teradataml 20.0.0.6__py3-none-any.whl → 20.0.0.7__py3-none-any.whl

teradataml/automl/autodataprep/__init__.py

@@ -1,3 +1,18 @@
+# ################################################################## 
+# 
+# Copyright 2025 Teradata. All rights reserved.
+# TERADATA CONFIDENTIAL AND TRADE SECRET
+# 
+# Primary Owner: Sweta Shaw
+# Email Id: Sweta.Shaw@Teradata.com
+# 
+# Secondary Owner: Akhil Bisht
+# Email Id: AKHIL.BISHT@Teradata.com
+# 
+# Version: 1.1
+# Function Version: 1.0
+# ##################################################################
+
 # External libraries
 import pandas as pd
 

teradataml/automl/custom_json_utils.py

@@ -1,6 +1,6 @@
 # ################################################################## 
 # 
-# Copyright 2024 Teradata. All rights reserved.
+# Copyright 2025 Teradata. All rights reserved.
 # TERADATA CONFIDENTIAL AND TRADE SECRET
 # 
 # Primary Owner: Sweta Shaw
@@ -14,15 +14,21 @@
 # ##################################################################
 
 import json
-
+from teradataml.common.constants import AutoMLConstants
 
 class _GenerateCustomJson:
     
-    def __init__(self):
+    def __init__(self, cluster=False):
         """
         DESCRIPTION:
             Function initializes the data and flags for custom JSON file generation.
-            
+
+        PARAMETERS:
+            cluster:
+                Optional Argument.
+                Specifies whether to apply clustering techniques.
+                Default Value: False
+                Types: bool
         """
         # Initializing data dictionary for storing custom parameters
         self.data = {}
@@ -30,6 +36,7 @@ class _GenerateCustomJson:
         self.fe_flag = {index : False for index in range(1, 8)}
         self.de_flag = {index : False for index in range(1, 5)}
         self.mt_flag = {index : False for index in range(1, 2)}
+        self.cluster = cluster
     
     def _process_list_input(self, 
                             input_data, 
@@ -280,13 +287,21 @@ class _GenerateCustomJson:
         """
         print("\nCustomizing Data Preparation Phase ...")
         # Available options for customization of data preparation phase
-        dp_customize_options = {
-            1: 'Customize Data Imbalance Handling',
-            2: 'Customize Outlier Handling',
-            3: 'Customize Feature Scaling',
-            4: 'Back to main menu',
-            5: 'Generate custom json and exit'
+        if self.cluster:
+            dp_customize_options = {
+                1: 'Customize Outlier Handling',
+                2: 'Customize Feature Scaling',
+                3: 'Back to main menu',
+                4: 'Generate custom json and exit'
             }
+        else:
+            dp_customize_options = {
+                1: 'Customize Data Imbalance Handling',
+                2: 'Customize Outlier Handling',
+                3: 'Customize Feature Scaling',
+                4: 'Back to main menu',
+                5: 'Generate custom json and exit'
+                }
         
         while True:
         
@@ -296,19 +311,26 @@ class _GenerateCustomJson:
                 print(f"\nIndex {index}: {options}")
             print("-"*80)
             # Mapping each index to corresponding functionality
-            de_method_map = {
-                1: self._get_customize_input_data_imbalance_handling,
-                2: self._get_customize_input_outlier_handling,
-                3: self._get_customize_input_feature_scaling
-            }
-            
+            if self.cluster:
+                de_method_map = {
+                    1: self._get_customize_input_outlier_handling,
+                    2: self._get_customize_input_feature_scaling
+                }
+                de_back_key, de_exit_key = 3, 4
+            else:
+                de_method_map = {
+                    1: self._get_customize_input_data_imbalance_handling,
+                    2: self._get_customize_input_outlier_handling,
+                    3: self._get_customize_input_feature_scaling
+                }
+                de_back_key, de_exit_key = 4, 5
             # Taking required input for customizing data preparation.
             dp_phase_idx = self._process_list_input(
                 input("\nEnter the list of indices you want to customize in data preparation phase: "),
                 'int', list(dp_customize_options.keys()))
             
             # Setting back_key and exit_key
-            de_back_key, de_exit_key = 4, 5
+            
             # Flag variable to back to main menu
             de_exit_to_main_flag = False
             # Flag variable to exit from main menu
@@ -664,7 +686,6 @@ class _GenerateCustomJson:
         self._set_generic_arguement(func_name='StringManipulationParam')
         print("\nCustomization of string manipulation has been completed successfully.")
 
