aind-data-schema/examples/processing.py at c63c510ceeebe6da925a8250703dfc78719ea3f8 · AllenNeuralDynamics/aind-data-schema · GitHub

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
"""example processing"""

import argparse
from datetime import datetime, timezone

from aind_data_schema.components.identifiers import Code
from aind_data_schema.core.processing import (
    DataProcess,
    Processing,
    ProcessName,
    ProcessStage,
    ResourceTimestamped,
    ResourceUsage,
)
from aind_data_schema_models.units import MemoryUnit
from aind_data_schema_models.system_architecture import OperatingSystem, CPUArchitecture

# If a timezone isn't specified, the timezone of the computer running this
# script will be used as default
t = datetime(2022, 11, 22, 8, 43, 00, tzinfo=timezone.utc)


cpu_usage_list = [
    ResourceTimestamped(timestamp=datetime(2024, 9, 13, tzinfo=timezone.utc), usage=75.5),
    ResourceTimestamped(timestamp=datetime(2024, 9, 13, tzinfo=timezone.utc), usage=80.0),
]

gpu_usage_list = [
    ResourceTimestamped(timestamp=datetime(2024, 9, 13, tzinfo=timezone.utc), usage=60.0),
    ResourceTimestamped(timestamp=datetime(2024, 9, 13, tzinfo=timezone.utc), usage=65.5),
]

ram_usage_list = [
    ResourceTimestamped(timestamp=datetime(2024, 9, 13, tzinfo=timezone.utc), usage=70.0),
    ResourceTimestamped(timestamp=datetime(2024, 9, 13, tzinfo=timezone.utc), usage=72.5),
]

file_io_usage_list = [
    ResourceTimestamped(timestamp=datetime(2024, 9, 13, tzinfo=timezone.utc), usage=5.5),
    ResourceTimestamped(timestamp=datetime(2024, 9, 13, tzinfo=timezone.utc), usage=6.0),
]

example_code = Code(
    url="https://github.com/abcd",
    version="0.1",
    parameters={"size": 7},
)

p = Processing.create_with_sequential_process_graph(
    pipelines=[
        Code(
            name="Imaging processing pipeline",
            url="https://url/for/pipeline",
            version="0.1.1",
        ),
    ],
    data_processes=[
        DataProcess(
            process_type=ProcessName.IMAGE_TILE_FUSING,
            experimenters=["Dr. Dan"],
            stage=ProcessStage.PROCESSING,
            start_date_time=t,
            end_date_time=t,
            output_path="/path/to/outputs",
            pipeline_name="Imaging processing pipeline",
            code=example_code.model_copy(
                update=dict(
                    parameters={"size": 7},
                )
            ),
            resources=ResourceUsage(
                os=OperatingSystem.UBUNTU_20_04,
                architecture=CPUArchitecture.X86_64,
                cpu="Intel Core i7",
                cpu_cores=8,
                gpu="NVIDIA GeForce RTX 3080",
                system_memory=32.0,
                system_memory_unit=MemoryUnit.GB,
                ram=16.0,
                ram_unit=MemoryUnit.GB,
                cpu_usage=cpu_usage_list,
                gpu_usage=gpu_usage_list,
                ram_usage=ram_usage_list,
            ),
        ),
        DataProcess(
            process_type=ProcessName.FILE_FORMAT_CONVERSION,
            pipeline_name="Imaging processing pipeline",
            experimenters=["Dr. Dan"],
            stage=ProcessStage.PROCESSING,
            start_date_time=t,
            end_date_time=t,
            output_path="/path/to/outputs",
            code=example_code.model_copy(
                update=dict(
                    parameters={"u": 7, "z": True},
                )
            ),
        ),
        DataProcess(
            process_type=ProcessName.IMAGE_DESTRIPING,
            pipeline_name="Imaging processing pipeline",
            experimenters=["Dr. Dan"],
            stage=ProcessStage.PROCESSING,
            start_date_time=t,
            end_date_time=t,
            output_path="/path/to/output",
            code=example_code.model_copy(
                update=dict(
                    parameters={"a": 2, "b": -2},
                )
            ),
        ),
        DataProcess(
            stage=ProcessStage.ANALYSIS,
            experimenters=["Some Analyzer"],
            process_type=ProcessName.ANALYSIS,
            start_date_time=t,
            end_date_time=t,
            output_path="/path/to/outputs",
            code=example_code.model_copy(
                update=dict(
                    parameters={"size": 7},
                )
            ),
        ),
        DataProcess(
            name="Analysis 2",
            stage=ProcessStage.ANALYSIS,
            experimenters=["Some Analyzer"],
            process_type=ProcessName.ANALYSIS,
            start_date_time=t,
            end_date_time=t,
            output_path="/path/to/outputs",
            code=example_code.model_copy(
                update=dict(
                    parameters={"u": 7, "z": True},
                )
            ),
        ),
    ],
)

if __name__ == "__main__":
    parser = argparse.ArgumentParser()
    parser.add_argument("--output-dir", default=None, help="Output directory for generated JSON file")
    args = parser.parse_args()

    serialized = p.model_dump_json()
    deserialized = Processing.model_validate_json(serialized)
    p.write_standard_file(output_directory=args.output_dir)