336 lines
14 KiB
Python
336 lines
14 KiB
Python
# coding: utf-8
|
||
import os
|
||
import pandas as pd
|
||
import openpyxl
|
||
from win32com.client import DispatchEx
|
||
import time
|
||
|
||
|
||
def just_open(filename):
|
||
"""
|
||
功能:为了让有公式的excel计算出数值,进而做下一步处理
|
||
参考:
|
||
1. https://blog.csdn.net/claria029/article/details/116486904
|
||
2. https://blog.csdn.net/zhfak/article/details/125382349
|
||
参数:文件路径,一定是 r'D:\\Syncthing\\company\\D-测试工作\\X-自动化测试\\01-制动数据处理\test.xlsx' 的格式
|
||
返回值:无
|
||
"""
|
||
xlApp = DispatchEx("Excel.Application")
|
||
xlApp.Visible = False
|
||
xlBook = xlApp.Workbooks.Open(filename)
|
||
xlApp.DisplayAlerts = 0
|
||
xlBook.SaveAs(filename)
|
||
xlBook.Close()
|
||
|
||
|
||
def traversal_files(path):
|
||
"""
|
||
功能:以列表的形式分别返回指定路径下的文件和文件夹,不包含子目录
|
||
参数:路径
|
||
返回值:无
|
||
"""
|
||
dirs = []
|
||
files = []
|
||
for item in os.scandir(path):
|
||
if item.is_dir():
|
||
dirs.append(item.path)
|
||
elif item.is_file():
|
||
files.append(item.path)
|
||
|
||
return dirs, files
|
||
|
||
|
||
def find_row_start(excel_file, ws_data, conditions):
|
||
"""
|
||
函数功能:查找数据文件中有效数据的行号
|
||
:param excel_file: excel 文件的路径
|
||
:param ws_data: excle 中数据页的指针
|
||
:param conditions: 通过路径特征提取出来的信息,比如 ['reaach100', 'speed66']
|
||
:return: 有效数据的起始行行号
|
||
"""
|
||
global AV
|
||
global RR
|
||
ratio = float(conditions[1].removeprefix('speed'))/100
|
||
speed_max = AV * ratio * RR / 6
|
||
|
||
row_max = ws_data.max_row
|
||
row_start = row_max - 1000
|
||
|
||
while row_start > 0:
|
||
_a = ws_data[f"A{row_start}"].value
|
||
_b = ws_data[f"A{row_start - 200}"].value
|
||
if abs(_a-speed_max) < 50 and abs(_b-speed_max) < 50 and abs(_a - _b) < 70:
|
||
row_start -= 200
|
||
break
|
||
else:
|
||
row_start -= 200
|
||
else:
|
||
print(f"{excel_file.replace('xlsx', 'data')}, 这个文件数据有问题,请检查......")
|
||
os.remove(excel_file)
|
||
exit(9)
|
||
|
||
return row_max, row_start
|
||
|
||
|
||
def find_result_sheet_name(conditions, count):
|
||
# 该函数比较简单,功能是获取结果文件准确的sheet页名称
|
||
# 33%臂展_33%速度_正1
|
||
reach = conditions[0].removeprefix('reach')
|
||
speed = conditions[1].removeprefix('speed')
|
||
result_sheet_name = f"{reach}%臂展_{speed}%速度_正{count}"
|
||
|
||
return result_sheet_name
|
||
|
||
|
||
def copy_data_to_result(ws_data, ws_result, row_max, row_start):
|
||
"""
|
||
函数功能:将数据文件中有效数据拷贝至结果文件对应的 sheet
|
||
:param ws_data: excle 中数据页的指针
|
||
:param ws_result: 结果文件对应 sheet 的指针
|
||
:param row_max: 数据文件中获取到的最后一行的行号
|
||
:param row_start: 数据文件中获取到的第一行有效行的行号
|
||
:return: -
|
||
"""
|
||
# 结果文件数据清零
|
||
for row in ws_result.iter_rows(min_row=2, min_col=1, max_row=6000 - row_start + 2, max_col=2):
|
||
for cell in row:
|
||
cell.value = None
|
||
|
||
# 将合适的数据复制到结果文件
|
||
data = []
|
||
for row in ws_data.iter_rows(min_row=row_start, min_col=1, max_row=row_max, max_col=2):
|
||
for cell in row:
|
||
data.append(cell.value)
|
||
i = 0
|
