add types in frames

Author: JohnMount

coverage.txt

@@ -2,21 +2,22 @@
 platform darwin -- Python 3.9.12, pytest-7.1.1, pluggy-1.0.0
 rootdir: /Users/johnmount/Documents/work/wvpy/pkg
 plugins: anyio-3.5.0, cov-3.0.0
-collected 18 items
+collected 19 items
 
 tests/test_cross_plan1.py .                                              [  5%]
-tests/test_cross_predict.py ..                                           [ 16%]
-tests/test_deviance_calc.py .                                            [ 22%]
-tests/test_eval_fn_pre_row.py .                                          [ 27%]
-tests/test_match_auc.py .                                                [ 33%]
-tests/test_nb_fns.py ...                                                 [ 50%]
-tests/test_onehot.py ..                                                  [ 61%]
-tests/test_perm_score_vars.py .                                          [ 66%]
-tests/test_plots.py .                                                    [ 72%]
-tests/test_se.py .                                                       [ 77%]
-tests/test_search_grid.py ..                                             [ 88%]
-tests/test_stats1.py .                                                   [ 94%]
-tests/test_threshold_stats.py .                                          [100%]
+tests/test_cross_predict.py ..                                           [ 15%]
+tests/test_deviance_calc.py .                                            [ 21%]
+tests/test_eval_fn_pre_row.py .                                          [ 26%]
+tests/test_match_auc.py .                                                [ 31%]
+tests/test_nb_fns.py ...                                                 [ 47%]
+tests/test_onehot.py ..                                                  [ 57%]
+tests/test_perm_score_vars.py .                                          [ 63%]
+tests/test_plots.py .                                                    [ 68%]
+tests/test_se.py .                                                       [ 73%]
+tests/test_search_grid.py ..                                             [ 84%]
+tests/test_stats1.py .                                                   [ 89%]
+tests/test_threshold_stats.py .                                          [ 94%]
+tests/test_typs_in_frame.py .                                            [100%]
 
 =============================== warnings summary ===============================
 ../../../../opt/anaconda3/envs/research_env/lib/python3.9/site-packages/seaborn/rcmod.py:82
@@ -36,8 +37,8 @@ wvpy/__init__.py              3      0   100%
 wvpy/jtools.py              136     34    75%
 wvpy/pysheet.py              33     33     0%
 wvpy/render_workbook.py      29     29     0%
-wvpy/util.py                316      7    98%
+wvpy/util.py                321      7    98%
 ---------------------------------------------
-TOTAL                       517    103    80%
+TOTAL                       522    103    80%
 
-======================= 18 passed, 2 warnings in 15.55s ========================
+======================= 19 passed, 2 warnings in 17.22s ========================

pkg/build/lib/wvpy/util.py

@@ -2,7 +2,7 @@
 Utility functions for teaching data science.
 """
 
-from typing import Iterable, List, Tuple
+from typing import Dict, Iterable, List, Tuple
 
 import re
 import os
@@ -20,6 +20,25 @@
 from data_algebra.cdata import RecordMap, RecordSpecification
 
 
+def types_in_frame(d: pandas.DataFrame) -> Dict[str, List[type]]:
+    """
+    Report what type as seen as values in a Pandas data frame.
+    
+    :param d: Pandas data frame to inspect, not altered.
+    :return: dictionary mapping column names to order lists of types found in column.
+    """
+    assert isinstance(d, pandas.DataFrame)
+    type_dict_map = {
+        col_name: {str(type(v)): type(v) for v in d[col_name]}
+            for col_name in d.columns
+    }
+    type_dict = {
+        col_name: [type_set[k] for k in sorted(list(type_set.keys()))]
+            for col_name, type_set in type_dict_map.items()
+    }
+    return type_dict
+
+
 # noinspection PyPep8Naming
 def cross_predict_model(
     fitter, X: pandas.DataFrame, y: pandas.Series, plan: List

pkg/dist/wvpy-0.3.0-py3-none-any.whl

@@ -0,0 +1,19 @@
+
+import pandas as pd
+from wvpy.util import types_in_frame
+
+
+def test_types_in_frame():
+    d = pd.DataFrame({
+        'x': [1, 2],
+        'y': ['a', 'b'],
+        'z': ['a', 1],
+    })
+    found = types_in_frame(d)
+    expect = {
+        'x': [int],
+        'y': [str],
+        'z': [int, str],
+    }
+    assert found == expect
+

pkg/dist/wvpy-0.3.0.tar.gz

@@ -2,7 +2,7 @@
 Utility functions for teaching data science.
 """
 
-from typing import Iterable, List, Tuple
+from typing import Dict, Iterable, List, Tuple
 
 import re
 import os
@@ -20,6 +20,25 @@
 from data_algebra.cdata import RecordMap, RecordSpecification
 
 
+def types_in_frame(d: pandas.DataFrame) -> Dict[str, List[type]]:
+    """
+    Report what type as seen as values in a Pandas data frame.
+    
+    :param d: Pandas data frame to inspect, not altered.
+    :return: dictionary mapping column names to order lists of types found in column.
+    """
+    assert isinstance(d, pandas.DataFrame)
+    type_dict_map = {
+        col_name: {str(type(v)): type(v) for v in d[col_name]}
+            for col_name in d.columns
+    }
+    type_dict = {
+        col_name: [type_set[k] for k in sorted(list(type_set.keys()))]
+            for col_name, type_set in type_dict_map.items()
+    }
+    return type_dict
+
+
 # noinspection PyPep8Naming
 def cross_predict_model(
     fitter, X: pandas.DataFrame, y: pandas.Series, plan: List