metacountregressor 0.1.122__tar.gz → 0.1.125__tar.gz

{metacountregressor-0.1.122 → metacountregressor-0.1.125}/PKG-INFO

@@ -1,10 +1,10 @@
 Metadata-Version: 2.2
 Name: metacountregressor
-Version: 0.1.122
+Version: 0.1.125
 Summary: Extensions for a Python package for estimation of count models.
 Home-page: https://github.com/zahern/CountDataEstimation
 Author: Zeke Ahern
-Author-email: zeke.ahern@hdr.qut.edu.au
+Author-email: z.ahern@qut.edu.au
 License: QUT
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown

{metacountregressor-0.1.122 → metacountregressor-0.1.125}/metacountregressor/helperprocess.py

@@ -180,6 +180,23 @@ config = {
 '''
 
 
+# Function to guess Low, Medium, High ranges
+def guess_low_medium_high(column_name, series):
+    # Compute the tertiles (33rd and 66th percentiles)
+    low_threshold = series.quantile(0.33)
+    high_threshold = series.quantile(0.66)
+
+    # Define the bins and labels
+    bins = [series.min() - 1, low_threshold, high_threshold, series.max()]
+    labels = ['Low', 'Medium', 'High']
+
+    return {
+        'type': 'bin',
+        'bins': bins,
+        'labels': labels,
+        'prefix': f'{column_name}_Binned'
+    }
+
 def transform_dataframe(df, config):
     output_df = pd.DataFrame()
 
@@ -226,12 +243,13 @@ def guess_column_type(column_name, series):
         return {'type': 'one-hot', 'prefix': column_name}
     elif pd.api.types.is_numeric_dtype(series):
         unique_values = series.nunique()
-        if unique_values < 10:
+        if unique_values < 5:
+            return {'type': 'one-hot', 'prefix': column_name}
+
+
+        elif series.range() > 20:
             # If there are few unique values, assume binning with default bins
-            min_val, max_val = series.min(), series.max()
-            bins = np.linspace(min_val, max_val, num=unique_values + 1)
-            labels = [f'Bin_{i}' for i in range(1, len(bins))]
-            return {'type': 'bin', 'bins': bins, 'labels': labels, 'prefix': f'{column_name}_Binned'}
+            guess_low_medium_high(column_name,series)
         else:
            # # Otherwise, assume continuous data with normalization
             # Otherwise, fallback to continuous standardization
@@ -293,14 +311,26 @@ def interactions(df, keep=None, drop_this_perc=0.6, interact = False):
         df = pd.concat([df, df_interactions], axis=1, sort=False)
 
     # second
-    corr_matrix = df.corr().abs()
+    # Remove `keep` columns from the correlation matrix
+    if keep is not None:
+        df_corr = df.drop(columns=keep, errors='ignore')  # Exclude `keep` columns
+    else:
+        df_corr = df
+
+    # Compute the absolute correlation matrix
+    corr_matrix = df_corr.corr().abs()
+
+    # Keep only the upper triangle of the correlation matrix
     upper = corr_matrix.where(np.triu(np.ones(corr_matrix.shape), k=1).astype(bool))
 
-    # Find features with correlation greater than 0.6
+    # Find features with correlation greater than the threshold
     to_drop = [column for column in upper.columns if any(upper[column] > drop_this_perc)]
+
+    # Ensure `keep` columns are not dropped
     if keep is not None:
         to_drop = [column for column in to_drop if column not in keep]
-    # Drop features
+
+    # Drop the identified features
     df.drop(to_drop, axis=1, inplace=True)
 
     return df

{metacountregressor-0.1.122 → metacountregressor-0.1.125}/metacountregressor/solution.py

@@ -2983,7 +2983,7 @@ class ObjectiveFunction(object):
         argument = prob.mean(axis=1)
         # if less than 0 penalise
         if np.min(argument) < 0:
-            print('what the fuck')
+            print('Error with args..')
         if np.min(argument) < limit:
             # add a penalty for too small argument of log
             log_lik += -np.sum(np.minimum(0.0, argument - limit)) / limit
@@ -3473,8 +3473,7 @@ class ObjectiveFunction(object):
             corr_pairs = list(itertools.combinations(self.Kr, 2))
         else:
             corr_pairs = list(itertools.combinations(corr_indices, 2))
-            if len(corr_pairs) >0:
-                print('maybe get the terms here')
+
 
         for ii, corr_pair in enumerate(corr_pairs):
             # lower cholesky matrix
@@ -3635,7 +3634,7 @@ class ObjectiveFunction(object):
             #print("Custom functieon time:", end_time - start_time)
 
         except Exception as e:
-            print(e)
+            print("Neg Binom error.")
         return gg_alt
 
     def lindley_pmf(self, x, r, theta, k=50):
@@ -3969,7 +3968,7 @@ class ObjectiveFunction(object):
 
 
         # proba_d = self.dnegbimonli(y, eVd, b_gam )
-        # print('fuck if this actually works')
+
 
         elif dispersion == 2:
 

{metacountregressor-0.1.122 → metacountregressor-0.1.125}/metacountregressor.egg-info/PKG-INFO

@@ -1,10 +1,10 @@
 Metadata-Version: 2.2
 Name: metacountregressor
-Version: 0.1.122
+Version: 0.1.125
 Summary: Extensions for a Python package for estimation of count models.
 Home-page: https://github.com/zahern/CountDataEstimation
 Author: Zeke Ahern
-Author-email: zeke.ahern@hdr.qut.edu.au
+Author-email: z.ahern@qut.edu.au
 License: QUT
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown

{metacountregressor-0.1.122 → metacountregressor-0.1.125}/setup.py

@@ -53,7 +53,7 @@ setuptools.setup(
     long_description_content_type='text/markdown',  # Specify the content type as Markdown
     url='https://github.com/zahern/CountDataEstimation',
     author='Zeke Ahern',
-    author_email='zeke.ahern@hdr.qut.edu.au',
+    author_email='z.ahern@qut.edu.au',
     license='QUT',
     packages=['metacountregressor'],
     zip_safe=False,
@@ -61,6 +61,7 @@ setuptools.setup(
     install_requires=[
         'numpy>=1.13.1',
         'scipy>=1.0.0',
-        'requests','latextable'
+        'requests',
+        'latextable'
     ]
 )