sean-mcclure

function survival_probability(options) {
    var group_size = 1;
    if(options.hasOwnProperty("custom_beta")) {
        var betas = [options.custom_beta]
    } else {
        var betas = [100, 50, 25];
    }
    x_values = [-1, -0.75, -0.5, -0.25, 0, 0.25, 0.5, 0.75, 1];
    plot_data = [];
    betas.forEach(function(beta) {

sean-mcclure

# Training the AutoML algorithm
pipeline_optimizer.fit(X_train, y_train)

sean-mcclure

# Loading a dataset for training
data = datasets.load_breast_cancer()

# Splitting our data into train and test sets
X_train, X_test, y_train, y_test = train_test_split(data["data"], 
                                                    data["target"], 
                                                    test_size=0.2, 
                                                    stratify=data["target"])

sean-mcclure

# Initializing our TPOT pipeline optimizer
pipeline_optimizer = TPOTClassifier(generations=5, verbosity=2, config_dict="TPOT light")

sean-mcclure

# Importing necessary tools and libraries
import tpot
from tpot import TPOTClassifier
import pandas as pd
from sklearn import datasets
from sklearn.model_selection import train_test_split

sean-mcclure

classifier_config_dict = {

    # Classifiers
    'sklearn.naive_bayes.GaussianNB': {
    },

    'sklearn.naive_bayes.BernoulliNB': {
        'alpha': [1e-3, 1e-2, 1e-1, 1., 10., 100.],
        'fit_prior': [True, False]
    },

sean-mcclure

Configuration Name,Description,Operators
Default TPOT,"TPOT will search over a broad range of preprocessors, feature constructors, feature selectors, models, and parameters to find a series of operators that minimize the error of the model predictions. Some of these operators are complex and may take a long time to run, especially on larger datasets.

Note: This is the default configuration for TPOT. To use this configuration, use the default value (None) for the config_dict parameter.","Classification

Regression"
TPOT light,"TPOT will search over a restricted range of preprocessors, feature constructors, feature selectors, models, and parameters to find a series of operators that minimize the error of the model predictions. Only simpler and fast-running operators will be used in these pipelines, so TPOT light is useful for finding quick and simple pipelines for a classification or regression problem.

This configuration works for both the TPOTClassifier and TPOTRegressor.","Classification

sean-mcclure

Configuration Name,Description,Operators
Default TPOT,"TPOT will search over a broad range of preprocessors, feature constructors, feature selectors, models, and parameters to find a series of operators that minimize the error of the model predictions. Some of these operators are complex and may take a long time to run, especially on larger datasets."
"Note: This is the default configuration for TPOT. To use this configuration, use the default value (None) for the config_dict parameter.",Classification
Regression
TPOT light,"TPOT will search over a restricted range of preprocessors, feature constructors, feature selectors, models, and parameters to find a series of operators that minimize the error of the model predictions. Only simpler and fast-running operators will be used in these pipelines, so TPOT light is useful for finding quick and simple pipelines for a classification or regression problem."
This configuration works for both the TPOTClassifier and TPOTRegressor.,Classification
Regression
TPOT MDR,"T

sean-mcclure

# Loading our model
model = h2o.load_model(model_path)

sean-mcclure

# Saving our model
model_path = h2o.save_model(model=best_model,   
                            path="/tmp/leader_model", 
                            force=True)