def main ():
start_time = datetime.datetime.now()
print('Tiempo inicial', start_time)
#Iniciar Spark
sc = init_spark()
spark = SparkSession(sc)
# Conexion a sqlite
c = init_sqlite()
# Generar una lista con todos los generos y asignarle un numero a cada uno
genres = load_genres(c)
# Cargar la data a un dataframe
data, headers_feature = load_dataset(c, spark, genres)
# Correr la clasificacion por regresion logistica
regression.run(data, headers_feature)
# Correr la clasificacion por redes neuronales
neural.run(data, headers_feature)
end_time = datetime.datetime.now()
print('Tiempo final', end_time)
print('Tiempo total transcurrido', end_time - start_time)
def predict():
neighborhood = request.args.get('neighborhood')
layout = request.args.get('layout')
bathrooms = request.args.get('bathrooms')
square_footage = request.args.get('square_footage')
predicted_price = regression.run([{
'neighborhood': neighborhood,
'layout': layout,
'bathrooms': bathrooms,
'square_footage': int(square_footage)
}])
return jsonify(predicted_price[0][0])
epochs = args.epochs,
criterion = criterion,
batch_size=args.batch_size,
subspace_type=args.subspace, subspace_kwargs={'max_rank':args.max_num_models},
momentum = args.momentum, wd=args.wd, lr_init=args.lr_init,
swag_lr = args.swag_lr, swag_freq = 1, swag_start = args.swag_start,
use_cuda = torch.cuda.is_available(), use_swag = args.swag,
scale=args.scale, num_samples=args.num_samples,
const_lr=args.no_schedule, double_bias_lr=False,
model_variance=args.model_variance,
**extra_args,
input_dim=dataset.D, output_dim=output_dim, apply_var=args.noise_var, **model_cfg.kwargs
)
mname = args.model
if args.swag:
mname = mname + args.subspace + args.inference
bb_args = argparse.Namespace(model=mname, dataset=args.dataset, split=args.split, seed=args.seed, database_path=args.database_path)
bb_result = run(bb_args, data=dataset, model=regression_model, is_test=args.database_path=='')
print(bb_result)
utils.save_checkpoint(
args.dir,
args.epochs,
model_state_dict=regression_model.model.state_dict(),
optimizer=regression_model.optimizer.state_dict(),
result=bb_result
)
})
result = self.execute_command(
self.BASE_COMMAND + "ninjadroid /apks/Example.apk --all --json")
# NOTE: the below hack is needed to remove the SHA1withRSA signature algorithm warning...
result = "\n".join(result.split('\n')[4:])
self.assert_json_equal(expected, result)
@RegressionSuite.test
def extract_extended(self):
expected = self.read_plain_text_file(
"regression/expected/extract.txt",
overrides={
18:
"7ab36f88adf38f96df05c9e024d548ab output/report-Example.json"
})
self.execute_command(
self.BASE_COMMAND_WITH_OUTPUT +
"ninjadroid /apks/Example.apk --all --extract /output")
# NOTE: the .jar file checksum changes at every run...
result = self.execute_command(
"find output/ -type f -exec md5sum '{}' + | grep -v Example.jar")
self.assert_plain_text_equal(expected, result)
if __name__ == "__main__":
run(suite=DockerRegressionSuite())
result = self.execute_command(
"ninjadroid regression/data/Example.apk --json")
self.assert_json_equal(expected, result)
@RegressionSuite.test
def show_json_extended(self):
expected = self.read_json_file("regression/expected/extended.json")
result = self.execute_command(
"ninjadroid regression/data/Example.apk --all --json")
self.assert_json_equal(expected, result)
@RegressionSuite.test
def extract_extended(self):
expected = self.read_plain_text_file("regression/expected/extract.txt")
self.execute_command(
"ninjadroid regression/data/Example.apk --all --extract output/")
# NOTE: the .jar file checksum changes at every run...
result = self.execute_command(
"find output/ -type f -exec md5sum '{}' + | grep -v Example.jar")
self.assert_plain_text_equal(expected, result)
if __name__ == "__main__":
run(suite=NativeRegressionSuite())
self.assert_plain_text_equal(expected, result, multiline=False)
@RegressionSuite.test
def show_extended(self):
expected = self.read_plain_text_file("regression/expected/extended.txt")
result = self.execute_command(self.BASE_COMMAND + "ninjadroid regression/data/Example.apk --all")
self.assert_plain_text_equal(expected, result, multiline=False)
@RegressionSuite.test
def show_json_summary(self):
expected = self.read_json_file("regression/expected/summary.json")
result = self.execute_command(self.BASE_COMMAND + "ninjadroid regression/data/Example.apk --json")
self.assert_json_equal(expected, result)
@RegressionSuite.test
def show_json_extended(self):
expected = self.read_json_file("regression/expected/extended.json")
result = self.execute_command(self.BASE_COMMAND + "ninjadroid regression/data/Example.apk --all --json")
self.assert_json_equal(expected, result)
if __name__ == "__main__":
run(suite = FlatpakRegressionSuite())
},
})
result = self.execute_command(
self.BASE_PATH +
"ninjadroid regression/data/Example.apk --all --json")
self.assert_json_equal(expected, result)
@RegressionSuite.test
def extract_extended(self):
expected = self.read_plain_text_file(
"regression/expected/extract.txt",
overrides={
18:
"25ada2132e42197adfaccd8293c8363a output/report-Example.json"
})
self.execute_command(
self.BASE_PATH +
"ninjadroid regression/data/Example.apk --all --extract output/")
# NOTE: the .jar file checksum changes at every run...
result = self.execute_command(
"find output/ -type f -exec md5sum '{}' + | grep -v Example.jar")
self.assert_plain_text_equal(expected, result)
if __name__ == "__main__":
run(suite=SnapRegressionSuite())
cfb.PassIntOff.describe() # How many interceptions this team has thrown cfb.FumblesOff.describe() # How many fumbles this team has had cfb.Opponent.describe() # Opponent's name cfb.ScoreDef.describe() # Opponent's total score cfb.RushAttDef.describe() # Opponent's rush attempts cfb.RushYdsDef.describe() # Opponent's rush yards cfb.PassAttDef.describe() # Opponent's passing attempts cfb.PassCompDef.describe() # Opponent's passing completions cfb.PassYdsDef.describe() # Opponent's total passing yards cfb.PassIntDef.describe() # How many interceptions the opponent has thrown cfb.FumblesDef.describe() # How many fumbles the opponent has had cfb.Site.describe() # Whether the game was home, away, or at a neutral site cfb.Line.describe() # Vegas betting line; Human prediction of score cfb.ScoreOffCat.describe() # This teams score broken into categories cfb.ScoreDefCat.describe() # Opposing team's score broken into categories # 5 # Visuals visuals.run() # 6 # Machine learning regression.run() predictwin.run()
def run_regression():
reload(reg)
reg.training_file_name = './data/regression_data.txt'
reg.groundtruth_file_name = './data/regression_groundtruth.txt'
reg.run()