def predict_sub(model_lgb, testdex, test, subfilename): print_header('Submission') print_doing_in_task('predicting') lgpred = model_lgb.predict(test) lgsub = pd.DataFrame(lgpred, columns=["deal_probability"], index=testdex) lgsub['deal_probability'].clip(0.0, 1.0, inplace=True) print('saving submission file to', subfilename) lgsub.to_csv(subfilename, index=True, header=True) print('done')
def prepare_training(mat_filename, dir_feature, predictors, is_textadded): print_header('Load features') df, y, len_train, traindex, testdex = load_train_test(['item_id'], TARGET, DEBUG) del len_train gc.collect() df = drop_col(df, REMOVED_LIST) # add features print_doing('add tabular features') for feature in predictors: dir_feature_file = dir_feature + feature + '.pickle' if not os.path.exists(dir_feature_file): print('can not find {}. Please check'.format(dir_feature_file)) else: if feature in df: print('{} already added'.format(feature)) else: print_doing_in_task('adding {}'.format(feature)) df = add_feature(df, dir_feature_file) print_memory() if is_textadded: # add text_feature print_doing_in_task('add text features') ready_df, tfvocab = get_text_matrix(mat_filename, 'all', 2, 0) # stack print_doing_in_task('stack') X = hstack([ csr_matrix(df.loc[traindex, :].values), ready_df[0:traindex.shape[0]] ]) # Sparse Matrix testing = hstack([ csr_matrix(df.loc[testdex, :].values), ready_df[traindex.shape[0]:] ]) print_memory() print_doing_in_task('prepare vocab') tfvocab = df.columns.tolist() + tfvocab for shape in [X, testing]: print("{} Rows and {} Cols".format(*shape.shape)) print("Feature Names Length: ", len(tfvocab)) else: tfvocab = df.columns.tolist() testing = hstack([csr_matrix(df.loc[testdex, :].values)]) X = hstack([csr_matrix(df.loc[traindex, :].values)]) # Sparse Matrix return X, y, testing, tfvocab, df.columns.tolist(), testdex
def get_svdtruncated_vectorizer(todir): print_doing('doing svdtruncated text feature') filename = todir + 'text_feature_kernel.pickle' savename = todir + 'truncated_text_feature_kernel.pickle' if os.path.exists(savename): print('done already...') with open(savename, "rb") as f: svd_matrix, vocab = pickle.load(f) with open(filename, "rb") as f: tfid_matrix, tfvocab = pickle.load(f) else: with open(filename, "rb") as f: tfid_matrix, tfvocab = pickle.load(f) svdT = TruncatedSVD(n_components=400) print_doing_in_task('truncated svd') svd_matrix = svdT.fit_transform(tfid_matrix) print_doing_in_task('convert to sparse') svd_matrix = sparse.csr_matrix(svd_matrix, dtype=np.float32) vocab = [] for i in range(np.shape(svd_matrix)[1]): vocab.append('lsa' + str(i + 1)) with open(savename, "wb") as f: pickle.dump((svd_matrix, vocab), f, protocol=pickle.HIGHEST_PROTOCOL) print('---- before truncate') print(tfid_matrix.shape), print('len of feature:', len(tfvocab)) print('---- after truncate') print(svd_matrix.shape), print('len of feature:', len(vocab)) if DEBUG: print(tfid_matrix) print('\n') print(svd_matrix) del svd_matrix, vocab, tfid_matrix, tfvocab gc.collect() print_memory()
def train(X, y, num_leave, full_predictors, categorical, predictors, boosting_type, option, seed): if DEBUG: subfilename = '../sub/debug_findseed_{}_{}_{}features_num_leave{}_OPTION{}.csv'. \ format(yearmonthdate_string,boosting_type,str(len(predictors)),num_leave,option) modelfilename = '../trained_models/debug_findseed_{}_{}_{}features_num_leave{}_OPTION{}.txt'. \ format(yearmonthdate_string,boosting_type,str(len(predictors)),num_leave,option) else: subfilename = '../sub/findseed_{}_{}_{}features_num_leave{}_OPTION{}.csv'. \ format(yearmonthdate_string,boosting_type,str(len(predictors)),num_leave,option) modelfilename = '../trained_models/findseed_{}_{}_{}features_num_leave{}_OPTION{}.txt'. \ format(yearmonthdate_string,boosting_type,str(len(predictors)),num_leave,option) print_header("Training") start_time = time.time() print_doing_in_task('prepare dataset...') X, X_local_valid, y, y_local_valid = train_test_split(X, y, test_size=0.2, random_state=seed) X_train, X_valid, y_train, y_valid = train_test_split(X, y, test_size=0.10, random_state=seed) print('training shape: {} \n'.format(X.shape)) print("Light Gradient Boosting Regressor") lgbm_params = { 'task': 'train', 'boosting_type': boosting_type, 'objective': 'regression', 'metric': 'rmse', 'max_depth': 15, 'feature_fraction': 0.7, 'bagging_fraction': 0.8, 'learning_rate': 0.1, 'verbose': 0 } print('params:', lgbm_params) lgtrain = lgb.Dataset(X_train, y_train, feature_name=full_predictors, categorical_feature=categorical) lgvalid = lgb.Dataset(X_valid, y_valid, feature_name=full_predictors, categorical_feature=categorical) if DEBUG: num_boost_round = 300 early_stopping_rounds = 10 else: num_boost_round = 20000 early_stopping_rounds = 30 lgb_clf = lgb.train(lgbm_params, lgtrain, num_boost_round=num_boost_round, valid_sets=[lgtrain, lgvalid], valid_names=['train', 'valid'], early_stopping_rounds=early_stopping_rounds, verbose_eval=10) print_memory() print_header("Model Report") runnning_time = '{0:.2f}'.format((time.time() - start_time) / 60) num_boost_rounds_lgb = lgb_clf.best_iteration print_doing_in_task('fit val') val_rmse = '{0:.4f}'.format( np.sqrt(metrics.mean_squared_error(y_valid, lgb_clf.predict(X_valid)))) print_doing_in_task('fit train') train_rmse = '{0:.4f}'.format( np.sqrt(metrics.mean_squared_error(y_train, lgb_clf.predict(X_train)))) print_doing_in_task('fit local val') local_valid_rmse = '{0:.4f}'.format( np.sqrt( metrics.mean_squared_error(y_local_valid, lgb_clf.predict(X_local_valid)))) diff_lb = '{0:.4f}'.format(abs(float(local_valid_rmse) - 0.2300)) print('OPTION', option) print('model training time: {} mins'.format(runnning_time)) print('seed number: {}'.format(seed)) print('num_boost_rounds_lgb: {}'.format(num_boost_rounds_lgb)) print('train rmse: {}'.format(train_rmse)) print('val rmse: {}'.format(val_rmse)) print('local valid rmse: {}'.format(local_valid_rmse)) print('diff comapred to lb: {}'.format(diff_lb)) print('saving model to', modelfilename) lgb_clf.save_model(modelfilename) seed_name = 'seed_' + str(seed) LOCAL_VALIDATION_RESULT['seed'][seed_name] = seed LOCAL_VALIDATION_RESULT['running_time'][seed_name] = runnning_time LOCAL_VALIDATION_RESULT['num_round'][seed_name] = num_boost_rounds_lgb LOCAL_VALIDATION_RESULT['train'][seed_name] = train_rmse LOCAL_VALIDATION_RESULT['val'][seed_name] = val_rmse LOCAL_VALIDATION_RESULT['local_test'][seed_name] = local_valid_rmse LOCAL_VALIDATION_RESULT['diff'][seed_name] = diff_lb return lgb_clf, subfilename
def train(X, y, num_leave, max_depth, full_predictors, categorical, predictors, boosting_type, option): print_header("Training") start_time = time.time() print_doing_in_task('prepare dataset...') X_train, X_valid, y_train, y_valid = train_test_split(X, y, test_size=0.10, random_state=SEED) print('training shape: {} \n'.format(X.shape)) print("Light Gradient Boosting Regressor") lgbm_params = { 'task': 'train', 'boosting_type': boosting_type, 'objective': 'regression', 'metric': 'rmse', 'max_depth': max_depth, 'num_leave': num_leave, 'feature_fraction': 0.8, 'bagging_fraction': 0.8, 'learning_rate': 0.1, 'lambda_l1': 10, 'max_bin': 512, 'verbose': -1 } print('params:', lgbm_params) lgtrain = lgb.Dataset(X_train, y_train, feature_name=full_predictors, categorical_feature=categorical) lgvalid = lgb.Dataset(X_valid, y_valid, feature_name=full_predictors, categorical_feature=categorical) if DEBUG: num_boost_round = 300 early_stopping_rounds = 10 else: num_boost_round = 20000 early_stopping_rounds = 100 lgb_clf = lgb.train(lgbm_params, lgtrain, num_boost_round=num_boost_round, valid_sets=[lgtrain, lgvalid], valid_names=['train', 'valid'], early_stopping_rounds=early_stopping_rounds, verbose_eval=10) print_memory() print_header("Model Report") runnning_time = '{0:.2f}'.format((time.time() - start_time) / 60) num_boost_rounds_lgb = lgb_clf.best_iteration print_doing_in_task('fit val') val_rmse = '{0:.4f}'.format( np.sqrt(metrics.mean_squared_error(y_valid, lgb_clf.predict(X_valid)))) print_doing_in_task('fit train') train_rmse = '{0:.4f}'.format( np.sqrt(metrics.mean_squared_error(y_train, lgb_clf.predict(X_train)))) print_header("Model Report") print('boosting_type {}, num_leave {}, max_depth {}'.format( boosting_type, num_leave, max_depth)) print('model training time: {0:.2f} mins'.format( (time.time() - start_time) / 60)) print('num_boost_rounds_lgb: {}'.format(lgb_clf.best_iteration)) print('best rmse: {0:.4f}'.format( np.sqrt(metrics.mean_squared_error(y_valid, lgb_clf.predict(X_valid))))) model = '{}_{}_{}'.format(boosting_type, num_leave, max_depth) LOCAL_TUNE_RESULT['running_time'][model] = runnning_time LOCAL_TUNE_RESULT['num_round'][model] = num_boost_rounds_lgb LOCAL_TUNE_RESULT['train'][model] = train_rmse LOCAL_TUNE_RESULT['val'][model] = val_rmse