def get_train_test_features0():
config.set_feature_name('f0')
if os.path.exists(config.train_feature_file) and os.path.exists(config.test_feature_file):
logger.info('loading the training and test features from files.')
trn = pd.read_csv(config.train_feature_file)
tst = pd.read_csv(config.test_feature_file)
y = trn['click_mode'].values
sub = tst[['sid']].copy()
feat = pd.read_csv('/home/ubuntu/projects/kddcup2019track1/build/feature/od_coord_feature.csv')
trn = trn.merge(feat, how='left', on='sid')
tst = tst.merge(feat, how='left', on='sid')
feat = pd.read_csv('/home/ubuntu/projects/kddcup2019track1/input/data_set_phase1/var_dist_time.csv')
trn = trn.merge(feat, how='left', on='sid')
tst = tst.merge(feat, how='left', on='sid')
feat = pd.read_csv('/home/ubuntu/projects/kddcup2019track1/input/data_set_phase1/var_dist_min.csv')
trn = trn.merge(feat, how='left', on='sid')
tst = tst.merge(feat, how='left', on='sid')
trn.drop(['sid', 'click_mode'], axis=1, inplace=True)
tst.drop(['sid', 'click_mode'], axis=1, inplace=True)
return trn, y, tst, sub
def get_train_test_features4():
config.set_feature_name('f4')
if os.path.exists(config.train_feature_file) and os.path.exists(config.test_feature_file):
logger.info('loading the training and test features from files.')
trn = pd.read_csv(config.train_feature_file)
tst = pd.read_csv(config.test_feature_file)
y = trn['click_mode'].values
sub = tst[['sid']].copy()
trn.drop(['sid', 'pid', 'click_mode'], axis=1, inplace=True)
tst.drop(['sid', 'pid', 'click_mode'], axis=1, inplace=True)
return trn, y, tst, sub
def get_train_test_features3():
config.set_feature_name('f3')
if os.path.exists(config.train_feature_file) and os.path.exists(config.test_feature_file):
logger.info('loading the training and test features from files.')
trn = pd.read_csv(config.train_feature_file)
tst = pd.read_csv(config.test_feature_file)
else:
df = merge_raw_data()
logger.info('generating feature f3.')
trn, tst = generate_f3(df)
logger.info('saving the training and test f3 features.')
trn.to_csv(config.train_feature_file, index=False)
tst.to_csv(config.test_feature_file, index=False)
y = trn['click_mode'].values
sub = tst[['sid']].copy()
trn.drop(['sid', 'pid', 'click_mode'], axis=1, inplace=True)
tst.drop(['sid', 'pid', 'click_mode'], axis=1, inplace=True)
return trn, y, tst, sub
prob_trn_tst = 0
for seed in [0, 17, 23, 29]:
params['seed'] = 2019 + seed
print(params)
clf = lgb.train(params,
lgb_trn,
valid_sets=[lgb_trn],
num_boost_round=best_iteration,
verbose_eval=50,
feval=eval_f)
prob_trn_tst += clf.predict(tst)
prob_trn_tst /= 4.0
np.savetxt(config.predict_trn_tst_bag_file, prob_trn_tst, delimiter=',')
trn_tst = np.argmax(prob_trn_tst, axis=1)
return trn_tst
if __name__ == '__main__':
trn, y, tst, sub = get_train_test_features2a()
config.set_algo_name('lgb3')
config.set_feature_name('f2a')
p_tst = train_lgb(trn, y, tst)
submit_result(sub, p_tst)
prob_trn_tst = 0
for seed in [0, 17, 23, 29]:
params['seed'] = 2019 + seed
print(params)
clf = lgb.train(params,
lgb_trn,
valid_sets=[lgb_trn],
num_boost_round=best_iteration,
verbose_eval=50,
feval=eval_f)
prob_trn_tst += clf.predict(tst)
prob_trn_tst /= 4.0
np.savetxt(config.predict_trn_tst_bag_file, prob_trn_tst, delimiter=',')
trn_tst = np.argmax(prob_trn_tst, axis=1)
return trn_tst
if __name__ == '__main__':
trn, y, tst, sub = get_train_test_features0()
config.set_algo_name('lgb5')
config.set_feature_name('f0')
p_tst = train_lgb(trn, y, tst)
submit_result(sub, p_tst)
X_trn, y_trn, X_val, y_val = trn.iloc[:-63388,:], y[:-63388], trn.iloc[-63388:,], y[-63388:]
eval_set = [(X_trn, y_trn), (X_val, y_val)]
clf.fit(X_trn, y_trn, eval_set=eval_set, eval_metric=f1_weighted, categorical_feature=cat_cols, verbose=10, early_stopping_rounds=100)
#clf.fit(X_trn, y_trn, eval_set=eval_set, eval_metric=f1_adj_weighted, categorical_feature=cat_cols, verbose=10, early_stopping_rounds=100)
feature_importances = list(clf.feature_importances_)
feature_names = trn.columns.values.tolist()
imp = pd.DataFrame({'feature_importances': feature_importances, 'feature_names':feature_names})
imp = imp.sort_values('feature_importances', ascending=False).drop_duplicates()
print("[+] All feature importances", list(imp.values))
pred = clf.predict(X_val, num_iteration=clf.best_iteration_)
print('Val F1: %f', f1_score(y_val, pred, average='weighted'))
print(classification_report(y_val, pred))
if __name__ == '__main__':
trn, y, tst, sub = get_train_test_features2()
#df = pd.read_csv(config.train_feature_file)
#df = df[~pd.isnull(df['click_mode'])]
#trn = df.drop(['sid','req_time', 'click_mode'], axis=1)
#y = df['click_mode'].values
config.set_algo_name('lgb4')
config.set_feature_name('f2') # f2 =
train_lgb(trn, y)