hover config usage: hover.config -> hover.<module>.<module_config/loc…

…al_config> -> other modules

hover/__init__.py

@@ -1,124 +1,130 @@
 """
 Module root where constants get configured.
 """
-import re
+from .config_constants import (
+    ConfigSection,
+    ConfigKey,
+    Validator,
+    Preprocessor,
+)
 from flexmod import AutolockedConfigValue, Config, ConfigIndex
 from bokeh.palettes import Turbo256
 
+
 config = ConfigIndex(
     [
         Config(
-            "io",
+            ConfigSection.IO,
             [
                 AutolockedConfigValue(
-                    "data_save_dir",
+                    ConfigKey.DATA_SAVE_DIR,
                     "The directory path for saving labeled data.",
                     ".",
-                    validation=lambda x: isinstance(x, str),
+                    validation=Validator.is_str,
                 ),
             ],
         ),
         Config(
             "visual",
             [
                 AutolockedConfigValue(
-                    "abstain_hexcolor",
+                    ConfigKey.ABSTAIN_HEXCOLOR,
                     "Hex code of RGB color.",
                     "#dcdcdc",
-                    validation=lambda x: bool(re.match(r"^\#[0-9a-fA-F]{6}$", x)),
+                    validation=Validator.is_hex_color,
                 ),
                 AutolockedConfigValue(
-                    "bokeh_palette",
+                    ConfigKey.BOKEH_PALETTE,
                     "The bokeh color palette to use for plotting. This should be a list of hex color codes.",
                     Turbo256,
-                    validation=lambda x: hasattr(x, "__iter__"),
+                    validation=Validator.is_iterable,
                 ),
                 AutolockedConfigValue(
-                    "bokeh_palette_usage",
+                    ConfigKey.BOKEH_PALETTE_USAGE,
                     "Specify how colors from the palette should be chosen when there are fewer categories than colors. This needs to be 'iterate' or 'linspace'",
                     "linspace",
-                    validation=lambda x: x in ["iterate", "linspace"],
+                    validation=Validator.is_supported_traversal_mode,
                 ),
                 AutolockedConfigValue(
-                    "table_img_style",
+                    ConfigKey.TABLE_IMG_STYLE,
                     "HTML style of images shown in selection tables.",
                     "max-height: 100%; max-width: 100%; object-fit: contain",
-                    preprocessor=lambda x: re.sub(r"(^[\'\"]|[\'\"]$)", "", x),
+                    preprocessor=Preprocessor.remove_quote_at_ends,
                 ),
                 AutolockedConfigValue(
-                    "tooltip_img_style",
+                    ConfigKey.TOOLTIP_IMG_STYLE,
                     "HTML style of images shown in mouse-over-data-point tooltips.",
                     "float: left; margin: 2px 2px 2px 2px; width: 60px; height: 60px;",
-                    preprocessor=lambda x: re.sub(r"(^[\'\"]|[\'\"]$)", "", x),
+                    preprocessor=Preprocessor.remove_quote_at_ends,
                 ),
             ],
         ),
         Config(
-            "data.embedding",
+            ConfigSection.DATA_EMBEDDING,
             [
                 AutolockedConfigValue(
-                    "default_reduction_method",
+                    ConfigKey.DEFAULT_REDUCTION_METHOD,
                     "Default method for dimensionality reduction. Currently either 'umap' or 'ivis'.",
                     "umap",
-                    validation=lambda x: x in ["umap", "ivis"],
+                    validation=Validator.is_supported_dimensionality_reduction,
                 ),
             ],
         ),
         Config(
-            "data.columns",
+            ConfigSection.DATA_COLUMNS,
             [
                 AutolockedConfigValue(
-                    "encoded_label_key",
+                    ConfigKey.ENCODED_LABEL_KEY,
                     "The column name for the encoded label.",
                     "label_encoded",
-                    validation=lambda x: isinstance(x, str),
+                    validation=Validator.is_str,
                 ),
                 AutolockedConfigValue(
-                    "dataset_subset_field",
+                    ConfigKey.DATASET_SUBSET_FIELD,
                     "The column name for dataset subsets.",
                     "SUBSET",
-                    validation=lambda x: isinstance(x, str),
+                    validation=Validator.is_str,
                 ),
                 AutolockedConfigValue(
-                    "embedding_field_prefix",
+                    ConfigKey.EMBEDDING_FIELD_PREFIX,
                     "The prefix of column names for embedding coordinates.",
                     "embed_",
-                    validation=lambda x: isinstance(x, str),
+                    validation=Validator.is_str,
                 ),
                 AutolockedConfigValue(
-                    "source_color_field",
+                    ConfigKey.SOURCE_COLOR_FIELD,
                     "The column name for plotted data point color.",
                     "__COLOR__",
-                    validation=lambda x: isinstance(x, str),
+                    validation=Validator.is_str,
                 ),
                 AutolockedConfigValue(
-                    "source_alpha_field",
+                    ConfigKey.SOURCE_ALPHA_FIELD,
                     "The column name for plotted data point color alpha (opacity).",
                     "__ALPHA__",
-                    validation=lambda x: isinstance(x, str),
+                    validation=Validator.is_str,
                 ),
                 AutolockedConfigValue(
-                    "search_score_field",
+                    ConfigKey.SEARCH_SCORE_FIELD,
                     "The column name for data points' score from search widgets.",
                     "__SEARCH_SCORE__",
-                    validation=lambda x: isinstance(x, str),
+                    validation=Validator.is_str,
                 ),
             ],
         ),
         Config(
-            "data.values",
+            ConfigSection.DATA_VALUES,
             [
                 AutolockedConfigValue(
-                    "abstain_decoded",
+                    ConfigKey.ABSTAIN_DECODED,
                     "The placeholder label indicating 'no label yet'.",
                     "ABSTAIN",
-                    validation=lambda x: isinstance(x, str),
+                    validation=Validator.is_str,
                 ),
                 AutolockedConfigValue(
-                    "abstain_encoded",
+                    ConfigKey.ABSTAIN_ENCODED,
                     "The encoded value of 'no label yet' which should almost always be -1, never 0 or positive.",
                     -1,
-                    validation=lambda x: isinstance(x, int) and x < 0,
+                    validation=Validator.is_negative_int,
                 ),
             ],
         ),

