feat: fist version of the gap analysis tab for ts (#1410)

* feat: fist version of the gap analysis tab for ts

* feat: add gap stats table

* fix: adjust gap plot the image size

* feat: new gap analysis visualization

src/ydata_profiling/model/pandas/describe_timeseries_pandas.py

@@ -7,6 +7,7 @@
 from statsmodels.tsa.stattools import adfuller
 
 from ydata_profiling.config import Settings
+from ydata_profiling.model.pandas.utils_pandas import get_period_and_frequency
 from ydata_profiling.model.summary_algorithms import (
     describe_numeric_1d,
     describe_timeseries_1d,
@@ -141,6 +142,49 @@ def get_fft_peaks(
     return threshold, orig_peaks, peaks
 
 
+def compute_gap_stats(series: pd.Series) -> pd.Series:
+    """Computes the intertevals in the series normalized by the period.
+
+    Args:
+        series (pd.Series): time series data to analysis.
+
+    Returns:
+        A series with the gaps intervals.
+    """
+
+    gap = series.dropna()
+    index_name = gap.index.name if gap.index.name else "index"
+    gap = gap.reset_index()[index_name]
+    gap.index.name = None
+
+    if isinstance(series.index, pd.DatetimeIndex):
+        period, frequency = get_period_and_frequency(series.index)
+        period = pd.Timedelta(f"{period} {frequency}")
+        base_frequency = pd.Timedelta(f"1 {frequency}")
+    else:
+        period = np.abs(np.diff(series.index)).mean()
+        base_frequency = 1
+
+    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": 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
+    return stats
+
+
 @describe_timeseries_1d.register
 @series_hashable
 @series_handle_nulls
@@ -164,5 +208,6 @@ def pandas_describe_timeseries_1d(
     stats["stationary"] = is_stationary and not stats["seasonal"]
     stats["addfuller"] = p_value
     stats["series"] = series
+    stats["gap_stats"] = compute_gap_stats(series)
 
     return config, series, stats

src/ydata_profiling/model/pandas/timeseries_index_pandas.py

@@ -4,6 +4,7 @@
 from pandas.api.types import is_numeric_dtype
 
 from ydata_profiling.config import Settings
+from ydata_profiling.model.pandas.utils_pandas import get_period_and_frequency
 from ydata_profiling.model.timeseries_index import get_time_index_description
 
 
@@ -21,10 +22,7 @@ def pandas_get_time_index_description(
     start = df.index.min()
     end = df.index.max()
     if isinstance(df.index, pd.DatetimeIndex):
-        freq = df.index.inferred_freq
-        delta = abs(np.diff(df.index)).mean()
-        delta = delta.astype(f"timedelta64[{df.index.inferred_freq}]")
-        period = delta.astype(float)
+        period, freq = get_period_and_frequency(df.index)
     else:
         freq = None
         period = abs(np.diff(df.index)).mean()

src/ydata_profiling/model/pandas/utils_pandas.py

@@ -1,4 +1,7 @@
+from typing import Tuple
+
 import numpy as np
+import pandas as pd
 
 
 def weighted_median(data: np.ndarray, weights: np.ndarray) -> int:
@@ -25,3 +28,21 @@ def weighted_median(data: np.ndarray, weights: np.ndarray) -> int:
         else:
             w_median = s_data[idx + 1]
     return w_median
+
+
+def get_period_and_frequency(index: pd.DatetimeIndex) -> Tuple[float, str]:
+    delta = abs(np.diff(index)).mean()
+    delta = pd.Timedelta(delta)
+    if delta.days > 0:
+        frequency = "Days"
+        period = delta / pd.Timedelta(days=1)
+    elif delta.seconds > 0:
+        frequency = "Seconds"
+        period = delta / pd.Timedelta(seconds=1)
+    elif delta.microseconds > 0:
+        frequency = "Microseconds"
+        period = delta / pd.Timedelta(microseconds=1)
+    else:
+        frequency = "Nanoseconds"
+        period = delta.nanoseconds / pd.Timedelta(nanoseconds=1)
+    return period, frequency