-    
     def _get_customize_input_categorical_encoding(self,
                                                   first_execution_flag=False):
         """
@@ -927,8 +948,7 @@ class _GenerateCustomJson:
         self.data['DataImbalanceMethod'] = sampling_methods[sampling_mthd_idx]
         
         print("\nCustomization of data imbalance handling has been completed successfully.")
-
-    
+  
     def _get_customize_input_outlier_handling(self,
                                               first_execution_flag=False):
         """
@@ -946,13 +966,30 @@ class _GenerateCustomJson:
         if first_execution_flag:
             print("\nWARNING : Reinitiated outlier handling customization. "
                   "Overwriting the previous input.")
-            keys_to_remove = ['OutlierLowerPercentile', 'OutlierUpperPercentile']
+            keys_to_remove = ['OutlierLowerPercentile', 'OutlierUpperPercentile', 'OutlierFilterMethod', 'OutlierFilterParam']
             for key in keys_to_remove:
                 if key in self.data:
                     del self.data[key]
             
         
         print("\nCustomizing Outlier Handling ...")
+
+        apply_outlier_options = {1: 'Yes', 2: 'No'}
+        print("\nDo you want to apply outlier filtering?")
+        for idx, val in apply_outlier_options.items():
+            print(f"Index {idx}: {val}")
+
+        user_choice = self._process_single_input(
+            input("\nEnter the index of your choice (1 for Yes, 2 for No): "),
+            'int',
+            list(apply_outlier_options.keys())
+        )
+
+        if user_choice == 2:
+            self.data['OutlierFilterIndicator'] = False
+            print("\nSkipping outlier filtering as per user choice.")
+            return
+        
         # Setting indicator for outlier handling
         self.data['OutlierFilterIndicator'] = True
         outlier_methods = {1: 'percentile', 
@@ -1127,52 +1164,68 @@ class _GenerateCustomJson:
             Allowed hyperparameters for model.
         """
         # Setting allowed common hyperparameters for tree like model
-        allowed_common_hyperparameters_tree_model ={
-            1 : 'min_impurity',
-            2 : 'max_depth',
-            3 : 'min_node_size',
-        }
-        # Setting allowed hyperparameters for xgbooost model
-        allowed_hyperparameters_xgboost = { 
-            **allowed_common_hyperparameters_tree_model,
-            4 : 'shrinkage_factor',
-            5 : 'iter_num'
-        }
-        # Setting allowed hyperparameters for decision forest model
-        allowed_hyperparameters_decision_forest = {
-            **allowed_common_hyperparameters_tree_model,
-            4 : 'num_trees'
-        }
-        # Setting allowed hyperparameters for knn model
-        allowed_hyperparameters_knn = {
-            0 : 'k'
-        }
-        # Setting allowed hyperparameters for svm model
-        allowed_hyperparameters_svm = {
-            1 : 'alpha',
-            2 : 'learning_rate',
-            3 : 'initial_eta',
-            4 : 'momentum',
-            5 : 'iter_num_no_change',
-            6 : 'iter_max',
-            7 : 'batch_size'
-        }
-        # Setting allowed hyperparameters for glm model
-        allowed_hyperparameters_glm = {
-            **allowed_hyperparameters_svm,
-            8 : 'tolerance',
-            9 : 'nesterov',
-            10 : 'intercept',
-            11 : 'local_sgd_iterations'
-        }
-        # Setting allowed hyperparameters for different models
-        allowed_hyperparameters = {
-            'xgboost' : allowed_hyperparameters_xgboost,
-            'decision_forest' : allowed_hyperparameters_decision_forest,
-            'knn' : allowed_hyperparameters_knn,
-            'svm' : allowed_hyperparameters_svm,
-            'glm' : allowed_hyperparameters_glm
-        }
+        if self.cluster:
+            allowed_hyperparameters_kmeans ={
+                1 : 'n_clusters',
+                2 : 'init',
+                3 : 'max_iter',
+            }
+            allowed_hyperparameters_gaussian_mixture ={
+                1 : 'n_components',
+                2 : 'covariance_type',
+                3 : 'max_iter',
+            }
+            allowed_hyperparameters = {
+                'KMeans' : allowed_hyperparameters_kmeans,
+                'GaussianMixture' : allowed_hyperparameters_gaussian_mixture,
+            }
+        else:    
+            allowed_common_hyperparameters_tree_model ={
+                1 : 'min_impurity',
+                2 : 'max_depth',
+                3 : 'min_node_size',
+            }
+            # Setting allowed hyperparameters for xgbooost model
+            allowed_hyperparameters_xgboost = { 
+                **allowed_common_hyperparameters_tree_model,
+                4 : 'shrinkage_factor',
+                5 : 'iter_num'
+            }
+            # Setting allowed hyperparameters for decision forest model
+            allowed_hyperparameters_decision_forest = {
+                **allowed_common_hyperparameters_tree_model,
+                4 : 'num_trees'
+            }
+            # Setting allowed hyperparameters for knn model
+            allowed_hyperparameters_knn = {
+                0 : 'k'
+            }
+            # Setting allowed hyperparameters for svm model
+            allowed_hyperparameters_svm = {
+                1 : 'alpha',
+                2 : 'learning_rate',
+                3 : 'initial_eta',
+                4 : 'momentum',
+                5 : 'iter_num_no_change',
+                6 : 'iter_max',
+                7 : 'batch_size'
+            }
+            # Setting allowed hyperparameters for glm model
+            allowed_hyperparameters_glm = {
+                **allowed_hyperparameters_svm,
+                8 : 'tolerance',
+                9 : 'nesterov',
+                10 : 'intercept',
+                11 : 'local_sgd_iterations'
+            }
+            # Setting allowed hyperparameters for different models
+            allowed_hyperparameters = {
+                'xgboost' : allowed_hyperparameters_xgboost,
+                'decision_forest' : allowed_hyperparameters_decision_forest,
+                'knn' : allowed_hyperparameters_knn,
+                'svm' : allowed_hyperparameters_svm,
+                'glm' : allowed_hyperparameters_glm
+            }
         return allowed_hyperparameters[model_name]
     
