def test_generate_statistics_some_codes(self):
needed_feature_codes = random.sample(self.feature_codes, k=2)
file_processor = FileProcessor(self.input_file_path)
actual_stats = file_processor.generate_statistics(needed_feature_codes)
_, feature_codes, features = read_test_data_as_arrays(
self.input_file_path)
selected_indexes = []
for code in needed_feature_codes:
indexes = np.where(feature_codes == code)[0].tolist()
selected_indexes += indexes
selected_features = features[selected_indexes]
expected_stats = {
"count": np.uint32(selected_features.shape[0]),
"mean": selected_features.mean(axis=0),
"std": selected_features.std(axis=0, ddof=1),
"max": np.amax(selected_features, axis=0),
"min": np.amin(selected_features, axis=0)
}
for metric in expected_stats:
np.testing.assert_allclose(actual_stats[metric],
expected_stats[metric])
def main():
fileConfig('logging_config.ini')
db_util = DatabaseUtility()
primary_ui = PrimaryUI()
primary_ui.set_doc_names(db_util.get_saved_doc_names())
file_processor = FileProcessor()
while True:
event, file_names = primary_ui.Read()
if event is not None:
# Process the data
if file_names[0] != '':
if event == primary_ui.IMPORT:
db_util.save_docs(
file_processor.convert_file_names_to_name_data_dict(
file_names[0]))
# elif event == primary_ui.EXPORT:
else:
break
def __init__(self,
input_file,
input_dir,
file_regex,
latest,
debug,
recursive=False):
"""
Return an instance of JsonFileProcessor.
Parameters:
input_file (string): file (full path) to check for data
input_dir (string): directory (full path) to check for data files
latest (Boolean): check for latest files only
debug (Boolean): enable debug logging
recursive (Boolean): check the search directory recursively
"""
self.debug = debug
root_logger.info("Debug: %s", debug)
if input_file:
self.file_names = FileProcessor.match_file(input_file, file_regex)
root_logger.info("Found %d json files for %s in %s",
self.file_count(), file_regex, input_file)
if input_dir:
self.file_names = FileProcessor.dir_to_files(
input_dir, file_regex, latest, recursive)
root_logger.info("Found %d json files for %s in %s",
self.file_count(), file_regex, input_dir)
def test_run(self):
mock_repo = mock.Mock(spec=FileRepoABC)
mock_repo.get_files.return_value = [BytesIO(b"foo"), BytesIO(b"bar")]
fp = FileProcessor(mock_repo, "some/path")
results = fp.run()
self.assertEqual(results, ["acbd18db4cc2f85cedef654fccc4a4d8",
"37b51d194a7513e45b56f6524f2d51f2"])
def test_transform_features_all_codes(self):
file_processor = FileProcessor(self.input_file_path)
file_processor.transform_features(self.output_file_path)
job_ids, feature_codes, features = read_test_data_as_arrays(
self.input_file_path)
means = features.mean(axis=0)
expected_z_scores = stats.zscore(
features, axis=0, ddof=1) # using sample standard deviation
expected_argmaxs = np.argmax(features, axis=1)
expected_maxs = np.amax(features, axis=1)
expected_diffs = np.abs(expected_maxs - means[expected_argmaxs])
line_index = 0
with open(self.output_file_path) as f:
next(f)
for line in f:
job_id, z_scores, argmax, diff = _parse_transformed_line(line)
np.testing.assert_equal(job_id, job_ids[line_index])
np.testing.assert_allclose(z_scores,
expected_z_scores[line_index])
np.testing.assert_equal(argmax, expected_argmaxs[line_index])
np.testing.assert_almost_equal(diff,
expected_diffs[line_index])
line_index += 1
def main():
"""
Use custom file processor to pull bcket hashes
"""
gcs_repo = GCSFileRepo(APP_CREDENTIALS_JSON, COVID_BUCKET)
fp = FileProcessor(gcs_repo, None)
gcs_bucket_hashes = fp.run()
print(gcs_bucket_hashes)
def __init__(self, input_file, input_dir, db_params_dict, metric, debug):
"""Return a new instance of FitBitData given the location of the data files, paramters for accessing the database, and if the data should be stored in metric units."""
