386 lines
15 KiB
Python
386 lines
15 KiB
Python
#!/usr/bin/env python3
|
||
"""
|
||
生成课消指标 Excel：按周 + 按 L1/L2 拆分
|
||
"""
|
||
import psycopg2
|
||
from collections import defaultdict
|
||
from datetime import datetime, timedelta, date
|
||
import openpyxl
|
||
from openpyxl.styles import Font, Alignment, PatternFill, Border, Side
|
||
from openpyxl.chart import LineChart, Reference
|
||
from openpyxl.utils import get_column_letter
|
||
from openpyxl.chart.label import DataLabelList
|
||
from openpyxl.chart.series import DataPoint
|
||
|
||
conn = psycopg2.connect(
|
||
host="bj-postgres-16pob4sg.sql.tencentcdb.com",
|
||
port=28591, user="ai_member",
|
||
password="LdfjdjL83h3h3^$&**YGG*", dbname="vala_bi"
|
||
)
|
||
cur = conn.cursor()
|
||
|
||
# ===== 时间参数 =====
|
||
overall_start = date(2025, 9, 1)
|
||
overall_end = date(2026, 5, 11)
|
||
|
||
weeks = []
|
||
d = overall_start
|
||
while d < overall_end:
|
||
ws = d
|
||
days_to_sunday = 6 - d.weekday()
|
||
we = d + timedelta(days=days_to_sunday)
|
||
if we >= overall_end:
|
||
we = overall_end - timedelta(days=1)
|
||
weeks.append((ws, we))
|
||
d = we + timedelta(days=1)
|
||
|
||
# ===== Step 1: 用户分类 =====
|
||
print("Step 1: 分类付费用户...")
|
||
cur.execute("""
|
||
SELECT o.account_id, o.trade_no, o.order_status, o.pay_success_date,
|
||
CASE WHEN o.goods_id IN (57, 60, 63) THEN 'L1'
|
||
WHEN o.goods_id = 61 THEN 'L1+L2'
|
||
WHEN o.goods_id IN (31, 32, 33, 54) THEN 'L2'
|
||
ELSE '其他' END as level_type
|
||
FROM bi_vala_order o
|
||
INNER JOIN bi_vala_app_account a ON o.account_id = a.id
|
||
WHERE a.status = 1 AND a.deleted_at IS NULL AND o.pay_success_date IS NOT NULL
|
||
""")
|
||
orders = cur.fetchall()
|
||
print(f" 订单数: {len(orders)}")
|
||
|
||
cur.execute("SELECT trade_no FROM bi_refund_order WHERE status = 3")
|
||
refund_trades = set(r[0] for r in cur.fetchall())
|
||
|
||
user_data = defaultdict(lambda: {'levels': set(), 'orders': []})
|
||
for aid, trade_no, order_status, pay_date, lt in orders:
|
||
is_refunded = (order_status == 4 and trade_no in refund_trades)
|
||
user_data[aid]['levels'].add(lt)
|
||
user_data[aid]['orders'].append((pay_date.date(), is_refunded, lt))
|
||
|
||
def classify_user(levels):
|
||
has_l1, has_l2 = 'L1' in levels, 'L2' in levels
|
||
return 'L1+L2' if ('L1+L2' in levels or (has_l1 and has_l2)) else ('仅L1' if has_l1 else ('仅L2' if has_l2 else '其他'))
|
||
|
||
for aid in user_data:
|
||
user_data[aid]['category'] = classify_user(user_data[aid]['levels'])
|
||
|
||
def is_paid_as_of(aid, as_of_date):
|
||
return sum(1 for pd, ref, lt in user_data[aid]['orders'] if pd <= as_of_date and not ref) > 0
|
||
|
||
# ===== Step 2: 课消 =====
|
||
print("Step 2: 查询课消...")
|
||
consumption_map = {}
|
||
for table_idx in range(8):
|
||
tbl = f"bi_user_chapter_play_record_{table_idx}"
|
||
cur.execute(f"""
|
||
SELECT user_id, chapter_id, updated_at
|
||
FROM {tbl}
|
||
WHERE play_status = 1 AND updated_at >= '2025-09-01' AND updated_at < '2026-05-11'
|
||
""")
|
||
for user_id, chapter_id, updated_at in cur.fetchall():
|
||
key = (user_id, chapter_id)
|
||
d = updated_at.date() if hasattr(updated_at, 'date') else datetime.strptime(str(updated_at)[:10], '%Y-%m-%d').date()
|
||
if key not in consumption_map or d < consumption_map[key]:
|
||
consumption_map[key] = d
|
||
|
||
print(f" 去重后: {len(consumption_map)} 条")
|
||
|
||
# ===== Step 3: 角色映射 =====
|
||
print("Step 3: 角色映射...")
