def __init__(self):
self.counters = np.load(os.path.join('data/', 'value_counters.npy'))
def fit_transform(self, X, y=None):
return self.transform(X), y
def transform(self, X):
var_cols = ['var_{}'.format(x) for x in range(200)]
for i, c in enumerate(var_cols):
X['count_' + c] = (X[c].map(self.counters[i]) == 1)
return X
model.preprocess_online(UpsamplingPreprocessor, IsUniqueOnline)
fit_params = {'use_best_model': True, 'verbose': 5000, 'plot': True}
predict_params = {}
results = model.run(data_loader,
roc_auc_score,
fit_params,
predict_params,
verbose=True)
if args.save:
current_file_path = os.path.abspath(__file__) # to save this .py file
model.save(data_loader, results, current_file_path, args.preds,
args.models)
## << Create and train model
return self.transform(X), y
def transform(self, X):
var_cols = ['var_{}'.format(x) for x in range(200)]
for i, c in enumerate(var_cols):
if c not in self.to_exclude:
X['varcount_' + c] = X[c].map(self.counters[i]).astype(
np.int32)
X['unique_' + c] = (X['varcount_' + c] == 1)
X['varcount_' + c] = X['varcount_' + c] * X[c]
return X
model.preprocess_online(UpsamplingPreprocessor, CountersGeneratorOnline)
fit_params = {'use_best_model': True, 'verbose': 5000, 'plot': True}
predict_params = {}
results = model.run(data_loader,
roc_auc_score,
fit_params,
predict_params,
verbose=True)
if args.save:
current_file_path = os.path.abspath(__file__) # to save this .py file
model.save(data_loader, results, current_file_path, args.preds,
args.models)
## << Create and train model
