In [24]:
import pandas as pd
from glob import glob
from tqdm import tqdm_notebook
from sklearn.cross_validation import train_test_split
from sklearn.metrics import accuracy_score
from evoml.subspacing import FeatureStackerFECV

In [25]:
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier, GradientBoostingClassifier

def check_for_benchmarks(X_train, X_test, y_train, y_test, n_estimators):
    
    # The exploration of the dataset by benchmark algorithms
    clf = DecisionTreeClassifier(random_state=34092)
    clf.fit(X_train, y_train)
    pred_DTC = clf.predict(X_test)
    a = clf.score(X_test, y_test)
#     print('Base DecisionTreeClassifier accuracy: {}'.format(clf.score(X_test, y_test)))

    clf = RandomForestClassifier(random_state=34092, n_estimators=n_estimators)
    clf.fit(X_train, y_train)
    pred_RFC = clf.predict(X_test)
    b = clf.score(X_test, y_test)
#     print('Base RandomForestClassifier accuracy: {}'.format(clf.score(X_test, y_test)))

    clf = GradientBoostingClassifier(random_state=34092, n_estimators=n_estimators)
    clf.fit(X_train, y_train)
    pred_GBC = clf.predict(X_test)
    c = clf.score(X_test, y_test)
#     print('Base GradientBoostingClassifier accuracy: {}'.format(clf.score(X_test, y_test)))

#     print('')
    return a,b,c

In [28]:
evoml_params={
    'name': 'Experiment',
    'n_estimators': 10,
    'cv': 5,
    'n_population': 30,
    'ngen' : 5
}

In [33]:
logdump = []

for i,dataset in tqdm_notebook(enumerate(glob('C:/Users/harshnisar/Programming/data/*'))):
    if i<5: #Max number of datasets you want to do
        continue
        
    input_data = pd.read_csv(dataset, compression='gzip', sep='\t')
    X, y = input_data.iloc[:,:-1], input_data.iloc[:,-1] 
    
    
    for seed in tqdm_notebook(range(0,5)): #How many per dataset?
        X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=seed, stratify=y)
        dt_score, rf_score, gb_score = check_for_benchmarks(X_train, X_test, y_train, y_test, n_estimators=10)
        
        clf_dt = DecisionTreeClassifier(max_depth=None, random_state=34092)
        
        clf = FeatureStackerFECV(base_estimator=clf_dt, model_type = 'classification',
                                 N_individual=evoml_params['n_estimators'],
                                 ngen=evoml_params['ngen'], verbose_flag = False, N_population=evoml_params['n_population'],
                                 maxOrMin = 1,
                                 featMax = None, featMin=1, folds_CV=evoml_params['cv'])
        
        clf.fit(X_train, y_train)
        pred = clf.predict(X_test)
        final_test_score = accuracy_score(pred,y_test)

        
        final_train_fitness = clf.hof[0].fitness
        
        
        log ={
            'dataset': dataset,
            'seed': seed,
            'final_train_fitness': final_train_fitness,
            'final_test_score': final_test_score,
            'RF_holdout': rf_score,
            'DT_holdout': dt_score,
            'GB_holdout': gb_score,
            'nrows': X.shape[0],
            'ncols': X.shape[1]
        }
        
        logdump.append(log)


C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 3 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 3 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 3 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 3 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 2 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 2 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 2 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 2 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 2 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 2 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 2 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 2 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 2 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 2 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 3 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 3 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 3 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 4 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 4 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 4 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 2 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 2 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 2 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 2 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 4 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 4 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 4 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 4 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 2 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 1 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 2 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 2 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 2 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 2 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 2 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 2 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 4 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 4 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 4 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 4 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 4 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 4 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 4 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 4 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 4 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 4 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 4 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 4 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 4 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)
C:\Anaconda3\lib\site-packages\sklearn\cross_validation.py:516: Warning: The least populated class in y has only 4 members, which is too few. The minimum number of labels for any class cannot be less than n_folds=5.
  % (min_labels, self.n_folds)), Warning)

Exception ignored in: <bound method tqdm.__del__ of 29it [00:00, 370.92it/s]>
Traceback (most recent call last):
  File "C:\Anaconda3\lib\site-packages\tqdm\_tqdm.py", line 645, in __del__
    self.close()
  File "C:\Anaconda3\lib\site-packages\tqdm\_tqdm_notebook.py", line 208, in close
    if self.n < self.total:
TypeError: unorderable types: int() < NoneType()
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-33-aa38fc354b43> in <module>()
     21                                  featMax = None, featMin=1, folds_CV=evoml_params['cv'])
     22 
---> 23         clf.fit(X_train, y_train)
     24         pred = clf.predict(X_test)
     25         final_test_score = accuracy_score(pred,y_test)

