qdesc 0.1.8.5__tar.gz → 0.1.9__tar.gz

{qdesc-0.1.8.5 → qdesc-0.1.9}/PKG-INFO

@@ -1,11 +1,17 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: qdesc
-Version: 0.1.8.5
+Version: 0.1.9
 Summary: Quick and Easy way to do descriptive analysis.
 Author: Paolo Hilado
 Author-email: datasciencepgh@proton.me
 Description-Content-Type: text/markdown
 License-File: LICENCE.txt
+Dynamic: author
+Dynamic: author-email
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: license-file
+Dynamic: summary
 
 # qdesc - Quick and Easy Descriptive Analysis
 

{qdesc-0.1.8.5 → qdesc-0.1.9}/qdesc/__init__.py

@@ -40,6 +40,47 @@ def desc(df):
     x_df = np.round(pd.concat([xl, mad_df, xr, anderson_df], axis=1),2)
     return x_df
 
+
+def grp_desc(df, numeric_col, group_col):
+    import pandas as pd
+    import numpy as np
+    from scipy.stats import median_abs_deviation, anderson
+    results = []
+    for group, group_df in df.groupby(group_col):
+        data = group_df[numeric_col].dropna()
+        if len(data) < 2:
+            # Not enough data for stats like std or AD test
+            stats = {
+                group_col: group,
+                'count': len(data),
+                'mean': np.nan,
+                'std': np.nan,
+                'median': np.nan,
+                'mad': np.nan,
+                'min': np.nan,
+                'max': np.nan,
+                'anderson_stat': np.nan,
+                'crit_5%': np.nan,
+                'crit_1%': np.nan
+            }
+        else:
+            ad_result = anderson(data, dist='norm')
+            stats = {
+                group_col: group,
+                'count': len(data),
+                'mean': data.mean(),
+                'std': data.std(),
+                'median': data.median(),
+                'mad': median_abs_deviation(data),
+                'min': data.min(),
+                'max': data.max(),
+                'anderson_stat': ad_result.statistic,
+                'crit_5%': ad_result.critical_values[2],  # 5% is the third value
+                'crit_1%': ad_result.critical_values[3],  # 1% is the fourth value
+            }
+        results.append(stats)
+    return np.round(pd.DataFrame(results),2)
+
 def freqdist(df, column_name):
     import pandas as pd
     if column_name not in df.columns:

{qdesc-0.1.8.5 → qdesc-0.1.9}/qdesc.egg-info/PKG-INFO

@@ -1,11 +1,17 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: qdesc
-Version: 0.1.8.5
+Version: 0.1.9
 Summary: Quick and Easy way to do descriptive analysis.
 Author: Paolo Hilado
 Author-email: datasciencepgh@proton.me
 Description-Content-Type: text/markdown
 License-File: LICENCE.txt
+Dynamic: author
+Dynamic: author-email
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: license-file
+Dynamic: summary
 
 # qdesc - Quick and Easy Descriptive Analysis
 

{qdesc-0.1.8.5 → qdesc-0.1.9}/setup.py

@@ -7,7 +7,7 @@ long_description = (this_directory / "README.md").read_text()
 
 setup(
     name='qdesc',
-    version='0.1.8.5',
+    version='0.1.9',
     packages=find_packages(),
     install_requires=[
         # List your dependencies here, e.g., pandas if your function requires it