def initialize(context):
"""
Called once at the start of the algorithm.
"""
feature_num = 11
context.orders_submitted = False
large_num = 9999999
least_num = 0
context.n_components = feature_num
context.security = symbol(SYMBOL) # Trade SPY
set_benchmark(symbol(SYMBOL)) # Set benchmarks
context.model = DecisionTreeClassifier(criterion='entropy',
max_depth=feature_num,
random_state=0)
context.lookback = 350 # Look back 62 days
context.history_range = 350 # Only consider the past 400 days' history
context.threshold = 4.05
context.longprices = large_num
context.shortprices = least_num
set_long_only()
# Generate a new model every week
schedule_function(create_model, date_rules.week_end(),
time_rules.market_close(minutes=10))
"""
# Generate a new model every week
schedule_function(create_model1, date_rules.week_end(), time_rules.market_close(minutes=10))
"""
# Trade at the start of every day
schedule_function(rebalance, date_rules.every_day(),
time_rules.market_open(minutes=1))
def initialize(context):
"""
Called once at the start of the algorithm.
"""
feature_num = 11
context.orders_submitted = False
large_num = 9999999
least_num = 0
context.n_components = feature_num
context.security = symbol(SYMBOL) # Trade SPY
set_benchmark(symbol(SYMBOL)) # Set benchmarks
context.model = SVC(kernel='rbf', tol=1e-3, random_state=0, gamma=0.2, C=10.0, verbose=True) # 8.05 for SVM model
context.lookback = 350 # Look back 62 days
context.history_range = 350 # Only consider the past 400 days' history
context.threshold = 4.05
context.longprices = large_num
context.shortprices = least_num
set_long_only()
# Generate a new model every week
schedule_function(create_model, date_rules.week_end(), time_rules.market_close(minutes=10))
"""
# Generate a new model every week
schedule_function(create_model1, date_rules.week_end(), time_rules.market_close(minutes=10))
"""
# Trade at the start of every day
schedule_function(rebalance, date_rules.every_day(), time_rules.market_open(minutes=1))
def initialize(context):
# AAPL
context.security = symbol('AAPL')
# Algorithm will only take long positions.
# It will stop if encounters a short position.
set_long_only()
def initialize(context):
"""
Called once at the start of the algorithm.
"""
feature_num = 11
context.orders_submitted = False
large_num = 9999999
least_num = 0
context.n_components = 6
context.security = symbol(SYMBOL) # Trade SPY
set_benchmark(symbol(SYMBOL)) # Set benchmarks
context.model2 = SVC(kernel='rbf', tol=1e-3, random_state=0, gamma=0.2, C=10.0, verbose=True) # 8.05 for SVM model
context.model3 = KNeighborsClassifier(n_neighbors=feature_num, p=3, metric='minkowski') # 7.05 for model
context.model = DecisionTreeClassifier(criterion='entropy', max_depth=feature_num, random_state=0)
context.model4 = RandomForestClassifier(criterion='entropy', n_estimators=feature_num, random_state=1,