hover/config_constants.py

@@ -0,0 +1,59 @@
+import re
+
+
+class ConfigSection:
+    IO = "io"
+    VISUAL = "visual"
+    DATA_EMBEDDING = "data.embedding"
+    DATA_COLUMNS = "data.columns"
+    DATA_VALUES = "data.columns"
+
+
+class ConfigKey:
+    DATA_SAVE_DIR = "data_save_dir"
+    ABSTAIN_HEXCOLOR = "abstain_hexcolor"
+    BOKEH_PALETTE = "bokeh_palette"
+    BOKEH_PALETTE_USAGE = "bokeh_palette_usage"
+    TABLE_IMG_STYLE = "table_img_style"
+    TOOLTIP_IMG_STYLE = "tooltip_img_style"
+    DEFAULT_REDUCTION_METHOD = "default_reduction_method"
+    ENCODED_LABEL_KEY = "encoded_label_key"
+    DATASET_SUBSET_FIELD = "dataset_subset_field"
+    EMBEDDING_FIELD_PREFIX = "embedding_field_prefix"
+    SOURCE_COLOR_FIELD = "source_color_field"
+    SOURCE_ALPHA_FIELD = "source_alpha_field"
+    SEARCH_SCORE_FIELD = "search_score_field"
+    ABSTAIN_DECODED = "abstain_decoded"
+    ABSTAIN_ENCODED = "abstain_encoded"
+
+
+class Validator:
+    @staticmethod
+    def is_hex_color(x):
+        return bool(re.match(r"^\#[0-9a-fA-F]{6}$", x))
+
+    @staticmethod
+    def is_iterable(x):
+        return hasattr(x, "__iter__")
+
+    @staticmethod
+    def is_supported_dimensionality_reduction(x):
+        return x.lower() in ["umap", "ivis"]
+
+    @staticmethod
+    def is_supported_traversal_mode(x):
+        return x.lower() in ["iterate", "linspace"]
+
+    @staticmethod
+    def is_str(x):
+        return isinstance(x, str)
+
+    @staticmethod
+    def is_negative_int(x):
+        return isinstance(x, int) and x < 0
+
+
+class Preprocessor:
+    @staticmethod
+    def remove_quote_at_ends(x):
+        return re.sub(r"(^[\'\"]|[\'\"]$)", "", x)

hover/core/dataset.py

@@ -11,7 +11,6 @@
     -   loading data for training models
 """
 import os
-import hover
 import numpy as np
 import pandas as pd
 from tqdm import tqdm
@@ -35,6 +34,7 @@
     dataset_default_sel_table_kwargs,
     COLOR_GLYPH_TEMPLATE,
     DATASET_SUBSET_FIELD,
+    DEFAULT_REDUCTION_METHOD,
     embedding_field,
 )
 
@@ -161,6 +161,12 @@ def burner(d):
 
             self.dfs[_key] = _df
 
+    def subset(self, key):
+        """
+        ???+ note "Return the DataFrame by reference for the given subset."
+        """
+        return self.dfs[key]
+
     def copy(self):
         """
         ???+ note "Create another instance, copying over the data entries."
@@ -760,7 +766,9 @@ def vectorizer_lookup(self):
     def vectorizer_lookup(self, *args, **kwargs):
         self._fail("assigning vectorizer lookup by reference is forbidden.")
 
