**Greetings Quantopian Community (any help you can provide me would be very much appreciated!) -
When I try to run the code below, I get a 'Syntax Error' message for line 154 - the line that says 'clf1 = DecisionTreeClassifier()'
I tried messing around with this to no avail. I dont understand the problem as I thought I had imported the sk library and its accompanying algorithms. Any thoughts?!**
from quantopian.algorithm import attach_pipeline, pipeline_output
from quantopian.pipeline import Pipeline
from quantopian.pipeline.data.builtin import USEquityPricing
from quantopian.pipeline.factors import AverageDollarVolume
from quantopian.pipeline.filters.morningstar import Q1500US
import sys
import logbook
from datetime import datetime
import numpy as np
import pandas as pd
from pandas import Series, DataFrame
import scipy.stats as stats
import matplotlib.pyplot as plt
import seaborn as sns
import collections
from collections import Counter
import sklearn
from sklearn import preprocessing
from sklearn.datasets import load_iris
from sklearn.preprocessing import MinMaxScaler
from sklearn.feature_selection import SelectKBest
from sklearn import model_selection
from sklearn.metrics import accuracy_score, precision_score, recall_score
from sklearn.model_selection import train_test_split
from sklearn.model_selection import KFold
from sklearn.model_selection import GridSearchCV
from sklearn import linear_model
from sklearn.linear_model import LinearRegression, Logisticregression
from sklearn import svm
from sklearn.svm import SVC, LinearSVC, NuSVC
from sklearn import tree
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
import pytz
import pyfolio as pf
import talib as tb
from talib.abstract import *
import translate
from translate import translator
import alphalens
import zipline
from zipline import TradingAlgorithm
from zipline.api import order_target, record, symbol
translator('en', 'zh-TW', 'Hello Traders. Welcome to Hua er Jie')
def initialize(context):
set_universe = fetch_csv('https://www.dropbox.com/s/v4jak4le814i33v/finviz%20%281%29.csv?dl=0')
context.stocks = symbols('ABTX', 'AMH', 'BLDR','CCOI', 'CHCT', 'CNQ', 'CXP', 'DRE', 'E', 'ENLK', 'EXAR', 'GMS', 'GPT', 'GTN', 'GWGH', 'HBMD', 'INVA', 'INVH', 'JCAP', 'JD', 'KMT', 'LFL', 'MOMO', 'NEP', 'NEWR', 'NORD', 'NRG', 'OAK', 'OLBK', 'RGEN', 'RICK', 'RP', 'RYN', 'SBY', 'SSP', 'SUPN', 'SWC', 'SYX', 'TITN', 'TPC', 'TWOU', 'UMH', 'USAP', 'USFD', 'UTEK', 'VDTH', 'VRNS', 'WGP', 'WMGI', 'WWE')
context.historical_bars = 100
context.feature_window = 10
pipe = Pipeline(screen = set_universe)
attach_pipeline(pipe, 'my_pipeline')
# talib stuff here to add into pipeline
sma = abstract.SMA # Do i need this line?
sma_ = SMA(context.stocks, timeperiod=100)
rsi_ = RSI(context.stocks, timeperiod=100)
morning_star = CDLMORNINGSTAR(context.stocks, timeperiod=100) # do i need a ohlc here?
technical_indicators = [sma_, rsi_, morning_star]
# add a filter for signals you dont want (optional)
# pipe.add()
pipe.add(technical_indicators, 'technical_indicators')
# pipe.set_screen(add filter here) (optional) def before_trading_start(context, data):
output = pipeline_output('my_pipeline')
# two lines from 'Pipeline API' doc
context.my_universe = output.sort('technical_indicators', ascending=False)
update_universe(context.my_universe.index) # index?
print outputdef handle_data(context, data):
cash = context.portfolio.cash
current_positions = context.portfolio.positions
prices = history(bar_count = context.historical_bars, \
frequency = '1d', field = 'price')
for stock in context.my_universe: # or 'output'
try:
ma1 = data[stock].mavg(50)
ma2 = data[stock].mavg(200)
start_bar = context.feature_window
price_list = prices[stock].tolist()
X = []
y = []
# feature creation
bar = start_bar
while bar < len(price_list) - 1:
try:
end_price = price_list[bar + 1]
begin_price = price_list[bar]
pricing_list = []
xx = 0
for _ in range(context.feature_window):
price = price_list[bar - (context.feature_window -xx)]
pricing_list.append(price)
xx += 1
features = np.around(np.diff(pricing_list) /
pricing_list[:-1] \
* 100.0, 1)
print(features)
if end_price > begin_price:
label = 1
else:
label = -1
bar += 1
X.append(features)
y.append(labels)
except Exception as e:
bar += 1
print (('feature creation', str(e))
clf1 = DecisionTreeClassifier()
clf2 = RandomForestClassifier()
clf3 = SVC()
clf4 = LinearSVC()
clf5 = LogisticRegression()
clf6 = LinearRegression()
last_prices = price_list[-context.feature_window:]
current_features = np.around(np.diff(last_prices) / last_prices[:-1] * 100.0, 1) # other code from my sheet?
X.append(current_featurs)
X = preprocessing.scale(X)
current_features = X[-1]
X = X[:-1]
clf1.fit(X, y)
clf2.fit(X, y)
clf3.fit(X, y)
clf4.fit(X, y)
clf5.fit(X, y)
clf6.fit(X, y)
p1 = clf1.predict(current_features)[0]
p2 = clf2.predict(current_features)[0]
p3 = clf3.predict(current_features)[0]
p4 = clf4.predict(current_features)[0]
p5 = clf5.predict(current_features)[0]
p6 = clf6.predict(current_features)[0]
if Counter([p1, p2, p3, p4, p5, p6]).most_common(1)[0][1] > = 4:
p = Counter([p1, p2, p3, p4, p5, p6]).most_common(1)[0][1]
else:
p = 0
print(('Prediction', p))
if p == 1 and ma1 > ma2:
order_target_percent(stock, 0.11) #leverage set at 11x
elif p == -1 and ma1 < ma2:
order_target_percent(stock, -0.11)
record('ma1', ma1)
record('ma2', ma2)
record('Leverage', context.account.leverage) 
