docs: fix report titles (#1710)

gmartinsribeiro · azory-ydata · fabclmnt · web-flow · commit 0ed32b7a8593 · 2025-03-04T09:47:40.000-08:00
* docs: fix report titles

change pandas to ydata

* fix(linting): code formatting

* docs: fix typo

remove extra word

* fix(linting): code formatting

---------

Co-authored-by: Azory YData Bot &lt;azory@ydata.ai&gt;
Co-authored-by: Fabiana &lt;30911746+fabclmnt@users.noreply.github.com&gt;
diff --git a/docs/advanced_settings/tables/config_general.csv b/docs/advanced_settings/tables/config_general.csv
@@ -1,4 +1,4 @@
 Parameter,Type,Default,Description
-``title``,string,"Pandas Profiling Report","Title for the report, shown in the header and title bar."
+``title``,string,"YData Profiling Report","Title for the report, shown in the header and title bar."
 ``pool_size``,integer,0,"Number of workers in thread pool. When set to zero, it is set to the number of CPUs available."
 ``progress_bar``,boolean,``True``,"If ``True``, ``ydata-profiling`` will display a progress bar."
diff --git a/docs/features/custom_reports.md b/docs/features/custom_reports.md
@@ -28,7 +28,7 @@ An example would be:
 ```python linenums="1" title="Customize plots rendering"
 profile = ProfileReport(
     planets,
-    title="Pandas Profiling Report",
+    title="YData Profiling Report",
     explorative=True,
     plot={"dpi": 200, "image_format": "png"},
 )
@@ -68,7 +68,7 @@ the palette used by the correlation matrix, use the ``correlation`` key:
 
   profile = ProfileReport(
       df,
-      title="Pandas Profiling Report",
+      title="YData Profiling Report",
       explorative=True,
       plot={"correlation": {"cmap": "RdBu_r", "bad": "#000000"}},
   )
@@ -81,7 +81,7 @@ Similarly, the palette for *Missing values* can be changed using ``missing`` arg
 
   profile = ProfileReport(
       df,
-      title="Pandas Profiling Report",
+      title="YData Profiling Report",
       explorative=True,
       plot={"missing": {"cmap": "RdBu_r"}},
   )
diff --git a/docs/getting-started/quickstart.md b/docs/getting-started/quickstart.md
@@ -14,7 +14,7 @@ df = pd.DataFrame(np.random.rand(100, 5), columns=["a", "b", "c", "d", "e"])
 To generate the standard profiling report, merely run:
 