     def _get_allowed_hyperparameters_types(self, hyperparameter):
@@ -1190,26 +1243,35 @@ class _GenerateCustomJson:
             Allowed hyperparameters types for hyperparameter.
         """
         # Setting allowed hyperparameters types for different hyperparameters
-        allowed_hyperparameters_types = {
-            'min_impurity' : 'float',
-            'max_depth' : 'int',
-            'min_node_size' : 'int',
-            'shrinkage_factor' : 'float',
-            'iter_num' : 'int',
-            'num_trees' : 'int',
-            'k' : 'int',
-            'alpha' : 'float',
-            'learning_rate' : 'str',
-            'initial_eta' : 'float',
-            'momentum' : 'float',
-            'iter_num_no_change' : 'int',
-            'iter_max' : 'int',
-            'batch_size' : 'int',
-            'tolerance' : 'float',
-            'nesterov' : 'bool',
-            'intercept' : 'bool',
-            'local_sgd_iterations' : 'int'
-        }
+        if self.cluster:
+            allowed_hyperparameters_types = {
+                'n_clusters': 'int',
+                'init': 'str',
+                'max_iter': 'int',
+                'n_components': 'int',
+                'covariance_type': 'str'
+            }
+        else:
+            allowed_hyperparameters_types = {
+                'min_impurity' : 'float',
+                'max_depth' : 'int',
+                'min_node_size' : 'int',
+                'shrinkage_factor' : 'float',
+                'iter_num' : 'int',
+                'num_trees' : 'int',
+                'k' : 'int',
+                'alpha' : 'float',
+                'learning_rate' : 'str',
+                'initial_eta' : 'float',
+                'momentum' : 'float',
+                'iter_num_no_change' : 'int',
+                'iter_max' : 'int',
+                'batch_size' : 'int',
+                'tolerance' : 'float',
+                'nesterov' : 'bool',
+                'intercept' : 'bool',
+                'local_sgd_iterations' : 'int'
+            }
         return allowed_hyperparameters_types[hyperparameter]
     
