Python实现轻松处理两行表头Excel并可视化分析(附完整代码)

df = pd.read_excel("data.xlsx", header=[0, 1])

new_cols = []
for col1, col2 in df.columns:
    if col1 == '门店编码':
        new_cols.append('门店编码')
    else:
        new_cols.append(f"{col1}-{col2}")
df.columns = new_cols

result = []

for index, row in df.iterrows():
    store = row['门店编码']

    for i in range(1, 6):
        inv = row[f"商品{i}-库存"]
        sales = row[f"商品{i}-销量"]

        if inv > sales:
            result.append([store, f"商品{i}", inv])

result_df = pd.DataFrame(result, columns=['门店', '商品', '库存'])
print(result_df)

import matplotlib.pyplot as plt

store_count = result_df.groupby("门店").size()

plt.figure(figsize=(10,5))
store_count.plot(kind='bar')
plt.title("每个门店 库存>销量 的商品数量")
plt.xlabel("门店")
plt.ylabel("商品数量")
plt.tight_layout()
plt.show()

product_count = result_df.groupby("商品").size()

plt.figure(figsize=(8,5))
product_count.plot(kind='bar')
plt.title("各商品 库存>销量 次数统计")
plt.xlabel("商品")
plt.ylabel("次数")
plt.tight_layout()
plt.show()

import seaborn as sns

matrix = {}

for index, row in df.iterrows():
    store = row['门店编码']
    diff_list = []
    for i in range(1, 6):
        diff = row[f"商品{i}-库存"] - row[f"商品{i}-销量"]
        diff_list.append(diff)
    matrix[store] = diff_list

heat_df = pd.DataFrame(matrix, index=[f"商品{i}" for i in range(1, 6)])

plt.figure(figsize=(12,6))
sns.heatmap(heat_df, annot=True, fmt="d", cmap="YlGnBu")
plt.title("库存 - 销量 热力图")
plt.xlabel("门店")
plt.ylabel("商品")
plt.tight_layout()
plt.show()