631 lines
28 KiB
Python
631 lines
28 KiB
Python
#!/usr/bin/env python3
|
||
"""达播业务三维度深度分析图表：达人 × 月度 × 平台"""
|
||
import openpyxl, glob, os, numpy as np
|
||
from datetime import datetime, timedelta
|
||
from collections import defaultdict
|
||
import matplotlib
|
||
matplotlib.use('Agg')
|
||
import matplotlib.pyplot as plt
|
||
import matplotlib.ticker as mticker
|
||
|
||
plt.rcParams['font.sans-serif'] = ['WenQuanYi Micro Hei', 'Noto Sans CJK SC', 'SimHei', 'DejaVu Sans']
|
||
plt.rcParams['axes.unicode_minus'] = False
|
||
|
||
# === Colors ===
|
||
C_BLUE = '#2563EB'; C_GOLD = '#F59E0B'; C_RED = '#EF4444'; C_GREEN = '#10B981'
|
||
C_PURPLE = '#8B5CF6'; C_TEAL = '#14B8A6'; C_PINK = '#EC4899'; C_ORANGE = '#F97316'
|
||
C_DARK = '#1F2937'; C_GRAY = '#6B7280'; C_LIGHT = '#F3F4F6'
|
||
PALETTE = [C_BLUE, C_GOLD, C_RED, C_PURPLE, C_GREEN, C_PINK, C_TEAL, C_ORANGE, '#6366F1', '#84CC16']
|
||
PALETTE_SOFT = ['#BFDBFE','#FDE68A','#FECACA','#C4B5FD','#A7F3D0','#FBCFE8','#99F6E4','#FDBA74','#C7D2FE','#BEF264']
|
||
|
||
# === Data loading ===
|
||
files = glob.glob('/root/.openclaw/media/inbound/*3403f15a*')
|
||
wb = openpyxl.load_workbook(files[0])
|
||
ws = wb['Sheet1']
|
||
|
||
def excel_date_to_str(val):
|
||
if val is None: return None
|
||
if isinstance(val, datetime): return val.strftime('%Y-%m-%d')
|
||
if isinstance(val, str): return val
|
||
if isinstance(val, (int, float)):
|
||
try: return (datetime(1899,12,30)+timedelta(days=int(val))).strftime('%Y-%m-%d')
|
||
except: return str(val)
|
||
return str(val)
|
||
|
||
data = []
|
||
for row in ws.iter_rows(min_row=2, max_row=ws.max_row, values_only=True):
|
||
name = str(row[0]).strip() if row[0] else ''
|
||
if '合计' in name or '总计' in name or row[3] is None: continue
|
||
data.append({
|
||
'name': name, 'date': excel_date_to_str(row[1]),
|
||
'platform': str(row[2]).strip() if row[2] else '',
|
||
'orders': row[3], 'gmv': row[4] or 0, 'refund_orders': row[5] or 0,
|
||
'refund_amount': row[6] or 0, 'gsv': row[10] or 0,
|
||
})
|
||
|
||
# Name norm
|
||
name_map = {
|
||
'晚柠也是个妈妈了':'晚柠','晚柠':'晚柠','念妈讲学习规划':'念妈','念妈':'念妈',
|
||
'学霸三人行':'学霸三人行','学霸老王':'学霸老王',
|
||
'开心妈妈学习宝藏':'开心妈妈','开心爸育儿':'开心爸',
|
||
'小花生网':'小花生网','小花生':'小花生网','盈姐':'盈姐',
|
||
'百克力':'百克力','亮爸':'亮爸',
|
||
'万物分销':'万物分销','万物内购':'万物分销','万物团购':'万物分销',
|
||
'小小鹰萱妈':'小小鹰萱妈','老狼聊育儿':'老狼聊育儿',
|
||
'海淀妈妈优选':'海淀妈妈优选','神奇瓜妈聊成长':'神奇瓜妈',
|
||
'宣儿妈妈':'宣儿妈妈','宣儿麻麻':'宣儿妈妈',
|
||
'四个娃的组合生活':'四个娃的组合生活','肆个葫芦娃的妈':'四个娃的组合生活',
|
||
'小暖阿姨慢一点':'小暖阿姨',
|
||
}
|
||
for r in data: r['norm_name'] = name_map.get(r['name'], r['name'])
|
||
|
||
# Month mapping for raw date strings
|
||
MONTH_ORDER = ['2025-09','2025-10','2025-11','2025-12','2026-01','2026-02','2026-03','2026-04','2026-05']
|
||
MONTH_LABELS = ['9月','10月','11月','12月','1月','2月','3月','4月','5月']
|
||
|
||
def parse_month(date_str):
|
||
"""Parse date to standardized YYYY-MM"""
|
||
if not date_str: return None
|
||
d = date_str[:7]
|
||
remap = {'2026-09':'2025-09','2026-10':'2025-10','2026-11':'2025-11','2026-12':'2025-12',
|
||
'2025-12':'2025-12'}
|
||
return remap.get(d, d)
|
||
|
||
# Platform merge
|
||
def merge_platform(p):
|
||
if '三开' in p: return '三开'
|
||
if '小红书' in p: return '小红书'
|
||
if '抖音' in p and '视频号' in p: return '抖音+视频号'
|
||
if '视频号' in p: return '视频号'
|
||
if '抖音' in p: return '抖音'
|
||
if '分销' in p: return '分销'
|
||
if '万物' in p: return '万物'
|
||
if '公众号' in p: return '公众号'
|
||
if '社群' in p: return '社群'
|
||
if '微信小店' in p: return '微信小店'
|
||
return p
|
||
|
||
# === Prepare cross-dimensional data ===
|
||
# 1. By influencer × month
|
||
inf_monthly = defaultdict(lambda: defaultdict(lambda: {'gmv':0,'gsv':0,'orders':0,'ref_ords':0}))