C:\Users\harshnisar\Programming\bhanu\EvoML\evoml\subspacing\feature_stacker_FECV.py in fit(self, X, y)
    157         toolbox.register("select", tools.selTournament, tournsize=3)
    158 
--> 159         pop = toolbox.population(n=self.N_population)
    160         hof = tools.HallOfFame(1, similar=compare_hof);
    161         stats = tools.Statistics(lambda ind: ind.fitness.values)

C:\Anaconda3\lib\site-packages\deap\tools\init.py in initRepeat(container, func, n)
     21     See the :ref:`list-of-floats` and :ref:`population` tutorials for more examples.
     22     """
---> 23     return container(func() for _ in range(n))
     24 
     25 def initIterate(container, generator):

C:\Anaconda3\lib\site-packages\deap\tools\init.py in <genexpr>(.0)
     21     See the :ref:`list-of-floats` and :ref:`population` tutorials for more examples.
     22     """
---> 23     return container(func() for _ in range(n))
     24 
     25 def initIterate(container, generator):

C:\Anaconda3\lib\site-packages\deap\tools\init.py in initRepeat(container, func, n)
     21     See the :ref:`list-of-floats` and :ref:`population` tutorials for more examples.
     22     """
---> 23     return container(func() for _ in range(n))
     24 
     25 def initIterate(container, generator):

C:\Anaconda3\lib\site-packages\deap\creator.py in initType(self, *args, **kargs)
    148             setattr(self, obj_name, obj())
    149         if base.__init__ is not object.__init__:
--> 150             base.__init__(self, *args, **kargs)
    151 
    152     objtype = type(str(name), (base,), dict_cls)

C:\Anaconda3\lib\site-packages\deap\tools\init.py in <genexpr>(.0)
     21     See the :ref:`list-of-floats` and :ref:`population` tutorials for more examples.
     22     """
---> 23     return container(func() for _ in range(n))
     24 
     25 def initIterate(container, generator):

C:\Users\harshnisar\Programming\bhanu\EvoML\evoml\subspacing\feature_stacker_FECV.py in get_indiv_sample_bag(self, data, output, base_estimator, indiv_replace_flag)
    119             self.featMax = data.shape[1]-1
    120         feat_name = list(data.columns.values)
--> 121         feat_count = (randint(self.featMin,self.featMax))
    122         ind = random.sample(range(0, self.featMax), feat_count)
    123         new_feat = []

C:\Anaconda3\lib\random.py in randint(self, a, b)
    216         """
    217 
--> 218         return self.randrange(a, b+1)
    219 
    220     def _randbelow(self, n, int=int, maxsize=1<<BPF, type=type,

C:\Anaconda3\lib\random.py in randrange(self, start, stop, step, _int)
    194             return istart + self._randbelow(width)
    195         if step == 1:
--> 196             raise ValueError("empty range for randrange() (%d,%d, %d)" % (istart, istop, width))
    197 
    198         # Non-unit step argument supplied.

ValueError: empty range for randrange() (1,1, 0)

In [35]:
logs = pd.DataFrame(logdump)

In [36]:
logs.dataset.unique().shape


Out[36]:
(24,)

