rename examples

portellaa · portellaa · commit b09352d301d9 · 2026-04-16T17:17:28.000+01:00
diff --git a/.github/ISSUE_TEMPLATE/bug_report_form.yaml b/.github/ISSUE_TEMPLATE/bug_report_form.yaml
@@ -41,7 +41,7 @@ body:
       description: A minimal standalone code sample that reproduces the bug
       placeholder: |
         import pandas as pd
-        from ydata_profiling import ProfileReport
+        from data_profiling import ProfileReport
 
         df = pd.read_parquet(r"<file>")
         report = ProfileReport(df, title="bug report")
diff --git a/MANIFEST.in b/MANIFEST.in
@@ -6,10 +6,10 @@ include LICENSE
 include *.md
 
 # Templates and static resources
-recursive-include src/ydata_profiling/report/presentation/flavours/html/templates *.html *.js *.css
+recursive-include src/data_profiling/report/presentation/flavours/html/templates *.html *.js *.css
 
 # Configuration
-include src/ydata_profiling/*.yaml
+include src/data_profiling/*.yaml
 
 # Spark Dev venv
 recursive-include venv *.yml
diff --git a/Makefile b/Makefile
@@ -7,17 +7,17 @@ test:
 	pytest tests/unit/
 	pytest tests/issues/
 	pytest --nbval tests/notebooks/
-	ydata_profiling -h
+	data_profiling -h
 
 test_spark:
 	pytest tests/backends/spark_backend/
-	ydata_profiling -h
+	data_profiling -h
 
 test_cov:
 	pytest --cov=. tests/unit/
 	pytest --cov=. --cov-append tests/issues/
 	pytest --cov=. --cov-append --nbval tests/notebooks/
-	ydata_profiling -h
+	data_profiling -h
 
 examples:
 	find ./examples -maxdepth 2 -type f -name "*.py" -execdir python {} \;
diff --git a/README.md b/README.md
@@ -50,7 +50,7 @@ Start by loading your pandas `DataFrame` as you normally would, e.g. by using:
 ```python
 import numpy as np
 import pandas as pd
-from ydata_profiling import ProfileReport
+from data_profiling import ProfileReport
 
 df = pd.DataFrame(np.random.rand(100, 5), columns=["a", "b", "c", "d", "e"])
 ```
@@ -142,10 +142,10 @@ profile.to_file("your_report.json")
 
 ### Using in the command line
 
-For standard formatted CSV files (which can be read directly by pandas without additional settings), the `ydata_profiling` executable can be used in the command line. The example below generates a report named *Example Profiling Report*, using a configuration file called `default.yaml`, in the file `report.html` by processing a `data.csv` dataset.
+For standard formatted CSV files (which can be read directly by pandas without additional settings), the `data_profiling` executable can be used in the command line. The example below generates a report named *Example Profiling Report*, using a configuration file called `default.yaml`, in the file `report.html` by processing a `data.csv` dataset.
 
 ```sh
-ydata_profiling --title "Example Profiling Report" --config_file default.yaml data.csv report.html
+data_profiling --title "Example Profiling Report" --config_file default.yaml data.csv report.html
 ```
 
 Additional details on the CLI are available [on the documentation](https://data-profiling.ydata.ai/docs/master/pages/getting_started/quickstart.html#command-line-usage).
diff --git a/examples/bank_marketing_data/banking_data.py b/examples/bank_marketing_data/banking_data.py
@@ -4,8 +4,8 @@
 
 import pandas as pd
 
-from ydata_profiling import ProfileReport
-from ydata_profiling.utils.cache import cache_zipped_file
+from data_profiling import ProfileReport
+from data_profiling.utils.cache import cache_zipped_file
 
 if __name__ == "__main__":
     file_name = cache_zipped_file(
diff --git a/examples/census/census.py b/examples/census/census.py
@@ -4,9 +4,9 @@
 import numpy as np
 import pandas as pd
 
