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

#Create EIA API using your specific API key
api_key = 'YOUR API KEY HERE'
api = eia.API(api_key)
    
#Pull the oil WTI price data
series_ID='PET.RWTC.D'
#Retrieve Data By Series ID 
series_search = api.data_by_series(series=series_ID)
##Create a pandas dataframe from the retrieved time series
price_df = pd.DataFrame(series_search)

kperry2215

import pandas as pd
import matplotlib.pyplot as plt
import eia

def retrieve_time_series(api, series_ID):
    """
    Return the time series dataframe, based on API and unique Series ID
    Arguments:
        api: API that we're connected to
        series_ID: string. Name of the series that we want to pull from the EIA API

kperry2215

#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}

kperry2215

def low_pass_filter_anomaly_detection(df, 
                                      column_name, 
                                      number_of_stdevs_away_from_mean):
    """
    Implement a low-pass filter to detect anomalies in a time series, and save the filter outputs 
    (True/False) to a new column in the dataframe.
    Arguments:
        df: Pandas dataframe
        column_name: string. Name of the column that we want to detect anomalies in
        number_of_stdevs_away_from_mean: float. Number of standard deviations away from

kperry2215

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:

kperry2215

def decompose_time_series(series, desired_frequency):
    """
    Perform STL decomposition on the time series.
    Arguments:
        series: Pandas series. Time series sequence that we wish to decompose.
        desired_frequency: Integer. Time frequency of the series. If we want to detect 
        a yearly trend, we'd set the value equal to 365.
    Outputs:
        Plot of time series STL decomposition.
    """

kperry2215

def sesd_anomaly_detection(dataframe, 
                           column_name, 
                           desired_frequency, 
                           max_anomalies,
                           alpha_level):
    """
    In this definition, time series anomalies are detected using the S-ESD algorithm.
    Arguments:
        dataframe: Pandas dataframe
        column_name: string. Name of the column that we want to detect anomalies in

kperry2215

def one_class_SVM_anomaly_detection(dataframe, columns_to_filter_by, outliers_fraction):
    """
    In this definition, time series anomalies are detected
    using a One Class SVM algorithm.
    Arguments:
        df: Pandas dataframe
        columns_to_filter_by: string, or list of strings. Name of the column(s) that 
        we want to use in the One Class SVM to detect time series anomalies
        outliers_fraction: float. Percentage of outliers allowed in the sequence.
    Outputs:

kperry2215

#Read in the cancer data set
df = pd.read_csv('https://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer/breast-cancer.data', header=None)
#Declare the column names of the cancer data set
df.columns=["Class", "Age", "Menopause",
            "Tumor_Size", "Inv_Nodes", 
            "Node_Caps", "Deg_Malig",
            "Breast", "Breast_quad",
            "Irradiat"]
#Convert all of the categorical features variables to numeric (use LabelEncoder)
d = defaultdict(LabelEncoder)