rm deaultf pararms + set default to minhash

amy12xx · Aug 18, 2020 · 8de9993 · 8de9993
1 parent bdaa1ab
commit 8de9993
Show file tree

Hide file tree

Showing 3 changed files with 3 additions and 5 deletions.
diff --git a/dirty_cat/minhash_encoder.py b/dirty_cat/minhash_encoder.py
@@ -57,7 +57,7 @@ class MinHashEncoder(BaseEstimator, TransformerMixin):
     
     """
 
-    def __init__(self, n_components, ngram_range=(2, 4),
+    def __init__(self, n_components=30, ngram_range=(2, 4),
                  hashing='fast', minmax_hash=False):
         self.ngram_range = ngram_range
         self.n_components = n_components

diff --git a/examples/02_fit_predict_plot_employee_salaries.py b/examples/02_fit_predict_plot_employee_salaries.py
@@ -73,8 +73,7 @@
     'one-hot': OneHotEncoder(handle_unknown='ignore', sparse=False),
     'similarity': SimilarityEncoder(similarity='ngram'),
     'target': TargetEncoder(handle_unknown='ignore'),
-    'minhash': MinHashEncoder(n_components=100, ngram_range=(2, 4),
-                              hashing='fast', minmax_hash=False),
+    'minhash': MinHashEncoder(n_components=100),
     'numerical': FunctionTransformer(None)}
 
 # We then create a function that takes one key of our ``encoders_dict``,

diff --git a/examples/03_fit_predict_plot_midwest_survey.py b/examples/03_fit_predict_plot_midwest_survey.py
@@ -69,8 +69,7 @@
 encoder_dict = {
     'one-hot': OneHotEncoder(handle_unknown='ignore', sparse=False),
     'similarity': SimilarityEncoder(similarity='ngram'),
-    'minhash': MinHashEncoder(n_components=30, ngram_range=(2, 4),
-                              hashing='fast', minmax_hash=False),
+    'minhash': MinHashEncoder(),
     'num': FunctionTransformer(None)
 }
 ##############################################################################