"""Standalone synthetic teaching example. Run locally with Python, not in the HTML."""
import json
import numpy as np
import pandas as pd
from scipy.special import expit

def clean(value):
    if isinstance(value, dict): return {str(k):clean(v) for k,v in value.items()}
    if isinstance(value,(list,tuple,np.ndarray)): return [clean(v) for v in value]
    if isinstance(value,(np.integer,)): return int(value)
    if isinstance(value,(float,np.floating)): return float(value) if np.isfinite(value) else None
    if isinstance(value,(np.bool_,)): return bool(value)
    return value

def print_result(result):
    print(json.dumps(clean(result),ensure_ascii=False,allow_nan=False))


def make_panel(seed=42, T=180, N=24, k=5, mechanism="linear"):
    """Illustrative weekdays, 6 AR factors, future open-to-open k-day label."""
    if mechanism not in {"null","linear","interaction","regime"}:
        raise ValueError("Unknown mechanism")
    rng=np.random.default_rng(seed)
    dates=pd.bdate_range("2020-01-02",periods=T)
    factors=np.empty((T,N,6)); factors[0]=rng.normal(size=(N,6))
    for t in range(1,T):
        factors[t]=.6*factors[t-1]+.8*rng.normal(size=(N,6))
    factors[:,:,3]=.9*factors[:,:,0]+.15*rng.normal(size=(T,N))
    prices=np.full((T,N),100.)
    for t in range(T-1):
        x=factors[max(0,t-1)]
        signal=np.zeros(N)
        if mechanism!="null": signal=.0015*x[:,0]
        if mechanism in {"interaction","regime"}: signal += .0015*x[:,1]*x[:,2]
        if mechanism=="regime" and t>=int(.65*T): signal -= .002*x[:,0]
        noise=.006*rng.standard_t(5,N)/np.sqrt(5/3)+rng.normal(0,.002)
        prices[t+1]=prices[t]*np.exp(signal+noise)
    panel=pd.DataFrame(factors.reshape(T*N,6),columns=[f"x{i}" for i in range(6)])
    panel["date"]=np.repeat(dates,N); panel["stock"]=np.tile([f"S{i:03}" for i in range(N)],T)
    panel["tpos"]=np.repeat(np.arange(T),N); panel["open"]=prices.ravel()
    panel["signal_time"]=panel.date+pd.Timedelta(hours=15)
    panel["feature_available_time"]=panel.signal_time
    labels=panel.groupby("stock").open
    panel["y"]=labels.shift(-(k+1))/labels.shift(-1)-1
    exit_dates=pd.Series(dates).shift(-(k+1)).to_numpy()[panel.tpos]
    panel["label_available_time"]=exit_dates+pd.Timedelta(hours=9,minutes=30)
    return panel

def validate_panel(frame):
    if frame.duplicated(["date","stock"]).any():
        raise ValueError("Duplicate (date,stock) keys")
    if frame[["signal_time","feature_available_time"]].isna().any().any():
        raise ValueError("Missing availability timestamps")
    if (frame.feature_available_time>frame.signal_time).any():
        raise ValueError("Feature was unavailable at decision time")
    if (frame.y.notna() & frame.label_available_time.isna()).any():
        raise ValueError("Known label has unknown availability time")

def time_fold(frame, start, end, train_start=0):
    """Train at prior signal day's 15:00; dates [start,end) are held out."""
    validate_panel(frame)
    dates=frame.date.drop_duplicates().sort_values().reset_index(drop=True)
    if not 1<=start<end<=len(dates) or not 0<=train_start<start:
        raise ValueError("Invalid date fold")
    cutoff=dates.iloc[start-1]+pd.Timedelta(hours=15)
    train=frame[(frame.date>=dates.iloc[train_start]) & (frame.date<dates.iloc[start])
                & frame.y.notna() & (frame.label_available_time<=cutoff)].copy()
    valid=frame[frame.date.isin(dates.iloc[start:end]) & frame.y.notna()].copy()
    if train.empty or valid.empty: raise ValueError("Empty fold")
    return train,valid,cutoff

if __name__ == "__main__":
    panel = make_panel(T=20,N=3,k=5)
    train, valid, cutoff = time_fold(panel,10,14)
    assert sorted(train.tpos.unique()) == [0,1,2,3]
    print_result({"cutoff":str(cutoff),"train_signal_positions":sorted(train.tpos.unique()),
        "train_rows":len(train),"validation_rows":len(valid),
        "label_head":panel.loc[panel.stock=="S000",["tpos","open","y"]].head(4).to_dict("records")})