data-analyze-refined
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseData Analyze Refined Skill
Data Analyze Refined Skill
适用场景：把任意 Excel/CSV 做成“市场部可用”的一键分析包——自动识别核心维度/指标，产出 CSV + 带目录回链的 Excel 汇总、PNG/SVG 图表、HTML 信息图、市场策略化的 Word 报告。默认输出在数据同级的 。跨行业通用，优先从字段中判断品牌/产品/客户/渠道/区域/机构等维度再决定分析重点，不要求用户先定义完整分析题。
outputs/Use cases: Turn any Excel/CSV file into a “marketing-team-ready” one-click analysis package—automatically identify core dimensions and metrics, then produce a CSV + an Excel summary with table-of-contents backlinks, PNG/SVG charts, an HTML infographic, and a market-strategy-oriented Word report. Outputs are written by default to alongside the source data. It works across industries, first inferring dimensions such as brand/product/customer/channel/region/institution from the fields and then deciding the analytical focus, without requiring the user to define a complete analytical question in advance.
outputs/核心原则
Core Principles
- 市场视角优先：用业务语言解释现状、机会、策略、风险，避免学术表达与模型化术语。
- 自动判别方向：字段缺失时做可替代的洞察，不因“数据不全”而停工。
- 图表服从洞察：图表数量与类型由洞察决定，不固定数量，不为画图而画图。
- 先结论后展开：先给管理层可读结论，再展开证据与明细。
- Market perspective first: Explain the current state, opportunities, strategy, and risks in business language, avoiding academic expressions and model-oriented terminology.
- Automatically determine the analysis direction: When fields are missing, produce alternative insights rather than stopping because the data is incomplete.
- Charts follow insights: The number and type of charts are determined by the insights. Do not create charts merely for the sake of visualization.
- Conclusions first, details later: Begin with conclusions that management can easily understand, then present the supporting evidence and details.
快速使用
Quick Usage
bash
undefinedbash
undefined默认输出到数据同级 outputs/
默认输出到数据同级 outputs/
node src/index.js /path/to/data.xlsx --sheet "导出数据表" --core-dimension "申报企业名称" --value-column "协议采购量" --charts-mode on
node src/index.js /path/to/data.xlsx --sheet "导出数据表" --core-dimension "申报企业名称" --value-column "协议采购量" --charts-mode on
自定义输出目录
自定义输出目录
node src/index.js /path/to/data.xlsx --sheet "工作表" --output-dir "/path/to/outputs"
node src/index.js /path/to/data.xlsx --sheet "工作表" --output-dir "/path/to/outputs"
图表策略：auto/on/off（默认 auto）；截图需要时加 --enable-screenshot
图表策略：auto/on/off（默认 auto）；截图需要时加 --enable-screenshot
环境依赖：
- Python 3.8+ 且 `pip install -r requirements.txt`（pandas/numpy/matplotlib/seaborn/openpyxl/python-docx 等）
- Node 18+ 可选，仅用于 node 入口；先 `npm install`（已移除错误依赖）。若 npm 报错可直接用 `python3 src/main.py ...`。
必选/优先参数：
- `--sheet`：Excel 工作表名（CSV 可省略）
- `--core-dimension`：核心实体列（优先品牌/企业；若不指定自动推断）
- `--value-column`：核心指标列（优先采购量/数量/总量类）
- `--target-brand`：可选，目标品牌/申报企业，用于白区/机会（缺省时可取头部品牌或公司名）
Environment requirements:
- Python 3.8+ and `pip install -r requirements.txt` (pandas/numpy/matplotlib/seaborn/openpyxl/python-docx, etc.)
- Node 18+ is optional and used only for the Node.js entry point; run `npm install` first (the incorrect dependency has been removed). If npm reports an error, you can directly use `python3 src/main.py ...`.
