ["text","review","message","comment","content","sentence","body","ข้อความ","รีวิว"]
 LIKELY_DATE_COLS = ["date","created_at","time","timestamp","datetime","วันที่","วันเวลา","เวลา"]
 
@@ -107,11 +120,9 @@ def detect_text_and_date_cols(df: pd.DataFrame):
         if c.lower() in LIKELY_DATE_COLS:
             date_candidates.append(c)
             continue
-        # try parse sample
         sample = df[c].head(50)
         if _to_datetime_safe(sample).notna().sum() >= max(3, int(len(sample)*0.2)):
             date_candidates.append(c)
-
     date_candidates = list(dict.fromkeys(date_candidates))
     date_col = date_candidates[0] if len(date_candidates)>0 else None
     return text_col, date_candidates, date_col
@@ -223,7 +234,6 @@ def on_file_change(file_obj):
     - toggle visibility ของ date controls + line chart placeholder
     """
     if file_obj is None:
-        # reset UI
         return (
             gr.update(choices=[], value=None),   # text_dd
             gr.update(choices=[], value=None),   # date_dd
@@ -240,7 +250,6 @@ def on_file_change(file_obj):
         cols = list(df_raw.columns)
         text_col, date_candidates, date_col = detect_text_and_date_cols(df_raw)
 
-        # show/hide date controls
         has_date = date_col is not None
         note = "Detected text column: **{}**".format(text_col)
         if has_date:
@@ -273,7 +282,7 @@ def on_file_change(file_obj):
 
 # ================= CSV Predict =================
 def predict_csv(file_obj, model_choice: str, text_col_name: str,
-                date_col_name: str, date_from: str, date_to: str,
+                date_col_name: str, date_from, date_to,
                 freq_choice: str, use_ma: bool):
 
     try:
@@ -281,8 +290,8 @@ def predict_csv(file_obj, model_choice: str, text_col_name: str,
             return pd.DataFrame(), go.Figure(), go.Figure(), gr.update(visible=False, value=go.Figure()), "Please upload a CSV.", None
 
         df_raw = pd.read_csv(file_obj.name)
-
         cols = list(df_raw.columns)
+
         col_text = text_col_name if text_col_name in cols else detect_text_and_date_cols(df_raw)[0]
 
         texts = [_norm_text(v) for v in df_raw[col_text].tolist()]
@@ -306,11 +315,16 @@ def predict_csv(file_obj, model_choice: str, text_col_name: str,
                 df_time = out_df.copy()
                 df_time["__dt__"] = dts
                 df_time = df_time.dropna(subset=["__dt__"])
-                # filter range if chosen
-                if date_from:
-                    df_time = df_time[df_time["__dt__"] >= pd.to_datetime(date_from)]
-                if date_to:
-                    df_time = df_time[df_time["__dt__"] <= pd.to_datetime(date_to)]
+
+                # normalize datepicker values
+                start_ts = _normalize_datepicker_value(date_from)
+                end_ts   = _normalize_datepicker_value(date_to)
+
+                if start_ts is not None:
+                    df_time = df_time[df_time["__dt__"] >= start_ts]
+                if end_ts is not None:
+                    df_time = df_time[df_time["__dt__"] <= end_ts]
+
                 if len(df_time) > 0:
                     fig_line = make_time_chart(df_time, "__dt__", freq_choice, use_ma)
                     show_time = True
@@ -350,7 +364,6 @@ with gr.Blocks(title="Thai Sentiment (WangchanBERTa Variants)") as demo:
         bar2 = gr.Plot(label="Label counts (bar)")
         pie2 = gr.Plot(label="Positive vs Negative (pie)")
         sum2 = gr.Markdown()
-
         btn_batch.click(predict_many, [t2, model_radio], [df2, bar2, pie2, sum2])
 
     # ---- CSV Upload ----
@@ -360,8 +373,9 @@ with gr.Blocks(title="Thai Sentiment (WangchanBERTa Variants)") as demo:
             text_dd = gr.Dropdown(label="คอ���ัมน์ข้อความ", choices=[], value=None)
             date_dd = gr.Dropdown(label="คอลัมน์วันเวลา (ถ้ามี)", choices=[], value=None)
         with gr.Row():
-            date_from = gr.Date(label="เริ่มวันที่", visible=False)
-            date_to   = gr.Date(label="ถึงวันที่", visible=False)
+            # ใช้ DatePicker แทน Date (รองรับ gradio เวอร์ชันที่ไม่เคยมี gr.Date)
+            date_from = gr.DatePicker(label="เริ่มวันที่", visible=False)
+            date_to   = gr.DatePicker(label="ถึงวันที่", visible=False)
             freq      = gr.Radio(choices=["D","W","M"], value="D", label="ความถี่ (Day/Week/Month)", visible=False)
             use_ma    = gr.Checkbox(value=True, label="Moving average (7/4/3)", visible=False)
 
@@ -375,13 +389,11 @@ with gr.Blocks(title="Thai Sentiment (WangchanBERTa Variants)") as demo:
         sum3 = gr.Markdown()
         dl3  = gr.File(label="ดาวน์โหลดผลเป็น CSV", interactive=False)
 
-        # เมื่ออัปโหลดไฟล์ → เติม dropdowns + toggle date controls + เคลียร์ผลลัพธ์เก่า
         file_in.change(
             on_file_change, [file_in],
             [text_dd, date_dd, date_from, date_to, freq, use_ma, line, note_detect]
         )
 
-        # ปุ่ม predict CSV อยู่ใต้ตัวกรอง (ใกล้มือ)
         btn_csv.click(
             predict_csv,
             [file_in, model_radio, text_dd, date_dd, date_from, date_to, freq, use_ma],