self.metric = metric
self.fitbitdb = FitBitDB.FitBitDB(db_params_dict, debug)
if input_file:
self.file_names = FileProcessor.match_file(input_file, r'.*\.csv')
if input_dir:
self.file_names = FileProcessor.dir_to_files(input_dir, r'.*\.csv')
class SecondPassCrawler:
session = attr.ib()
navigator = attr.ib(init=False)
file_processor = attr.ib(init=False)
def __attrs_post_init__(self):
self.navigator = SeleniumNavigator(loading_strategy='none')
self.file_processor = FileProcessor()
def exit(self):
self.navigator.close_browser()
self.session.close()
def get_urls(self):
# results = self.session.query(Report).all()
# return (report.url for report in results)
return ['http://media.ethics.ga.gov/search/Campaign/Campaign_ReportOptions.aspx?NameID=16067&FilerID=C2012000744&CDRID=59991']
def add_scrapelog_to_db(self, url, content, dtime):
slog = ScrapeLog(scrape_date=dtime,
raw_data=content,
page_url=url)
try:
self.session.add(slog)
self.session.commit()
except Exception as e:
self.session.rollback()
logging.info(e)
def crawl_download_link(self):
parser = CSVLinkParser(self.navigator.page_source())
parsed_link = parser.parse()
if parsed_link is not None:
logging.info(f'Parsed link: {parsed_link}')
url = self.navigator.get_current_url()
self.navigator.click_link(parsed_link)
logging.info('Clicking download link for csv file.')
content, dtime = self.file_processor.process()
self.add_scrapelog_to_db(url, content, dtime)
self.file_processor.delete_csv()
def crawl_view_contributions_ids(self):
logging.info(f'Current page: {self.navigator.get_current_url()}')
parser = ContributionsViewParser(self.navigator.page_source())
parsed_link = parser.parse()
if parsed_link is not None:
logging.info(f'Parsed link: {parsed_link}')
self.navigator.click_link(parsed_link)
self.navigator.wait_for_csv_link()
self.crawl_download_link()
def crawl(self):
urls = self.get_urls()
for url in urls:
logging.info(f'Current url: {url}')
self.navigator.navigate(url)
self.navigator.wait_for_contributions_id()
self.crawl_view_contributions_ids()
def __init__(self, input_file, input_dir, db_params_dict, metric, debug):
self.metric = metric
self.mshealth_db = MSHealthDB.MSHealthDB(db_params_dict, debug)
if input_file:
self.file_names = FileProcessor.match_file(
input_file, r'Daily_Summary_.*\.csv')
if input_dir:
self.file_names = FileProcessor.dir_to_files(
input_dir, r'Daily_Summary_.*\.csv')
def main():
"""
:return:
"""
file_processor = FileProcessor("")
db_stock_data = StockData(config['postgresql']['host'],
config['postgresql']['database'])
# get stock symbols from data file
# pharma_stocks = file_processor.read_file("lookup_data/pharma_stocks")
fortune_500_0_stocks = file_processor.read_file("lookup_data/fortune_500_0")
s_p_500_data = pd.read_csv("lookup_data/s_p_500.csv", delimiter=',')
s_p_500_data_stocks = s_p_500_data['stock'].tolist()
stock_data_list = []
dt_utc_now = datetime.utcnow()
stocks = s_p_500_data_stocks + fortune_500_0_stocks
invalid_data = []
print('getting data from yahoo . . .')
for stock in stocks:
stock_data = get_stock_info(stock, dt_utc_now)
if stock_data:
stock_data_list.append(stock_data)
else:
invalid_data.append(stock)
file_processor.save_file('data/fortune_500_0.json',str(stock_data_list))
print('adding to database . . .')
