Merge branch 'master' into feature/setup-pyproject-toml

pycytominer/cyto_utils/features.py

@@ -152,8 +152,11 @@ def drop_outlier_features(
         DataFrame that includes metadata and observation features.
     features : list of str or str, default "infer"
         Features present in the population dataframe. If "infer", then assume Cell Painting features are those that start with "Cells_", "Nuclei_", or "Cytoplasm_"
-    samples : list of str or str, default "all"
-        Samples to perform the operation on
+    samples : str, default "all"
+        List of samples to perform operation on. The function uses a pd.DataFrame.query()
+        function, so you should  structure samples in this fashion. An example is
+        "Metadata_treatment == 'control'" (include all quotes).
+        If "all", use all samples to calculate.
     outlier_cutoff : int or float, default 500
     see https://github.com/cytomining/pycytominer/issues/237 for details.
         Threshold to remove features if absolute values is greater
@@ -166,7 +169,7 @@ def drop_outlier_features(
 
     # Subset dataframe
     if samples != "all":
-        population_df = population_df.loc[samples, :]
+        population_df.query(samples, inplace=True)
 
     if features == "infer":
         features = infer_cp_features(population_df)

pycytominer/operations/correlation_threshold.py

@@ -25,8 +25,11 @@ def correlation_threshold(
          List of features present in the population dataframe [default: "infer"]
          if "infer", then assume cell painting features are those that start with
          "Cells_", "Nuclei_", or "Cytoplasm_".
-    samples : list or str, default "all"
-        List of samples to perform operation on. If "all", use all samples to calculate.
+    samples : str, default "all"
+        List of samples to perform operation on. The function uses a pd.DataFrame.query()
+        function, so you should  structure samples in this fashion. An example is
+        "Metadata_treatment == 'control'" (include all quotes).
+        If "all", use all samples to calculate.
     threshold - float, default 0.9
         Must be between (0, 1) to exclude features
     method - str, default "pearson"
@@ -45,7 +48,7 @@ def correlation_threshold(
 
     # Subset dataframe and calculate correlation matrix across subset features
     if samples != "all":
-        population_df = population_df.loc[samples, :]
+        population_df.query(samples, inplace=True)
 
     if features == "infer":
         features = infer_cp_features(population_df)

pycytominer/operations/get_na_columns.py

@@ -18,8 +18,11 @@ def get_na_columns(population_df, features="infer", samples="all", cutoff=0.05):
          List of features present in the population dataframe [default: "infer"]
          if "infer", then assume cell painting features are those that start with
          "Cells_", "Nuclei_", or "Cytoplasm_".
-    samples : list or str, default "all"
-        List of samples to perform operation on. If "all", use all samples to calculate.
+    samples : str, default "all"
+        List of samples to perform operation on. The function uses a pd.DataFrame.query()
+        function, so you should  structure samples in this fashion. An example is
+        "Metadata_treatment == 'control'" (include all quotes).
+        If "all", use all samples to calculate.
     cutoff : float
         Exclude features that have a certain proportion of missingness
 
@@ -30,7 +33,7 @@ def get_na_columns(population_df, features="infer", samples="all", cutoff=0.05):
     """
 
     if samples != "all":
-        population_df = population_df.loc[samples, :]
+        population_df.query(samples, inplace=True)
 
     if features == "infer":
         features = infer_cp_features(population_df)

pycytominer/operations/noise_removal.py

@@ -27,8 +27,11 @@ def noise_removal(
          List of features present in the population dataframe [default: "infer"]
          if "infer", then assume cell painting features are those that start with
          "Cells_", "Nuclei_", or "Cytoplasm_".
-    samples : list or str, default "all"
-        List of samples to perform operation on. If "all", use all samples to calculate.
+    samples : str, default "all"
+        List of samples to perform operation on. The function uses a pd.DataFrame.query()
+        function, so you should  structure samples in this fashion. An example is
+        "Metadata_treatment == 'control'" (include all quotes).
+        If "all", use all samples to calculate.
     noise_removal_stdev_cutoff : float
         Maximum mean stdev value for a feature to be kept, with features grouped according to the perturbations in
         noise_removal_perturbation_groups.
@@ -41,7 +44,7 @@ def noise_removal(
     """
     # Subset dataframe
     if samples != "all":
-        population_df = population_df.loc[samples, :]
+        population_df.query(samples, inplace=True)
 
     if features == "infer":
         features = infer_cp_features(population_df)