|
||
all_uids = list(set(k[0] for k in consumption_map))
|
||
char2acct = {}
|
||
bs = 500
|
||
for i in range(0, len(all_uids), bs):
|
||
batch = all_uids[i:i+bs]
|
||
ph = ','.join(['%s'] * len(batch))
|
||
cur.execute(f"SELECT id, account_id FROM bi_vala_app_character WHERE id IN ({ph})", batch)
|
||
for cid, aid in cur.fetchall():
|
||
char2acct[cid] = aid
|
||
print(f" 映射: {len(char2acct)}")
|
||
|
||
# ===== Step 4: 按周汇总 =====
|
||
print("Step 4: 按周汇总...")
|
||
results = []
|
||
for ws, we in weeks:
|
||
paid_by_cat = defaultdict(set)
|
||
for aid in user_data:
|
||
if is_paid_as_of(aid, we):
|
||
paid_by_cat[user_data[aid]['category']].add(aid)
|
||
|
||
cons_by_cat = defaultdict(int)
|
||
cons_users_by_cat = defaultdict(set)
|
||
|
||
for (uid, ch_id), cons_date in consumption_map.items():
|
||
if ws <= cons_date <= we:
|
||
aid = char2acct.get(uid)
|
||
if aid:
|
||
cat = user_data.get(aid, {}).get('category', '其他')
|
||
if aid in paid_by_cat.get(cat, set()):
|
||
cons_by_cat[cat] += 1
|
||
cons_users_by_cat[cat].add(aid)
|
||
|
||
row = {'ws': ws, 'we': we}
|
||
for cat in ['仅L1', '仅L2', 'L1+L2', '其他', '合计']:
|
||
if cat == '合计':
|
||
n_paid = sum(len(v) for v in paid_by_cat.values())
|
||
n_cons = sum(cons_by_cat.values())
|
||
n_cons_users = len(set.union(*cons_users_by_cat.values())) if cons_users_by_cat else 0
|
||
else:
|
||
n_paid = len(paid_by_cat.get(cat, set()))
|
||
n_cons = cons_by_cat.get(cat, 0)
|
||
n_cons_users = len(cons_users_by_cat.get(cat, set()))
|
||
|
||
row[f'{cat}_paid'] = n_paid
|
||
row[f'{cat}_cons'] = n_cons
|
||
row[f'{cat}_cons_users'] = n_cons_users
|
||
row[f'{cat}_avg_all'] = round(n_cons / n_paid, 2) if n_paid > 0 else 0
|
||
row[f'{cat}_avg_cons'] = round(n_cons / n_cons_users, 2) if n_cons_users > 0 else 0
|
||
|
||
results.append(row)
|
||
|
||
cur.close()
|
||
conn.close()
|
||
|
||
# ===== 生成 Excel =====
|
||
print("\n生成 Excel...")
