move vtreat parameters out of pipeline parameters

Examples/Pipeline/Pipeline_Example.ipynb

@@ -88,8 +88,8 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "/Users/johnmount/opt/anaconda3/envs/ai_academy_3_7/lib/python3.7/site-packages/vtreat/vtreat_api.py:369: UserWarning: called transform on same data used to fit (this causes over-fit, please use fit_transform() instead)\n",
-      "  \"called transform on same data used to fit (this causes over-fit, please use fit_transform() instead)\")\n"
+      "/Users/johnmount/opt/anaconda3/envs/ai_academy_3_7/lib/python3.7/site-packages/vtreat/vtreat_api.py:348: UserWarning: possibly called transform on same data used to fit (this causes over-fit, please use fit_transform() instead)\n",
+      "  \"possibly called transform on same data used to fit (this causes over-fit, please use fit_transform() instead)\")\n"
      ]
     },
     {
@@ -134,22 +134,7 @@
      "text": [
       "Pipeline(memory=None,\n",
       "         steps=[('preprocessor',\n",
-      "                 vtreat.vtreat_api.BinomialOutcomeTreatment(outcome_target=True,\n",
-      "params={'coders': {'clean_copy',\n",
-      "            'deviation_code',\n",
-      "            'impact_code',\n",
-      "            'indicator_code',\n",
-      "            'logit_code',\n",
-      "            'missing_indicator',\n",
-      "            'prevalence_code'},\n",
-      " 'cross_validation_k': 5,\n",
-      " 'cross_validation_plan': <vtreat.cross_plan.KWayCrossPlanYStratified object at 0x10fa81b50>,\n",
-      " '...\n",
-      " 'missingness_imputation': <function mean at 0x11093bb90>,\n",
-      " 'sparse_indicators': True,\n",
-      " 'use_hierarchical_estimate': True,\n",
-      " 'user_transforms': []},\n",
-      ")),\n",
+      "                 vtreat.vtreat_api.BinomialOutcomeTreatment(outcome_target=True, )),\n",
       "                ('classifier',\n",
       "                 LogisticRegression(C=1.0, class_weight=None, dual=False,\n",
       "                                    fit_intercept=True, intercept_scaling=1,\n",
@@ -210,7 +195,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "{'use_hierarchical_estimate': True, 'coders': {'prevalence_code', 'logit_code', 'indicator_code', 'deviation_code', 'impact_code', 'missing_indicator', 'clean_copy'}, 'filter_to_recommended': True, 'indicator_min_fraction': 0.1, 'cross_validation_plan': <vtreat.cross_plan.KWayCrossPlanYStratified object at 0x10fa81b50>, 'cross_validation_k': 5, 'user_transforms': [], 'sparse_indicators': True, 'missingness_imputation': <function mean at 0x11093bb90>, 'outcome_target': True}\n"
+      "{}\n"
      ]
     }
    ],
@@ -236,47 +221,15 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "{'memory': None, 'steps': [('preprocessor', vtreat.vtreat_api.BinomialOutcomeTreatment(outcome_target=True,\n",
-      "params={'coders': {'clean_copy',\n",
-      "            'deviation_code',\n",
-      "            'impact_code',\n",
-      "            'indicator_code',\n",
-      "            'logit_code',\n",
-      "            'missing_indicator',\n",
-      "            'prevalence_code'},\n",
-      " 'cross_validation_k': 5,\n",
-      " 'cross_validation_plan': <vtreat.cross_plan.KWayCrossPlanYStratified object at 0x10fa81b50>,\n",
-      " 'filter_to_recommended': True,\n",
-      " 'indicator_min_fraction': 0.1,\n",
-      " 'missingness_imputation': <function mean at 0x11093bb90>,\n",
-      " 'sparse_indicators': True,\n",
-      " 'use_hierarchical_estimate': True,\n",
-      " 'user_transforms': []},\n",