Required/preferred parameters:
- `--sheet`: Excel worksheet name (optional for CSV)
- `--core-dimension`: Core entity column (brand/company preferred; inferred automatically if unspecified)
- `--value-column`: Core metric column (purchase volume/quantity/total volume preferred)
- `--target-brand`: Optional target brand/applicant company used for white-space and opportunity analysis (if omitted, the leading brand or company name may be used)自动分析路由（行业无关）
Automatic Analysis Routing (Industry-Agnostic)
| 字段条件 | 优先洞察 | 常用图表 |
|---|---|---|
| 有时间 + 数值 | 趋势、增长来源、波动风险 | 折线图、面积图 |
| 有地区/城市 + 数值 | 区域机会、白区、区域集中度 | 排名条形图、散点/气泡图 |
| 有渠道 + 数值 | 渠道效率、渠道白区、预算分配 | 分组条形图、漏斗图 |
| 有产品/SKU + 数值 | 结构贡献、价格带、替代机会 | 堆叠条形图、帕累托图 |
| 有客户/机构 + 数值 | 重点客户贡献、覆盖深度、空白客户 | 排名条形图、分布图 |
| 仅有分类 + 数值 | 份额、集中度、TopN 贡献 | 条形图、帕累托图 |
| Field condition | Priority insights | Common charts |
|---|---|---|
| Time + numeric value | Trends, growth sources, volatility risk | Line chart, area chart |
| Region/city + numeric value | Regional opportunities, white spaces, regional concentration | Ranked bar chart, scatter/bubble chart |
| Channel + numeric value | Channel efficiency, channel white spaces, budget allocation | Grouped bar chart, funnel chart |
| Product/SKU + numeric value | Structural contribution, price bands, substitution opportunities | Stacked bar chart, Pareto chart |
| Customer/institution + numeric value | Key customer contribution, coverage depth, untapped customers | Ranked bar chart, distribution chart |
| Category only + numeric value | Share, concentration, TopN contribution | Bar chart, Pareto chart |
工作流（自动判别 → 市场洞察）
Workflow (Automatic Direction Detection → Market Insights)
- 读取与预处理
- 去除列名空白，统一别名：；
品牌/企业/厂家/供应商 -> 品牌名称（层级字段可按分隔符取市级）；地区/地市/区域 -> 城市。目录/品类/类目 -> 产品大类 - 关键数值列尝试转为数值：。
数量/销量/订单量/GMV/金额/合同量/需求量/消耗量
- 去除列名空白，统一别名：
- 自动判别核心维度/指标
- 核心维度优先顺序：品牌/申报企业/厂家 → 医院/渠道/客户 → 城市/区域 → 其他非唯一度低的分类列。
- 核心指标优先顺序：> 数量/销量/订单量/GMV/金额/合同量/需求量 > 首个数值列。
--value-column
- 降噪规则
- 分类 TopN 仅用于唯一值 2~50 且非 90% 全唯一的列；全一致/全唯一列跳过。
- 相关性需 ≥0.3 且存在 ≥2 个数值列；否则不输出。
- 无时间列/价格列时明确说明不做趋势/价量分析，用结构/覆盖/机会替代。
- 分析视角
- 字段画像、数值统计、分类分布、集中度（Top1/3/5、覆盖 80/90 所需实体数、离群阈值）。
- 份额与交叉：品牌/企业、城市、渠道、品类/SKU；品牌×城市、品牌×渠道、城市×品类、品牌内产品Top。
- 覆盖与客户：覆盖客户数/单客均量（核心维度），客户TOP，目标品牌的客户白区（低份额×高容量）。
- 机会：目标品牌白区（城市总量×目标品牌份额），并生成机会优先级（影响×可行性×投入效率）；如有时间/价格/结构则补充价格带、结构占比、时间趋势。
- 输出生成
- CSV：核心维度/城市/目录/大类/覆盖、城市品牌分布、城市Top3、城市白区、机会优先级（城市/医院或客户）、产品分布、品牌产品分布、城市产品分布、品牌产品Top、客户TOP、客户白区等（字段概览/数值统计仅供参考）。
- Excel：（目录页+返回目录，含上述业务表；默认不放字段概览/数值统计）。
outputs/excel/数据分析汇总.xlsx - 图表：按 charts-mode 生成 PNG+SVG 至 （核心维度份额、城市、目录、大类、覆盖等，自动判断是否有意义；图表数量由洞察点数决定）。
outputs/figures/{png,svg} - HTML：（核心结论/机会摘要+嵌入核心图表），
outputs/html/market_analysis_infographic.html（图表汇总）。outputs/html/charts_gallery.html - Word 报告：，站在市场部视角给核心结论、白区/机会、策略、行动计划（无字段时也要明确缺口）。
outputs/reports/<数据名>_分析报告.docx
- Reading and preprocessing
- Remove whitespace from column names and normalize aliases: ;
品牌/企业/厂家/供应商 -> 品牌名称(for hierarchical fields, extract the city level according to the delimiter);地区/地市/区域 -> 城市.目录/品类/类目 -> 产品大类 - Attempt to convert key numeric columns to numeric values: .
