Spaces:
Running
Running
File size: 17,942 Bytes
1acd6e1 dc2be38 0f95c64 1acd6e1 dc2be38 0f95c64 4fb476c 0f95c64 4fb476c dc2be38 828f0f0 3268778 4a31bd8 3268778 4a31bd8 3268778 828f0f0 3268778 828f0f0 4a31bd8 828f0f0 4a31bd8 828f0f0 4a31bd8 0f95c64 828f0f0 4a31bd8 828f0f0 4a31bd8 828f0f0 3268778 4a31bd8 1acd6e1 dc2be38 4a31bd8 0f95c64 dc2be38 3268778 4a31bd8 1acd6e1 4a31bd8 0f95c64 1acd6e1 dd6e62d 0f95c64 dd6e62d 0f95c64 dd6e62d 0f95c64 1acd6e1 dc2be38 0f95c64 dc2be38 1acd6e1 dc2be38 1acd6e1 dc2be38 1acd6e1 dc2be38 1acd6e1 dc2be38 4a31bd8 dc2be38 0f95c64 dd6e62d 0f95c64 dd6e62d 0f95c64 dd6e62d 0f95c64 dd6e62d 0f95c64 dd6e62d 0f95c64 dd6e62d 0f95c64 dd6e62d 1acd6e1 3268778 4a31bd8 3268778 dc2be38 3268778 0f95c64 dd6e62d 0f95c64 dd6e62d 0f95c64 dd6e62d 0f95c64 dd6e62d 1acd6e1 3268778 dc2be38 dd6e62d 0f95c64 dd6e62d dc2be38 3268778 dc2be38 dd6e62d 0f95c64 dd6e62d 0f95c64 dd6e62d 0f95c64 dd6e62d 0f95c64 dd6e62d 0f95c64 dd6e62d 0f95c64 762f595 0f95c64 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 |
import streamlit as st
import pandas as pd
import numpy as np
from prophet import Prophet
import plotly.express as px
import seaborn as sns
import matplotlib.pyplot as plt
from datetime import date
from pathlib import Path
import matplotlib.font_manager as fm
import matplotlib as mpl
# -------------------------------------------------
# CONFIG ------------------------------------------
# -------------------------------------------------
CSV_PATH = Path("price_data.csv")
PARQUET_PATH = Path("domae-202503.parquet")
MACRO_START, MACRO_END = "1996-01-01", "2030-12-31"
MICRO_START, MICRO_END = "2020-01-01", "2026-12-31"
# ํ๊ธ ํฐํธ ์ค์
# 1. ์์คํ
์ ์ค์น๋ ํ๊ธ ํฐํธ ์ฐพ๊ธฐ
font_list = [f.name for f in fm.fontManager.ttflist if 'gothic' in f.name.lower() or
'gulim' in f.name.lower() or 'malgun' in f.name.lower() or
'nanum' in f.name.lower() or 'batang' in f.name.lower()]
if font_list:
font_name = font_list[0]
plt.rcParams['font.family'] = font_name
mpl.rcParams['axes.unicode_minus'] = False
else:
# ํฐํธ๊ฐ ์์ ๊ฒฝ์ฐ ๊ธฐ๋ณธ ํฐํธ ์ค์
plt.rcParams['font.family'] = 'DejaVu Sans'
st.set_page_config(page_title="ํ๋ชฉ๋ณ ๊ฐ๊ฒฉ ์์ธก", page_icon="๐", layout="wide")
# -------------------------------------------------
# UTILITIES ---------------------------------------
# -------------------------------------------------
DATE_CANDIDATES = {"date", "ds", "ymd", "๋ ์ง", "prce_reg_mm", "etl_ldg_dt"}
ITEM_CANDIDATES = {"item", "ํ๋ชฉ", "code", "category", "pdlt_nm", "spcs_nm"}
PRICE_CANDIDATES = {"price", "y", "value", "๊ฐ๊ฒฉ", "avrg_prce"}
def _standardize_columns(df: pd.DataFrame) -> pd.DataFrame:
"""Standardize column names to date/item/price and deduplicate."""
col_map = {}
for c in df.columns:
lc = c.lower()
if lc in DATE_CANDIDATES:
col_map[c] = "date"
elif lc in PRICE_CANDIDATES:
col_map[c] = "price"
elif lc in ITEM_CANDIDATES:
# first hit as item, second as species
if "item" not in col_map.values():
col_map[c] = "item"
else:
col_map[c] = "species"
df = df.rename(columns=col_map)
# โโ handle duplicated columns after rename โโโโโโโโโโโโโโโโโโโโโโโโโ
if df.columns.duplicated().any():
df = df.loc[:, ~df.columns.duplicated()]
# โโ index datetime to column โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
if "date" not in df.columns and df.index.dtype.kind == "M":
df.reset_index(inplace=True)
df.rename(columns={df.columns[0]: "date"}, inplace=True)
# โโ convert YYYYMM string to datetime โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
if "date" in df.columns and pd.api.types.is_object_dtype(df["date"]):
if len(df) > 0: # ๋ฐ์ดํฐ๊ฐ ์๋์ง ํ์ธ
sample = str(df["date"].iloc[0])
if sample.isdigit() and len(sample) in (6, 8):
df["date"] = pd.to_datetime(df["date"].astype(str).str[:6], format="%Y%m", errors="coerce")
# โโ build item from pdlt_nm + spcs_nm if needed โโโโโโโโโโโโโโโโโโโโ
if "item" not in df.columns and {"pdlt_nm", "spcs_nm"}.issubset(df.columns):
df["item"] = df["pdlt_nm"].str.strip() + "-" + df["spcs_nm"].str.strip()
# โโ merge item + species โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
if {"item", "species"}.issubset(df.columns):
df["item"] = df["item"].astype(str).str.strip() + "-" + df["species"].astype(str).str.strip()
df.drop(columns=["species"], inplace=True)
return df
@st.cache_data(show_spinner=False)
def load_data() -> pd.DataFrame:
"""Load price data from Parquet if available, else CSV. Handle flexible schema."""
try:
if PARQUET_PATH.exists():
st.sidebar.info("Parquet ํ์ผ์์ ๋ฐ์ดํฐ๋ฅผ ๋ถ๋ฌ์ต๋๋ค.")
df = pd.read_parquet(PARQUET_PATH)
st.sidebar.success(f"Parquet ๋ฐ์ดํฐ ๋ก๋ ์๋ฃ: {len(df)}๊ฐ ํ")
elif CSV_PATH.exists():
st.sidebar.info("CSV ํ์ผ์์ ๋ฐ์ดํฐ๋ฅผ ๋ถ๋ฌ์ต๋๋ค.")
df = pd.read_csv(CSV_PATH)
st.sidebar.success(f"CSV ๋ฐ์ดํฐ ๋ก๋ ์๋ฃ: {len(df)}๊ฐ ํ")
else:
st.error("๐พ price_data.csv ๋๋ domae-202503.parquet ํ์ผ์ ์ฐพ์ ์ ์์ต๋๋ค.")
st.stop()
# ์๋ณธ ๋ฐ์ดํฐ ํํ ํ์ธ
st.sidebar.write("์๋ณธ ๋ฐ์ดํฐ ์ปฌ๋ผ:", list(df.columns))
df = _standardize_columns(df)
st.sidebar.write("ํ์คํ ํ ์ปฌ๋ผ:", list(df.columns))
missing = {c for c in ["date", "item", "price"] if c not in df.columns}
if missing:
st.error(f"ํ์ ์ปฌ๋ผ ๋๋ฝ: {', '.join(missing)} โ ํ์ผ ์ปฌ๋ผ๋ช
์ ํ์ธํ์ธ์.")
st.stop()
# ๋ ์ง ๋ณํ ์ ํ ๋ฐ์ดํฐ ์ ํ์ธ
before_date_convert = len(df)
df["date"] = pd.to_datetime(df["date"], errors="coerce")
after_date_convert = df.dropna(subset=["date"]).shape[0]
if before_date_convert != after_date_convert:
st.warning(f"๋ ์ง ๋ณํ ์ค {before_date_convert - after_date_convert}๊ฐ ํ์ด ์ ์ธ๋์์ต๋๋ค.")
