generate_anomalies.py

#Add in a couple anomalous data points for detection by the algorithm
anomaly_dictionary={80: 3.1, 
                    200: 3,
                    333: 1,
                    600: 2.6,
                    710: 2.1,
                    890: 2.3,
                    1100: 1,
                    1211: 2.6,
                    1309: 2.3}
#Set default for Artificially_Generated_Anomaly column to 0
gasoline_price_df.loc[:,'Artificially_Generated_Anomaly']=0

#Create fake anomaly values based on anomaly_dictionary
for index, anomaly_value in anomaly_dictionary.items():
    gasoline_price_df.loc[index,'Gasoline_Price']=anomaly_value
    #Create a column to indicate Anomalies
    gasoline_price_df.loc[index,'Artificially_Generated_Anomaly']=1
    
#Re-visualize data with artificially generated anomalies
scatterplot_with_color_coding(gasoline_price_df['Date'],
                     gasoline_price_df['Gasoline_Price'], 
                     gasoline_price_df['Artificially_Generated_Anomaly'],
                     'Date', 
                     'Gasoline Price (Dollars Per Gallon)', 
                     'Gasoline Prices, Color-Coded on Real/Artificially Generated Data Points')