统计CRM必填项

analyze_crm_mandatory.py

@@ -0,0 +1,107 @@
+import pandas as pd
+from typing import List
+from openpyxl import Workbook
+
+df = pd.read_excel('./data_src/pingcap_pipeline.xlsx')
+
+# unique_values = df['Sales stage'].unique()
+# print("Unique values using unique():")
+# print(unique_values)
+
+crm_mandatory_fields = {
+    "1-prospecting": [
+        "联系人姓名", "部门", "职务", "手机",
+        "预估整体项目节点数或vCPU数", "现用数据库痛点", "主要数据库", "客户业务场景", "数据量"
+    ],
+    "2-evaluation": [
+        "客户预算情况", "是否是独立预算", "预算是否完成审批","是否进PcC", "PcC是否已审批", "PcC状态", "测试类型",
+          "测试项（用飞书链接）","参与友商", "poc开始日期", "poc预计结束日期", "MBO评审结果", 
+       
+    ],
+    "3-qualification": [
+        "立项批复", "立项时间", "立项贡献（立项报告的内容）", "招标方式"
+    ],
+    "4-bidding/negotiating": [
+        "是否投标", "发标时间", "投标时间", "竞争对手", "对手产配置", "对手投标金额",
+        "标书/谈判文件（最大100M，考虑链接方式）", "中标结果", "丢标原因"
+    ],
+    "5-contract review": [],
+    "6A-cancel": [
+        "取消原因", "leader审批结果"
+    ],
+    "6B-closed lost": [
+        "输单原因", "leader审批结果"
+    ],
+    "6C-closed won": [
+        "生成销售订单并关联商机", "商机字段更新到赢单"
+    ]
+}
+crm_mandatory_fields_list = list(crm_mandatory_fields.keys())
+
+stage_mapping = {
+    # "prospecting": "1-prospecting",
+    "Evaluation": "2-evaluation",
+    "Qualification": "3-qualification",
+    "PoC Won/Bidding+Negotiation": "4-bidding/negotiating",
+    # "contract review": "5-contract review",
+    # "cancel": "6A-cancel",
+    # "closed lost": "6B-closed lost",
+    "Closed Won": "6C-closed won"
+}
+
+def get_stages_up_to(crm_stage, stages_list):
+    if crm_stage.startswith('6'):
+        # Find the element starting with '5'
+        index_5 = stages_list.index("5-contract review")
+        if index_5 is not None:
+            result_list = stages_list[:index_5 + 1]
+            result_list.append(crm_stage)
+            return result_list
+        else:
+            return stages_list  # Return all stages if no '5' is found
+    else:
+        index = stages_list.index(crm_stage)
+        return stages_list[:index + 1]
+
+
+def check_mandatory_fields(row, crm_stage):
+    mandatory_fields = crm_mandatory_fields[crm_stage]
+    sales_stage = row['Sales stage']
+    print(f"Sales stage: {sales_stage}, CRM stage: {crm_stage}")
+    result = {
+        "fields_filled": [],
+        "fields_not_filled": []
+    }
+    for field in mandatory_fields:
+        if field in row and pd.notna(row[field]) and row[field] != '':
+            print(f"Field: {field}, Value: {row[field]}")
+            data = {
+                "field": field,
+                "value": row[field]
+            }
+            result["fields_filled"].append(data)
+        else:
+
+            result["fields_not_filled"].append(field)
+    return result
+
+
+for index, row in df.iterrows():
+    print("-" * 20,index ,"-" * 20)
+
+    sales_stage = row['Sales stage']
+    crm_stage = stage_mapping.get(sales_stage, "unknown")
+    if crm_stage == "unknown":
+        print(f"Sales stage: {sales_stage}, CRM stage: {crm_stage}")
+        continue
+    else:
+        print(f"Sales stage: {sales_stage}, CRM stage: {crm_stage}")
+
+    crm_stages = get_stages_up_to(crm_stage, crm_mandatory_fields_list)
+    df.at[index, "crm_stage"] = crm_stage
+    for stage in crm_stages:
+        result = check_mandatory_fields(row, stage)
+        df.at[index, stage] = ', '.join(result["fields_not_filled"])
+        print("-"*10, stage, "-"*10)
+        print(result)
+df.to_excel("./data_output/pingcap_pipeline_mandatory.xlsx")