数量/销量/订单量/GMV/金额/合同量/需求量/消耗量
- Remove whitespace from column names and normalize aliases:
- Automatically identify core dimensions and metrics
- Core dimension priority: brand/applicant company/manufacturer → hospital/channel/customer → city/region → other categorical columns with low uniqueness.
- Core metric priority: > quantity/sales/order volume/GMV/amount/contract volume/demand > the first numeric column.
--value-column
- Noise-reduction rules
- Use categorical TopN only when a column has 2–50 unique values and is not at least 90% unique; skip columns whose values are entirely identical or entirely unique.
- Correlation requires a value of at least 0.3 and at least two numeric columns; otherwise, do not output it.
- When there is no time or price column, explicitly state that trend or price-volume analysis is not being performed, and use structure, coverage, or opportunity analysis instead.
- Analytical perspectives
- Field profiling, numerical statistics, categorical distribution, and concentration (Top 1/3/5, number of entities required for 80%/90% coverage, and outlier thresholds).
- Share and cross-tab analysis: brand/company, city, channel, category/SKU; brand × city, brand × channel, city × category, and top products within each brand.
- Coverage and customer analysis: number of covered customers/average volume per customer for the core dimension, top customers, and target-brand customer white spaces (low share × high capacity).
- Opportunities: target-brand white spaces (city total × target-brand share), with opportunity priorities calculated from impact × feasibility × investment efficiency. If time, price, or structural fields are available, add insights on price bands, structural mix, and time trends.
- Output generation
- CSV: core dimension/city/product category/major category/coverage, city-brand distribution, city Top 3, city white spaces, opportunity priorities (city/hospital or customer), product distribution, brand-product distribution, city-product distribution, top products within brands, customer TOP, customer white spaces, etc. (field overview/numerical statistics are for reference only).
- Excel: (table-of-contents sheet + links back to it, containing the business tables above; field overview/numerical statistics are excluded by default).
outputs/excel/数据分析汇总.xlsx - Charts: Generate PNG + SVG files in based on charts-mode (core dimension share, city, product category, major category, coverage, etc.); automatically determine whether each chart is meaningful, and base the chart count on the number of insights.
outputs/figures/{png,svg} - HTML: (core conclusions/opportunity summary + embedded core charts) and
outputs/html/market_analysis_infographic.html(chart gallery).outputs/html/charts_gallery.html - Word report: , written from the marketing team’s perspective with core conclusions, white spaces/opportunities, strategy, and an action plan; explicitly identify data gaps even when fields are missing.
outputs/reports/<数据名>_分析报告.docx
最小可交付（数据稀疏时仍要产出）
Minimum Deliverables (Still Required for Sparse Data)
- 至少输出：+
1页结论+>=1张有效图。>=1个机会清单CSV - 若无时间列：移除趋势，强化结构/覆盖/机会。
- 若无金额列：移除价格带，保留数量份额与集中度。
- 若无地区列：移除区域白区，转为渠道/客户白区。
- 若仅 1 个数值列：不做相关性，只做分布、份额、集中度和TopN。
- Always output at least: a one-page conclusion section + at least one meaningful chart + at least one opportunity-list CSV.
- If there is no time column: remove trend analysis and strengthen structural, coverage, and opportunity insights.
- If there is no amount column: remove price bands and retain quantity share and concentration analysis.
- If there is no region column: remove regional white-space analysis and switch to channel/customer white spaces.
- If there is only one numeric column: do not perform correlation analysis; analyze distributions, shares, concentration, and TopN only.
