refactor: restructure monorepo for clean portfolio layout

- Move timesfm-forecast into apps/ directory
- Flatten Udacity portfolio projects from deep URL-encoded paths
  into data-engineering/01-XX numbered directories
- Remove old My-Data-Engineering-Portifolio/ parent directory
- Rewrite root README.md: professional overview with badges,
  project table, and repo structure diagram
- Create data-engineering/README.md with per-project descriptions
- Add README.md for 02-cassandra-modeling (was missing)
- Add README.md for 05-airflow-pipelines (was missing)
- Normalize capstone readme.md -> README.md
- Update .gitignore: add *.cfg, *.env, *.zip, *.sas7bdat,
  Jupyter checkpoints, IDE dirs; remove uv.lock exclusion
- Add dwh.cfg.example and dl.cfg.example credential templates
- Untrack real credential files (dwh.cfg, dl.cfg)

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

apps/timesfm-forecast/src/timesfm_app/ui/app.py

@@ -0,0 +1,178 @@
+import io
+
+import pandas as pd
+import streamlit as st
+import torch
+
+from timesfm_app.core import (
+    ForecastConfig,
+    TimesFMService,
+    ForecastPipeline,
+    DataValidator,
+)
+
+st.set_page_config(page_title="TimesFM Forecast", layout="wide")
+
+
+def horizon_range_slider(label: str, default_min: int = 1, default_max: int = 12):
+    return st.slider(
+        label,
+        min_value=1,
+        max_value=120,
+        value=(default_min, default_max),
+        step=1,
+        help="Select an inclusive range of horizons. The app outputs each step separately.",
+    )
+
+
+@st.cache_resource(show_spinner="Preparing TimesFM service…")
+def get_service(model_name: str, device: str) -> TimesFMService:
+    return TimesFMService(model_name=model_name, device=device)
+
+
+def main():
+    st.title("📈 TimesFM Forecast")
+
+    st.markdown(
+        """
+Upload a CSV with columns **`date, value, key`**.
+
+**Features**
+- Uses **all rows** as training (no holdout)
+- Choose a **range of horizons** (e.g., 1–12)
+- Multi-series (**by key**) batching
+- **Progress bar** during inference
+- **Download** forecasts as CSV
+        """
+    )
+
+    with st.sidebar:
+        st.header("Settings")
+
+        model_name = st.text_input(
+            "TimesFM model",
+            value="google/timesfm-2.0-500m-pytorch",
+        )
+
+        cuda_available = torch.cuda.is_available()
+        device = st.selectbox(
+            "Device",
+            options=(["cuda", "cpu"] if cuda_available else ["cpu"]),
+            index=(0 if cuda_available else 0),
+        )
+
+        timesfm_freq_code = st.number_input(
+            "TimesFM frequency code",
+            min_value=0,
+            max_value=99,
+            value=2,  # monthly by default
+            step=1,
+            help="Default 2 = monthly (matches your draft).",
+        )
+
+        pandas_freq_fallback = st.selectbox(
+            "Fallback pandas frequency for future dates",
+            options=["D", "W", "M", "Q", "Y"],
+            index=2,  # "M"
+            help="Used when per-key frequency inference fails.",
+        )
+
+        batch_size = st.slider("Batch size", 1, 64, 16, 1)
+        h_min, h_max = horizon_range_slider("Horizon range", 1, 12)
+
+    uploaded = st.file_uploader("Upload CSV", type=["csv"])
+
+    if "forecast" not in st.session_state:
+        st.session_state["forecast"] = None
+    if "history" not in st.session_state:
+        st.session_state["history"] = None
+
+    if uploaded is None:
+        st.info("👆 Upload a CSV to begin.")
+        return
+
+    raw_df = pd.read_csv(uploaded)
+    st.dataframe(raw_df.head(10), use_container_width=True)
+
+    run = st.button("▶️ Run forecast", type="primary")
+
+    if run:
+        cfg = ForecastConfig(
+            model_name=model_name,
+            device=device,
+            batch_size=batch_size,
+            timesfm_freq_code=timesfm_freq_code,
+            pandas_freq_fallback=pandas_freq_fallback,
+            horizon_min=h_min,
+            horizon_max=h_max,
+        )
+
+        svc = get_service(model_name=cfg.model_name, device=cfg.device)
+        pipe = ForecastPipeline(svc=svc, config=cfg)
+
+        progress = st.progress(0.0)
+        info = st.empty()
+
+        def progress_cb(batch_idx: int, total_batches: int, message: str):
+            pct = min(1.0, batch_idx / max(1, total_batches))
+            progress.progress(pct)
+            info.write(f"{message} ({batch_idx}/{total_batches})")
+
+        st.info("Running TimesFM… This may take a while for large files.")
+
+        try:
+            forecast_df = pipe.run(raw_df, progress_cb=progress_cb)
+        finally:
+            info.empty()
+            progress.empty()
+
+        hist = DataValidator.standardize_columns(raw_df)
+        hist = DataValidator.parse_dates(hist)
+        hist = DataValidator.sanitize(hist)
+
+        st.session_state["forecast"] = forecast_df
+        st.session_state["history"] = hist
+
+        st.success("✅ Forecast complete!")
+
+    forecast_df = st.session_state["forecast"]
+    hist = st.session_state["history"]
+
+    if forecast_df is None or hist is None:
+        return
+
+    st.subheader("Forecast preview (long format)")
+    st.dataframe(forecast_df.head(20), use_container_width=True)
+
+    st.subheader("Visualize one key")
+    keys_sorted = sorted(hist["key"].unique().tolist())
+    sel_key = st.selectbox("Select key", options=keys_sorted)
+
+    hist_k = hist[hist["key"] == sel_key][["date", "value"]].rename(
+        columns={"value": "y"}
+    )
+    hist_k = hist_k.assign(series="history")
+
+    fcast_k = forecast_df[forecast_df["key"] == sel_key][["date", "forecast"]]
+    fcast_k = fcast_k.rename(columns={"forecast": "y"}).assign(series="forecast")
+
+    display_df = pd.concat([hist_k, fcast_k], ignore_index=True).sort_values("date")
+    st.line_chart(data=display_df, x="date", y="y", color="series", height=340)
+
+    st.subheader("Download")
+    buf = io.StringIO()
+    forecast_df.to_csv(buf, index=False)
+    st.download_button(
+        label="💾 Download forecasts (CSV)",
+        data=buf.getvalue().encode("utf-8"),
+        file_name="timesfm_forecasts_long.csv",
+        mime="text/csv",
+    )
+
+    st.caption(
+        "Output columns: key, date, step, forecast. Each 'step' is the horizon (1..H)."
+    )
+
+
+if __name__ == "__main__":
+    main()