|
||
wb = openpyxl.Workbook()
|
||
|
||
# 样式
|
||
header_font = Font(name='微软雅黑', bold=True, size=10, color='FFFFFF')
|
||
header_fill = PatternFill(start_color='2F5496', end_color='2F5496', fill_type='solid')
|
||
data_font = Font(name='微软雅黑', size=10)
|
||
title_font = Font(name='微软雅黑', bold=True, size=14, color='2F5496')
|
||
subtitle_font = Font(name='微软雅黑', bold=True, size=11, color='2F5496')
|
||
border = Border(left=Side(style='thin'), right=Side(style='thin'), top=Side(style='thin'), bottom=Side(style='thin'))
|
||
center = Alignment(horizontal='center', vertical='center')
|
||
|
||
l1_fill = PatternFill(start_color='DAEEF3', end_color='DAEEF3', fill_type='solid')
|
||
l2_fill = PatternFill(start_color='FDE9D9', end_color='FDE9D9', fill_type='solid')
|
||
l1l2_fill = PatternFill(start_color='E4DFEC', end_color='E4DFEC', fill_type='solid')
|
||
total_fill = PatternFill(start_color='D9EAD3', end_color='D9EAD3', fill_type='solid')
|
||
|
||
def apply_cell(ws, row, col, value, font=data_font, fill=None, border_style=border, align=center):
|
||
c = ws.cell(row=row, column=col, value=value)
|
||
c.font, c.border, c.alignment = font, border_style, align
|
||
if fill: c.fill = fill
|
||
return c
|
||
|
||
def apply_header(ws, row, col, value):
|
||
c = ws.cell(row=row, column=col, value=value)
|
||
c.font, c.fill, c.border, c.alignment = header_font, header_fill, border, center
|
||
return c
|
||
|
||
# ===== Sheet 1: 概览 =====
|
||
ws1 = wb.active
|
||
ws1.title = "概览"
|
||
ws1.merge_cells('A1:G1')
|
||
apply_cell(ws1, 1, 1, "付费用户 L1/L2 课消分析", font=title_font, border_style=Border(), align=Alignment(horizontal='left'))
|
||
ws1.merge_cells('A2:G2')
|
||
apply_cell(ws1, 2, 1, f"数据区间: 2025-09-01 ~ 2026-05-10 | 更新日期: 2026-05-14", font=Font(name='微软雅黑', size=9, color='666666'), border_style=Border(), align=Alignment(horizontal='left'))
|
||
|
||
# 口径说明
|
||
notes = [
|
||
"口径说明：",
|
||
"• 课消：用户首次完成某一课时（play_status=1，按(user_id,chapter_id)取最早updated_at）",
|
||
"• L1商品: goods_id IN (57,60,63) | L2商品: goods_id IN (31,32,33,54) | L1+L2商品: goods_id=61",
|
||
"• 付费用户：status=1 + deleted_at IS NULL + 有订单 + 未全部退款",
|
||
"• 人均课消 = 周内课消次数 / 付费用户数",
|
||
"• 有消用户人均 = 周内课消次数 / 至少完成1次课消的付费用户数",
|
||
]
|
||
for i, note in enumerate(notes):
|
||
apply_cell(ws1, 4+i, 1, note, font=Font(name='微软雅黑', size=9), border_style=Border(), align=Alignment(horizontal='left'))
|
||
|
||
# 汇总表
|
||
row = 11
|
||
ws1.merge_cells(f'A{row}:K{row}')
|
||
apply_cell(ws1, row, 1, "付费用户分类（截至最后一周）", font=subtitle_font, border_style=Border(), align=Alignment(horizontal='left'))
|
||
row += 1
|
||
|
||
headers_summary = ['分类', '付费用户数', '占比']
|
||
for j, h in enumerate(headers_summary, 1):
|
||
apply_header(ws1, row, j, h)
|
||
row += 1
|
||
|
||
last = results[-1]
|
||
cats_data = [('仅L1', last['仅L1_paid']), ('仅L2', last['仅L2_paid']), ('L1+L2', last['L1+L2_paid'])]
|
||
total = sum(v for _, v in cats_data)
|
||
for cat, v in cats_data:
|
||
apply_cell(ws1, row, 1, cat)
|
||
apply_cell(ws1, row, 2, v)
|
||
apply_cell(ws1, row, 3, f"{v/total*100:.1f}%")
|
||
if '仅L1' in cat: fill = l1_fill