结论页结构（必须包含）
Conclusion Page Structure (Required)
- 现状解读：市场规模/结构/集中度/覆盖等关键事实。
- 洞察体现：增长来源、结构错配、白区/机会清单、渠道/区域差异。
- 未来策略：扩点/深耕/产品结构/价格带/预算调整等可执行路径。
- 风险分析：数据缺口、结构不匹配风险、渠道依赖、集中度过高风险等。
- Current-state interpretation: Key facts such as market size, structure, concentration, and coverage.
- Insights: Growth sources, structural mismatches, white-space/opportunity lists, and channel/regional differences.
- Future strategy: Actionable paths such as expanding coverage, deepening existing accounts, adjusting product mix or price bands, and reallocating budget.
- Risk analysis: Data gaps, structural mismatch risks, channel dependency, excessive concentration, and other relevant risks.
图表选择规则（按洞察驱动）
Chart Selection Rules (Insight-Driven)
- 份额/集中度：条形图、堆叠条形或帕累托。
- 结构/价格带：100% 堆叠条形或分组条形。
- 机会/白区：散点或气泡图（量×份额/覆盖）。
- 趋势（仅有时间列）：折线或面积图。
- 渠道效率/漏斗：漏斗图或转化率条形。
- Share/concentration: Bar chart, stacked bar chart, or Pareto chart.
- Structure/price bands: 100% stacked bar chart or grouped bar chart.
- Opportunities/white spaces: Scatter or bubble chart (volume × share/coverage).
- Trends (only when a time column exists): Line or area chart.
- Channel efficiency/funnel: Funnel chart or conversion-rate bar chart.
机会优先级规则（新增）
Opportunity Priority Rules (New)
- 影响分：潜在增量规模（总量 × 份额缺口）。
- 可行性分：已有基础（目标品牌量/既有覆盖）或份额缺口替代。
- 投入效率分：投入强度近似（规模越大通常投入越高，分值越低）。
- 综合优先级分：按“影响 × 可行性 × 投入效率”融合排序，输出高优先/中高优先/中优先/观察。
- Impact score: Potential incremental scale (total volume × share gap).
- Feasibility score: Existing foundation (target-brand volume or existing coverage), with share gap used as a proxy when necessary.
- Investment efficiency score: Approximates investment intensity; larger scale generally requires more investment and therefore receives a lower score.
- Overall priority score: Rank by combining “impact × feasibility × investment efficiency” and output high priority, medium-high priority, medium priority, or watchlist.
市场部报告要点
Marketing Team Report Highlights
- 核心结论：总量、CR3/CR5、龙头品牌与份额、主力目录/城市、覆盖（覆盖医院数/城市数/单院均量）。
- 产品/结构：品类/SKU Top、品牌内主打产品/结构（有产品或结构列时）。
- 机会：目标品牌城市白区、客户白区（低份额×高容量），如有价格/时间/结构字段则补充对应洞察。
- 行动计划：头部清单、长尾/白区试点、产品/结构/价格打法、补充字段建议（时间/渠道/价格等）。
- Core conclusions: Total volume, CR3/CR5, leading brands and shares, primary product categories/cities, and coverage (number of hospitals/cities covered and average volume per hospital).
- Products/structure: Top categories/SKUs and flagship products or mix within each brand when product or structural fields are available.
- Opportunities: Target-brand city white spaces and customer white spaces (low share × high capacity), supplemented with price, time, or structural insights when those fields exist.
- Action plan: Priority target list, long-tail/white-space pilots, product/mix/pricing tactics, and recommendations for additional fields such as time, channel, and price.
快速参考
Quick Reference
| 场景 | 关键维度 | 默认洞察 |
|---|---|---|
| 销售/订单 | 城市/渠道/产品 | 城市机会、渠道白区、结构/价格带、增长来源 |
| 投放/线索 | 渠道/地区 | ROI、漏斗转化、渠道效率、预算优化 |
| 招投标/中标 | 地区/机构/品牌 | 竞争格局、集中度、白区机构、策略路径 |
| Scenario | Key dimensions | Default insights |
|---|---|---|
| Sales/orders | City/channel/product | City opportunities, channel white spaces, mix/price bands, growth sources |
| Campaigns/leads | Channel/region | ROI, funnel conversion, channel efficiency, budget optimization |
| Tenders/bid wins | Region/institution/brand | Competitive landscape, concentration, white-space institutions, strategic paths |
常见错误与修正
Common Mistakes and Corrections
- 过学术：出现显著性检验/回归模型 → 改为业务指标与对比口径。
- 图表硬凑：没有洞察也画图 → 只保留能支撑结论的图表。
- 数据缺失即停：缺时间/价格就不输出 → 改为结构/覆盖/机会洞察并说明缺口。
- 结论过简：只给一句话 → 按“现状-洞察-策略-风险”补全。
- Too academic: significance tests or regression models are used → replace them with business metrics and comparison criteria.