In [38]:
logs


Out[38]:
DT_holdout GB_holdout RF_holdout dataset final_test_score final_train_fitness ncols nrows seed
0 0.988335 0.983033 0.980912 C:/Users/harshnisar/Programming/data\allrep.cs... 0.992577 (0.98515773110142324,) 29 3772 0
1 0.976670 0.979852 0.974549 C:/Users/harshnisar/Programming/data\allrep.cs... 0.978791 (0.98267736658972571,) 29 3772 1
2 0.981972 0.972428 0.973489 C:/Users/harshnisar/Programming/data\allrep.cs... 0.983033 (0.98409203614828145,) 29 3772 2
3 0.978791 0.971368 0.972428 C:/Users/harshnisar/Programming/data\allrep.cs... 0.981972 (0.98409884048181928,) 29 3772 3
4 0.986214 0.985154 0.980912 C:/Users/harshnisar/Programming/data\allrep.cs... 0.987275 (0.98515952134318341,) 29 3772 4
5 0.846154 0.692308 0.692308 C:/Users/harshnisar/Programming/data\analcatda... 0.846154 (0.67500000000000004,) 4 50 0
6 0.615385 0.615385 0.692308 C:/Users/harshnisar/Programming/data\analcatda... 0.769231 (0.67500000000000004,) 4 50 1
7 0.307692 0.461538 0.615385 C:/Users/harshnisar/Programming/data\analcatda... 0.461538 (0.74285714285714288,) 4 50 2
8 0.538462 0.615385 0.538462 C:/Users/harshnisar/Programming/data\analcatda... 0.615385 (0.69999999999999996,) 4 50 3
9 0.769231 0.692308 0.615385 C:/Users/harshnisar/Programming/data\analcatda... 0.692308 (0.62976190476190474,) 4 50 4
10 0.809524 0.904762 0.809524 C:/Users/harshnisar/Programming/data\analcatda... 0.761905 (0.85641025641025637,) 3 83 0
11 0.714286 0.666667 0.619048 C:/Users/harshnisar/Programming/data\analcatda... 0.714286 (0.81190476190476191,) 3 83 1
12 0.809524 0.761905 0.857143 C:/Users/harshnisar/Programming/data\analcatda... 0.619048 (0.7404761904761904,) 3 83 2
13 0.666667 0.666667 0.666667 C:/Users/harshnisar/Programming/data\analcatda... 0.666667 (0.80897435897435899,) 3 83 3
14 0.619048 0.619048 0.666667 C:/Users/harshnisar/Programming/data\analcatda... 0.666667 (0.82179487179487187,) 3 83 4
15 0.928910 0.957346 0.957346 C:/Users/harshnisar/Programming/data\analcatda... 0.981043 (0.9841372872241777,) 70 841 0
16 0.952607 0.971564 0.981043 C:/Users/harshnisar/Programming/data\analcatda... 0.985782 (0.98411309055118112,) 70 841 1
17 0.943128 0.938389 0.990521 C:/Users/harshnisar/Programming/data\analcatda... 0.981043 (0.98576169354838716,) 70 841 2
18 0.895735 0.957346 0.981043 C:/Users/harshnisar/Programming/data\analcatda... 0.981043 (0.98573827787655577,) 70 841 3
19 0.895735 0.976303 0.995261 C:/Users/harshnisar/Programming/data\analcatda... 0.990521 (0.98252678415198103,) 70 841 4
20 0.769231 0.769231 0.769231 C:/Users/harshnisar/Programming/data\analcatda... 0.769231 (0.88928571428571423,) 6 50 0
21 0.923077 0.923077 0.846154 C:/Users/harshnisar/Programming/data\analcatda... 0.769231 (0.89642857142857157,) 6 50 1
22 0.846154 0.769231 0.923077 C:/Users/harshnisar/Programming/data\analcatda... 0.769231 (0.94999999999999996,) 6 50 2
23 0.769231 0.846154 0.846154 C:/Users/harshnisar/Programming/data\analcatda... 0.769231 (0.92142857142857137,) 6 50 3
24 0.846154 0.923077 1.000000 C:/Users/harshnisar/Programming/data\analcatda... 0.769231 (0.87142857142857155,) 6 50 4
25 0.400000 0.400000 0.400000 C:/Users/harshnisar/Programming/data\analcatda... 0.400000 (0.67662337662337668,) 11 57 0
26 0.533333 0.466667 0.533333 C:/Users/harshnisar/Programming/data\analcatda... 0.533333 (0.67420634920634925,) 11 57 1
27 0.333333 0.600000 0.466667 C:/Users/harshnisar/Programming/data\analcatda... 0.466667 (0.64777777777777767,) 11 57 2
28 0.333333 0.400000 0.400000 C:/Users/harshnisar/Programming/data\analcatda... 0.400000 (0.65194805194805194,) 11 57 3
29 0.400000 0.400000 0.400000 C:/Users/harshnisar/Programming/data\analcatda... 0.333333 (0.7343434343434343,) 11 57 4