|
||
elif '仅L2' in cat: fill = l2_fill
|
||
else: fill = l1l2_fill
|
||
for c in range(1, 4): ws1.cell(row=row, column=c).fill = fill
|
||
row += 1
|
||
|
||
apply_cell(ws1, row, 1, '合计', font=Font(name='微软雅黑', bold=True, size=10))
|
||
apply_cell(ws1, row, 2, total, font=Font(name='微软雅黑', bold=True, size=10))
|
||
apply_cell(ws1, row, 3, '100%', font=Font(name='微软雅黑', bold=True, size=10))
|
||
for c in range(1, 4): ws1.cell(row=row, column=c).fill = total_fill
|
||
|
||
# 近期趋势摘要
|
||
row += 2
|
||
ws1.merge_cells(f'A{row}:K{row}')
|
||
apply_cell(ws1, row, 1, "近期人均课消趋势", font=subtitle_font, border_style=Border(), align=Alignment(horizontal='left'))
|
||
row += 1
|
||
|
||
trend_headers = ['周', '合计人均', '仅L1人均', '仅L2人均', 'L1+L2人均', '合计有消人均', '仅L1有消人均', '仅L2有消人均', 'L1+L2有消人均']
|
||
for j, h in enumerate(trend_headers, 1):
|
||
apply_header(ws1, row, j, h)
|
||
row += 1
|
||
|
||
for r in results[-8:]: # 最近8周
|
||
wl = f"{r['ws'].strftime('%m/%d')}-{r['we'].strftime('%m/%d')}"
|
||
apply_cell(ws1, row, 1, wl, font=Font(name='微软雅黑', size=9))
|
||
apply_cell(ws1, row, 2, r['合计_avg_all'], font=Font(name='微软雅黑', size=9))
|
||
apply_cell(ws1, row, 3, r['仅L1_avg_all'], font=Font(name='微软雅黑', size=9))
|
||
apply_cell(ws1, row, 4, r['仅L2_avg_all'], font=Font(name='微软雅黑', size=9))
|
||
apply_cell(ws1, row, 5, r['L1+L2_avg_all'], font=Font(name='微软雅黑', size=9))
|
||
apply_cell(ws1, row, 6, r['合计_avg_cons'], font=Font(name='微软雅黑', size=9))
|
||
apply_cell(ws1, row, 7, r['仅L1_avg_cons'], font=Font(name='微软雅黑', size=9))
|
||
apply_cell(ws1, row, 8, r['仅L2_avg_cons'], font=Font(name='微软雅黑', size=9))
|
||
apply_cell(ws1, row, 9, r['L1+L2_avg_cons'], font=Font(name='微软雅黑', size=9))
|
||
row += 1
|
||
|
||
# 列宽
|
||
for col in range(1, 10):
|
||
ws1.column_dimensions[get_column_letter(col)].width = 14
|
||
|
||
# ===== Sheet 2: 明细 =====
|
||
ws2 = wb.create_sheet("每周明细")
|
||
|
||
# 标题行
|
||
row2 = 1
|
||
# 第一部分：付费用户数
|
||
group_headers = [
|
||
('付费用户数', ['合计', '仅L1', '仅L2', 'L1+L2']),
|
||
('课消次数', ['合计', '仅L1', '仅L2', 'L1+L2']),
|
||
('有课消用户数', ['合计', '仅L1', '仅L2', 'L1+L2']),
|
||
('人均课消（全部付费用户）', ['合计', '仅L1', '仅L2', 'L1+L2']),
|
||
('人均课消（有课消用户）', ['合计', '仅L1', '仅L2', 'L1+L2']),
|
||
]
|
||
|
||
apply_header(ws2, row2, 1, '周')
|
||
apply_header(ws2, row2, 2, '周一起')
|
||
apply_header(ws2, row2, 3, '周日')
|
||
col = 4
|
||
spans = []
|
||
for grp_name, cols in group_headers:
|
||
start_col = col
|
||
for _ in cols:
|
||
col += 1
|
||
end_col = col - 1
|
||
if start_col < end_col:
|
||
ws2.merge_cells(start_row=row2, start_column=start_col, end_row=row2, end_column=end_col)
|
||
apply_header(ws2, row2, start_col, grp_name)
|
||
spans.append((start_col, end_col, grp_name, cols))
|
||
for ic, cname in enumerate(cols):
|
||
apply_header(ws2, row2+1, start_col+ic, cname)
|
||
col_count = col - 1
|
||
|
||
# 数据
|
||
row2 = 3
|
||
for r in results:
|
||
wl = f"{r['ws'].strftime('%m/%d')}-{r['we'].strftime('%m/%d')}"
|
||
apply_cell(ws2, row2, 1, wl)
|
||
apply_cell(ws2, row2, 2, r['ws'].strftime('%Y-%m-%d'))
|
||
apply_cell(ws2, row2, 3, r['we'].strftime('%Y-%m-%d'))
