def main():
raw_tickers = input('Enter stocks separated by a comma: ')
investment = int(input("Enter total investment to allocate: "))
stock_tickers = raw_tickers.split(", ")
print(stock_tickers)
listed_prices, returns, cov_mat, avg_rets = gd.get_stock_data(
stock_tickers)
section("Example returns")
print(returns.head(10))
print("...")
section("Average returns")
print(avg_rets)
section("Covariance matrix")
print(cov_mat)
section("Minimum variance portfolio (long only)")
weights = pfopt.min_var_portfolio(cov_mat)
print_portfolio_info(returns, avg_rets, weights)
allocation = investment * weights
print(allocation)
# Define some target return, here the 70% quantile of the average returns
target_ret = avg_rets.quantile(0.7)
section("Markowitz portfolio (long only, target return: {:.5f})".format(
target_ret))
weights = pfopt.markowitz_portfolio(cov_mat, avg_rets, target_ret)
print_portfolio_info(returns, avg_rets, weights)
allocation = investment * weights
print(allocation)
def intrinsic_val_calculation(stock_ticker):
global stock_eps_input, stock_growth_rate_input
while True:
try:
print(
Fore.RED +
"Warning! The EPS must be positive to do this Intrinsic Value Calculation"
+ Style.RESET_ALL)
stock_eps_input = float(
input("\nWhat is " + stock_ticker + "'s EPS? "))
if stock_eps_input < 0:
print(
"Sorry! We can't calculate the intrinsic value with a negative EPS"
)
stock_growth_rate_input = float(
input("What is " + stock_ticker + "'s Growth Rate? "))
break
except ValueError:
print("The input must be numbers (Example: '25', '2.5', etc.)")
pe_ratio = 7
corp_Bond_Yield = 4.4
aaa_Bond_Yield = 2.41
# Basic Graham Intrinsic Value
# Source: https://www.youtube.com/channel/UCOi_Zu4asFEMKISIbL9yuUA
graham_intrinsic = (stock_eps_input *
(pe_ratio + stock_growth_rate_input) *
corp_Bond_Yield) / aaa_Bond_Yield
# Basic EPS Intrinsic Value
# Source: https://www.youtube.com/channel/UCOi_Zu4asFEMKISIbL9yuUA
index_num_years = list(range(0, 4))
pe_ratio = stock_growth_rate_input * 2
eps_prediction_list = [stock_eps_input]
discount_rate = 0.1
for year in index_num_years:
eps_prediction_list.append(
(eps_prediction_list[year] * (1 + stock_growth_rate_input / 100)))
stock_price_prediction_list = [0] * 5
stock_price_prediction_list[0] = eps_prediction_list[4] * pe_ratio
index = list(range(1, 5))
for i in index:
stock_price_prediction_list[i] = stock_price_prediction_list[i - 1] / (
1 + discount_rate)
stock_price_prediction_list.reverse()
eps_intrinsic = stock_price_prediction_list[0]
# Average of both intrinsic values
stock_data = get_stock_data(
stock_ticker
) # Can put it as a variable in the menu to avoid this step over and over
intrinsic_value = (eps_intrinsic + graham_intrinsic) / 2
current_value = stock_data['Adj Close'][stock_data.shape[0] - 1]
upside = ((intrinsic_value / current_value) - 1) * 100
return intrinsic_value, upside, current_value
def current_earnings(portfolio_data):
stocks_tickers_owned_list = portfolio_data['Ticker']
stocks_purchase_price_owned = portfolio_data['Purchase_Price']
earnings_percentage_list = []
earnings_dollars_list = []
for ticker, shares, purchased_price in zip(stocks_tickers_owned_list,
portfolio_data['Shares'],
stocks_purchase_price_owned):
stock_data = get_stock_data(
ticker
) # Can put it as a variable in the menu to avoid this step over again
current_value = stock_data['Adj Close'][stock_data.shape[0] - 1]
earnings_percentage_list.append(
((current_value / purchased_price) - 1) * 100)
earnings_dollars_list.append(
(current_value - purchased_price) * shares)
return earnings_percentage_list, earnings_dollars_list
def home_input():
continue_program = True
print("\nHello Santiago,")
while continue_program:
print(
"\nThis is your Virtual Stock Portfolio (VSP), where you can manage your stocks.\n"
"You can:\n"
"a) 'Current': See My Portfolio and current earnings.\n"
"b) 'Edit': Change My Portfolio or Add a new stock.\n"
"c) 'Explore': Check out and analyze a new stock.\n"
"d) 'Exit': Stop the program.\n")
intro_command_input = input("Enter the command: ")
if intro_command_input == 'Current':
myPortfolio = get_data.open_portfolio() # IDK WHY DOESN'T WORK
print("\nmyPortfolio:")
print(myPortfolio)
earnings_percentage_list, earnings_dollars_list = current_command.current_earnings(
myPortfolio)
current_command.print_earnings(myPortfolio,
earnings_percentage_list,
earnings_dollars_list)
in_depth_command = input(
"\nDo you want to take a look at a specific stock? Yes or No? "
)
current_continue = False if ((in_depth_command == 'No') or
(in_depth_command == 'no')) else True
while current_continue:
stock_evaluating = input(
"From MyPortfolio, Which stock do you want to take a look at? "
)
print(
"\nWith the stocks of My Portfolio, you can:\n"
"a) 'Graphs': Get the current graph for the stock and the analytics graph\n"
"b) 'Intrinsic': Calculate the intrinsic value\n"
"c) 'Back': Go back\n")
current_command_input = input("Enter the command: ")
if current_command_input == 'Graphs':
stock_data = get_data.get_stock_data(
stock_evaluating
) # Can put it as a variable in the menu to avoid this step over and over
current_command.stock_graph(stock_evaluating, stock_data)
current_command.stock_graph_MACD(stock_evaluating,
stock_data)
elif current_command_input == 'Intrinsic':
stock_intrinsic_val, stock_upside, current_value = current_command. \
intrinsic_val_calculation(stock_evaluating)
print("\nIntrinsic Value Calculation:")
print("Stock:", stock_evaluating)
print("Current Value : $ {:.2f}".format(current_value))
print("Intrinsic Value: $ {:.2f}".format(
stock_intrinsic_val))
print("Upside : % {:.2f}\n".format(stock_upside))
elif current_command_input == 'Back':
break
else:
print("Please type the command correctly")
current_repeat = input(
"Do you want to check something else in 'Current'? 'Yes' or 'No': "
)
current_continue = False if (
(current_repeat == 'No') or
(current_repeat == 'no')) else True
elif intro_command_input == 'Edit':
edit_continue = True
while edit_continue:
print("For this section you can:\n"
"a) 'Add': Add a new stock to your portfolio\n"
"b) 'Delete': Delete a stock\n"
"c) 'Back': Go back\n")
edit_command_input = input("Enter the command: ")
if edit_command_input == 'Add':
edit_command.add_to_csv()
elif edit_command_input == 'Delete':
edit_command.delete_csv_row()
elif edit_command_input == 'Back':
break
else:
print("Please type the command correctly")
edit_repeat = input(
"Do you want to check something else in 'Edit'? 'Yes' or 'No'? "
)
edit_continue = False if ((edit_repeat == 'No') or
(edit_repeat == 'no')) else True
elif intro_command_input == 'Explore':
explore_continue = True
while explore_continue:
exploring_stock = input(
"What stock ticker symbol you want to take a look at? ")
print(
"\nFor '", exploring_stock, "' you can:\n"
"a) 'Graphs': Get the current graph for the stock and the analytics "
"graph\n"
"b) 'Intrinsic': Calculate the intrinsic value\n"
"c) 'Back': Go back\n")
explore_command_input = input("Enter the command: ")
if explore_command_input == 'Graphs':
explore_stock_data = get_data.get_stock_data(
exploring_stock)
current_command.stock_graph(exploring_stock,
explore_stock_data)
current_command.stock_graph_MACD(exploring_stock,
explore_stock_data)
elif explore_command_input == 'Intrinsic':
explore_stock_intrinsic_val, explore_stock_upside, explore_current_value = current_command. \
intrinsic_val_calculation(exploring_stock)
print("\nIntrinsic Value Calculation:")
print("Stock:", exploring_stock)
print("Current Value : $ {:.2f}".format(
explore_current_value))
print("Intrinsic Value: $ {:.2f}".format(
explore_stock_intrinsic_val))
print("Upside : % {:.2f}\n".format(explore_stock_upside))
elif explore_command_input == 'Back':
break
else:
print("Please type the command correctly")
explore_repeat = input(
"Do you want to check something else in 'Explore'? 'Yes' or 'No'? "
)
explore_continue = False if (
(explore_repeat == 'No') or
(explore_repeat == 'no')) else True
elif intro_command_input == 'Exit':
break
else:
print("Please type the command correctly")
