kperry2215

def calculate_model_accuracy_metrics(actual, predicted):
    """
    Output model accuracy metrics, comparing predicted values
    to actual values.
    Arguments:
        actual: list. Time series of actual values.
        predicted: list. Time series of predicted values
    Outputs:
        Forecast bias metrics, mean absolute error, mean squared error,
        and root mean squared error in the console

kperry2215

def calculate_model_accuracy_metrics(actual, predicted):
    """
    Output model accuracy metrics, comparing predicted values
    to actual values.
    Arguments:
        actual: list. Time series of actual values.
        predicted: list. Time series of predicted values
    Outputs:
        Forecast bias metrics, mean absolute error, mean squared error,
        and root mean squared error in the console

kperry2215

#Convert the dataframe to a numpy array
master_array=np.array(master_df[['Electricity_Price_Transformed_Differenced', 
                                     'Nat_Gas_Price_MCF_Transformed_Differenced']].dropna())
    
#Generate a training and test set for building the model: 95/5 split
training_set = master_array[:int(0.95*(len(master_array)))]
test_set = master_array[int(0.95*(len(master_array))):]
    
#Fit to a VAR model
model = VAR(endog=training_set)

kperry2215

def augmented_dickey_fuller_statistics(time_series):
    """
    Run the augmented Dickey-Fuller test on a time series
    to determine if it's stationary.
    Arguments: 
        time_series: series. Time series that we want to test 
    Outputs: 
        Test statistics for the Augmented Dickey Fuller test in 
        the console 
    """

kperry2215

#Transform the columns using natural log
master_df['Electricity_Price_Transformed']=np.log(master_df['Electricity_Price'])
master_df['Nat_Gas_Price_MCF_Transformed']=np.log(master_df['Nat_Gas_Price_MCF'])
    
#Difference the data by 1 month
n=1
master_df['Electricity_Price_Transformed_Differenced'] = master_df['Electricity_Price_Transformed'] - master_df['Electricity_Price_Transformed'].shift(n)
master_df['Nat_Gas_Price_MCF_Transformed_Differenced'] = master_df['Nat_Gas_Price_MCF_Transformed'] - master_df['Nat_Gas_Price_MCF_Transformed'].shift(n)

kperry2215

#Pull in natural gas time series data
series_ID='NG.N3035TX3.M'
nat_gas_df=retrieve_time_series(api, series_ID)
nat_gas_df.reset_index(level=0, inplace=True)
#Rename the columns
nat_gas_df.rename(columns={'index':'Date',
            nat_gas_df.columns[1]:'Nat_Gas_Price_MCF'}, 
            inplace=True)
#Convert the Date column into a date object
nat_gas_df['Date']=pd.to_datetime(nat_gas_df['Date'])

kperry2215

#Pull in natural gas time series data
series_ID='NG.N3035TX3.M'
nat_gas_df=retrieve_time_series(api, series_ID)
nat_gas_df.reset_index(level=0, inplace=True)
#Rename the columns
nat_gas_df.rename(columns={'index':'Date',
            nat_gas_df.columns[1]:'Nat_Gas_Price_MCF'}, 
            inplace=True)
#Convert the Date column into a date object
nat_gas_df['Date']=pd.to_datetime(nat_gas_df['Date'])

kperry2215

def retrieve_time_series(api, series_ID):
    """
    Return the time series dataframe, based on API and unique Series ID
    api: API that we're connected to
    series_ID: string. Name of the series that we want to pull from the EIA API
    """
    #Retrieve Data By Series ID 
    series_search = api.data_by_series(series=series_ID)
    ##Create a pandas dataframe from the retrieved time series
    df = pd.DataFrame(series_search)

kperry2215

def decompose_time_series(series):
    """
    Decompose a time series and plot it in the console
    Arguments: 
        series: series. Time series that we want to decompose
    Outputs: 
        Decomposition plot in the console
    """
    result = seasonal_decompose(series, model='additive')
    result.plot()

kperry2215

def retrieve_time_series(api, series_ID):
    """
    Return the time series dataframe, based on API and unique Series ID
    api: API that we're connected to
    series_ID: string. Name of the series that we want to pull from the EIA API
    """
    #Retrieve Data By Series ID 
    series_search = api.data_by_series(series=series_ID)
    ##Create a pandas dataframe from the retrieved time series
    df = pd.DataFrame(series_search)