# NA ๋ฐ์ดํฐ ์ฒ๋ฆฌ
before_na_drop = len(df)
df = df.dropna(subset=["date", "item", "price"])
after_na_drop = len(df)
if before_na_drop != after_na_drop:
st.warning(f"NA ์ ๊ฑฐ ์ค {before_na_drop - after_na_drop}๊ฐ ํ์ด ์ ์ธ๋์์ต๋๋ค.")
df.sort_values("date", inplace=True)
# ๋ฐ์ดํฐ ๋ ์ง ๋ฒ์ ํ์ธ
if len(df) > 0:
st.sidebar.write(f"๋ฐ์ดํฐ ๋ ์ง ๋ฒ์: {df['date'].min().strftime('%Y-%m-%d')} ~ {df['date'].max().strftime('%Y-%m-%d')}")
st.sidebar.write(f"์ด ํ๋ชฉ ์: {df['item'].nunique()}")
else:
st.error("์ ํจํ ๋ฐ์ดํฐ๊ฐ ์์ต๋๋ค!")
return df
except Exception as e:
st.error(f"๋ฐ์ดํฐ ๋ก๋ ์ค ์ค๋ฅ ๋ฐ์: {str(e)}")
st.stop()
@st.cache_data(show_spinner=False)
def get_items(df: pd.DataFrame):
return sorted(df["item"].unique())
@st.cache_data(show_spinner=False, ttl=3600)
def fit_prophet(df: pd.DataFrame, horizon_end: str):
# Make a copy and ensure we have data
df = df.copy()
df = df.dropna(subset=["date", "price"])
# ์ค๋ณต ๋ ์ง ์ฒ๋ฆฌ - ๋์ผ ๋ ์ง์ ์ฌ๋ฌ ๊ฐ์ด ์์ผ๋ฉด ํ๊ท ๊ฐ ์ฌ์ฉ
df = df.groupby("date")["price"].mean().reset_index()
if len(df) < 2:
st.warning(f"๋ฐ์ดํฐ ํฌ์ธํธ๊ฐ ๋ถ์กฑํฉ๋๋ค. ์์ธก์ ์ํด์๋ ์ต์ 2๊ฐ ์ด์์ ์ ํจ ๋ฐ์ดํฐ๊ฐ ํ์ํฉ๋๋ค. (ํ์ฌ {len(df)}๊ฐ)")
return None, None
# Convert to Prophet format
prophet_df = df.rename(columns={"date": "ds", "price": "y"})
try:
# Fit the model
m = Prophet(yearly_seasonality=True, weekly_seasonality=False, daily_seasonality=False)
m.fit(prophet_df)
# Generate future dates
periods = max((pd.Timestamp(horizon_end) - df["date"].max()).days, 1)
future = m.make_future_dataframe(periods=periods, freq="D")
# Make predictions
forecast = m.predict(future)
return m, forecast
except Exception as e:
st.error(f"Prophet ๋ชจ๋ธ ์์ฑ ์ค ์ค๋ฅ: {str(e)}")
return None, None
# -------------------------------------------------
# LOAD DATA ---------------------------------------
# -------------------------------------------------
raw_df = load_data()
if len(raw_df) == 0:
st.error("๋ฐ์ดํฐ๊ฐ ๋น์ด ์์ต๋๋ค. ํ์ผ์ ํ์ธํด์ฃผ์ธ์.")
st.stop()
st.sidebar.header("๐ ํ๋ชฉ ์ ํ")
selected_item = st.sidebar.selectbox("ํ๋ชฉ", get_items(raw_df))
current_date = date.today()
st.sidebar.caption(f"์ค๋: {current_date}")
item_df = raw_df.query("item == @selected_item").copy()
if item_df.empty:
st.error("์ ํํ ํ๋ชฉ ๋ฐ์ดํฐ ์์")
st.stop()
# -------------------------------------------------
# MACRO FORECAST 1996โ2030 ------------------------
# -------------------------------------------------
st.header(f"๐ {selected_item} ๊ฐ๊ฒฉ ์์ธก ๋์๋ณด๋")
# ๋ฐ์ดํฐ ํํฐ๋ง ๋ก์ง ๊ฐ์ - ์๊ฐ ๋ฒ์๋ฅผ ์กฐ์ ํ์ฌ ๋ ๋ง์ ๋ฐ์ดํฐ ํฌํจ
try:
macro_start_dt = pd.Timestamp(MACRO_START)
# ๋ฐ์ดํฐ๊ฐ ์ถฉ๋ถํ์ง ์์ผ๋ฉด ์์ ๋ ์ง๋ฅผ ์กฐ์
if len(item_df[item_df["date"] >= macro_start_dt]) < 10:
# ๊ฐ์ฅ ์ค๋๋ ๋ ์ง๋ถํฐ ์์
macro_start_dt = item_df["date"].min()
st.info(f"์ถฉ๋ถํ ๋ฐ์ดํฐ๊ฐ ์์ด ์์ ๋ ์ง๋ฅผ {macro_start_dt.strftime('%Y-%m-%d')}๋ก ์กฐ์ ํ์ต๋๋ค.")
