PyPI - EDAeasy - Versions diffs - 1.0.0__tar.gz - Mend

EDAeasy 1.0.0__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (15) hide show

EDAeasy-1.0.0/LICENSE +21 -0
EDAeasy-1.0.0/MANIFEST.in +1 -0
EDAeasy-1.0.0/PKG-INFO +86 -0
EDAeasy-1.0.0/README.md +51 -0
EDAeasy-1.0.0/pyproject.toml +53 -0
EDAeasy-1.0.0/setup.cfg +4 -0
EDAeasy-1.0.0/src/EDAeasy/__init__.py +6 -0
EDAeasy-1.0.0/src/EDAeasy/config.toml +0 -0
EDAeasy-1.0.0/src/EDAeasy/functions.py +78 -0
EDAeasy-1.0.0/src/EDAeasy.egg-info/PKG-INFO +86 -0
EDAeasy-1.0.0/src/EDAeasy.egg-info/SOURCES.txt +13 -0
EDAeasy-1.0.0/src/EDAeasy.egg-info/dependency_links.txt +1 -0
EDAeasy-1.0.0/src/EDAeasy.egg-info/requires.txt +13 -0
EDAeasy-1.0.0/src/EDAeasy.egg-info/top_level.txt +1 -0
EDAeasy-1.0.0/test/test_functions.py +77 -0

EDAeasy-1.0.0/LICENSE ADDED Viewed

@@ -0,0 +1,21 @@
+MIT License
+Copyright (c) [year] [fullname]
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

EDAeasy-1.0.0/MANIFEST.in ADDED Viewed

	@@ -0,0 +1 @@
1	+ include src/EDAeasy/*.toml

EDAeasy-1.0.0/PKG-INFO ADDED Viewed

@@ -0,0 +1,86 @@
+Metadata-Version: 2.1
+Name: EDAeasy
+Version: 1.0.0
+Summary: Functions and tools for making Exploratory Data Analysis easy!
+Author-email: Francisco Ocazionez-Cardozo <focazionez@gmail.com>
+License: MIT License
+        Copyright (c) [year] [fullname]
+        Permission is hereby granted, free of charge, to any person obtaining a copy
+        of this software and associated documentation files (the "Software"), to deal
+        in the Software without restriction, including without limitation the rights
+        to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+        copies of the Software, and to permit persons to whom the Software is
+        furnished to do so, subject to the following conditions:
+        The above copyright notice and this permission notice shall be included in all
+        copies or substantial portions of the Software.
+        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+        IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+        FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+        AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+        LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+        OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+        SOFTWARE.
+Keywords: Exploratory Data Analysis,EDA,Data
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 3
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+Provides-Extra: dev
+License-File: LICENSE
+# EDAeasy 😀
+The package for quick exploratory data analysis
+## Instalation
+`pip install EDAeasy`
+## Usage
+The **dataframe_summary** function have relative simple summary of the columns of your dataframe
+for quick look at tabular data
+    Generate a summary DataFrame of the input DataFrame 'dataframe'.
+    Parameters
+    ----------
+    dataframe : pandas.DataFrame
+        The input DataFrame for which the summary needs to be generated.
+    Returns
+    -------
+    pandas.DataFrame
+        A DataFrame containing summary information for each column in 'df':
+        - Type: Data type of the column.
+        - Min: Minimum value in the column.
+        - Max: Maximum value in the column.
+        - Nan %: Percentage of NaN values in the column.
+        - # Unique Values: Total number of unique values in the column.
+        - Unique values: List of unique values in the column.
+    Example
+    -------
+    >>> data = {
+            'age': ['[40-50)', '[60-70)', '[70-80)'],
+            'time_in_hospital': [8, 3, 5],
+            'n_lab_procedures': [72, 34, 45],
+            ...
+        }
+    >>> dataframe = pd.DataFrame(data)
+    >>> result = dataframe_summary(df)
+    >>> print(result)
+               Type       Min        Max  Nan %  # Unique Values                                  Unique values
+    Variables
+    age       object   [40-50)    [90-100)    0.0        3      ['[70-80)', '[50-60)', '[60-70)', '[40-50)', '[80-90)', ...
+    time_in_hospital  int64    1           14    0.0        3        [8, 3, 5]
+    n_lab_procedures  int64    1          113    0.0        3        [72, 34, 45]
+    ...
+    Note
+    ----
+    The function uses vectorized operations to improve performance and memory usage.

