'reg_lambda': .1,
'subsample': .9,
'min_split_gain': .01,
'min_child_weight': 2,
'colsample_bytree': .9, # Subsample ratio of columns when constructing each tree.
'scale_pos_weight': 9, # because training data is unbalanced
'verbose': -1
}
features = list(pd.read_csv(DATA_FOLDER + '/v3/importances.csv', index_col=0).head(800).index)
train_features = [*features, "target"]
train = pd.read_pickle(DATA_FOLDER + '/v3/train.pkl')[train_features]
folds = prepare_folds(train)
models, result = train_folds(folds, config)
test = load_test(DATA_FOLDER + '/v3/test.pkl')[features]
test_target = evaluate(models, test)
print("AUC: %.4f, F1: %.4f" % (result['auc'], result['f1']))
importance = result['importances'].groupby(['feature']) \
.agg({'importance': 'mean'}) \
.sort_values(by="importance", ascending=False)
importance.to_csv(DATA_FOLDER + "/v3/importances.csv")
prepare_submission(test_target, "v3_AUC_%.4f_F1_%.4f" % (result['auc'], result['f1']))
}
train = pd.read_pickle(DATA_FOLDER + '/v2/train.pkl')
inter_features = list(pd.read_csv(DATA_FOLDER + '/v2/importances.csv', index_col=0).head(200).index)
categorical = set(train.columns[train.dtypes == int]).intersection(inter_features)
cats = [[x] for x in categorical]
folds = prepare_folds(train)
folds = mean_encode_train_fold(folds, cats)
models, result = train_folds(folds, config)
test = load_test(DATA_FOLDER + '/v2/test.pkl')
test = mean_encode_test(train, test, cats)
test_target = evaluate(models, test)
print("AUC: %.4f, F1: %.4f" % (result['auc'], result['f1']))
importance = result['importances'].groupby(['feature']) \
.agg({'importance': 'mean'}) \
.sort_values(by="importance", ascending=False)
importance.to_csv(DATA_FOLDER + "/v4/importances.csv")
prepare_submission(test_target, "v4_AUC_%.4f_F1_%.4f" % (result['auc'], result['f1']))