def test_raise_error_when_columns_with_same_name_are_added():
test_question_1 = simplesurvey.Question("repeat_column_name")
test_question_2 = simplesurvey.Question("repeat_column_name")
survey = simplesurvey.Survey()
survey.add_column(test_question_1)
with pytest.raises(simplesurvey.DuplicateColumnException):
survey.add_column(test_question_2)
def test_set_response_data(tmpdir):
path = tmpdir.join("data.csv")
path.write("""col1,col2,col3
data1,data2,data2""")
survey = simplesurvey.Survey()
survey.responses(str(path))\
.add_column(simplesurvey.Question("col1"))\
.add_column(simplesurvey.Question("col2"))\
.add_column(simplesurvey.Question("col3"))\
.process()
result = survey.data
assert sorted(result.columns) == sorted(['col1', 'col2', 'col3'])
def test_add_question_to_survey():
test_question = simplesurvey.Question("A test column")
survey = simplesurvey.Survey()
survey.add_column(test_question)
assert len(survey.questions) == 1
assert survey.questions[0].column == "A test column"
def test_survey_summary_returns_summarizer_with_loaded_columns():
data = pd.DataFrame({'a': [1, 2, 3, 4, 5]})
survey = simplesurvey.Survey()
survey.responses(data)\
.add_column(simplesurvey.Question('a'))\
.process()
result = survey.summarize(['a'])
assert isinstance(result, simplesurvey.Summarizer)
def test_data_raises_exception_if_column_doesnt_exist():
survey = simplesurvey.Survey()
question1 = simplesurvey.Question("I am a missing column")
data = pd.DataFrame(data={'col1': ['1'], 'col2': ['2']})
survey._responses = data
survey.add_column(question1)
with pytest.raises(simplesurvey.SurveyLoadingException):
survey.process()
def test_supplementary_data(tmpdir):
path = tmpdir.join("data.csv")
path.write("""col1,col2,col3
1,data2,data2""")
suppath = tmpdir.join("data2.csv")
suppath.write("""natural_key,sup2,sup3
1,data2,data2""")
survey = simplesurvey.Survey()
survey.responses(str(path), natural_key='col1')\
.supplementary_data(str(suppath), "natural_key")\
.add_column(simplesurvey.Question("col2"))\
.add_column(simplesurvey.Question("col3"))\
.add_column(simplesurvey.Question("sup2"))\
.add_column(simplesurvey.Question("sup3"))\
.process()
result = survey.data
assert sorted(list(result.columns)) == sorted(
['col2', 'col3', 'sup2', 'sup3'])
def test_simple_filter_data():
survey = simplesurvey.Survey()
question1 = simplesurvey.Question("col1").add_filter(lambda x: x == 1)
data = pd.DataFrame(data={'col1': [1, 2, 3], 'col2': [2, 3, 4]})
survey._responses = data
survey.add_column(question1)\
.process()
result = survey.data
expected = pd.DataFrame({'col1': [1]})
assert result.equals(expected)