def test_csv_file_to_data(self):
try:
data_return_path = RESOURCES_DIR + "/" + 'temp2.csv'
initial_data_path = RESOURCES_DIR + "/" + 'temp.csv'
test_csv_write3 = CsvWriter(self.host, self.port, self.username, self.password, self.database)
test_csv_write3.csv_file_to_db()
test_csv_write3.data_to_csv_file('select * from per15min', new_csv_file_name=data_return_path, fillGaps=False)
self.assertTrue(self.compare_csv_files(data_return_path, initial_data_path),
"Integration test failed, file is not the same")
os.remove(data_return_path)
except ConnectionError as error:
print("Test: Failed - {0}\n".format(error))
class Generator:
def __init__(self, config_object=None):
if isinstance(config_object, GeneratorConfig):
self._Config = config_object
else:
self._Config = GeneratorConfig()
self._Columns = 'avg_hrcrx_max_byt'
self._data_writer = CsvWriter(host=db_config.host,
port=db_config.port,
username=db_config.username,
password=db_config.password,
database=self._Config.Database)
self.Dist_Array = self._Config.Func_Type.generate()
def nparray_to_dataframe(self):
indexes = pd.DataFrame(self.Dist_Array[:, 0])
indexes[0] = pd.to_datetime(indexes[0], format='%Y-%m-%d %H:%M:%S')
cols = [self._Columns]
df = pd.DataFrame(data=self.Dist_Array[0:, 1:],
index=indexes[0],
columns=cols)
return df
def write_data_to_csv(self):
df = self.nparray_to_dataframe()
model_name = self._Config.Func_Type.Name
if not isinstance(df, pd.DataFrame):
print("Error reading the data from database.")
df.to_csv(path.join(RESOURCES_DIR, model_name + "_generated.csv"))
def write_data_to_database(self):
df = self.nparray_to_dataframe()
model_name = self._Config.Func_Type.Name
df.to_csv(path.join(RESOURCES_DIR, model_name + "_generated.csv"))
self._data_writer.csv_file_to_db(
measurement_to_use=model_name + '_generated',
new_csv_file_name=path.join(RESOURCES_DIR,
model_name + "_generated.csv"))
remove(path.join(RESOURCES_DIR, model_name + "_generated.csv"))
class TrafficPredictor:
_default_stride = None
_num_of_series = None
_selected_model = None
_data_writer = None
def __init__(self, database="predicted_data"):
self._default_stride = Stride.WEEKLY
self._num_of_series = 8
self._selected_model = None
self._data_writer = CsvWriter(host=db_config.host,
port=db_config.port,
username=db_config.username,
password=db_config.password,
database=database)
def main(self):
print("Welcome to the Traffic Predictor!")
print("Please choose your model (enter its index):")
for model in models:
x = models.index(model)
print("{0}: {1}".format(x, model))
print("-: Exit")
selection = input("Prompt: ")
if selection == '-':
return
else:
try:
model = models[int(selection)]
print("Please, wait...")
np = self.call_model(model)
df = self.nparray_to_dataframe(np)
print("Finished prediction")
print(
"Would you like to run Error analysis on the predicted data? [y]/[n]"
)
selection = input("Prompt: ")
if selection.lower() == 'y':
err_analysis = ErrorAnalysis(np)
err_analysis.compute_error()
print(
"Would you like to write predicted data to database? [y]/[n]"
"\nIf selected [n] the data will be written to local csv file"
)
selection = input("Prompt: ")
if selection.lower() == 'y':
self.write_data_to_database(model, df)
else:
self.write_data_to_csv(model, df)
except IndexError:
print("There's no model under index: {}".format(selection))
except TypeError:
print(
"ERROR: The model import failed. Please make sure to properly add/choose your model."
)
raise TypeError
def call_model(self, model_name):
model_root = 'PModules.' + model_name + "." + model_name + "." + model_name
model = locate(model_root)
self._selected_model = model()
# Your model class instance
self._selected_model.set_parameters()
result = self._selected_model.call_model()
return result
def write_data_to_csv(self, model_name, df):
if not isinstance(df, pd.DataFrame):
print(
"Error reading the data from database. Please test this query in Chronograf/Grafana."
)
df.to_csv(path.join(RESOURCES_DIR, model_name + "_predicted.csv"))
def write_data_to_database(self, model_name, df):
df.to_csv(path.join(RESOURCES_DIR, model_name + "_predicted.csv"))
self._data_writer.csv_file_to_db(
measurement_to_use=model_name + '_predicted',
new_csv_file_name=path.join(RESOURCES_DIR,
model_name + "_predicted.csv"))
remove(path.join(RESOURCES_DIR, model_name + "_predicted.csv"))
def nparray_to_dataframe(self, nparray_data):
indexes = pd.DataFrame(nparray_data[:, 0])
indexes[0] = pd.to_datetime(indexes[0], format='%Y-%m-%d %H:%M:%S')
cols = [self._selected_model.get_data_column_name()]
df = pd.DataFrame(data=nparray_data[0:, 1:],
index=indexes[0],
columns=cols)
return df