     def _get_customize_input_model_hyperparameter(self,
@@ -1233,11 +1295,12 @@ class _GenerateCustomJson:
         # Setting indicator for model hyperparameter tuning
         self.data['HyperparameterTuningIndicator'] = True
         self.data['HyperparameterTuningParam'] = {}
-        all_models = {1: 'decision_forest',
-                      2: 'xgboost',
-                      3: 'knn',
-                      4: 'glm',
-                      5: 'svm'}
+        if self.cluster:
+            # Create numbered mapping for clustering models
+            all_models = {i+1: model for i, model in enumerate(AutoMLConstants.CLUSTERING_MODELS.value)}
+        else:
+            # Create numbered mapping for supervised models
+            all_models = {i+1: model for i, model in enumerate(AutoMLConstants.SUPERVISED_MODELS.value)}
         # Displaying available models for hyperparameter tuning
         print("\nAvailable models for hyperparameter tuning with corresponding indices:")
         for index, model in all_models.items():
@@ -1309,26 +1372,35 @@ class _GenerateCustomJson:
                 Types: str      
         """
         # Setting example hyperparameter values for different hyperparameters
-        example_hyperparameters = {
-            'min_impurity' : ([0.1,0.6], 'float'),
-            'max_depth' : ([1,5,10], 'int'),
-            'min_node_size' : ([1,20,100], 'int'),
-            'num_trees' : ([10,50,100], 'int'),
-            'k' : ([5,25,100], 'int'),
-            'shrinkage_factor': ([0.1,0.5,1.0], 'float'),
-            'alpha' : ([0.1,0.5,1.0], 'float'),
-            'learning_rate' : (['constant','optimal','invtime','adaptive'], 'str'),
-            'initial_eta' : ([0.05,0.1], 'float'),
-            'momentum' : ([0.65,0.95], 'float'),
-            'iter_num_no_change' : ([25,50,100], 'int'),
-            'iter_max' : ([10,100,300], 'int'),
-            'batch_size' : ([10,50,100], 'int'),
-            'tolerance' : ([0.0001,0.01], 'float'),
-            'nesterov' : (['true','false'], 'bool'),
-            'intercept' : (['true','false'], 'bool'),
-            'local_sgd_iterations' : ([10,25,50], 'int'),
-            'iter_num' : ([10,50,100], 'int')
-        }
+        if self.cluster:
+            example_hyperparameters = {
+                'n_clusters': ([2, 3, 4], 'int'),
+                'init': (['k-means++', 'random'], 'str'),
+                'max_iter': ([100, 300], 'int'),
+                'n_components': ([2, 3, 4], 'int'),
+                'covariance_type': (['full', 'tied', 'diag', 'spherical'], 'str')
+            }
+        else:
+            example_hyperparameters = {
+                'min_impurity' : ([0.1,0.6], 'float'),
+                'max_depth' : ([1,5,10], 'int'),
+                'min_node_size' : ([1,20,100], 'int'),
+                'num_trees' : ([10,50,100], 'int'),
+                'k' : ([5,25,100], 'int'),
+                'shrinkage_factor': ([0.1,0.5,1.0], 'float'),
+                'alpha' : ([0.1,0.5,1.0], 'float'),
+                'learning_rate' : (['constant','optimal','invtime','adaptive'], 'str'),
+                'initial_eta' : ([0.05,0.1], 'float'),
+                'momentum' : ([0.65,0.95], 'float'),
+                'iter_num_no_change' : ([25,50,100], 'int'),
+                'iter_max' : ([10,100,300], 'int'),
+                'batch_size' : ([10,50,100], 'int'),
+                'tolerance' : ([0.0001,0.01], 'float'),
+                'nesterov' : (['true','false'], 'bool'),
+                'intercept' : (['true','false'], 'bool'),
+                'local_sgd_iterations' : ([10,25,50], 'int'),
+                'iter_num' : ([10,50,100], 'int')
+            }
 
         print(f"\nExample values for hyperparameter '{hyperparameter_name}' :")
         if hyperparameter_name in example_hyperparameters: