185 lines
6.6 KiB
Python
185 lines
6.6 KiB
Python
# -*- coding: utf-8 -*-
|
||
|
||
"""
|
||
脚本说明：
|
||
本脚本用于KANO需求分析，能够处理问卷数据并输出需求分类结果
|
||
"""
|
||
|
||
import re
|
||
|
||
import numpy
|
||
import pandas
|
||
|
||
from utils.pandas_extension import save_as_workbook
|
||
|
||
print("1 打开并读取Excel文件...", end="")
|
||
try:
|
||
dataset = pandas.read_excel(io="KANO模型客户调研问卷.xlsx", sheet_name="问卷结果")
|
||
|
||
# 选项范围
|
||
alternatives = ["非常满意", "理应如此", "无所谓", "勉强接受", "不满意"]
|
||
|
||
# 数据清洗
|
||
dataset = (
|
||
dataset.iloc[
|
||
:, 3:
|
||
] # 原始数据第一列为编号、第二列为提交人、第三列为提交时间，从第四列到最后一列为选项，删除第一列至第三列
|
||
.loc[lambda dataframe: dataframe.nunique(axis=1) != 1] # 删除相同选项的样本
|
||
.map(
|
||
lambda cell: cell if cell in alternatives else pandas.NA
|
||
) # 检查是否在选项范围，若不在选项范围则置为缺失值
|
||
.dropna(axis="index", how="any") # 删除缺失值
|
||
)
|
||
|
||
# 统计样本数
|
||
samples_size = dataset.shape[0]
|
||
# 若样本数为0则抛出异常
|
||
if samples_size == 0:
|
||
raise Exception("样本数为0")
|
||
|
||
# 统计列数
|
||
columns = dataset.shape[1]
|
||
# 若列数非奇数则抛出异常
|
||
if columns % 2 != 0:
|
||
raise Exception("列数为奇数")
|
||
|
||
print(f"已完成，样本数为{samples_size}")
|
||
|
||
except Exception as exception:
|
||
print(f"发生异常：{str(exception)}")
|
||
exit()
|
||
|
||
print("2 生成KANO评价结果...", end="")
|
||
|
||
# KANO评价结果
|
||
kano = pandas.DataFrame()
|
||
|
||
for column in range(columns):
|
||
if column % 2 != 0:
|
||
continue
|
||
|
||
# 功能名称
|
||
if not (
|
||
match := re.search(
|
||
pattern="【(?P<feature>.*?)】", string=dataset.columns[column]
|
||
)
|
||
):
|
||
raise RuntimeError(f"功能名称未匹配到")
|
||
feature = match.group("feature")
|
||
|
||
# 生成某功能的选项分布
|
||
distribution = pandas.crosstab(
|
||
index=dataset.iloc[:, column], # 行索引为如果该产品有{{功能名称}}的选项
|
||
columns=dataset.iloc[:, column + 1], # 列索引为如果该产品没有{{功能名称}}的选项
|
||
rownames=[""],
|
||
colnames=[""],
|
||
normalize=True, # 转为占比
|
||
).reindex(index=alternatives, columns=alternatives, fill_value=0)
|
||
|
||
kano = pandas.concat(
|
||
objs=[
|
||
kano,
|
||
pandas.DataFrame(
|
||
[
|
||
{
|
||
"功能名称": feature,
|
||
"魅力属性": distribution.loc[
|
||
"非常满意", ["理应如此", "无所谓", "勉强接受"]
|
||
].sum(),
|
||
"期望属性": distribution.loc["非常满意", "不满意"].sum(),
|
||
"必备属性": distribution.loc[
|
||
["理应如此", "无所谓", "勉强接受"], "不满意"
|
||
].sum(),
|
||
"无差异属性": distribution.loc[
|
||
["理应如此", "无所谓", "勉强接受"],
|
||
["理应如此", "无所谓", "勉强接受"],
