StockPriceTimeSeries / src /streamlit_app.py
EnYa32's picture
Update src/streamlit_app.py
229dc69 verified
Raw History Blame Contribute Delete
8.31 kB
import os
from pathlib import Path
import joblib
import numpy as np
import pandas as pd
import streamlit as st
import matplotlib.pyplot as plt
from sklearn.metrics import mean_absolute_error, mean_squared_error
from tensorflow.keras.models import load_model
st.set_page_config(page_title="Stock LSTM Forecast", page_icon="πŸ“ˆ", layout="wide")
BASE_DIR = Path(__file__).resolve().parent
TICKERS = ["AAPL", "GOOG", "MSFT", "NFLX"]
FEATURE_COLS = ["Open", "High", "Low", "Close", "Volume"]
def find_file(name_candidates):
for name in name_candidates:
p = BASE_DIR / name
if p.exists():
return p
return None
@st.cache_resource
def load_artifacts(ticker: str):
model_path = find_file([f"{ticker}_lstm.keras", f"{ticker}_lstm.keras".lower(), f"{ticker}_lstm.keras".upper(),
f"{ticker}_lstm.keras".replace("_", ""), f"{ticker}_lstm.keras"])
# You used: "AAPL_lstm.keras", "GOOG_lstm.keras" ...
model_path = find_file([f"{ticker}_lstm.keras"])
x_scaler_path = find_file([f"{ticker}_x_scaler.pkl"])
y_scaler_path = find_file([f"{ticker}_y_scaler.pkl"])
if model_path is None or x_scaler_path is None or y_scaler_path is None:
missing = []
if model_path is None: missing.append(f"{ticker}_lstm.keras")
if x_scaler_path is None: missing.append(f"{ticker}_x_scaler.pkl")
if y_scaler_path is None: missing.append(f"{ticker}_y_scaler.pkl")
raise FileNotFoundError(f"Missing artifacts: {missing}. Make sure they are in the repo root.")
model = load_model(model_path)
x_scaler = joblib.load(x_scaler_path)
y_scaler = joblib.load(y_scaler_path)
return model, x_scaler, y_scaler
def load_data(uploaded_file):
# Default local file
if uploaded_file is None:
default_csv = find_file(["stocks.csv", "stocks"])
if default_csv is None:
raise FileNotFoundError("No stocks.csv found in repo. Upload a CSV in the sidebar or add stocks.csv to repo root.")
df = pd.read_csv(default_csv)
else:
df = pd.read_csv(uploaded_file)
# Basic cleanup
df.columns = [c.strip() for c in df.columns]
if "Date" not in df.columns or "Ticker" not in df.columns:
raise ValueError("CSV must contain at least columns: Ticker, Date, Open, High, Low, Close, Volume")
df["Date"] = pd.to_datetime(df["Date"])
df = df.sort_values(["Ticker", "Date"]).reset_index(drop=True)
# Ensure needed columns exist
for c in FEATURE_COLS + ["Adj Close"]:
if c not in df.columns:
# Adj Close is optional; we won't require it
pass
missing_feats = [c for c in FEATURE_COLS if c not in df.columns]
if missing_feats:
raise ValueError(f"Missing required feature columns: {missing_feats}")
return df
def make_sequences(X: np.ndarray, y: np.ndarray, lookback: int):
xs, ys = [], []
for i in range(lookback, len(X)):
xs.append(X[i - lookback:i])
ys.append(y[i])
return np.array(xs), np.array(ys)
def eval_on_test(df_ticker: pd.DataFrame, model, x_scaler, y_scaler, lookback: int, split_ratio: float = 0.8):
X = df_ticker[FEATURE_COLS]
y = df_ticker["Close"]
split = int(len(X) * split_ratio)
X_train = X.iloc[:split]
X_test = X.iloc[split:]
y_train = y.iloc[:split]
y_test = y.iloc[split:]
# Scale (fit on train only)
X_train_s = x_scaler.fit_transform(X_train)
X_test_s = x_scaler.transform(X_test)
y_train_s = y_scaler.fit_transform(y_train.values.reshape(-1, 1))
y_test_s = y_scaler.transform(y_test.values.reshape(-1, 1))
# Sequences
X_train_seq, y_train_seq = make_sequences(X_train_s, y_train_s, lookback)
X_test_seq, y_test_seq = make_sequences(X_test_s, y_test_s, lookback)
if len(X_test_seq) == 0:
raise ValueError(f"Not enough test rows to build sequences. "
f"Test rows={len(X_test_s)} must be > LOOKBACK={lookback}. "
f"Try smaller LOOKBACK.")
