fix: add sliced string as a separate column (#71)

chrislemke · Jan 25, 2023 · 743f617 · 743f617
1 parent b03d46a
commit 743f617
Show file tree

Hide file tree

Showing 4 changed files with 61 additions and 59 deletions.
diff --git a/poetry.lock b/poetry.lock
diff --git a/requirements.txt b/requirements.txt
@@ -480,9 +480,9 @@ jsonschema==4.17.3 ; python_version >= "3.8" and python_version < "3.11" \
 jupyter-client==7.4.9 ; python_version >= "3.8" and python_version < "3.11" \
     --hash=sha256:214668aaea208195f4c13d28eb272ba79f945fc0cf3f11c7092c20b2ca1980e7 \
     --hash=sha256:52be28e04171f07aed8f20e1616a5a552ab9fee9cbbe6c1896ae170c3880d392
-jupyter-core==5.1.4 ; python_version >= "3.8" and python_version < "3.11" \
-    --hash=sha256:80d29fef4210ca8d30f25018a28d06dcc582bb1a82b848f2eab61a349a007af1 \
-    --hash=sha256:fe812ffffd0ead286327dc570888684183cef4070e57d9ebadc92f3bd9c9a05d
+jupyter-core==5.1.5 ; python_version >= "3.8" and python_version < "3.11" \
+    --hash=sha256:83064d61bb2a9bc874e8184331c117b3778c2a7e1851f60cb00d273ceb3285ae \
+    --hash=sha256:8e54c48cde1e0c8345f64bcf9658b78044ddf02b273726cea9d9f59be4b02130
 jupyterlab-widgets==3.0.5 ; python_version >= "3.8" and python_version < "3.11" \
     --hash=sha256:a04a42e50231b355b7087e16a818f541e53589f7647144ea0344c4bf16f300e5 \
     --hash=sha256:eeaecdeaf6c03afc960ddae201ced88d5979b4ca9c3891bcb8f6631af705f5ef
@@ -1146,28 +1146,28 @@ pyzmq==25.0.0 ; python_version >= "3.8" and python_version < "3.11" \
 requests==2.28.2 ; python_version >= "3.8" and python_version < "3.11" \
     --hash=sha256:64299f4909223da747622c030b781c0d7811e359c37124b4bd368fb8c6518baa \
     --hash=sha256:98b1b2782e3c6c4904938b84c0eb932721069dfdb9134313beff7c83c2df24bf
-scikit-learn==1.2.0 ; python_version >= "3.8" and python_version < "3.11" \
-    --hash=sha256:0834e4cec2a2e0d8978f39cb8fe1cad3be6c27a47927e1774bf5737ea65ec228 \
-    --hash=sha256:184a42842a4e698ffa4d849b6019de50a77a0aa24d26afa28fa49c9190bb144b \
-    --hash=sha256:1beaa631434d1f17a20b1eef5d842e58c195875d2bc11901a1a70b5fe544745b \
-    --hash=sha256:23a88883ca60c571a06278e4726b3b51b3709cfa4c93cacbf5568b22ba960899 \
-    --hash=sha256:25ba705ee1600ffc5df1dccd8fae129d7c6836e44ffcbb52d78536c9eaf8fcf9 \
-    --hash=sha256:40f3ff68c505cb9d1f3693397c73991875d609da905087e00e7b4477645ec67b \
-    --hash=sha256:4e1ea0bc1706da45589bcf2490cde6276490a1b88f9af208dbb396fdc3a0babf \
-    --hash=sha256:5546a8894a0616e92489ef995b39a0715829f3df96e801bb55cbf196be0d9649 \
-    --hash=sha256:680b65b3caee469541385d2ca5b03ff70408f6c618c583948312f0d2125df680 \
-    --hash=sha256:6b63ca2b0643d30fbf9d25d93017ed3fb8351f31175d82d104bfec60cba7bb87 \
-    --hash=sha256:83c772fa8c64776ad769fd764752c8452844307adcf10dee3adcc43988260f21 \
-    --hash=sha256:867023a044fdfe59e5014a7fec7a3086a8928f10b5dce9382eedf4135f6709a2 \
-    --hash=sha256:bc7073e025b62c1067cbfb76e69d08650c6b9d7a0e7afdfa20cb92d4afe516f6 \
-    --hash=sha256:ceb0008f345188aa236e49c973dc160b9ed504a3abd7b321a0ecabcb669be0bd \
-    --hash=sha256:d395730f26d8fc752321f1953ddf72647c892d8bed74fad4d7c816ec9b602dfa \
-    --hash=sha256:da29d2e379c396a63af5ed4b671ad2005cd690ac373a23bee5a0f66504e05272 \
-    --hash=sha256:de897720173b26842e21bed54362f5294e282422116b61cd931d4f5d870b9855 \
-    --hash=sha256:e9535e867281ae6987bb80620ba14cf1649e936bfe45f48727b978b7a2dbe835 \
-    --hash=sha256:f17420a8e3f40129aeb7e0f5ee35822d6178617007bb8f69521a2cefc20d5f00 \
-    --hash=sha256:fc0a72237f0c56780cf550df87201a702d3bdcbbb23c6ef7d54c19326fa23f19 \
-    --hash=sha256:fd3480c982b9e616b9f76ad8587804d3f4e91b4e2a6752e7dafb8a2e1f541098
+scikit-learn==1.2.1 ; python_version >= "3.8" and python_version < "3.11" \
+    --hash=sha256:479aedd0abedbda6b8b4529145fe4cd8622f69f726a72cef8f75548a93eeb1e1 \
+    --hash=sha256:54731e2c2fbff40da6d76cbb9022ace5f44a4020a10bd5cd92107e86882bad15 \
+    --hash=sha256:5523e21ab2b4d52b2bd41bedd335dbe8f3c1b5f6dd7c9c001b2e17ec9818af8d \
+    --hash=sha256:559f66e12f93b34c8c85c0a5728c3b8af98f04eb12f2c9ee18ea3c82c3d2fad1 \
+    --hash=sha256:5a8111f3c7a314017ebf90d6feab861c11d1ca14f3dbafb39abcc31aa4c54ba6 \
+    --hash=sha256:5b2c5d9930ced2b7821ad936b9940706ccb5471d89b8a516bb641cec87257d1c \
+    --hash=sha256:61bb9c654b5d2e6cdd4b1c7e6048fc66270c1682bda1b0f7d2726fdae09010f4 \
+    --hash=sha256:70fa30d146b7e9d0c256e73e271b3e17f23123b7c4adcbde1a385031adf59090 \
+    --hash=sha256:a9abf17d177df54e529154f26acfd42930e19117d045e8a9a8e893ca82dd94ec \
+    --hash=sha256:bed9f75763bd392c094bf474c7ab75a01d68b15146ea7a20c0f9ff6fb3063dad \
+    --hash=sha256:c722f3446ad8c4f1a93b2399fe1a188635b94709a3f25e6f4d61efbe75fe8eaa \
+    --hash=sha256:c9285275a435d1f8f47bbe3500346ab9ead2499e0e090518404d318ea90d1c1c \
+    --hash=sha256:cba0c7c6bf1493f8ce670bab69f9317874826ee838988de377ae355abd4d74cf \
+    --hash=sha256:d00e46a2a7fce6e118ed0f4c6263785bf6c297a94ffd0cd7b32455043c508cc8 \
+    --hash=sha256:d8bcd303dd982494842a3f482f844d539484c6043b4eed896b43ea8e5f609a21 \
+    --hash=sha256:da0e2d50a8435ea8dc5cd21f1fc1a45d329bae03dcca92087ebed859d22d184e \
+    --hash=sha256:dbb7831b2308c67bb6dd83c5ea3cdaf8e8cafd2de4000b93d78bb689126bd2cf \
+    --hash=sha256:dc838b5a4057c55ba81b82316ea8bf443af445f96eb21500b0e40618017e0923 \
+    --hash=sha256:dcfab6a19b236194af88771d8e6e778a60c3339248ab0018696ebf2b7c8bed4b \
+    --hash=sha256:e0ee4d4d32c94e082344308528f7b3c9294b60ab19c84eb37a2d9c88bdffd9d1 \
+    --hash=sha256:fbf8a5c893c9b4b99bcc7ed8fb3e8500957a113f4101860386d06635520f7cfb
 scipy==1.10.0 ; python_version >= "3.8" and python_version < "3.11" \
     --hash=sha256:0490dc499fe23e4be35b8b6dd1e60a4a34f0c4adb30ac671e6332446b3cbbb5a \
     --hash=sha256:0ab2a58064836632e2cec31ca197d3695c86b066bc4818052b3f5381bfd2a728 \