 ``` python
-profile = ProfileReport(df, title="Pandas Profiling Report")
+profile = ProfileReport(df, title="YData Profiling Report")
 ```
 
 ## Using inside Jupyter Notebooks
diff --git a/docs/integrations/great_expectations.md b/docs/integrations/great_expectations.md
@@ -72,7 +72,7 @@ from ydata_profiling import ProfileReport
 
 df = pd.read_csv("titanic.csv")
 
-profile = ProfileReport(df, title="Pandas Profiling Report", explorative=True)
+profile = ProfileReport(df, title="YData Profiling Report", explorative=True)
 
 # Obtain an Expectation Suite with a set of default Expectations
 # By default, this also profiles the dataset, saves the suite, runs validation, and builds Data Docs
diff --git a/examples/hcc/eda-with-feature-comparison.ipynb b/examples/hcc/eda-with-feature-comparison.ipynb
@@ -4,7 +4,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Pandas Profiling: HCC Dataset\n",
+    "# YData Profiling: HCC Dataset\n",
     "Source of data: https://www.kaggle.com/datasets/mrsantos/hcc-dataset\n",
     "\n",
     "As modifiations have been introduced for the purpose of this use case, the .csv file is provided (hcc.csv)."
@@ -67,7 +67,7 @@
    "metadata": {},
    "source": [
     "## Analysis of \"Alerts\"\n",
-    "Pandas Profiling alerts for the presence of 4 potential data quality problems:\n",
+    "YData Profiling alerts for the presence of 4 potential data quality problems:\n",
     "\n",
     "- `DUPLICATES`: 4 duplicate rows in data\n",
     "- `CONSTANT`: Constant value “999” in ‘O2’\n",
diff --git a/examples/integrations/great_expectations/great_expectations_example.py b/examples/integrations/great_expectations/great_expectations_example.py
@@ -11,7 +11,7 @@
 
 df = pd.read_csv(file_name)
 
-profile = ProfileReport(df, title="Pandas Profiling Report", explorative=True)
+profile = ProfileReport(df, title="YData Profiling Report", explorative=True)
 
 # Example 1
 # Obtain expectation suite, this includes profiling the dataset, saving the expectation suite, validating the
diff --git a/examples/meteorites/meteorites.ipynb b/examples/meteorites/meteorites.ipynb
@@ -4,7 +4,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Pandas Profiling: NASA Meteorites example\n",
+    "## YData Profiling: NASA Meteorites example\n",
     "Source of data: https://data.nasa.gov/Space-Science/Meteorite-Landings/gh4g-9sfh"
    ]
   },
diff --git a/examples/meteorites/meteorites_cloud.ipynb b/examples/meteorites/meteorites_cloud.ipynb
@@ -4,7 +4,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Pandas Profiling: NASA Meteorites example\n",
+    "## YData Profiling: NASA Meteorites example\n",
     "Source of data: https://data.nasa.gov/Space-Science/Meteorite-Landings/gh4g-9sfh"
    ]
   },
diff --git a/examples/usaairquality/usaairquality.ipynb b/examples/usaairquality/usaairquality.ipynb
@@ -5,7 +5,7 @@
    "id": "75bdb225-9ba6-479b-b15a-8fde07034146",
    "metadata": {},
    "source": [
-    "## Pandas Profiling: USA Air Pollution Data\n",
+    "## YData Profiling: USA Air Pollution Data\n",
     "Source of data: https://data.world/data-society/us-air-pollution-data"
    ]
   },
@@ -33,7 +33,7 @@
    "id": "fd3ef034-d2d1-4e12-9c8d-7cd685bfe001",
    "metadata": {},
    "source": [
-    "Make sure that we have the latest version of pandas-profiling."
+    "Make sure that we have the latest version of ydata-profiling."
    ]
   },
   {
@@ -46,7 +46,7 @@
     "%%capture\n",
     "import sys\n",
     "\n",
-    "!{sys.executable} -m pip install -U pandas-profiling[notebook]\n",
+    "!{sys.executable} -m pip install -U ydata-profiling[notebook]\n",
     "!pip install jupyter-contrib-nbextensions\n",
     "!jupyter nbextension enable --py widgetsnbextension"
    ]
@@ -120,7 +120,7 @@
    "id": "01519464",
    "metadata": {},
    "source": [
-    "The support to time series can be enabled by passing the parameter tsmode=True to the ProfileReport when its enabled, pandas profiling will try to identify time-dependent features using the feature's autocorrelation, which requires a sorted DataFrame or the definition of the `sortby` parameter.\n",
+    "The support to time series can be enabled by passing the parameter tsmode=True to the ProfileReport when its enabled, ydata-profiling will try to identify time-dependent features using the feature's autocorrelation, which requires a sorted DataFrame or the definition of the `sortby` parameter.\n",
     "\n",
     "When a feature is identified as time series will trigger the following changes:\n",
     "   - the histogram will be replaced by a line plot\n",
diff --git a/src/ydata_profiling/compare_reports.py b/src/ydata_profiling/compare_reports.py
@@ -105,7 +105,7 @@ def _placeholders(reports: List[BaseDescription]) -> None:
 def _update_titles(reports: List[ProfileReport]) -> None:
     """Redefine title of reports with the default one."""
     for idx, report in enumerate(reports):
-        if report.config.title == "Pandas Profiling Report":
+        if report.config.title == "YData Profiling Report":
             report.config.title = f"Dataset {chr(65 + idx)}"
 
 
diff --git a/src/ydata_profiling/config.py b/src/ydata_profiling/config.py
@@ -294,7 +294,7 @@ class Config:
         env_prefix = "profile_"
 
     # Title of the document
-    title: str = "Pandas Profiling Report"