|
||
for r in data:
|
||
m = parse_month(r['date'])
|
||
if m: inf_monthly[r['norm_name']][m]['gmv'] += r['gmv']
|
||
if m: inf_monthly[r['norm_name']][m]['gsv'] += r['gsv']
|
||
if m: inf_monthly[r['norm_name']][m]['orders'] += r['orders']
|
||
if m: inf_monthly[r['norm_name']][m]['ref_ords'] += r['refund_orders']
|
||
|
||
# 2. By platform × month
|
||
plat_monthly = defaultdict(lambda: defaultdict(lambda: {'gmv':0,'gsv':0,'orders':0,'ref_ords':0}))
|
||
for r in data:
|
||
m = parse_month(r['date'])
|
||
p = merge_platform(r['platform'])
|
||
if m: plat_monthly[p][m]['gmv'] += r['gmv']
|
||
if m: plat_monthly[p][m]['gsv'] += r['gsv']
|
||
if m: plat_monthly[p][m]['orders'] += r['orders']
|
||
if m: plat_monthly[p][m]['ref_ords'] += r['refund_orders']
|
||
|
||
# Get top influencers
|
||
inf_total = defaultdict(lambda: {'gmv':0})
|
||
for r in data: inf_total[r['norm_name']]['gmv'] += r['gmv']
|
||
TOP_N = 8
|
||
# Filter out empty names
|
||
inf_filtered = [(k,v) for k,v in inf_total.items() if k and k.strip()]
|
||
top_inf = [x[0] for x in sorted(inf_filtered, key=lambda x:x[1]['gmv'], reverse=True)[:TOP_N]]
|
||
|
||
# Get top platforms
|
||
plat_total = defaultdict(lambda: {'gmv':0})
|
||
for r in data: plat_total[merge_platform(r['platform'])]['gmv'] += r['gmv']
|
||
top_plat = [x[0] for x in sorted(plat_total.items(), key=lambda x:x[1]['gmv'], reverse=True) if x[1]['gmv']>0 and x[0].strip()]
|
||
|
||
print(f"Top influencers: {top_inf}")
|
||
print(f"Top platforms: {top_plat}")
|
||
|
||
# ============================================================
|
||
# FIGURE A: 达人维度深度分析 (2 rows × 3 cols)
|
||
# ============================================================
|
||
figA, axesA = plt.subplots(2, 3, figsize=(22, 14))
|
||
figA.patch.set_facecolor('#FAFBFC')
|
||
|
||
# A1: 达人月度GMV热力图
|
||
ax = axesA[0, 0]
|
||
heat = np.zeros((len(top_inf), len(MONTH_ORDER)))
|
||
for i, name in enumerate(top_inf):
|
||
for j, m in enumerate(MONTH_ORDER):
|
||
heat[i, j] = inf_monthly[name][m]['gmv'] / 10000
|
||
|
||
masked = np.ma.masked_equal(heat, 0)
|
||
im = ax.imshow(masked, cmap='YlOrRd', aspect='auto', vmin=0, vmax=150)
|
||
for i in range(len(top_inf)):
|
||
for j in range(len(MONTH_ORDER)):
|
||
v = heat[i, j]
|
||
if v > 0:
|
||
col = 'white' if v > 80 else C_DARK
|
||
ax.text(j, i, f'{v:.0f}', ha='center', va='center', fontsize=8, fontweight='bold', color=col)
|
||
ax.set_xticks(range(len(MONTH_ORDER))); ax.set_xticklabels(MONTH_LABELS, fontsize=9)
|
||
ax.set_yticks(range(len(top_inf))); ax.set_yticklabels(top_inf, fontsize=9)
|
||
ax.set_title('达人月度 GMV 热力图 (万元)', fontsize=13, fontweight='bold', pad=10)
|
||
plt.colorbar(im, ax=ax, shrink=0.8, pad=0.02).set_label('万元', fontsize=9)
|
||
|
||
# A2: 达人月度退款率走势
|
||
ax = axesA[0, 1]
|
||
for idx, name in enumerate(top_inf):
|
||
rates = []
|
||
for m in MONTH_ORDER:
|
||
s = inf_monthly[name][m]
|
||
rates.append((s['ref_ords']/s['orders']*100) if s['orders']>0 else np.nan)
|
||
ax.plot(range(len(MONTH_ORDER)), rates, 'o-', color=PALETTE[idx], linewidth=2,
|
||
markersize=7, markerfacecolor='white', markeredgewidth=2, label=name, alpha=0.9)
|
||
|
||
ax.axhline(y=40, color=C_RED, linestyle='--', alpha=0.3, linewidth=1)
|
||
ax.set_xticks(range(len(MONTH_ORDER))); ax.set_xticklabels(MONTH_LABELS, fontsize=9)
|
||
ax.set_title('达人月度退款率走势', fontsize=13, fontweight='bold', pad=10)
|
||
ax.set_ylabel('退款率 (%)', fontsize=10)
|
||
ax.legend(loc='upper left', fontsize=7.5, ncol=2, framealpha=0.9)
|
||
ax.grid(alpha=0.3)
|
||
ax.set_ylim(0, 85)
|
||
|
||
# A3: 达人综合评分雷达 (GMV, GSV, 订单量, 退款率倒数, 单均GMV, 场次)
|