for stock_data in stock_data_list:
try:
db_stock_data.insert_stock_data(stock_data)
except Exception as ex:
# todo log exception
invalid_data.append(stock_data.name)
continue
print('invalid_data:')
print(invalid_data)
# ['AET', 'APC', 'ANDV', 'BHGE', 'BBT', 'BF.B', 'CA', 'CSRA', 'DWDP', 'DPS', 'EVHC',
# 'ESRX', 'GGP', 'HCP', 'LLL', 'LUK', 'KORS', 'MON', 'NFX', 'PX', 'RHT', 'COL',
# 'SCG', 'SYMC', 'TWX', 'TMK', 'TSS', 'WYN', 'XL']
# ['AET', 'APC', 'ANDV', 'BHGE', 'BBT', 'BF.B', 'CA', 'CSRA', 'DWDP', 'DPS', 'EVHC',
# 'ESRX', 'GGP', 'HRS', 'HCP', 'LLL', 'KORS', 'MON', 'NFX', 'PX', 'RHT', 'COL', 'SCG',
# 'TWX', 'TMK', 'TSS', 'WYN', 'XL', 'BRK.B', 'GD', 'JEC', 'LUK', 'MCK', 'CRM',
# 'STI', 'SYMC', 'VIAB', 'MCK', 'CRM']
print('total records added: {0}'.format(len(stock_data_list)))
def __init__(self, input_file, input_dir, db_params_dict, metric, debug):
"""Return an instance of MSHealthData given an input file or files and information on the databse to put it in."""
self.metric = metric
self.mshealth_db = MSHealthDB.MSHealthDB(db_params_dict, debug)
if input_file:
self.file_names = FileProcessor.match_file(
input_file, r'Daily_Summary_.*\.csv')
if input_dir:
self.file_names = FileProcessor.dir_to_files(
input_dir, r'Daily_Summary_.*\.csv')
def test_zip_bytes_io(s3):
file_processor = FileProcessor({}, {}, s3)
actual = file_processor._zip_bytes_io(pytest.bucket_origin, pytest.key)
assert type(actual) is BytesIO
with ZipFile(actual) as zip_obj:
assert zip_obj.namelist() == [pytest.file_zipped]
with zip_obj.open(pytest.file_zipped) as file_obj:
assert file_obj.read() == pytest.body_zipped.encode()
def test_upload_file_obj(s3, s3_prefix):
bytes_io = BytesIO()
key = f'{s3_prefix}/{pytest.file_zipped}'
os.environ['BUCKET_PROCESSED'] = pytest.bucket_processed
file_processor = FileProcessor({}, {}, s3)
zip_bytes_io = file_processor._zip_bytes_io(pytest.bucket_origin,
pytest.key)
file_processor._upload_file_obj(zip_bytes_io)
s3.download_fileobj(pytest.bucket_processed, key, bytes_io)
assert type(bytes_io) is BytesIO
assert bytes_io.getvalue() == pytest.body_zipped.encode()
def test_valid_bucket_key_list(event):
file_processor = FileProcessor(event, {}, {})
actual = file_processor._bucket_key_list()
assert type(actual) is list
for i in range(len(event)):
assert 'bucket' in actual[i]
assert actual[i]['bucket'] == event['Records'][i]['s3']['bucket'][
'name']
assert 'key' in actual[i]
assert actual[i]['key'].startswith('test')
assert actual[i]['key'].endswith('.zip')
def __init__(self, input_file, input_dir, db_params_dict, metric, debug):
self.metric = metric
self.mshealth_db = MSHealthDB.MSHealthDB(db_params_dict, debug)
self.cols_map = {
'Date': ('timestamp', CsvImporter.map_mdy_date),
'Weight': ('weight', MSVaultData.__map_weight),
}
if input_file:
self.file_names = FileProcessor.match_file(
input_file, r'HealthVault_Weight_.*\.csv')
if input_dir:
self.file_names = FileProcessor.dir_to_files(
input_dir, r'HealthVault_Weight_.*\.csv')
def __init__(self, input_file, input_dir, db_params_dict, metric, debug):
"""Return an instance of MSVaultData given an input file or files and information on the databse to put it in."""