+    title: str = "YData Profiling Report"
 
     dataset: Dataset = Dataset()
     variables: Variables = Variables()
diff --git a/src/ydata_profiling/controller/console.py b/src/ydata_profiling/controller/console.py
@@ -55,7 +55,7 @@ def parse_args(args: Optional[List[Any]] = None) -> argparse.Namespace:
     parser.add_argument(
         "--title",
         type=str,
-        default="Pandas Profiling Report",
+        default="YData Profiling Report",
         help="Title for the report",
     )
 
diff --git a/src/ydata_profiling/model/description.py b/src/ydata_profiling/model/description.py
@@ -90,7 +90,7 @@ class BaseDescription:
         correlations (Dict[str, Any]): Prepare correlation matrix for DataFrame
         missing (Dict[str, Any]): Describe missing values.
         alerts (Any): Take alerts from all modules (variables, scatter, correlations), and group them.
-        package (Dict[str, Any]): Contains version of pandas profiling and config.
+        package (Dict[str, Any]): Contains version of ydata-profiling and config.
         sample (Any): Sample of data.
         duplicates (Any): Description of duplicates.
     """
diff --git a/src/ydata_profiling/model/summarizer.py b/src/ydata_profiling/model/summarizer.py
@@ -44,7 +44,7 @@ def summarize(
 
 
 class PandasProfilingSummarizer(BaseSummarizer):
-    """The default Pandas Profiling summarizer"""
+    """The default YData Profiling summarizer"""
 
     def __init__(self, typeset: VisionsTypeset, *args, **kwargs):
         summary_map: Dict[str, List[Callable]] = {
diff --git a/tests/issues/test_issue353.py b/tests/issues/test_issue353.py
@@ -15,7 +15,7 @@ def test_issue353():
 
     profile = ProfileReport(
         df,
-        title="Pandas Profiling Report",
+        title="YData Profiling Report",
         html={"style": {"full_width": True}},
         progress_bar=False,
     )
diff --git a/tests/issues/test_issue416.py b/tests/issues/test_issue416.py
@@ -19,7 +19,7 @@ def test_issue416():
 
     profile = ydata_profiling.ProfileReport(
         df,
-        title="Pandas Profiling Report",
+        title="YData Profiling Report",
         html={"style": {"full_width": True}},
         explorative=True,
         progress_bar=False,
diff --git a/tests/issues/test_issue51.py b/tests/issues/test_issue51.py
@@ -18,10 +18,10 @@ def test_issue51(get_data_file):
     df = pd.read_pickle(str(file_name))
 
     report = ProfileReport(
-        df, title="Pandas Profiling Report", progress_bar=False, explorative=True
+        df, title="YData Profiling Report", progress_bar=False, explorative=True
     )
     assert (
-        "<title>Pandas Profiling Report</title>" in report.to_html()
+        "<title>YData Profiling Report</title>" in report.to_html()
     ), "Profile report should be generated."
 
 
@@ -35,13 +35,13 @@ def test_issue51_similar():
     )
 
     report = ProfileReport(
-        df, title="Pandas Profiling Report", progress_bar=False, explorative=True
+        df, title="YData Profiling Report", progress_bar=False, explorative=True
     )
     report.config.vars.num.low_categorical_threshold = 0
     # FIXME: assert correlation values (report.description_set["correlations"])
 
     assert (
-        "<title>Pandas Profiling Report</title>" in report.to_html()
+        "<title>YData Profiling Report</title>" in report.to_html()
     ), "Profile report should be generated."
 
 
@@ -56,7 +56,7 @@ def test_issue51_empty():
 
     report = ProfileReport(
         df,
-        title="Pandas Profiling Report",
+        title="YData Profiling Report",
         progress_bar=False,
         explorative=True,
     )
@@ -80,7 +80,7 @@ def test_issue51_identical():
     )
 
     report = ProfileReport(
-        df, title="Pandas Profiling Report", progress_bar=False, explorative=True
+        df, title="YData Profiling Report", progress_bar=False, explorative=True
     )
     report.config.vars.num.low_categorical_threshold = 0
     # this should not return any correlation value as the variables are identical constants
diff --git a/tests/issues/test_issue664.py b/tests/issues/test_issue664.py
@@ -14,7 +14,7 @@ def test_issue664():
     df = df.fillna(value=np.nan)
 
     profile = ProfileReport(
-        df, title="Pandas Profiling Report", explorative=True, minimal=True
+        df, title="YData Profiling Report", explorative=True, minimal=True
     )
     _ = profile.get_description()
 
diff --git a/tests/issues/test_issue94.py b/tests/issues/test_issue94.py
@@ -28,5 +28,5 @@ def test_issue94(tmpdir):
 CHEM"""
     )
     df = pd.read_csv(str(file_path), parse_dates=True)
-    profile = ydata_profiling.ProfileReport(df, title="Pandas Profiling Report")
-    assert "<title>Pandas Profiling Report</title>" in profile.to_html()
+    profile = ydata_profiling.ProfileReport(df, title="YData Profiling Report")
+    assert "<title>YData Profiling Report</title>" in profile.to_html()

Original file line number	Diff line number	Diff line change
`@@ -4,7 +4,7 @@`
`4`	`4`	`"cell_type": "markdown",`
`5`	`5`	`"metadata": {},`
`6`	`6`	`"source": [`
`7`		`- "## Pandas Profiling: NASA Meteorites example\n",`
	`7`	`+ "## YData Profiling: NASA Meteorites example\n",`
`8`	`8`	`"Source of data: https://data.nasa.gov/Space-Science/Meteorite-Landings/gh4g-9sfh"`
`9`	`9`	`]`
`10`	`10`	`},`