-from ydata_profiling import ProfileReport
-from ydata_profiling.config import Dataset
-from ydata_profiling.utils.cache import cache_file
+from data_profiling import ProfileReport
+from data_profiling.config import Dataset
+from data_profiling.utils.cache import cache_file
 
 if __name__ == "__main__":
     file_name = cache_file(
diff --git a/examples/chicago_employees/chicago_employees.py b/examples/chicago_employees/chicago_employees.py
@@ -2,8 +2,8 @@
 
 import pandas as pd
 
-from ydata_profiling import ProfileReport
-from ydata_profiling.utils.cache import cache_file
+from data_profiling import ProfileReport
+from data_profiling.utils.cache import cache_file
 
 if __name__ == "__main__":
     file_name = cache_file(
diff --git a/examples/colors/colors.py b/examples/colors/colors.py
@@ -2,8 +2,8 @@
 
 import pandas as pd
 
-from ydata_profiling import ProfileReport
-from ydata_profiling.utils.cache import cache_file
+from data_profiling import ProfileReport
+from data_profiling.utils.cache import cache_file
 
 if __name__ == "__main__":
     file_name = cache_file(
diff --git a/examples/features/correlation_auto_example.py b/examples/features/correlation_auto_example.py
@@ -2,8 +2,8 @@
 
 import pandas as pd
 
-from ydata_profiling import ProfileReport
-from ydata_profiling.utils.cache import cache_zipped_file
+from data_profiling import ProfileReport
+from data_profiling.utils.cache import cache_zipped_file
 
 """
 The "Auto" correlation is an interpretable pairwise column metric of the following mapping:
diff --git a/examples/features/correlation_demo.py b/examples/features/correlation_demo.py
@@ -2,8 +2,8 @@
 
 import pandas as pd
 
-from ydata_profiling import ProfileReport
-from ydata_profiling.utils.cache import cache_zipped_file
+from data_profiling import ProfileReport
+from data_profiling.utils.cache import cache_zipped_file
 
 """
 The "Auto" correlation is an interpretable pairwise column metric of the following mapping:
diff --git a/examples/features/eda_dataset_compare.py b/examples/features/eda_dataset_compare.py
@@ -1,7 +1,7 @@
 import pandas as pd
 
-from ydata_profiling import ProfileReport
-from ydata_profiling.utils.cache import cache_file
+from data_profiling import ProfileReport
+from data_profiling.utils.cache import cache_file
 
 if __name__ == "__main__":
     # Read the Titanic Dataset
diff --git a/examples/features/images_cats_and_dogs.py b/examples/features/images_cats_and_dogs.py
@@ -1,8 +1,8 @@
 import kaggle
 import pandas as pd
 
-from ydata_profiling import ProfileReport
-from ydata_profiling.utils.paths import get_data_path
+from data_profiling import ProfileReport
+from data_profiling.utils.paths import get_data_path
 
 # The dataset in this example is obtained using the `kaggle` api.
 # If you haven't done so already, you should set up the api credentials:
diff --git a/examples/features/images_exif.py b/examples/features/images_exif.py
@@ -1,8 +1,8 @@
 import kaggle
 import pandas as pd
 
-from ydata_profiling import ProfileReport
-from ydata_profiling.utils.paths import get_data_path
+from data_profiling import ProfileReport
+from data_profiling.utils.paths import get_data_path
 
 # The dataset in this example is obtained using the `kaggle` api.
 # If you haven't done so already, you should set up the api credentials:
diff --git a/examples/features/mask_sensitive.py b/examples/features/mask_sensitive.py
@@ -2,8 +2,8 @@
 
 import pandas as pd
 
-from ydata_profiling import ProfileReport
-from ydata_profiling.utils.cache import cache_file
+from data_profiling import ProfileReport
+from data_profiling.utils.cache import cache_file
 
 if __name__ == "__main__":
     file_name = cache_file("auto2.dta", "http://www.stata-press.com/data/r15/auto2.dta")
diff --git a/examples/features/russian_vocabulary.py b/examples/features/russian_vocabulary.py
@@ -2,7 +2,7 @@
 
 import pandas as pd
 
-from ydata_profiling import ProfileReport
+from data_profiling import ProfileReport
 
 if __name__ == "__main__":
     df = pd.read_csv(
diff --git a/examples/features/spark_example.py b/examples/features/spark_example.py
@@ -7,8 +7,8 @@
 from matplotlib import MatplotlibDeprecationWarning
 from pyspark.sql import SparkSession
 