is_repeat = input(
"Do you want to check something else in the General Menu? 'Yes' or 'No'? "
)
continue_program = False if ((is_repeat == 'No') or
(is_repeat == 'no')) else True
def predict(ticker, pred_period=1):
pred_values = []
json_file = open(model_dir + '/' + ticker + '/model.json', 'r')
loaded_model_json = json_file.read()
json_file.close()
model = model_from_json(loaded_model_json)
# load weights into new model
model.load_weights(model_dir + '/' + ticker + "/model.h5")
#print("Loaded model from disk")
#model.summary()
today = date.today()
days = timedelta(80)
period = today - days
data = get_stock_data(ticker, start_date=period,
end_date=today).reset_index(drop=True)
clean_data = data.dropna()
clean_data = clean_data.iloc[:-10]
scaler = pickle.load(open(model_dir + '/' + ticker + "/scaler.pkl", "rb"))
#print(data)
for i in range(pred_period):
req_data = clean_data.values
if i == 0:
pred_values.append({
"Open": req_data[-1, 0],
"High": req_data[-1, 1],
"Low": req_data[-1, 2],
"Close": req_data[-1, 3],
"Day": i
})
scaled = scaler.transform(req_data)
print()
to_pred = scaled[-5:]
to_pred = to_pred.reshape((1, 5, scaled.shape[1]))
######PREDICTION#######
#print('before pred')
pred = model.predict(to_pred)
#print('after_pred')
#print(pred)
pred1 = np.zeros((to_pred.shape[0], 18))
pred1[:, :4] = pred[0]
pred1 = np.around(scaler.inverse_transform(pred1), decimals=2)
pred_values.append({
"Open": pred1[0, 0],
"High": pred1[0, 1],
"Low": pred1[0, 2],
"Close": pred1[0, 3],
"Day": i + 1
})
if pred_period > 1:
data.loc[len(data)] = pred1[0]
clean_data = calculate_indicators(data).dropna()
#print(data)
#print(data.loc[data.index.max()])
#new = new + timedelta(1)
#print("The predicted value for the next trading day for " + ticker + " is : " + str(pred1[0,3]))
return pred_values
plt.legend()
#fig1 = plt.gcf()
plt.savefig(ticker + '_' + type + "conv.jpg", transparent=False)
plt.show()
#print("tf.__version__ is", tf.__version__)
#print("tf.keras.__version__ is:", tf.keras.__version__)
#tfback._get_available_gpus = _get_available_gpus
ticker = input("Please enter symbol: ")
present_date = date.today()
prev_date = date.today() - timedelta(days=5457)
print(date(present_date.year, present_date.month, present_date.day))
get_stock_data(ticker, start_date=prev_date, end_date=present_date)
dataset = pd.read_csv('stock_prices' + ticker + '.csv')
scaler = MinMaxScaler(feature_range=(0, 1))
scaled = scaler.fit_transform(dataset.values)
##### TRAIN TEST SPLITTING #####
train_gen = TimeseriesGenerator(scaled,
scaled[:, 3],
start_index=0,
end_index=int(len(scaled) * 0.8),
length=3,
batch_size=256)
test_gen = TimeseriesGenerator(scaled,
scaled[:, 3],
def train(ticker):
#Initializing the Paths
create_dir(model_dir + '/' + ticker)
output = {}
present_date = date.today()
prev_date = date.today() - timedelta(days=5457)
dataset = get_stock_data(ticker,
start_date=prev_date,
end_date=present_date,
drop_na=True).reset_index(drop=True)
dataset.to_csv(model_dir + '/' + ticker + '/' + str(ticker) + '.csv',
index=False)
scaler = MinMaxScaler(feature_range=(0, 1))
scaled = scaler.fit_transform(dataset.values)
pickle.dump(scaler, open(model_dir + '/' + ticker + '/scaler.pkl', 'wb'))
##### TRAIN TEST SPLITTING #####
'''
train_gen = TimeseriesGenerator(scaled, scaled[:,0:4], start_index = 0, end_index = int(len(scaled) * 0.90), length = 1, batch_size = 256)
test_gen = TimeseriesGenerator(scaled, scaled[:,0:4], start_index = int(len(scaled) * 0.90), end_index = int(len(scaled) - 1), length = 1, batch_size = 256)
'''
train_gen = TimeseriesGenerator(scaled,
scaled[:, :4],
start_index=0,
end_index=int(len(scaled) * 0.85),
length=5,
batch_size=16)
test_gen = TimeseriesGenerator(scaled,
scaled[:, :4],
start_index=int(len(scaled) * 0.85),
end_index=int(len(scaled) - 1),
length=5,
batch_size=16)
##### MODEL CREATION ######
'''
model = Sequential()
model.add(Conv1D(18, kernel_size=3, activation='relu', padding = 'valid', strides=1, input_shape=(1,18), data_format='channels_first'))
