WIP

src/xtgeo/well/_welldata.py

@@ -8,15 +8,17 @@
 4      463256.916  5930542.302   -46.1533     2.0000     NaN        NaN     NaN ...
               ...          ...        ...        ...     ...        ...     ...
 
-Where each log beside the 3 first has a wlogtypes dictoniary, telling if the logs are
+Where each log has a wlogtypes dictionary, telling if the logs are
 treated as discrete (DISC) or continuous (CONT). In addition there is a wlogrecords
 dict, storing the unit for continuous logs (defaulted to None) or a dictionary
 of codes if the log in DISC type.
 
-The purpose here is to automate; if a column is added to the dataframe, then the
-class methods here will try to guess the wlogtype and wlogtype, and add those; similarly
-of a column is removed, the corresponding entries in wlogtypes and wlogrecords will be
-deleted.
+The 3 first columsn are the coordinates.
+
+The purpose here is to automate and improve; if a column is added to the dataframe, then
+the class methods here will try to guess the wlogtype and wlogtype, and add those;
+similarly of a column is removed, the corresponding entries in wlogtypes and wlogrecords
+will be deleted.
 """
 from dataclasses import dataclass, field
 from enum import Enum, EnumMeta, unique
@@ -25,7 +27,7 @@ class methods here will try to guess the wlogtype and wlogtype, and add those; s
 
 
 class _LogTypeMeta(EnumMeta):
-    """For 'in' method, cf https://stackoverflow.com/questions/43634618"""
+    """For enabling 'in' method, cf https://stackoverflow.com/questions/43634618"""
 
     def __contains__(cls, item):
         try:
@@ -252,3 +254,21 @@ def set_wlogrecord(self, name: str, record: dict) -> None:
             raise ValueError("Something went wrong when setting logrecord.")
 
         self.ensure_consistency()
+
+    def get_dataframe_copy(self, infer_dtype: bool = False):
+        """Get a deep copy of the dataframe, with options.
+
+        If infer_dtype is True, then DISC columns will be of "int32" type
+        """
+
+        if infer_dtype:
+            dfr = self.data.copy()
+
+            for name, wtype in self.wlogtypes.items():
+                if "DISC" in wtype:
+                    dfr[name] = dfr[name].astype("int32")
+
+            return dfr
+
+        else:
+            return self.data.copy()

tests/test_well/test_welldata_class.py

@@ -153,3 +153,38 @@ def test_logtype_class():
 
     with pytest.raises(ValueError, match="is not a valid"):
         _LogType("FOO")
+
+
+def test_welldata_dataframe_copy(generate_data: pd.DataFrame):
+    """Test get dataframe method, with option"""
+
+    instance = _WellData(generate_data)
+
+    copy = instance.get_dataframe_copy()
+    col = list(copy)
+
+    dtypes = [str(entry) for entry in copy[col].dtypes]
+    assert dtypes == [
+        "float64",
+        "float64",
+        "float64",
+        "float32",
+        "float32",
+        "float32",
+        "float32",
+    ]
+
+    copy = instance.get_dataframe_copy(infer_dtype=True)
+
+    dtypes = [str(entry) for entry in copy[col].dtypes]
+    assert dtypes == [
+        "float64",
+        "float64",
+        "float64",
+        "float32",
+        "float32",
+        "int32",
+        "int32",
+    ]
+
+    instance.data =