||
ax = axesA[0, 2]
|
||
# Normalize metrics for radar
|
||
metrics = {}
|
||
for name in top_inf[:6]:
|
||
s = inf_total[name]
|
||
total_s = inf_monthly[name]
|
||
all_orders = sum(v['orders'] for v in total_s.values())
|
||
all_gmv = sum(v['gmv'] for v in total_s.values())
|
||
all_gsv = sum(v['gsv'] for v in total_s.values())
|
||
all_ref = sum(v['ref_ords'] for v in total_s.values())
|
||
sessions = sum(1 for v in total_s.values() if v['orders']>0)
|
||
metrics[name] = {
|
||
'GMV': all_gmv,
|
||
'GSV': all_gsv,
|
||
'订单量': all_orders,
|
||
'留存率': (1 - all_ref/all_orders)*100 if all_orders>0 else 100,
|
||
'均单额': all_gmv/all_orders if all_orders>0 else 0,
|
||
'场次': sessions,
|
||
}
|
||
|
||
# Normalize
|
||
maxes = {}
|
||
for k in ['GMV','GSV','订单量','留存率','均单额','场次']:
|
||
maxes[k] = max(metrics[name][k] for name in metrics)
|
||
|
||
categories = ['GMV', 'GSV', '订单量', '留存率', '均单额', '场次']
|
||
N_cat = len(categories)
|
||
angles = np.linspace(0, 2*np.pi, N_cat, endpoint=False).tolist()
|
||
angles += angles[:1]
|
||
|
||
for idx, (name, m) in enumerate(metrics.items()):
|
||
values = [m[k]/maxes[k]*100 for k in categories]
|
||
values += values[:1]
|
||
ax.fill(angles, values, alpha=0.08, color=PALETTE[idx])
|
||
ax.plot(angles, values, 'o-', color=PALETTE[idx], linewidth=2, markersize=5, label=name)
|
||
|
||
ax.set_xticks(angles[:-1]); ax.set_xticklabels(categories, fontsize=9, fontweight='bold')
|
||
ax.set_title('达人能力雷达图 (TOP6)', fontsize=13, fontweight='bold', pad=15)
|
||
ax.legend(loc='lower right', fontsize=7.5, bbox_to_anchor=(1.3,0))
|
||
ax.set_ylim(0, 110)
|
||
|
||
# A4: 达人GSV贡献占比 (按时间)
|
||
ax = axesA[1, 0]
|
||
# Stacked area chart of top5 + others
|
||
top5_names = top_inf[:5]
|
||
monthly_stacked = defaultdict(lambda: defaultdict(float))
|
||
for r in data:
|
||
m = parse_month(r['date'])
|
||
n = r['norm_name'] if r['norm_name'] in top5_names else '其他'
|
||
if m: monthly_stacked[m][n] += r['gsv']/10000
|
||
|
||
areas = {}
|
||
for n in top5_names + ['其他']:
|
||
areas[n] = [monthly_stacked[m].get(n,0) for m in MONTH_ORDER]
|
||
|
||
bottom = np.zeros(len(MONTH_ORDER))
|
||
for idx, name in enumerate(top5_names + ['其他']):
|
||
vals = areas[name]
|
||
ax.fill_between(range(len(MONTH_ORDER)), bottom, bottom+np.array(vals),
|
||
color=PALETTE[idx], alpha=0.8, label=name, linewidth=0.5, edgecolor='white')
|
||
bottom += np.array(vals)
|
||
|
||
ax.set_xticks(range(len(MONTH_ORDER))); ax.set_xticklabels(MONTH_LABELS, fontsize=9)
|
||
ax.set_title('月度 GSV 达人贡献占比 (万元)', fontsize=13, fontweight='bold', pad=10)
|
||
ax.set_ylabel('GSV (万元)', fontsize=10)
|
||
ax.legend(loc='upper left', fontsize=8, ncol=2, framealpha=0.9)
|
||
ax.grid(axis='y', alpha=0.3)
|
||
|
||
# A5: 达人单均GMV & 退款率散点 (by month bubble)
|
||
ax = axesA[1, 1]
|
||
for idx, name in enumerate(top_inf[:6]):
|
||
x_vals, y_vals, s_vals = [], [], []
|
||
for m in MONTH_ORDER:
|
||
s = inf_monthly[name][m]
|
||
if s['orders'] > 0:
|
||
avg = s['gmv']/s['orders']
|
||
rr = s['ref_ords']/s['orders']*100
|
||
x_vals.append(avg)
|
||
y_vals.append(rr)
|
||
s_vals.append(s['orders']*12)
|
||
if x_vals:
|
||
ax.scatter(x_vals, y_vals, s=s_vals, color=PALETTE[idx], alpha=0.7, edgecolors='white', linewidth=1.2, label=name)
|
||
for x,y,si in zip(x_vals, y_vals, s_vals):
|
||
ax.annotate(name[:3], (x,y), fontsize=6.5, ha='center', va='bottom', color=C_GRAY, alpha=0.7)
|
||
|
||
ax.axhline(y=40, color=C_RED, linestyle='--', alpha=0.3)
|
||
ax.set_xlabel('单均GMV (元)', fontsize=10)
|
||
ax.set_ylabel('退款率 (%)', fontsize=10)
|
||
ax.set_title('达人效率矩阵：单均GMV × 退款率\n(气泡=月订单量, 每点=一个月)', fontsize=12, fontweight='bold', pad=10)