||
for row in ws_result.iter_rows(min_row=2, min_col=1, max_row=row_max - row_start + 2, max_col=2):
|
||
for cell in row:
|
||
cell.value = data[i]
|
||
i = i + 1
|
||
|
||
|
||
def copy_data_to_excel_file(wb_data, ws_result, row_max, row_start, excel_file):
|
||
"""
|
||
|
||
:param wb_data: excel 的指针
|
||
:param ws_result: 结果文件对应 sheet 的指针
|
||
:param row_max: 数据文件中获取到的最后一行的行号
|
||
:param row_start: 数据文件中获取到的第一行有效行的行号
|
||
:param excel_file: excel 文件的路径
|
||
:return: wb_data 是新打开的 excel 文件的指针,ws_dp 是新打开的 excel 文件中的 dp 页指针
|
||
"""
|
||
try:
|
||
del wb_data['dp']
|
||
wb_data.create_sheet('dp')
|
||
ws_dp = wb_data['dp']
|
||
except:
|
||
wb_data.create_sheet('dp')
|
||
ws_dp = wb_data['dp']
|
||
|
||
data = []
|
||
for row in ws_result.iter_rows(min_row=1, min_col=1, max_row=row_max-row_start+2, max_col=5):
|
||
for cell in row:
|
||
data.append(cell.value)
|
||
i = 0
|
||
for row in ws_dp.iter_rows(min_row=1, min_col=1, max_row=row_max-row_start+2, max_col=5):
|
||
for cell in row:
|
||
cell.value = data[i]
|
||
i = i + 1
|
||
|
||
global RC
|
||
global RR
|
||
ws_dp.cell(row=5, column=7).value = RC
|
||
ws_dp.cell(row=6, column=7).value = RR
|
||
|
||
wb_data.save(excel_file)
|
||
just_open(excel_file) # 为了能读取到公式计算的数值,必须要用 win32com 打开关闭一次
|
||
wb_data = openpyxl.load_workbook(excel_file, data_only=True)
|
||
ws_dp = wb_data['dp']
|
||
|
||
return wb_data, ws_dp
|
||
|
||
|
||
def find_row_start_dp(ws_dp, row_max, row_start, conditions):
|
||
"""
|
||
函数功能:获取结果文件 G2 单元格的数据值
|
||
:param ws_dp: excel 中新建 sheet 的指针
|
||
:param row_max: 数据文件中获取到的最后一行的行号
|
||
:param row_start: 数据文件中获取到的第一行有效行的行号
|
||
:param conditions: 通过路径特征提取出来的信息,比如 ['reaach100', 'speed66']
|
||
:return: 返回 excel 中 dp 这个 sheet 中的有效数据行号,并做了加工处理,因为结果文件的部分属性
|
||
"""
|
||
global AV
|
||
ratio = float(conditions[1].removeprefix('speed'))/100
|
||
av_max = AV * ratio
|
||
row_max_dp = row_max - row_start + 1 + 1 # title row
|
||
row_start_dp = row_max_dp - 5
|
||
print(f"row_start_dp = {row_start_dp}")
|
||
while row_start_dp > 1:
|
||
# 处理异常数据:当从数据文件中拷贝的有效数据超过5000时,会触发该代码块
|
||
if ws_dp.cell(row=row_start_dp, column=4).value is None:
|
||
row_start_dp -= 100
|
||
continue
|
||
# 确认数据有效后,开始查找 G2 的值,这里使用到的原理是:
|
||
# 1. 计算连续 5 个点的平均值
|
||
# 2. 和当前测试条件下的最大值做差,如果绝对值在 1 之内,则认定获取到了该值
|
||
_a = float(ws_dp.cell(row=row_start_dp, column=4).value)
|
||
_b = float(ws_dp.cell(row=row_start_dp - 1, column=4).value)
|
||
_c = float(ws_dp.cell(row=row_start_dp - 2, column=4).value)
|
||
_d = float(ws_dp.cell(row=row_start_dp - 3, column=4).value)
|
||
_e = float(ws_dp.cell(row=row_start_dp - 4, column=4).value)
|
||
avg = (_a + _b + _c + _d + _e) / 5
|
||
if abs(avg - av_max) < 1:
|
||
row_start_dp = row_start_dp + 10 - 5 # +10 是因为结果文件 C2 的值是 10,-5是做了保守处理,相当于再往前移动 5 个点位
|
||
break
|
||
else:
|
||
row_start_dp -= 5 # 保守一点,每次移动 5 个点位,如果想要加快程序运行,可适当调整更大一些,建议不超过 15
|
||
else:
|
||
print("数据有误,请确认!")
