version 0.17.2 with self.n_classes_

Author: thierrymoudiki

CHANGES.md

@@ -1,3 +1,7 @@
+# version 0.17.2
+
+- `self.n_classes_ = len(np.unique(y))` # for compatibility with sklearn 
+
 # version 0.17.1
 
 - `preprocess`ing for all `LazyDeep*`

nnetsauce/boosting/adaBoostClassifier.py

@@ -248,6 +248,7 @@ def fit(self, X, y, sample_weight=None, **kwargs):
         # training
         n, p = X.shape
         self.n_classes = len(np.unique(y))
+        self.n_classes_ = len(np.unique(y)) # for compatibility with sklearn 
 
         if sample_weight is None:
             w_m = np.repeat(1.0 / n, n)

nnetsauce/custom/customClassifier.py

@@ -187,6 +187,7 @@ def fit(self, X, y, sample_weight=None, **kwargs):
         """
 
         output_y, scaled_Z = self.cook_training_set(y=y, X=X, **kwargs)
+        self.n_classes_ = len(np.unique(y)) # for compatibility with sklearn 
 
         # if sample_weights, else: (must use self.row_index)
         if sample_weight is not None:

nnetsauce/deep/deepClassifier.py

@@ -101,6 +101,8 @@ def fit(self, X, y):
         if isinstance(X, np.ndarray):
             X = pd.DataFrame(X)
 
+        self.n_classes_ = len(np.unique(y)) # for compatibility with sklearn 
+        
         # init layer
         self.stacked_obj = CustomClassifier(
             obj=self.stacked_obj,

nnetsauce/glm/glmClassifier.py

@@ -221,6 +221,8 @@ def fit(self, X, y, **kwargs):
             y
         ), "y must contain only integers"  # change is_factor and subsampling everywhere
 
+        self.n_classes_ = len(np.unique(y)) # for compatibility with sklearn 
+
         self.beta_ = None
 
         n, p = X.shape

nnetsauce/lazypredict/lazydeepClassifier.py

@@ -91,7 +91,7 @@ class LazyDeepRegressor(Custom, RegressorMixin):
         estimators: list, optional (default='all')
             list of Estimators names or just 'all' (default='all')
 
-        preprocess: bool 
+        preprocess: bool
             preprocessing is done when set to True
 
         n_jobs : int, when possible, run in parallel
@@ -264,7 +264,7 @@ def fit(self, X_train, X_test, y_train, y_test):
             ]
 
         if self.preprocess is True:
-            
+
             for name, model in tqdm(self.regressors):  # do parallel exec
                 start = time.time()
                 try:
@@ -305,7 +305,7 @@ def fit(self, X_train, X_test, y_train, y_test):
                             row_sample=self.row_sample,
                             seed=self.seed,
                             backend=self.backend,
-                        )                    
+                        )
 
                     for _ in range(self.n_layers):
                         layer_regr = deepcopy(
@@ -331,9 +331,13 @@ def fit(self, X_train, X_test, y_train, y_test):
 
                     layer_regr.fit(X_train, y_train)
 
-                    pipe = Pipeline(steps=[("preprocessor", preprocessor),
-                                ("regressor", layer_regr)])
-                    
+                    pipe = Pipeline(
+                        steps=[
+                            ("preprocessor", preprocessor),
+                            ("regressor", layer_regr),
+                        ]
+                    )
+
                     pipe.fit(X_train, y_train)
 
                     self.models[name] = pipe
@@ -376,7 +380,7 @@ def fit(self, X_train, X_test, y_train, y_test):
                         print(name + " model failed to execute")
                         print(exception)
 
-        else: # no preprocessing
+        else:  # no preprocessing
 
             for name, model in tqdm(self.regressors):  # do parallel exec
                 start = time.time()

nnetsauce/lazypredict/lazydeepRegressor.py

@@ -189,6 +189,8 @@ def fit(self, X, y, sample_weight=None, **kwargs):
 
         assert mx.is_factor(y), "y must contain only integers"
 
+        self.n_classes_ = len(np.unique(y)) # for compatibility with sklearn 
+
         output_y, scaled_Z = self.cook_training_set(y=y, X=X, **kwargs)
 
         self.n_classes_ = len(np.unique(y))

nnetsauce/multitask/multitaskClassifier.py

@@ -105,9 +105,9 @@ def fit(self, X, y, sample_weight=None, **kwargs):
 
         assert mx.is_factor(y), "y must contain only integers"
 
-        self.scaled_X_ = self.X_scaler_.fit_transform(X)
+        self.n_classes_ = len(np.unique(y)) # for compatibility with sklearn 
 
-        self.n_classes_ = len(np.unique(y))
+        self.scaled_X_ = self.X_scaler_.fit_transform(X)        
 
         # multitask response
         Y = mo.one_hot_encode2(y, self.n_classes_)

nnetsauce/multitask/simplemultitaskClassifier.py

@@ -200,6 +200,8 @@ def fit(self, X, y, **kwargs):
 
         assert mx.is_factor(y), "y must contain only integers"
 
+        self.n_classes_ = len(np.unique(y)) # for compatibility with sklearn 
+
         # training
         self.n_classes = len(np.unique(y))
 

nnetsauce/randombag/randomBagClassifier.py

@@ -323,6 +323,8 @@ def fit(self, X, y, solver="L-BFGS-B", **kwargs):
 
         assert mx.is_factor(y), "y must contain only integers"
 
+        self.n_classes_ = len(np.unique(y)) # for compatibility with sklearn 
+
         output_y, scaled_Z = self.cook_training_set(y=y, X=X, **kwargs)
 
         self.n_classes = len(np.unique(y))

nnetsauce/ridge2/ridge2Classifier.py

@@ -178,6 +178,8 @@ def fit(self, X, y, **kwargs):
 
         assert mx.is_factor(y), "y must contain only integers"
 
+        self.n_classes_ = len(np.unique(y)) # for compatibility with sklearn 
+
         output_y, scaled_Z = self.cook_training_set(y=y, X=X, **kwargs)
 
         n_X, p_X = X.shape

nnetsauce/ridge2/ridge2MultitaskClassifier.py

@@ -3,7 +3,7 @@
 from codecs import open
 from os import path
 
-__version__ = '0.17.1'
+__version__ = '0.17.2'
 
 # get the dependencies and installs
 here = path.abspath(path.dirname(__file__))