scaler = MinMaxScaler(feature_range=(0, 1))
data = db_functions.getDb()
add_datepart(data, 'Date')
data.drop('Elapsed', axis=1, inplace=True)
train = data[:987]
valid = data[987:]
x_train = train.drop('Close', axis=1)
y_train = train['Close']
x_valid = valid.drop('Close', axis=1)
y_valid = valid['Close']
x_train_scaled = scaler.fit_transform(x_train)
x_train = pd.DataFrame(x_train_scaled)
x_valid_scaled = scaler.fit_transform(x_valid)
x_valid = pd.DataFrame(x_valid_scaled)
params = {'n_neighbors': [2, 3, 4, 5, 6, 7, 8, 9]}
knn = neighbors.KNeighborsRegressor()
model = GridSearchCV(knn, params, cv=5)
model.fit(x_train, y_train)
prediction = model.predict(x_valid)
print(db_functions.getRMSE(valid, prediction))
db_functions.plot(train, valid, prediction)
from fbprophet import Prophet
import db_functions
data = db_functions.getDb()
data.rename(columns={'Close': 'y', 'Date': 'ds'}, inplace=True)
train = data[:987]
valid = data[987:]
model = Prophet()
model.fit(train)
close_prices = model.make_future_dataframe(periods=len(valid))
forecast = model.predict(close_prices)
forecast_valid = forecast['yhat'][987:]
valid.rename(columns={'y': 'Close'}, inplace=True)
train.rename(columns={'y': 'Close'}, inplace=True)
print(db_functions.getRMSE(valid, forecast_valid))
db_functions.plot(train, valid, forecast_valid)
import db_functions
data = db_functions.getDb()
train = data[:987]
test = data[987:]
predictions = []
for i in range(0, len(test)):
a = train['Close'][len(train) - len(test) + i:].sum() + sum(predictions)
b = a / len(test)
predictions.append(b)
db_functions.plot(train, test, predictions)
print db_functions.getRMSE(test, predictions)