EDAeasy-1.0.0/README.md ADDED Viewed

@@ -0,0 +1,51 @@
+# EDAeasy 😀
+The package for quick exploratory data analysis
+## Instalation
+`pip install EDAeasy`
+## Usage
+The **dataframe_summary** function have relative simple summary of the columns of your dataframe
+for quick look at tabular data
+    Generate a summary DataFrame of the input DataFrame 'dataframe'.
+    Parameters
+    ----------
+    dataframe : pandas.DataFrame
+        The input DataFrame for which the summary needs to be generated.
+    Returns
+    -------
+    pandas.DataFrame
+        A DataFrame containing summary information for each column in 'df':
+        - Type: Data type of the column.
+        - Min: Minimum value in the column.
+        - Max: Maximum value in the column.
+        - Nan %: Percentage of NaN values in the column.
+        - # Unique Values: Total number of unique values in the column.
+        - Unique values: List of unique values in the column.
+    Example
+    -------
+    >>> data = {
+            'age': ['[40-50)', '[60-70)', '[70-80)'],
+            'time_in_hospital': [8, 3, 5],
+            'n_lab_procedures': [72, 34, 45],
+            ...
+        }
+    >>> dataframe = pd.DataFrame(data)
+    >>> result = dataframe_summary(df)
+    >>> print(result)
+               Type       Min        Max  Nan %  # Unique Values                                  Unique values
+    Variables
+    age       object   [40-50)    [90-100)    0.0        3      ['[70-80)', '[50-60)', '[60-70)', '[40-50)', '[80-90)', ...
+    time_in_hospital  int64    1           14    0.0        3        [8, 3, 5]
+    n_lab_procedures  int64    1          113    0.0        3        [72, 34, 45]
+    ...
+    Note
+    ----
+    The function uses vectorized operations to improve performance and memory usage.

EDAeasy-1.0.0/pyproject.toml ADDED Viewed

@@ -0,0 +1,53 @@
+#config
+[built-system]
+requires = ["setuptools>=65.5.0","wheel"]
+build-backend = "setuptools.build_meta"
+[project]
+name = "EDAeasy"
+version = "1.0.0"
+description = "Functions and tools for making Exploratory Data Analysis easy!"
+readme = "README.md"
+authors = [{ name = "Francisco Ocazionez-Cardozo", email = "focazionez@gmail.com" }]
+license = { file = "LICENSE" }
+classifiers = [
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python",
+    "Programming Language :: Python :: 3",
+]
+keywords = ["Exploratory Data Analysis", "EDA", "Data"]
+dependencies = [
+    'numpy>=1.25.1',
+    'pandas>=2.0.3',
+    'python-dateutil>=2.8.2',
+    'pytz>=2023.3',
+    'six>=1.16.0',
+    'tzdata>=2023.3',
+]
+requires-python = ">=3.10"
+[project.optional-dependencies]
+dev = ["black", "bumpver", "isort", "pip-tools", "pytest"]
+[tool.bumpver]
+current_version = "1.0.0"
+version_pattern = "MAYOR.MINOR.PATCH"
+commit_message = "bump version {old_version} -> {new_version}"
+tag_message = "{new_version}"
+tag_scope = "default"
+commit = true
+tag = true
+push = true
+[tool.bumpver.file_patterns]
+"pyproject.toml" = [
+    'current_version = "{version}"',
+]
+"README.md" = [
+    "{version}",
+    "{pep440_version}",
+]
+"src/EDAeasy/__init__.py" = [
+    "{version}"
+]

