classify_stats.json

{
    "num_3_seen": 13,
    "num_5_seen": 11,
    "num_filtered_short_reads": 0,
    "num_fl": 9,
    "num_flc": 0,
    "num_flnc": 9,
    "num_flnc_bases": 35563,
    "num_nfl": 13,
    "num_nflc": null,
    "num_nflnc": null,
    "num_polyA_seen": 13,
    "num_reads": 22
}

convert_to_report.py

import sys
import json
import warnings
import itertools
from collections import defaultdict

from pbcommand.models.report import Report, Attribute, Table, Column


def to_attributes(raw_d, namespace):
    attributes = []
    for k, v in raw_d.items():
        ns = "_".join([namespace, k.lower()])
        # These can't be none for some reason
        if v is not None:
            a = Attribute(ns, v, name=k)
            attributes.append(a)
        else:
            warnings.warn("skipping null entry {k}->{v}".format(k=k, v=v))

    return attributes


def _merge_attributes_d(attributes_list):
    attrs = defaultdict(lambda : [])
    for ax in attributes_list:
        for a in ax:
            attrs[a.id].append(a.value)

    return attrs


def sum_attributes(attributes_list):
    d = _merge_attributes_d(attributes_list)
    return [Attribute(k, sum(values), name=k) for k, values in d.iteritems()]


def attributes_to_table(attributes_list, table_id, title):
    """Merge the Attributes in from different chunks to create a table"""
    attrs = _merge_attributes_d(attributes_list)
    columns = [Column(k.lower(), header=k, values=values) for k, values in attrs.iteritems()]
    table = Table(table_id, title=title, columns=columns)
    return table


def load_raw(file_name):

    with open(file_name, 'r') as f:
        d = json.loads(f.read())

    return d


def main():
    d = load_raw('classify_stats.json')

    report_id = "iso_seq_stats"
    namespace = "classify_stats"
    attributes = to_attributes(d, namespace)
    report = Report(report_id, attributes=attributes)
    report.write_json("report.json")

    # Create new Report with Table and Merged stats
    # mock chunks
    chunk_attrs = [attributes, attributes]
    table = attributes_to_table(chunk_attrs, 'chunk_metrics', "Chunk Metrics")
    print table
    merged_attributes = sum_attributes(chunk_attrs)
    mreport = Report(report_id, attributes=merged_attributes, tables=[table])
    mreport.write_json("merged-report.json")

    return 0

if __name__ == '__main__':
    sys.exit(main())

