Ignore notebooks.

Author: MarenBermudezBoeckle

.gitignore

@@ -43,3 +43,6 @@ docs_template/scripts/latex/*.png
 
 # data
 *.sav
+
+# notebooks
+work_maren/

README.md

@@ -71,7 +71,7 @@ $ pytest
 ```
 
 It is important to run `pytask` and then `pytest`, such that the tests for the plots
-work.
+work. (It is normal that tests take up to 3 minutes to run)
 
 If you encounter any issues, refer to the sections **"Preparing your system"** and
 **"How to get started on a second machine"** in this

inst/WORDLIST

@@ -1,4 +1,5 @@
 "base-usuario-20-enusc-2023.sav"
+https://www.dropbox.com/scl/fo/0oe4pz0epdx9az31s43rt/ACFL6YD4UZk6tIym7caipMU?rlkey=ds6wtw5ehatssgrkuqq29coeu&st=yw25julf&dl=0
 fo
 aa
 aA

src/project_mbb/analysis/model.py

@@ -27,7 +27,7 @@ def regression_perception_info(enusc_clean):
 def _set_category_values(enusc_clean):
     """Encodes categorical values for perception and information source."""
     _fail_if_invalid_categories_perception(enusc_clean, perception_change_mapping)
-    _fail_if_invalid_categories_source(enusc_clean, info_sources_mapping)
+    _fail_if_invalid_categories_source(enusc_clean)
 
     enusc_model_pre = pd.DataFrame()
     enusc_model_pre["crime_increase_perception_commune"] = enusc_clean[

src/project_mbb/data_management/clean_enusc.py

@@ -28,7 +28,7 @@ def clean_enusc(raw_enusc):
     """
     enusc_filtered = _filter_enusc(raw_enusc, relevant_var)
     enusc_renamed = _rename_enusc(enusc_filtered, rename_mapping)
-    enusc_mapped = _map_categories(enusc_renamed)
+    enusc_mapped = _map_categories(enusc_renamed, map_category)
     enusc_filled = _fill_missing(enusc_mapped)
     enusc_dtypes = _set_data_types_not_mapped_var(enusc_filled)
     return enusc_dtypes

src/project_mbb/final/task_plot.py

@@ -23,4 +23,4 @@ def task_plot_perception(
         None (plots saved to path)
     """
     enusc_clean = pd.read_pickle(enusc_clean)
-    plot_crime_perception(enusc_clean)
+    plot_crime_perception(enusc_clean, products)

tests/data_management/test_data_mgt_enusc.py

@@ -13,6 +13,7 @@
     categories,
     floats,
     integers,
+    map_category,
     relevant_var,
     rename_mapping,
     security_levels_mapping,
@@ -77,7 +78,7 @@ def test_rename_enusc(enusc_raw):
 def test_value_presence(enusc_raw_short, column, expected_value):
     enusc_filtered = _filter_enusc(enusc_raw_short, relevant_var)
     enusc_renamed = _rename_enusc(enusc_filtered, rename_mapping)
-    enusc_category = _map_categories(enusc_renamed)
+    enusc_category = _map_categories(enusc_renamed, map_category)
 
     assert (
         expected_value in enusc_category[column].values
@@ -91,7 +92,7 @@ def test_value_presence(enusc_raw_short, column, expected_value):
 def test_column_is_categorical(enusc_raw_short, column):
     enusc_filtered = _filter_enusc(enusc_raw_short, relevant_var)
     enusc_renamed = _rename_enusc(enusc_filtered, rename_mapping)
-    enusc_category = _map_categories(enusc_renamed)
+    enusc_category = _map_categories(enusc_renamed, map_category)
 
     assert isinstance(
         enusc_category[column].dtype, pd.CategoricalDtype
@@ -109,7 +110,7 @@ def test_value_presence_continued(enusc_raw_short, column, values_dict):
     errors = []
     enusc_filtered = _filter_enusc(enusc_raw_short, relevant_var)
     enusc_renamed = _rename_enusc(enusc_filtered, rename_mapping)
-    enusc_category = _map_categories(enusc_renamed)
+    enusc_category = _map_categories(enusc_renamed, map_category)
 
     for value in enusc_category[column]:
         if pd.isna(value):  # Skip missing values
@@ -125,14 +126,14 @@ def test_value_presence_continued(enusc_raw_short, column, values_dict):
 def test_fail_age_not_categorical(enusc_raw_short):
     enusc_filtered = _filter_enusc(enusc_raw_short, relevant_var)
     enusc_renamed = _rename_enusc(enusc_filtered, rename_mapping)
-    enusc_category = _map_categories(enusc_renamed)
+    enusc_category = _map_categories(enusc_renamed, map_category)
     assert isinstance(enusc_category["age"].dtype, pd.CategoricalDtype)
 
 
 def test_amount_of_missing(enusc_raw_short):
     enusc_filtered = _filter_enusc(enusc_raw_short, relevant_var)
     enusc_renamed = _rename_enusc(enusc_filtered, rename_mapping)
-    enusc_category = _map_categories(enusc_renamed)
+    enusc_category = _map_categories(enusc_renamed, map_category)
     enusc_filled = _fill_missing(enusc_category)
 
     errors = []
@@ -168,7 +169,7 @@ def test_set_data_types_not_mapped_var(enusc_raw_short, column, expected_dtype):
     errors = []
     enusc_filtered = _filter_enusc(enusc_raw_short, relevant_var)
     enusc_renamed = _rename_enusc(enusc_filtered, rename_mapping)
-    enusc_category = _map_categories(enusc_renamed)
+    enusc_category = _map_categories(enusc_renamed, map_category)
     enusc_filled = _fill_missing(enusc_category)
     enusc_dtypes = _set_data_types_not_mapped_var(enusc_filled)
 
@@ -202,7 +203,7 @@ def test_fail_set_data_types_not_mapped_var(
     errors = []
     enusc_filtered = _filter_enusc(enusc_raw_short, relevant_var)
     enusc_renamed = _rename_enusc(enusc_filtered, rename_mapping)
-    enusc_category = _map_categories(enusc_renamed)
+    enusc_category = _map_categories(enusc_renamed, map_category)
     enusc_filled = _fill_missing(enusc_category)
     enusc_dtypes = _set_data_types_not_mapped_var(enusc_filled)