Open-CT
/
openbrain
1
0
Fork 4
Code Issues Pull Requests 1 Projects Releases Wiki Activity

feat: use process data to supplement stop-time

This commit is contained in:
HanFujing 2022-08-20 14:37:10 +08:00
parent c7c1545d55
commit 1be992752c
4 changed files with 247 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

77
pydata-han/Process/get_stoptime_a.py Normal file
View File

@ -0,0 +1,77 @@
import pandas as pd
from datetime import datetime
time_dict = {}
stop_time_dict = {}
data = pd.read_excel(r'A.xlsx')
datetimeFormat = '%Y-%m-%dT%H:%M:%S.%f+08:00'
datetimeFormat2 = '%Y-%m-%dT%H:%M:%S+08:00'
for index, row in data.iterrows():
id = str(row['ticket_id'])
timestamp = str(row['timestamp'])
if (id not in time_dict.keys()):
time_dict[id] = []
time_dict[id].append(timestamp)
else:
time_dict[id].append(timestamp)
for key, value in time_dict.items():
stop_time_dict[key] = value[-1]
data2 = pd.read_excel(r'a_out_0714.xlsx')
stoptime_new_list = []
time_new_list = []
empty = 0
for index, row in data2.iterrows():
print(index)
id = str(row['ticket_id'])
P1_CODE = row['P3_CODE']
MM60101_CODE = row['MM60311_CODE']
if (pd.isna(row['stop_time']) and (int(P1_CODE) != 99 or int(MM60101_CODE) != 99)):
if (id in stop_time_dict.keys()):
timestamp = stop_time_dict[id]
stoptime_new_list.append(timestamp)
try:
date2 = datetime.strptime(str(timestamp), datetimeFormat)
except ValueError:
date2 = datetime.strptime(str(timestamp), datetimeFormat2)
else:
empty = empty + 1
stoptime_new_list.append("")
time_new_list.append("")
continue
elif (pd.isna(row['stop_time']) and int(P1_CODE) == 99 and int(MM60101_CODE) == 99):
empty = empty + 1
stoptime_new_list.append("")
time_new_list.append("")
continue
else:
stoptime_new_list.append("")
try:
date2 = datetime.strptime(str(row['stop_time']), datetimeFormat)
except ValueError:
date2 = datetime.strptime(str(row['stop_time']), datetimeFormat2)
try:
date1 = datetime.strptime(str(row['start_time']), datetimeFormat)
except ValueError:
date1 = datetime.strptime(str(row['start_time']), datetimeFormat2)
delta = date2 - date1
miao = delta.seconds
fen = round(miao/60, 2)
time_new_list.append(fen)
col_name = data2.columns.tolist()
col_name.insert(col_name.index('stop_time')+1, 'stoptime_new')
data2 = data2.reindex(columns=col_name)
data2['stoptime_new'] = stoptime_new_list
col_name.insert(col_name.index('cost_time')+1, 'time_new')
data2 = data2.reindex(columns=col_name)
data2['time_new'] = time_new_list
data2.to_excel('a_out_0719.xlsx')

77
pydata-han/Process/get_stoptime_z.py Normal file
View File

@ -0,0 +1,77 @@
import pandas as pd
from datetime import datetime
time_dict = {}
stop_time_dict = {}
data = pd.read_excel(r'Z.xlsx')
datetimeFormat = '%Y-%m-%dT%H:%M:%S.%f+08:00'
datetimeFormat2 = '%Y-%m-%dT%H:%M:%S+08:00'
for index, row in data.iterrows():
id = str(row['ticket_id'])
timestamp = str(row['timestamp'])
if (id not in time_dict.keys()):
time_dict[id] = []
time_dict[id].append(timestamp)
else:
time_dict[id].append(timestamp)
for key, value in time_dict.items():
stop_time_dict[key] = value[-1]
data2 = pd.read_excel(r'z_out_0715.xlsx')
stoptime_new_list = []
time_new_list = []
empty = 0
for index, row in data2.iterrows():
print(index)
id = str(row['ticket_id'])
P1_CODE = row['P1_CODE']
MM60101_CODE = row['MM60101_CODE']
if (pd.isna(row['stop_time']) and (int(P1_CODE) != 99 or int(MM60101_CODE) != 99)):
if (id in stop_time_dict.keys()):
timestamp = stop_time_dict[id]
stoptime_new_list.append(timestamp)
try:
date2 = datetime.strptime(str(timestamp), datetimeFormat)
except ValueError:
date2 = datetime.strptime(str(timestamp), datetimeFormat2)
else:
empty = empty + 1
stoptime_new_list.append("")
time_new_list.append("")
continue
elif (pd.isna(row['stop_time']) and int(P1_CODE) == 99 and int(MM60101_CODE) == 99):
empty = empty + 1
stoptime_new_list.append("")
time_new_list.append("")
continue
else:
stoptime_new_list.append("")
try:
date2 = datetime.strptime(str(row['stop_time']), datetimeFormat)
except ValueError:
date2 = datetime.strptime(str(row['stop_time']), datetimeFormat2)
try:
date1 = datetime.strptime(str(row['start_time']), datetimeFormat)
except ValueError:
date1 = datetime.strptime(str(row['start_time']), datetimeFormat2)
delta = date2 - date1
miao = delta.seconds
fen = round(miao/60, 2)
time_new_list.append(fen)
col_name = data2.columns.tolist()
col_name.insert(col_name.index('stop_time')+1, 'stoptime_new')
data2 = data2.reindex(columns=col_name)
data2['stoptime_new'] = stoptime_new_list
col_name.insert(col_name.index('cost_time')+1, 'time_new')
data2 = data2.reindex(columns=col_name)
data2['time_new'] = time_new_list
data2.to_excel('z_out_0719.xlsx')