model.add(Conv1D(18, kernel_size=3, activation='relu', padding = 'valid', strides=1))
#model.add(MaxPooling1D(pool_size=2))
model.add(LSTM(100, activation = 'tanh', recurrent_activation = 'sigmoid', unroll = False, use_bias = True, recurrent_dropout = 0, return_sequences=True))
model.add(Dropout(0.4))
model.add(LSTM(100, activation = 'tanh', recurrent_activation = 'sigmoid', unroll = False, use_bias = True, recurrent_dropout = 0,return_sequences=True))
model.add(Dropout(0.4))
model.add(LSTM(100, activation = 'tanh', recurrent_activation = 'sigmoid', unroll = False, use_bias = True, recurrent_dropout = 0,return_sequences= True))
model.add(Dropout(0.2))
model.add(Flatten())
model.add(Dense(4, activation = 'linear'))
adadelta = Adadelta(learning_rate=1.0, rho=0.95)
model.compile(loss= 'mae', optimizer = adadelta, metrics=[tf.keras.metrics.MeanAbsolutePercentageError()])
#model.summary()
'''
from tensorflow.keras.regularizers import l1
model = Sequential()
model.add(
Conv1D(18,
kernel_size=3,
activation='relu',
padding='valid',
strides=1,
input_shape=(5, 18),
data_format='channels_first'))
model.add(
Conv1D(18,
kernel_size=4,
activation='relu',
padding='valid',
strides=1))
#model.add(MaxPooling1D(pool_size=2))
model.add(
LSTM(100,
activation='tanh',
recurrent_activation='sigmoid',
unroll=False,
use_bias=True,
recurrent_dropout=0,
return_sequences=True,
kernel_regularizer=l1(0.001)))
model.add(Dropout(0.4))
model.add(
LSTM(50,
activation='tanh',
recurrent_activation='sigmoid',
unroll=False,
use_bias=True,
recurrent_dropout=0,
return_sequences=True,
activity_regularizer=l1(0.001)))
model.add(Dropout(0.4))
model.add(
LSTM(25,
activation='tanh',
recurrent_activation='sigmoid',
unroll=False,
use_bias=True,
recurrent_dropout=0,
return_sequences=True,
activity_regularizer=l1(0.001)))
model.add(Dropout(0.2))
model.add(Flatten())
model.add(Dense(4, activation='linear'))
adadelta = Adadelta(learning_rate=1.0, rho=0.95)
model.compile(loss='mse',
optimizer=adadelta,
metrics=[tf.keras.metrics.RootMeanSquaredError()])
model.summary()
##### TRAINING #####
my_callbacks = [
#tf.keras.callbacks.ReduceLROnPlateau(monitor='val_loss', patience=4, factor=0.2, min_lr=0.001),
tf.keras.callbacks.ModelCheckpoint(
filepath=model_dir + "/" + ticker + "/model" + ".h5",
save_weights_only=True,
save_best_only=True,
monitor="val_root_mean_squared_error",
mode="min"),
]
history = model.fit_generator(train_gen,
epochs=300,
verbose=0,
shuffle=True,
validation_data=test_gen,
callbacks=my_callbacks)
##### PLOTTING LOSS ######
'''plt.plot(history.history['loss'], label='train')
plt.plot(history.history['val_loss'], label='test')
plt.legend()
plt.show()
score = model.evaluate_generator(test_gen, verbose = 1)
print()
print('Test loss:', score[0])
print('Test accuracy:', score[1])
print()'''
###### RESHAPE ACTUAL DATA #######
actual_train = reshape_actual(train_gen)
predictions_train = model.predict_generator(train_gen, verbose=0)
print(predictions_train)
##### RSME FOR TRAIN #####
rmse_train = math.sqrt(
mean_squared_error(actual_train[:], predictions_train[:]))
print(rmse_train)
###### TEST DATA ######
actual_test = reshape_actual(test_gen)
predictions_test = model.predict_generator(test_gen, verbose=0)
rmse_test = math.sqrt(
mean_squared_error(actual_test[:], predictions_test[:]))
print(rmse_test)
output["Accuracy"] = {
"Train": round(rmse_train * 100, 2),
"Test": round(rmse_test * 100, 2)
}
###### PLOT TEST ######
output["Train"] = plot_them_graphs(actual_train, predictions_train,
"train", ticker, scaler)
output["Test"] = plot_them_graphs(actual_test, predictions_test, "test",
ticker, scaler)
##### SAVE IT!!!!!! #####
model_json = model.to_json()
with open(model_dir + "/" + ticker + "/model" + ".json", "w") as json_file:
json_file.write(model_json)
#model.save_weights(model_dir + "/" + ticker + "/model" + ".h5")
print("Saved model to disk")
data = {"name": ticker, "date": present_date.strftime("%d-%b-%Y")}
with open(model_dir + "/" + ticker + '/data.json', 'w') as outfile:
json.dump(data, outfile)
return output