n_jobs=2) # 5.2 for randomforest
context.model1 = LogisticRegression(random_state=0, solver='lbfgs', multi_class='multinomial')
context.modellist = {'SVM':context.model2,'KNeighbors':context.model3,'DecisionTree':context.model,'RandomForest':context.model4,'LogisticRegression':context.model1}
context.lookback = 350 # Look back 62 days
context.history_range = 350 # Only consider the past 400 days' history
context.threshold = 4.05
context.longprices = large_num
context.shortprices = least_num
context.time_series = 0
context.init = 0
set_long_only()
# Generate a new model every week
#schedule_function(create_model, date_rules.week_end(), time_rules.market_close(minutes=10))
"""
# Generate a new model every week
schedule_function(create_model1, date_rules.week_end(), time_rules.market_close(minutes=10))
"""
# Trade at the start of every day
schedule_function(rebalance, date_rules.every_day(), time_rules.market_open(minutes=1))
def initialize(context):
context.has_ordered = False
set_commission(
OrderCost(open_tax=0,
close_tax=0.001,
open_commission=0.0003,
close_commission=0.0003,
close_today_commission=0,
min_commission=5))
set_long_only()
def initialize(context):
context.security = symbol(SYMBOL) # Trade
set_benchmark(symbol(SYMBOL)) # Set benchmarks
#print(context.security)
context.start = True
set_long_only()
schedule_function(market_open, date_rules.every_day(),
time_rules.market_open(minutes=1))
context.orders_submitted = False
def initialize(context):
algo.set_long_only()
algo.attach_pipeline(make_pipeline(), 'pipeline')
algo.schedule_function(
rebalance,
algo.date_rules.every_day(),
algo.time_rules.market_close(minutes=30),
)
def initialize(context):
ws.send(msg_placeholder % "Simulation Start")
context.security = symbol(ticker)
context.long_threshold = 0
context.short_threshold = -0.06
context.no_shorts = no_shorts
if context.no_shorts:
set_long_only()
context.n_clusters = 9
context.ret_windows = [30]
context.window_lengths = [30, 90, 150, 210, 240]
context.lookback = 8 * 250
context.refresh_frequency = 30
context.use_classifier = use_clf
if context.use_classifier:
context.ret_buckets = {
"gen": [-0.04, 0, 0.04]
}
context.long_prob_lb = 0.5
context.short_prob_ub = 0.3
context.model = {}
context.return_projections = {}
context.price_projections = {}
context.bucket_probs = {}
context.days_traded = 0
context.last_traded_date = 0
schedule_function(rebalance, date_rule=date_rules.every_day(), time_rule=time_rules.market_open(hours=1))
ws.send(msg_placeholder % "Execution of clustering scheduled at 1 hour after market open")
def initialize(context):
# Manually define stocks instead of downloading a universe with Fetch or using a cross section with set_universe
context.stocks = symbols('AAPL', 'IBM', 'CSCO', 'SYN')
# Dictionary of durations, optional for any order
context.duration = {}
