add h2o.trim() to python client and respective pyunit

h2o-py/h2o/frame.py

@@ -1154,6 +1154,18 @@ def transpose(self):
     expr = "(= !{} (t %{}))".format(tmp_key,frame_keys[0])
     return H2OFrame._get_frame_from_rapids_string(expr, tmp_key, frame_keys)
 
+  def trim(self):
+    """
+    Trim the edge-spaces in a column of strings (only operates on frame with one column)
+    :return: H2OFrame
+    """
+    if self._vecs is None or self._vecs == []:
+      raise ValueError("Frame Removed")
+    frame_keys = [self.send_frame()]
+    tmp_key = H2OFrame.py_tmp_key()
+    expr = "(= !{} (trim %{}))".format(tmp_key,frame_keys[0])
+    return H2OFrame._get_frame_from_rapids_string(expr, tmp_key, frame_keys)
+
   def table(self, data2=None):
     """
     :return: a frame of the counts at each combination of factor levels
@@ -1744,6 +1756,15 @@ def transpose(self):
     expr = "(= !{} (t %{}))".format(tmp_key,self.key())
     return H2OFrame._get_frame_from_rapids_string(expr, tmp_key, [])
 
+  def trim(self):
+    """
+    Trim the edge-spaces in a column of strings
+    :return: H2OVec
+    """
+    tmp_key = H2OFrame.py_tmp_key()
+    expr = "(= !{} (trim %{}))".format(tmp_key,self.key())
+    return H2OVec._get_vec_from_rapids_string(self, expr, tmp_key)
+
   def table(self, data2=None):
     """
     :return: a frame of the counts at each combination of factor levels

h2o-py/h2o/h2o.py

@@ -987,6 +987,7 @@ def var(data)   : return data.var()
 def mean(data)  : return data.mean()
 def median(data): return data.median()
 
+def trim(data)      : return data.trim()
 def asnumeric(data) : return data.asnumeric()
 def transpose(data) : return data.transpose()
 def anyfactor(data) : return data.anyfactor()

h2o-py/tests/testdir_munging/pyunit_trim.py

@@ -0,0 +1,31 @@
+import sys
+sys.path.insert(1, "../../")
+import h2o
+
+def trim_check(ip,port):
+    # Connect to a pre-existing cluster
+    h2o.init(ip,port)
+
+    frame = h2o.import_frame(path=h2o.locate("smalldata/junit/cars_trim.csv"))
+
+    # single column (frame)
+    trimmed_frame = h2o.trim(frame[["name"]])
+    assert trimmed_frame[0,0] == "AMC Ambassador Brougham", "Expected 'AMC Ambassador Brougham', but got " \
+                                                            "{0}".format(trimmed_frame[0,0])
+    assert trimmed_frame[1,0] == "AMC Ambassador DPL", "Expected 'AMC Ambassador DPL', but got " \
+                                                       "{0}".format(trimmed_frame[1,0])
+    assert trimmed_frame[2,0] == "AMC Ambassador SST", "Expected 'AMC Ambassador SST', but got " \
+                                                       "{0}".format(trimmed_frame[2,0])
+
+    # single column (vec)
+    vec = frame["name"]
+    trimmed_vec = h2o.trim(vec)
+    assert trimmed_vec[0] == "AMC Ambassador Brougham", "Expected 'AMC Ambassador Brougham', but got " \
+                                                        "{0}".format(trimmed_frame[0])
+    assert trimmed_vec[1] == "AMC Ambassador DPL", "Expected 'AMC Ambassador DPL', but got " \
+                                                   "{0}".format(trimmed_frame[1])
+    assert trimmed_vec[2] == "AMC Ambassador SST", "Expected 'AMC Ambassador SST', but got " \
+                                                   "{0}".format(trimmed_frame[2])
+
+if __name__ == "__main__":
+    h2o.run_test(sys.argv, trim_check)