File size: 5,574 Bytes
ab46b5d |
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 |
import pandas as pd
import numpy as np
import datetime as dt
import warnings
from statsmodels.tsa.holtwinters import ExponentialSmoothing
import plotly.graph_objects as go
import gradio as gr
warnings.filterwarnings("ignore")
# -----------------------------
# CONFIG
# -----------------------------
DATA_FILE = "202503-domae.parquet" # ๊ฐ์ ๊ฒฝ๋ก์ ๋์ฌ ์์ด์ผ ํจ
FORECAST_END_YEAR = 2030 # ์์ธก ์ข
๋ฃ ์ฐ๋(12์๊น์ง)
SEASONAL_PERIODS = 12 # ์๋ณ seasonality
# -----------------------------
# 1. ๋ฐ์ดํฐ ์ ์ฌ & ์ ์ฒ๋ฆฌ
# -----------------------------
def load_data(path: str) -> pd.DataFrame:
"""Parquet โ ์๋ณ ํผ๋ฒ ํ
์ด๋ธ(DateIndex, ์ด: ํ๋ชฉ, ๊ฐ: ๊ฐ๊ฒฉ)."""
df = pd.read_parquet(path)
# ๋ ์ง ์ปฌ๋ผ ์์ฑ/์ ๊ทํ (๋ ๊ฐ์ง ์ผ์ด์ค ์ง์)
if "date" in df.columns:
df["date"] = pd.to_datetime(df["date"])
elif "PRCE_REG_MM" in df.columns:
df["date"] = pd.to_datetime(df["PRCE_REG_MM"].astype(str), format="%Y%m")
else:
raise ValueError("์ง์๋์ง ์๋ ๋ ์ง ์ปฌ๋ผ ํ์์
๋๋ค.")
# ๊ธฐ๋ณธ ์ปฌ๋ผ๋ช
ํต์ผ
item_col = "PDLT_NM" if "PDLT_NM" in df.columns else "item"
price_col = "AVRG_PRCE" if "AVRG_PRCE" in df.columns else "price"
monthly = (
df.groupby(["date", item_col])[price_col]
.mean()
.reset_index()
)
pivot = (
monthly
.pivot(index="date", columns=item_col, values=price_col)
.sort_index()
)
# ์ ์์์ผ MS ๋น๋๋ก ์ ๋ ฌ
pivot.index = pd.to_datetime(pivot.index).to_period("M").to_timestamp()
return pivot
pivot = load_data(DATA_FILE)
products = pivot.columns.tolist()
# -----------------------------
# 2. ๊ณ ์ ๋ชจ๋ธ ์ ์ (HoltโWinters + fallback)
# -----------------------------
def _fit_forecast(series: pd.Series) -> pd.Series:
"""์๋ณ ์๊ณ์ด โ 2025โ04 ์ดํ FORECAST_END_YEARโ12๊น์ง ์์ธก."""
# Ensure Monthly Start frequency
series = series.asfreq("MS")
# ์์ธก ๊ธฐ๊ฐ ๊ณ์ฐ
last_date = series.index[-1]
end_date = dt.datetime(FORECAST_END_YEAR, 12, 1)
horizon = (end_date.year - last_date.year) * 12 + (end_date.month - last_date.month)
if horizon <= 0:
return pd.Series(dtype=float)
try:
model = ExponentialSmoothing(
series,
trend="add",
seasonal="mul",
seasonal_periods=SEASONAL_PERIODS,
initialization_method="estimated",
)
res = model.fit(optimized=True)
fc = res.forecast(horizon)
except Exception:
# ํํธ์ํฐ์ค ํ์ต ์คํจ ์ ๋จ์ CAGR ๊ธฐ๋ฐ ์์ธก
growth = series.pct_change().fillna(0).mean()
fc = pd.Series(
[series.iloc[-1] * (1 + growth) ** i for i in range(1, horizon + 1)],
index=pd.date_range(
series.index[-1] + pd.DateOffset(months=1),
periods=horizon,
freq="MS",
),
)
return fc
# ํ๋ชฉ๋ณ ์ ์ฒด ์๋ฆฌ์ฆ(๊ณผ๊ฑฐ+์์ธก) ์ฌ์ ๊ตฌ์ถ โ ์ฑ ๋ฐ์ ์๋ ๊ฐ์
FULL_SERIES = {}
FORECASTS = {}
for item in products:
hist = pivot[item].dropna()
fc = _fit_forecast(hist)
FULL_SERIES[item] = pd.concat([hist, fc])
FORECASTS[item] = fc
# -----------------------------
# 3. ๋ด์ผ ๊ฐ๊ฒฉ ์์ธก ํจ์
# -----------------------------
today = dt.date.today()
tomorrow = today + dt.timedelta(days=1)
def build_tomorrow_df() -> pd.DataFrame:
"""๋ด์ผ(์ผ ๋จ์) ์์ ๊ฐ๊ฒฉ DataFrame ๋ฐํ."""
preds = {}
for item, series in FULL_SERIES.items():
# ์ผ ๋จ์ ์ ํ ๋ณด๊ฐ
daily = series.resample("D").interpolate("linear")
preds[item] = round(daily.loc[tomorrow], 2) if tomorrow in daily.index else np.nan
return (
pd.DataFrame.from_dict(preds, orient="index", columns=[f"๋ด์ผ({tomorrow}) ์์๊ฐ(KRW)"])
.sort_index()
)
tomorrow_df = build_tomorrow_df()
# -----------------------------
# 4. ์๊ฐํ ํจ์
# -----------------------------
def plot_item(item: str):
hist = pivot[item].dropna().asfreq("MS")
fc = FORECASTS[item]
fig = go.Figure()
fig.add_trace(go.Scatter(x=hist.index, y=hist.values, mode="lines", name="Historical"))
fig.add_trace(go.Scatter(x=fc.index, y=fc.values, mode="lines", name="Forecast"))
fig.update_layout(
title=f"{item} โ Monthly Avg Price (1996โ2025) & Forecast(2025โ04โ2030โ12)",
xaxis_title="Date",
yaxis_title="Price (KRW)",
legend=dict(orientation="h", y=1.02, x=0.01),
margin=dict(l=40, r=20, t=60, b=40),
)
return fig
# -----------------------------
# 5. Gradio UI
# -----------------------------
with gr.Blocks(title="๋๋งค ๊ฐ๊ฒฉ ์์ธกย App") as demo:
gr.Markdown("## ๐ ๋๋งค ๊ฐ๊ฒฉ ์์ธก ๋์๋ณด๋ (1996โ2030)")
# ํ๋ชฉ ์ ํ โ ๊ทธ๋ํ ์
๋ฐ์ดํธ
item_dd = gr.Dropdown(products, value=products[0], label="ํ๋ชฉ ์ ํ")
chart_out = gr.Plot(label="๊ฐ๊ฒฉ ์ถ์ธ")
# ๋ด์ผ ๊ฐ๊ฒฉ ํ (์ด๊ธฐ ๊ณ ์ )
gr.Markdown(f"### ๋ด์ผ({tomorrow}) ๊ฐ ํ๋ชฉ ์์๊ฐ (KRW)")
tomorrow_table = gr.Dataframe(tomorrow_df, interactive=False, height=400)
def update_chart(product):
return plot_item(product)
item_dd.change(update_chart, inputs=item_dd, outputs=chart_out, queue=False)
# -----------------------------
# 6. ์คํ ์คํฌ๋ฆฝํธ ์ํธ๋ฆฌํฌ์ธํธ
# -----------------------------
if __name__ == "__main__":
demo.launch()
|