EDAeasy-1.0.0/setup.cfg ADDED Viewed

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build =
+tag_date = 0

EDAeasy-1.0.0/src/EDAeasy/__init__.py ADDED Viewed

@@ -0,0 +1,6 @@
+# Version
+__version__ = '1.0.0'
+# Importing
+from .functions import *

EDAeasy-1.0.0/src/EDAeasy/config.toml ADDED Viewed

File without changes

EDAeasy-1.0.0/src/EDAeasy/functions.py ADDED Viewed

@@ -0,0 +1,78 @@
+import pandas as pd
+def dataframe_summary(dataframe: pd.DataFrame):
+    """Generate a summary DataFrame of the input DataFrame 'dataframe'.
+    Parameters
+    ----------
+    dataframe : pandas.DataFrame
+        The input DataFrame for which the summary needs to be generated.
+    Returns
+    -------
+    pandas.DataFrame
+        A DataFrame containing summary information for each column in 'df':
+        - Type: Data type of the column.
+        - Min: Minimum value in the column.
+        - Max: Maximum value in the column.
+        - Nan %: Percentage of NaN values in the column.
+        - # Unique Values: Total number of unique values in the column.
+        - Unique values: List of unique values in the column.
+    Example
+    -------
+    >>> data = {
+            'age': ['[40-50)', '[60-70)', '[70-80)'],
+            'time_in_hospital': [8, 3, 5],
+            'n_lab_procedures': [72, 34, 45],
+            ...
+        }
+    >>> dataframe = pd.DataFrame(data)
+    >>> result = dataframe_summary(df)
+    >>> print(result)
+               Type       Min        Max  Nan %  # Unique Values                                  Unique values
+    Variables
+    age       object   [40-50)    [90-100)    0.0        3      ['[70-80)', '[50-60)', '[60-70)', '[40-50)', '[80-90)', ...
+    time_in_hospital  int64    1           14    0.0        3        [8, 3, 5]
+    n_lab_procedures  int64    1          113    0.0        3        [72, 34, 45]
+    ...
+    Note
+    ----
+    The function uses vectorized operations to improve performance and memory usage.
+    """
+    ret = pd.DataFrame(columns=['Type', 'Min', 'Max', 'Nan %', '# Unique Values', 'Unique values'])
+    for col, content in dataframe.items():
+        values = []
+        dtype = content.dtype
+        # Convert 'object' columns to appropriate data types
+        if dtype == 'object':
+            if col in ['Min', 'Max', 'Type']:
+                # Clean and convert 'Min', 'Max', and 'Type' columns to strings
+                content = content.astype(str)
+        values.append(content.dtype)  # Data type after conversion
+        try:
+            values.append(content.min())  # Min
+            values.append(content.max())  # Max
+        except Exception:
+            values.append('None')
+            values.append('None')
+        values.append(content.isnull().mean() * 100)  # % of NaN's
+        # Calculate the number of unique values in the column
+        num_unique_values = len(content.drop_duplicates())
+        values.append(num_unique_values)  # Number of unique values
+        # Handle the 'Unique values' column as a list of strings
+        unique_values = content.drop_duplicates().astype(str).tolist()
+        unique_values.sort()
+        values.append(unique_values)
+        ret.loc[col] = values
+    ret.index.names = ['Variables']
+    rows = dataframe.shape[0]
+    columns = dataframe.shape[1]
+    return ret, (rows, columns)