macro_df = item_df[item_df["date"] >= macro_start_dt].copy()
except Exception as e:
st.error(f"๋ ์ง ํํฐ๋ง ์ค๋ฅ: {str(e)}")
macro_df = item_df.copy() # ํํฐ๋ง ์์ด ์ ์ฒด ๋ฐ์ดํฐ ์ฌ์ฉ
# Add diagnostic info
with st.expander("๋ฐ์ดํฐ ์ง๋จ"):
st.write(f"- ์ ์ฒด ๋ฐ์ดํฐ ์: {len(item_df)}")
st.write(f"- ๋ถ์ ๋ฐ์ดํฐ ์: {len(macro_df)}")
if len(macro_df) > 0:
st.write(f"- ๊ธฐ๊ฐ: {macro_df['date'].min().strftime('%Y-%m-%d')} ~ {macro_df['date'].max().strftime('%Y-%m-%d')}")
st.dataframe(macro_df.head())
else:
st.write("๋ฐ์ดํฐ๊ฐ ์์ต๋๋ค.")
if len(macro_df) < 2:
st.warning(f"{selected_item}์ ๋ํ ๋ฐ์ดํฐ๊ฐ ์ถฉ๋ถํ์ง ์์ต๋๋ค. ์ ์ฒด ๊ธฐ๊ฐ ๋ฐ์ดํฐ๋ฅผ ํ์ํฉ๋๋ค.")
fig = px.line(item_df, x="date", y="price", title=f"{selected_item} ๊ณผ๊ฑฐ ๊ฐ๊ฒฉ")
st.plotly_chart(fig, use_container_width=True)
else:
try:
with st.spinner("์ฅ๊ธฐ ์์ธก ๋ชจ๋ธ ์์ฑ ์ค..."):
m_macro, fc_macro = fit_prophet(macro_df, MACRO_END)
if m_macro is not None and fc_macro is not None:
fig_macro = px.line(fc_macro, x="ds", y="yhat", title="์ฅ๊ธฐ ์์ธก (1996โ2030)")
fig_macro.add_scatter(x=macro_df["date"], y=macro_df["price"], mode="lines", name="์ค์ ๊ฐ๊ฒฉ")
st.plotly_chart(fig_macro, use_container_width=True)
latest_price = macro_df.iloc[-1]["price"]
# 2030๋
๋ง์ง๋ง ๋ ์ฐพ๊ธฐ
target_date = pd.Timestamp(MACRO_END)
close_dates = fc_macro.loc[(fc_macro["ds"] - target_date).abs().argsort()[:1], "ds"].values[0]
macro_pred = fc_macro.loc[fc_macro["ds"] == close_dates, "yhat"].iloc[0]
macro_pct = (macro_pred - latest_price) / latest_price * 100
st.metric("2030 ์์ธก๊ฐ", f"{macro_pred:,.0f}", f"{macro_pct:+.1f}%")
else:
st.warning("์์ธก ๋ชจ๋ธ์ ์์ฑํ ์ ์์ต๋๋ค.")
