非计算机专业转行学Python可行吗？文科生与传统行业从业者的机会分析

import re
import pandas as pd

# 示例输入：模拟出海电商平台收集的多语种、夹杂格式杂乱的原始评论数据
raw_feedbacks = [
    {"id": 101, "lang": "en", "text": "Delivery was slow (over 14 days), but the sound quality is top-notch! #audio"},
    {"id": 102, "lang": "es", "text": "El paquete llego roto. Muy mala experiencia con el envio. [[REF:9921]]"},
    {"id": 103, "lang": "en", "text": "Contacted support 3 times, NO RESPONSE AT ALL. Totally unacceptable."},
    {"id": 104, "lang": "fr", "text": "Excellente finition, conforme a la description! Livré en 3 jours."},
    {"id": 105, "lang": "en", "text": "Great packaging, but Bluetooth disconnects frequently during workouts."}
]

def clean_text_content(text: str) -> str:
    """剔除文档中的特殊标记、URL或非文本标签，规范化空格"""
    # 过滤类似 [[REF:xxxx]] 或 #tag 等元数据标签
    cleaned = re.sub(r"\[\[.*?\]\]", "", text)
    cleaned = re.sub(r"#[A-Za-z0-9_]+", "", cleaned)
    # 消除连续冗余空格并修剪首尾
    cleaned = re.sub(r"\s+", " ", cleaned).strip()
    return cleaned

def tag_logistics_issue(text: str) -> bool:
    """根据语境关键词识别是否属于物流/配送客诉"""
    logistics_keywords = ["delivery", "slow", "envio", "livr", "package", "days", "días"]
    pattern = re.compile(r"\b(" + "|".join(logistics_keywords) + r")\b", re.IGNORECASE)
    return bool(pattern.search(text))

# 执行处理流水线
df = pd.DataFrame(raw_feedbacks)
df["cleaned_text"] = df["text"].apply(clean_text_content)
df["is_logistics_issue"] = df["cleaned_text"].apply(tag_logistics_issue)

# 筛选存在物流配送痛点的记录
logistics_report = df[df["is_logistics_issue"]][["id", "lang", "cleaned_text"]]
print(logistics_report.to_string(index=False))

import pandas as pd

# 示例数据源1：WMS实物扫码盘点表
wms_data = pd.DataFrame([
    {"sku": "SKU-A101", "wms_qty": 450, "warehouse": "华东一号仓"},
    {"sku": "SKU-B202", "wms_qty": 120, "warehouse": "华东一号仓"},
    {"sku": "SKU-C303", "wms_qty": 80,  "warehouse": "华东一号仓"},
    {"sku": "SKU-D404", "wms_qty": 300, "warehouse": "华北二号仓"},
])

# 示例数据源2：财务ERP账面库存与单价表
erp_data = pd.DataFrame([
    {"sku": "SKU-A101", "erp_qty": 500, "unit_cost": 25.0},
    {"sku": "SKU-B202", "erp_qty": 120, "unit_cost": 88.0},
    {"sku": "SKU-C303", "erp_qty": 65,  "unit_cost": 150.0},
    {"sku": "SKU-E505", "erp_qty": 10,  "unit_cost": 320.0},
])

# 以SKU为键进行外连接对账（确保两边遗漏的SKU均被检出）
recon = pd.merge(wms_data, erp_data, on="sku", how="outer").fillna(0)

# 计算数量差异：实物数量 - 账面数量（负数代表盘亏盘损，正数代表账外盘盈）
recon["diff_qty"] = recon["wms_qty"] - recon["erp_qty"]
recon["diff_amount"] = recon["diff_qty"] * recon["unit_cost"]

# 筛选出存在异常的记录
anomaly_records = recon[recon["diff_qty"] != 0].copy()
anomaly_records["status"] = anomaly_records["diff_qty"].apply(
    lambda x: "盘亏 (缺少)" if x < 0 else "盘盈 (多余)"
)

print(anomaly_records[["sku", "warehouse", "wms_qty", "erp_qty", "diff_qty", "diff_amount", "status"]].to_string(index=False))