Descriptive

microdf/generic.py

@@ -1,4 +1,4 @@
-from typing import Callable, Union
+from typing import Any, Callable, Dict, Union
 from functools import wraps
 import warnings
 import copy
@@ -7,14 +7,32 @@
 
 
 class MicroSeries(pd.Series):
-    def __init__(self, *args, weights: np.array = None, **kwargs):
+    codebook = {}
+    description = "No description provided"
+
+    def __init__(
+        self,
+        *args,
+        weights: np.array = None,
+        codebook: dict = None,
+        description: str = None,
+        **kwargs
+    ):
         """A Series-inheriting class for weighted microdata.
         Weights can be provided at initialisation, or using set_weights.
 
         :param weights: Array of weights.
         :type weights: np.array
+
+        :param codebook: Dictionary to decode categorical codes.
+        :type codebook: dict
+
+        :param description: A description of this series.
+        :type description: str
         """
         super().__init__(*args, **kwargs)
+        self.codebook = codebook or self.codebook
+        self.description = description or self.description
         self.set_weights(weights)
 
     def weighted_function(fn: Callable) -> Callable:
@@ -48,6 +66,13 @@ def set_weights(self, weights: np.array) -> None:
         else:
             self.weights = pd.Series(weights, dtype=float)
 
+    @vector_function
+    def decode(self):
+        if self.codebook == {}:
+            return self
+        result = MicroSeries(self.map(self.codebook), weights=self.weights)
+        return MicroSeries(result, weights=self.weights)
+
     @vector_function
     def weight(self) -> pd.Series:
         """Calculates the weighted value of the MicroSeries.
@@ -484,19 +509,43 @@ def fn(*args, **kwargs):
 
 
 class MicroDataFrame(pd.DataFrame):
-    def __init__(self, *args, weights=None, **kwargs):
+    description = "No description provided."
+    codebook = {}
+
+    def __init__(
+        self,
+        *args,
+        weights=None,
+        codebook: Dict[str, Dict[Any, Any]] = None,
+        description: str = None,
+        **kwargs
+    ):
         """A DataFrame-inheriting class for weighted microdata.
         Weights can be provided at initialisation, or using set_weights or
         set_weight_col.
 
         :param weights: Array of weights.
         :type weights: np.array
+
+
+        :param codebook: A dict dicts for categorical columns.
+        :type codebook: Dict[str, Dict[Any, Any]]
+
+        :param description: A description of this dataframe.
+        :type description: str
         """
         super().__init__(*args, **kwargs)
         self.weights = None
         self.set_weights(weights)
         self._link_all_weights()
         self.override_df_functions()
+        if codebook is not None:
+            self.set_codebook(codebook)
+        self.description = description or self.description
+
+    def set_codebook(self, codebook: dict):
+        for col in codebook:
+            self[col].codebook = codebook[col]
 
     def override_df_functions(self):
         for name in MicroSeries.FUNCTIONS:

microdf/tests/test_generic.py

@@ -200,3 +200,10 @@ def test_subset():
     df_no_z_diff_weights = df_no_z.copy()
     df_no_z_diff_weights.weights += 1
     assert not df[["x", "y"]].equals(df_no_z_diff_weights)
+
+
+def test_decode():
+    s = MicroSeries([1, 2, 2], codebook={1: "Male", 2: "Female"})
+    assert pd.Series(s.decode()).equals(
+        pd.Series(["Male", "Female", "Female"])
+    )