|
||
ax.legend(fontsize=7.5, loc='upper right', framealpha=0.9)
|
||
ax.grid(alpha=0.3)
|
||
|
||
# A6: 达人月度活跃度 (何时开播)
|
||
ax = axesA[1, 2]
|
||
# Binary heatmap - which months each influencer streamed
|
||
active = np.zeros((len(top_inf), len(MONTH_ORDER)))
|
||
for i, name in enumerate(top_inf):
|
||
for j, m in enumerate(MONTH_ORDER):
|
||
if inf_monthly[name][m]['orders'] > 0:
|
||
active[i, j] = 1
|
||
|
||
ax.imshow(active, cmap='RdYlGn', aspect='auto', alpha=0.8)
|
||
for i in range(len(top_inf)):
|
||
for j in range(len(MONTH_ORDER)):
|
||
if active[i,j] == 1:
|
||
ax.text(j, i, '●', ha='center', va='center', fontsize=14, color='#065F46', fontweight='bold')
|
||
else:
|
||
ax.text(j, i, '—', ha='center', va='center', fontsize=10, color='#D1D5DB')
|
||
|
||
# Color background by month phase
|
||
phase_colors = ['#FEF3C7','#FEF3C7','#FEF3C7','#FEF3C7','#DBEAFE','#DBEAFE','#FEE2E2','#FEE2E2','#D1FAE5']
|
||
for j in range(len(MONTH_ORDER)):
|
||
ax.axvspan(j-0.5, j+0.5, alpha=0.12, color=phase_colors[j], zorder=0)
|
||
|
||
ax.set_xticks(range(len(MONTH_ORDER))); ax.set_xticklabels(MONTH_LABELS, fontsize=9)
|
||
ax.set_yticks(range(len(top_inf))); ax.set_yticklabels(top_inf, fontsize=9)
|
||
ax.set_title('达人月度开播活跃度', fontsize=13, fontweight='bold', pad=10)
|
||
|
||
figA.suptitle('维度一：达人维度深度分析', fontsize=17, fontweight='bold', y=1.01, color=C_DARK)
|
||
plt.tight_layout(pad=3.5)
|
||
outA = '/root/.openclaw/workspace/output/daren_dim_people.png'
|
||
figA.savefig(outA, dpi=180, bbox_inches='tight', facecolor=figA.get_facecolor())
|
||
plt.close()
|
||
print(f"✅ Figure A: {outA} ({os.path.getsize(outA)/1024:.0f} KB)")
|
||
|
||
# ============================================================
|
||
# FIGURE B: 月度维度深度分析 (2 rows × 3 cols)
|
||
# ============================================================
|
||
figB, axesB = plt.subplots(2, 3, figsize=(22, 14))
|
||
figB.patch.set_facecolor('#FAFBFC')
|
||
|
||
# Monthly totals computed from data
|
||
m_totals = {}
|
||
for r in data:
|
||
m = parse_month(r['date'])
|
||
if not m: continue
|
||
if m not in m_totals:
|
||
m_totals[m] = {'gmv':0,'gsv':0,'orders':0,'ref_ords':0,'ref_amt':0,'sessions':set()}
|
||
m_totals[m]['gmv'] += r['gmv']
|
||
m_totals[m]['gsv'] += r['gsv']
|
||
m_totals[m]['orders'] += r['orders']
|
||
m_totals[m]['ref_ords'] += r['refund_orders']
|
||
m_totals[m]['ref_amt'] += r['refund_amount']
|
||
m_totals[m]['sessions'].add(r['date'])
|
||
|
||
# B1: 月度核心指标面板
|
||
ax = axesB[0, 0]
|
||
x = np.arange(len(MONTH_ORDER))
|
||
|
||
# GMV bar + GSV bar overlay
|
||
gmv_arr = [m_totals[m]['gmv']/10000 if m in m_totals else 0 for m in MONTH_ORDER]
|
||
gsv_arr = [m_totals[m]['gsv']/10000 if m in m_totals else 0 for m in MONTH_ORDER]
|
||
refund_arr = np.array(gmv_arr) - np.array(gsv_arr)
|
||
order_arr = [m_totals[m]['orders'] if m in m_totals else 0 for m in MONTH_ORDER]
|
||
|
||
bars_b1 = ax.bar(x, gsv_arr, color=C_GREEN, alpha=0.85, label='GSV', zorder=3)
|
||
bars_b2 = ax.bar(x, refund_arr, bottom=gsv_arr, color=C_RED, alpha=0.5, label='退款', zorder=3)
|
||
|
||
for i in range(len(MONTH_ORDER)):
|
||
if gmv_arr[i] > 0:
|
||
ax.text(i, gmv_arr[i]+1, f'{gmv_arr[i]:.0f}万\n{order_arr[i]}单', ha='center', fontsize=8, fontweight='bold', color=C_DARK)
|
||
|
||
ax.set_xticks(x); ax.set_xticklabels(MONTH_LABELS, fontsize=9)
|
||
ax.set_title('月度 GMV 构成 & 订单量', fontsize=13, fontweight='bold', pad=10)
|
||
ax.set_ylabel('万元', fontsize=10)
|
||
ax.legend(fontsize=8)
|
||
ax.grid(axis='y', alpha=0.3, zorder=0)
|
||
|
||
# B2: 月度退款率 + GSV率 双轴
|
||
ax = axesB[0, 1]
|
||
ax2 = ax.twinx()
|
||
