3catz

D = reconstruct(s, dim = 22 * 2 + 5, tau = 1)
Xs = []
Ys = [] 
for choice in np.repeat("random",3):
  X = D[:,:22 * 2] ; Y = D[:,-5:]

  if choice == 'random':
    import random
    y = []
    for i in range(len(Y)):

3catz

3catz

from catboost import Pool, cv, CatBoostClassifier
from bayes_opt import BayesianOptimization
from sklearn.model_selection import * 
from sklearn.metrics import *


def CB_opt(n_estimators, depth, learning_rate, max_bin,
             subsample, num_leaves, l2_leaf_reg, model_size_reg): 
  scores = []
  skf = StratifiedKFold(n_splits = 5, shuffle = True, random_state = 1944)

3catz

n_trials = 10000
n_candidates = 100
max_burn = int(0.66 * n_candidates) 
for T in range(1, max_burn, 5):
  global_maxes = [] 
  diff_from_max = [] 
  time_taken = []
  final_choices = [] 
  for i in range(n_trials):
    

3catz

exper = setup(
    data = bike_yes,
    categorical_features = ["Seasons", "Holiday"],
    silent = True,
    ordinal_features = {"Hour": sorted_hours},
    ignore_features = ["Functioning Day","Date"],
    target = 'Rented Bike Count',
    use_gpu = True,
    data_split_shuffle = False,
    fold_strategy = "timeseries",

3catz

acts = ["jogging","standing","downstairs","upstairs","walkfast","walkmod","walkslow","lying","sitting"]
def create_windows(subjects): 
  length = 100
  stride = 50
  sample = 10
  framelist = []
  targetlist = [] 
  global acts
  for act in acts:
    for f in glob.glob(subjects + act):

3catz

from sklearn.metrics import *
mcc = make_scorer(matthews_corrcoef)
estimator = LogisticRegression(solver = "liblinear", C = 6, tol = 1, fit_intercept = True)

from sklearn.model_selection import *
report = pd.DataFrame()
nofeats = [] 
chosen_feats = [] 
cvscore = [] 
rkf = RepeatedStratifiedKFold(n_repeats = 2, n_splits = 10)

3catz

from pycaret.datasets import get_data
from pycaret.classification import *
report["Scores"] = np.round(report["Scores"], 3)
report.sort_values(by = "Scores", ascending = False, inplace = True)
#report.index
ga_feats = report.iloc[0]["Chosen Feats"]
ename = setup(data = D[used_feats], target = "DEATH_EVENT", 
              test_data = None,
              fold_strategy = "stratifiedkfold",
              fold_shuffle = True, 

3catz

from sklearn.feature_selection import *
feat_list = [] 
all_scores = [] 
for i in range(10):
  np.random.seed(i)
  sfm = SelectFromModel(estimator = clf, threshold=None, prefit=False, 
                       norm_order=1, max_features = 12)
  sfm.fit(D[allfeats], y)
  modfeats = sfm.get_support()
  

3catz

scores = [] 
for i in range(len(report)):
  
  myfeats = report.iloc[i,1] ; print(myfeats)
  X = D[myfeats] ; y = y
  clf = LogisticRegression(solver = "liblinear", C = 6, tol = 1)
  #clf = RandomForestClassifier()
  rskf = RepeatedStratifiedKFold(n_splits = 10, n_repeats = 100)
  score = np.mean(cross_val_score(clf, X, y, cv = rskf, scoring = "roc_auc"))
  scores.append(score)