Roman Paolucci romanmichaelpaolucci

## Evolution.py
# Read Data
data = pd.read_csv('banknote.csv')
# Create Matrix of Independent Variables
X = data.drop(['Y'], axis=1)
# Create Vector of Dependent Variable
y = data['Y']
# Create a Train Test Split for Genetic Optimization
X_train, X_test, y_train, y_test = train_test_split(X, y)
# Create a List of all active GeneticNeuralNetworks
networks = []

## Genetic Neural Network.py
# New Type of Neural Network
class GeneticNeuralNetwork(Sequential):
    # Constructor
    def __init__(self, child_weights=None):
        # Initialize Sequential Model Super Class
        super().__init__()
        # If no weights provided randomly generate them
        if child_weights is None:
            # Layers are created and randomly generated
            layer1 = Dense(4, input_shape=(4,), activation='sigmoid')

## Neural Evolution Results.txt
[Command: python -u 'C:\Users\Roman\Documents\Software Development\archive\(deprecated) Neural Evolution Algorithm\neural_genetics.py']
Using TensorFlow backend.
WARNING:tensorflow:From C:\Users\Roman\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow\python\framework\op_def_library.py:263: colocate_with (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version.
Instructions for updating:
Colocations handled automatically by placer.
Generation:  1
2019-07-10 18:00:54.582107: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2
Max Fitness:  0.620019436345967
[array([[-0.55393076,  0.6676968 , -0.447821  ,  0.2897933 ],
       [-0.760463  ,  0.49176246,  0.48069805,  0.42872745],

## Normal Network Results.txt
[Command: python -u 'C:\Users\Roman\Documents\Software Development\archive\(deprecated) Neural Evolution Algorithm\test.py']
Using TensorFlow backend.
WARNING:tensorflow:From C:\Users\Roman\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow\python\framework\op_def_library.py:263: colocate_with (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version.
Instructions for updating:
Colocations handled automatically by placer.
WARNING:tensorflow:From C:\Users\Roman\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow\python\ops\math_ops.py:3066: to_int32 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.cast instead.
Epoch 1/10
2019-07-10 21:16:45.434436: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2

## api_socket.py
import pandas as pd
import quandl
import requests

class QuandlSocket:

    """
        Socket for cached historical market data requests
    """

## portfolio_data_request.py
class PortfolioDataRequest:

    """ stocks = [], start_date/end_date are strings 'YYYY-MM-DD' """
    """
        Class for portfolfio optimization, downloads relevant portfolio data
        and caches it for use in optimization without saving it locally.
    """

    def __init__(self, stocks, start_date, end_date):
        QuandlSocket()

## portfolio_optimization.py
class PortfolioOptimization:

    """
        Class for optimizing a historic portfolio
    """

    def __init__(self, table):
        mu = expected_returns.mean_historical_return(table)
        S = risk_models.sample_cov(table)

## portfolio_returns.py
class PortfolioReturns:

    def __init__(self, stocks, discrete_allocation, start_date, end_date):
        data = PortfolioDataRequest(stocks, start_date, end_date).table
        self.start_date = start_date
        self.end_date = end_date
        starting_value = 0
        ending_value = 0
        for stock in stocks:
            try:

## pyopt_pipeline.py
from portfolio_tools import PortfolioDataRequest
from portfolio_tools import PortfolioOptimization
from portfolio_tools import PortfolioReturns

"""
    Script for portfolio optimization pipeline research
"""

if __name__ == '__main__':
    stocks = 'AAPL MSFT JNJ JPM XOM WMT UNH PFE VZ V BA'.split()

## bad_AI_PM.py
# Class to develop your AI portfolio manager
class AIPMDevelopment:

    def __init__(self):
        # Read your data in and split the dependent and independent
        data = pd.read_csv('IBM.csv')
        X = data['Delta Close']
        y = data.drop(['Delta Close'], axis=1)

        # Train test spit
	# Read Data
	data = pd.read_csv('banknote.csv')
	# Create Matrix of Independent Variables
	X = data.drop(['Y'], axis=1)
	# Create Vector of Dependent Variable
	y = data['Y']
	# Create a Train Test Split for Genetic Optimization
	X_train, X_test, y_train, y_test = train_test_split(X, y)
	# Create a List of all active GeneticNeuralNetworks
	networks = []
	# New Type of Neural Network
	class GeneticNeuralNetwork(Sequential):
	# Constructor
	def __init__(self, child_weights=None):
	# Initialize Sequential Model Super Class
	super().__init__()
	# If no weights provided randomly generate them
	if child_weights is None:
	# Layers are created and randomly generated
	layer1 = Dense(4, input_shape=(4,), activation='sigmoid')
	[Command: python -u 'C:\Users\Roman\Documents\Software Development\archive\(deprecated) Neural Evolution Algorithm\neural_genetics.py']
	Using TensorFlow backend.
	WARNING:tensorflow:From C:\Users\Roman\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow\python\framework\op_def_library.py:263: colocate_with (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version.
	Instructions for updating:
	Colocations handled automatically by placer.
	Generation: 1
	2019-07-10 18:00:54.582107: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2
	Max Fitness: 0.620019436345967
	[array([[-0.55393076, 0.6676968 , -0.447821 , 0.2897933 ],
	[-0.760463 , 0.49176246, 0.48069805, 0.42872745],
	import pandas as pd
	import quandl
	import requests

	class QuandlSocket:

	"""
	Socket for cached historical market data requests
	"""
	class PortfolioDataRequest:

	""" stocks = [], start_date/end_date are strings 'YYYY-MM-DD' """
	"""
	Class for portfolfio optimization, downloads relevant portfolio data
	and caches it for use in optimization without saving it locally.
	"""

	def __init__(self, stocks, start_date, end_date):
	QuandlSocket()
	class PortfolioOptimization:

	"""
	Class for optimizing a historic portfolio
	"""

	def __init__(self, table):
	mu = expected_returns.mean_historical_return(table)
	S = risk_models.sample_cov(table)
	class PortfolioReturns:

	def __init__(self, stocks, discrete_allocation, start_date, end_date):
	data = PortfolioDataRequest(stocks, start_date, end_date).table
	self.start_date = start_date
	self.end_date = end_date
	starting_value = 0
	ending_value = 0
	for stock in stocks:
	try:
	from portfolio_tools import PortfolioDataRequest
	from portfolio_tools import PortfolioOptimization
	from portfolio_tools import PortfolioReturns

	"""
	Script for portfolio optimization pipeline research
	"""

	if __name__ == '__main__':
	stocks = 'AAPL MSFT JNJ JPM XOM WMT UNH PFE VZ V BA'.split()
	# Class to develop your AI portfolio manager
	class AIPMDevelopment:

	def __init__(self):
	# Read your data in and split the dependent and independent
	data = pd.read_csv('IBM.csv')
	X = data['Delta Close']
	y = data.drop(['Delta Close'], axis=1)

	# Train test spit