feat: update core packages (#1790)

* feat: upgrade support to python 3.13

* feat: remove python 3.9, as it is no longer supported since last October

* fix: remove display message

* chore: fix the tests for the multiprocessing

* fix(linting): code formatting

* fix: histograms support Numpy 2.x

* fix: histogram for numpy 2.2x

* fix(linting): code formatting

* fix: histogram safe error

* chore: add Union typing fix

* fix: improve hist compute logic

* fix(linting): code formatting

* fix: fix chi_squared function

* fix: typing

* fix: array optional typing

* fix: change the logic to align with the typing

* fix(linting): code formatting

---------

Co-authored-by: Azory YData Bot <azory@ydata.ai>

Author: fabclmnt

.github/workflows/tests.yml

@@ -16,7 +16,7 @@ jobs:
     strategy:
       matrix:
         os: [ ubuntu-22.04 ]
-        python-version: ["3.9", "3.10", "3.11", "3.12", "3.13" ]
+        python-version: ["3.10", "3.11", "3.12", "3.13" ]
         pandas: [ "pandas>1.1" ]
         numpy: [ "numpy>=1.21" ]
     runs-on: ${{ matrix.os }}
@@ -65,7 +65,7 @@ jobs:
     strategy:
       matrix:
         os: [ubuntu-22.04]
-        python-version: ["3.12"]
+        python-version: ["3.13"]
         pandas: [ "pandas>1.1" ]
         numpy: [ "numpy>=1.21" ]
 

pyproject.toml

@@ -11,7 +11,7 @@ package_name = "ydata-profiling"
 
 [project]
 name = "ydata-profiling"
-requires-python = ">=3.7,<3.14"
+requires-python = ">=3.10,<3.14"
 authors = [
     {name = "YData Labs Inc", email = "opensource@ydata.ai"}
 ]
@@ -32,43 +32,42 @@ classifiers = [
     "Topic :: Scientific/Engineering",
     "Framework :: IPython",
     "Programming Language :: Python :: 3",
-    "Programming Language :: Python :: 3.7",
-    "Programming Language :: Python :: 3.8",
-    "Programming Language :: Python :: 3.9",
     "Programming Language :: Python :: 3.10",
     "Programming Language :: Python :: 3.11",
     "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Programming Language :: Python :: 3.14",
 ]
 
 dependencies = [
-    "scipy>=1.4.1, <1.16",
-    "pandas>1.1, <3.0, !=1.4.0",
+    "scipy>=1.8, <1.17",
+    "pandas>1.5, <3.0, !=1.4.0",
     "matplotlib>=3.5, <=3.10",
-    "pydantic>=2",
-    "PyYAML>=5.0.0, <6.1",
-    "jinja2>=2.11.1, <3.2",
+    "pydantic>=2, <3",
+    "PyYAML>=6.0.3, <6.1",
+    "jinja2>=3.1.6, <3.2",
     "visions[type_image_path]>=0.7.5, <0.8.2",
-    "numpy>=1.16.0,<2.2",
+    "numpy>=1.22,<2.4",
     # Could be optional
     # Related to HTML report
     "minify-html>=0.15.0",
     "filetype>=1.0.0",
     # Correlations
-    "phik>=0.11.1,<0.13",
+    "phik>=0.12.5, <0.13",
     # Examples
-    "requests>=2.24.0, <3",
+    "requests>=2.32.0, <3",
     # Progress bar
-    "tqdm>=4.48.2, <5",
+    "tqdm>=4.66.3, <5",
     "seaborn>=0.10.1, <0.14",
     "multimethod>=1.4, <2",
     # metrics
     "statsmodels>=0.13.2, <1",
     # type checking
-    "typeguard>=3, <5",
-    "imagehash==4.3.1",
-    "wordcloud>=1.9.3",
-    "dacite>=1.8",
-    "numba>=0.56.0, <=0.61",
+    "typeguard>=4, <5",
+    "imagehash==4.3.2",
+    "wordcloud>=1.9.4",
+    "dacite>=1.9, <2",
+    "numba>=0.60,<0.63",
 ]
 
 dynamic = [

src/ydata_profiling/__init__.py

@@ -11,7 +11,6 @@
 from ydata_profiling.controller import pandas_decorator  # isort:skip # noqa
 from ydata_profiling.profile_report import ProfileReport  # isort:skip # noqa
 from ydata_profiling.version import __version__  # isort:skip # noqa
-from ydata_profiling.utils.information import display_banner
 
