def test_modz_multiple_columns():
replicate_columns = ["Metadata_g", "Metadata_h"]
data_replicate_multi_df = data_replicate_df.assign(
Metadata_h=["c", "c", "c", "d", "d", "d"])
# The expected result is to completely remove influence of anticorrelated sample
consensus_df = modz(data_replicate_multi_df,
replicate_columns,
min_weight=0,
precision=precision)
expected_result = pd.DataFrame({
"Metadata_g": ["a", "b"],
"Metadata_h": ["c", "d"],
"Cells_x": [1.0, 4.0],
"Cytoplasm_y": [5.0, 2.0],
"Nuclei_z": [2.0, -0.5],
})
pd.testing.assert_frame_equal(expected_result.reset_index(),
consensus_df.reset_index())
# With the min_weight = 1, then modz is mean
consensus_df = modz(data_replicate_multi_df,
replicate_columns,
min_weight=1,
precision=precision)
expected_result = data_replicate_multi_df.groupby(
replicate_columns).mean().round(4)
pd.testing.assert_frame_equal(expected_result.reset_index(),
consensus_df,
check_less_precise=True)
def test_modz():
# The expected result is to completely remove influence of anticorrelated sample
consensus_df = modz(data_replicate_df,
replicate_columns,
min_weight=0,
precision=precision)
expected_result = pd.DataFrame(
{
"Cells_x": [1.0, 4.0],
"Cytoplasm_y": [5.0, 2.0],
"Nuclei_z": [2.0, -0.5]
},
index=["a", "b"],
)
expected_result.index.name = replicate_columns
pd.testing.assert_frame_equal(expected_result.reset_index(), consensus_df)
# With the min_weight = 1, then modz is mean
consensus_df = modz(data_replicate_df,
replicate_columns,
min_weight=1,
precision=precision)
expected_result = data_replicate_df.groupby(
replicate_columns).mean().round(4)
expected_result.index.name = replicate_columns
pd.testing.assert_frame_equal(expected_result.reset_index(),
consensus_df,
check_less_precise=True)
def test_modz_extraneous_column():
# The expected result is to completely remove influence of anticorrelated sample
data_replicate_new_col_df = data_replicate_df.assign(Metadata_h="c")
consensus_df = modz(data_replicate_new_col_df,
replicate_columns,
min_weight=0,
precision=precision)
expected_result = pd.DataFrame(
{
"Cells_x": [1.0, 4.0],
"Cytoplasm_y": [5.0, 2.0],
"Nuclei_z": [2.0, -0.5]
},
index=["a", "b"],
)
expected_result.index.name = replicate_columns
pd.testing.assert_frame_equal(expected_result.reset_index(), consensus_df)
def test_modz_unbalanced_sample_numbers():
# The expected result is to not freak out when only one sample exists for a piece of metadata
data_replicate_multi_df = data_replicate_df.assign(
Metadata_h=["c", "c", "c", "c", "c", "d"])
consensus_df = modz(
data_replicate_multi_df,
replicate_columns="Metadata_h",
min_weight=0,
precision=precision,
)
expected_result = pd.DataFrame(
{
"Metadata_h": ["c", "d"],
"Cells_x": [0.9999, 5.0],
"Cytoplasm_y": [5.9994, 1.0],
"Nuclei_z": [2.9997, 1],
}, )
pd.testing.assert_frame_equal(expected_result, consensus_df)
def test_modz_multiple_columns_feature_specify():
# Include replicate information
data_replicate_feature_df = pd.concat([
pd.DataFrame({
"g": "a",
"x": [1, 1, -1],
"y": [5, 5, -5],
"z": [2, 2, -2]
}),
pd.DataFrame({
"g": "b",
"x": [1, 3, 5],
"y": [8, 3, 1],
"z": [5, -2, 1]
}),
]).reset_index(drop=True)
data_replicate_feature_df.index = [
"sample_{}".format(x) for x in data_replicate_feature_df.index
]
# The expected result is to completely remove influence of anticorrelated sample
consensus_df = modz(
data_replicate_feature_df,
replicate_columns="g",
features=["x", "y", "z"],
min_weight=0,
precision=precision,
)
expected_result = pd.DataFrame(
{
"x": [1.0, 4.0],
"y": [5.0, 2.0],
"z": [2.0, -0.5]
}, index=["a", "b"])
expected_result.index.name = "g"
pd.testing.assert_frame_equal(expected_result.reset_index(), consensus_df)
def consensus(
profiles,
replicate_columns=["Metadata_Plate", "Metadata_Well"],
operation="median",
features="infer",
output_file="none",
compression_options=None,
float_format=None,
modz_args={"method": "spearman"},
):
"""Form level 5 consensus profile data.
:param profiles: A file or pandas DataFrame of profile data
:type profiles: str
:param replicate_columns: Metadata columns indicating which replicates to collapse, defaults to ["Metadata_Plate", "Metadata_Well"]
:type replicate_columns: list
:param operation: The method used to form consensus profiles, defaults to "median"
:type operation: str
:param features: The features to collapse, defaults to "infer"
:type features: str, list
:param output_file: If specified, the location to write the file, defaults to "none"
:type output_file: str
:param modz_args: Additional custom arguments passed as kwargs if operation="modz". See pycytominer.cyto_utils.modz for more details.
:type modz_args: dict
:param compression_options: the method to compress output data, defaults to None. See pycytominer.cyto_utils.output.py for options
:type compression_options: str
:param float_format: decimal precision to use in writing output file, defaults to None. For example, use "%.3g" for 3 decimal precision.
:Example:
import pandas as pd
from pycytominer import consensus
data_df = pd.concat(
[
pd.DataFrame(
{
"Metadata_Plate": "X",
"Metadata_Well": "a",
"Cells_x": [0.1, 0.3, 0.8],
"Nuclei_y": [0.5, 0.3, 0.1],
}
),
pd.DataFrame(
{
"Metadata_Plate": "X",
"Metadata_Well": "b",
"Cells_x": [0.4, 0.2, -0.5],
"Nuclei_y": [-0.8, 1.2, -0.5],
}
),
]
).reset_index(drop=True)
consensus_df = consensus(
profiles=data_df,
replicate_columns=["Metadata_Plate", "Metadata_Well"],
operation="median",
features="infer",
output_file="none",
)
"""
# Confirm that the operation is supported
check_consensus_operation(operation)
# Load Data
profiles = load_profiles(profiles)
if operation == "modz":
consensus_df = modz(population_df=profiles,
replicate_columns=replicate_columns,
features=features,
**modz_args)
else:
consensus_df = aggregate(
population_df=profiles,
strata=replicate_columns,
features=features,
operation=operation,
subset_data_df="none",
)
if output_file != "none":
output(
df=consensus_df,
output_filename=output_file,
compression_options=compression_options,
float_format=float_format,
)
else:
return consensus_df
