stock price prediction.py

def prepare_data(df,forecast_col,forecast_out,test_size):
    label = df[forecast_col].shift(-forecast_out) #creating new column called label with the last 5 rows are nan
    X = np.array(df[[forecast_col]]) #creating the feature array
    X = preprocessing.scale(X) #processing the feature array
    X_lately = X[-forecast_out:] #creating the column i want to use later in the predicting method
    X = X[:-forecast_out] # X that will contain the training and testing
    label.dropna(inplace=True) #dropping na values
    y = np.array(label)  # assigning Y
    X_train, X_test, Y_train, Y_test = train_test_split(X, y, test_size=test_size, random_state=0) #cross validation

    response = [X_train,X_test , Y_train, Y_test , X_lately]
    return response