adds package versions and optional model name to saved pipelines

auto_ml/predictor.py

@@ -189,7 +189,7 @@ def _construct_pipeline(self, model_name='LogisticRegression', trained_pipeline=
             final_model = utils_models.get_model_from_name(model_name, training_params=params)
             pipeline_list.append(('final_model', utils_model_training.FinalModelATC(model=final_model, type_of_estimator=self.type_of_estimator, ml_for_analytics=self.ml_for_analytics, name=self.name, _scorer=self._scorer, feature_learning=feature_learning, uncertainty_model=self.need_to_train_uncertainty_model, training_prediction_intervals=training_prediction_intervals, column_descriptions=self.column_descriptions, training_features=training_features, keep_cat_features=keep_cat_features, is_hp_search=is_hp_search, X_test=self.X_test, y_test=self.y_test)))
 
-        constructed_pipeline = utils.ExtendedPipeline(pipeline_list, keep_cat_features=keep_cat_features)
+        constructed_pipeline = utils.ExtendedPipeline(pipeline_list, keep_cat_features=keep_cat_features, name=self.name)
         return constructed_pipeline
 
 

auto_ml/utils.py

@@ -2,6 +2,7 @@
 import datetime
 import numbers
 import os
+import pkg_resources
 
 import numpy as np
 import pandas as pd
@@ -13,6 +14,8 @@
 from sklearn.utils.metaestimators import if_delegate_has_method
 from sklearn.utils import column_or_1d
 
+from _version import __version__ as auto_ml_version
+
 
 def is_linear_model(model_names):
     linear_models = set(['RANSACRegressor', 'LinearRegression', 'Ridge', 'Lasso', 'ElasticNet', 'LassoLars', 'OrthogonalMatchingPursuit', 'BayesianRidge', 'ARDRegression', 'SGDRegressor', 'PassiveAggressiveRegressor', 'LogisticRegression', 'RidgeClassifier', 'SGDClassifier', 'Perceptron', 'PassiveAggressiveClassifier'])
@@ -225,15 +228,6 @@ def __init__(self):
         super(self.__class__, self).__init__()
 
     def transform(self, y):
-        """Transform labels to normalized encoding.
-        Parameters
-        ----------
-        y : array-like of shape [n_samples]
-            Target values.
-        Returns
-        -------
-        y : array-like of shape [n_samples]
-        """
         y = column_or_1d(y, warn=True)
 
         classes = np.unique(y)
@@ -242,11 +236,31 @@ def transform(self, y):
             self.classes_ = np.hstack((self.classes_, diff))
         return np.searchsorted(self.classes_, y)[0]
 
+
+def get_versions():
+
+    libraries_to_check = ['dill', 'h5py', 'keras', 'lightgbm', 'numpy', 'pandas', 'pathos', 'python', 'scikit-learn', 'scipy', 'sklearn-deap2', 'tabulate', 'tensorflow', 'xgboost']
+
+    versions = {
+        'auto_ml': auto_ml_version
+    }
+
+    for lib in libraries_to_check:
+        try:
+            versions[lib] = pkg_resources.get_distribution(lib).version
+        except:
+            pass
+
+    return versions
+
+
 class ExtendedPipeline(Pipeline):
 
-    def __init__(self, steps, keep_cat_features=False):
+    def __init__(self, steps, keep_cat_features=False, name=None):
         super(self.__class__, self).__init__(steps)
         self.keep_cat_features = keep_cat_features
+        self.__versions__ = get_versions()
+        self.name = name
 
 
     @if_delegate_has_method(delegate='_final_estimator')