beannguyen

## vn-stock-momentum-strategy.ipynb

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                beannguyen
                / vn-stock-momentum-strategy.ipynb
            
            
              Created
              April 3, 2021 16:08
            
              
                VN Stock Momentum Strategy.ipynb
              
          
      Sorry, something went wrong. Reload?
      Sorry, we cannot display this file.
      Sorry, this file is invalid so it cannot be displayed.
      
          Viewer requires iframe.
      
    
## 101Alpha_code_1.py
import numpy as np
import pandas as pd
from numpy import abs
from numpy import log
from numpy import sign
from scipy.stats import rankdata

# region Auxiliary functions
def ts_sum(df, window=10):
    """

## ml_cross_val_score.py
from sklearn.metrics import log_loss, f1_score, accuracy_score

def ml_cross_val_score(
        baseline_fn,
        X: pd.DataFrame,
        y: pd.Series,
        cv_gen,
        sample_weight_train: np.ndarray = None,
        sample_weight_score: np.ndarray = None,
        scoring = log_loss):

## setup_svm_model.py
from sklearn.svm import SVC
from time import time
from sklearn.metrics import f1_score

def train_classifier(clf, X_train, y_train):
    ''' Fits a classifier to the training data. '''

    # Start the clock, train the classifier, then stop the clock
    start = time()
    clf.fit(X_train, y_train)

## create_train_test_data.py
_train_data, _test_data, _eval_data = create_dataset(['bitcoin.csv'])
print(_train_data.shape, _test_data.shape, _eval_data.shape)
train_scaler, train_data = scale_data(_train_data)
train_x, train_y = extract_features_labels(train_data)

test_scaler, test_data = scale_data(_test_data)
test_x, test_y = extract_features_labels(test_data)

## preprocessing.py
def preprocessing(file):
    _data = []
    print('Processing file ', file)
    f = open(file, 'r')
    try:
        df = pd.read_csv(f, delimiter=',', usecols=['date', 'open', 'high', 'low', 'close'])
        df = df.sort_values('date')
        df = df.drop(['date'], axis=1)

        dataset = df.values

## bitcoin.csv

          
            Datetime
            Open
            High
            Low
            Close
            Volume
            MarketCap

            
              2013-04-28T00:00:00
              135.3
              135.98
              132.1
              134.21
              0
              1500519936

            
              2013-04-29T00:00:00
              134.44
              147.49
              134
              144.54
              0
              1491160064

            
              2013-04-30T00:00:00
              144
              146.93
              134.05
              139
              0
              1597779968

            
              2013-05-01T00:00:00
              139
              139.89
              107.72
              116.99
              0
              1542819968

            
              2013-05-02T00:00:00
              116.38
              125.6
              92.28
              105.21
              0
              1292189952

            
              2013-05-03T00:00:00
              106.25
              108.13
              79.1
              97.75
              0
              1180070016

            
              2013-05-04T00:00:00
              98.1
              115
              92.5
              112.5
              0
              1089890048

            
              2013-05-05T00:00:00
              112.9
              118.8
              107.14
              115.91
              0
              1254759936

            
              2013-05-06T00:00:00
              115.98
              124.66
              106.64
              112.3
              0
              1289469952

## data_preprocessing.py
from __future__ import absolute_import, division, print_function

from math import sqrt

import numpy as np
import pandas as pd
import tensorflow as tf
from keras import Sequential, optimizers, metrics
from keras.layers import LSTM, Dropout, Dense
from keras.losses import mean_squared_error

## xpath_soup.py
#!/usr/bin/python
# -*- coding: utf-8 -*-

def xpath_soup(element):
    """
    Generate xpath from BeautifulSoup4 element

    :param element: BeautifulSoup4 element.
    :type element: bs4.element.Tag or bs4.element.NavigableString
    :return: xpath as string
	import numpy as np
	import pandas as pd
	from numpy import abs
	from numpy import log
	from numpy import sign
	from scipy.stats import rankdata

	# region Auxiliary functions
	def ts_sum(df, window=10):
	"""
	from sklearn.metrics import log_loss, f1_score, accuracy_score

	def ml_cross_val_score(
	baseline_fn,
	X: pd.DataFrame,
	y: pd.Series,
	cv_gen,
	sample_weight_train: np.ndarray = None,
	sample_weight_score: np.ndarray = None,
	scoring = log_loss):
	from sklearn.svm import SVC
	from time import time
	from sklearn.metrics import f1_score

	def train_classifier(clf, X_train, y_train):
	''' Fits a classifier to the training data. '''

	# Start the clock, train the classifier, then stop the clock
	start = time()
	clf.fit(X_train, y_train)
	_train_data, _test_data, _eval_data = create_dataset(['bitcoin.csv'])
	print(_train_data.shape, _test_data.shape, _eval_data.shape)
	train_scaler, train_data = scale_data(_train_data)
	train_x, train_y = extract_features_labels(train_data)

	test_scaler, test_data = scale_data(_test_data)
	test_x, test_y = extract_features_labels(test_data)
	def preprocessing(file):
	_data = []
	print('Processing file ', file)
	f = open(file, 'r')
	try:
	df = pd.read_csv(f, delimiter=',', usecols=['date', 'open', 'high', 'low', 'close'])
	df = df.sort_values('date')
	df = df.drop(['date'], axis=1)

	dataset = df.values
Datetime	Open	High	Low	Close	Volume	MarketCap
2013-04-28T00:00:00	135.3	135.98	132.1	134.21	0	1500519936
2013-04-29T00:00:00	134.44	147.49	134	144.54	0	1491160064
2013-04-30T00:00:00	144	146.93	134.05	139	0	1597779968
2013-05-01T00:00:00	139	139.89	107.72	116.99	0	1542819968
2013-05-02T00:00:00	116.38	125.6	92.28	105.21	0	1292189952
2013-05-03T00:00:00	106.25	108.13	79.1	97.75	0	1180070016
2013-05-04T00:00:00	98.1	115	92.5	112.5	0	1089890048
2013-05-05T00:00:00	112.9	118.8	107.14	115.91	0	1254759936
2013-05-06T00:00:00	115.98	124.66	106.64	112.3	0	1289469952
	from __future__ import absolute_import, division, print_function

	from math import sqrt

	import numpy as np
	import pandas as pd
	import tensorflow as tf
	from keras import Sequential, optimizers, metrics
	from keras.layers import LSTM, Dropout, Dense
	from keras.losses import mean_squared_error
	#!/usr/bin/python
	# -- coding: utf-8 --

	def xpath_soup(element):
	"""
	Generate xpath from BeautifulSoup4 element

	:param element: BeautifulSoup4 element.
	:type element: bs4.element.Tag or bs4.element.NavigableString
	:return: xpath as string