python如何应用于数据的基础统计分析

def prod_describe(data, classify, category, remove_col):

    desc = data.groupby([classify])[category].describe()

    desc.drop(columns=remove_col, axis=1, inplace=True)

    # Range(极差) = max - min

    desc["极差"] = desc["max"] - desc["min"]

    # 更新统计数据的列名称（英文--》中文）

    desc = desc.rename(columns={"count": "样品数量",

                               "mean": "平均值",

                               "std": "标准偏差",

                               "min": "最小值",

                               "max": "值"})

    desc = desc.sort_values(by=["样品数量"], axis=0, ascending=False)

    return desc

# 由于报告不需要分位数的统计量，故删除这些字段[25%, 50%, 70%]

remove_col = ["25%", "50%", "75%"]

classify = "产品"

category1 = "蛋白质"

category2 = "固形物"

data = data_prep.copy()

category1_desc = prod_describe(data, classify, category1, remove_col)

category2_desc = prod_describe(data, classify, category2, remove_col)

category2])

file = "d:/test/Summary/Data_Statistics.xlsx"

result.to_excel(file, sheet_name="Statistics")

print("已经全部完成，请检查！")