metacountregressor 0.1.124__py3-none-any.whl → 0.1.127__py3-none-any.whl

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/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-0.1.124.dist-info → metacountregressor-0.1.127.dist-info}/METADATA

@@ -1,10 +1,10 @@
 Metadata-Version: 2.2
 Name: metacountregressor
-Version: 0.1.124
+Version: 0.1.127
 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-0.1.124.dist-info → metacountregressor-0.1.127.dist-info}/RECORD

@@ -3,7 +3,7 @@ metacountregressor/_device_cust.py,sha256=759fnKmTYccJm4Lpi9_1reurh6OB9d6q9soPR0
 metacountregressor/app_main.py,sha256=vY3GczTbGbBRalbzMkl_9jVW7RMgEOc6z2Dr1IZJv9c,10014
 metacountregressor/data_split_helper.py,sha256=M2fIMdIO8znUaYhx5wlacRyNWdQjNYu1z1wkE-kFUYU,3373
 metacountregressor/halton.py,sha256=jhovA45UBoZYU9g-hl6Lb2sBIx_ZBTNdPrpgkzR9fng,9463
-metacountregressor/helperprocess.py,sha256=4aSoyKP1GfzjwCzZ_dXlTbokOiMt_8sbzB6_tu0GPDg,16290
+metacountregressor/helperprocess.py,sha256=gzZ6g_uzctQeuyzqj3mV1n1Y4Kw8CLYK02Dkoz_fV9w,17041
 metacountregressor/main.py,sha256=A3XGwbwhhKVgMxnEgbAmMpgYaWkS8Rk30-cYs3FxvEk,22713
 metacountregressor/main_old.py,sha256=eTS4ygq27MnU-dZ_j983Ucb-D5XfbVF8OJQK2hVVLZc,24123
 metacountregressor/metaheuristics.py,sha256=Kkx1Jfox6NBlm5zVrI26Vc_NI7NFQSS9dinrZU9SpV8,105871
@@ -11,10 +11,10 @@ metacountregressor/pareto_file.py,sha256=whySaoPAUWYjyI8zo0hwAOa3rFk6SIUlHSpqZiL
 metacountregressor/pareto_logger__plot.py,sha256=mEU2QN4wmsM7t39GJ_XhJ_jjsdl09JOmG0U2jICrAkI,30037
 metacountregressor/setup.py,sha256=5UcQCCLR8Fm5odA3MX78WwahavxFq4mVD6oq0IuQvAY,936
 metacountregressor/single_objective_finder.py,sha256=jVG7GJBqzSP4_riYr-kMMKy_LE3SlGmKMunNhHYxgRg,8011
-metacountregressor/solution.py,sha256=OJqB00cvGMLFei6RsjphPamOdLm3EWOOzK7k-uVbvFY,277671
+metacountregressor/solution.py,sha256=_InL6f_DHPuP518NfYXhQJQwDejR5CVEXdWyU1kKY7E,277562
 metacountregressor/test_generated_paper2.py,sha256=pwOoRzl1jJIIOUAAvbkT6HmmTQ81mwpsshn9SLdKOg8,3927
-metacountregressor-0.1.124.dist-info/LICENSE.txt,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
-metacountregressor-0.1.124.dist-info/METADATA,sha256=8d5RG71XKfReAVDxLlVwVbDMJXZqnCEElx7AUwrY_2E,23441
-metacountregressor-0.1.124.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-metacountregressor-0.1.124.dist-info/top_level.txt,sha256=zGG7UC5WIpr76gsFUpwJ4En2aCcoNTONBaS3OewwjR0,19
-metacountregressor-0.1.124.dist-info/RECORD,,
+metacountregressor-0.1.127.dist-info/LICENSE.txt,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
+metacountregressor-0.1.127.dist-info/METADATA,sha256=oQWg23dV1Dww0iSx684RxlhJyAKwn0Ud6PVNcdKt6LQ,23434
+metacountregressor-0.1.127.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+metacountregressor-0.1.127.dist-info/top_level.txt,sha256=zGG7UC5WIpr76gsFUpwJ4En2aCcoNTONBaS3OewwjR0,19
+metacountregressor-0.1.127.dist-info/RECORD,,