def validate_summary(self):
"""Ensure the summary is correct."""
data_path = url_path_join(self.warehouse_path, 'course_enrollment_summary', 'dt=2014-08-07')
raw_output = self.read_dfs_directory(data_path)
output = StringIO(raw_output.replace('\t\\N', '\t'))
columns = EnrollmentSummaryRecord.get_fields().keys()
data = pandas.read_table(output, header=None, names=columns, parse_dates=True)
expected_output_csv = os.path.join(self.data_dir, 'output', 'acceptance_expected_d_user_course.csv')
expected = pandas.read_csv(expected_output_csv, parse_dates=True)
for frame in (data, expected):
frame.sort('first_enrollment_time', inplace=True, ascending=True)
frame.reset_index(drop=True, inplace=True)
self.assert_data_frames_equal(data, expected)
def validate_summary(self):
"""Ensure the summary is correct."""
data_path = url_path_join(self.warehouse_path,
'course_enrollment_summary', 'dt=2014-08-06')
raw_output = self.read_dfs_directory(data_path)
output = StringIO(raw_output.replace('\t\\N', '\t'))
columns = EnrollmentSummaryRecord.get_fields().keys()
data = pandas.read_table(output,
header=None,
names=columns,
parse_dates=True)
expected_output_csv = os.path.join(
self.data_dir, 'output', 'acceptance_expected_d_user_course.csv')
expected = pandas.read_csv(expected_output_csv, parse_dates=True)
for frame in (data, expected):
frame.sort('first_enrollment_time', inplace=True, ascending=True)
frame.reset_index(drop=True, inplace=True)
self.assert_data_frames_equal(data, expected)
def columns(self):
return EnrollmentSummaryRecord.get_sql_schema()