ref_rates = [(m_totals[m]['ref_ords']/m_totals[m]['orders']*100) if m in m_totals and m_totals[m]['orders']>0 else 0 for m in MONTH_ORDER]
|
||
gsv_rates = [(m_totals[m]['gsv']/m_totals[m]['gmv']*100) if m in m_totals and m_totals[m]['gmv']>0 else 0 for m in MONTH_ORDER]
|
||
|
||
ax.bar(x, ref_rates, 0.5, color=C_RED, alpha=0.25, zorder=2)
|
||
ax.plot(x, ref_rates, 'o-', color=C_RED, linewidth=2.5, markersize=9, zorder=4)
|
||
ax2.plot(x, gsv_rates, 's--', color=C_GREEN, linewidth=2.5, markersize=9, zorder=4)
|
||
|
||
for i, (r, g) in enumerate(zip(ref_rates, gsv_rates)):
|
||
if r > 0:
|
||
ax.annotate(f'{r:.0f}%', (i, r), textcoords="offset points", xytext=(0,12), ha='center', fontsize=9, fontweight='bold', color=C_RED)
|
||
if g > 0:
|
||
ax2.annotate(f'{g:.0f}%', (i, g), textcoords="offset points", xytext=(0,-16), ha='center', fontsize=9, fontweight='bold', color=C_GREEN)
|
||
|
||
ax.set_xticks(x); ax.set_xticklabels(MONTH_LABELS, fontsize=9)
|
||
ax.set_title('月度退款率 & GSV率 (净收入率)', fontsize=13, fontweight='bold', pad=10)
|
||
ax.set_ylabel('退款率 (%)', color=C_RED, fontsize=10)
|
||
ax2.set_ylabel('GSV率 (%)', color=C_GREEN, fontsize=10)
|
||
ax.tick_params(axis='y', colors=C_RED)
|
||
ax2.tick_params(axis='y', colors=C_GREEN)
|
||
ax.grid(axis='y', alpha=0.3, zorder=0)
|
||
ax.set_ylim(0, 80); ax2.set_ylim(0, 100)
|
||
|
||
# B3: 月度场次 vs 场均GMV vs 场均单量
|
||
ax = axesB[0, 2]
|
||
sessions_arr = [len(m_totals[m]['sessions']) if m in m_totals else 0 for m in MONTH_ORDER]
|
||
avg_gmv_session = [m_totals[m]['gmv']/len(m_totals[m]['sessions'])/10000 if m in m_totals and len(m_totals[m]['sessions'])>0 else 0 for m in MONTH_ORDER]
|
||
avg_orders_session = [m_totals[m]['orders']/len(m_totals[m]['sessions']) if m in m_totals and len(m_totals[m]['sessions'])>0 else 0 for m in MONTH_ORDER]
|
||
|
||
ax3_twin = ax.twinx()
|
||
bars_b3 = ax.bar(x, sessions_arr, 0.5, color=C_PURPLE, alpha=0.3, label='直播场次', zorder=2)
|
||
ax.plot(x, avg_gmv_session, 'D-', color=C_BLUE, linewidth=2.5, markersize=10, zorder=4, label='场均GMV(万)')
|
||
ax3_twin.plot(x, avg_orders_session, '^--', color=C_ORANGE, linewidth=2, markersize=9, zorder=4, label='场均单量')
|
||
|
||
for i, (s, a, o) in enumerate(zip(sessions_arr, avg_gmv_session, avg_orders_session)):
|
||
if s > 0:
|
||
ax.text(i-0.25, s+0.3, str(s), fontsize=9, color=C_PURPLE, fontweight='bold')
|
||
ax.annotate(f'¥{a:.0f}万', (i, a), textcoords="offset points", xytext=(0,12), ha='center', fontsize=8.5, color=C_BLUE, fontweight='bold')
|
||
ax3_twin.annotate(f'{o:.0f}单', (i, o), textcoords="offset points", xytext=(0,-16), ha='center', fontsize=8.5, color=C_ORANGE, fontweight='bold')
|
||
|
||
ax.set_xticks(x); ax.set_xticklabels(MONTH_LABELS, fontsize=9)
|
||
ax.set_title('月度场次 & 场均效率', fontsize=13, fontweight='bold', pad=10)
|
||
ax.set_ylabel('场次', color=C_PURPLE, fontsize=10)
|
||
ax3_twin.set_ylabel('场均单量', color=C_ORANGE, fontsize=10)
|
||
ax.tick_params(axis='y', colors=C_PURPLE)
|
||
ax3_twin.tick_params(axis='y', colors=C_ORANGE)
|
||
ax.grid(axis='y', alpha=0.3, zorder=0)
|
||
|
||
# Handle combined legend
|
||
l1, l1a = ax.get_legend_handles_labels()
|
||
l2, l2a = ax3_twin.get_legend_handles_labels()
|
||
ax.legend(l1+l2, l1a+l2a, loc='upper left', fontsize=7.5)
|
||
|
||
# B4: 月度平台GMV分布 (堆叠柱状)
|
||
ax = axesB[1, 0]
|
||
plat_order = ['小红书','三开','抖音+视频号','视频号','抖音','分销','微信小店','公众号','万物','社群']
|
||
stack_bottom = np.zeros(len(MONTH_ORDER))
|
||
for pidx, p in enumerate(plat_order):
|
||
vals = [plat_monthly[p][m]['gmv']/10000 for m in MONTH_ORDER]
|
||
if sum(vals) > 0:
|
||
ax.bar(x, vals, bottom=stack_bottom, color=PALETTE[pidx % len(PALETTE)], alpha=0.85, label=p, zorder=3)
