fix(eda):fix value table display

dataprep/eda/distribution/compute/univariate.py

@@ -107,12 +107,10 @@ def nom_comps(srs: dd.Series, cfg: Config) -> Dict[str, Any]:
     srs = srs.dropna()  # drop null values
     grps = srs.value_counts(sort=False)  # counts of unique values in the series
     data["geo"] = grps
-
-    if cfg.stats.enable or cfg.bar.enable or cfg.pie.enable:
-        data["nuniq"] = grps.shape[0]  # total number of groups
+    data["nuniq"] = grps.shape[0]  # total number of groups
 
     # compute bar and pie together unless the parameters are different
-    if cfg.bar.enable or cfg.pie.enable:
+    if cfg.bar.enable or cfg.pie.enable or cfg.value_table.enable:
         # select the largest or smallest groups
         data["bar"] = (
             grps.nlargest(cfg.bar.bars) if cfg.bar.sort_descending else grps.nsmallest(cfg.bar.bars)
@@ -138,7 +136,7 @@ def nom_comps(srs: dd.Series, cfg: Config) -> Dict[str, Any]:
             data["chisq"] = chisquare(grps.values)
 
     df = grps.reset_index()  # dataframe with group names and counts
-    if cfg.stats.enable:
+    if cfg.stats.enable or cfg.value_table.enable:
         data.update(_calc_nom_stats(srs, df, data["nrows"], data["nuniq"]))
     elif cfg.wordfreq.enable and cfg.insight.enable:
         data["len_stats"] = {"Minimum": srs.str.len().min(), "Maximum": srs.str.len().max()}
@@ -190,11 +188,9 @@ def cont_comps(srs: dd.Series, cfg: Config) -> Dict[str, Any]:
     # pylint: disable=too-many-branches
     data: Dict[str, Any] = {}
 
-    if cfg.stats.enable or cfg.hist.enable:
-        data["nrows"] = srs.shape[0]  # total rows
+    data["nrows"] = srs.shape[0]  # total rows
     srs = srs.dropna()
-    if cfg.stats.enable:
-        data["npres"] = srs.shape[0]  # number of present (not null) values
+    data["npres"] = srs.shape[0]  # number of present (not null) values
     srs = srs[~srs.isin({np.inf, -np.inf})]  # remove infinite values
     if cfg.hist.enable or cfg.qqnorm.enable and cfg.insight.enable:
         data["hist"] = da.histogram(srs, cfg.hist.bins, (srs.min(), srs.max()))
@@ -237,8 +233,7 @@ def cont_comps(srs: dd.Series, cfg: Config) -> Dict[str, Any]:
         data.update(_calc_box(srs, data["qntls"], cfg))
     if cfg.value_table.enable:
         value_counts = srs.value_counts(sort=False)
-        if cfg.stats.enable:
-            data["nuniq"] = value_counts.shape[0]
+        data["nuniq"] = value_counts.shape[0]
         data["value_table"] = value_counts.nlargest(cfg.value_table.ngroups)
     elif cfg.stats.enable:
         data["nuniq"] = srs.nunique_approx()

dataprep/eda/distribution/render.py

@@ -1619,6 +1619,7 @@ def render_cat(itmdt: Intermediate, cfg: Config) -> Dict[str, Any]:
 
     if cfg.value_table.enable:
         htgs["Value Table"] = cfg.value_table.how_to_guide()
+        stats = data["stats"]
         value_table = _value_table(
             data["value_table"], stats["nrows"], stats["npres"], stats["nuniq"]
         )
@@ -1628,7 +1629,10 @@ def render_cat(itmdt: Intermediate, cfg: Config) -> Dict[str, Any]:
     # panel.child.children[0] is a figure
     for panel in tabs[0:]:
         panel.child.children[0].frame_width = int(plot_width * 0.9)
-    tabs[0].child.children[0].frame_width = int(plot_width_bar * 0.9)
+
+    if len(tabs) > 0:
+        tabs[0].child.children[0].frame_width = int(plot_width_bar * 0.9)
+
     return {
         "tabledata": format_cat_stats(stats, len_stats, letter_stats) if cfg.stats.enable else [],
         "value_table": value_table,

dataprep/tests/eda/test_plot.py

@@ -12,6 +12,7 @@
 from ...eda import plot
 from ...eda.dtypes_v2 import Nominal, LatLong
 from ...eda.utils import to_dask
+from ...datasets import load_dataset
 from .random_data_generator import random_df
 
 LOGGER = logging.getLogger(__name__)
@@ -98,3 +99,9 @@ def test_geo(geodf: dd.DataFrame) -> None:
 
 def test_random_df(random_df: pd.DataFrame) -> None:
     plot(random_df)
+
+
+def test_plot_titanic() -> None:
+    df = load_dataset("titanic")
+    plot(df, "Sex", display=["Value Table"])
+    plot(df, "Age", display=["Value Table"])