-    def compute_nd_embedding(self, vectorizer, method=None, dimension=2, **kwargs):
+    def compute_nd_embedding(
+        self, vectorizer, method=DEFAULT_REDUCTION_METHOD, dimension=2, **kwargs
+    ):
         """
         ???+ note "Get embeddings in n-dimensional space and return the dimensionality reducer."
             Reference: [`DimensionalityReducer`](https://github.com/phurwicz/hover/blob/main/hover/core/representation/reduction.py)
@@ -774,8 +782,6 @@ def compute_nd_embedding(self, vectorizer, method=None, dimension=2, **kwargs):
         """
         from hover.core.representation.reduction import DimensionalityReducer
 
-        if method is None:
-            method = hover.config["data.embedding"]["default_reduction_method"]
         # register the vectorizer for scenarios that may need it
         self.vectorizer_lookup[dimension] = vectorizer
 
@@ -846,7 +852,7 @@ def compute_2d_embedding(self, vectorizer, method=None, **kwargs):
             | `**kwargs`   |            | kwargs for `DimensionalityReducer` |
         """
         reducer = self.compute_nd_embedding(
-            vectorizer, method=None, dimension=2, **kwargs
+            vectorizer, method=method, dimension=2, **kwargs
         )
         return reducer
 

hover/core/explorer/base.py

@@ -1,7 +1,6 @@
 """
 ???+ note "Base class(es) for ALL explorer implementations."
 """
-import pandas as pd
 from abc import ABC, abstractmethod
 from collections import OrderedDict, defaultdict
 from bokeh.events import SelectionGeometry
@@ -345,13 +344,15 @@ def _setup_dfs(self, df_dict, copy=False):
         expected_not_supplied = expected_keys.difference(supplied_keys)
 
         for _key in supplied_not_expected:
-            self._warn(
-                f"{self.__class__.__name__}.__init__(): got unexpected df key {_key}"
+            self._fail(
+                f"expected df keys {list(expected_keys)}, got unexpected df key {_key}"
             )
         for _key in expected_not_supplied:
-            self._warn(
-                f"{self.__class__.__name__}.__init__(): missing expected df key {_key}"
-            )
+            self._fail(f"expected df keys {list(expected_keys)}, missing df key {_key}")
+        # raise an exception if the supplied keys and expected keys are any different
+        assert (
+            not supplied_not_expected and not expected_not_supplied
+        ), "df key mismatch"
 
         # assign df with column checks
         self.dfs = dict()
@@ -372,11 +373,6 @@ def _setup_dfs(self, df_dict, copy=False):
                     _df[_col] = _default
             self.dfs[_key] = _df.copy() if copy else _df
 
-        # expected dfs must be present
-        for _key in expected_not_supplied:
-            _df = pd.DataFrame(columns=list(mandatory_col_to_default.keys()))
-            self.dfs[_key] = _df
-
     def _setup_sources(self):
         """
         ???+ note "Create, **(not update)**, `ColumnDataSource` objects."

hover/core/explorer/feature.py

@@ -2,11 +2,11 @@
 ???+ note "Intermediate classes based on the main feature."
 """
 import re
-import hover
 import numpy as np
 from functools import lru_cache
 from bokeh.models import TextInput, Slider
 from .base import BokehBaseExplorer
+from .local_config import TOOLTIP_IMG_STYLE
 
 
 class BokehForText(BokehBaseExplorer):
@@ -200,7 +200,7 @@ class BokehForImage(BokehForUrlToVector):
     MANDATORY_COLUMNS = [PRIMARY_FEATURE, "label"]
     TOOLTIP_KWARGS = {
         "label": {"label": "Label"},
-        "image": {"image": hover.config["visual"]["tooltip_img_style"]},
+        "image": {"image": TOOLTIP_IMG_STYLE},
         "coords": True,
         "index": True,
     }

hover/core/explorer/local_config.py

@@ -1,5 +1,11 @@
 import hover
+from hover.config_constants import (
+    ConfigSection as Section,
+    ConfigKey as Key,
+)
 
-SOURCE_COLOR_FIELD = hover.config["data.columns"]["source_color_field"]
-SOURCE_ALPHA_FIELD = hover.config["data.columns"]["source_alpha_field"]
-SEARCH_SCORE_FIELD = hover.config["data.columns"]["search_score_field"]
+SOURCE_COLOR_FIELD = hover.config[Section.DATA_COLUMNS][Key.SOURCE_COLOR_FIELD]
+SOURCE_ALPHA_FIELD = hover.config[Section.DATA_COLUMNS][Key.SOURCE_ALPHA_FIELD]
+SEARCH_SCORE_FIELD = hover.config[Section.DATA_COLUMNS][Key.SEARCH_SCORE_FIELD]
+
+TOOLTIP_IMG_STYLE = hover.config[Section.VISUAL][Key.TOOLTIP_IMG_STYLE]