-      ")), ('classifier', LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,\n",
+      "{'memory': None, 'steps': [('preprocessor', vtreat.vtreat_api.BinomialOutcomeTreatment(outcome_target=True, )), ('classifier', LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,\n",
       "                   intercept_scaling=1, l1_ratio=None, max_iter=100,\n",
       "                   multi_class='warn', n_jobs=None, penalty='l2',\n",
       "                   random_state=None, solver='lbfgs', tol=0.0001, verbose=0,\n",
-      "                   warm_start=False))], 'verbose': False, 'preprocessor': vtreat.vtreat_api.BinomialOutcomeTreatment(outcome_target=True,\n",
-      "params={'coders': {'clean_copy',\n",
-      "            'deviation_code',\n",
-      "            'impact_code',\n",
-      "            'indicator_code',\n",
-      "            'logit_code',\n",
-      "            'missing_indicator',\n",
-      "            'prevalence_code'},\n",
-      " 'cross_validation_k': 5,\n",
-      " 'cross_validation_plan': <vtreat.cross_plan.KWayCrossPlanYStratified object at 0x10fa81b50>,\n",
-      " 'filter_to_recommended': True,\n",
-      " 'indicator_min_fraction': 0.1,\n",
-      " 'missingness_imputation': <function mean at 0x11093bb90>,\n",
-      " 'sparse_indicators': True,\n",
-      " 'use_hierarchical_estimate': True,\n",
-      " 'user_transforms': []},\n",
-      "), 'classifier': LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,\n",
+      "                   warm_start=False))], 'verbose': False, 'preprocessor': vtreat.vtreat_api.BinomialOutcomeTreatment(outcome_target=True, ), 'classifier': LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,\n",
       "                   intercept_scaling=1, l1_ratio=None, max_iter=100,\n",
       "                   multi_class='warn', n_jobs=None, penalty='l2',\n",
       "                   random_state=None, solver='lbfgs', tol=0.0001, verbose=0,\n",
-      "                   warm_start=False), 'preprocessor__use_hierarchical_estimate': True, 'preprocessor__coders': {'prevalence_code', 'logit_code', 'indicator_code', 'deviation_code', 'impact_code', 'missing_indicator', 'clean_copy'}, 'preprocessor__filter_to_recommended': True, 'preprocessor__indicator_min_fraction': 0.1, 'preprocessor__cross_validation_plan': <vtreat.cross_plan.KWayCrossPlanYStratified object at 0x10fa81b50>, 'preprocessor__cross_validation_k': 5, 'preprocessor__user_transforms': [], 'preprocessor__sparse_indicators': True, 'preprocessor__missingness_imputation': <function mean at 0x11093bb90>, 'preprocessor__outcome_target': True, 'classifier__C': 1.0, 'classifier__class_weight': None, 'classifier__dual': False, 'classifier__fit_intercept': True, 'classifier__intercept_scaling': 1, 'classifier__l1_ratio': None, 'classifier__max_iter': 100, 'classifier__multi_class': 'warn', 'classifier__n_jobs': None, 'classifier__penalty': 'l2', 'classifier__random_state': None, 'classifier__solver': 'lbfgs', 'classifier__tol': 0.0001, 'classifier__verbose': 0, 'classifier__warm_start': False}\n"
+      "                   warm_start=False), 'classifier__C': 1.0, 'classifier__class_weight': None, 'classifier__dual': False, 'classifier__fit_intercept': True, 'classifier__intercept_scaling': 1, 'classifier__l1_ratio': None, 'classifier__max_iter': 100, 'classifier__multi_class': 'warn', 'classifier__n_jobs': None, 'classifier__penalty': 'l2', 'classifier__random_state': None, 'classifier__solver': 'lbfgs', 'classifier__tol': 0.0001, 'classifier__verbose': 0, 'classifier__warm_start': False}\n"
      ]
     }
    ],

