# construct our data dictionary which maps the data types of the
# columns in the CSV file to built-in data types
print("[INFO] building column names...")
types = {"feat_{}".format(i): float for i in range(0, args["cols"])}
types["class"] = int
# create a CSV data generator for the extracted Keras features
dataset = stream.iter_csv(args["csv"], target_name="class", types=types)
# construct our pipeline
model = Pipeline([
("scale", StandardScaler()),
("learn", OneVsRestClassifier(binary_classifier=LogisticRegression()))])
# initialize our metric
print("[INFO] starting training...")
metric = Accuracy()
# loop over the dataset
for (i, (X, y)) in enumerate(dataset):
# make predictions on the current set of features, train the
# model on the features, and then update our metric
preds = model.predict_one(X)
model = model.fit_one(X, y)
metric = metric.update(y, preds)
print("INFO] update {} - {}".format(i, metric))
# show the accuracy of the model
print("[INFO] final - {}".format(metric))
required=True,
help='Number of columns in the feature CSV file (excluding label).')
arguments = vars(argument_parser.parse_args())
print('[INFO] Building column names...')
types = {f'feature_{i}': float
for i in range(arguments['num_cols'])} # Data type per feature
types['class'] = int
dataset = stream.iter_csv(arguments['train'], target_name='class', types=types)
model = Pipeline([('scaler', StandardScaler()),
('learner',
OneVsRestClassifier(binary_classifier=PAClassifier()))])
metric = Accuracy()
print('[INFO] Training started...')
for index, (X, y) in enumerate(dataset):
try:
predictions = model.predict_one(X)
model = model.fit_one(X, y)
metric = metric.update(y, predictions)
if index % 10 == 0:
print(f'[INFO] Update {index} - {metric}')
except OverflowError as e:
print(f'Overflow error. Skipping metric update for {index}')
print(f'[INFO] Final - {metric}')
engine = create_engine('mysql+pymysql://root:@localhost/tez')
session = 41
query = "select * from elderly_sensor where session = "+str(session)+" order by 'time(second)'"
df = pandas.read_sql(query, engine)
df = df.drop("index", axis=1)
timeList = list(df["time(second)"])
df = df.drop("time(second)", axis=1)
x = df.drop("class", axis=1).to_dict(orient="row")
y = list(df["class"])
metrics = (
MSE(),
Accuracy()
)
model = (
StandardScaler() |
DecisionTreeClassifier()
)
# Mse Accuracy Real
outputfile = open('C:\\Users\\YigitCan\\Desktop\\Tez-Workspace\\Real-Time-Big-Data-Analytics\\Elderly Sensor\\Output'+str(session)+'.txt', 'w')
previous_time = 0.0
for row, target, time_passed in zip(x, y, timeList):
time_range = time_passed - previous_time
session = 60
#query = "select * from elderly_sensor where session = "+str(session)+" order by 'time(second)'"
query = "select * from elderly_sensor"
df = pandas.read_sql(query, engine)
#logging.info("Data retrieved by Session = " + str(session))
logging.info("Data retrieved by all")
df = df.drop("index", axis=1)
timeList = list(df["time(second)"])
df = df.drop("time(second)", axis=1)
x = df.drop("class", axis=1).to_dict(orient="row")
y = list(df["class"])
acc = Accuracy()
fbeta = MultiFBeta(betas=({1: 0.5, 2: 0.5, 3: 0.5, 4: 0.5}))
model = (StandardScaler() | DecisionTreeClassifier())
logging.info("Initial model created")
# Mse Accuracy Real
recordNumber = len(y)
text = ""
previous_time = 0.0
logging.info("Learning process has been started")
startTime = time.time()
for row, target, time_passed in tqdm.tqdm(zip(x, y, timeList)):
'''
time_range = time_passed - previous_time
if time_range > 0.0: