def main(tickers=['AAPL'], start=None, end=None, n_steps=21):
data = OrderedDict()
pred_data = OrderedDict()
forecast_data = OrderedDict()
for ticker in tickers:
data[ticker] = fc.get_time_series(ticker, start, end)
# add the outcome variable, 1 if the trading session was positive (close>open), 0 otherwise
data[ticker]['outcome'] = data[ticker].apply(
lambda x: 1 if x['adj_close'] > x['adj_open'] else 0, axis=1)
data[ticker] = fc.get_sma_classifier_features(data[ticker]).dropna()
# cross-validation testing
split = rand.uniform(0.60, 0.80)
train_size = int(len(data[ticker]) * split)
train, test = data[ticker][0:train_size], data[ticker][
train_size:len(data[ticker])]
features = ['sma_2', 'sma_3', 'sma_4', 'sma_5', 'sma_6']
# values of features
X = list(train[features].values)
# target values
Y = list(train['outcome'])
# fit a Naive Bayes model to the data
mdl = MLPClassifier(hidden_layer_sizes=(100, 100, 100)).fit(X, Y)
print(mdl)
# make predictions
pred = mdl.predict(test[features].values)
# summarize the fit of the model
classification_report, confusion_matrix = fc.get_classifier_metrics(
test['outcome'].values, pred)
print("{} Neural Network\n"
"-------------\n"
"Classification report: {}\n\n"
"Confusion matrix: {}\n\n".format(ticker, classification_report,
confusion_matrix))
pred_results = pd.DataFrame(data=dict(original=test['outcome'],
prediction=pred),
index=test.index)
pred_data[ticker] = pred_results
# out-of-sample test
forecast_data[ticker] = fc.forecast_classifier(model=mdl,
sample=test,
features=features,
steps=n_steps)
return forecast_data
def main(tickers=['AAPL'], start=None, end=None, n_steps=21):
data = OrderedDict()
pred_data = OrderedDict()
forecast_data = OrderedDict()
for ticker in tickers:
data[ticker] = fc.get_time_series(ticker, start, end)
# add the outcome variable, 1 if the trading session was positive (close>open), 0 otherwise
data[ticker]['outcome'] = data[ticker].apply(
lambda x: 1 if x['adj_close'] > x['adj_open'] else 0, axis=1)
data[ticker] = fc.get_sma_classifier_features(data[ticker])
train_size = int(len(data[ticker]) * 0.80)
train, test = data[ticker][0:train_size], data[ticker][
train_size:len(data[ticker])]
features = ['sma_2', 'sma_3', 'sma_4', 'sma_5', 'sma_6']
# values of features
X = list(train[features].values)
# target values
Y = list(train['outcome'])
mdl = DecisionTreeClassifier().fit(X, Y)
print(mdl)
'''
dot_data = export_graphviz(mdl,
out_file=None,
feature_names=list(train[['feat1', 'feat2', 'feat3', 'feat4', 'feat5']]),
class_names='outcome',
filled=True,
rounded=True,
special_characters=True)
graph = pydot.graph_from_dot_data(dot_data)
graph.write_png("charts/decision-tree-classifier2.png")
'''
pred = mdl.predict(test[features].values)
pred_prob = mdl.predict_proba(test[features].values)
# summarize the fit of the model
classification_report, confusion_matrix = fc.get_classifier_metrics(
test['outcome'].values, pred)
print("{} Decision Tree\n"
"-------------\n"
"Classification report: {}\n"
"Confusion matrix: {}\n"
"Prediction probability: {}\n".format(ticker,
classification_report,
confusion_matrix,
pred_prob))
pred_results = pd.DataFrame(data=dict(original=test['outcome'],
prediction=pred),
index=test.index)
pred_data[ticker] = pred_results
# out-of-sample test
forecast_data[ticker] = fc.forecast_classifier(model=mdl,
sample=test,
features=features,
steps=n_steps)
return forecast_data
def main(tickers=['AAPL'], start=None, end=None, n_steps=21):
data = OrderedDict()
pred_data = OrderedDict()
forecast_data = OrderedDict()
for ticker in tickers:
data[ticker] = fc.get_time_series(ticker, start, end)
# add the outcome variable, 1 if the trading session was positive (close>open), 0 otherwise
data[ticker]['outcome'] = data[ticker].apply(
lambda x: 1 if x['adj_close'] > x['adj_open'] else -1, axis=1)
data[ticker] = fc.get_sma_classifier_features(data[ticker])
# cross-validation testing
split = rand.uniform(0.60, 0.80)
train_size = int(len(data[ticker]) * split)
train, test = data[ticker][0:train_size], data[ticker][
train_size:len(data[ticker])]
features = ['sma_2', 'sma_3', 'sma_4', 'sma_5', 'sma_6']
# values of features
X = list(train[features].values)
# target values
Y = list(train['outcome'])
clf1 = AdaBoostClassifier()
clf2 = RandomForestClassifier()
clf3 = DecisionTreeClassifier()
clf4 = KNeighborsClassifier()
clf5 = LogisticRegression()
clf6 = SGDClassifier()
clf7 = MLPClassifier()
clf8 = GaussianNB()
clf9 = BernoulliNB()
clf10 = SVC()
mdl = VotingClassifier(estimators=[('bt', clf1), ('rf', clf2),
('dt', clf3), ('knn', clf4),
('lgt', clf5), ('sgd', clf6),
('mlp', clf7), ('gnb', clf8),
('bnb', clf9), ('svm', clf10)],
voting='hard').fit(X, Y)
print(mdl)
confidence = mdl.score(test[features].values, test['outcome'].values)
print("{} Voting Classifier\n"
"-------------\n"
"Confidence: {}\n".format(ticker, confidence))
pred = mdl.predict(test[features].values)
pred_data[ticker] = pred
# out-of-sample test
forecast_data[ticker] = fc.forecast_classifier(
model=mdl, sample=test, features=features,
steps=n_steps)['outcome']
return forecast_data