"""
sentiment_page.py
=================
PERBAIKAN: Hapus parameter key= dari semua st.container() karena tidak
didukung di Streamlit versi lama. CSS styling tetap berjalan via class HTML.
"""
import streamlit as st
import pandas as pd
import numpy as np
import os
import re
import string
from collections import Counter
from datetime import datetime, timedelta
from html import escape
from database import engine, get_tweet_count, get_latest_crawl_time
from timezone_utils import (
parse_dt_with_tz,
parse_dt_with_source_tz,
get_timezone_label,
get_timezone_name,
)
import plotly.graph_objects as go
from sentiment_service import (
preprocess_for_model,
preprocess_untuk_lexicon,
_hitung_skor_lexicon,
_klasifikasi_hybrid,
_load_stopwords,
_load_stemmer,
_STOPWORDS,
_STEMMER,
)
from page_modules.table_utils import render_standard_table
# ─────────────────────────────────────────────────────────────
# Timezone & formatting helpers
# ─────────────────────────────────────────────────────────────
def parse_dt(series):
return parse_dt_with_tz(series, st.session_state.get("user_timezone", "WIB (UTC+7)"))
def parse_crawled_dt(series):
return parse_dt_with_source_tz(
series,
st.session_state.get("user_timezone", "WIB (UTC+7)"),
os.getenv("APP_TIMEZONE", "Asia/Makassar"),
)
def format_dt(value):
if value is None or pd.isna(value):
return "Belum ada"
try:
tz_label = get_timezone_label(st.session_state.get("user_timezone", "WIB (UTC+7)"))
return f"{value.strftime('%d/%m/%Y %H:%M')} {tz_label}"
except Exception:
return "Belum ada"
def format_now():
now = parse_dt(pd.Series([datetime.utcnow().isoformat()])).iloc[0]
return format_dt(now)
def user_today():
timezone_choice = st.session_state.get("user_timezone", "WIB (UTC+7)")
return pd.Timestamp.now(tz=get_timezone_name(timezone_choice)).date()
def _sync_dynamic_period():
mode = st.session_state.get("analysis_mode")
today = user_today()
configs = {
"realtime": (today - timedelta(days=6), today, "Tweet Terkini — 7 Hari Terakhir"),
"30days": (today - timedelta(days=29), today, "30 Hari Terakhir"),
"captured": (today, today, "Tweet Hari Ini"),
}
if mode not in configs:
return
start_day, end_day, mode_display = configs[mode]
start_day = pd.Timestamp(start_day).date()
end_day = pd.Timestamp(end_day).date()
dt_start = datetime.combine(start_day, datetime.min.time())
dt_end = datetime.combine(end_day + timedelta(days=1), datetime.min.time())
st.session_state.filter_start_date = dt_start
st.session_state.filter_end_date = dt_end
st.session_state.filter_label = f"{dt_start.strftime('%d/%m/%Y')} s/d {end_day.strftime('%d/%m/%Y')}"
st.session_state.mode_display = mode_display
st.session_state.filter_date_column = "created_at"
# ─────────────────────────────────────────────────────────────
# Core prediction
# ─────────────────────────────────────────────────────────────
def predict_batch_hybrid(texts):
results = []
for text in texts:
teks_model = preprocess_for_model(text)
teks_lexicon = preprocess_untuk_lexicon(text)
teks_lower = str(text).lower()
skor = _hitung_skor_lexicon(teks_lexicon)
label, conf = _klasifikasi_hybrid(teks_model, skor, teks_lower)
results.append((label, conf))
return results
def preprocess_single(text):
return preprocess_for_model(text)
# ─────────────────────────────────────────────────────────────
# UI helpers
# ─────────────────────────────────────────────────────────────
def _section_header(title, subtitle=""):
sub_html = (
f'{subtitle}
'
if subtitle else ""
)
st.markdown(
f''
f'
{title}
'
f'{sub_html}
',
unsafe_allow_html=True,
)
def _card_close():
st.markdown('
', unsafe_allow_html=True)
def _render_sentiment_styles():
st.markdown("""
""", unsafe_allow_html=True)
# ─────────────────────────────────────────────────────────────
# Page Header
# ─────────────────────────────────────────────────────────────
def _render_page_header():
st.markdown("""
""", unsafe_allow_html=True)
# ─────────────────────────────────────────────────────────────
# Summary Pills
# ─────────────────────────────────────────────────────────────
def _render_summary_pills(total, pos_n, neu_n, neg_n, pos_p, neu_p, neg_p, filter_label):
pills = [
("stat-1", "📊", "linear-gradient(135deg,#eef2ff,#e0e7ff)", "#3b6cf7", "#1e3a8a", "#c7d2fe",
"Total Dianalisis", f"{total:,}", f"Periode {filter_label}"),
("stat-2", "😊", "linear-gradient(135deg,#f0fdf4,#dcfce7)", "#16a34a", "#14532d", "#86efac",
"Positif", f"{pos_n:,}", f"{pos_p:.1f}% dari total"),
("stat-3", "😐", "linear-gradient(135deg,#f8fafc,#f1f5f9)", "#64748b", "#334155", "#cbd5e1",
"Netral", f"{neu_n:,}", f"{neu_p:.1f}% dari total"),
("stat-4", "😞", "linear-gradient(135deg,#fef2f2,#fee2e2)", "#ef4444", "#7f1d1d", "#fca5a5",
"Negatif", f"{neg_n:,}", f"{neg_p:.1f}% dari total"),
]
cols = st.columns(4, gap="medium")
for col, (anim, icon, bg, color, dark, border, label, val, sub) in zip(cols, pills):
fs = "1.6rem" if len(str(val)) <= 6 else "1.2rem"
with col:
st.markdown(
f''
f'
{icon}
'
f'
{label}
'
f'
{val}
'
f'
{sub}
'
f'
'
f'
Proporsi Sentimen Keseluruhan
'
f'
'
f'
'
f'{"😊 " + str(pos_p) + "%" if pos_p >= 8 else ""}
'
f'
'
f'{"😐 " + str(neu_p) + "%" if neu_p >= 8 else ""}
'
f'
'
f'{"😞 " + str(neg_p) + "%" if neg_p >= 8 else ""}
'
f'
'
f'
'
f'● Positif {pos_p}%'
f'● Netral {neu_p}%'
f'● Negatif {neg_p}%'
f'
%{value:,} tweet — %{percent}",
direction="clockwise", sort=False,
)])
fig.add_annotation(
text=f"{dom_pct}%
{dom_emoji} {dominant[0]}",
x=0.5, y=0.5, showarrow=False, align="center", font=dict(size=18, color="#0f172a"),
)
fig.update_layout(
height=290, margin=dict(l=10, r=10, t=10, b=10),
showlegend=True,
legend=dict(orientation="h", y=-0.1, x=0.5, xanchor="center", font=dict(size=11)),
paper_bgcolor="rgba(0,0,0,0)",
)
st.plotly_chart(fig, use_container_width=True, config={"displayModeBar": False})
return dominant