|
||
stack_bottom += np.array(vals)
|
||
|
||
ax.set_xticks(x); ax.set_xticklabels(MONTH_LABELS, fontsize=9)
|
||
ax.set_title('月度平台 GMV 分布', fontsize=13, fontweight='bold', pad=10)
|
||
ax.set_ylabel('GMV (万元)', fontsize=10)
|
||
ax.legend(loc='upper left', fontsize=8, ncol=2, framealpha=0.9)
|
||
ax.grid(axis='y', alpha=0.3, zorder=0)
|
||
|
||
# B5: 月度新老达人对比 (首月开播 vs 复播)
|
||
ax = axesB[1, 1]
|
||
first_appear = {}
|
||
for r in data:
|
||
n = r['norm_name']; m = parse_month(r['date'])
|
||
if m and (n not in first_appear or m < first_appear[n]):
|
||
first_appear[n] = m
|
||
|
||
new_count = defaultdict(int); old_count = defaultdict(int)
|
||
new_gmv = defaultdict(float); old_gmv = defaultdict(float)
|
||
for r in data:
|
||
n = r['norm_name']; m = parse_month(r['date'])
|
||
if not m: continue
|
||
if first_appear.get(n) == m:
|
||
new_count[m] += 1; new_gmv[m] += r['gmv']/10000
|
||
else:
|
||
old_count[m] += 1; old_gmv[m] += r['gmv']/10000
|
||
|
||
new_arr = [new_gmv[m] for m in MONTH_ORDER]
|
||
old_arr = [old_gmv[m] for m in MONTH_ORDER]
|
||
|
||
ax.bar(x, old_arr, color=C_BLUE, alpha=0.85, label='复播达人', zorder=3)
|
||
ax.bar(x, new_arr, bottom=old_arr, color=C_GOLD, alpha=0.85, label='新达人', zorder=3)
|
||
|
||
for i in range(len(MONTH_ORDER)):
|
||
if new_arr[i]+old_arr[i] > 0:
|
||
ax.text(i, new_arr[i]+old_arr[i]+3, f'新{new_count[MONTH_ORDER[i]]}\n复{old_count[MONTH_ORDER[i]]}',
|
||
ha='center', fontsize=7.5, color=C_DARK)
|
||
|
||
ax.set_xticks(x); ax.set_xticklabels(MONTH_LABELS, fontsize=9)
|
||
ax.set_title('月度新老达人 GMV 贡献\n(按首月开播分类)', fontsize=13, fontweight='bold', pad=10)
|
||
ax.set_ylabel('GMV (万元)', fontsize=10)
|
||
ax.legend(fontsize=8)
|
||
ax.grid(axis='y', alpha=0.3, zorder=0)
|
||
|
||
# B6: 月度GMV增长率 & 环比变化
|
||
ax = axesB[1, 2] # B6 (last subplot in 2x3 grid)
|
||
m_gmv_arr = [m_totals[m]['gmv']/10000 if m in m_totals else 0 for m in MONTH_ORDER]
|
||
mom_growth = []
|
||
for i, g in enumerate(m_gmv_arr):
|
||
if i == 0: mom_growth.append(0)
|
||
else: mom_growth.append((g-m_gmv_arr[i-1])/m_gmv_arr[i-1]*100 if m_gmv_arr[i-1]>0 else 0)
|
||
|
||
growth_colors = [C_GREEN if v>=0 else C_RED for v in mom_growth]
|
||
ax.bar(x, mom_growth, color=growth_colors, alpha=0.7, zorder=3)
|
||
ax.plot(x, m_gmv_arr, 'D-', color=C_DARK, linewidth=2, markersize=10, markerfacecolor=C_GOLD, zorder=4)
|
||
|
||
for i, (g, gm) in enumerate(zip(mom_growth, m_gmv_arr)):
|
||
if i > 0:
|
||
label = f'{g:+.0f}%'
|
||
else: label = '—'
|
||
ax.text(i, mom_growth[i]+(8 if mom_growth[i]>=0 else -12), label, ha='center', fontsize=8, fontweight='bold', color=C_DARK)
|
||
ax.text(i, gm+3, f'{gm:.0f}万', ha='center', fontsize=8, color=C_BLUE, fontweight='bold')
|
||
|
||
ax.axhline(y=0, color=C_DARK, linewidth=0.5, alpha=0.5)
|
||
ax.set_xticks(x); ax.set_xticklabels(MONTH_LABELS, fontsize=9)
|
||
ax.set_title('月度 GMV 环比增长率', fontsize=13, fontweight='bold', pad=10)
|
||
ax.set_ylabel('环比增长 (%)', fontsize=10)
|
||
ax.grid(axis='y', alpha=0.3, zorder=0)
|
||
|
||
figB.suptitle('维度二：月度维度深度分析', fontsize=17, fontweight='bold', y=1.01, color=C_DARK)
|
||
plt.tight_layout(pad=3.5)
|
||
outB = '/root/.openclaw/workspace/output/daren_dim_month.png'
|
||
figB.savefig(outB, dpi=180, bbox_inches='tight', facecolor=figB.get_facecolor())
|
||
plt.close()
|
||
print(f"✅ Figure B: {outB} ({os.path.getsize(outB)/1024:.0f} KB)")
|
||
|
||
# ============================================================
|
||
# FIGURE C: 平台维度深度分析 (2 rows × 3 cols)
|
||
# ============================================================
|
||
figC, axesC = plt.subplots(2, 3, figsize=(22, 14))
|
||