# Inside the data loop, keep track of commited cash for the new orders.
# The portfolio cash is not updated on an intra cycle time scale yet.
context.cashCommitedToBuy = 0
context.cashCommitedToSell = 0
# set a more realistic commission for IB
set_commission(commission.PerShare(cost=0.014, min_trade_cost=1.4))
# Prevent shorting, not needed here but it will stop
# runaway code, like if you buy condition goes nuts
# borrowing uncontrollably.
set_long_only()
logging.info(
"---Prices below reflect market price or average held value at time of action and"
+ " NOT the value of the transactions. Use the Run Full Backtest" +
" button and view the transactions tab to view real prices.---")
def initialize(context):
"""
Called once at the start of the algorithm.
"""
feature_num = 11
context.orders_submitted = False
large_num = 9999999
least_num = 0
context.n_components = 11
context.n_components = 6
context.SP500_symbol = [
'AAPL', 'ABT', 'ABBV', 'ACN', 'ACE', 'ADBE', 'ADT', 'AAP', 'AES',
'AET', 'AFL', 'AMG', 'A', 'GAS', 'ARE', 'APD', 'AKAM', 'AA', 'AGN',
'ALXN', 'ALLE', 'ADS', 'ALL', 'ALTR', 'MO', 'AMZN', 'AEE', 'AAL',
'AEP', 'AXP', 'AIG', 'AMT', 'AMP', 'ABC', 'AME', 'AMGN', 'APH', 'APC',
'ADI', 'AON', 'APA', 'AIV', 'AMAT', 'ADM', 'AIZ', 'T', 'ADSK', 'ADP',
'AN', 'AZO', 'AVGO', 'AVB', 'AVY', 'BHI', 'BLL', 'BAC', 'BK', 'BCR',
'BXLT', 'BAX', 'BBT', 'BDX', 'BBBY', 'BRK.B', 'BBY', 'BLX', 'HRB',
'BA', 'BWA', 'BXP', 'BSX', 'BMY', 'BRCM', 'BF.B', 'CHRW', 'CA', 'CVC',
'COG', 'CAM', 'CPB', 'COF', 'CAH', 'HSIC', 'KMX', 'CCL', 'CAT', 'CBG',
'CBS', 'CELG', 'CNP', 'CTL', 'CERN', 'CF', 'SCHW', 'CHK', 'CVX', 'CMG',
'CB', 'CI', 'XEC', 'CINF', 'CTAS', 'CSCO', 'C', 'CTXS', 'CLX', 'CME',
'CMS', 'COH', 'KO', 'CCE', 'CTSH', 'CL', 'CMCSA', 'CMA', 'CSC', 'CAG',
'COP', 'CNX', 'ED', 'STZ', 'GLW', 'COST', 'CCI', 'CSX', 'CMI', 'CVS',
'DHI', 'DHR', 'DRI', 'DVA', 'DE', 'DLPH', 'DAL', 'XRAY', 'DVN', 'DO',
'DTV', 'DFS', 'DISCA', 'DISCK', 'DG', 'DLTR', 'D', 'DOV', 'DOW', 'DPS',
'DTE', 'DD', 'DUK', 'DNB', 'ETFC', 'EMN', 'ETN', 'EBAY', 'ECL', 'EIX',
'EW', 'EA', 'EMC', 'EMR', 'ENDP', 'ESV', 'ETR', 'EOG', 'EQT', 'EFX',
'EQIX', 'EQR', 'ESS', 'EL', 'ES', 'EXC', 'EXPE', 'EXPD', 'ESRX', 'XOM',
'FFIV', 'FB', 'FAST', 'FDX', 'FIS', 'FITB', 'FSLR', 'FE', 'FISV',
'FLIR', 'FLS', 'FLR', 'FMC', 'FTI', 'F', 'FOSL', 'BEN', 'FCX', 'FTR',
'GME', 'GPS', 'GRMN', 'GD', 'GE', 'GGP', 'GIS', 'GM', 'GPC', 'GNW',
'GILD', 'GS', 'GT', 'GOOGL', 'GOOG', 'GWW', 'HAL', 'HBI', 'HOG', 'HAR',
'HRS', 'HIG', 'HAS', 'HCA', 'HCP', 'HCN', 'HP', 'HES', 'HPQ', 'HD',
'HON', 'HRL', 'HSP', 'HST', 'HCBK', 'HUM', 'HBAN', 'ITW', 'IR', 'INTC',
'ICE', 'IBM', 'IP', 'IPG', 'IFF', 'INTU', 'ISRG', 'IVZ', 'IRM', 'JEC',
'JBHT', 'JNJ', 'JCI', 'JOY', 'JPM', 'JNPR', 'KSU', 'K', 'KEY', 'GMCR',
'KMB', 'KIM', 'KMI', 'KLAC', 'KSS', 'KRFT', 'KR', 'LB', 'LLL', 'LH',
'LRCX', 'LM', 'LEG', 'LEN', 'LVLT', 'LUK', 'LLY', 'LNC', 'LLTC', 'LMT',
