metacountregressor 0.1.133__tar.gz → 0.1.136__tar.gz

{metacountregressor-0.1.133 → metacountregressor-0.1.136}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: metacountregressor
-Version: 0.1.133
+Version: 0.1.136
 Summary: Extensions for a Python package for estimation of count models.
 Home-page: https://github.com/zahern/CountDataEstimation
 Author: Zeke Ahern

{metacountregressor-0.1.133 → metacountregressor-0.1.136}/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')
@@ -178,15 +179,54 @@ config = {
     }
 }
 '''
-
+def set_up_analyst_constraints(data_characteristic, variable_decisions_alt = None):
+    name_data_characteristics = data_characteristic.columns.tolist()
+    distu = ['n', 'u', 't']
+    tra = ['no']
+    variable_decisions = {
+        name: {
+            'levels': list(range(6)),
+            'distributions': distu,
+            'transformations': tra
+        }
+        for name in name_data_characteristics
+    }
+    # Override elements in the original dictionary with the alt dictionary
+    if variable_decisions_alt is not None:
+        for key, alt_value in variable_decisions_alt.items():
+            if key in variable_decisions:
+                # Update the existing entry
+                variable_decisions[key].update(alt_value)
+            else:
+                # Add new entry if it doesn't exist
+                variable_decisions[key] = alt_value
+    # Prepare the data for the DataFrame
+    rows = []
+    for column_name, details in variable_decisions.items():
+        # Create a row dictionary
+        row = {'Column': column_name}
+
+        # Add levels as True/False for Level 0 through Level 5
+        for level in range(6):  # Assuming Level 0 to Level 5
+            row[f'Level {level}'] = level in details['levels']
+
+        # Add distributions and transformations directly
+        row['distributions'] = details['distributions']
+        row['transformations'] = details['transformations']
+
+        rows.append(row)
+
+    # Create the DataFrame
+    df = pd.DataFrame(rows)
+    return  df
 
 # Function to guess Low, Medium, High ranges
 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
-    print('good')
-    series = pd.to_numeric(series, errors='coerce').fillna(mode_value)
+    #print('did it make it...')
+    #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)
     high_threshold = np.quantile(series,0.66)
 

{metacountregressor-0.1.133 → metacountregressor-0.1.136}/metacountregressor/main.py

@@ -28,11 +28,16 @@ def convert_df_columns_to_binary_and_wide(df):
     return df
 
 
+
+
+
+
 def process_arguments(**kwargs):
     '''
     TRYING TO TURN THE CSV FILES INTO RELEVANT ARGS
     '''
     #dataset
+    '''
     if kwargs.get('dataset_file', False
     ):
         dataset = pd.read_csv(kwargs.get('dataset_file'))
@@ -71,15 +76,15 @@ def process_arguments(**kwargs):
 
         update_constant = kwargs.get('analyst_constraints')
         #update the decision_constraints
-
+    '''
     data_characteristic = pd.read_csv(kwargs.get('problem_data', 'problem_data.csv'))
     # Extract the column as a list of characteristic names
-    name_data_characteristics = data_characteristic.columns.tolist()
+    #name_data_characteristics = data_characteristic.columns.tolist()
 
     # Create the dictionary
-    decision_constraints = {name: list(range(7)) for name in name_data_characteristics}
+    #decision_constraints = {name: list(range(7)) for name in name_data_characteristics}
 
-    print('this gets all the features, I need to remove...')
+    #print('this gets all the features, I need to remove...')
 
     analyst_d = pd.read_csv(kwargs.get('decison_constraints', 'decisions.csv'))
     hyper = pd.read_csv('setup_hyper.csv')
@@ -377,10 +382,10 @@ def main(args, **kwargs):
         #data_info['data']['Panel'][0]
         args['decisions'] = data_info['analyst']
 
-        if not np.isnan(data_info['data']['Grouped'][0]):
+        if type(data_info['data']['Grouped'][0]) == str and len(data_info['data']['Grouped'][0]) >1:
             args['group'] = data_info['data']['Grouped'][0]
             args['ID'] = data_info['data']['Grouped'][0]
-        if not np.isnan(data_info['data']['Panel'][0]):
+        if type(data_info['data']['Panel'][0]) == str and len(data_info['data']['Panel'][0])>1:
             args['panels'] = data_info['data']['Panel'][0]
 
         df = pd.read_csv(str(data_info['data']['Problem'][0]))

{metacountregressor-0.1.133 → metacountregressor-0.1.136}/metacountregressor.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: metacountregressor
-Version: 0.1.133
+Version: 0.1.136
 Summary: Extensions for a Python package for estimation of count models.
 Home-page: https://github.com/zahern/CountDataEstimation
 Author: Zeke Ahern