feat: replace missing plots to avoid dependencies' confilicts

README.md

@@ -35,7 +35,7 @@ For each column, the following information (whenever relevant for the column typ
 - **Most frequent and extreme values**
 - **Histograms**: categorical and numerical
 - **Correlations**: high correlation warnings, based on different correlation metrics (Spearman, Pearson, Kendall, Cramér’s V, Phik)
-- **Missing values**: through counts, matrix, heatmap and dendrograms
+- **Missing values**: through counts, matrix and heatmap
 - **Duplicate rows**: list of the most common duplicated rows
 - **Text analysis**: most common categories (uppercase, lowercase, separator), scripts (Latin, Cyrillic) and blocks (ASCII, Cyrilic)
 - **File and Image analysis**: file sizes, creation dates, dimensions, indication of truncated images and existence of EXIF metadata

docsrc/source/pages/advanced_usage/available_settings.rst

@@ -62,18 +62,15 @@ Settings related with the missing data section and the visualizations it can inc
    :header-rows: 1
 
 .. code-block:: python
-  :caption: Configuration example: disable heatmap and dendrogram for large datasets
+  :caption: Configuration example: disable heatmap for large datasets
 
   profile = df.profile_report(
       missing_diagrams={
           "heatmap": False,
-          "dendrogram": False,
       }
   )
   profile.to_file("report.html")
 
-The missing data diagrams are generated by the `missingno <https://github.com/ResidentMario/missingno>`_ package.
-
 Correlations
 ------------
 

docsrc/source/pages/getting_started/overview.rst

@@ -38,7 +38,7 @@ For each column, the following information (whenever relevant for the column typ
 * **Most frequent and extreme values**
 * **Histograms:** categorical and numerical
 * **Correlations**: high correlation warnings, based on different correlation metrics (Spearman, Pearson, Kendall, Cramér's V, Phik)
-* **Missing values**: through counts, matrix, heatmap and dendrograms
+* **Missing values**: through counts, matrix and heatmap
 * **Duplicate rows**: list of the most common duplicated rows
 * **Text analysis**: most common categories (uppercase, lowercase, separator), scripts (Latin, Cyrillic) and blocks (ASCII, Cyrilic)
 * **File and Image analysis**: file sizes, creation dates, dimensions, indication of truncated images and existence of EXIF metadata

docsrc/source/pages/reference/api/_autosummary/pandas_profiling.visualisation.missing.rst

@@ -15,7 +15,6 @@
 
       get_font_size
       plot_missing_bar
-      plot_missing_dendrogram
       plot_missing_heatmap
       plot_missing_matrix
 

docsrc/source/pages/tables/config_missing.csv

@@ -1,5 +1,4 @@
 Parameter,Type,Default,Description
 ``missing_diagrams.bar``,boolean,``True``,"Display a bar chart with counts of missing values for each column."
 ``missing_diagrams.matrix``,boolean,``True``,"Display a matrix of missing values. Similar to the bar chart, but might provide overview of the co-occurrence of missing values in rows."
-``missing_diagrams.heatmap``,boolean,``True``,"Display a heatmap of missing values, that measures nullity correlation (i.e. how strongly the presence or absence of one variable affects the presence of another)."
-``missing_diagrams.dendrogram``,boolean,``True``,"Display a dendrogram. Provides insight in the co-occurrence of missing values (i.e. columns that are both filled or both none)."
+``missing_diagrams.heatmap``,boolean,``True``,"Display a heatmap of missing values, that measures nullity correlation (i.e. how strongly the presence or absence of one variable affects the presence of another)."

requirements.txt

@@ -9,8 +9,6 @@ numpy>=1.16.0,<1.24
 # Could be optional
 # Related to HTML report
 htmlmin==0.1.12
-# Missing values
-missingno>=0.4.2, <0.6
 # Correlations
 phik>=0.11.1,<0.13
 # Text analysis

src/pandas_profiling/config.py

@@ -113,7 +113,6 @@ class Univariate(BaseModel):
 
 class MissingPlot(BaseModel):
     # Force labels when there are > 50 variables
-    # https://github.com/ResidentMario/missingno/issues/93#issuecomment-513322615
     force_labels: bool = True
     cmap: str = "RdBu"
 
@@ -298,7 +297,6 @@ class Config:
     missing_diagrams: Dict[str, bool] = {
         "bar": True,
         "matrix": True,
-        "dendrogram": True,
         "heatmap": True,
     }
 
@@ -390,7 +388,6 @@ class Config:
             "bar": False,
             "matrix": False,
             "heatmap": False,
-            "dendrogram": False,
         },
         "correlations": {
             "pearson": {"calculate": False},

src/pandas_profiling/config_default.yaml

@@ -87,7 +87,6 @@ missing_diagrams:
     bar: true
     matrix: true
     heatmap: true
-    dendrogram: true
 
 correlations:
     pearson:

src/pandas_profiling/config_minimal.yaml

@@ -88,7 +88,6 @@ missing_diagrams:
     bar: false
     matrix: false
     heatmap: false
-    dendrogram: false
 
 correlations:
     pearson:
@@ -139,7 +138,6 @@ plot:
     missing:
         cmap: 'RdBu'
         # Force labels when there are > 50 variables
-        # https://github.com/ResidentMario/missingno/issues/93#issuecomment-513322615
         force_labels: true
 
     cat_frequency:

src/pandas_profiling/model/missing.py

@@ -22,11 +22,6 @@ def missing_heatmap(config: Settings, df: Any) -> str:
     raise NotImplementedError()
 