diff --git a/src/sk_transformers/string_transformer.py b/src/sk_transformers/string_transformer.py
@@ -347,10 +347,10 @@ class StringSlicerTransformer(BaseTransformer):
     transformer.fit_transform(X)
     ```
     ```
-      foo bar
-    0  ac  jk
-    1  df  mn
-    2  gi  pq
+       foo  bar foo_slice bar_slice
+    0  abc  jkl        ac        jk
+    1  def  mno        df        mn
+    2  ghi  pqr        gi        pq
     ```
 
     Args:
@@ -381,7 +381,7 @@ def transform(self, X: pd.DataFrame) -> pd.DataFrame:
         X = check_ready_to_transform(self, X, [feature[0] for feature in self.features])
 
         for feature, slice_args in self.features:
-            X[feature] = [x[slice(*slice_args)] for x in X[feature]]
+            X[feature + "_slice"] = [x[slice(*slice_args)] for x in X[feature]]
 
         return X
 

diff --git a/tests/test_transformer/test_string_transformer.py b/tests/test_transformer/test_string_transformer.py
@@ -128,23 +128,23 @@ def test_string_slicer_transformer_in_pipeline(X_strings):
 
     expected = pd.DataFrame(
         {
-            "email": [
+            "email_slice": [
                 "test@",
                 "test1",
                 "test_",
                 "test_",
                 "ttt@t",
                 "test_",
             ],
-            "strings_1": [
+            "strings_1_slice": [
                 "a_string",
                 "another_",
                 "a_third_",
                 "a_fourth",
                 "a_fifth_",
                 "a_sixth_",
             ],
-            "strings_2": [
+            "strings_2_slice": [
                 "i_o__",
                 "i_nte",
                 "i  hr",
@@ -156,7 +156,9 @@ def test_string_slicer_transformer_in_pipeline(X_strings):
     )
 
     assert pipeline.steps[0][0] == "stringslicertransformer"
-    assert result.equals(expected)
+    assert result[["email_slice", "strings_1_slice", "strings_2_slice"]].equals(
+        expected
+    )
 
 
 def test_string_splitter_transformer_in_pipeline(X_strings):