pycytominer/operations/variance_threshold.py

@@ -21,8 +21,11 @@ def variance_threshold(
          List of features present in the population dataframe [default: "infer"]
          if "infer", then assume cell painting features are those that start with
          "Cells_", "Nuclei_", or "Cytoplasm_".
-    samples : list or str, default "all"
-        List of samples to perform operation on. If "all", use all samples to calculate.
+    samples : str, default "all"
+        List of samples to perform operation on. The function uses a pd.DataFrame.query()
+        function, so you should  structure samples in this fashion. An example is
+        "Metadata_treatment == 'control'" (include all quotes).
+        If "all", use all samples to calculate.
     freq_cut : float, default 0.05
         Ratio (2nd most common feature val / most common). Must range between 0 and 1.
         Remove features lower than freq_cut. A low freq_cut will remove features
@@ -45,7 +48,7 @@ def variance_threshold(
 
     # Subset dataframe
     if samples != "all":
-        population_df = population_df.loc[samples, :]
+        population_df.query(samples, inplace=True)
 
     if features == "infer":
         features = infer_cp_features(population_df)

tests/test_cyto_utils/test_feature_drop_outlier.py

@@ -20,6 +20,8 @@
             "control",
             "control",
         ],
+        "Metadata_test_drop_me": ["no", "no", "no", "no", "yes", "no", "yes", "yes"],
+        "Metadata_test_drop_me_2": ["no", "no", "no", "no", "yes", "yes", "yes", "yes"],
         "Cells_x": [1, 2, -8, 2, 5, 5, 5, -1],
         "Cytoplasm_y": [3, -1, 7, 4, 5, -9, 6, 1],
         "Nuclei_z": [-1, 8, 2, 5, -6, 20, 2, -2],
@@ -41,11 +43,15 @@ def test_outlier_15_cutoff():
 
 
 def test_outlier_samples_15():
-    result = drop_outlier_features(data_df, samples=[0, 1, 2, 3, 5], outlier_cutoff=15)
+    result = drop_outlier_features(
+        data_df, samples="Metadata_test_drop_me == 'no'", outlier_cutoff=15
+    )
     expected_result = ["Cells_zz", "Nuclei_z"]
     assert sorted(result) == sorted(expected_result)
 
-    result = drop_outlier_features(data_df, samples=[0, 1, 2, 3], outlier_cutoff=15)
+    result = drop_outlier_features(
+        data_df, samples="Metadata_test_drop_me_2 == 'no'", outlier_cutoff=15
+    )
     expected_result = ["Cells_zz"]
     assert result == expected_result
 

tests/test_feature_select.py

@@ -87,6 +87,7 @@ def test_feature_select_noise_removal():
     result1 = feature_select(
         profiles=data_df,
         features=data_df.columns.tolist(),
+        samples="all",
         operation="noise_removal",
         noise_removal_perturb_groups=data_df_groups,
         noise_removal_stdev_cutoff=2.5,
@@ -105,18 +106,22 @@ def test_feature_select_noise_removal():
         noise_removal_perturb_groups=data_df_groups,
         noise_removal_stdev_cutoff=3.5,
     )
+
     expected_result1 = data_df[["x", "y"]]
     expected_result2 = data_df[[]]
     expected_result3 = data_df[["x", "y", "z", "zz"]]
+
     pd.testing.assert_frame_equal(result1, expected_result1)
     pd.testing.assert_frame_equal(result2, expected_result2)
     pd.testing.assert_frame_equal(result3, expected_result3)
 
     # Test on data_unique_test_df, which has 100 rows
     data_unique_test_df_groups = []
+
     # Create a 100 element list containing 10 replicates of 10 perturbations
     for elem in ["a", "b", "c", "d", "e", "f", "g", "h", "i", "j"]:
         data_unique_test_df_groups.append([elem] * 10)
+
     # Unstack so it's just a single list
     data_unique_test_df_groups = [
         item for sublist in data_unique_test_df_groups for item in sublist
@@ -136,8 +141,10 @@ def test_feature_select_noise_removal():
         noise_removal_perturb_groups=data_unique_test_df_groups,
         noise_removal_stdev_cutoff=500,
     )
+
     expected_result4 = data_unique_test_df[["a", "b"]]
     expected_result5 = data_unique_test_df[["a", "b", "c", "d"]]
+
     pd.testing.assert_frame_equal(result4, expected_result4)
     pd.testing.assert_frame_equal(result5, expected_result5)
 