 # backend
 import ydata_profiling.model.pandas  # isort:skip  # noqa
@@ -26,8 +25,6 @@
 
     warnings.simplefilter("ignore", category=NumbaDeprecationWarning)
 
-display_banner()
-
 __all__ = [
     "pandas_decorator",
     "ProfileReport",

src/ydata_profiling/model/pandas/describe_categorical_pandas.py

@@ -16,7 +16,6 @@
     series_handle_nulls,
     series_hashable,
 )
-from ydata_profiling.utils.information import DisplayInfo
 
 
 def get_character_counts_vc(vc: pd.Series) -> pd.Series:
@@ -270,11 +269,6 @@ def pandas_describe_categorical_1d(
 
     if config.vars.cat.dirty_categories:  # noqa: SIM102
         if not _displayed_catvar_banner:
-            display_info = DisplayInfo(
-                title="Identify dirty categories with ydata-sdk",
-                info_text="This feature is only available for ydata-sdk users. Register to give try it.",
-            )
-            display_info.display_message()
             _displayed_catvar_banner = True
 
     return config, series, summary

src/ydata_profiling/model/summary_algorithms.py

@@ -1,5 +1,5 @@
 import functools
-from typing import Any, Callable, Optional, Tuple, TypeVar
+from typing import Any, Callable, Optional, Tuple, TypeVar, Union
 
 import numpy as np
 import pandas as pd
@@ -26,6 +26,41 @@ def inner(
     return inner
 
 
+def safe_histogram(
+    values: np.ndarray,
+    bins: Union[int, str, np.ndarray] = "auto",
+    weights: Optional[np.ndarray] = None,
+    density: bool = False,
+) -> Tuple[np.ndarray, np.ndarray]:
+    """
+    Wrapper to avoid
+    ValueError: Too many bins for data range. Cannot create N finite-sized bins.
+    """
+    try:
+        return np.histogram(values, bins=bins, weights=weights, density=density)
+    except ValueError as exc:
+        if "Too many bins for data range" in str(exc):
+            try:
+                return np.histogram(
+                    values, bins="auto", weights=weights, density=density
+                )
+            except ValueError:
+                finite = values[np.isfinite(values)]
+                if finite.size == 0:
+                    return np.array([]), np.array([])
+                vmin = float(np.min(finite))
+                vmax = float(np.max(finite))
+                if vmin == vmax:
+                    eps = 0.5 if vmin == 0 else abs(vmin) * 0.5
+                    bin_edges = np.array([vmin - eps, vmin + eps])
+                else:
+                    bin_edges = np.array([vmin, vmax])
+                return np.histogram(
+                    values, bins=bin_edges, weights=weights, density=density
+                )
+        raise
+
+
 def histogram_compute(
     config: Settings,
     finite_values: np.ndarray,
@@ -36,27 +71,75 @@ def histogram_compute(
     stats = {}
     if len(finite_values) == 0:
         return {name: []}
+
     hist_config = config.plot.histogram
-    bins_arg = "auto" if hist_config.bins == 0 else min(hist_config.bins, n_unique)
-    bins = np.histogram_bin_edges(finite_values, bins=bins_arg)
-    if len(bins) > hist_config.max_bins:
-        bins = np.histogram_bin_edges(finite_values, bins=hist_config.max_bins)
-        weights = weights if weights and len(weights) == hist_config.max_bins else None
-
-    stats[name] = np.histogram(
-        finite_values, bins=bins, weights=weights, density=config.plot.histogram.density
+
+    # Compute data range
+    finite = finite_values[np.isfinite(finite_values)]
+    vmin = float(np.min(finite))
+    vmax = float(np.max(finite))
+    data_range = vmax - vmin
+
+    # Choose of Bins based on observed data values
+    if data_range == 0:
+        eps = 0.5 if vmin == 0 else abs(vmin) * 0.1
+        bins = np.array([vmin - eps, vmin + eps])
+    else:
+        requested_bins = hist_config.bins if hist_config.bins > 0 else "auto"
+
+        if isinstance(requested_bins, int):
+            safe_bins = min(requested_bins, n_unique, hist_config.max_bins)
+
+            safe_bins = max(1, safe_bins)
+
+            bins = np.linspace(vmin, vmax, safe_bins + 1)
+        else:
+            bins = np.histogram_bin_edges(finite_values, bins="auto")
+            if len(bins) - 1 > hist_config.max_bins:
+                bins = np.linspace(vmin, vmax, hist_config.max_bins + 1)
+
+    hist = np.histogram(
+        finite_values,
+        bins=bins,
+        weights=weights,
+        density=hist_config.density,
     )
+
+    stats[name] = hist
     return stats
 
