metacountregressor 0.1.132__tar.gz → 0.1.134__tar.gz

{metacountregressor-0.1.132 → metacountregressor-0.1.134}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: metacountregressor
-Version: 0.1.132
+Version: 0.1.134
 Summary: Extensions for a Python package for estimation of count models.
 Home-page: https://github.com/zahern/CountDataEstimation
 Author: Zeke Ahern

{metacountregressor-0.1.132 → metacountregressor-0.1.134}/metacountregressor/helperprocess.py

@@ -2,6 +2,7 @@ import numpy as np
 import pandas as pd
 import csv
 import matplotlib.pyplot as plt
+from scipy import stats as st
 from sklearn.preprocessing import StandardScaler
 
 plt.style.use('https://github.com/dhaitz/matplotlib-stylesheets/raw/master/pitayasmoothie-dark.mplstyle')
@@ -184,7 +185,7 @@ config = {
 def guess_low_medium_high(column_name, series):
     # Compute the tertiles (33rd and 66th percentiles)
     print('did it make it...')
-    mode_value = np.mode(series)  # Get the most frequent value
+    mode_value = st.mode(series)  # Get the most frequent value
     print('good')
     series = pd.to_numeric(series, errors='coerce').fillna(mode_value)
     low_threshold = np.quantile(series, 0.33)
@@ -192,7 +193,19 @@ def guess_low_medium_high(column_name, series):
 
     # Define the bins and labels
     bins = [np.min(series) - 1, low_threshold, high_threshold, np.max(series)]
-    labels = ['Low', 'Medium', 'High']
+    # Handle duplicate bins by adjusting labels
+    if len(set(bins)) < len(bins):  # Check for duplicate bin edges
+        if low_threshold == high_threshold:
+            # Collapse to two bins (Low and High)
+            bins = [np.min(series) - 1, low_threshold, np.max(series)]
+            labels = ['Low', 'High']
+        else:
+            # Collapse to three unique bins
+            bins = sorted(set(bins))  # Remove duplicate edges
+            labels = [f'Bin {i + 1}' for i in range(len(bins) - 1)]
+    else:
+        # Standard case: Low, Medium, High
+        labels = ['Low', 'Medium', 'High']
 
     return {
         'type': 'bin',
@@ -211,7 +224,8 @@ def transform_dataframe(df, config):
                 df[column],
                 bins=settings['bins'],
                 labels=settings['labels'],
-                right=False
+                right=False,
+
             )
             # One-hot encode the binned column
             binned_dummies = pd.get_dummies(binned, prefix=settings['prefix'])

{metacountregressor-0.1.132 → metacountregressor-0.1.134}/metacountregressor.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: metacountregressor
-Version: 0.1.132
+Version: 0.1.134
 Summary: Extensions for a Python package for estimation of count models.
 Home-page: https://github.com/zahern/CountDataEstimation
 Author: Zeke Ahern