from sklearn import svm, datasets
from sigopt_sklearn.search import SigOptSearchCV

# find your SigOpt client token here : https://sigopt.com/tokens
client_token = '<YOUR_SIGOPT_CLIENT_TOKEN>'

iris = datasets.load_iris()

# define parameter domains
svc_parameters  = {'kernel': ['linear', 'rbf'], 'C': (0.5, 100)}

# define sklearn estimator
svr = svm.SVC()

# define SigOptCV search strategy
clf = SigOptSearchCV(svr, svc_parameters, cv=5,
    client_token=client_token, n_jobs=5, n_iter=20)

# perform CV search for best parameters and fits estimator
# on all data using best found configuration
clf.fit(iris.data, iris.target)

# clf.predict() now uses best found estimator
# clf.best_score_ contains CV score for best found estimator
# clf.best_params_ contains best found param configuration

from sklearn.metrics import f1_score, make_scorer
f1_scorer = make_scorer(f1_score)

# define SigOptCV search strategy
clf = SigOptSearchCV(svr, svc_parameters, cv=5, scoring=f1_scorer,
    client_token=client_token, n_jobs=5, n_iter=50)

# perform CV search for best parameters
clf.fit(X, y)

import xgboost as xgb
from xgboost.sklearn import XGBClassifier
from sklearn import datasets
from sigopt_sklearn.search import SigOptSearchCV

# find your SigOpt client token here : https://sigopt.com/tokens
client_token = '<YOUR_SIGOPT_CLIENT_TOKEN>'
iris = datasets.load_iris()

xgb_params = {
  'learning_rate': (0.01, 0.5),
  'n_estimators': (10, 50),
  'max_depth': (3, 10),
  'min_child_weight': (6, 12),
  'gamma': (0, 0.5),
  'subsample': (0.6, 1.0),
  'colsample_bytree': (0.6, 1.)
}

xgbc = XGBClassifier()

clf = SigOptSearchCV(xgbc, xgb_params, cv=5,
    client_token=client_token, n_jobs=5, n_iter=70, verbose=1)

clf.fit(iris.data, iris.target)

pip install sigopt_sklearn[ensemble]

# Human Activity Recognition Using Smartphone
# https://archive.ics.uci.edu/ml/datasets/Human+Activity+Recognition+Using+Smartphones
wget https://archive.ics.uci.edu/ml/machine-learning-databases/00240/UCI%20HAR%20Dataset.zip
unzip UCI\ HAR\ Dataset.zip
cd UCI\ HAR\ Dataset

import numpy as np
import pandas as pd
from sigopt_sklearn.ensemble import SigOptEnsembleClassifier

def load_datafile(filename):
  X = []
  with open(filename, 'r') as f:
    for l in f:
      X.append(np.array([float(v) for v in l.split()]))
  X = np.vstack(X)
  return X

X_train = load_datafile('train/X_train.txt')
y_train = load_datafile('train/y_train.txt').ravel()
X_test = load_datafile('test/X_test.txt')
y_test = load_datafile('test/y_test.txt').ravel()

# fit and tune several classification models concurrently
# find your SigOpt client token here : https://sigopt.com/tokens
sigopt_clf = SigOptEnsembleClassifier()
sigopt_clf.parallel_fit(X_train, y_train, est_timeout=(40 * 60),
    client_token='<YOUR_CLIENT_TOKEN>')

# compare model performance on hold out set
ensemble_train_scores = [est.score(X_train,y_train) for est in sigopt_clf.estimator_ensemble]
ensemble_test_scores = [est.score(X_test,y_test) for est in sigopt_clf.estimator_ensemble]
data = sorted(zip([est.__class__.__name__
                        for est in sigopt_clf.estimator_ensemble], ensemble_train_scores, ensemble_test_scores),
                        reverse=True, key=lambda x: (x[2], x[1]))
pd.DataFrame(data, columns=['Classifier ALGO.', 'Train ACC.', 'Test ACC.'])

from sklearn import svm, datasets
from sigopt_sklearn.search import SigOptSearchCV

# find your SigOpt client token here : https://sigopt.com/tokens
client_token = '<YOUR_SIGOPT_CLIENT_TOKEN>'
dataset = datasets.fetch_20newsgroups_vectorized()
X = dataset.data
y = dataset.target

# define parameter domains
svc_parameters  = {
  'kernel': ['linear', 'rbf'],
  'C': (0.5, 100),
  'max_iter': (10, 200),
  'tol': (1e-2, 1e-6)
}
svr = svm.SVC()

# SVM fitting can be quite slow, so we set timeout = 180 seconds
# for each fit.  SigOpt will then avoid configurations that are too slow
clf = SigOptSearchCV(svr, svc_parameters, cv=5, opt_timeout=180,
    client_token=client_token, n_jobs=5, n_iter=40)

clf.fit(X, y)

svc_parameters  = {'kernel': ['linear', 'rbf'], 'C': (0.5, 100)}

parameters = {
  'activation': ['relu', 'tanh', 'logistic'],
  'solver': ['lbfgs', 'adam'],
  'alpha': (0.0001, 0.01),
  'learning_rate_init': (0.001, 0.1),
  'power_t': (0.001, 1.0),
  'beta_1': (0.8, 0.999),
  'momentum': (0.001, 1.0),
  'beta_2': (0.8, 0.999),
  'epsilon': (0.00000001, 0.0001),
  'hidden_layer_sizes': {
    'shallow': (100,),
    'medium': (10, 10),
    'deep': (10, 10, 10, 10)
  }
}
nn = MLPRegressor()
clf = SigOptSearchCV(nn, parameters, cv=5, cv_timeout=240,
    client_token=client_token, n_jobs=5, n_iter=40)

clf.fit(X, y)