'L', 'LOW', 'LYB', 'MTB', 'MAC', 'M', 'MNK', 'MRO', 'MPC', 'MAR',
'MMC', 'MLM', 'MAS', 'MA', 'MAT', 'MKC', 'MCD', 'MCK', 'MJN', 'MMV',
'MDT', 'MRK', 'MET', 'KORS', 'MCHP', 'MU', 'MSFT', 'MHK', 'TAP',
'MDLZ', 'MON', 'MNST', 'MCO', 'MS', 'MOS', 'MSI', 'MUR', 'MYL', 'NDAQ',
'NOV', 'NAVI', 'NTAP', 'NFLX', 'NWL', 'NFX', 'NEM', 'NWSA', 'NEE',
'NLSN', 'NKE', 'NI', 'NE', 'NBL', 'JWN', 'NSC', 'NTRS', 'NOC', 'NRG',
'NUE', 'NVDA', 'ORLY', 'OXY', 'OMC', 'OKE', 'ORCL', 'OI', 'PCAR',
'PLL', 'PH', 'PDCO', 'PAYX', 'PNR', 'PBCT', 'POM', 'PEP', 'PKI',
'PRGO', 'PFE', 'PCG', 'PM', 'PSX', 'PNW', 'PXD', 'PBI', 'PCL', 'PNC',
'RL', 'PPG', 'PPL', 'PX', 'PCP', 'PCLN', 'PFG', 'PG', 'PGR', 'PLD',
'PRU', 'PEG', 'PSA', 'PHM', 'PVH', 'QRVO', 'PWR', 'QCOM', 'DGX', 'RRC',
'RTN', 'O', 'RHT', 'REGN', 'RF', 'RSG', 'RAI', 'RHI', 'ROK', 'COL',
'ROP', 'ROST', 'RLD', 'R', 'CRM', 'SNDK', 'SCG', 'SLB', 'SNI', 'STX',
'SEE', 'SRE', 'SHW', 'SPG', 'SWKS', 'SLG', 'SJM', 'SNA', 'SO', 'LUV',
'SWN', 'SE', 'STJ', 'SWK', 'SPLS', 'SBUX', 'HOT', 'STT', 'SRCL', 'SYK',
'STI', 'SYMC', 'SYY', 'TROW', 'TGT', 'TEL', 'TE', 'TGNA', 'THC', 'TDC',
'TSO', 'TXN', 'TXT', 'HSY', 'TRV', 'TMO', 'TIF', 'TWX', 'TWC', 'TJX',
'TMK', 'TSS', 'TSCO', 'RIG', 'TRIP', 'FOXA', 'TSN', 'TYC', 'UA', 'UNP',
'UNH', 'UPS', 'URI', 'UTX', 'UHS', 'UNM', 'URBN', 'VFC', 'VLO', 'VAR',
'VTR', 'VRSN', 'VZ', 'VRTX', 'VIAB', 'V', 'VNO', 'VMC', 'WMT', 'WBA',
'DIS', 'WM', 'WAT', 'ANTM', 'WFC', 'WDC', 'WU', 'WY', 'WHR', 'WFM',
'WMB', 'WEC', 'WYN', 'WYNN', 'XEL', 'XRX', 'XLNX', 'XL', 'XYL', 'YHOO',
'YUM', 'ZBH', 'ZION', 'ZTS'
]
context.model2 = SVC(kernel='rbf',
tol=1e-3,
random_state=0,
gamma=0.2,
C=10.0,
verbose=True) # 8.05 for SVM model
context.model3 = KNeighborsClassifier(
n_neighbors=feature_num, p=3, metric='minkowski') # 7.05 for model
context.model5 = DecisionTreeClassifier(criterion='entropy',
max_depth=feature_num,
random_state=0)
context.model4 = RandomForestClassifier(criterion='entropy',
n_estimators=feature_num,
random_state=1,
n_jobs=2) # 5.2 for randomforest
context.model1 = LogisticRegression(random_state=0,
solver='lbfgs',
multi_class='multinomial')
context.model = KMeans(n_clusters=8,
init='k-means++',
max_iter=300,
tol=1e-4,
random_state=0)
#context.model = DBSCAN(eps=0.2,min_samples=3,metric='euclidean')
context.lookback = 350 # Look back 62 days
context.history_range = 350 # Only consider the past 400 days' history
context.threshold = 4.05
context.longprices = large_num
context.shortprices = least_num
context.times = 0
set_long_only()
# Generate a new model every week
schedule_function(create_model, date_rules.week_end(),
time_rules.market_close(minutes=10))
"""
# Generate a new model every week
schedule_function(create_model1, date_rules.week_end(), time_rules.market_close(minutes=10))
"""
# Trade at the start of every day
schedule_function(rebalance, date_rules.every_day(),
time_rules.market_open(minutes=1))