Initial commit
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
This commit is contained in:
lofyer
co-authored by
factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
commit
71db82393a
@@ -0,0 +1,207 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
批量报告生成脚本：为长宁区全部9所学校生成课程实施监测报告
|
||||
数据加载和赋分/统计只做一次，LLM和渲染对每校独立执行
|
||||
"""
|
||||
import sys
|
||||
import time
|
||||
import argparse
|
||||
import logging
|
||||
from pathlib import Path
|
||||
|
||||
sys.path.insert(0, str(Path(__file__).parent.parent / "backend"))
|
||||
|
||||
from app.engines.data_engine import DataEngine
|
||||
from app.engines.scoring_engine import ScoringEngine
|
||||
from app.engines.stats_engine import StatsEngine
|
||||
from app.engines.llm_engine import LLMEngine
|
||||
from app.engines.report_renderer import ReportRenderer
|
||||
|
||||
logging.basicConfig(
|
||||
level=logging.INFO,
|
||||
format="%(asctime)s [%(levelname)s] %(message)s",
|
||||
datefmt="%H:%M:%S",
|
||||
)
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def progress_callback(completed, total, segment_id):
|
||||
"""进度回调"""
|
||||
pct = completed / total * 100
|
||||
bar = "█" * int(pct / 5) + "░" * (20 - int(pct / 5))
|
||||
print(f"\r [{bar}] {pct:.0f}% ({completed}/{total}) {segment_id:<40}", end="", flush=True)
|
||||
|
||||
|
||||
def main():
|
||||
parser = argparse.ArgumentParser(description="批量生成全部学校课程实施监测报告")
|
||||
parser.add_argument("--no-cache", action="store_true", help="不使用LLM缓存")
|
||||
parser.add_argument("--no-llm", action="store_true", help="跳过LLM生成（仅图表+数据）")
|
||||
parser.add_argument("--schools", nargs="*", help="指定学校列表（默认全部9所）")
|
||||
args = parser.parse_args()
|
||||
|
||||
total_start = time.time()
|
||||
|
||||
print("=" * 70)
|
||||
print("📊 课程实施监测报告 — 批量生成系统")
|
||||
print("=" * 70)
|
||||
|
||||
# ===== Step 1: 加载数据（只做一次） =====
|
||||
logger.info("[全局 1/3] 加载Excel数据...")
|
||||
data_engine = DataEngine()
|
||||
data_engine.load_all()
|
||||
|
||||
# ===== Step 2: 全区赋分（只做一次） =====
|
||||
logger.info("[全局 2/3] 全区赋分计算...")
|
||||
scoring_engine = ScoringEngine(data_engine)
|
||||
raw_scores = scoring_engine.score_all_schools()
|
||||
|
||||
# ===== Step 3: 统计分析（只做一次） =====
|
||||
logger.info("[全局 3/3] PCA合成 + 标准化...")
|
||||
stats_engine = StatsEngine()
|
||||
sub_scores = stats_engine.compute_dimension_scores(raw_scores)
|
||||
dim_scores = stats_engine.compute_dimension_aggregates(sub_scores)
|
||||
|
||||
# 确定生成哪些学校
|
||||
all_schools = list(data_engine.schools)
|
||||
if args.schools:
|
||||
schools = []
|
||||
for s in args.schools:
|
||||
if s in all_schools:
|
||||
schools.append(s)
|
||||
else:
|
||||
print(f" ⚠️ 学校 '{s}' 不在数据中，跳过")
|
||||
if not schools:
|
||||
print("❌ 没有有效的学校，退出")
|
||||
return
|
||||
else:
|
||||
schools = all_schools
|
||||
|
||||
print(f"\n🏫 将为以下 {len(schools)} 所学校生成报告：")
|
||||
for i, s in enumerate(schools, 1):
|
||||
from app.config import SCHOOL_TYPE_MAP
|
||||
info = SCHOOL_TYPE_MAP.get(s, {})
|
||||
print(f" {i}. {s} ({info.get('type', '未知类型')})")
|
||||
|
||||
# ===== 初始化引擎 =====
|
||||
renderer = ReportRenderer()
|
||||
llm_engine = None
|
||||
if not args.no_llm:
|
||||
llm_engine = LLMEngine()
|
||||
llm_engine.set_progress_callback(progress_callback)
|
||||
|
||||
output_dir = Path(__file__).parent.parent / "output"
|
||||
output_dir.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
# ===== 逐校生成 =====
|
||||
results = []
|
||||
for idx, school in enumerate(schools, 1):
|
||||
school_start = time.time()
|
||||
print(f"\n{'─' * 70}")
|
||||
print(f"🔄 [{idx}/{len(schools)}] 正在生成: {school}")
|
||||
print(f"{'─' * 70}")
|
||||
|
||||
try:
|
||||
# 统计分析（学校专属数据包）
|
||||
report_data = stats_engine.compute_school_report_data(school, sub_scores, dim_scores)
|
||||
|
||||
# LLM生成
|
||||
if args.no_llm:
|
||||
print(" ⏭️ 跳过LLM生成（--no-llm模式）")
|
||||
llm_sections = {}
|
||||
else:
|
||||
print(" 🤖 LLM并行生成报告文字...")