def _render_bar_chart(pos_n, neu_n, neg_n, total):
categories = ["Positif 😊", "Netral 😐", "Negatif 😞"]
values = [pos_n, neu_n, neg_n]
colors = ["#16a34a", "#94a3b8", "#ef4444"]
percentages = [(v / total * 100) if total > 0 else 0 for v in values]
fig = go.Figure()
for cat, val, color, pct in zip(categories, values, colors, percentages):
fig.add_trace(go.Bar(
x=[cat], y=[val],
marker=dict(color=color, opacity=0.88, cornerradius=8),
text=[f"{val:,}"], textposition="outside",
textfont=dict(size=13, color="#0f172a"), width=0.5,
hovertemplate=f"{cat}
{val:,} tweet ({pct:.1f}%)",
))
fig.update_layout(
height=290, margin=dict(l=0, r=0, t=30, b=0),
paper_bgcolor="rgba(0,0,0,0)", plot_bgcolor="rgba(0,0,0,0)",
showlegend=False,
xaxis=dict(showgrid=False, tickfont=dict(size=11, color="#64748b")),
yaxis=dict(showgrid=True, gridcolor="rgba(226,232,240,0.8)", griddash="dot",
tickfont=dict(size=10, color="#94a3b8")),
)
st.plotly_chart(fig, use_container_width=True, config={"displayModeBar": False})
# ─────────────────────────────────────────────────────────────
# Trend chart
# ─────────────────────────────────────────────────────────────
def _render_trend_chart(fdf, filter_label, dt_start, dt_end):
_section_header(
"📅 Tren Sentimen dari Hari ke Hari",
f"Periode {filter_label} · Diupdate: {format_now()}"
)
df_tl = fdf.copy()
df_tl["date"] = pd.to_datetime(df_tl["created_at"], errors="coerce").dt.date
actual_tl = df_tl.groupby(["date", "sentiment"]).size().reset_index(name="count")
date_range = pd.date_range(pd.Timestamp(dt_start).date(), pd.Timestamp(dt_end).date(), freq="D")
base_dates = pd.DataFrame({"date": date_range.date})
fig = go.Figure()
config_lines = [
("Positif", "#16a34a", "rgba(22,163,74,0.08)"),
("Netral", "#94a3b8", "rgba(148,163,184,0.06)"),
("Negatif", "#ef4444", "rgba(239,68,68,0.08)"),
]
for sent, color, fill in config_lines:
data = base_dates.merge(
actual_tl[actual_tl["sentiment"] == sent][["date", "count"]],
on="date", how="left",
)
data["count"] = data["count"].fillna(0).astype(int)
fig.add_trace(go.Scatter(
x=data["date"], y=data["count"], name=sent,
mode="lines+markers",
line=dict(color=color, width=2.5, shape="spline", smoothing=0.8),
marker=dict(size=6, color="white", line=dict(color=color, width=2.5)),
fill="tozeroy", fillcolor=fill,
hovertemplate=f"{sent}
%{{x}}: %{{y}} tweet",
))
fig.update_layout(
height=290, margin=dict(l=0, r=0, t=10, b=0),
paper_bgcolor="rgba(0,0,0,0)", plot_bgcolor="rgba(0,0,0,0)",
legend=dict(orientation="h", y=1.1, x=0, font=dict(size=11)),
xaxis=dict(showgrid=True, gridcolor="rgba(226,232,240,0.6)",
tickfont=dict(size=10, color="#94a3b8")),
yaxis=dict(showgrid=True, gridcolor="rgba(226,232,240,0.6)", griddash="dot",
tickfont=dict(size=10, color="#94a3b8")),
hovermode="x unified",
)
# ─── PERBAIKAN: hapus key= dari st.container() ───
with st.container():
st.plotly_chart(fig, use_container_width=True, config={"displayModeBar": False})
