1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
| class Controller(object):
def __init__(self, funcset: BasicFuncSet = FuncSet()):
self.funcset = funcset
@validate
def compute_single(
self,
get_id_and_params: t.Callable[[], tuple[int, T.general.Params]],
get_full_path: t.Callable[[str], str],
*,
is_write: bool = True,
) -> tuple[result.ComputeResult, pd.DataFrame]:
"""compute single values.
is_write: write to file
"""
id, params = get_id_and_params()
input_data = InputData.from_dict(params)
filelist: t.List[result.ResultFile] = []
# 生成写入数据的函数
write_data = use_write_data(
id,
params["udl2_file"],
filelist.append,
current_type=1 if is_zhiliu(params) else 0, # ac 0, dc 1. zhiliu is dc
)
# filter period
df = self.funcset.filter(input_data=input_data)
if is_write:
write_data(
df, params["udl2_file"], get_full_path(params["out_file_path_1"])
)
# stat period, support multiple files, but not use this is api call
df = (
self.funcset.stat(
df, params, interval_jihua=params.get("interval_jihua", True)
),
)
df = (dict(iter(row)) for row in df)
df = pd.DataFrame(df)
if is_write:
write_data(
df, params["out_file_path_1"], get_full_path(params["out_file_path_2"])
)
# model period
df = self.funcset.model(df, params)
if is_write:
write_data(
df, params["out_file_path_2"], get_full_path(params["out_file_path_3"])
)
# 包含了三级文件
file_result = result.ComputeResult(
status=result.Status.success,
msg="success!",
data=filelist,
)
# 返回文件以及最终的DataFrame
return file_result, df
def write_final_files(
self,
ac_df: pd.DataFrame,
dc_df: pd.DataFrame,
output_path_fn: t.Callable[[str], str],
) -> result.FinalFiles:
"""写入 ac dc 文件"""
ac_file = output_path_fn("ac")
dc_file = output_path_fn("dc")
fileutils.to_csv(ac_df, str(ac_file))
fileutils.to_csv(dc_df, str(dc_file))
return result.FinalFiles(
ac=result.ResultFile(
id=1,
current_type=0,
original_filename="all udl2_files",
original_filepath="null",
in_filename="all results of udl2_files",
filename=fileutils.get_file_name(str(ac_file)),
filepath=str(ac_file),
),
dc=result.ResultFile(
id=2,
current_type=1,
original_filename="all udl2_files",
original_filepath="null",
in_filename="all results of udl2_files",
filename=fileutils.get_file_name(str(dc_file)),
filepath=str(dc_file),
),
)
def collect_files(
self,
param_group: T.general.ParamGroup,
is_write: bool = True,
) -> tuple[list[result.ComputeResult], list[pd.DataFrame]]:
"""
对参数列表里面的数据进行计算，并返回结果列表
compute_single: 计算单一文件的函数
"""
res: t.List[result.ComputeResult] = []
df_list: t.List[pd.DataFrame] = []
for i, p in enumerate(param_group["param_list"]):
def get_id_and_params():
return i, p
r, df = self.compute_single(
get_id_and_params,
param_group["get_full_path"],
is_write=is_write,
)
# r contains stage-1, stage-2, stage-3 files
res.append(r)
df_list.append(df)
return res, df_list
def compute(
self,
param_group: T.general.ParamGroup,
is_write: bool = True,
) -> result.FinalResult:
"""
计算并返回最终结果
collect_files 是收集文件的函数，也包含了计算单个文件的过程
"""
res, df_list = self.collect_files(param_group, is_write)
# 整理最终的文件
ac_df, dc_df = fileutils.merge_files(res, df_list)
output_fn = param_group.get("output_path")
if output_fn is None:
raise ValueError("output_path is None")
final_files = self.write_final_files(ac_df, dc_df, output_fn)
return result.FinalResult(
status=result.Status.success,
msg="success!",
compute_result=res,
final_files=final_files,
)
|