self.metric = metric
self.mshealth_db = MSHealthDB.MSHealthDB(db_params_dict, debug)
self.cols_map = {
'Date': ('timestamp', CsvImporter.map_mdy_date),
'Weight': ('weight', MSVaultData.__map_weight),
}
if input_file:
self.file_names = FileProcessor.match_file(
input_file, r'HealthVault_Weight_.*\.csv')
if input_dir:
self.file_names = FileProcessor.dir_to_files(
input_dir, r'HealthVault_Weight_.*\.csv')
def test_run_returns_md5_of_contents(self):
with mock.patch('file_processor.storage'):
fp = FileProcessor('some/path')
with mock.patch.object(fp, 'bucket') as mock_bucket:
mock_blob = mock.Mock(name='mock_blob')
def mock_download_to_file(bytez):
bytez.write(b'foobarbaz')
mock_blob.download_to_file = mock_download_to_file
mock_bucket.list_blobs.return_value = [mock_blob]
# WHEN
results = fp.run()
# THEN
self.assertEqual(results, ['6df23dc03f9b64cc38a0fc1483df6e21'])
def test_transform_features_some_codes(self):
selected_codes = random.sample(self.feature_codes, k=2)
file_processor = FileProcessor(self.input_file_path)
file_processor.transform_features(self.output_file_path,
selected_codes)
job_ids, feature_codes, features = read_test_data_as_arrays(
self.input_file_path)
selected_indexes = []
for code in selected_codes:
indexes = np.where(feature_codes == code)[0].tolist()
selected_indexes += indexes
selected_indexes = sorted(selected_indexes)
selected_job_ids = job_ids[selected_indexes]
selected_features = features[selected_indexes]
means = selected_features.mean(axis=0)
expected_z_scores = stats.zscore(
selected_features, axis=0,
ddof=1) # using sample standard deviation
expected_argmaxs = np.argmax(selected_features, axis=1)
expected_maxs = np.amax(selected_features, axis=1)
expected_diffs = np.abs(expected_maxs - means[expected_argmaxs])
line_index = 0
with open(self.output_file_path) as f:
next(f)
for line in f:
job_id, z_scores, argmax, diff = _parse_transformed_line(line)
np.testing.assert_equal(job_id, selected_job_ids[line_index])
np.testing.assert_allclose(z_scores,
expected_z_scores[line_index])
np.testing.assert_equal(argmax, expected_argmaxs[line_index])
np.testing.assert_almost_equal(diff,
expected_diffs[line_index])
line_index += 1
self.assertEqual(line_index, len(selected_indexes))
def backup(config, database):
"""
Process directoreis to be backed up
"""
logger = logging.getLogger('mylog')
clean_removed(config, database)
if not consistency_check(config, database):
logger.warning('Consistency check detected problems!')
if not query_yes_no('Continue?'):
sys.exit()
dirs = config.get('Backup', 'to_backup').split()
logger.info('Directories to backup: ' + ','.join(dirs))
exclude_dirs = config.get('Backup', 'to_exclude').split()
logger.info('Directories to exclude: ' + ','.join(exclude_dirs))
file_proc = FileProcessor(config, database, encrypt_file)
#Count files to show progress later
total = 0
for directory in dirs:
for subdir, _, files in os.walk(directory):
if subdir in exclude_dirs:
continue
for single_file in files:
fpath = os.path.join(subdir, single_file)
total = total + 1
count = 0
for directory in dirs:
logger.debug('Processing directory' + directory)
for subdir, dirs, files in os.walk(directory):
if subdir in exclude_dirs:
logger.debug('Skipping directory' + subdir)
continue
for single_file in files:
fpath = os.path.join(subdir, single_file)
logger.debug('Processing file ' + fpath)
logger.info(str((count * 100) / total) + ' %')
file_proc.process(fpath)
count = count + 1
def __init__(self, input_dir, latest, measurement_system, debug):
logger.info("Processing daily FIT data")
self.measurement_system = measurement_system
self.debug = debug
if input_dir:
self.file_names = FileProcessor.dir_to_files(
input_dir, Fit.file.name_regex, latest, True)
def main():
print('IN Code Generator started....\nAnalysing input file...')
input_file_path, package_name = parse_args()
input_file_contents = FileProcessor.get_file_contents(input_file_path)
if input_file_contents:
file_contents: [
FileContent
] = CodeProcessor.process_file_contents(input_file_contents)
FileProcessor.remove_output_dir()
for file_content in file_contents:
file_content.package_name = package_name
if file_content:
file_exports: FileProcessor = FileProcessor(file_content)
file_exports.process_and_export_templates()
def copy_monitoring(self, monitoring_dir, latest):
"""Copy daily monitoring data FIT files from a USB mounted Garmin device to the given directory."""
