EDAeasy 1.0.0__py3-none-any.whl

EDAeasy/__init__.py

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

EDAeasy/functions.py

@@ -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.dist-info/LICENSE

@@ -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.dist-info/METADATA

@@ -0,0 +1,97 @@
+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
+License-File: LICENSE
+Requires-Dist: numpy (>=1.25.1)
+Requires-Dist: pandas (>=2.0.3)
+Requires-Dist: python-dateutil (>=2.8.2)
+Requires-Dist: pytz (>=2023.3)
+Requires-Dist: six (>=1.16.0)
+Requires-Dist: tzdata (>=2023.3)
+Provides-Extra: dev
+Requires-Dist: black ; extra == 'dev'
+Requires-Dist: bumpver ; extra == 'dev'
+Requires-Dist: isort ; extra == 'dev'
+Requires-Dist: pip-tools ; extra == 'dev'
+Requires-Dist: pytest ; extra == 'dev'
+
+# 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.dist-info/RECORD

@@ -0,0 +1,8 @@
+EDAeasy/__init__.py,sha256=ZUIgIq7T10orfqVP0um6YTOE5_-Vmc1UlofgP3NYTl0,71
+EDAeasy/config.toml,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+EDAeasy/functions.py,sha256=TbsWanvNGTvvVpLLSKzSkiClyRnq60MBIHcm8C_0gD8,3022
+EDAeasy-1.0.0.dist-info/LICENSE,sha256=pAZXnNE2dxxwXFIduGyn1gpvPefJtUYOYZOi3yeGG94,1068
+EDAeasy-1.0.0.dist-info/METADATA,sha256=11Y1KYGvpIifb87JxfPDO-uasQXBucEyE1FFgnnCprY,3951
+EDAeasy-1.0.0.dist-info/WHEEL,sha256=AtBG6SXL3KF_v0NxLf0ehyVOh0cold-JbJYXNGorC6Q,92
+EDAeasy-1.0.0.dist-info/top_level.txt,sha256=HqmFuRclSfgxacHSdzpiOdwVuAboC28f8OEBXLJqsPc,8
+EDAeasy-1.0.0.dist-info/RECORD,,

EDAeasy-1.0.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: bdist_wheel (0.41.0)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

EDAeasy-1.0.0.dist-info/top_level.txt

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