kperry2215

import matplotlib.pyplot as plt

def generate_distribution_histogram(dataframe, 
                                    column_name, 
                                    title, x_axis_label, y_axis_label,
                                    label_name,
                                    number_bins = 15):
    """
    This function generates a histogram.
    Args:

kperry2215

df = pd.read_csv('https://archive.ics.uci.edu/ml/machine-learning-databases/adult/adult.data', header = None)
#Declare the column names of the data set
df.columns = ['age', 'workclass', 'fnlwgt', 'education', 'education-num',
              'marital-status', 'occupation', 'relationship',
              'race', 'sex', 'capital-gain', 'capital-loss', 'hours-per-week',
              'native-country', 'salary']

kperry2215

results_rounded = np.round(results)
confusion_matrix(testing_target, results_rounded)

kperry2215

import numpy as np
import pandas as pd
from sklearn.ensemble import ExtraTreesClassifier
from sklearn.model_selection import train_test_split
from sklearn.naive_bayes import BernoulliNB
from sklearn.pipeline import make_pipeline, make_union
from sklearn.preprocessing import RobustScaler
from tpot.builtins import StackingEstimator

# NOTE: Make sure that the class is labeled 'target' in the data file

kperry2215

def run_tpot_automl(dataframe, 
                    variable_to_predict, 
                    number_generations,
                    file_to_export_pipeline_to = 'tpot_classifier_pipeline.py'):
    """
    This function runs a TPOT classifier on the dataset, after splitting into
    a training and test set, and then oversampling the training set.
    Args:
        dataframe: pandas dataframe. Master dataframe containing the feature and target
        data

kperry2215

performance = aml.leader.model_performance(test)
print(performance)

kperry2215

def run_h2o_automl(dataframe, variable_to_predict,
                   max_number_models):
    """
    This function initiates an h2o cluster, converts
    the dataframe to an h2o dataframe, and then runs
    the autoML function to generate a list of optimal 
    predictor models. The best models are displayed via a 
    scoreboard.
    Arguments:
        dataframe: Pandas dataframe. 

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)    

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

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