jerry/OpenBB
1
0
Fork 0
mirror of https://github.com/OpenBB-finance/OpenBB.git synced 2026-11-08 10:22:09 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add regression file with linear,quadratic,cubic,and personalized funcs

Browse Source
This commit is contained in:
didier
2021-02-07 23:14:30 +00:00
parent b1feeb59c4
commit e7b4e8d334
2 changed files with 47 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
prediction_techniques/pred_menu.py
View File

@@ -11,7 +11,7 @@ register_matplotlib_converters()
from prediction_techniques import sma
from prediction_techniques import knn
from prediction_techniques import lr
from prediction_techniques import regression
# -----------------------------------------------------------------------------------------------------------------------
def print_prediction(s_ticker, s_start, s_interval):
@@ -31,7 +31,10 @@ def print_prediction(s_ticker, s_start, s_interval):
print("")
print(" sma simple moving average")
print(" knn k-Nearest Neighbors")
print(" lr linear regression")
print(" linear linear regression (polynomial 1)")
print(" quadratic quadratic regression (polynomial 2)")
print(" cubic cubic regression (polynomial 3)")
print(" regression regression (other polynomial)")
print("")
@@ -41,7 +44,8 @@ def pred_menu(df_stock, s_ticker, s_start, s_interval):
# Add list of arguments that the prediction techniques parser accepts
pred_parser = argparse.ArgumentParser(prog='technical_analysis', add_help=False)
pred_parser.add_argument('cmd', choices=['help', 'q', 'quit',
'sma', 'knn', 'lr'])
'sma', 'knn',
'linear', 'quadratic', 'cubic', 'regression'])
print_prediction(s_ticker, s_start, s_interval)
@@ -77,9 +81,18 @@ def pred_menu(df_stock, s_ticker, s_start, s_interval):
elif ns_known_args.cmd == 'knn':
knn.k_nearest_neighbors(l_args, s_ticker, s_interval, df_stock)
# --------------------------------------------- LINEAR REGRESSION ---------------------------------------------
elif ns_known_args.cmd == 'lr':
lr.linear_regression(l_args, s_ticker, s_interval, df_stock)
# ------------------------------------------------- REGRESSION -------------------------------------------------
elif ns_known_args.cmd == 'linear':
regression.regression(l_args, s_ticker, s_interval, df_stock, regression.LINEAR)
elif ns_known_args.cmd == 'quadratic':
regression.regression(l_args, s_ticker, s_interval, df_stock, regression.QUADRATIC)
elif ns_known_args.cmd == 'cubic':
regression.regression(l_args, s_ticker, s_interval, df_stock, regression.CUBIC)
elif ns_known_args.cmd == 'regression':
regression.regression(l_args, s_ticker, s_interval, df_stock, regression.USER_INPUT)
# ------------------------------------------------------------------------------------------------------------
else:

40
prediction_techniques/lr.py → prediction_techniques/regression.py
View File

@@ -7,19 +7,29 @@ from pandas.plotting import register_matplotlib_converters
register_matplotlib_converters()
from TimeSeriesCrossValidation import splitTrain
from sklearn import linear_model
from sklearn import pipeline
from sklearn import preprocessing
# ----------------------------------------------------- LR -----------------------------------------------------
def linear_regression(l_args, s_ticker, s_interval, df_stock):
parser = argparse.ArgumentParser(prog='linear_regression',
description="""Linear regression attempts to model the relationship between
two variables by fitting a linear equation to observed data. One variable is
considered to be an explanatory variable, and the other is considered to be a
dependent variable. """)
USER_INPUT = 0
LINEAR = 1
QUADRATIC = 2
CUBIC = 3
# -------------------------------------------------- REGRESSION --------------------------------------------------
def regression(l_args, s_ticker, s_interval, df_stock, polynomial):
parser = argparse.ArgumentParser(prog='regression',
description="""Regression attempts to model the relationship between
two variables by fitting a linear/quadratic/cubic/other equation to
observed data. One variable is considered to be an explanatory variable,
and the other is considered to be a dependent variable. """)
parser.add_argument('-i', "--input", action="store", dest="n_inputs", type=check_positive, default=40, help='number of days to use for prediction')
parser.add_argument('-d', "--days", action="store", dest="n_days", type=check_positive, default=5, help='prediction days')
parser.add_argument('-j', "--jumps", action="store", dest="n_jumps", type=check_non_negative, default=0, help='number of jumps in training data')
if polynomial == USER_INPUT:
parser.add_argument('-p', "--polynomial", action="store", dest="n_polynomial", type=check_positive, required=True, help='polynomial associated with regression')
try:
(ns_parser, l_unknown_args) = parser.parse_known_args(l_args)
@@ -31,17 +41,23 @@ def linear_regression(l_args, s_ticker, s_interval, df_stock):
stock_x, stock_y = splitTrain.split_train(df_stock['4. close'].values, ns_parser.n_inputs, ns_parser.n_days, ns_parser.n_jumps)
# Machine Learning model
lr = linear_model.LinearRegression(n_jobs=-1)
lr.fit(stock_x, stock_y)
if polynomial == LINEAR:
model = linear_model.LinearRegression(n_jobs=-1)
else:
if polynomial == USER_INPUT:
polynomial = ns_parser.n_polynomial
model = pipeline.make_pipeline(preprocessing.PolynomialFeatures(polynomial), linear_model.Ridge())
model.fit(stock_x, stock_y)
l_predictions = model.predict(df_stock['4. close'].values[-ns_parser.n_inputs:].reshape(1, -1))[0]
# Prediction data
l_predictions = lr.predict(df_stock['4. close'].values[-ns_parser.n_inputs:].reshape(1, -1))[0]
l_pred_days = get_next_stock_market_days(last_stock_day=df_stock['4. close'].index[-1], n_next_days=ns_parser.n_days)
df_pred = pd.Series(l_predictions, index=l_pred_days, name='Price')
# Plotting
plt.plot(df_stock.index, df_stock['4. close'], lw=2)
plt.title(f"Linear Regression on {s_ticker} - {ns_parser.n_days} days prediction")
plt.title(f"Regression (polynomial {polynomial}) on {s_ticker} - {ns_parser.n_days} days prediction")
plt.xlim(df_stock.index[0], get_next_stock_market_days(df_pred.index[-1], 1)[-1] )
plt.xlabel('Time')
plt.ylabel('Share Price ($)')