qdesc 0.1.8.5__py3-none-any.whl → 0.1.9.1__py3-none-any.whl

qdesc/__init__.py

@@ -22,24 +22,61 @@ def desc(df):
         result = anderson(df[column])
         statistic = result.statistic
         critical_values = result.critical_values
-        # Only select the 5% and 1% significance levels
+        # Only select the 5% levels
         selected_critical_values = {
-            '5% crit_value': critical_values[2],  # 5% critical value
-            '1% crit_value': critical_values[4]   # 1% critical value
+            '5% crit_value': critical_values[2]
         }
         # Store the results in a dictionary
         results[column] = {
             'AD_stat': statistic,
-            **selected_critical_values  # Add critical values for 5% and 1% levels
+            **selected_critical_values  # Add critical values for 5%
         }
     # Convert the results dictionary into a DataFrame
     anderson_df = pd.DataFrame.from_dict(results, orient='index')
-    
     xl = x.iloc[:, :4]
     xr = x.iloc[:, 4:]
     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
+            }
+        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(),
+                'AD_stat': ad_result.statistic,
+                'crit_5%': ad_result.critical_values[2],  # 5% is the third 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.dist-info → qdesc-0.1.9.1.dist-info}/METADATA

@@ -1,11 +1,17 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: qdesc
-Version: 0.1.8.5
+Version: 0.1.9.1
 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-0.1.9.1.dist-info/RECORD

@@ -0,0 +1,6 @@
+qdesc/__init__.py,sha256=-NWrytwAkpgU387wvyk5ORWMNEERuRKQlWzWM_DBZi8,7861
+qdesc-0.1.9.1.dist-info/licenses/LICENCE.txt,sha256=xdFo-Rt6I7EP7C_qrVeIBIcH_7mRGUh8sciJs2R8VmY,9684
+qdesc-0.1.9.1.dist-info/METADATA,sha256=A_XkoWOTN_s9ZJtO8Bvm586OEKESqiGTLNgxNzHMIXY,4545
+qdesc-0.1.9.1.dist-info/WHEEL,sha256=wXxTzcEDnjrTwFYjLPcsW_7_XihufBwmpiBeiXNBGEA,91
+qdesc-0.1.9.1.dist-info/top_level.txt,sha256=JuSs1wWRGN77DVuq-SX-5P7m_mIZF0ikEVgPTBOrHb0,6
+qdesc-0.1.9.1.dist-info/RECORD,,

{qdesc-0.1.8.5.dist-info → qdesc-0.1.9.1.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: bdist_wheel (0.38.4)
+Generator: setuptools (80.1.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

qdesc-0.1.8.5.dist-info/RECORD

@@ -1,6 +0,0 @@
-qdesc/__init__.py,sha256=1I8XCqG4wwqfKijIVFRZ-PK84MiKOkW57zWU372NPRc,6624
-qdesc-0.1.8.5.dist-info/LICENCE.txt,sha256=xdFo-Rt6I7EP7C_qrVeIBIcH_7mRGUh8sciJs2R8VmY,9684
-qdesc-0.1.8.5.dist-info/METADATA,sha256=qhonWRLjCIoRy2s2T58oepk02dsdC0t2ZwP2nliifP0,4407
-qdesc-0.1.8.5.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
-qdesc-0.1.8.5.dist-info/top_level.txt,sha256=JuSs1wWRGN77DVuq-SX-5P7m_mIZF0ikEVgPTBOrHb0,6
-qdesc-0.1.8.5.dist-info/RECORD,,