device_monitoring_dir = GarminDBConfigManager.device_monitoring_dir(self.device_mount_dir)
logger.info("Copying monitoring files from %s to %s", device_monitoring_dir, monitoring_dir)
file_names = FileProcessor.dir_to_files(device_monitoring_dir, Fit.file.name_regex, latest)
for file in progressbar.progressbar(file_names):
shutil.copy(file, monitoring_dir)
def process_input(self, f_name, query):
"""
@summary: This method process the input file using FileProcessor class and returns the output
@param f_name:file name to be processed
@param query:query to be searched
@return: Dictionary with query as the key and list of top found elems as the value
"""
fp_obj = FileProcessor()
data_leftover = ""
with open(f_name) as fp:
for chunk in fp_obj.read_in_chunks(fp, config.CHUNK_SIZE):
curr_list, data_leftover = self.convert_to_list(
(data_leftover + chunk).strip('[]'))
self.prefix_match(curr_list, query)
return self.convert_to_dict(self.result_list, query)
def test_generate_statistics_all_codes(self):
file_processor = FileProcessor(self.input_file_path)
actual_stats = file_processor.generate_statistics()
_, _, features = read_test_data_as_arrays(self.input_file_path)
expected_stats = {
"count": np.uint32(features.shape[0]),
"mean": features.mean(axis=0),
"std": features.std(axis=0, ddof=1),
"max": np.amax(features, axis=0),
"min": np.amin(features, axis=0)
}
for metric in expected_stats:
np.testing.assert_allclose(actual_stats[metric],
expected_stats[metric])
class TestFileProcessor(TestCase):
def setUp(self):
self.processor = FileProcessor()
def getFakeFile(self, string):
fake_file = FakeFile()
fake_file.write(string)
fake_file.seek(0)
return fake_file
def test_readFile_returns_list_of_words_from_file(self):
test_str = "Test String"
self.assertTrue(
isinstance(self.processor.readFile(self.getFakeFile(test_str)),
list))
def test_readFile_returns_list_of_words_from_file_splitted_by_space_by_default(
self):
test_str = "Test String"
self.assertEqual(self.processor.readFile(self.getFakeFile(test_str)),
[["Test", "String"]])
def test_readFile_returns_list_of_words_from_file_splitted_by_tab(self):
test_str = "Test\tString"
self.assertEqual(
self.processor.readFile(self.getFakeFile(test_str), "\t"),
[["Test", "String"]])
def test_readFile_returns_comma_separated_values_as_list(self):
test_str = "test,str"
self.assertEqual(
self.processor.readFile(self.getFakeFile(test_str), ","),
[["test", "str"]])
def test_readFile_returns_each_line_as_new_list(self):
test_str = "test,this\nline,str"
self.assertEqual(
self.processor.readFile(self.getFakeFile(test_str), ","),
[["test", "this"], ["line", "str"]])
def test_retrieveData_returns_dict_of_variables_and_last_element_as_desired_class(
self):
test_list = ["test_var1", "test_var2", "test_var3", "90", "test_class"]
(data, des_class) = self.processor.retrieveData(test_list)
self.assertTrue(isinstance(data, dict))
self.assertEqual(des_class, "test_class")
def test_retrieveData_returns_string_and_number_variables_in_separate_list(
self):
test_list = [
"test_var1", "123.5samp", "sadkf123", "90", "test_var2",
"3434.134", "test_class"
]
(data, des_class) = self.processor.retrieveData(test_list)
self.assertEqual(
data, {
"string": ["test_var1", "123.5samp", "sadkf123", "test_var2"],
"num": [90, 3434.134]
})
def test_processor(feature_size, chunksize):
"""Tests FileProcessor.
:param feature_size: int, size of feature vector.
:param chunksize: int, FileProcessor chunk size.