# Predict
y_pred_s = model.predict(X_test_seq, verbose=0)
# Inverse
y_pred = y_scaler.inverse_transform(y_pred_s).flatten()
y_true = y_scaler.inverse_transform(y_test_seq).flatten()
mae = mean_absolute_error(y_true, y_pred)
rmse = np.sqrt(mean_squared_error(y_true, y_pred))
return {
"mae": mae,
"rmse": rmse,
"y_true": y_true,
"y_pred": y_pred,
"test_dates": df_ticker["Date"].iloc[split:].reset_index(drop=True).iloc[lookback:].values
}
def next_day_forecast(df_ticker: pd.DataFrame, model, x_scaler, y_scaler, lookback: int):
# Fit scalers on ALL available data for "latest window" inference (common for deployment)
X_all = df_ticker[FEATURE_COLS].values
y_all = df_ticker["Close"].values.reshape(-1, 1)
X_all_s = x_scaler.fit_transform(X_all)
y_all_s = y_scaler.fit_transform(y_all)
if len(X_all_s) < lookback:
raise ValueError(f"Not enough rows for LOOKBACK={lookback}. Need at least {lookback} rows.")
last_window = X_all_s[-lookback:] # (lookback, features)
last_window = np.expand_dims(last_window, axis=0) # (1, lookback, features)
pred_s = model.predict(last_window, verbose=0)
pred = y_scaler.inverse_transform(pred_s).flatten()[0]
last_date = df_ticker["Date"].iloc[-1]
return pred, last_date
# ---------------- UI ----------------
st.title("πŸ“ˆ Multivariate Stock Forecasting (LSTM)")
st.caption("Train/test evaluation + next-step forecast for AAPL, GOOG, MSFT, NFLX.")
with st.sidebar:
st.header("Settings")
uploaded = st.file_uploader("Upload CSV (optional)", type=["csv"])
ticker = st.selectbox("Select Ticker", TICKERS, index=0)
lookback = st.slider("LOOKBACK (timesteps)", min_value=3, max_value=20, value=5, step=1)
split_ratio = st.slider("Train/Test split ratio", 0.6, 0.9, 0.8, 0.05)
run_btn = st.button("Run Forecast")
try:
df = load_data(uploaded)
except Exception as e:
st.error(str(e))
st.stop()
df_t = df[df["Ticker"] == ticker].copy().sort_values("Date").reset_index(drop=True)
if df_t.empty:
st.error(f"No rows found for ticker: {ticker}")
st.stop()
# Quick preview
c1, c2, c3 = st.columns(3)
c1.metric("Rows", len(df_t))
c2.metric("Date start", str(df_t["Date"].min().date()))
c3.metric("Date end", str(df_t["Date"].max().date()))
st.subheader("Data preview")
st.dataframe(df_t.head(10), use_container_width=True)
# Load artifacts for selected ticker
try:
model, x_scaler, y_scaler = load_artifacts(ticker)
except Exception as e:
st.error(str(e))
st.stop()
if run_btn:
st.subheader("Test evaluation (chronological split)")
try:
out = eval_on_test(df_t, model, x_scaler, y_scaler, lookback=lookback, split_ratio=split_ratio)
except Exception as e:
st.error(str(e))
st.stop()
m1, m2 = st.columns(2)
m1.metric("Test MAE (USD)", f"{out['mae']:.3f}")
m2.metric("Test RMSE (USD)", f"{out['rmse']:.3f}")
# Plot actual vs predicted
fig = plt.figure(figsize=(12, 5))
plt.plot(out["test_dates"], out["y_true"], label="Actual")
plt.plot(out["test_dates"], out["y_pred"], label="Predicted")
plt.title(f"{ticker} LSTM – Actual vs Predicted Close")
plt.xlabel("Date")
plt.ylabel("Close Price")
plt.legend()
st.pyplot(fig)
# Residuals
resid = out["y_true"] - out["y_pred"]
fig2 = plt.figure(figsize=(12, 4))
plt.plot(out["test_dates"], resid)
plt.axhline(0, linestyle="--")
plt.title("Residuals (Actual - Predicted)")
plt.xlabel("Date")
plt.ylabel("Error (USD)")
st.pyplot(fig2)
# Error histogram
fig3 = plt.figure(figsize=(7, 4))
plt.hist(resid, bins=10)
plt.title("Distribution of Prediction Errors")
plt.xlabel("Error (USD)")
plt.ylabel("Frequency")
st.pyplot(fig3)
st.subheader("Next-step forecast (latest window)")
try:
pred_next, last_date = next_day_forecast(df_t, model, x_scaler, y_scaler, lookback=lookback)
st.success(f"Predicted next close after {last_date.date()} for **{ticker}**: **{pred_next:.2f} USD**")
except Exception as e:
st.warning(str(e))
else:
st.info("Click **Run Forecast** in the sidebar to evaluate and forecast.")