New tests and his starting scripts

lab1/scripts/run_tuning_experiments.sh

@@ -0,0 +1,140 @@
+#!/usr/bin/env bash
+# Тюнинг поверх полной серии scripts/run_all_experiments.sh.
+# Не повторяет E0–E16: только гиперпараметры, состав признаков, веса, k LSA.
+#
+# Запуск из каталога lab1:
+#   bash scripts/run_tuning_experiments.sh
+#
+# Быстрый черновик:
+#   REPEATS=1 bash scripts/run_tuning_experiments.sh
+
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+PROJECT_ROOT="$(cd "${SCRIPT_DIR}/.." && pwd)"
+cd "${PROJECT_ROOT}"
+
+PYTHON="${PYTHON:-python}"
+REPEATS="${REPEATS:-3}"
+SEED="${SEED:-42}"
+PRESET="${PRESET:-stylometry_pos_lsa}"
+
+LOG_DIR="${PROJECT_ROOT}/results/logs"
+mkdir -p "${LOG_DIR}"
+RUN_ID="${RUN_ID:-$(date +%Y%m%d_%H%M%S)}"
+LOG_FILE="${LOG_DIR}/tune_${RUN_ID}.log"
+exec > >(tee -a "${LOG_FILE}") 2>&1
+
+step() {
+    echo
+    echo "============================================================"
+    echo "== $*"
+    echo "============================================================"
+}
+
+run() {
+    echo
+    echo ">>> $*"
+    "$@"
+}
+
+echo "Тюнинг: $(date)"
+echo "Интерпретатор: ${PYTHON}"
+echo "Повторы: ${REPEATS}, seed: ${SEED}, пресет: ${PRESET}"
+echo "Лог: ${LOG_FILE}"
+
+step "T1. Logreg: C"
+for c in 0.03 0.1 0.3 1 3 10; do
+    run "${PYTHON}" -m stylometry.cli run \
+        --preset "${PRESET}" --model logreg \
+        --repeats "${REPEATS}" --seed "${SEED}" \
+        --model-params "{\"C\": ${c}}"
+done
+
+step "T2. Linear SVM: C"
+for c in 0.03 0.1 0.3 1 3 10; do
+    run "${PYTHON}" -m stylometry.cli run \
+        --preset "${PRESET}" --model linear_svc \
+        --repeats "${REPEATS}" --seed "${SEED}" \
+        --model-params "{\"C\": ${c}}"
+done
+
+step "T3. Logreg без балансировки классов"
+run "${PYTHON}" -m stylometry.cli run \
+    --preset "${PRESET}" --model logreg \
+    --repeats "${REPEATS}" --seed "${SEED}" \
+    --model-params '{"class_weight": null}'
+
+step "T4. Без vocabulary и readability"
+run "${PYTHON}" -m stylometry.cli run \
+    --config configs/tune_no_vocab_readability.toml \
+    --preset "${PRESET}" --model logreg \
+    --repeats "${REPEATS}" --seed "${SEED}"
+
+step "T5. Без vocabulary, readability и length"
+run "${PYTHON}" -m stylometry.cli run \
+    --config configs/tune_no_vocab_readability_length.toml \
+    --preset "${PRESET}" --model logreg \
+    --repeats "${REPEATS}" --seed "${SEED}"
+
+step "T6. Char/POS n-граммы"
+run "${PYTHON}" -m stylometry.cli run \
+    --config configs/tune_char_narrow.toml \
+    --preset "${PRESET}" --model logreg \
+    --repeats "${REPEATS}" --seed "${SEED}"
+run "${PYTHON}" -m stylometry.cli run \
+    --config configs/tune_char_wide.toml \
+    --preset "${PRESET}" --model logreg \
+    --repeats "${REPEATS}" --seed "${SEED}"
+
+step "T7. Веса блоков"
+run "${PYTHON}" -m stylometry.cli run \
+    --config configs/tune_block_weights.toml \
+    --preset "${PRESET}" --model logreg \
+    --repeats "${REPEATS}" --seed "${SEED}"
+
+step "T8. LSA k=150 и k=300 (в полной серии были 50/100/200)"
+run "${PYTHON}" -m stylometry.cli run \
+    --config configs/tune_lsa_k150.toml \
+    --preset "${PRESET}" --model logreg \
+    --repeats "${REPEATS}" --seed "${SEED}"
+run "${PYTHON}" -m stylometry.cli run \
+    --config configs/tune_lsa_k300.toml \
+    --preset "${PRESET}" --model logreg \
+    --repeats "${REPEATS}" --seed "${SEED}"
+run "${PYTHON}" -m stylometry.cli lsa-sweep \
+    --variants word,content,fw,char,pos \
+    --components 150,300 \
+    --model logreg --repeats 1 --seed "${SEED}"
+
+step "T9. Случайный лес: глубина и лист"
+for depth in 10 20 30; do
+    for leaf in 2 3 5; do
+        run "${PYTHON}" -m stylometry.cli run \
+            --preset "${PRESET}" --model random_forest \
+            --repeats "${REPEATS}" --seed "${SEED}" \
+            --model-params "{\"max_depth\": ${depth}, \"min_samples_leaf\": ${leaf}}"
+    done
+done
+run "${PYTHON}" -m stylometry.cli run \
+    --preset "${PRESET}" --model random_forest \
+    --repeats "${REPEATS}" --seed "${SEED}" \
+    --model-params '{"max_depth": 20, "min_samples_leaf": 3, "max_features": 0.1}'
+
+step "T10. Extra trees (не было в benchmark полной серии)"
+run "${PYTHON}" -m stylometry.cli run \
+    --preset "${PRESET}" --model extra_trees \
+    --repeats "${REPEATS}" --seed "${SEED}" \
+    --model-params '{"max_depth": 20, "min_samples_leaf": 3}'
+
+step "T11. Дельта: 50 и 1000 MFW (100/200/500 уже в полной серии)"
+run "${PYTHON}" -m stylometry.cli delta \
+    --features 50,1000 --metrics manhattan,cosine \
+    --repeats 2 --seed "${SEED}"
+
+step "Готово"
+echo "Конец тюнинга: $(date)"
+echo "Лог: ${LOG_FILE}"
+echo
+echo "Сравнить два каталога:"
+echo "  python -m stylometry.cli compare --run-a results/<A> --run-b results/<B>"