 
-@multimethod
-def missing_dendrogram(config: Settings, df: Any) -> str:
-    raise NotImplementedError()
-
-
 def get_missing_active(config: Settings, table_stats: dict) -> Dict[Any, Any]:
     """
 
@@ -56,12 +51,6 @@ def get_missing_active(config: Settings, table_stats: dict) -> Dict[Any, Any]:
             "caption": "The correlation heatmap measures nullity correlation: how strongly the presence or absence of one variable affects the presence of another.",
             "function": missing_heatmap,
         },
-        "dendrogram": {
-            "min_missing": 1,
-            "name": "Dendrogram",
-            "caption": "The dendrogram allows you to more fully correlate variable completion, revealing trends deeper than the pairwise ones visible in the correlation heatmap.",
-            "function": missing_dendrogram,
-        },
     }
 
     missing_map = {
@@ -114,7 +103,7 @@ def get_missing_diagram(
         settings: missing diagram name, caption and function
 
     Returns:
-        A dictionary containing the base64 encoded plots for each diagram that is active in the config (matrix, bar, heatmap, dendrogram).
+        A dictionary containing the base64 encoded plots for each diagram that is active in the config (matrix, bar, heatmap).
     """
 
     if len(df) == 0:

src/pandas_profiling/model/pandas/missing_pandas.py

@@ -3,13 +3,11 @@
 from pandas_profiling.config import Settings
 from pandas_profiling.model.missing import (
     missing_bar,
-    missing_dendrogram,
     missing_heatmap,
     missing_matrix,
 )
 from pandas_profiling.visualisation.missing import (
     plot_missing_bar,
-    plot_missing_dendrogram,
     plot_missing_heatmap,
     plot_missing_matrix,
 )
@@ -28,8 +26,3 @@ def pandas_missing_matrix(config: Settings, df: pd.DataFrame) -> str:
 @missing_heatmap.register
 def pandas_missing_heatmap(config: Settings, df: pd.DataFrame) -> str:
     return plot_missing_heatmap(config, df)
-
-
-@missing_dendrogram.register
-def pandas_missing_dendrogram(config: Settings, df: pd.DataFrame) -> str:
-    return plot_missing_dendrogram(config, df)

src/pandas_profiling/visualisation/missing.py

@@ -1,10 +1,14 @@
 """Plotting functions for the missing values diagrams"""
 import pandas as pd
 from matplotlib import pyplot as plt
-from missingno import missingno
 
 from pandas_profiling.config import Settings
 from pandas_profiling.visualisation.context import manage_matplotlib_context
+from pandas_profiling.visualisation.plot import (
+    missing_bar,
+    missing_heatmap,
+    missing_matrix,
+)
 from pandas_profiling.visualisation.utils import hex_to_rgb, plot_360_n0sc0pe
 
 
@@ -44,11 +48,10 @@ def plot_missing_matrix(config: Settings, data: pd.DataFrame) -> str:
         The resulting missing values matrix encoded as a string.
     """
 
-    missingno.matrix(
+    missing_matrix(
         data,
         figsize=(10, 4),
         fontsize=get_font_size(data) / 20 * 16,
-        sparkline=False,
         color=hex_to_rgb(config.html.style.primary_colors[0]),
         labels=config.plot.missing.force_labels,
     )
@@ -67,7 +70,7 @@ def plot_missing_bar(config: Settings, data: pd.DataFrame) -> str:
     Returns:
         The resulting missing values bar plot encoded as a string.
     """
-    missingno.bar(
+    missing_bar(
         data,
         figsize=(10, 5),
         fontsize=get_font_size(data),
@@ -102,7 +105,7 @@ def plot_missing_heatmap(config: Settings, data: pd.DataFrame) -> str:
     if len(data.columns) > 40:
         font_size /= 1.4
 
-    missingno.heatmap(
+    missing_heatmap(
         data,
         figsize=(10, height),
         fontsize=font_size,
@@ -116,20 +119,3 @@ def plot_missing_heatmap(config: Settings, data: pd.DataFrame) -> str:
         plt.subplots_adjust(left=0.2, right=0.9, top=0.8, bottom=0.3)
 
     return plot_360_n0sc0pe(config)
-
-
-@manage_matplotlib_context()
-def plot_missing_dendrogram(config: Settings, data: pd.DataFrame) -> str:
-    """Generate a dendrogram plot for missing values.
-
-    Args:
-        config: report Settings object
-        data: Pandas DataFrame to generate missing values dendrogram plot from.
-
-    Returns:
-      The resulting missing values dendrogram plot encoded as a string.
-
-    """
-    missingno.dendrogram(data, fontsize=get_font_size(data) * 2.0)
-    plt.subplots_adjust(left=0.1, right=0.9, top=0.7, bottom=0.2)
-    return plot_360_n0sc0pe(config)