From 639a6a09e716ac6f0014e80bbff4fff47e855b6a Mon Sep 17 00:00:00 2001
From: Sergey Melderis <sergey.melderis@gmail.com>
Date: Sat, 31 Mar 2018 22:43:19 -0400
Subject: [PATCH] idf_ setter for TfidfTransformer. Fixes #7102

---
 sklearn/feature_extraction/tests/test_text.py | 10 ++++++++++
 sklearn/feature_extraction/text.py            | 13 +++++++++++++
 2 files changed, 23 insertions(+)

diff --git a/sklearn/feature_extraction/tests/test_text.py b/sklearn/feature_extraction/tests/test_text.py
index 22fbd3f17bea8..8beadbb53ec33 100644
--- a/sklearn/feature_extraction/tests/test_text.py
+++ b/sklearn/feature_extraction/tests/test_text.py
@@ -942,6 +942,16 @@ def test_pickling_transformer():
         orig.fit_transform(X).toarray())
 
 
+def test_transformer_idf_setter():
+    X = CountVectorizer().fit_transform(JUNK_FOOD_DOCS)
+    orig = TfidfTransformer().fit(X)
+    copy = TfidfTransformer()
+    copy.idf_ = orig.idf_
+    assert_array_equal(
+        copy.fit_transform(X).toarray(),
+        orig.fit_transform(X).toarray())
+
+
 def test_non_unique_vocab():
     vocab = ['a', 'b', 'c', 'a', 'a']
     vect = CountVectorizer(vocabulary=vocab)
diff --git a/sklearn/feature_extraction/text.py b/sklearn/feature_extraction/text.py
index 9b1ebd6320b29..b231f20b463a9 100644
--- a/sklearn/feature_extraction/text.py
+++ b/sklearn/feature_extraction/text.py
@@ -1062,6 +1062,12 @@ class TfidfTransformer(BaseEstimator, TransformerMixin):
     sublinear_tf : boolean, default=False
         Apply sublinear tf scaling, i.e. replace tf with 1 + log(tf).
 
+    Attributes
+    ----------
+    idf_ : array, shape = [n_features], or None
+        The learned idf vector (global term weights)
+        when ``use_idf`` is set to True, None otherwise.
+
     References
     ----------
 
@@ -1157,6 +1163,13 @@ def idf_(self):
         # which means hasattr(self, "idf_") is False
         return np.ravel(self._idf_diag.sum(axis=0))
 
+    @idf_.setter
+    def idf_(self, value):
+        value = np.asarray(value, dtype=np.float64)
+        n_features = value.shape[0]
+        self._idf_diag = sp.spdiags(value, diags=0, m=n_features,
+                                    n=n_features, format='csr')
+
 
 class TfidfVectorizer(CountVectorizer):
     """Convert a collection of raw documents to a matrix of TF-IDF features.