|
||
col = 4
|
||
for grp_name, cols in group_headers:
|
||
for cname in cols:
|
||
key_map = {
|
||
'付费用户数': f"{cname}_paid",
|
||
'课消次数': f"{cname}_cons",
|
||
'有课消用户数': f"{cname}_cons_users",
|
||
'人均课消（全部付费用户）': f"{cname}_avg_all",
|
||
'人均课消（有课消用户）': f"{cname}_avg_cons",
|
||
}
|
||
val = r[key_map[grp_name]]
|
||
apply_cell(ws2, row2, col, val)
|
||
col += 1
|
||
row2 += 1
|
||
|
||
# 列宽
|
||
ws2.column_dimensions['A'].width = 14
|
||
ws2.column_dimensions['B'].width = 12
|
||
ws2.column_dimensions['C'].width = 12
|
||
for ci in range(4, col_count + 1):
|
||
ws2.column_dimensions[get_column_letter(ci)].width = 10
|
||
|
||
# 冻结首3列+标题
|
||
ws2.freeze_panes = 'D4'
|
||
|
||
# ===== 图表 =====
|
||
chart_sheet = wb.create_sheet("图表")
|
||
|
||
# Chart 1: 人均课消趋势（按类别）
|
||
chart1 = LineChart()
|
||
chart1.title = "人均课消数（全部付费用户）"
|
||
chart1.style = 10
|
||
chart1.y_axis.title = "课消数（节/周）"
|
||
chart1.x_axis.title = None
|
||
chart1.width = 28
|
||
chart1.height = 14
|
||
chart1.y_axis.scaling.min = 0
|
||
|
||
data_row_start = 3
|
||
data_row_end = row2 - 1
|
||
|
||
# Categories (周标签)
|
||
cats_ref = Reference(ws2, min_col=1, min_row=data_row_start, max_row=data_row_end)
|
||
|
||
# 各系列列号（人均课消 - 全部付费用户 section）
|
||
# 合计: col 16, 仅L1: col 17, 仅L2: col 18, L1+L2: col 19
|
||
# 需要先确定列号
|
||
header_row = 2
|
||
grp_col_map = {}
|
||
col = 4
|
||
for grp_name, cols in group_headers:
|
||
grp_col_map[grp_name] = col
|
||
col += len(cols)
|
||
|
||
# 人均课消（全部）: group 4, 从 grp_col_map['人均课消（全部付费用户）']
|
||
start_avg = grp_col_map['人均课消（全部付费用户）']
|
||
colors = ['333333', '4A90D9', 'E85D47', '7B9E4B']
|
||
labels = ['合计', '仅L1', '仅L2', 'L1+L2']
|
||
for i in range(4):
|
||
ref = Reference(ws2, min_col=start_avg+i, min_row=data_row_start-1, max_row=data_row_end) # -1 for header in row2
|
||
chart1.add_data(ref, titles_from_data=True)
|
||
chart1.set_categories(cats_ref)
|
||
s = chart1.series[i]
|
||
s.graphicalProperties.line.solidFill = colors[i]
|
||
s.graphicalProperties.line.width = 25000 if i == 0 else 20000
|
||
if i > 0:
|
||
s.graphicalProperties.line.dashStyle = 'solid'
|
||
|
||
chart_sheet.add_chart(chart1, "A1")
|
||
|
||
# Chart 2: 付费用户数增长
|
||
chart2 = LineChart()
|
||
chart2.title = "付费用户数增长趋势"
|
||
chart2.style = 10
|
||
chart2.y_axis.title = "用户数"
|
||
chart2.width = 28
|
||
chart2.height = 14
|
||
|
||
start_paid = grp_col_map['付费用户数']
|
||
for i in range(4):
|
||
ref = Reference(ws2, min_col=start_paid+i, min_row=data_row_start-1, max_row=data_row_end)
|
||
chart2.add_data(ref, titles_from_data=True)
|
||
chart2.set_categories(cats_ref)
|
||
s = chart2.series[i]
|
||
s.graphicalProperties.line.solidFill = colors[i]
|
||
s.graphicalProperties.line.width = 25000 if i == 0 else 20000
|
||
|
||
chart_sheet.add_chart(chart2, "A18")
|
||
|
||
# ===== 保存 =====
|
||
path = '/root/.openclaw/workspace/output/course_consumption_by_level.xlsx'
|
||
wb.save(path)
|
||
print(f"\n✅ Excel 已保存: {path}")
|
||
print(f" Sheet 1: 概览（口径说明 + 近期趋势）")
|
||
print(f" Sheet 2: 每周明细（36周完整数据）")
|
||
print(f" Sheet 3: 图表（人均课消趋势 + 付费用户增长）")
|