def predict_apple():
csv = 'assets/Apple.csv'
global model, graph, last, df
model, graph = init('apple_model')
df = pd.read_csv(csv)
df = df.set_index('Date')
df = df.iloc[:, 10:11].values
df = np.array(df)
df = scaler.fit_transform(df)
last = length(csv)
x = [df[last - 60:last, 0]]
x = np.array(x)
x = x.reshape(1, x.shape[1], 1)
pred = model.predict(x)
K.clear_session()
prediction = scaler.inverse_transform(pred)
return prediction[0]
csv = '../assets/Apple.csv'
scaler = MinMaxScaler(feature_range=(0, 1))
df = pd.read_csv(csv, header=0)
df = df.set_index('Date')
df = df[::-1]
df = df.iloc[:, 10:11].values
print(df[0:5])
data = scaler.fit_transform(df)
X = []
y = []
for i in range(60, length(csv)):
X.append(data[i - 60:i, 0])
y.append(data[i, 0])
X = np.array(X)
y = np.array(y)
X = X.reshape(X.shape[0], X.shape[1], 1)
model = Sequential()
model.add(LSTM(64, input_shape=(X.shape[1], 1), return_sequences=True))
model.add(Dropout(.1))
model.add(LSTM(64, return_sequences=True))
model.add(Dropout(.1))
model.add(LSTM(64))