def test_read_raw_file_FileNotFoundError():
path = 'nonsense'
with pytest.raises(FileNotFoundError):
mk.read_raw_file(path, minimal_length=4)
def test_read_raw_file_number_of_lines():
number_of_records = 69934
path = './datasource/influx-export.csv'
data = mk.read_raw_file(path, minimal_length=4)
assert data.__len__() == number_of_records
def test_read_raw_file_FileTooShort():
path = './datasource/influx-export_testfile_header_only.csv'
with pytest.raises(mk.FileTooShort):
mk.read_raw_file(path, minimal_length=4)
def test_read_raw_file_type():
path = './datasource/influx-export.csv'
data = mk.read_raw_file(path, minimal_length=4)
assert type(data) is list
target_file_prefix = None
data_directory = './aws-datasource'
charts_directory = './aws-diagrams'
# source_file = 'influx-export-short.csv'
source_file = 'influx-export.csv'
attributes = [
'co2_hum', 'co2_ppm', 'co2_tmp', 'ec', 'ph', 'rpi_t', 'rtd_t', 'tsl'
]
print("Downloading data from AWS S3")
logging.info("Downloading data from AWS S3")
get_data_from_s3(source_bucket, source_file_name,
os.path.join(data_directory, source_file))
source_file_path = os.path.join(data_directory, source_file)
source_data = mikrolab.read_raw_file(source_file_path)
for index in range(10):
print("{}".format(source_data[index]))
sd_location, sd_feature_names, sd_column_lengths, sd_dataset = mikrolab.process_data(
source_data)
print("Location: {}".format(sd_location))
print("Feature names: {}".format(",".join(sd_feature_names)))
print("Column lengths: {}".format(",".join(
str(l) for l in sd_column_lengths)))
print("number of data points: {}".format(sd_dataset.__len__()))
print("last datapoint: {}".format(sd_dataset[-20:-1]))
mikrolab.write_csv_file(target_directory, target_file_prefix, sd_location,