Merge pull request #66 from ONSdigital/419-test-outliering-with-anon-…

…data "419-test-outliering-with-anon-data"
ONSdigital · Aug 2, 2024 · 39788bc · 39788bc
2 parents 5d69cfe + 00ebc36
commit 39788bc
Show file tree

Hide file tree

Showing 5 changed files with 6 additions and 6 deletions.
diff --git a/mbs_results/calculate_predicted_unit_value.py b/mbs_results/calculate_predicted_unit_value.py
@@ -28,7 +28,7 @@ def calculate_predicted_unit_value(
         A pandas DataFrame with a new column containing the predicted unit value.
     """
 
-    winsorised = (df[sampled] == 1) & (not df[nw_ag_flag] is True)
+    winsorised = (df[sampled] == 1) & (df[nw_ag_flag] == False)  # noqa: E712
     filtered_df = df.loc[winsorised]
 
     sum_weighted_target_values = (
@@ -40,7 +40,7 @@ def calculate_predicted_unit_value(
         lambda x: x * (sum_weighted_target_values / sum_weighted_auxiliary_values)
     )
 
-    non_winsorised = (df[sampled] == 0) | (df[nw_ag_flag] is True)
+    non_winsorised = (df[sampled] == 0) | (df[nw_ag_flag] == True)  # noqa: E712
     df["predicted_unit_value"] = df["predicted_unit_value"].mask(non_winsorised, np.nan)
 
     return df
diff --git a/mbs_results/calculate_ratio_estimation.py b/mbs_results/calculate_ratio_estimation.py
@@ -49,7 +49,7 @@ def calculate_ratio_estimation(
     )
     df = df.drop("flag_calculation", axis=1)
 
-    non_winsorised = (df[sampled] == 0) | (df[nw_ag_flag] is True)
+    non_winsorised = (df[sampled] == 0) | (df[nw_ag_flag] == True)  # noqa: E712
     df["ratio_estimation_treshold"] = df["ratio_estimation_treshold"].mask(
         non_winsorised, np.nan
     )

diff --git a/mbs_results/calculate_winsorised_weight.py b/mbs_results/calculate_winsorised_weight.py
@@ -67,7 +67,7 @@ def calculate_winsorised_weight(
 
     df = df.drop(["w", "new_target"], axis=1)
 
-    non_winsorised = (df[sampled] == 0) | (df[nw_ag_flag] is True)
+    non_winsorised = (df[sampled] == 0) | (df[nw_ag_flag] == True)  # noqa: E712
     df["outlier_weight"] = df["outlier_weight"].mask(non_winsorised, np.nan)
     df["new_target_variable"] = df["new_target_variable"].mask(non_winsorised, np.nan)
 

diff --git a/mbs_results/flag_for_winsorisation.py b/mbs_results/flag_for_winsorisation.py
@@ -26,7 +26,7 @@ def winsorisation_flag(df, a_weight, g_weight):
 
     df["flag_calculation"] = df[a_weight] * df[g_weight]
 
-    df["nw_ag_flag"] = df["flag_calculation"].apply(lambda x: True if x <= 1 else 0)
+    df["nw_ag_flag"] = df["flag_calculation"].apply(lambda x: True if x <= 1 else False)
 
     df = df.drop("flag_calculation", axis=1)
 

diff --git a/tests/test_flag_for_winsorisation.py b/tests/test_flag_for_winsorisation.py
@@ -28,4 +28,4 @@ def test_winsorisation_flag(self, winsorisation_flag_test_data):
             df=df_input, a_weight="a_weight", g_weight="g_weight"
         )
 
-        assert_frame_equal(df_output, df_expected_output, check_dtype=False)
+        assert_frame_equal(df_output, df_expected_output)