# ─────────────────────────────────────────────────────────────
# Word frequency per sentimen
# ─────────────────────────────────────────────────────────────
def _render_word_freq_per_sentiment(fdf):
_section_header(
"📊 Kata Dominan per Sentimen",
"Top 15 kata paling sering muncul di masing-masing kelompok sentimen"
)
stop_extra = {"ongkos", "kirim", "gratis", "komdigi", "ongkir"}
sent_cfg = [
("Positif", "#16a34a", "#1e3a8a"),
("Netral", "#64748b", "#334155"),
("Negatif", "#ef4444", "#7f1d1d"),
]
cols = st.columns(3, gap="medium")
for col, (sent, color, dark) in zip(cols, sent_cfg):
with col:
sub = fdf[fdf["sentiment"] == sent]
all_words = " ".join(sub["clean_text"].fillna("")).split()
filtered = [w for w in all_words if len(w) > 2 and w not in stop_extra]
wf = Counter(filtered).most_common(15)
st.markdown(
f''
f'
'
f'
'
f'{"😊" if sent=="Positif" else "😐" if sent=="Netral" else "😞"}
'
f'
{sent}
'
f'
'
f'{len(sub):,} tweet
'
f'
',
unsafe_allow_html=True,
)
if not wf:
st.info("Belum ada data")
st.markdown('
%{x} kali",
)])
fig.update_layout(
height=360, margin=dict(l=0, r=40, t=4, b=4),
paper_bgcolor="rgba(0,0,0,0)", plot_bgcolor="rgba(0,0,0,0)",
showlegend=False,
xaxis=dict(showgrid=True, gridcolor="rgba(203,213,225,0.6)",
tickfont=dict(size=8, color="#94a3b8"), fixedrange=True),
yaxis=dict(showgrid=False, tickfont=dict(size=9, color="#334155"), fixedrange=True),
)
st.plotly_chart(fig, use_container_width=True, config={"displayModeBar": False})
st.markdown('', unsafe_allow_html=True)
# ─────────────────────────────────────────────────────────────
# Word cloud
# ─────────────────────────────────────────────────────────────
def _render_wordcloud(fdf):
_section_header(
"☁️ Word Cloud per Sentimen",
"Kata-kata populer dari tweet yang sudah melalui preprocessing"
)
try:
from wordcloud import WordCloud
import matplotlib.pyplot as plt
stop_wc = {"ongkos", "kirim", "gratis", "komdigi", "ongkir"}
wc1, wc2, wc3 = st.columns(3, gap="medium")
cfg = [
(wc1, "Positif", "Greens", "😊 Positif", "#f0fdf4", "#14532d"),
(wc2, "Netral", "Blues", "😐 Netral", "#f8fafc", "#334155"),
(wc3, "Negatif", "Reds", "😞 Negatif", "#fef2f2", "#7f1d1d"),
]
for col, sent, cmap, title, bg, tc in cfg:
with col:
st.markdown(
f''
f'{title}
',
unsafe_allow_html=True,
)
sub = fdf[fdf["sentiment"] == sent]
words = [w for w in " ".join(sub["clean_text"].fillna("")).split()
if len(w) > 2 and w not in stop_wc]
if words:
wc = WordCloud(
width=420, height=260, background_color="white",
colormap=cmap, max_words=60,
relative_scaling=0.5, collocations=False,
).generate(" ".join(words))
fig, ax = plt.subplots(figsize=(5, 3.1))
ax.imshow(wc, interpolation="bilinear")
ax.axis("off")
plt.tight_layout(pad=0)
st.pyplot(fig, clear_figure=True)
else:
st.info("Data kata tidak cukup")
except ImportError:
st.warning("Install `wordcloud` dan `matplotlib` terlebih dahulu.")
