def test_merge_most_common_chars_count(self):
### default values of most common chars for both profiles
text_profile1 = TextProfiler("Name")
sample1 = pd.Series(["this is test,", " this is a test sentence"])
text_profile1.update(sample1)
text_profile2 = TextProfiler("Name")
sample2 = pd.Series(["this is", "this"])
text_profile2.update(sample2)
text_profile3 = text_profile1 + text_profile2
profile = text_profile3.profile
# as merged profile's vocab_count length is None, it is set to
# the length of the merged vocab_count, which is 10
expected_vocab_count = {
's': 10,
't': 9,
' ': 8,
'i': 7,
'e': 5,
'h': 4,
'n': 2,
',': 1,
'a': 1,
'c': 1
}
self.assertDictEqual(expected_vocab_count, profile["vocab_count"])
### one profile has default values of most common chars
### the other profile has it set
text_profile1._top_k_chars = 3
text_profile3 = text_profile1 + text_profile2
profile = text_profile3.profile
# as merged profile's vocab_count length is None, it is set to
# the length of the merged vocab_count, which is 10
expected_vocab_count = {
's': 10,
't': 9,
' ': 8,
'i': 7,
'e': 5,
'h': 4,
'n': 2,
',': 1,
'a': 1,
'c': 1
}
self.assertDictEqual(expected_vocab_count, profile["vocab_count"])
### equal number of most common chars
text_profile1._top_k_chars = 3
text_profile2._top_k_chars = 3
text_profile3 = text_profile1 + text_profile2
profile = text_profile3.profile
expected_vocab_count = {'s': 10, 't': 9, ' ': 8}
self.assertDictEqual(expected_vocab_count, profile["vocab_count"])
### different number of most common chars
text_profile1._top_k_chars = 2
text_profile2._top_k_chars = 3
text_profile3 = text_profile1 + text_profile2
profile = text_profile3.profile
expected_vocab_count = {'s': 10, 't': 9, ' ': 8}
self.assertDictEqual(expected_vocab_count, profile["vocab_count"])
def test_merge_most_common_chars_count(self):
### default values of most common chars for both profiles
text_profile1 = TextProfiler("Name")
sample1 = pd.Series(["this is test,", " this is a test sentence"])
text_profile1.update(sample1)
text_profile2 = TextProfiler("Name")
sample2 = pd.Series(["this is", "this"])
text_profile2.update(sample2)
text_profile3 = text_profile1 + text_profile2
profile = text_profile3.profile
# as merged profile's vocab_count length is None, it is set to
# the length of the merged vocab_count, which is 10
expected_vocab_count = {
"s": 10,
"t": 9,
" ": 8,
"i": 7,
"e": 5,
"h": 4,
"n": 2,
",": 1,
"a": 1,
"c": 1,
}
self.assertDictEqual(expected_vocab_count, profile["vocab_count"])
### one profile has default values of most common chars
### the other profile has it set
text_profile1._top_k_chars = 3
text_profile3 = text_profile1 + text_profile2
profile = text_profile3.profile
# as merged profile's vocab_count length is None, it is set to
# the length of the merged vocab_count, which is 10
expected_vocab_count = {
"s": 10,
"t": 9,
" ": 8,
"i": 7,
"e": 5,
"h": 4,
"n": 2,
",": 1,
"a": 1,
"c": 1,
}
self.assertDictEqual(expected_vocab_count, profile["vocab_count"])
### equal number of most common chars
text_profile1._top_k_chars = 3
text_profile2._top_k_chars = 3
text_profile3 = text_profile1 + text_profile2
profile = text_profile3.profile
expected_vocab_count = {"s": 10, "t": 9, " ": 8}
self.assertDictEqual(expected_vocab_count, profile["vocab_count"])
### different number of most common chars
text_profile1._top_k_chars = 2
text_profile2._top_k_chars = 3
text_profile3 = text_profile1 + text_profile2
profile = text_profile3.profile
expected_vocab_count = {"s": 10, "t": 9, " ": 8}
self.assertDictEqual(expected_vocab_count, profile["vocab_count"])