Skip to content

Config params model

cellcounter.utils.config_params_model.ConfigParamsModel

Bases: BaseModel

Pydantic model for registration parameters.

Source code in cellcounter/utils/config_params_model.py 
 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
class ConfigParamsModel(BaseModel):
    """
    Pydantic model for registration parameters.
    """

    # NOTE: can set extra as "forbid" to prevent extra keys
    model_config = ConfigDict(
        extra="ignore",
        # arbitrary_types_allowed=True,
        validate_default=True,
        use_enum_values=True,
    )

    # REFERENCE
    atlas_dir: str = ATLAS_DIR
    ref_version: str = RefVersions.AVERAGE_TEMPLATE_25.value
    annot_version: str = AnnotVersions.CCF_2016_25.value
    map_version: str = MapVersions.ABA_ANNOTATIONS.value
    # RAW
    zarr_chunksize: tuple[int, int, int] = PROC_CHUNKS
    # REGISTRATION
    ref_orient_ls: tuple[int, int, int] = (1, 2, 3)
    ref_z_trim: tuple[int | None, int | None, int | None] = (None, None, None)
    ref_y_trim: tuple[int | None, int | None, int | None] = (None, None, None)
    ref_x_trim: tuple[int | None, int | None, int | None] = (None, None, None)
    z_rough: int = 3
    y_rough: int = 6
    x_rough: int = 6
    z_fine: float = 1.0
    y_fine: float = 0.6
    x_fine: float = 0.6
    z_trim: tuple[int | None, int | None, int | None] = (None, None, None)
    y_trim: tuple[int | None, int | None, int | None] = (None, None, None)
    x_trim: tuple[int | None, int | None, int | None] = (None, None, None)
    lower_bound: tuple[int, int] = (100, 0)
    upper_bound: tuple[int, int] = (5000, 5000)
    # MASK
    mask_gaus_blur: int = 1
    mask_thresh: int = 300
    # CELL COUNT TUNING CROP
    tuning_z_trim: tuple[int | None, int | None, int | None] = (0, 100, None)
    tuning_y_trim: tuple[int | None, int | None, int | None] = (0, 2000, None)
    tuning_x_trim: tuple[int | None, int | None, int | None] = (0, 2000, None)
    # OVERLAP
    overlap_depth: int = DEPTH
    # CELL COUNTING
    tophat_sigma: int = 10
    dog_sigma1: int = 1
    dog_sigma2: int = 4
    large_gauss_sigma: int = 101
    threshd_value: int = 60
    min_threshd_size: int = 100
    max_threshd_size: int = 10000
    maxima_sigma: int = 10
    min_wshed_size: int = 1
    max_wshed_size: int = 1000
    # VISUAL CHECK
    heatmap_raw_radius: int = 5
    heatmap_trfm_radius: int = 3
    # COMBINE ARRAYS
    combine_cellc_z_trim: tuple[int | None, int | None, int | None] = (0, 10, None)
    combine_cellc_y_trim: tuple[int | None, int | None, int | None] = (None, None, None)
    combine_cellc_x_trim: tuple[int | None, int | None, int | None] = (None, None, None)

    @model_validator(mode="after")
    def _validate_trims(self):
        # Orient validation
        vect = np.array(self.ref_orient_ls)
        vect_abs = np.abs(vect)
        vect_abs_sorted = np.sort(vect_abs)
        assert np.all(vect_abs_sorted == np.array([1, 2, 3]))
        # TODO: Size validation
        # TODO: Trim validation
        return self

    @classmethod
    def read_fp(cls, fp: str):
        model = cls.model_validate(read_json(fp))
        return model

    def update(self, **kwargs):
        return self.model_validate(self.model_copy(update=kwargs))

    @classmethod
    def update_file(cls, fp: str, **kwargs):
        """
        Reads the json file in `fp`, updates the parameters with `kwargs`,
        writes the updated parameters back to `fp` (if there are any updates),
        and returns the model instance.
        """
        configs = cls.model_validate(read_json(fp))
        # Updating and saving if kwargs is not empty
        if kwargs != {}:
            configs = cls.model_validate(configs.model_copy(update=kwargs))
            write_json(fp, configs.model_dump())
        return configs

update_file(fp, **kwargs) classmethod

Reads the json file in fp, updates the parameters with kwargs, writes the updated parameters back to fp (if there are any updates), and returns the model instance.

Source code in cellcounter/utils/config_params_model.py 
113
114
115
116
117
118
119
120
121
122
123
124
125
@classmethod
def update_file(cls, fp: str, **kwargs):
    """
    Reads the json file in `fp`, updates the parameters with `kwargs`,
    writes the updated parameters back to `fp` (if there are any updates),
    and returns the model instance.
    """
    configs = cls.model_validate(read_json(fp))
    # Updating and saving if kwargs is not empty
    if kwargs != {}:
        configs = cls.model_validate(configs.model_copy(update=kwargs))
        write_json(fp, configs.model_dump())
    return configs