6002459992

Committed 28 Aug 2023 04:33PM UTC coverage: 80.919%. Remained the same

Build # 6002459992

Build Type

push

github

Committed by

web-flow

Commit Message

Update README.md

Run Details

574 of 738 branches covered (0.0%)

Branch coverage included in aggregate %.

1398 of 1699 relevant lines covered (82.28%)

0.82 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

0.0

/src/cell_classification/prepare_data_script_tonic_annotated.py

import os

from cell_classification.simple_data_prep import SimpleTFRecords

os.environ["CUDA_VISIBLE_DEVICES"] = "-1"


def naming_convention(fname):
    return os.path.join(
        "E:/angelo_lab/data/TONIC/raw/segmentation_data/deepcell_output",
        fname + "_feature_0.tif"
    )


data_prep = SimpleTFRecords(
    data_dir=os.path.normpath(
        "C:/Users/Lorenz/OneDrive - Charité - Universitätsmedizin Berlin/cell_classification/" +
        "data_annotation/tonic/raw"
    ),
    cell_table_path=os.path.normpath(
        "C:/Users/Lorenz/OneDrive - Charité - Universitätsmedizin Berlin/cell_classification/" +
        "data_annotation/tonic/ground_truth.csv"
    ),
    imaging_platform="MIBI",
    dataset="TONIC",
    tissue_type="TNBC",
    nuclei_channels=["H3K27me3", "H3K9ac"],
    membrane_channels=["CD45", "ECAD", "CD14", "CD38", "CK17"],
    selected_markers=[
        "Calprotectin", "CD14", "CD163", "CD20", "CD3", "CD31", "CD4", "CD45", "CD56", "CD68",
        "CD8", "ChyTr", "CK17", "Collagen1", "ECAD", "FAP", "Fibronectin", "FOXP3", "HLADR", "SMA",
        "VIM"
    ],
    tile_size=[256, 256],
    stride=[240, 240],
    tf_record_path=os.path.normpath("E:/angelo_lab/data/TONIC/annotated"),
    normalization_dict_path=os.path.normpath(
      "E:/angelo_lab/data/TONIC/normalization_dict.json"
    ),
    normalization_quantile=0.999,
    sample_key="fov",
    segmentation_fname="cell_segmentation",
    segmentation_naming_convention=naming_convention,
    segment_label_key="labels",
    exclude_background_tiles=True,
    gt_suffix="",
)

data_prep.make_tf_record()

1	import os	×
2
3	from cell_classification.simple_data_prep import SimpleTFRecords	×
4
5	os.environ["CUDA_VISIBLE_DEVICES"] = "-1"	×
6
7
8	def naming_convention(fname):	×
9	return os.path.join(	×
10	"E:/angelo_lab/data/TONIC/raw/segmentation_data/deepcell_output",
11	fname + "_feature_0.tif"
12	)
13
14
15	data_prep = SimpleTFRecords(	×
16	data_dir=os.path.normpath(
17	"C:/Users/Lorenz/OneDrive - Charité - Universitätsmedizin Berlin/cell_classification/" +
18	"data_annotation/tonic/raw"
19	),
20	cell_table_path=os.path.normpath(
21	"C:/Users/Lorenz/OneDrive - Charité - Universitätsmedizin Berlin/cell_classification/" +
22	"data_annotation/tonic/ground_truth.csv"
23	),
24	imaging_platform="MIBI",
25	dataset="TONIC",
26	tissue_type="TNBC",
27	nuclei_channels=["H3K27me3", "H3K9ac"],
28	membrane_channels=["CD45", "ECAD", "CD14", "CD38", "CK17"],
29	selected_markers=[
30	"Calprotectin", "CD14", "CD163", "CD20", "CD3", "CD31", "CD4", "CD45", "CD56", "CD68",
31	"CD8", "ChyTr", "CK17", "Collagen1", "ECAD", "FAP", "Fibronectin", "FOXP3", "HLADR", "SMA",
32	"VIM"
33	],
34	tile_size=[256, 256],
35	stride=[240, 240],
36	tf_record_path=os.path.normpath("E:/angelo_lab/data/TONIC/annotated"),
37	normalization_dict_path=os.path.normpath(
38	"E:/angelo_lab/data/TONIC/normalization_dict.json"
39	),
40	normalization_quantile=0.999,
41	sample_key="fov",
42	segmentation_fname="cell_segmentation",
43	segmentation_naming_convention=naming_convention,
44	segment_label_key="labels",
45	exclude_background_tiles=True,
46	gt_suffix="",
47	)
48
49	data_prep.make_tf_record()	×

angelolab / cell_classification / 6002459992

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous