ospc.org/distributed/api/celery_tasks.py at de70e56028105c7366e8b7ae93b5ce743d176029 · ospc-org/ospc.org · 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
import json
import os
from io import BytesIO

from celery import Celery

import taxcalc
import btax
from btax.front_end_util import runner_json_tables

from collections import defaultdict


CELERY_BROKER_URL = os.environ.get('CELERY_BROKER_URL',
                                   'redis://localhost:6379')
CELERY_RESULT_BACKEND = os.environ.get('CELERY_RESULT_BACKEND',
                                       'redis://localhost:6379')

celery_app = Celery('tasks2', broker=CELERY_BROKER_URL,
                    backend=CELERY_RESULT_BACKEND)
celery_app.conf.update(
    task_serializer='json',
    accept_content=['msgpack', 'json'],
)


def dropq_task(year_n, user_mods, start_year, use_puf_not_cps=True,
               use_full_sample=True):
    print(
        'keywords to dropq',
        dict(
            year_n_n=year_n,
            start_year=int(start_year),
            use_puf_not_cps=use_puf_not_cps,
            use_full_sample=use_full_sample,
            user_mods=user_mods
        )
    )

    raw_data = taxcalc.tbi.run_nth_year_taxcalc_model(
        year_n=year_n,
        start_year=int(start_year),
        use_puf_not_cps=use_puf_not_cps,
        use_full_sample=use_full_sample,
        user_mods=user_mods
    )

    return raw_data


def postprocess(ans, postprocess_func):
    all_to_process = defaultdict(list)
    for year_data in ans:
        for key, value in year_data.items():
            all_to_process[key] += value
    results = postprocess_func(all_to_process)
    # Add taxcalc version to results
    vinfo = taxcalc._version.get_versions()
    results['taxcalc_version'] = vinfo['version']
    # TODO: Make this the distributed app version, not the TC version
    results['dropq_version'] = vinfo['version']
    return json.dumps(results)


@celery_app.task(name='api.celery_tasks.dropq_task_async')
def dropq_task_async(year_n, user_mods, start_year, use_puf_not_cps=True):
    return dropq_task(year_n, user_mods, start_year,
                      use_puf_not_cps=use_puf_not_cps, use_full_sample=True)


@celery_app.task(name='api.celery_tasks.dropq_task_small_async')
def dropq_task_small_async(year_n, user_mods, start_year,
                           use_puf_not_cps=True):
    return dropq_task(year_n, user_mods, start_year,
                      use_puf_not_cps=use_puf_not_cps, use_full_sample=False)


@celery_app.task(name='api.celery_tasks.taxbrain_postprocess')
def taxbrain_postprocess(ans):
    return postprocess(ans, taxcalc.tbi.postprocess)


@celery_app.task(name='api.celery_tasks.taxbrain_elast_async')
def taxbrain_elast_async(year_n, start_year,
                         use_puf_not_cps,
                         user_mods,
                         gdp_elasticity,
                         use_full_sample=True,
                         return_dict=True):

    gdp_elast_i = taxcalc.tbi.run_nth_year_gdp_elast_model(
        year_n=year_n,
        start_year=start_year,
        use_puf_not_cps=use_puf_not_cps,
        use_full_sample=use_full_sample,
        user_mods=user_mods,
        gdp_elasticity=gdp_elasticity,
        return_dict=True
    )
    print(gdp_elast_i)

    return gdp_elast_i


@celery_app.task(name='api.celery_tasks.taxbrain_elast_postprocess')
def taxbrain_elast_postprocess(ans):
    return postprocess(ans, taxcalc.tbi.postprocess_elast)


@celery_app.task(name='api.celery_tasks.btax_async')
def btax_async(user_mods, start_year):
    print("user mods: ", user_mods)
    user_mods['start_year'] = start_year
    print("submitting btax data: ", user_mods)
    results = {}
    tables = json.loads(runner_json_tables(**user_mods))
    if tables.get("json_table"):
        results.update(tables["json_table"])
        if tables.get("dataframes"):
            dataframes = json.loads(tables["dataframes"])
            for x, y in list(dataframes.items()):
                dataframes[x] = json.loads(y)
            results["dataframes"] = dataframes
    else:
        results.update(tables)
    vinfo = taxcalc._version.get_versions()
    results['taxcalc_version'] = vinfo['version']
    results['dropq_version'] = vinfo['version']
    binfo = btax._version.get_versions()
    results['btax_version'] = binfo['version']
    json_res = json.dumps(results)
    return json_res


@celery_app.task(name='api.celery_tasks.file_upload_test')
def file_upload_test(data, compression):
    import pandas as pd
    df = pd.read_csv(BytesIO(data), compression='gzip')
    desc = df.describe()
    formatted = {'outputs': [], 'aggr_outputs': []}
    formatted['aggr_outputs'].append({
            'tags': {'default': 'default'},
            'title': 'desc',
            'downloadable': [{'filename': 'desc' + '.csv',
                              'text': desc.to_csv()}],
            'renderable': desc.to_html()
        })
    return json.dumps(formatted)