X_test = features[mid + 1:high - 1]
y_test = result[mid + 2:high]
dates = dates[mid + 2:high]
reg.fit(X_train, y_train)
# predict data #
y_pred = reg.predict(X_test)
print("[INFO] %s: %3.2f%%" %
(symbol, round(reg.score(X_test, y_test) * 100, 2)),
file=sys.stderr)
# save last 100 days' prediction data
sql_data = []
for i in range(0, len(y_pred)):
save_date = dates[i][0:4] + "-" + dates[i][4:6] + "-" + dates[i][6:8]
sql_data.append((save_date, str(y_pred[i])))
saveData.saveMultipleData(symbol, "SGDRegression", sql_data)
# Predict the next day
today = datetime.strptime(dates[len(dates) - 1], '%Y%m%d')
next_day = today + timedelta(days=7 -
today.weekday() if today.weekday() > 3 else 1)
next_day = next_day.strftime('%Y-%m-%d')
next_price = str(reg.predict([features[len(features) - 1]])[0])
saveData.saveMultipleData(symbol, "SGDRegression",
[tuple((next_day, next_price))])
print(next_day + ": " + next_price)
y_train = result[low + 1:mid + 1]
X_test = features[mid + 1:high - 1]
y_test = result[mid + 2:high]
dates = dates[mid + 2:high]
reg.fit(X_train, y_train)
# predict data #
y_pred = reg.predict(X_test)
# print the result
print("[INFO] %s: %3.2f%%" %
(symbol, round(reg.score(X_test, y_test) * 100, 2)),
file=sys.stderr)
# save last 100 days' prediction data
sql_data = []
for i in range(0, len(y_pred)):
save_date = dates[i][0:4] + "-" + dates[i][4:6] + "-" + dates[i][6:8]
sql_data.append((save_date, str(y_pred[i])))
# Predict the next day
today = datetime.strptime(dates[len(dates) - 1], '%Y%m%d')
next_day = today + timedelta(days=7 -
today.weekday() if today.weekday() > 3 else 1)
next_day = next_day.strftime('%Y-%m-%d')
next_price = str(reg.predict([features[len(features) - 1]])[0])
sql_data.append((next_day, next_price))
saveData.saveMultipleData(symbol, "LASSORegression", sql_data)
print(next_day + ": " + next_price)
# create classifier
my_classifier = SGDClassifier(loss="log", penalty="elasticnet")
# train the classifier
my_classifier.fit(X_train, y_train)
# do prediction
predictions = my_classifier.predict(X_test)
# print the result
print("[INFO] %s: %3.2f%%" % (symbol, accuracy_score(y_test, predictions)*100), file=sys.stderr)
# save last 100 days' prediction data
sql_data = []
for i in range(0, len(predictions)):
save_date = dates[i][0:4] + "-" + dates[i][4:6] + "-" + dates[i][6:8]
sql_data.append((save_date, str(predictions[i])))
saveData.saveMultipleData(symbol, "SGDLinear", sql_data)
# Predict the next day
today = datetime.strptime(dates[len(dates)-1], '%Y%m%d')
next_day = today + timedelta(days= 7-today.weekday() if today.weekday()>3 else 1)
next_day = next_day.strftime('%Y-%m-%d')
next_price = str(my_classifier.predict([features[len(features)-1]])[0])
saveData.saveMultipleData(symbol, "SGDLinear", [tuple((next_day, next_price))])
print(next_day + ": " + next_price)
y_train = result[1:901]
X_test = features[901:998]
y_test = result[902:999]
reg = SGDRegressor(max_iter=100000, loss='squared_loss', penalty='l2', shuffle=False, tol=1e-3, eta0=0.0001).fit(X_train, y_train)
# predict data #
y_pred = reg.predict(X_test)
# accuracy score: returns the coefficient of determination R^2 of the prediction
# The best possible score is 1.0 and it can be negative (because the model can be arbitrarily worse)
accuracy[symbol].append(str(round(reg.score(X_test, y_test)*100, 2))+'%')
# The square of the difference between the original values and the predicted values
# It gives us the measure of how far the predictions were from the actual output
meanSquaredError[symbol].append(str(round(mean_absolute_error(y_test, y_pred)))+'%')
print("[INFO] %s: %3.2f%%" %
(symbol, round(reg.score(X_test, y_test)*100, 2)), file=sys.stderr)
print(symbol + ', ' + '(score accuracy)' + ', '.join(accuracy[symbol]), file=results)
print(symbol + ', ' + '(mean squared error)' + ', '.join(meanSquaredError[symbol]), file=results)
# save last 100 days' prediction data, date save as the date of 'yesterday'
for i in range(1000, 900, -1):
res = reg.predict([features[i]])
save_date = dates[i][0:4] + "-" + dates[i][4:6] + "-" + dates[i][6:8]
print(save_date)
print(res[0])
saveData.saveMultipleData(symbol, "SGDRegression", [tuple((save_date, str(res[0])))])
y_test = result[mid+1:high]
dates = dates[mid+2:high]
# create classifier
my_classifier = tree.DecisionTreeClassifier()
# train the classifier
my_classifier.fit(X_train, y_train)
# do prediction
predictions = my_classifier.predict(X_test)
# print the result
print("[INFO] %s: %3.2f%%" %(symbol, accuracy_score(y_test, predictions)*100), file=sys.stderr)
# save last 100 days' prediction data
sql_data = []
for i in range(0, len(predictions)):
save_date = dates[i][0:4] + "-" + dates[i][4:6] + "-" + dates[i][6:8]
sql_data.append((save_date, str(predictions[i])))
saveData.saveMultipleData(symbol, "DTree", sql_data)
# Predict the next day
today = datetime.strptime(dates[len(dates)-1], '%Y%m%d')
next_day = today + timedelta(days= 7-today.weekday() if today.weekday()>3 else 1)
next_day = next_day.strftime('%Y-%m-%d')
next_price = str(my_classifier.predict([features[len(features)-1]])[0])
saveData.saveMultipleData(symbol, "DTree", [tuple((next_day, next_price))])
print(next_day + ": " + next_price)
# create train and test data set #
X_train = features[0:900]
y_train = result[1:901]
X_test = features[901:998]
y_test = result[902:999]
# create classifier
my_classifier = SGDClassifier(loss="log", penalty="elasticnet")
# train the classifier
my_classifier.fit(X_train, y_train)
# do prediction
predictions = my_classifier.predict(X_test)
accuracy[symbol].append(str(round(accuracy_score(y_test, predictions)*100, 2))+'%')
# print the result
print("[INFO] %s: %3.2f%%" %
(symbol, accuracy_score(y_test, predictions)*100), file=sys.stderr)
# save the results to db
for i in range(1000, 900, -1):
res = my_classifier.predict([features[i]])
save_date = dates[i][0:4] + "-" + dates[i][4:6] + "-" + dates[i][6:8]
saveData.saveMultipleData(symbol, "SGDLinear", [tuple((save_date, str(res[0])))])