@@ -158,13 +165,16 @@ def test_feature_select_noise_removal():
         noise_removal_perturb_groups="perturb_group",
         noise_removal_stdev_cutoff=500,
     )
+
     expected_result4b = data_unique_test_df2[["a", "b", "perturb_group"]]
     expected_result5b = data_unique_test_df2[["a", "b", "c", "d", "perturb_group"]]
+
     pd.testing.assert_frame_equal(result4b, expected_result4b)
     pd.testing.assert_frame_equal(result5b, expected_result5b)
 
     # Test assertion errors for the user inputting the perturbation groupings
     bad_perturb_list = ["a", "a", "b", "b", "a", "a", "b"]
+
     with pytest.raises(
         AssertionError
     ):  # When the inputted perturb list doesn't match the length of the data
@@ -198,6 +208,22 @@ def test_feature_select_noise_removal():
             noise_removal_stdev_cutoff=2.5,
         )
 
+    with pytest.raises(
+        AssertionError
+    ):  # When the perturbation group doesn't match b/c samples argument used
+        # Add metadata_sample column
+        data_sample_id_df = data_df.assign(
+            Metadata_sample=[f"sample_{x}" for x in range(0, data_df.shape[0])]
+        )
+        feature_select(
+            profiles=data_sample_id_df,
+            features=data_df.columns.tolist(),
+            samples="Metadata_sample != 'sample_1'",
+            operation="noise_removal",
+            noise_removal_perturb_groups=data_df_groups,
+            noise_removal_stdev_cutoff=2.5,
+        )
+
 
 def test_feature_select_get_na_columns():
     """

tests/test_operations/test_correlation_threshold.py

@@ -12,7 +12,6 @@
     }
 ).reset_index(drop=True)
 
-
 data_uncorrelated_df = pd.DataFrame(
     {
         "x": [2, 2, 2, 5, 2, 1],
@@ -62,14 +61,17 @@ def test_correlation_threshold_uncorrelated():
 
 
 def test_correlation_threshold_samples():
+    # Add metadata_sample column
+    data_sample_id_df = data_df.assign(
+        Metadata_sample=[f"sample_{x}" for x in range(0, data_df.shape[0])]
+    )
     correlation_threshold_result = correlation_threshold(
-        population_df=data_df,
+        population_df=data_sample_id_df,
         features=data_df.columns.tolist(),
-        samples=[0, 1, 3, 4, 5],
+        samples="Metadata_sample != 'sample_2'",
         threshold=0.9,
         method="pearson",
     )
-
     expected_result = ["y"]
 
     assert correlation_threshold_result == expected_result

tests/test_operations/test_get_na_columns.py

@@ -45,17 +45,21 @@ def test_get_na_columns_sample():
     """
     Testing get_na_columns pycyominer function with samples option
     """
+    data_sample_id_df = data_df.assign(
+        Metadata_sample=[f"sample_{x}" for x in range(0, data_df.shape[0])]
+    )
     get_na_columns_result = get_na_columns(
-        population_df=data_df,
-        samples=[1, 2, 3, 4, 5],
+        population_df=data_sample_id_df,
+        samples="Metadata_sample != 'sample_0'",
         features=["x", "y", "zz"],
         cutoff=0.4,
     )
+
     assert len(get_na_columns_result) == 0
 
     get_na_columns_result = get_na_columns(
-        population_df=data_df,
-        samples=[1, 2, 3, 4, 5],
+        population_df=data_sample_id_df,
+        samples="Metadata_sample != 'sample_0'",
         features=["x", "y", "zz"],
         cutoff=0.1,
     )

tests/test_operations/test_variance_threshold.py

@@ -121,3 +121,30 @@ def test_variance_threshold_featureinfer():
     expected_result = ["Cells_a"]
 
     assert excluded_features == expected_result
+
+
+def test_variance_threshold_samples():
+    unique_cut = 0.01
+    excluded_features = variance_threshold(
+        population_df=data_unique_test_df,
+        features=data_unique_test_df.columns.tolist(),
+        samples="all",
+        unique_cut=unique_cut,
+    )
+    expected_result = ["a"]
+
+    assert sorted(excluded_features) == sorted(expected_result)
+
+    # Add metadata_sample column
+    data_sample_id_df = data_df.assign(
+        Metadata_sample=[f"sample_{x}" for x in range(0, data_df.shape[0])]
+    )
+
+    excluded_features = variance_threshold(
+        population_df=data_sample_id_df,
+        features=data_sample_id_df.columns.tolist(),
+        samples="Metadata_sample != 'sample_5'",
+        unique_cut=unique_cut,
+    )
+    expected_result = ["a", "b"]
+    assert sorted(excluded_features) == sorted(expected_result)