figC.patch.set_facecolor('#FAFBFC')
|
||
|
||
# Filter platforms with meaningful data
|
||
meaningful_plats = [p for p in plat_order if sum(plat_monthly[p][m]['gmv'] for m in MONTH_ORDER) > 50000]
|
||
|
||
# C1: 平台 GMV 占比饼图
|
||
ax = axesC[0, 0]
|
||
plat_pie_gmv = [sum(plat_monthly[p][m]['gmv'] for m in MONTH_ORDER)/10000 for p in meaningful_plats]
|
||
wedges, texts, autotexts = ax.pie(plat_pie_gmv, labels=meaningful_plats, autopct='%1.1f%%',
|
||
colors=PALETTE[:len(meaningful_plats)], startangle=90, pctdistance=0.82,
|
||
textprops={'fontsize':8.5})
|
||
for at in autotexts: at.set_fontweight('bold'); at.set_fontsize(8)
|
||
ax.set_title('平台 GMV 占比', fontsize=13, fontweight='bold', pad=10)
|
||
|
||
# C2: 平台退款率对比 (柱状+标注)
|
||
ax = axesC[1, 0]
|
||
plat_ref = []
|
||
for p in meaningful_plats:
|
||
total_o = sum(plat_monthly[p][m]['orders'] for m in MONTH_ORDER)
|
||
total_r = sum(plat_monthly[p][m]['ref_ords'] for m in MONTH_ORDER)
|
||
plat_ref.append({'name':p, 'orders':total_o, 'ref_rate':total_r/total_o*100 if total_o>0 else 0,
|
||
'gmv':sum(plat_monthly[p][m]['gmv'] for m in MONTH_ORDER)/10000})
|
||
|
||
plat_ref.sort(key=lambda x:x['ref_rate'])
|
||
names_r = [x['name'] for x in plat_ref]
|
||
rates_r = [x['ref_rate'] for x in plat_ref]
|
||
gmv_r = [x['gmv'] for x in plat_ref]
|
||
rate_colors = [C_GREEN if r<25 else C_GOLD if r<40 else C_RED for r in rates_r]
|
||
bars_c2 = ax.barh(range(len(names_r)), rates_r, color=rate_colors, height=0.6, zorder=3)
|
||
for bar, r, g in zip(bars_c2, rates_r, gmv_r):
|
||
ax.text(bar.get_width()+1, bar.get_y()+bar.get_height()/2,
|
||
f'{r:.1f}% | GMV ¥{g:.0f}万', va='center', fontsize=8.5, color=C_DARK)
|
||
ax.axvline(x=40, color=C_RED, linestyle='--', alpha=0.3, linewidth=1)
|
||
ax.set_yticks(range(len(names_r))); ax.set_yticklabels(names_r, fontsize=9)
|
||
ax.set_title('平台退款率对比\n(按退款率升序)', fontsize=13, fontweight='bold', pad=10)
|
||
ax.set_xlabel('退款率 (%)', fontsize=10)
|
||
ax.invert_yaxis()
|
||
ax.grid(axis='x', alpha=0.3, zorder=0)
|
||
|
||
# C3: 平台达人来源多样性
|
||
ax = axesC[0, 1]
|
||
# How many unique influencers per platform
|
||
plat_inf = defaultdict(set)
|
||
for r in data:
|
||
p = merge_platform(r['platform'])
|
||
plat_inf[p].add(r['norm_name'])
|
||
|
||
plat_div = [(p, len(inf_set), sum(plat_monthly[p][m]['gmv'] for m in MONTH_ORDER)/10000)
|
||
for p, inf_set in plat_inf.items() if p in meaningful_plats]
|
||
plat_div.sort(key=lambda x:x[1], reverse=True)
|
||
|
||
names_d = [x[0] for x in plat_div]
|
||
divers = [x[1] for x in plat_div]
|
||
gmv_d = [x[2] for x in plat_div]
|
||
|
||
ax_twin = ax.twinx()
|
||
bars_d = ax.bar(range(len(names_d)), divers, color=C_PURPLE, alpha=0.7, label='合作达人数', zorder=3)
|
||
ax_twin.plot(range(len(names_d)), gmv_d, 'D-', color=C_BLUE, linewidth=2.5, markersize=10, zorder=4, label='GMV(万)')
|
||
|
||
for i, (d, g) in enumerate(zip(divers, gmv_d)):
|
||
ax.text(i, d+0.3, str(d), ha='center', fontsize=10, fontweight='bold', color=C_PURPLE)
|
||
ax_twin.annotate(f'¥{g:.0f}万', (i, g), textcoords="offset points", xytext=(0,12), ha='center', fontsize=8.5, color=C_BLUE, fontweight='bold')
|
||
|
||
ax.set_xticks(range(len(names_d))); ax.set_xticklabels(names_d, fontsize=8.5, rotation=20)
|
||
ax.set_title('平台达人多样性\n(达人数 vs GMV)', fontsize=13, fontweight='bold', pad=10)
|
||
ax.set_ylabel('合作达人数', color=C_PURPLE, fontsize=10)
|
||
ax_twin.set_ylabel('GMV (万元)', color=C_BLUE, fontsize=10)
|
||
ax.tick_params(axis='y', colors=C_PURPLE)
|
||
ax_twin.tick_params(axis='y', colors=C_BLUE)
|
||
ax.grid(axis='y', alpha=0.3)
|
||
l1,l1a = ax.get_legend_handles_labels(); l2,l2a = ax_twin.get_legend_handles_labels()