fig = px.line(item_df, x="date", y="price", title=f"{selected_item} ๊ณผ๊ฑฐ ๊ฐ๊ฒฉ")
st.plotly_chart(fig, use_container_width=True)
except Exception as e:
st.error(f"์ฅ๊ธฐ ์์ธก ์ค๋ฅ ๋ฐ์: {str(e)}")
fig = px.line(item_df, x="date", y="price", title=f"{selected_item} ๊ณผ๊ฑฐ ๊ฐ๊ฒฉ")
st.plotly_chart(fig, use_container_width=True)
# -------------------------------------------------
# MICRO FORECAST 2024โ2026 ------------------------
# -------------------------------------------------
st.subheader("๐ 2024โ2026 ๋จ๊ธฐ ์์ธก")
# ๋ฐ์ดํฐ ํํฐ๋ง ๋ก์ง ๊ฐ์
try:
micro_start_dt = pd.Timestamp(MICRO_START)
# ๋ฐ์ดํฐ๊ฐ ์ถฉ๋ถํ์ง ์์ผ๋ฉด ์์ ๋ ์ง๋ฅผ ์กฐ์
if len(item_df[item_df["date"] >= micro_start_dt]) < 10:
# ์ต๊ทผ 30% ๋ฐ์ดํฐ๋ง ์ฌ์ฉ
n = max(2, int(len(item_df) * 0.3))
micro_df = item_df.sort_values("date").tail(n).copy()
st.info(f"์ถฉ๋ถํ ์ต๊ทผ ๋ฐ์ดํฐ๊ฐ ์์ด ์ต๊ทผ {n}๊ฐ ๋ฐ์ดํฐ ํฌ์ธํธ๋ง ์ฌ์ฉํฉ๋๋ค.")
else:
micro_df = item_df[item_df["date"] >= micro_start_dt].copy()
except Exception as e:
st.error(f"๋จ๊ธฐ ์์ธก ๋ฐ์ดํฐ ํํฐ๋ง ์ค๋ฅ: {str(e)}")
# ์ต๊ทผ 10๊ฐ ๋ฐ์ดํฐ ํฌ์ธํธ ์ฌ์ฉ
micro_df = item_df.sort_values("date").tail(10).copy()
if len(micro_df) < 2:
st.warning(f"{MICRO_START} ์ดํ ๋ฐ์ดํฐ๊ฐ ์ถฉ๋ถํ์ง ์์ต๋๋ค.")
fig = px.line(item_df, x="date", y="price", title=f"{selected_item} ์ต๊ทผ ๊ฐ๊ฒฉ")
st.plotly_chart(fig, use_container_width=True)
else:
try:
with st.spinner("๋จ๊ธฐ ์์ธก ๋ชจ๋ธ ์์ฑ ์ค..."):
m_micro, fc_micro = fit_prophet(micro_df, MICRO_END)
if m_micro is not None and fc_micro is not None:
fig_micro = px.line(fc_micro, x="ds", y="yhat", title="๋จ๊ธฐ ์์ธก (2024โ2026)")
fig_micro.add_scatter(x=micro_df["date"], y=micro_df["price"], mode="lines", name="์ค์ ๊ฐ๊ฒฉ")
st.plotly_chart(fig_micro, use_container_width=True)
latest_price = micro_df.iloc[-1]["price"]
target_date = pd.Timestamp(MICRO_END)
close_dates = fc_micro.loc[(fc_micro["ds"] - target_date).abs().argsort()[:1], "ds"].values[0]
micro_pred = fc_micro.loc[fc_micro["ds"] == close_dates, "yhat"].iloc[0]
micro_pct = (micro_pred - latest_price) / latest_price * 100
st.metric("2026 ์์ธก๊ฐ", f"{micro_pred:,.0f}", f"{micro_pct:+.1f}%")
else:
st.warning("๋จ๊ธฐ ์์ธก ๋ชจ๋ธ์ ์์ฑํ ์ ์์ต๋๋ค.")
except Exception as e:
st.error(f"๋จ๊ธฐ ์์ธก ์ค๋ฅ: {str(e)}")
# -------------------------------------------------
# SEASONALITY & PATTERN ---------------------------
# -------------------------------------------------
with st.expander("๐ ์์ฆ๋๋ฆฌํฐ & ํจํด ์ค๋ช
"):
if 'm_micro' in locals() and m_micro is not None and 'fc_micro' in locals() and fc_micro is not None:
try:
comp_fig = m_micro.plot_components(fc_micro)
st.pyplot(comp_fig)
month_season = (fc_micro[["ds", "yearly"]]
.assign(month=lambda d: d.ds.dt.month)
.groupby("month")["yearly"].mean())
st.markdown(
f"**์ฐ๊ฐ ํผํฌ ์:** {int(month_season.idxmax())}์ \n"
f"**์ฐ๊ฐ ์ ์ ์:** {int(month_season.idxmin())}์ \n"
f"**์ฐ๊ฐ ๋ณ๋ํญ:** {month_season.max() - month_season.min():.1f}")
except Exception as e:
st.error(f"์์ฆ๋๋ฆฌํฐ ๋ถ์ ์ค๋ฅ: {str(e)}")
else:
st.info("ํจํด ๋ถ์์ ์ํ ์ถฉ๋ถํ ๋ฐ์ดํฐ๊ฐ ์์ต๋๋ค.")