- Forced charts: charts are created without supporting insights → retain only charts that support the conclusions.
- Stopping when data is missing: omit output because time or price fields are unavailable → produce structural, coverage, and opportunity insights and disclose the gaps.
- Conclusion too brief: provide only one sentence → complete it using the “current state–insights–strategy–risk” structure.
理性化与纠偏
Rationalizations and Corrections
| 借口 | 纠偏 |
|---|---|
| “数据不全，先不输出” | 先给可替代洞察，并明确缺口与补充建议。 |
| “需要统计检验才可靠” | 用业务口径对比与结构差异给结论。 |
| “固定输出3张图更稳妥” | 图表数量由洞察决定，宁少勿乱。 |
| “结论页一句话即可” | 必须包含现状、洞察、策略、风险四段。 |
| Excuse | Correction |
|---|---|
| “The data is incomplete, so I will not output anything” | First provide alternative insights, then clearly identify the gaps and recommend additional fields. |
| “Statistical tests are required for reliability” | Draw conclusions using business-basis comparisons and structural differences. |
| “Generating exactly three charts is safer” | The number of charts is determined by the insights; fewer is better than clutter. |
| “A one-sentence conclusion page is enough” | It must contain four sections: current state, insights, strategy, and risk. |
红旗清单（出现即纠正）
Red Flag Checklist (Correct Immediately When Present)
- 使用学术/模型术语替代业务语言
- 固定图表数量或模板化结论
- 因字段缺失直接停止输出
- 结论缺少策略或风险
- Using academic or model-oriented terminology instead of business language
- Fixing the chart count or using templated conclusions
- Stopping output because fields are missing
- Providing conclusions without strategy or risk
示例（Python）
Example (Python)
python
undefinedpython
undefined根据字段可用性选择洞察与图表（示意）
根据字段可用性选择洞察与图表（示意）
fields = {"日期", "城市", "渠道", "产品", "数量", "金额"}
insights = []
charts = []
if "城市" in fields and "数量" in fields:
insights.append("城市机会与白区")
charts.append("城市份额条形图/白区散点")
if "渠道" in fields and "金额" in fields:
insights.append("渠道效率与预算建议")
charts.append("渠道ROI条形图")
if "日期" in fields:
insights.append("增长来源与趋势")
charts.append("时间趋势折线")
report_sections = ["现状解读", "洞察体现", "未来策略", "风险分析"]
undefinedfields = {"日期", "城市", "渠道", "产品", "数量", "金额"}
insights = []
charts = []
if "城市" in fields and "数量" in fields:
insights.append("城市机会与白区")
charts.append("城市份额条形图/白区散点")
if "渠道" in fields and "金额" in fields:
insights.append("渠道效率与预算建议")
charts.append("渠道ROI条形图")
if "日期" in fields:
insights.append("增长来源与趋势")
charts.append("时间趋势折线")
report_sections = ["现状解读", "洞察体现", "未来策略", "风险分析"]
undefined资源
Resources
- 代码：（管线）、
src/main.py（预处理/分析）、src/data_analyzer.py（图表）、src/chart_generator.py、src/infographic_generator.py。src/screenshot_generator.py - 参考：（SOP/字段映射/降噪要点）。
references/playbook.md - 示例结构：（示例输入与报告形态参考）。
examples/
- Code: (pipeline),
src/main.py(preprocessing/analysis),src/data_analyzer.py(charts),src/chart_generator.py, andsrc/infographic_generator.py.src/screenshot_generator.py - Reference: (SOP, field mapping, and noise-reduction key points).
references/playbook.md - Example structure: (sample inputs and report-format references).
examples/