EDAeasy-1.0.0/src/EDAeasy.egg-info/PKG-INFO ADDED Viewed

@@ -0,0 +1,86 @@
+Metadata-Version: 2.1
+Name: EDAeasy
+Version: 1.0.0
+Summary: Functions and tools for making Exploratory Data Analysis easy!
+Author-email: Francisco Ocazionez-Cardozo <focazionez@gmail.com>
+License: MIT License
+        Copyright (c) [year] [fullname]
+        Permission is hereby granted, free of charge, to any person obtaining a copy
+        of this software and associated documentation files (the "Software"), to deal
+        in the Software without restriction, including without limitation the rights
+        to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+        copies of the Software, and to permit persons to whom the Software is
+        furnished to do so, subject to the following conditions:
+        The above copyright notice and this permission notice shall be included in all
+        copies or substantial portions of the Software.
+        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+        IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+        FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+        AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+        LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+        OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+        SOFTWARE.
+Keywords: Exploratory Data Analysis,EDA,Data
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 3
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+Provides-Extra: dev
+License-File: LICENSE
+# EDAeasy 😀
+The package for quick exploratory data analysis
+## Instalation
+`pip install EDAeasy`
+## Usage
+The **dataframe_summary** function have relative simple summary of the columns of your dataframe
+for quick look at tabular data
+    Generate a summary DataFrame of the input DataFrame 'dataframe'.
+    Parameters
+    ----------
+    dataframe : pandas.DataFrame
+        The input DataFrame for which the summary needs to be generated.
+    Returns
+    -------
+    pandas.DataFrame
+        A DataFrame containing summary information for each column in 'df':
+        - Type: Data type of the column.
+        - Min: Minimum value in the column.
+        - Max: Maximum value in the column.
+        - Nan %: Percentage of NaN values in the column.
+        - # Unique Values: Total number of unique values in the column.
+        - Unique values: List of unique values in the column.
+    Example
+    -------
+    >>> data = {
+            'age': ['[40-50)', '[60-70)', '[70-80)'],
+            'time_in_hospital': [8, 3, 5],
+            'n_lab_procedures': [72, 34, 45],
+            ...
+        }
+    >>> dataframe = pd.DataFrame(data)
+    >>> result = dataframe_summary(df)
+    >>> print(result)
+               Type       Min        Max  Nan %  # Unique Values                                  Unique values
+    Variables
+    age       object   [40-50)    [90-100)    0.0        3      ['[70-80)', '[50-60)', '[60-70)', '[40-50)', '[80-90)', ...
+    time_in_hospital  int64    1           14    0.0        3        [8, 3, 5]
+    n_lab_procedures  int64    1          113    0.0        3        [72, 34, 45]
+    ...
+    Note
+    ----
+    The function uses vectorized operations to improve performance and memory usage.

EDAeasy-1.0.0/src/EDAeasy.egg-info/SOURCES.txt ADDED Viewed

@@ -0,0 +1,13 @@
+LICENSE
+MANIFEST.in
+README.md
+pyproject.toml
+src/EDAeasy/__init__.py
+src/EDAeasy/config.toml
+src/EDAeasy/functions.py
+src/EDAeasy.egg-info/PKG-INFO
+src/EDAeasy.egg-info/SOURCES.txt
+src/EDAeasy.egg-info/dependency_links.txt
+src/EDAeasy.egg-info/requires.txt
+src/EDAeasy.egg-info/top_level.txt
+test/test_functions.py

EDAeasy-1.0.0/src/EDAeasy.egg-info/dependency_links.txt ADDED Viewed

	@@ -0,0 +1 @@
1	+

EDAeasy-1.0.0/src/EDAeasy.egg-info/requires.txt ADDED Viewed

@@ -0,0 +1,13 @@
+numpy>=1.25.1
+pandas>=2.0.3
+python-dateutil>=2.8.2
+pytz>=2023.3
+six>=1.16.0
+tzdata>=2023.3
+[dev]
+black
+bumpver
+isort
+pip-tools
+pytest

