Exemple #1
0
 def test_bin_feature(self):
     df = pd.DataFrame([[0, 1], [7, 2], [6, 3]], 
                       columns=["MATH100", "PHYS125"])
     dataset = DataSet(df)
     
     dataset.bin("MATH100", [4, 7])
     
     assert_that(dataset, equals_dataset([[0, 1], [2, 2], [1, 3]]))
Exemple #2
0
 def test_bin_all(self):
     df = pd.DataFrame([[0, 6], [9, 2], [6, 4]], 
                       columns=["MATH100", "PHYS125"])
     dataset = DataSet(df)
     
     dataset.bin("*", [4, 7], bin_names=["low", "mid", "high"])
     
     assert_that(dataset, equals_dataset([["low", "mid"], ["high", "low"], 
                                          ["mid", "mid"]]))
Exemple #3
0
 def test_bin_feature_floats(self):
     df = pd.DataFrame([[3.5, 1], [9.1, 2], [6.2, 3]], 
                       columns=["MATH100", "PHYS125"])
     dataset = DataSet(df)
     
     dataset.bin("MATH100", [3.9, 7], bin_names=["low", "mid", "high"])
     
     assert_that(dataset, equals_dataset([["low", 1], ["high", 2], 
                                          ["mid", 3]]))
Exemple #4
0
 def test_bin_feature_1_boundary(self):
     df = pd.DataFrame([[0, 1], [9, 2], [6, 3]], 
                       columns=["MATH100", "PHYS125"])
     dataset = DataSet(df)
     
     dataset.bin("MATH100", [3], bin_names=["low", "high"])
     
     assert_that(dataset, equals_dataset([["low", 1], ["high", 2], 
                                          ["high", 3]]))