# ─────────────────────────────────────────────────────────────
# Tweet table
# ─────────────────────────────────────────────────────────────
def _render_tweet_table(fdf, filter_label):
_section_header(
"📋 Tabel Analisis Sentimen",
f"Total {len(fdf):,} tweet · {filter_label}"
)
# ─── PERBAIKAN: ganti st.container(key=) dengan st.columns biasa ───
tf1, tf2, tf3 = st.columns([3, 1.6, 1.7], gap="medium")
with tf1:
search = st.text_input(
"🔍 Cari tweet", placeholder="Ketik kata kunci di isi tweet...",
key="sentiment_table_search",
)
with tf2:
sf = st.selectbox(
"Filter sentimen",
["Semua", "Positif 😊", "Netral 😐", "Negatif 😞"],
key="sentiment_table_filter",
)
with tf3:
sort_by = st.selectbox(
"Urutkan",
["Terbaru dulu", "Terlama dulu", "Keyakinan tertinggi"],
key="sentiment_table_sort",
)
_section_gap("sm")
tdf = fdf.copy()
if "crawled_at" not in tdf.columns:
tdf["crawled_at"] = pd.NaT
if search:
tdf = tdf[tdf["text"].str.contains(search, case=False, na=False)]
sf_map = {"Positif 😊": "Positif", "Netral 😐": "Netral", "Negatif 😞": "Negatif"}
if sf != "Semua":
tdf = tdf[tdf["sentiment"] == sf_map.get(sf, sf)]
if sort_by == "Terbaru dulu":
tdf = tdf.sort_values("created_at", ascending=False)
elif sort_by == "Terlama dulu":
tdf = tdf.sort_values("created_at", ascending=True)
else:
tdf = tdf.sort_values("confidence", ascending=False)
out = tdf[["created_at", "crawled_at", "text", "clean_text", "sentiment"]].copy()
out["created_at"] = out["created_at"].apply(format_dt)
out["crawled_at"] = out["crawled_at"].apply(format_dt)
out["sentiment"] = out["sentiment"].map({
"Positif": "😊 Positif", "Netral": "😐 Netral", "Negatif": "😞 Negatif",
}).fillna(out["sentiment"])
out.columns = ["Tanggal Tweet", "Masuk Database", "Tweet Asli", "Tweet Bersih", "Sentimen"]
render_standard_table(
out, height=400, min_width=1220,
badge_columns=["Sentimen"],
nowrap=["Tanggal Tweet", "Masuk Database", "Sentimen"],
wide_columns=["Tweet Asli", "Tweet Bersih"],
column_widths={
"Tanggal Tweet": "170px", "Masuk Database": "170px",
"Tweet Asli": "360px", "Tweet Bersih": "360px",
"Sentimen": "130px",
},
)
st.caption(f"Menampilkan {len(tdf):,} tweet")
return tdf
# ─────────────────────────────────────────────────────────────
# Insight & Recommendation
# ─────────────────────────────────────────────────────────────
def _render_insight_panel(dominant, pos_n, neu_n, neg_n, total, filter_label):
dom_name = dominant[0]
dom_pct = dominant[1] / total * 100 if total else 0
neg_pct = neg_n / total * 100 if total else 0
pos_pct = pos_n / total * 100 if total else 0
neu_pct = neu_n / total * 100 if total else 0
_section_header(
"💡 Insight & Rekomendasi Tindakan",
f"Berdasarkan analisis {total:,} tweet · {filter_label}"
)
dom_color = {"Positif": "#16a34a", "Netral": "#64748b", "Negatif": "#ef4444"}.get(dom_name, "#3b6cf7")
dom_bg = {"Positif": "#f0fdf4", "Netral": "#f8fafc", "Negatif": "#fef2f2"}.get(dom_name, "#eef2ff")
dom_emoji = {"Positif": "😊", "Netral": "😐", "Negatif": "😞"}.get(dom_name, "📊")
st.markdown(
f''
f'
'
f'
{dom_emoji}
'
f'
'
f'
Sentimen Dominan
'
f'
'
f'{dom_name} · {dom_pct:.1f}%
'
f'
'
f'
'
f'Positif: {pos_pct:.1f}% · '
f'Netral: {neu_pct:.1f}% · '
f'Negatif: {neg_pct:.1f}%'
f'
'
f'
'
f'
'
f'{row.Prioritas}
'
f'
'
f'
'
f'{row.Tindakan}
'
f'
'
f'📌 {row["Dasar Analisis"]}
'
f'
'
f'✅ {row.Rekomendasi}
'
f'
'
f'
'
f''
f'👤 {row["Penanggung Jawab"]}
'
f'
'
f'
{mode_icon}'
f'
'
f'
{mode_display}
'
f'
'
f'Periode: {filter_label}
'
f'
'
f''
f'Mode {escape(str(mode_display))}'
f''
f'Periode {escape(str(filter_label))}'
f'
',
unsafe_allow_html=True,
)
_section_gap("sm")
fdf = (
df_s[df_s["text"].str.contains(kw, case=False, na=False)].copy()
if kw else df_s.copy()
)
if fdf.empty:
st.warning("⚠️ Tidak ada tweet yang cocok dengan kata kunci tersebut.")
