pu_est3.py

mod_data = data.copy()
#get the indices of the positives samples
pos_ind = np.where(mod_data.iloc[:,-1].values == 1)[0]
#shuffle them
np.random.shuffle(pos_ind)
#now lets take 150 positives that will remain labeled
pos_sample = pos_ind[:150]
#create the new target variable and mark all the data set as unlabeled
mod_data['class_test'] = -1
# label just the 150 postive samples we have put aside
mod_data.loc[pos_sample,'class_test'] = 1
print('target variable:\n', mod_data.iloc[:,-1].value_counts())
 #remember that this data frame (x_data) includes the former target variable 
 # that we keep here just to compare the results
x_data = mod_data.iloc[:,:-2].values
y_labeled = mod_data.iloc[:,-1].values
y_positive = mod_data.iloc[:,-2].values
#PU estimation
pu_estimator, probs1y1 = fit_PU_estimator(x_data, y_labeled, 0.2, xgb.XGBClassifier())
y_predict = predict_PU_prob(x_data, pu_estimator, probs1y1)
y_predict = [1 if x > 0.5 else 0 for x in y_predict]
evaluate_results(y_positive, y_predict)