merged-report.json

{
    "_changelist": "UNKNOWN", 
    "_version": "0.2.13", 
    "attributes": [
        {
            "id": "iso_seq_stats.classify_stats_num_flc", 
            "name": "classify_stats_num_flc", 
            "value": 0
        }, 
        {
            "id": "iso_seq_stats.classify_stats_num_5_seen", 
            "name": "classify_stats_num_5_seen", 
            "value": 22
        }, 
        {
            "id": "iso_seq_stats.classify_stats_num_flnc_bases", 
            "name": "classify_stats_num_flnc_bases", 
            "value": 71126
        }, 
        {
            "id": "iso_seq_stats.classify_stats_num_polya_seen", 
            "name": "classify_stats_num_polya_seen", 
            "value": 26
        }, 
        {
            "id": "iso_seq_stats.classify_stats_num_fl", 
            "name": "classify_stats_num_fl", 
            "value": 18
        }, 
        {
            "id": "iso_seq_stats.classify_stats_num_nfl", 
            "name": "classify_stats_num_nfl", 
            "value": 26
        }, 
        {
            "id": "iso_seq_stats.classify_stats_num_3_seen", 
            "name": "classify_stats_num_3_seen", 
            "value": 26
        }, 
        {
            "id": "iso_seq_stats.classify_stats_num_reads", 
            "name": "classify_stats_num_reads", 
            "value": 44
        }, 
        {
            "id": "iso_seq_stats.classify_stats_num_flnc", 
            "name": "classify_stats_num_flnc", 
            "value": 18
        }, 
        {
            "id": "iso_seq_stats.classify_stats_num_filtered_short_reads", 
            "name": "classify_stats_num_filtered_short_reads", 
            "value": 0
        }
    ], 
    "dataset_uuids": [], 
    "id": "iso_seq_stats", 
    "plotGroups": [], 
    "tables": [
        {
            "columns": [
                {
                    "header": "classify_stats_num_flc", 
                    "id": "iso_seq_stats.chunk_metrics.classify_stats_num_flc", 
                    "values": [
                        0, 
                        0
                    ]
                }, 
                {
                    "header": "classify_stats_num_5_seen", 
                    "id": "iso_seq_stats.chunk_metrics.classify_stats_num_5_seen", 
                    "values": [
                        11, 
                        11
                    ]
                }, 
                {
                    "header": "classify_stats_num_flnc_bases", 
                    "id": "iso_seq_stats.chunk_metrics.classify_stats_num_flnc_bases", 
                    "values": [
                        35563, 
                        35563
                    ]
                }, 
                {
                    "header": "classify_stats_num_polya_seen", 
                    "id": "iso_seq_stats.chunk_metrics.classify_stats_num_polya_seen", 
                    "values": [
                        13, 
                        13
                    ]
                }, 
                {
                    "header": "classify_stats_num_fl", 
                    "id": "iso_seq_stats.chunk_metrics.classify_stats_num_fl", 
                    "values": [
                        9, 
                        9
                    ]
                }, 
                {
                    "header": "classify_stats_num_nfl", 
                    "id": "iso_seq_stats.chunk_metrics.classify_stats_num_nfl", 
                    "values": [
                        13, 
                        13
                    ]
                }, 
                {
                    "header": "classify_stats_num_3_seen", 
                    "id": "iso_seq_stats.chunk_metrics.classify_stats_num_3_seen", 
                    "values": [
                        13, 
                        13
                    ]
                }, 
                {
                    "header": "classify_stats_num_reads", 
                    "id": "iso_seq_stats.chunk_metrics.classify_stats_num_reads", 
                    "values": [
                        22, 
                        22
                    ]
                }, 
                {
                    "header": "classify_stats_num_flnc", 
                    "id": "iso_seq_stats.chunk_metrics.classify_stats_num_flnc", 
                    "values": [
                        9, 
                        9
                    ]
                }, 
                {
                    "header": "classify_stats_num_filtered_short_reads", 
                    "id": "iso_seq_stats.chunk_metrics.classify_stats_num_filtered_short_reads", 
                    "values": [
                        0, 
                        0
                    ]
                }
            ], 
            "id": "iso_seq_stats.chunk_metrics", 
            "title": "Chunk Metrics"
        }
    ]
}

report.json

{
    "_changelist": "UNKNOWN", 
    "_version": "0.2.13", 
    "attributes": [
        {
            "id": "iso_seq_stats.classify_stats_num_polya_seen", 
            "name": "num_polyA_seen", 
            "value": 13
        }, 
        {
            "id": "iso_seq_stats.classify_stats_num_flc", 
            "name": "num_flc", 
            "value": 0
        }, 
        {
            "id": "iso_seq_stats.classify_stats_num_flnc_bases", 
            "name": "num_flnc_bases", 
            "value": 35563
        }, 
        {
            "id": "iso_seq_stats.classify_stats_num_3_seen", 
            "name": "num_3_seen", 
            "value": 13
        }, 
        {
            "id": "iso_seq_stats.classify_stats_num_reads", 
            "name": "num_reads", 
            "value": 22
        }, 
        {
            "id": "iso_seq_stats.classify_stats_num_fl", 
            "name": "num_fl", 
            "value": 9
        }, 
        {
            "id": "iso_seq_stats.classify_stats_num_flnc", 
            "name": "num_flnc", 
            "value": 9
        }, 
        {
            "id": "iso_seq_stats.classify_stats_num_filtered_short_reads", 
            "name": "num_filtered_short_reads", 
            "value": 0
        }, 
        {
            "id": "iso_seq_stats.classify_stats_num_5_seen", 
            "name": "num_5_seen", 
            "value": 11
        }, 
        {
            "id": "iso_seq_stats.classify_stats_num_nfl", 
            "name": "num_nfl", 
            "value": 13
        }
    ], 
    "dataset_uuids": [], 
    "id": "iso_seq_stats", 
    "plotGroups": [], 
    "tables": []
}