feat: new gap analysis visualization

src/ydata_profiling/model/pandas/describe_timeseries_pandas.py

@@ -155,7 +155,6 @@ def compute_gap_stats(series: pd.Series) -> pd.Series:
     gap = series.dropna()
     index_name = gap.index.name if gap.index.name else "index"
     gap = gap.reset_index()[index_name]
-    gap.index = gap
     gap.index.name = None
 
     if isinstance(series.index, pd.DatetimeIndex):
@@ -166,14 +165,20 @@ def compute_gap_stats(series: pd.Series) -> pd.Series:
         period = np.abs(np.diff(series.index)).mean()
         base_frequency = 1
 
-    gap = gap.diff()
+    diff = gap.diff()
+    anchors = gap[diff > period].index
+    gaps = []
+    for i in anchors:
+        gaps.append(gap.loc[gap.index[[i - 1, i]]].values)
+
     stats = {
         "period": period / base_frequency,
-        "min": gap.min() / base_frequency,
-        "max": gap.max() / base_frequency,
-        "mean": gap.mean() / base_frequency,
-        "std": gap.std() / base_frequency,
-        "normalized_diff": gap / period,
+        "min": diff.min() / base_frequency,
+        "max": diff.max() / base_frequency,
+        "mean": diff.mean() / base_frequency,
+        "std": diff.std() / base_frequency,
+        "series": series,
+        "gaps": gaps,
     }
     if isinstance(series.index, pd.DatetimeIndex):
         stats["frequency"] = frequency

src/ydata_profiling/report/structure/variables/render_timeseries.py

@@ -74,7 +74,7 @@ def _render_gap_tab(config: Settings, summary: dict) -> Container:
 
     gap_plot = Image(
         plot_timeseries_gap_analysis(
-            config, summary["gap_stats"]["normalized_diff"]
+            config, summary["gap_stats"]["series"], summary["gap_stats"]["gaps"]
         ),
         image_format=config.plot.image_format,
         alt="Gap plot",

src/ydata_profiling/visualisation/plot.py

@@ -561,6 +561,7 @@ def _format_ts_date_axis(
 def plot_timeseries_gap_analysis(
     config: Settings,
     series: Union[pd.Series, List[pd.Series]],
+    gaps: Union[pd.Series, List[pd.Series]],
     figsize: tuple = (6, 3),
 ) -> matplotlib.figure.Figure:
     """Plot an line plot from the data and return the AxesSubplot object.
@@ -573,10 +574,12 @@ def plot_timeseries_gap_analysis(
     fig = plt.figure(figsize=figsize)
     ax = fig.add_subplot(111)
 
+    colors = create_comparison_color_list(config)
     if isinstance(series, list):
-        colors = create_comparison_color_list(config)
+        min_ = min(s.min() for s in series)
+        max_ = max(s.max() for s in series)
         labels = config.html.style._labels
-        for serie, color, label in zip(series, colors, labels):
+        for serie, gaps_, color, label in zip(series, gaps, colors, labels):
             serie.plot(
                 ax=ax,
                 label=label,
@@ -585,12 +588,17 @@ def plot_timeseries_gap_analysis(
             )
             _format_ts_date_axis(serie, ax)
             ax.yaxis.set_major_locator(MaxNLocator(integer=True))
+            for gap in gaps_:
+                ax.fill_between(x=gap, y1=min_, y2=max_, color=color, alpha=0.25)
     else:
         series.plot(ax=ax)
         _format_ts_date_axis(series, ax)
         ax.yaxis.set_major_locator(MaxNLocator(integer=True))
 
-    plt.ylabel("gap (#periods)")
+        for gap in gaps:
+            ax.fill_between(
+                x=gap, y1=series.min(), y2=series.max(), color=colors[0], alpha=0.25
+            )
 
     return plot_360_n0sc0pe(config)