def setUpClass(self):
#TODO relative path to something better?
self.df = data_helper.import_data("data/" + _TEST_DATA_FILE)
self.odf = data_helper.import_operative_data("data/" + _OPERATIVE_TEST_DATA_FILE)
self.apps = analysis.summarize_applications(self.df, self.odf)
# print apps once for debugging
print "Application summary based on test data:"
print self.apps
def main():
args = parse_args()
inputFileNameUsage = args['input_file_usage']
inputFileNameOperative = args['input_file_operative']
outputApplicationsFileName = args['output_file_applications']
outputUsersFileName = args['output_file_users']
predictionOutputFileName = args['prediction_output_file']
utils.log_config()
logger = logging.getLogger(__name__)
logger.info("Data file: {}".format(inputFileNameUsage))
if inputFileNameOperative:
logger.info("Operative data file: {}".format(inputFileNameOperative))
else:
logger.info("No operative data available.")
startTime = datetime.datetime.now()
# exported to global scope for debugging purposes
global df
df = data_helper.import_data(inputFileNameUsage)
global odf
if inputFileNameOperative:
odf = data_helper.import_operative_data(inputFileNameOperative)
else:
odf = None
logger.info("N of events: {}, from {} to {} ".format(len(df), df['datetime'].min(), df['datetime'].max()))
create_user_summary(outputUsersFileName)
create_application_summary(outputApplicationsFileName)
# create_prediction_summary(predictionOutputFileName)
print_stats(startTime)
default=os.getcwd() + "summary-users.csv")
args = vars(parser.parse_args())
return args
if __name__ == "__main__":
pd.set_option('display.width', 240)
args = parse_args()
input_file_operative = args['input_file_operative']
input_file_usage = args['input_file_usage']
output_file_applications = args['output_file_applications']
output_file_users = args['output_file_users']
analysis_start_time = datetime.datetime.now()
odf = data_helper.import_operative_data(input_file_operative)
udf = data_helper.import_usage_data(input_file_usage)
print("Total number of apps: {}".format(len(odf)))
print("Total number of events: {} with time range from {} to {} ".format(
len(udf), udf['datetime'].min(), udf['datetime'].max()))
application_summary = analyze.summarize_applications(odf, udf)
application_summary.to_csv(output_file_applications,
sep=';',
encoding='utf-8')
user_summary = analyze.summarize_users(odf, udf)
user_summary.to_csv(output_file_users, sep=';', encoding='utf-8')
print("Analysis took {} seconds".format(datetime.datetime.now() -
def setUpClass(self):
self.odf = data_helper.import_operative_data(_OPERATIVE_TEST_DATA_FILE)
self.udf = data_helper.import_usage_data(_TEST_DATA_FILE)
self.users = analyze.summarize_users(self.odf, self.udf)