aboutsummaryrefslogtreecommitdiff
path: root/scripts/sampledata.py
blob: 411ec2b413dd1ce0b0f440742f71ad11c01e002d (plain)
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
import json

# Required Evils!
from flask import g
from wqflask import app

from wqflask.show_trait import show_trait
from wqflask.database import database_connection
from wqflask.search_results import SearchResultPage


class UserSessionSimulator():
    def __init__(self, user_id):
        self._user_id = user_id

    @property
    def user_id(self):
        return self._user_id


def dump_sample_data(dataset_name, trait_id):
    """Given a DATASET_NAME e.g. 'BXDPublish' and a TRAIT_ID
    e.g. '10007', dump the sample data as json object"""
    with database_connection() as conn, conn.cursor() as cursor:
        sample_data = {"headers": ["Name", "Value", "SE"], "data": []}

        with app.app_context():
            g.user_session = UserSessionSimulator(None)
            data = show_trait.ShowTrait(
                cursor, user_id=None,
                kw={
                    "trait_id": trait_id,
                    "dataset": dataset_name
                }
            )
            attributes = data.js_data.get("attributes")
            for id_ in attributes:
                sample_data["headers"].append(attributes[id_].name)
            for sample in data.js_data.get("sample_lists")[0]:
                sample_data["data"].append(
                    [
                        sample.name,
                        sample.value or 'x',
                        sample.variance or 'x',
                        *[str(sample.extra_attributes.get(str(key), "x"))
                          for key in attributes],
                    ])
            return sample_data


def fetch_all_traits(species, group, type_, dataset):
    with app.app_context():
        g.user_session = UserSessionSimulator(None)
        for result in SearchResultPage({
                "species": species,
                "group": group,
                "type": type_,
                "dataset": dataset,
                "search_terms_or": "*",
        }).trait_list:
            yield result.get('name')


# Dump all traits from a given dataset
for trait in fetch_all_traits(
        species="mouse",
        group="BXD",
        type_="Phenotypes",
        dataset="BXDPublish",
):
    print(json.dumps(dump_sample_data("BXDPublish", trait)))
    break  # Just do this once!