... ... ... ... ... ... ... ... ... ...
90 0.428571 0.571429 0.428571 C:/Users/harshnisar/Programming/data\analcatda... 0.285714 (0.47999999999999998,) 3 28 0
91 0.000000 0.142857 0.142857 C:/Users/harshnisar/Programming/data\analcatda... 0.428571 (0.47000000000000003,) 3 28 1
92 0.571429 0.428571 0.428571 C:/Users/harshnisar/Programming/data\analcatda... 0.285714 (0.14999999999999999,) 3 28 2
93 0.428571 0.428571 0.428571 C:/Users/harshnisar/Programming/data\analcatda... 0.428571 (0.42999999999999999,) 3 28 3
94 0.285714 0.285714 0.428571 C:/Users/harshnisar/Programming/data\analcatda... 0.285714 (0.49333333333333335,) 3 28 4
95 0.500000 0.500000 0.625000 C:/Users/harshnisar/Programming/data\analcatda... 0.500000 (0.83333333333333337,) 2 32 0
96 0.875000 0.875000 0.750000 C:/Users/harshnisar/Programming/data\analcatda... 0.875000 (0.79000000000000004,) 2 32 1
97 0.750000 0.875000 1.000000 C:/Users/harshnisar/Programming/data\analcatda... 0.875000 (0.71000000000000008,) 2 32 2
98 0.750000 0.750000 0.750000 C:/Users/harshnisar/Programming/data\analcatda... 0.875000 (0.88000000000000012,) 2 32 3
99 0.750000 0.875000 0.875000 C:/Users/harshnisar/Programming/data\analcatda... 0.750000 (0.83000000000000007,) 2 32 4
100 1.000000 1.000000 1.000000 C:/Users/harshnisar/Programming/data\analcatda... 1.000000 (1.0,) 3 14 0
101 1.000000 1.000000 1.000000 C:/Users/harshnisar/Programming/data\analcatda... 1.000000 (1.0,) 3 14 1
102 1.000000 1.000000 1.000000 C:/Users/harshnisar/Programming/data\analcatda... 1.000000 (1.0,) 3 14 2
103 1.000000 1.000000 1.000000 C:/Users/harshnisar/Programming/data\analcatda... 1.000000 (1.0,) 3 14 3
104 1.000000 1.000000 1.000000 C:/Users/harshnisar/Programming/data\analcatda... 1.000000 (1.0,) 3 14 4
105 0.545455 0.545455 0.545455 C:/Users/harshnisar/Programming/data\analcatda... 0.727273 (0.87142857142857133,) 11 42 0
106 0.545455 0.545455 0.727273 C:/Users/harshnisar/Programming/data\analcatda... 0.636364 (0.80285714285714282,) 11 42 1
107 0.636364 0.636364 0.636364 C:/Users/harshnisar/Programming/data\analcatda... 0.636364 (0.7790476190476191,) 11 42 2
108 0.636364 0.636364 0.636364 C:/Users/harshnisar/Programming/data\analcatda... 0.636364 (0.81428571428571428,) 11 42 3
109 0.545455 0.545455 0.545455 C:/Users/harshnisar/Programming/data\analcatda... 0.454545 (0.88571428571428579,) 11 42 4
110 0.350000 0.380000 0.310000 C:/Users/harshnisar/Programming/data\analcatda... 0.140000 (0.17968880244512364,) 5 400 0
111 0.300000 0.420000 0.260000 C:/Users/harshnisar/Programming/data\analcatda... 0.150000 (0.27292192564098522,) 5 400 1
112 0.300000 0.370000 0.200000 C:/Users/harshnisar/Programming/data\analcatda... 0.130000 (0.23701466781708369,) 5 400 2
113 0.260000 0.460000 0.270000 C:/Users/harshnisar/Programming/data\analcatda... 0.180000 (0.22678705502898416,) 5 400 3
114 0.320000 0.390000 0.240000 C:/Users/harshnisar/Programming/data\analcatda... 0.150000 (0.24310827081596739,) 5 400 4
115 0.333333 0.400000 0.466667 C:/Users/harshnisar/Programming/data\analcatda... 0.200000 (0.22121212121212119,) 3 60 0
116 0.466667 0.533333 0.266667 C:/Users/harshnisar/Programming/data\analcatda... 0.000000 (0.34857142857142859,) 3 60 1
117 0.333333 0.466667 0.133333 C:/Users/harshnisar/Programming/data\analcatda... 0.066667 (0.33944444444444449,) 3 60 2
118 0.533333 0.600000 0.400000 C:/Users/harshnisar/Programming/data\analcatda... 0.133333 (0.22444444444444445,) 3 60 3
119 0.333333 0.266667 0.200000 C:/Users/harshnisar/Programming/data\analcatda... 0.000000 (0.36071428571428571,) 3 60 4

120 rows × 9 columns


In [ ]: