forked from chiki2bum2/SniperGold_ML
95 lines
No EOL
3.6 KiB
Python
95 lines
No EOL
3.6 KiB
Python
# -*- coding: utf-8 -*-
|
|
"""P3-S.18 — LOGISTIC BASELINE.
|
|
|
|
Simple linear probabilistic baseline (LogisticRegression, L2, C=1.0, no
|
|
search). Standard scaler fitted on TRAIN ONLY. Binary target: WIN vs LOSS
|
|
(leads only; UNRESOLVED/AMBIGUOUS excluded from fit, retained in evaluation
|
|
as separate columns). Writes predictions CSV columns for evaluate_baselines.
|
|
"""
|
|
import csv
|
|
import json
|
|
import os
|
|
import sys
|
|
|
|
import numpy as np
|
|
from sklearn.linear_model import LogisticRegression
|
|
from sklearn.preprocessing import StandardScaler
|
|
|
|
HERE = os.path.dirname(os.path.abspath(__file__))
|
|
OUT = os.path.join(HERE, "output")
|
|
sys.path.insert(0, HERE)
|
|
sys.path.insert(0, os.path.normpath(os.path.join(HERE, "..", "setup_dataset")))
|
|
|
|
import prepare_dataset as PD # noqa: E402
|
|
|
|
SEED = 42
|
|
|
|
|
|
def main():
|
|
os.makedirs(OUT, exist_ok=True)
|
|
ctx = PD.load_verified_population()
|
|
rows = PD.build_rows(ctx)
|
|
# binary subset = leads with WIN/LOSS
|
|
bin_rows = [r for r in rows if r["lead"] and r["outcome"] in PD.BINARY_CLASSES]
|
|
bin_rows.sort(key=lambda r: (r["creation_bar"], r["setup_id"]))
|
|
tr_ids = set()
|
|
tr, va, te, _ = PD.temporal_split(rows)
|
|
tr_ids = {id(r) for r in tr}
|
|
# rebuild split membership by setup_id (stable)
|
|
split_map = {}
|
|
for part, tag in ((tr, "train"), (va, "val"), (te, "test")):
|
|
for r in part:
|
|
split_map[r["setup_id"]] = tag
|
|
X = np.asarray([[r["feature_" + k] for k in PD.FEATURE_COLS]
|
|
for r in bin_rows], dtype=float)
|
|
y = np.asarray([1.0 if r["outcome"] == "WIN" else 0.0
|
|
for r in bin_rows], dtype=float)
|
|
splits = np.asarray([split_map[r["setup_id"]] for r in bin_rows])
|
|
|
|
scaler = StandardScaler().fit(X[splits == "train"])
|
|
Xs = scaler.transform(X)
|
|
clf = LogisticRegression(C=1.0, max_iter=5000, random_state=SEED)
|
|
clf.fit(Xs[splits == "train"], y[splits == "train"])
|
|
p = clf.predict_proba(Xs)[:, 1]
|
|
|
|
rows_out = []
|
|
for i, r in enumerate(bin_rows):
|
|
rows_out.append({
|
|
"setup_id": r["setup_id"], "split": splits[i],
|
|
"outcome": r["outcome"], "y": int(y[i]),
|
|
"pred_logistic": float(p[i]),
|
|
})
|
|
with open(os.path.join(OUT, "p3_s18_predictions_logistic.csv"), "w",
|
|
newline="", encoding="utf-8") as f:
|
|
w = csv.DictWriter(f, fieldnames=list(rows_out[0].keys()))
|
|
w.writeheader()
|
|
for r in rows_out:
|
|
w.writerow(r)
|
|
|
|
coef = {PD.FEATURE_COLS[i]: float(clf.coef_[0][i])
|
|
for i in range(len(PD.FEATURE_COLS))}
|
|
with open(os.path.join(OUT, "p3_s18_logistic_model.json"), "w",
|
|
encoding="utf-8") as f:
|
|
json.dump({
|
|
"model": "LogisticRegression(C=1.0, L2, standardized-train-only)",
|
|
"feature_sha16": PD.make_manifest(
|
|
rows, tr, va, te, True)["feature_sha16"],
|
|
"seed": SEED, "n_train": int((splits == "train").sum()),
|
|
"n_val": int((splits == "val").sum()),
|
|
"n_test": int((splits == "test").sum()),
|
|
"class_counts": {
|
|
"train_win": int(((splits == "train") & (y == 1)).sum()),
|
|
"train_loss": int(((splits == "train") & (y == 0)).sum()),
|
|
"val_win": int(((splits == "val") & (y == 1)).sum()),
|
|
"val_loss": int(((splits == "val") & (y == 0)).sum()),
|
|
"test_win": int(((splits == "test") & (y == 1)).sum()),
|
|
"test_loss": int(((splits == "test") & (y == 0)).sum()),
|
|
},
|
|
"coefficients": coef,
|
|
}, f, indent=2)
|
|
print("[saved] p3_s18_predictions_logistic.csv / logistic_model.json")
|
|
return 0
|
|
|
|
|
|
if __name__ == "__main__":
|
|
sys.exit(main()) |