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

@@ -14,7 +14,80 @@
     VariableInfo,
 )
 from ydata_profiling.report.structure.variables.render_common import render_common
-from ydata_profiling.visualisation.plot import histogram, mini_ts_plot, plot_acf_pacf
+from ydata_profiling.visualisation.plot import (
+    histogram,
+    mini_ts_plot,
+    plot_acf_pacf,
+    plot_timeseries_gap_analysis,
+)
+
+
+def _render_gap_tab(config: Settings, summary: dict) -> Container:
+    gap_stats = [
+        {
+            "name": "period",
+            "value": fmt_numeric(
+                summary["gap_stats"]["period"], precision=config.report.precision
+            ),
+        },
+    ]
+    if "frequency" in summary["gap_stats"]:
+        gap_stats.append(
+            {
+                "name": "frequency",
+                "value": summary["gap_stats"]["frequency"],
+            }
+        )
+    gap_stats.extend(
+        [
+            {
+                "name": "min inverval",
+                "value": fmt_numeric(
+                    summary["gap_stats"]["min"], precision=config.report.precision
+                ),
+            },
+            {
+                "name": "max inverval",
+                "value": fmt_numeric(
+                    summary["gap_stats"]["max"], precision=config.report.precision
+                ),
+            },
+            {
+                "name": "mean inverval",
+                "value": fmt_numeric(
+                    summary["gap_stats"]["mean"], precision=config.report.precision
+                ),
+            },
+            {
+                "name": "interval std",
+                "value": fmt_numeric(
+                    summary["gap_stats"]["std"], precision=config.report.precision
+                ),
+            },
+        ]
+    )
+    gap_table = Table(
+        gap_stats,
+        name="Intervals statistics",
+        style=config.html.style,
+    )
+
+    gap_plot = Image(
+        plot_timeseries_gap_analysis(
+            config, summary["gap_stats"]["series"], summary["gap_stats"]["gaps"]
+        ),
+        image_format=config.plot.image_format,
+        alt="Gap plot",
+        name="",
+        anchor_id=f"{summary['varid']}_gap_plot",
+    )
+    return Container(
+        [gap_table, gap_plot],
+        image_format=config.plot.image_format,
+        sequence_type="grid",
+        name="Gap analysis",
+        anchor_id=f"{summary['varid']}_gap_analysis",
+    )
 
 
 def render_timeseries(config: Settings, summary: dict) -> dict:
@@ -289,8 +362,10 @@ def render_timeseries(config: Settings, summary: dict) -> dict:
         anchor_id=f"{varid}_ts_plot",
     )
 
+    ts_gap = _render_gap_tab(config, summary)
+
     template_variables["bottom"] = Container(
-        [statistics, hist, ts_plot, fq, evs, acf_pacf],
+        [statistics, hist, ts_plot, ts_gap, fq, evs, acf_pacf],
         sequence_type="tabs",
         anchor_id=f"{varid}bottom",
     )

src/ydata_profiling/visualisation/plot.py

@@ -11,7 +11,7 @@
 from matplotlib.colors import Colormap, LinearSegmentedColormap, ListedColormap, rgb2hex
 from matplotlib.dates import AutoDateLocator, ConciseDateFormatter
 from matplotlib.patches import Patch
-from matplotlib.ticker import FuncFormatter
+from matplotlib.ticker import FuncFormatter, MaxNLocator
 from statsmodels.graphics.tsaplots import plot_acf, plot_pacf
 from typeguard import typechecked
 from wordcloud import WordCloud
@@ -557,6 +557,52 @@ def _format_ts_date_axis(
     return axis
 
 
+@manage_matplotlib_context()
+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.
+    Args:
+        variables: The data to plot.
+        figsize: The size of the figure (width, height) in inches, default (6,4).
+    Returns:
+        The TimeSeries lineplot.
+    """
+    fig = plt.figure(figsize=figsize)
+    ax = fig.add_subplot(111)
+
+    colors = create_comparison_color_list(config)
+    if isinstance(series, list):
+        min_ = min(s.min() for s in series)
+        max_ = max(s.max() for s in series)
+        labels = config.html.style._labels
+        for serie, gaps_, color, label in zip(series, gaps, colors, labels):
+            serie.plot(
+                ax=ax,
+                label=label,
+                color=color,
+                alpha=0.65,
+            )
+            _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))
+
+        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)
+
+
 @manage_matplotlib_context()
 def plot_overview_timeseries(
     config: Settings,