 
 def chi_square(
-    values: Optional[np.ndarray] = None, histogram: Optional[np.ndarray] = None
+    values: Optional[np.ndarray] = None,
+    histogram: Optional[np.ndarray] = None,
 ) -> dict:
+    # Case 1: histogram not passed → we compute it
     if histogram is None:
-        bins = np.histogram_bin_edges(values, bins="auto")
+        if values is None:
+            return {"statistic": 0, "pvalue": 0}
+
+        # Try NumPy "auto" binning (may fail under NumPy 2)
+        try:
+            bins = np.histogram_bin_edges(values, bins="auto")
+        except ValueError:
+            # Fallback: basic 1-bin histogram covering the min→max range
+            finite = values[np.isfinite(values)]
+            if finite.size == 0:
+                return {"statistic": 0, "pvalue": 0}
+
+            vmin = float(finite.min())
+            vmax = float(finite.max())
+            if vmin == vmax:
+                bins = np.array([vmin - 0.5, vmin + 0.5])
+            else:
+                bins = np.array([vmin, vmax])
+
         histogram, _ = np.histogram(values, bins=bins)
-    if len(histogram) == 0 or np.sum(histogram) == 0:
+
+    # Case 2: histogram exists but is empty
+    if histogram.size == 0 or histogram.sum() == 0:
         return {"statistic": 0, "pvalue": 0}
+
     return dict(chisquare(histogram)._asdict())
 
 

src/ydata_profiling/report/presentation/flavours/html/templates/sequence/overview_tabs.html

@@ -1,7 +1,4 @@
 {% if tabs | length > 0 %}
-    {% if oss %}
-        <p class="text-body-secondary text-end">Brought to you by <a href="https://ydata.ai/?utm_source=opensource&utm_medium=ydataprofiling&utm_campaign=report">YData</a></p>
-    {% endif %}
     <div class="row item {% if classes %}{{ classes }}{% endif %}" {% if id %} id="{{ id }}"{% endif %}>
         <ul class="nav nav-tabs tab-nav" role="tablist">
             {% for tab in tabs %}

src/ydata_profiling/utils/information.py

@@ -1,17 +1,22 @@
 import os
 
 import pytest
+import requests
 
 from ydata_profiling.controller import console
 from ydata_profiling.utils.paths import get_config
 
+NASA_URL = "https://data.nasa.gov/docs/legacy/meteorite_landings/Meteorite_Landings.csv"
+
 
 @pytest.fixture
 def console_data(get_data_file):
-    return get_data_file(
-        "meteorites.csv",
-        "https://data.nasa.gov/docs/legacy/meteorite_landings/Meteorite_Landings.csv",
-    )
+    try:
+        return get_data_file("meteorites.csv", NASA_URL)
+    except requests.RequestException as e:
+        pytest.skip(f"Skipping console tests: NASA dataset unavailable ({e})")
+    except Exception as e:
+        pytest.skip(f"Skipping console tests: cannot fetch meteorites.csv ({e})")
 
 
 @pytest.mark.skipif(os.name == "nt", reason="multiprocessing+pytest broken on Windows")