# -------------------------------------------------
# CORRELATION HEATMAP -----------------------------
# -------------------------------------------------
st.subheader("๐งฎ ํ๋ชฉ ๊ฐ ์๊ด๊ด๊ณ")
try:
# ๋๋ฌด ๋ง์ ํ๋ชฉ์ด ์์ผ๋ฉด ์์ N๊ฐ๋ง ์ ํ
items_to_corr = raw_df['item'].value_counts().head(30).index.tolist()
if selected_item not in items_to_corr and selected_item in raw_df['item'].unique():
items_to_corr.append(selected_item)
filtered_df = raw_df[raw_df['item'].isin(items_to_corr)]
monthly_pivot = (filtered_df.assign(month=lambda d: d.date.dt.to_period("M"))
.groupby(["month", "item"], as_index=False)["price"].mean()
.pivot(index="month", columns="item", values="price"))
# ๊ฒฐ์ธก์น๊ฐ ๋๋ฌด ๋ง์ ์ด ์ ๊ฑฐ
threshold = 0.5 # 50% ์ด์ ๊ฒฐ์ธก์น๊ฐ ์๋ ์ด ์ ๊ฑฐ
monthly_pivot = monthly_pivot.loc[:, monthly_pivot.isnull().mean() < threshold]
if monthly_pivot.shape[1] > 1: # At least 2 items needed for correlation
# ๊ฒฐ์ธก์น ์ฒ๋ฆฌ
monthly_pivot = monthly_pivot.fillna(method='ffill').fillna(method='bfill')
# ์๊ด๊ด๊ณ ๊ณ์ฐ
corr = monthly_pivot.corr()
# ์๊ฐํ
fig, ax = plt.subplots(figsize=(12, 10))
mask = np.triu(np.ones_like(corr, dtype=bool))
# ์ฌ๊ธฐ์ ํฐํธ ์ค์ ๋ค์ ํ์ธ
plt.title(f"{selected_item} ๊ด๋ จ ์๊ด๊ด๊ณ", fontsize=15)
sns.heatmap(corr, mask=mask, annot=False, cmap="coolwarm", center=0,
square=True, linewidths=.5, cbar_kws={"shrink": .5})
plt.xticks(rotation=45, ha='right', fontsize=8)
plt.yticks(fontsize=8)
# Highlight correlations with selected item
if selected_item in corr.columns:
item_corr = corr[selected_item].sort_values(ascending=False)
top_corr = item_corr.drop(selected_item).head(5)
bottom_corr = item_corr.drop(selected_item).tail(5)
col1, col2 = st.columns(2)
with col1:
st.markdown(f"**{selected_item}์ ์๊ด๊ด๊ณ ๋์ ํ๋ชฉ**")
for item, val in top_corr.items():
st.write(f"{item}: {val:.2f}")
with col2:
st.markdown(f"**{selected_item}์ ์๊ด๊ด๊ณ ๋ฎ์ ํ๋ชฉ**")
for item, val in bottom_corr.items():
st.write(f"{item}: {val:.2f}")
st.pyplot(fig)
else:
st.info("์๊ด๊ด๊ณ ๋ถ์์ ์ํ ์ถฉ๋ถํ ํ๋ชฉ ๋ฐ์ดํฐ๊ฐ ์์ต๋๋ค.")
except Exception as e:
st.error(f"์๊ด๊ด๊ณ ๋ถ์ ์ค๋ฅ: {str(e)}")
st.write("์ค๋ฅ ์์ธ ์ ๋ณด:", str(e))
# -------------------------------------------------
# FOOTER ------------------------------------------
# -------------------------------------------------
st.markdown("---")
st.caption("ยฉ 2025 ํ๋ชฉ๋ณ ๊ฐ๊ฒฉ ์์ธก ์์คํ
| ๋ฐ์ดํฐ ๋ถ์ ์๋ํ") |