|
||||
llm_sections = llm_engine.generate_report_segments(
|
||||
report_data,
|
||||
use_cache=not args.no_cache,
|
||||
)
|
||||
print() # 换行（progress bar之后）
|
||||
|
||||
# 渲染HTML
|
||||
output_path = output_dir / f"{school}_报告.html"
|
||||
renderer.render_to_file(report_data, llm_sections, output_path)
|
||||
|
||||
# 保存数据JSON
|
||||
import json
|
||||
|
||||
def _json_safe(obj):
|
||||
"""处理numpy类型"""
|
||||
import numpy as np
|
||||
if isinstance(obj, (np.integer,)):
|
||||
return int(obj)
|
||||
if isinstance(obj, (np.floating,)):
|
||||
return float(obj)
|
||||
if isinstance(obj, np.ndarray):
|
||||
return obj.tolist()
|
||||
raise TypeError(f"Object of type {type(obj)} is not JSON serializable")
|
||||
|
||||
json_path = output_dir / f"{school}_report_data.json"
|
||||
with open(json_path, "w", encoding="utf-8") as f:
|
||||
json.dump(report_data, f, ensure_ascii=False, indent=2, default=_json_safe)
|
||||
|
||||
elapsed = time.time() - school_start
|
||||
score = report_data["overall"]["score"]
|
||||
rank = report_data["overall"]["rank_in_district"]
|
||||
cluster = report_data["overall"]["cluster"]
|
||||
llm_count = len(llm_sections)
|
||||
|
||||
results.append({
|
||||
"school": school,
|
||||
"status": "✅",
|
||||
"score": score,
|
||||
"rank": rank,
|
||||
"cluster": cluster,
|
||||
"llm_segments": llm_count,
|
||||
"time": elapsed,
|
||||
"output": str(output_path),
|
||||
})
|
||||
|
||||
print(f" ✅ 完成! 得分={score}分 排名={rank}/9 类型={cluster} LLM={llm_count}段 耗时={elapsed:.1f}s")
|
||||
|
||||
except Exception as e:
|
||||
elapsed = time.time() - school_start
|
||||
logger.error(f" ❌ 生成失败: {e}", exc_info=True)
|
||||
results.append({
|
||||
"school": school,
|
||||
"status": "❌",
|
||||
"error": str(e),
|
||||
"time": elapsed,
|
||||
})
|
||||
|
||||
# ===== 汇总报告 =====
|
||||
total_elapsed = time.time() - total_start
|
||||
|
||||
print(f"\n{'=' * 70}")
|
||||
print(f"📋 批量生成结果汇总")
|
||||
print(f"{'=' * 70}")
|
||||
print(f"{'学校':<10} {'状态':<4} {'得分':<8} {'排名':<8} {'类型':<8} {'LLM段':<8} {'耗时':<8}")
|
||||
print(f"{'─' * 62}")
|
||||
|
||||
success_count = 0
|
||||
for r in results:
|
||||
if r["status"] == "✅":
|
||||
success_count += 1
|
||||
print(f"{r['school']:<10} {r['status']:<4} {r['score']:<8.2f} {r['rank']}/9{'':<5} {r['cluster']:<8} {r['llm_segments']:<8} {r['time']:.1f}s")
|
||||
else:
|
||||
print(f"{r['school']:<10} {r['status']:<4} {'失败: ' + r.get('error', '未知')}")
|
||||
|
||||
print(f"{'─' * 62}")
|
||||
print(f"成功: {success_count}/{len(schools)} | 总耗时: {total_elapsed:.1f}s")
|
||||
print(f"输出目录: {output_dir}")
|
||||
print(f"{'=' * 70}")
|
||||
|
||||
# 保存汇总JSON
|
||||
import json
|
||||
summary_path = output_dir / "batch_summary.json"
|
||||
with open(summary_path, "w", encoding="utf-8") as f:
|
||||
json.dump({
|
||||
"generated_at": time.strftime("%Y-%m-%d %H:%M:%S"),
|
||||
"total_schools": len(schools),
|
||||
"success_count": success_count,
|
||||
"total_time": round(total_elapsed, 1),
|
||||
"results": results,
|
||||
}, f, ensure_ascii=False, indent=2)
|
||||
print(f"汇总文件: {summary_path}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
Reference in New Issue
Block a user