isolation_forest.py

def isolation_forest_anomaly_detection(df, 
                                       column_name, 
                                       outliers_fraction):
    """
    In this definition, time series anomalies are detected using an Isolation Forest algorithm.
    Arguments:
        df: Pandas dataframe
        column_name: string. Name of the column that we want to detect anomalies in
        outliers_fraction: float. Percentage of outliers allowed in the sequence.
    Outputs:
        df: Pandas dataframe with column for detected Isolation Forest anomalies (True/False)
    """
    #Scale the column that we want to flag for anomalies
    min_max_scaler = preprocessing.StandardScaler()
    np_scaled = min_max_scaler.fit_transform(df[[column_name]])
    scaled_time_series = pd.DataFrame(np_scaled)
    # train isolation forest 
    model =  IsolationForest(contamination = outliers_fraction, behaviour='new')
    model.fit(scaled_time_series)
    #Generate column for Isolation Forest-detected anomalies
    isolation_forest_anomaly_column = column_name+'_Isolation_Forest_Anomaly'
    df[isolation_forest_anomaly_column] = model.predict(scaled_time_series)
    df[isolation_forest_anomaly_column] = df[isolation_forest_anomaly_column].map( {1: False, -1: True} )
    return df

##EXECUTE IN MAIN BLOCK

#APPLY ISOLATION FOREST TO DETECT ANOMALIES
gasoline_price_df=isolation_forest_anomaly_detection(df=gasoline_price_df, 
                                                         column_name='Gasoline_Price', 
                                                         outliers_fraction=.04)
#Re-plot time series with color coding for anomaly column
scatterplot_with_color_coding(gasoline_price_df['Date'],
                                  gasoline_price_df['Gasoline_Price'], 
                                  gasoline_price_df['Gasoline_Price_Isolation_Forest_Anomaly'],
                                  'Date', 
                                  'Gasoline Price (Dollars Per Gallon)', 
                                  'Gasoline Prices, Color-Coded on Isolation Forest Anomalies')