#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
File name: scatter_plot.[extension].py
Description: Scatter plot for MyDataSet instance.
Author: Mathilde DUVERGER
Date created: 2018/10/08
Python Version: 3.6
"""
from mydataset import MyDataSet
dataset_train = MyDataSet().read_csv('resources/dataset_train.csv')
dataset_train.plot_scatter()
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
File name: describe.[extension].py
Description: Describe input CSV DataSet.
Author: Mathilde DUVERGER
Date created: 2018/10/08
Python Version: 3.6
"""
from mydataset import MyDataSet
import sys
path = str(sys.argv[1])
dataset_train = MyDataSet().read_csv(path)
dataset_train.describe()
# In[2]:
EPOCH = 25
BATCH_SIZE = 4
LR = 0.001
# In[3]:
transform = transforms.Compose([
transforms.Resize([96, 96]),
transforms.ToTensor(),
transforms.Normalize(mean=(0, 0, 0), std=(1, 1, 1))
])
train_set = MyDataSet('./birds/train/', transform=transform, labels=None)
train_loader = Data.DataLoader(train_set,
batch_size=BATCH_SIZE,
shuffle=True,
num_workers=4)
test_set = MyDataSet('./birds/test/', transform=transform, labels=None)
test_loader = Data.DataLoader(test_set,
batch_size=BATCH_SIZE,
shuffle=True,
num_workers=4)
# In[4]:
print(train_set.classes)
print(train_set.class_to_idx)
print(train_set.__len__)
"""
File name: logreg_train.[extension].py
Description: Train logistic regression.
Author: Mathilde DUVERGER, Alessandro GIRELLI, Louis LIMNAVONG
Date created: 2018/10/08
Python Version: 3.6
"""
from mydataset import MyDataSet
from logregmodel import LogRegModel
from preprocessing import full_one_hot_encoder, to_matrix
import sys
path = str(sys.argv[1])
print(path)
dataset_train = MyDataSet().read_csv(path)
# getting X
DictX = dataset_train[['Best Hand', 'Astronomy', 'Herbology',
'Defense Against the Dark Arts',
'Muggle Studies', 'Ancient Runes',
'History of Magic', 'Transfiguration',
'Charms', 'Flying']]
DictX_encod = full_one_hot_encoder(DictX)
X = to_matrix(DictX_encod)
# getting Y
Y = dataset_train['Hogwarts House']
###
model = LogRegModel()
"""
File name: logreg_train.[extension].py
Description: Predict logistic regression.
Author: Mathilde DUVERGER, Alessandro GIRELLI, Louis LIMNAVONG
Date created: 2018/10/08
Python Version: 3.6
"""
from mydataset import MyDataSet
from logregmodel import LogRegModel
from preprocessing import full_one_hot_encoder, to_matrix
import sys
import csv
path = str(sys.argv[1])
dataset_test = MyDataSet().read_csv(path)
# getting X
DictX_test = dataset_test[[
'Best Hand', 'Astronomy', 'Herbology', 'Defense Against the Dark Arts',
'Muggle Studies', 'Ancient Runes', 'History of Magic', 'Transfiguration',
'Charms', 'Flying'
]]
DictX_encod_test = full_one_hot_encoder(DictX_test)
X_test = to_matrix(DictX_encod_test)
###
dataset_train = MyDataSet().read_csv('resources/dataset_train.csv')
# getting X
def main(operation='train', code=None):
step = 30
input_size = 62
train_steps = 1000000
batch_size = 512
learning_rate = 0.001
hidden_size = 14
nclasses = 1
validation_size = 700
keep_rate = 0.7
selector = [
"ROCP", "OROCP", "HROCP", "LROCP", "MACD", "RSI", "VROCP", "BOLL",
"MA", "VMA", "PRICE_VOLUME", "AVERAGE"
]
input_shape = [30, 62] # [length of time series, length of feature]
if operation == 'train':
train_features = []
train_labels = []
val_features = []
val_labels = []
binance = get_binance()
merge_bean = SmartLSTMPair("BTCUSDT", "1h", binance)
raw_data = merge_bean.get_history_data()
X = numpy.array(raw_data)
moving_features, moving_labels = extract_feature(raw_data=X,
selector=selector,
window=input_shape[0],
with_label=True,
flatten=False)
train_features.extend(moving_features[:-validation_size])
train_labels.extend(moving_labels[:-validation_size])
val_features.extend(moving_features[-validation_size:])
val_labels.extend(moving_labels[-validation_size:])
merge_bean = SmartLSTMPair("ETHUSDT", "1h", binance)
raw_data = merge_bean.get_history_data()
X = numpy.array(raw_data)
moving_features, moving_labels = extract_feature(raw_data=X,
selector=selector,
window=input_shape[0],
with_label=True,
flatten=False)
train_features.extend(moving_features[:-validation_size])
train_labels.extend(moving_labels[:-validation_size])
val_features.extend(moving_features[-validation_size:])
val_labels.extend(moving_labels[-validation_size:])
train_features = numpy.transpose(numpy.asarray(train_features),
[0, 2, 1])
train_labels = numpy.asarray(train_labels)
train_labels = numpy.reshape(train_labels, [train_labels.shape[0], 1])
val_features = numpy.transpose(numpy.asarray(val_features), [0, 2, 1])
val_labels = numpy.asarray(val_labels)
val_labels = numpy.reshape(val_labels, [val_labels.shape[0], 1])
train_set = MyDataSet(train_features, train_labels)
val_set = MyDataSet(val_features, val_labels)
# raw_data = read_sample_data("toy_stock.csv")
# moving_features, moving_labels = extract_feature(raw_data=raw_data, selector=selector, window=input_shape[0],
# with_label=True, flatten=False)
# moving_features = numpy.asarray(moving_features)
# moving_features = numpy.transpose(moving_features, [0, 2, 1])
# moving_labels = numpy.asarray(moving_labels)
# moving_labels = numpy.reshape(moving_labels, [moving_labels.shape[0], 1])
# train_set = DataSet(moving_features[:-validation_size], moving_labels[:-validation_size])
# val_set = DataSet(moving_features[-validation_size:], moving_labels[-validation_size:])
trader = SmartTrader(step, input_size, learning_rate, hidden_size,
nclasses)
trader.build_graph()
train(trader,
train_set,
val_set,
train_steps,
batch_size=batch_size,
keep_rate=keep_rate)
elif operation == "predict":
binance = get_binance()
merge_bean = SmartLSTMPair("BTCUSDT", "1h", binance)
raw_data = merge_bean.get_history_data()
X = numpy.array(raw_data)
moving_features, moving_labels = extract_feature(raw_data=X,
selector=selector,
window=input_shape[0],
with_label=True,
flatten=False)
moving_features = numpy.asarray(moving_features)
moving_features = numpy.transpose(moving_features, [0, 2, 1])
moving_labels = numpy.asarray(moving_labels)
moving_labels = numpy.reshape(moving_labels,
[moving_labels.shape[0], 1])
# train_set = DataSet(moving_features[:-validation_size], moving_labels[:-validation_size])
val_set = MyDataSet(moving_features[-validation_size:],
moving_labels[-validation_size:])
predict(X,
val_set,
step=step,
input_size=input_size,
learning_rate=learning_rate,
hidden_size=hidden_size,
nclasses=nclasses)
else:
print("Operation not supported. ")