PassengersTimeSeries / src /streamlit_app.py
EnYa32's picture
Update src/streamlit_app.py
a9e65e7 verified
Raw History Blame Contribute Delete
6.59 kB
import pickle
from pathlib import Path
import numpy as np
import pandas as pd
import streamlit as st
import joblib
import matplotlib.pyplot as plt
from tensorflow.keras.models import load_model
# -------------------------
# Page config
# -------------------------
st.set_page_config(
page_title="Airline Passengers LSTM Forecast",
page_icon="✈️",
layout="wide"
)
st.title("✈️ Airline Passengers Forecast (LSTM)")
st.caption("Time Series Forecasting using an LSTM model (train: up to 1958, test: 1959–1960).")
# -------------------------
# Paths (robust: root or src)
# -------------------------
BASE_DIR = Path(__file__).resolve().parent
CANDIDATE_DIRS = [BASE_DIR, BASE_DIR / "src"]
def find_file(filename: str) -> Path | None:
for d in CANDIDATE_DIRS:
p = d / filename
if p.exists():
return p
return None
MODEL_PATH = find_file("lstm_airline_model.keras")
SCALER_PATH = find_file("scaler.pkl")
METRICS_PATH = find_file("metrics.pkl")
DATA_URL = "https://raw.githubusercontent.com/amankharwal/Website-data/master/airline-passengers.csv"
LOOKBACK = 12 # must match training
# -------------------------
# Load artifacts
# -------------------------
@st.cache_resource
def load_artifacts():
if MODEL_PATH is None:
raise FileNotFoundError("Missing model file: lstm_airline_model.keras")
if SCALER_PATH is None:
raise FileNotFoundError("Missing scaler file: scaler.pkl")
model = load_model(MODEL_PATH, compile=False)
scaler = joblib.load(SCALER_PATH)
return model, scaler
# -------------------------
# Load data
# -------------------------
@st.cache_data
def load_data():
df = pd.read_csv(DATA_URL)
# Standardize
df["Month"] = pd.to_datetime(df["Month"])
df = df.sort_values("Month").set_index("Month")
df["Passengers"] = df["Passengers"].astype("float32")
return df
def create_sequences(data_2d: np.ndarray, lookback: int = 12):
# data_2d shape: (n, 1)
X = np.array([data_2d[i-lookback:i] for i in range(lookback, len(data_2d))])
y = data_2d[lookback:]
return X, y
def inverse_safe(scaler, arr_2d: np.ndarray):
# scaler expects 2D
return scaler.inverse_transform(arr_2d)
def rolling_forecast(model, scaler, last_values: np.ndarray, steps: int, lookback: int = 12):
"""
last_values: unscaled original values, shape (lookback, 1)
steps: how many future points to forecast
"""
# scale with the saved scaler
window = scaler.transform(last_values.astype("float32"))
preds_scaled = []
for _ in range(steps):
x = window.reshape(1, lookback, 1)
pred_scaled = model.predict(x, verbose=0) # shape (1,1)
preds_scaled.append(pred_scaled[0, 0])
# shift window
window = np.vstack([window[1:], pred_scaled])
preds_scaled = np.array(preds_scaled).reshape(-1, 1)
preds = inverse_safe(scaler, preds_scaled)
return preds
# -------------------------
# Sidebar controls
# -------------------------
st.sidebar.header("Settings")
forecast_steps = st.sidebar.slider("Forecast months into the future", min_value=1, max_value=36, value=12, step=1)
show_metrics = st.sidebar.checkbox("Show saved metrics (metrics.pkl)", value=True)
show_test_plot = st.sidebar.checkbox("Show test forecast plot (1959–1960)", value=True)
show_future_plot = st.sidebar.checkbox("Show future forecast plot", value=True)
# -------------------------
# Main
# -------------------------
try:
model, scaler = load_artifacts()
df = load_data()
except Exception as e:
st.error(str(e))
st.stop()
col1, col2 = st.columns([1.2, 1])
with col1:
st.subheader("Dataset preview")
st.dataframe(df.head(10), use_container_width=True)
with col2:
st.subheader("Basic info")
st.write(f"Rows: **{len(df)}**")
st.write(f"Date range: **{df.index.min().date()} → {df.index.max().date()}**")
st.write("Lookback window:", f"**{LOOKBACK} months**")
if show_metrics and METRICS_PATH is not None:
st.subheader("Saved metrics")
try:
m = joblib.load(METRICS_PATH)
c1, c2, c3 = st.columns(3)
c1.metric("RMSE", f"{m['rmse']:.2f}")
c2.metric("MAE", f"{m['mae']:.2f}")
c3.metric("MAPE (%)", f"{m['mape']:.2f}")
except Exception as e:
st.info(f"metrics.pkl found but could not be read. ({e})")
st.divider()
# Plot original series
st.subheader("Time series")
fig = plt.figure(figsize=(10, 4))
plt.plot(df.index, df["Passengers"])
plt.title("Monthly Airline Passengers (1949–1960)")
plt.xlabel("Date")
plt.ylabel("Passengers")
plt.grid(alpha=0.3)
st.pyplot(fig)
# -------------------------
# Test forecast (1959–1960)
# -------------------------
if show_test_plot:
st.subheader("Test forecast (1959–1960)")
# Split exactly like training
train = df.loc[: "1958", ["Passengers"]].values.astype("float32")
test = df.loc["1959":, ["Passengers"]].values.astype("float32")
# Scale with loaded scaler (fitted on train during your training)
train_scaled = scaler.transform(train) # NOTE: scaler already fitted
test_scaled = scaler.transform(test)
# Sequences
x_test, y_test = create_sequences(test_scaled, LOOKBACK)
# Predict
y_pred_scaled = model.predict(x_test, verbose=0)
y_pred = inverse_safe(scaler, y_pred_scaled)
y_true = inverse_safe(scaler, y_test)
test_dates = df.loc["1959":].index[LOOKBACK:]
fig2 = plt.figure(figsize=(10, 4))
plt.plot(test_dates, y_true, label="Actual")
plt.plot(test_dates, y_pred, label="Predicted")
plt.title("LSTM Forecast vs Actual (Test)")
plt.xlabel("Date")
plt.ylabel("Passengers")
plt.legend()
plt.grid(alpha=0.3)
st.pyplot(fig2)
# -------------------------
# Future forecast
# -------------------------
if show_future_plot:
st.subheader("Future forecast")
last_window = df[["Passengers"]].values.astype("float32")[-LOOKBACK:]
future_preds = rolling_forecast(model, scaler, last_window, steps=forecast_steps, lookback=LOOKBACK)
last_date = df.index.max()
future_dates = pd.date_range(last_date + pd.offsets.MonthBegin(1), periods=forecast_steps, freq="MS")
fig3 = plt.figure(figsize=(10, 4))
plt.plot(df.index, df["Passengers"].values, label="History")
plt.plot(future_dates, future_preds, label="Forecast")
plt.title("Future Forecast")
plt.xlabel("Date")
plt.ylabel("Passengers")
plt.legend()
plt.grid(alpha=0.3)
st.pyplot(fig3)
st.success("✅ App ready. Make sure model/scaler files are in the repo (root or src).")