return
sc = fdf["sentiment"].value_counts()
total = len(fdf)
pos_n = int(sc.get("Positif", 0))
neu_n = int(sc.get("Netral", 0))
neg_n = int(sc.get("Negatif", 0))
pos_p = pos_n / total * 100
neu_p = neu_n / total * 100
neg_p = neg_n / total * 100
# ── Ringkasan ─────────────────────────────────────────────
_section_header(
"📌 Ringkasan Sentimen",
f"Berdasarkan tanggal asli tweet · {filter_label}"
)
_section_gap("sm")
_render_summary_pills(total, pos_n, neu_n, neg_n, pos_p, neu_p, neg_p, filter_label)
_section_gap("sm")
_render_proportion_bar(pos_p, neu_p, neg_p)
_section_gap("lg")
# ── Donut + Bar ───────────────────────────────────────────
col_left, col_right = st.columns(2, gap="medium")
with col_left:
_section_header("🔵 Sebaran Sentimen", f"Periode {filter_label}")
# ─── PERBAIKAN: hapus key= dari st.container() ───
with st.container():
dominant = _render_donut_chart(pos_n, neu_n, neg_n, total, filter_label)
with col_right:
_section_header("📊 Perbandingan Jumlah per Sentimen", f"Periode {filter_label}")
with st.container():
_render_bar_chart(pos_n, neu_n, neg_n, total)
_section_gap("lg")
# ── Trend ─────────────────────────────────────────────────
_render_trend_chart(fdf, filter_label, start_date, end_date)
_section_gap("lg")
# ── Word freq ─────────────────────────────────────────────
_render_word_freq_per_sentiment(fdf)
_section_gap("lg")
# ── Word cloud ────────────────────────────────────────────
_render_wordcloud(fdf)
_section_gap("lg")
# ── Tweet table ───────────────────────────────────────────
tdf = _render_tweet_table(fdf, filter_label)
_section_gap("lg")
# ── Insight ───────────────────────────────────────────────
df_rek = _render_insight_panel(dominant, pos_n, neu_n, neg_n, total, filter_label)
_section_gap("lg")
# ── Download ──────────────────────────────────────────────
_section_header("📥 Unduh Hasil Analisis")
# ─── PERBAIKAN: hapus key= dari st.container() ───
with st.container():
d1, d2, d3 = st.columns(3, gap="medium")
with d1:
st.download_button(
"📥 Semua Hasil Prediksi",
fdf.to_csv(index=False).encode("utf-8"),
f"hasil_prediksi_{datetime.now().strftime('%Y%m%d_%H%M')}.csv",
"text/csv",
use_container_width=True,
)
with d2:
summary = pd.DataFrame({
"Sentimen": ["Positif", "Netral", "Negatif"],
"Jumlah": [pos_n, neu_n, neg_n],
"Persen": [f"{pos_p:.2f}%", f"{neu_p:.2f}%", f"{neg_p:.2f}%"],
})
st.download_button(
"📈 Ringkasan Sentimen",
summary.to_csv(index=False).encode("utf-8"),
f"ringkasan_{datetime.now().strftime('%Y%m%d_%H%M')}.csv",
"text/csv",
use_container_width=True,
)
with d3:
st.download_button(
"🎯 Rekomendasi Tindakan",
df_rek.to_csv(index=False).encode("utf-8"),
f"rekomendasi_{datetime.now().strftime('%Y%m%d_%H%M')}.csv",
"text/csv",
use_container_width=True,
)