|
||
]
|
||
.sum()
|
||
.sum(),
|
||
"反向属性": distribution.loc[
|
||
["理应如此", "无所谓", "勉强接受", "不满意"], "非常满意"
|
||
].sum()
|
||
+ distribution.loc[
|
||
("不满意", ["理应如此", "无所谓", "勉强接受"])
|
||
].sum(),
|
||
"可疑结果": distribution.loc["非常满意", "非常满意"]
|
||
+ distribution.loc["不满意", "不满意"],
|
||
}
|
||
]
|
||
),
|
||
],
|
||
ignore_index=True,
|
||
)
|
||
|
||
# 计算better-worse分数，并贴标签
|
||
kano = (
|
||
kano.assign(
|
||
满意系数=lambda dataframe: (dataframe["魅力属性"] + dataframe["期望属性"])
|
||
/ (
|
||
dataframe["魅力属性"]
|
||
+ dataframe["期望属性"]
|
||
+ dataframe["必备属性"]
|
||
+ dataframe["无差异属性"]
|
||
),
|
||
不满意系数=lambda dataframe: (dataframe["必备属性"] + dataframe["期望属性"])
|
||
/ (
|
||
dataframe["魅力属性"]
|
||
+ dataframe["期望属性"]
|
||
+ dataframe["必备属性"]
|
||
+ dataframe["无差异属性"]
|
||
),
|
||
)
|
||
.pipe(
|
||
lambda dataframe: dataframe.assign(
|
||
需求标签=numpy.select(
|
||
condlist=[
|
||
(dataframe["满意系数"] >= dataframe["满意系数"].mean())
|
||
& (dataframe["不满意系数"] >= dataframe["不满意系数"].mean()),
|
||
(dataframe["满意系数"] >= dataframe["满意系数"].mean())
|
||
& (dataframe["不满意系数"] < dataframe["不满意系数"].mean()),
|
||
(dataframe["满意系数"] < dataframe["满意系数"].mean())
|
||
& (dataframe["不满意系数"] < dataframe["不满意系数"].mean()),
|
||
(dataframe["满意系数"] < dataframe["满意系数"].mean())
|
||
& (dataframe["不满意系数"] >= dataframe["不满意系数"].mean()),
|
||
],
|
||
choicelist=[
|
||
"期望型需求(P2)",
|
||
"魅力型需求(P3)",
|
||
"无差异需求(P4)",
|
||
"必备型需求(P1)",
|
||
],
|
||
default="未分类",
|
||
),
|
||
)
|
||
)
|
||
.assign(
|
||
魅力属性=lambda dataframe: dataframe["魅力属性"].apply(
|
||
lambda cell: f"{cell:.2f}"
|
||
),
|
||
期望属性=lambda dataframe: dataframe["期望属性"].apply(
|
||
lambda cell: f"{cell:.2f}"
|
||
),
|
||
必备属性=lambda dataframe: dataframe["必备属性"].apply(
|
||
lambda cell: f"{cell:.2f}"
|
||
),
|
||
无差异属性=lambda dataframe: dataframe["无差异属性"].apply(
|
||
lambda cell: f"{cell:.2f}"
|
||
),
|
||
反向属性=lambda dataframe: dataframe["反向属性"].apply(
|
||
lambda cell: f"{cell:.2f}"
|
||
),
|
||
可疑结果=lambda dataframe: dataframe["可疑结果"].apply(
|
||
lambda cell: f"{cell:.2f}"
|
||
),
|
||
满意系数=lambda dataframe: dataframe["满意系数"].apply(
|
||
lambda cell: f"{cell:.2f}"
|
||
),
|
||
不满意系数=lambda dataframe: dataframe["不满意系数"].apply(
|
||
lambda cell: f"{cell:.2f}"
|
||
),
|
||
)
|
||
)
|
||
|
||
save_as_workbook(worksheets=[("Sheet1", kano)], workbook_name="result.xlsx")
|
||
print("已完成")
|