|
||
print("未找到平衡的点")
|
||
exit(1)
|
||
|
||
return row_start_dp
|
||
|
||
|
||
def single_file_process(data_file, wb_result, count):
|
||
"""
|
||
函数功能:完成单个数据文件的处理:
|
||
1. 将 .data -> .xslx(excel)
|
||
2. 根据文件路径特征,获取到结果文件准确的 sheet name
|
||
3. 找到数据文件有效的起始点位置
|
||
4. 将有效数据 copy 到结果文件对应的 sheet 中的对应位置
|
||
5. 结果文件对应 sheet 中会根据公式生成一部分数据,需要将这部分数据 copy 到 excle 中
|
||
6. 将 excel 处理一下,获取合适的开始点位置,这个开始点指的是要写入结果文件中的 G2 单元格的值
|
||
7. 写入正确的值,int 类型
|
||
:param data_file: 数据文件,数据处理的最小单位
|
||
:param wb_result: 结果文件的指针,可以理解为打开的结果文件的句柄,从该变量引用到其他sheet
|
||
:param count: 计数器,对应急停的 1/2/3 次
|
||
:return: -
|
||
"""
|
||
excel_file = data_file.replace('data', 'xlsx')
|
||
sheet_name = data_file.split('\\')[-1].removesuffix('.data')
|
||
df = pd.read_csv(data_file, sep='\t')
|
||
df.to_excel(excel_file, sheet_name=sheet_name, index=False)
|
||
|
||
conditions = sorted(data_file.split('\\')[-2].split('_')[1:])
|
||
print(f"conditions = {conditions}")
|
||
result_sheet_name = find_result_sheet_name(conditions, count)
|
||
ws_result = wb_result[result_sheet_name]
|
||
|
||
wb_data = openpyxl.load_workbook(excel_file)
|
||
ws_data = wb_data[sheet_name]
|
||
row_max, row_start = find_row_start(excel_file, ws_data, conditions)
|
||
|
||
copy_data_to_result(ws_data, ws_result, row_max, row_start)
|
||
wb_data, ws_dp = copy_data_to_excel_file(wb_data, ws_result, row_max, row_start, excel_file)
|
||
row_start_dp = find_row_start_dp(ws_dp, row_max, row_start, conditions)
|
||
|
||
ws_result["G2"] = int(row_start_dp)
|
||
|
||
wb_data.save(excel_file)
|
||
wb_data.close()
|
||
|
||
|
||
def data_process(result_file, raw_data_dirs):
|
||
"""
|
||
函数功能:完成一个结果文件的数据处理
|
||
:param result_file: 每次处理一个结果文件
|
||
:param raw_data_dirs: 传入所有的数据文件夹,做筛选
|
||
:return: -
|
||
"""
|
||
prefix = result_file.split('\\')[-1].split('_')[0]
|
||
print(f"prefix = {prefix}")
|
||
print(f"raw_data_dirs = {raw_data_dirs}")
|
||
wb_result = openpyxl.load_workbook(result_file) # 打开和关闭结果文件夹十分耗时间
|
||
for raw_data_dir in raw_data_dirs:
|
||
if raw_data_dir.split('\\')[-1].split('_')[0] == prefix:
|
||
print(f"正在处理【{raw_data_dir}】中的数据......")
|
||
_, data_files = traversal_files(raw_data_dir)
|
||
count = 1 # 计数器,对应三次急停数据
|
||
for data_file in sorted(data_files):
|
||
print(f"正在处理【{data_file}】....")