-from ydata_profiling import ProfileReport
-from ydata_profiling.config import Settings
+from data_profiling import ProfileReport
+from data_profiling.config import Settings
 
 logging.basicConfig(level=logging.INFO)
 
diff --git a/examples/features/theme_flatly_demo.py b/examples/features/theme_flatly_demo.py
@@ -2,8 +2,8 @@
 
 import pandas as pd
 
-from ydata_profiling import ProfileReport
-from ydata_profiling.utils.cache import cache_file
+from data_profiling import ProfileReport
+from data_profiling.utils.cache import cache_file
 
 if __name__ == "__main__":
     file_name = cache_file(
diff --git a/examples/features/theme_united_demo.py b/examples/features/theme_united_demo.py
@@ -2,8 +2,8 @@
 
 import pandas as pd
 
-from ydata_profiling import ProfileReport
-from ydata_profiling.utils.cache import cache_file
+from data_profiling import ProfileReport
+from data_profiling.utils.cache import cache_file
 
 if __name__ == "__main__":
     file_name = cache_file(
diff --git a/examples/features/urls.py b/examples/features/urls.py
@@ -2,8 +2,8 @@
 
 import pandas as pd
 
-from ydata_profiling import ProfileReport
-from ydata_profiling.utils.cache import cache_file
+from data_profiling import ProfileReport
+from data_profiling.utils.cache import cache_file
 
 if __name__ == "__main__":
     file_name = cache_file(
diff --git a/examples/hcc/eda-with-feature-comparison.ipynb b/examples/hcc/eda-with-feature-comparison.ipynb
@@ -25,7 +25,7 @@
    "source": [
     "import pandas as pd\n",
     "\n",
-    "from ydata_profiling import ProfileReport"
+    "from data_profiling import ProfileReport"
    ]
   },
   {
diff --git a/examples/hcc/eda-with-feature-comparison.py b/examples/hcc/eda-with-feature-comparison.py
@@ -4,7 +4,7 @@
 import pandas as pd
 from sklearn.impute import SimpleImputer
 
-from ydata_profiling import ProfileReport
+from data_profiling import ProfileReport
 
 if __name__ == "__main__":
 
diff --git a/examples/integrations/databricks/ydata-profiling in Databricks.ipynb b/examples/integrations/databricks/ydata-profiling in Databricks.ipynb
@@ -98,7 +98,7 @@
    },
    "outputs": [],
    "source": [
-    "from ydata_profiling import ProfileReport\n",
+    "from data_profiling import ProfileReport\n",
     "\n",
     "report = ProfileReport(\n",
     "    df,\n",
diff --git a/examples/integrations/great_expectations/great_expectations_example.py b/examples/integrations/great_expectations/great_expectations_example.py
@@ -1,8 +1,8 @@
 import great_expectations as ge
 import pandas as pd
 
-from ydata_profiling import ProfileReport
-from ydata_profiling.utils.cache import cache_file
+from data_profiling import ProfileReport
+from data_profiling.utils.cache import cache_file
 
 file_name = cache_file(
     "titanic.csv",
diff --git a/examples/meteorites/meteorites.ipynb b/examples/meteorites/meteorites.ipynb
@@ -72,7 +72,7 @@
     "import requests\n",
     "\n",
     "import ydata_profiling\n",
-    "from ydata_profiling.utils.cache import cache_file"
+    "from data_profiling.utils.cache import cache_file"
    ]
   },
   {
diff --git a/examples/meteorites/meteorites.py b/examples/meteorites/meteorites.py
@@ -3,8 +3,8 @@
 import numpy as np
 import pandas as pd
 
-from ydata_profiling import ProfileReport
-from ydata_profiling.utils.cache import cache_file
+from data_profiling import ProfileReport
+from data_profiling.utils.cache import cache_file
 
 if __name__ == "__main__":
     file_name = cache_file(
diff --git a/examples/meteorites/meteorites_cloud.ipynb b/examples/meteorites/meteorites_cloud.ipynb
@@ -41,7 +41,7 @@
     "import pandas as pd\n",
     "\n",
     "import ydata_profiling\n",
-    "from ydata_profiling.utils.cache import cache_file"
+    "from data_profiling.utils.cache import cache_file"
    ]
   },
   {
diff --git a/examples/musical_instrument_reviews/review.py b/examples/musical_instrument_reviews/review.py
@@ -2,8 +2,8 @@
 
 import pandas as pd
 
-from ydata_profiling import ProfileReport
-from ydata_profiling.utils.cache import cache_file
+from data_profiling import ProfileReport
+from data_profiling.utils.cache import cache_file
 
 if __name__ == "__main__":
     file_name = cache_file(
diff --git a/examples/nza/nza.py b/examples/nza/nza.py
@@ -2,8 +2,8 @@
 
 import pandas as pd
 
-from ydata_profiling import ProfileReport
-from ydata_profiling.utils.cache import cache_file
+from data_profiling import ProfileReport
+from data_profiling.utils.cache import cache_file
 
 if __name__ == "__main__":
     file_name = cache_file(
diff --git a/examples/rdw/rdw.py b/examples/rdw/rdw.py
@@ -1,7 +1,7 @@
 import pandas as pd
 
-from ydata_profiling import ProfileReport
-from ydata_profiling.utils.cache import cache_file
+from data_profiling import ProfileReport
+from data_profiling.utils.cache import cache_file
 
 if __name__ == "__main__":
     file_name = cache_file(
diff --git a/examples/stata_auto/stata_auto.py b/examples/stata_auto/stata_auto.py
@@ -2,8 +2,8 @@
 
 import pandas as pd
 
-from ydata_profiling import ProfileReport
-from ydata_profiling.utils.cache import cache_file
+from data_profiling import ProfileReport
+from data_profiling.utils.cache import cache_file
 
 if __name__ == "__main__":
     file_name = cache_file("auto2.dta", "http://www.stata-press.com/data/r15/auto2.dta")
diff --git a/examples/titanic/titanic.ipynb b/examples/titanic/titanic.ipynb
@@ -58,8 +58,8 @@
     "from ipywidgets import widgets\n",
     "\n",
     "# Our package\n",
-    "from ydata_profiling import ProfileReport\n",
-    "from ydata_profiling.utils.cache import cache_file"
+    "from data_profiling import ProfileReport\n",
+    "from data_profiling.utils.cache import cache_file"
    ]
   },
   {
diff --git a/examples/titanic/titanic.py b/examples/titanic/titanic.py
@@ -1,7 +1,7 @@
 import pandas as pd
 
-from ydata_profiling import ProfileReport
-from ydata_profiling.utils.cache import cache_file
+from data_profiling import ProfileReport
+from data_profiling.utils.cache import cache_file
 
 if __name__ == "__main__":
     file_name = cache_file(
diff --git a/examples/titanic/titanic_cloud.ipynb b/examples/titanic/titanic_cloud.ipynb
@@ -29,8 +29,8 @@
     "import pandas as pd\n",
     "\n",
     "# Our package\n",
-    "from ydata_profiling import ProfileReport\n",
-    "from ydata_profiling.utils.cache import cache_file"
+    "from data_profiling import ProfileReport\n",
+    "from data_profiling.utils.cache import cache_file"
    ]
   },
   {
diff --git a/examples/usaairquality/usaairquality.ipynb b/examples/usaairquality/usaairquality.ipynb
@@ -76,8 +76,8 @@
    "source": [
     "import pandas as pd\n",
     "\n",
-    "from ydata_profiling import ProfileReport\n",
-    "from ydata_profiling.utils.cache import cache_file"
+    "from data_profiling import ProfileReport\n",
+    "from data_profiling.utils.cache import cache_file"
    ]
   },
   {
@@ -145,7 +145,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from ydata_profiling.visualisation.plot import timeseries_heatmap\n",
+    "from data_profiling.visualisation.plot import timeseries_heatmap\n",
     "\n",
     "timeseries_heatmap(dataframe=df, entity_column=\"Site Num\", sortby=\"Date Local\")"
    ]
diff --git a/examples/usaairquality/usaairquality.py b/examples/usaairquality/usaairquality.py
diff --git a/examples/vektis/vektis.py b/examples/vektis/vektis.py
diff --git a/pyproject.toml b/pyproject.toml
diff --git a/src/pandas_profiling/__init__.py b/src/pandas_profiling/__init__.py