33
pydata-han/Process/split.py Normal file
View File

@ -0,0 +1,33 @@
import pandas as pd
data1 = pd.read_excel(r'ticket_log_PBL_testing3.xlsx')
A1 = data1[data1['contest_id'].str.contains('高阶能力测试B|高阶能力测试C')]
Z1 = data1[data1['contest_id'].str.contains('数学建模')]
A1.to_excel('A1.xlsx')
Z1.to_excel('Z1.xlsx')
data2 = pd.read_excel(r'ticket_log_PBL_testing3.xlsx', sheet_name='Result 2')
A2 = data2[data2['contest_id'].str.contains('高阶能力测试B|高阶能力测试C')]
Z2 = data2[data2['contest_id'].str.contains('数学建模')]
A2.to_excel('A2.xlsx')
Z2.to_excel('Z2.xlsx')
data3 = pd.read_excel(r'ticket_log_PBL_testing3.xlsx', sheet_name='Result 3')
A3 = data3[data3['contest_id'].str.contains('高阶能力测试B|高阶能力测试C')]
Z3 = data3[data3['contest_id'].str.contains('数学建模')]
A3.to_excel('A3.xlsx')
Z3.to_excel('Z3.xlsx')
data4 = pd.read_excel(r'ticket_log_PBL_testing3.xlsx', sheet_name='Result 4')
A4 = data4[data4['contest_id'].str.contains('高阶能力测试B|高阶能力测试C')]
Z4 = data4[data4['contest_id'].str.contains('数学建模')]
A4.to_excel('A4.xlsx')
Z4.to_excel('Z4.xlsx')
A = pd.concat([A1, A2, A3, A4])
Z = pd.concat([Z1, Z2, Z3, Z4])
A.to_excel('A.xlsx')
Z.to_excel('Z.xlsx')

60
pydata-han/Process/statistic_time.py Normal file
View File

@ -0,0 +1,60 @@
import pandas as pd
data_a = pd.read_excel(r'a_out_0719.xlsx')
data_z = pd.read_excel(r'z_out_0719.xlsx')
level0to3 = 0
level3to6 = 0
level6to9 = 0
level9to12 = 0
level12to15 = 0
levelabove15 = 0
level0to5 = 0
level5to10 = 0
level10to15 = 0
level15to20 = 0
level20to25 = 0
level25to30 = 0
levelabove30 = 0
print("A")
for index, row in data_a.iterrows():
if (pd.isna(row['time_new'])):
continue
fen = float(row['time_new'])
if (fen <= 5):
level0to5 = level0to5 + 1
elif (fen > 5 and fen <= 10):
level5to10 = level5to10 + 1
elif (fen > 10 and fen <= 15):
level10to15 = level10to15 + 1
elif (fen > 15 and fen <= 20):
level15to20 = level15to20 + 1
elif (fen > 20 and fen <= 25):
level20to25 = level20to25 + 1
elif (fen > 25 and fen <= 30):
level25to30 = level25to30 + 1
else:
levelabove30 = levelabove30 + 1
print(level0to5, level5to10, level10to15, level15to20, level20to25, level25to30, levelabove30)
print("z")
for index, row in data_z.iterrows():
if (pd.isna(row['time_new'])):
continue
fen = float(row['time_new'])
if (fen <= 3):
level0to3 = level0to3 + 1
elif (fen > 3 and fen <= 6):
level3to6 = level3to6 + 1
elif (fen > 6 and fen <= 9):
level6to9 = level6to9 + 1
elif (fen > 9 and fen <= 12):
level9to12 = level9to12 + 1
elif (fen > 12 and fen <= 15):
level12to15 = level12to15 + 1
else:
levelabove15 = levelabove15 + 1
print(level0to3, level3to6, level6to9, level9to12, level12to15,levelabove15)