FurnitureForecasting / src /streamlit_app.py
EnYa32's picture
Update src/streamlit_app.py
c4335f1 verified
Raw History Blame Contribute Delete
5.71 kB
import pandas as pd
import streamlit as st
import matplotlib.pyplot as plt
from pathlib import Path
st.set_page_config(page_title="SARIMA Sales Forecast", page_icon="πŸ“ˆ", layout="wide")
BASE_DIR = Path(__file__).resolve().parent
FORECAST_CSV_DEFAULT = BASE_DIR / "prediction2.csv"
TS_CSV_DEFAULT = BASE_DIR / "monthly_sales_ts.csv"
def load_forecast_csv(path: Path) -> pd.DataFrame:
df = pd.read_csv(path)
# Handle index column saved by pandas (e.g., "Unnamed: 0")
if df.columns[0].lower().startswith("unnamed"):
df = df.rename(columns={df.columns[0]: "date"})
# If there's a date column, set it as index
if "date" in df.columns:
df["date"] = pd.to_datetime(df["date"])
df = df.set_index("date")
# Normalize column names
df.columns = [c.strip().lower() for c in df.columns]
# Ensure expected columns exist
required = {"forecast"}
if not required.issubset(set(df.columns)):
raise ValueError(
"prediction2.csv must contain at least a 'forecast' column "
"(and optionally 'lower_ci' and 'upper_ci')."
)
return df
def load_ts_csv(path: Path) -> pd.Series:
df = pd.read_csv(path)
if df.columns[0].lower().startswith("unnamed"):
df = df.rename(columns={df.columns[0]: "date"})
if "date" not in df.columns:
raise ValueError("src/monthly_sales_ts.csv should have a 'date' column.")
df["date"] = pd.to_datetime(df["date"])
df = df.set_index("date")
# Find a reasonable sales column
sales_col = None
for c in df.columns:
if c.strip().lower() in ["sales", "monthly_sales", "value", "y"]:
sales_col = c
break
if sales_col is None:
sales_col = df.columns[0] # fallback
return df[sales_col].astype(float)
def plot_forecast(ts_hist: pd.Series | None, forecast_df: pd.DataFrame):
fig = plt.figure(figsize=(12, 5))
if ts_hist is not None and len(ts_hist) > 0:
plt.plot(ts_hist.index, ts_hist.values, label="Historical Sales")
plt.plot(forecast_df.index, forecast_df["forecast"].values, label="Forecast")
if "lower_ci" in forecast_df.columns and "upper_ci" in forecast_df.columns:
plt.fill_between(
forecast_df.index,
forecast_df["lower_ci"].values,
forecast_df["upper_ci"].values,
alpha=0.25,
label="Confidence Interval",
)
plt.title("Monthly Sales Forecast (SARIMA)")
plt.xlabel("Date")
plt.ylabel("Sales")
plt.legend()
st.pyplot(fig)
st.title("πŸ“ˆ Monthly Sales Forecast (SARIMA)")
st.write(
"This app loads your saved forecast file from `src/prediction2.csv` and visualizes "
"the forecast with optional confidence intervals."
)
with st.sidebar:
st.header("βš™οΈ Settings")
steps = st.slider("Forecast horizon (rows to show)", min_value=3, max_value=24, value=8, step=1)
st.markdown("### πŸ“‚ Data Source (default: `src/`)")
use_upload = st.checkbox("Upload CSV instead of using src/ files", value=False)
uploaded_forecast = None
uploaded_ts = None
if use_upload:
uploaded_forecast = st.file_uploader("Upload prediction2.csv", type=["csv"])
uploaded_ts = st.file_uploader("Upload monthly_sales_ts.csv (optional)", type=["csv"])
show_table = st.checkbox("Show forecast table", value=True)
# --- Load forecast dataframe ---
try:
if use_upload and uploaded_forecast is not None:
forecast_df = pd.read_csv(uploaded_forecast)
if forecast_df.columns[0].lower().startswith("unnamed"):
forecast_df = forecast_df.rename(columns={forecast_df.columns[0]: "date"})
if "date" in forecast_df.columns:
forecast_df["date"] = pd.to_datetime(forecast_df["date"])
forecast_df = forecast_df.set_index("date")
forecast_df.columns = [c.strip().lower() for c in forecast_df.columns]
else:
if not FORECAST_CSV_DEFAULT.exists():
st.error(
"Missing file: `src/prediction2.csv`.\n\n"
"Please upload it to your HuggingFace repo inside the `src/` folder."
)
st.stop()
forecast_df = load_forecast_csv(FORECAST_CSV_DEFAULT)
except Exception as e:
st.error(f"Could not load forecast CSV: {e}")
st.stop()
# Show only first N forecast rows
forecast_df = forecast_df.iloc[:steps]
# --- Load historical series (optional) ---
ts_hist = None
try:
if use_upload and uploaded_ts is not None:
ts_df = pd.read_csv(uploaded_ts)
if ts_df.columns[0].lower().startswith("unnamed"):
ts_df = ts_df.rename(columns={ts_df.columns[0]: "date"})
ts_df["date"] = pd.to_datetime(ts_df["date"])
ts_df = ts_df.set_index("date")
# find sales col
candidates = [c for c in ts_df.columns if c.strip().lower() in ["sales", "monthly_sales", "value", "y"]]
sales_col = candidates[0] if candidates else ts_df.columns[0]
ts_hist = ts_df[sales_col].astype(float)
else:
if TS_CSV_DEFAULT.exists():
ts_hist = load_ts_csv(TS_CSV_DEFAULT)
except Exception:
ts_hist = None # do not crash if optional file is broken
# --- UI output ---
if show_table:
st.subheader("πŸ“„ Forecast Table")
st.dataframe(forecast_df, use_container_width=True)
st.subheader("πŸ“‰ Forecast Plot")
plot_forecast(ts_hist, forecast_df)
st.download_button(
"⬇️ Download forecast CSV",
data=forecast_df.to_csv().encode("utf-8"),
file_name="forecast_output.csv",
mime="text/csv",
)
st.caption("Files expected in repo: `src/prediction2.csv` (required) and `src/monthly_sales_ts.csv` (optional).")