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

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

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

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

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

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

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

#Subset the data into salary categories
df_less_than_50k = df[df['salary'] == ' <=50K']
df_greater_than_50k = df[df['salary'] == ' >50K']
#Plot the histogram for the distribution for data <=$50K
generate_distribution_histogram(df_less_than_50k, 'age',
                                title = 'Age Distribution: US Population',
                                x_axis_label = 'Age (years)',
                                y_axis_label = 'Frequency',
                                label_name = '<=$50K')
#Plot the histogram for the distribution for data >$50K

kperry2215

def mann_whitney_u_test(distribution_1, distribution_2):
    """
    Perform the Mann-Whitney U Test, comparing two different distributions.
    Args:
       distribution_1: List. 
       distribution_2: List.
    Outputs:
        u_statistic: Float. U statisitic for the test.
        p_value: Float.
    """

kperry2215

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

def retrieve_time_series(api, series_ID):
    """
    Return the time series dataframe, based on API and unique Series ID
    """
    #Retrieve Data By Series ID 
    series_search = api.data_by_series(series=series_ID)