|
||
ax.legend(l1+l2, l1a+l2a, loc='upper right', fontsize=7.5)
|
||
|
||
# C4: 头部平台月度趋势
|
||
ax = axesC[0, 2]
|
||
top_4_plats = [x[0] for x in plat_div[:4]]
|
||
for idx, p in enumerate(top_4_plats):
|
||
vals = [plat_monthly[p][m]['gmv']/10000 for m in MONTH_ORDER]
|
||
ax.plot(range(len(MONTH_ORDER)), vals, 'o-', color=PALETTE[idx], linewidth=2.5, markersize=9,
|
||
markerfacecolor='white', markeredgewidth=2, label=p)
|
||
|
||
ax.set_xticks(range(len(MONTH_ORDER))); ax.set_xticklabels(MONTH_LABELS, fontsize=9)
|
||
ax.set_title('TOP4 平台月度 GMV 趋势', fontsize=13, fontweight='bold', pad=10)
|
||
ax.set_ylabel('GMV (万元)', fontsize=10)
|
||
ax.legend(fontsize=9, framealpha=0.9)
|
||
ax.grid(alpha=0.3)
|
||
|
||
# C5: 平台退款率月度热力图
|
||
ax = axesC[1, 1]
|
||
heat_plat = np.zeros((len(meaningful_plats), len(MONTH_ORDER)))
|
||
for i, p in enumerate(meaningful_plats):
|
||
for j, m in enumerate(MONTH_ORDER):
|
||
s = plat_monthly[p][m]
|
||
heat_plat[i, j] = (s['ref_ords']/s['orders']*100) if s['orders']>0 else np.nan
|
||
|
||
masked_p = np.ma.masked_invalid(heat_plat)
|
||
im = ax.imshow(masked_p, cmap='RdYlGn_r', aspect='auto', vmin=0, vmax=80)
|
||
for i in range(len(meaningful_plats)):
|
||
for j in range(len(MONTH_ORDER)):
|
||
v = heat_plat[i, j]
|
||
if not np.isnan(v):
|
||
col = 'white' if v > 45 else C_DARK
|
||
ax.text(j, i, f'{v:.0f}%', ha='center', va='center', fontsize=8.5, fontweight='bold', color=col)
|
||
|
||
ax.set_xticks(range(len(MONTH_ORDER))); ax.set_xticklabels(MONTH_LABELS, fontsize=9)
|
||
ax.set_yticks(range(len(meaningful_plats))); ax.set_yticklabels(meaningful_plats, fontsize=9)
|
||
ax.set_title('平台退款率月份热力图', fontsize=13, fontweight='bold', pad=10)
|
||
plt.colorbar(im, ax=ax, shrink=0.8, pad=0.02).set_label('退款率 (%)', fontsize=9)
|
||
|
||
# C6: 平台场均效率 & 稳定性
|
||
ax = axesC[1, 2]
|
||
# Per-platform per-session avg GMV and stddev
|
||
plat_session_stats = defaultdict(list)
|
||
for r in data:
|
||
p = merge_platform(r['platform'])
|
||
plat_session_stats[p].append(r['gmv']/10000)
|
||
|
||
plat_eff = []
|
||
for p in meaningful_plats:
|
||
vals = plat_session_stats[p]
|
||
if vals:
|
||
plat_eff.append({'name': p, 'avg': np.mean(vals), 'std': np.std(vals), 'count': len(vals)})
|
||
|
||
plat_eff.sort(key=lambda x:x['avg'], reverse=True)
|
||
eff_names = [x['name'] for x in plat_eff]
|
||
eff_avg = [x['avg'] for x in plat_eff]
|
||
eff_std = [x['std'] for x in plat_eff]
|
||
|
||
y_pos = np.arange(len(eff_names))
|
||
bars_c6 = ax.barh(y_pos, eff_avg, xerr=eff_std, color=C_BLUE, alpha=0.75, height=0.6,
|
||
ecolor=C_DARK, capsize=4, zorder=3)
|
||
|
||
for bar, avg, std, cnt in zip(bars_c6, eff_avg, eff_std, [x['count'] for x in plat_eff]):
|
||
cv = std/avg*100 if avg>0 else 0
|
||
ax.text(bar.get_width()+0.3, bar.get_y()+bar.get_height()/2,
|
||
f'场均 ¥{avg:.1f}万 ±{std:.1f}万 (CV:{cv:.0f}%)',
|
||
va='center', fontsize=8, color=C_DARK)
|
||
|
||
ax.set_yticks(y_pos); ax.set_yticklabels(eff_names, fontsize=9)
|
||
ax.set_title('平台场均 GMV & 稳定性\n(误差线=标准差)', fontsize=13, fontweight='bold', pad=10)
|
||
ax.set_xlabel('场均 GMV (万元)', fontsize=10)
|
||
ax.invert_yaxis()
|
||
ax.grid(axis='x', alpha=0.3, zorder=0)
|
||
|
||
figC.suptitle('维度三：平台/渠道维度深度分析', fontsize=17, fontweight='bold', y=1.01, color=C_DARK)
|
||
plt.tight_layout(pad=3.5)
|
||
outC = '/root/.openclaw/workspace/output/daren_dim_platform.png'
|
||
figC.savefig(outC, dpi=180, bbox_inches='tight', facecolor=figC.get_facecolor())
|
||
plt.close()
|
||
print(f"✅ Figure C: {outC} ({os.path.getsize(outC)/1024:.0f} KB)")
|
||
|
||
print("\n🎉 All 3 dimensional analysis charts generated!")
|