README.md

@@ -12,7 +12,7 @@ in a statistically sound manner.
 Install `vtreat` with either of:
 
   * `pip install vtreat`
-  * `pip install https://github.com/WinVector/pyvtreat/raw/master/pkg/dist/vtreat-0.3.5.tar.gz`
+  * `pip install https://github.com/WinVector/pyvtreat/raw/master/pkg/dist/vtreat-0.3.6.tar.gz`
 
 # Details
 

coverage.txt

@@ -20,13 +20,13 @@ pkg/tests/test_util.py .                                                 [100%]
 Name                        Stmts   Miss  Cover
 -----------------------------------------------
 pkg/vtreat/__init__.py          6      0   100%
-pkg/vtreat/cross_plan.py       94     52    45%
-pkg/vtreat/transform.py        13      8    38%
+pkg/vtreat/cross_plan.py      104     57    45%
+pkg/vtreat/transform.py        17     10    41%
 pkg/vtreat/util.py            161     26    84%
-pkg/vtreat/vtreat_api.py      327    133    59%
+pkg/vtreat/vtreat_api.py      295    101    66%
 pkg/vtreat/vtreat_impl.py     481     79    84%
 -----------------------------------------------
-TOTAL                        1082    298    72%
+TOTAL                        1064    273    74%
 
 
-============================== 13 passed in 7.16s ==============================
+============================== 13 passed in 6.62s ==============================

pkg/README.md

@@ -12,7 +12,7 @@ in a statistically sound manner.
 Install `vtreat` with either of:
 
   * `pip install vtreat`
-  * `pip install https://github.com/WinVector/pyvtreat/raw/master/pkg/dist/vtreat-0.3.4.tar.gz`
+  * `pip install https://github.com/WinVector/pyvtreat/raw/master/pkg/dist/vtreat-0.3.6.tar.gz`
 
 # Details
 

pkg/build/lib/vtreat/__init__.py

@@ -7,7 +7,7 @@
 from vtreat.vtreat_api import *
 
 __docformat__ = "restructuredtext"
-__version__ = "0.3.5"
+__version__ = "0.3.6"
 
 __doc__ = """
 This<https://github.com/WinVector/pyvtreat> is the Python version of the vtreat data preparation system

pkg/build/lib/vtreat/cross_plan.py

@@ -15,11 +15,17 @@ class CrossValidationPlan:
     """Data splitting plan"""
 
     def __init__(self):
-        self.verbose_ = False
+        pass
 
     def split_plan(self, *, n_rows=None, k_folds=None, data=None, y=None):
         raise NotImplementedError("base class called")
 
+    def __repr__(self):
+        return "vtreat.cross_plan.CrossValidationPlan()"
+
+    def __str__(self):
+        return self.__repr__()
+
 
 def k_way_cross_plan(n_rows, k_folds):
     """randomly split range(n_rows) into k_folds disjoint groups"""
@@ -59,6 +65,9 @@ def split_plan(self, *, n_rows=None, k_folds=None, data=None, y=None):
             raise ValueError("k_folds must not be None")
         return k_way_cross_plan(n_rows=n_rows, k_folds=k_folds)
 
+    def __repr__(self):
+        return "vtreat.cross_plan.KWayCrossPlan()"
+
 
 def k_way_cross_plan_y_stratified(n_rows, k_folds, y):
     """randomly split range(n_rows) into k_folds disjoint groups, attempting an even y-distribution"""
@@ -116,6 +125,9 @@ def split_plan(self, *, n_rows=None, k_folds=None, data=None, y=None):
             raise ValueError("y must not be None")
         return k_way_cross_plan_y_stratified(n_rows=n_rows, k_folds=k_folds, y=y)
 
+    def __repr__(self):
+        return "vtreat.cross_plan.KWayCrossPlanYStratified()"
+
 
 def order_cross_plan(k_folds, order_vector):
     """Build a k_folds cross validation plan based on the ordered series"""
@@ -170,3 +182,6 @@ def split_plan(self, *, n_rows=None, k_folds=None, data=None, y=None):
             raise ValueError("k_folds must not be None")
         order_vector = data[self.order_column_name_]
         return order_cross_plan(k_folds=k_folds, order_vector=order_vector)
+
+    def __repr__(self):
+        return "vtreat.cross_plan.OrderedCrossPlan()"

pkg/build/lib/vtreat/transform.py

@@ -19,3 +19,15 @@ def transform(self, X):
     def fit_transform(self, X, y):
         self.fit(X, y)
         return self.transform(X)
+
+    def __repr__(self):
+        return ("vtreat.transform.UserTransform("
+                + "treatment=" + self.treatment_.__repr__()
+                + ") {"
+                + "'y_aware_': " + str(self.y_aware_)
+                + ", " + "'treatment_': " + str(self.treatment_)
+                + ", " + "'incoming_vars_': " + str(self.incoming_vars_)
+                + "}")
+
+    def __str__(self):
+        return self.__repr__()