EDAeasy-1.0.0/src/EDAeasy.egg-info/top_level.txt ADDED Viewed

	@@ -0,0 +1 @@
1	+ EDAeasy

EDAeasy-1.0.0/test/test_functions.py ADDED Viewed

@@ -0,0 +1,77 @@
+from EDAeasy import dataframe_summary
+import pandas as pd
+def test_dataframe_summary():
+    # Test Case 1: Basic test case with different data types
+    data = {
+        'age': ['[40-50)', '[60-70)', '[70-80)'],
+        'time_in_hospital': [8, 3, 5],
+        'n_lab_procedures': [72, 34, 45],
+        'weight': [65.5, 70.2, None],
+        'is_diabetic': [True, False, True],
+    }
+    dataframe = pd.DataFrame(data)
+    result, (rows, columns) = dataframe_summary(dataframe)
+    assert rows == 3
+    assert columns == 5
+    assert result.loc['age', 'Type'] == 'object'
+    assert result.loc['time_in_hospital', 'Type'] == 'int64'
+    assert result.loc['n_lab_procedures', 'Type'] == 'int64'
+    assert result.loc['weight', 'Type'] == 'float64'
+    assert result.loc['is_diabetic', 'Type'] == 'bool'
+    assert result.loc['age', 'Min'] == '[40-50)'
+    assert result.loc['age', 'Max'] == '[70-80)'
+    assert result.loc['time_in_hospital', 'Min'] == 3
+    assert result.loc['time_in_hospital', 'Max'] == 8
+    assert result.loc['n_lab_procedures', 'Min'] == 34
+    assert result.loc['n_lab_procedures', 'Max'] == 72
+    assert result.loc['weight', 'Min'] == 65.5
+    assert result.loc['weight', 'Max'] == 70.2
+    assert result.loc['is_diabetic', 'Min'] == False
+    assert result.loc['is_diabetic', 'Max'] == True
+    assert result.loc['age', 'Nan %'] == 0.0
+    assert result.loc['time_in_hospital', 'Nan %'] == 0.0
+    assert result.loc['n_lab_procedures', 'Nan %'] == 0.0
+    assert result.loc['weight', 'Nan %'] == 33.33333333333333
+    assert result.loc['is_diabetic', 'Nan %'] == 0.0
+    assert result.loc['age', '# Unique Values'] == 3
+    assert result.loc['time_in_hospital', '# Unique Values'] == 3
+    assert result.loc['n_lab_procedures', '# Unique Values'] == 3
+    assert result.loc['weight', '# Unique Values'] == 3
+    assert result.loc['is_diabetic', '# Unique Values'] == 2
+    assert result.loc['age', 'Unique values'] == ['[40-50)', '[60-70)', '[70-80)']
+    assert result.loc['time_in_hospital', 'Unique values'] == ['3','5','8']
+    assert result.loc['n_lab_procedures', 'Unique values'] == ['34', '45', '72']
+    assert result.loc['weight', 'Unique values'] == ['65.5', '70.2', 'nan']
+    assert result.loc['is_diabetic', 'Unique values'] == ['False', 'True']
+    # Test Case 2: Test with an empty DataFrame
+    data = {
+        'A': [],
+        'B': [],
+        'C': [],
+    }
+    dataframe = pd.DataFrame(data)
+    result, (rows, columns) = dataframe_summary(dataframe)
+    assert rows == 0
+    assert columns == 3
+    assert not result.empty
+    # Test Case 3: Test with all NaN values in a column
+    data = {
+        'X': [None, None, None],
+        'Y': [1, 2, 3],
+    }
+    dataframe = pd.DataFrame(data)
+    result, (rows, columns) = dataframe_summary(dataframe)
+    assert rows == 3
+    assert columns == 2
+    assert result.loc['X', 'Nan %'] == 100.0
+    assert result.loc['Y', 'Nan %'] == 0.0
+    # Add more test cases as needed
+    print("All test cases passed!")
+# Run the test function
+test_dataframe_summary()