|
||
print(f"count = {count}")
|
||
single_file_process(data_file, wb_result, count)
|
||
count += 1
|
||
|
||
wb_result.save(result_file)
|
||
wb_result.close()
|
||
|
||
|
||
def check_files(raw_data_dirs, result_files):
|
||
if len(result_files) != 3:
|
||
print("结果文件数目错误,请参考 readme.txt 中的规则。")
|
||
exit(3)
|
||
|
||
prefix = []
|
||
for result_file in result_files:
|
||
prefix.append(result_file.split('\\')[-1].split('_')[0])
|
||
if not sorted(prefix) == sorted(['load33', 'load66', 'load100']):
|
||
wd = result_file.split('\\')
|
||
del wd[-1]
|
||
wd = '\\'.join(wd)
|
||
print(f"请关闭所有相关数据文件,并检查工作目录【{wd}】下,有且只允许有类似如下三个文件:")
|
||
print("1. load33_自研_制动性能测试.xlsx")
|
||
print("2. load66_自研_制动性能测试.xlsx")
|
||
print("3. load100_自研_制动性能测试.xlsx")
|
||
exit(8)
|
||
for raw_data_dir in raw_data_dirs:
|
||
prefix = raw_data_dir.split('\\')[-1].split('_')[0]
|
||
if prefix not in ['load33', 'load66', 'load100']:
|
||
print(f"报错信息:数据目录【{raw_data_dir}】不合规,请参考如下形式。")
|
||
print("命名规则:\n\t1. loadAA_speedBB_reachCC\n\t2. loadAA_reachBB_speedCC")
|
||
print("规则解释:AA/BB/CC 指的是负载/速度/臂展的比例,比如 load66_speed100_reach33 意思是 66% 负载,100% 速度以及 33% 臂展情况下的测试结果文件夹。")
|
||
exit(7)
|
||
_, raw_data_files = traversal_files(raw_data_dir)
|
||
if len(raw_data_files) != 3:
|
||
print(f"数据目录【{raw_data_dir}】下数据文件个数错误,每个数据目录下有且只能有三个以 .data 为后缀的数据文件。")
|
||
exit(6)
|
||
for raw_data_file in raw_data_files:
|
||
if not raw_data_file.split('\\')[-1].endswith('.data'):
|
||
print(f"数据文件【{raw_data_file}】后缀错误,每个数据目录下有且只能有三个以 .data 为后缀的数据文件。")
|
||
exit(5)
|
||
print("数据目录合规性检查结束......")
|
||
|
||
|
||
def delete_excel_files():
|
||
global data_dir
|
||
raw_data_dirs, _ = traversal_files(data_dir)
|
||
for raw_data_dir in raw_data_dirs:
|
||
_, raw_data_files = traversal_files(raw_data_dir)
|
||
for raw_data_file in raw_data_files:
|
||
if raw_data_file.endswith('.xlsx'):
|
||
os.remove(raw_data_file)
|
||
|
||
|
||
def main():
|
||
time_start = time.time() # 记录开始时间
|
||
|
||
global data_dir
|
||
raw_data_dirs, result_files = traversal_files(data_dir)
|
||
print("#调试信息======================================")
|
||
print(f"结果文件:{result_files}")
|
||
print(f'数据目录:{raw_data_dirs}')
|
||
check_files(raw_data_dirs, result_files)
|
||
|
||
for result_file in result_files:
|
||
print(f"正在整理【{result_file}】文件的数据......")
|
||
data_process(result_file, raw_data_dirs)
|
||
|
||
delete_excel_files() # 运行结束之后,删除中间临时文件
|
||
|
||
time_end = time.time() # 记录结束时间
|
||
time_total = time_end - time_start # 计算的时间差为程序的执行时间,单位为秒/s
|
||
print(f"数据处理时间:{time_total//3600:02} h {time_total % 3600/60:05.2f} min")
|
||
|
||
# 定义初始参数,数据文件夹路径/最大角速度/减速比/额定电流
|
||
global data_dir
|
||
global AV
|
||
global RR
|
||
global RC
|
||
data_dir = r'D:\Syncthing\company\D-测试工作\X-自动化测试\99-Data\j1'
|
||
AV = 180 # AV for Angular velocity
|
||
RR = 120 # RR for Angular velocity
|
||
RC = 5.6 # RC for Rated Current
|
||
|
||
if __name__ == "__main__":
|
||
main()
|