"""
sep = '\t'
n_rows = 50
feature = 3
with TemporaryDirectory() as dir:
input_path = os.path.join(dir, 'data.tsv')
output_path = os.path.join(dir, 'data_proc.tsv')
data, feature_values = generate_data(n_rows=n_rows,
feature=feature,
feature_size=feature_size,
seed=42)
data.to_csv(input_path, sep=sep, index=False)
reader_params = {
'chunksize': chunksize,
'sep': sep,
}
transformers = (
Standardizer,
MaxIndex,
MaxFeatureAbsMeanDiff,
)
processor = FileProcessor(transformers, reader_params=reader_params)
processor.train(input_path)
processor.process(input_path, output_path)
processed = pd.read_csv(output_path, sep=sep)
# check feature_{i}_stand_{index}
expected_stand = (feature_values -
feature_values.mean(axis=0)) / feature_values.std(axis=0,
ddof=1)
stand = processed.filter(regex=f'feature_{feature}_stand_[0-9]+')
assert np.allclose(expected_stand, stand)
assert np.allclose(stand.mean(axis=0), 0)
assert np.allclose(stand.std(axis=0, ddof=1), 1)
# check max_feature_{i}_index
expected_max = feature_values.max(axis=1)
max_index = processed[f'max_feature_{feature}_index'].values
max_mask = (max_index.reshape(
(-1, 1)) == np.arange(feature_values.shape[1]).reshape((1, -1)))
fact_max = feature_values[max_mask]
assert np.allclose(expected_max, fact_max)
# check max_feature_{i}_abs_mean_diff
expected_max_mean = np.broadcast_to(feature_values.mean(axis=0),
shape=max_mask.shape)[max_mask]
expected_abs_mean_diff = np.abs(expected_max - expected_max_mean)
abs_mean_diff = processed[f'max_feature_{feature}_abs_mean_diff']
assert np.allclose(expected_abs_mean_diff, abs_mean_diff)
class FileHandler(PatternMatchingEventHandler):
def __init__(self):
PatternMatchingEventHandler.__init__(self, patterns=["*.txt"])
self.file_processor = FileProcessor()
def on_created(self, event):
logging.info("New file: {file}".format(file=event.src_path))
self.process(event)
def process(self, event):
filename = event.src_path
data = self.file_processor.parse_data(filename)
def test_check_lookup(self):
expected_result = FileProcessor.get_rate_code_lookup(TEST_ZIP_FILE)
# Check that inputs processed correctly and zips return the right region
self.assertEqual(expected_result['36749'], 'AL-11')
self.assertEqual(expected_result['36703'], 'AL-11')
self.assertEqual(expected_result['84310'], 'UT-2')
# Check that leading zeros were maintained
self.assertEqual(expected_result['05770'], 'VT-1')
# Check the conflicted rows were dropped
self.assertIsNone(expected_result.get('84409'))
def __init__(self, input_dir, latest, measurement_system, debug):
"""
Return an instance of GarminMonitoringFitData.
Parameters:
input_dir (string): directory (full path) to check for monitoring data files
latest (Boolean): check for latest files only
measurement_system (enum): which measurement system to use when importing the files
debug (Boolean): enable debug logging
"""
logger.info("Processing daily FIT data")
self.measurement_system = measurement_system
self.debug = debug
if input_dir:
self.file_names = FileProcessor.dir_to_files(
input_dir, Fit.file.name_regex, latest, True)
def __init__(self, input_dir, latest, measurement_system, debug):
"""
Return an instance of GarminTcxData.
Parameters:
db_params_dict (dict): configuration data for accessing the database
input_dir (string): directory (full path) to check for data files
latest (Boolean): check for latest files only
measurement_system (enum): which measurement system to use when importing the files
debug (Boolean): enable debug logging
"""
logger.debug("Processing activities tcx data")
self.measurement_system = measurement_system
self.debug = debug
if input_dir:
self.file_names = FileProcessor.dir_to_files(
input_dir, self.tcx_filename_regex, latest)
def test_find_second_lowest(self):
"""
Test whether the find second lowest function works on a small set of test data
"""
expected_result = FileProcessor.get_second_lowest_cost_lookup(
TEST_PLAN_FILE)
# Check that the two region that should have second best rates are included and correct
self.assertEqual(expected_result['GA-7'], 300.62)
self.assertEqual(expected_result['MI-4'], 150.6767)
# Check that two plan that were both the lowest returns the third item as the second lowest
# (see assumption in comments)
self.assertEqual(expected_result['TX-15'], 260.05)
# Check that only one silver isn't added to the final dictionary
self.assertNotIn('FL-60', expected_result)
# Check that no silver plan is not added to the final dictionary
self.assertNotIn('IL-5', expected_result)
def file_read (filename):
fp = FileProcessor (filename, ' ')
return fp.get_lines_as_array ()
def __init__(self):
PatternMatchingEventHandler.__init__(self, patterns=["*.txt"])
self.file_processor = FileProcessor()
