def test_fit_data():
pool = Pool(CLOUDNESS_TRAIN_FILE, column_description=CLOUDNESS_CD_FILE)
eval_pool = Pool(CLOUDNESS_TEST_FILE, column_description=CLOUDNESS_CD_FILE)
base_model = CatBoostClassifier(iterations=2,
random_seed=0,
loss_function="MultiClass")
base_model.fit(pool)
baseline = np.array(
base_model.predict(pool, prediction_type='RawFormulaVal'))
eval_baseline = np.array(
base_model.predict(eval_pool, prediction_type='RawFormulaVal'))
eval_pool.set_baseline(eval_baseline)
model = CatBoostClassifier(iterations=2,
random_seed=0,
loss_function="MultiClass")
data = map_cat_features(pool.get_features(),
pool.get_cat_feature_indices())
model.fit(data,
pool.get_label(),
pool.get_cat_feature_indices(),
sample_weight=np.arange(1,
pool.num_row() + 1),
baseline=baseline,
use_best_model=True,
eval_set=eval_pool)
model.save_model(OUTPUT_MODEL_PATH)
return compare_canonical_models(OUTPUT_MODEL_PATH)
def test_no_cat_in_predict():
train_pool = Pool(TRAIN_FILE, column_description=CD_FILE)
test_pool = Pool(TEST_FILE, column_description=CD_FILE)
model = CatBoostClassifier(iterations=2, random_seed=0)
model.fit(train_pool)
pred1 = model.predict(map_cat_features(test_pool.get_features(), train_pool.get_cat_feature_indices()))
pred2 = model.predict(Pool(map_cat_features(test_pool.get_features(), train_pool.get_cat_feature_indices()), cat_features=train_pool.get_cat_feature_indices()))
assert _check_data(pred1, pred2)
def test_no_cat_in_predict():
train_pool = Pool(TRAIN_FILE, column_description=CD_FILE)
test_pool = Pool(TEST_FILE, column_description=CD_FILE)
model = CatBoostClassifier(iterations=2, random_seed=0)
model.fit(train_pool)
pred1 = model.predict(map_cat_features(test_pool.get_features(), train_pool.get_cat_feature_indices()))
pred2 = model.predict(Pool(map_cat_features(test_pool.get_features(), train_pool.get_cat_feature_indices()), cat_features=train_pool.get_cat_feature_indices()))
assert _check_data(pred1, pred2)
def test_fit_data():
pool = Pool(CLOUDNESS_TRAIN_FILE, column_description=CLOUDNESS_CD_FILE)
eval_pool = Pool(CLOUDNESS_TEST_FILE, column_description=CLOUDNESS_CD_FILE)
base_model = CatBoostClassifier(iterations=2, random_seed=0, loss_function="MultiClass")
base_model.fit(pool)
baseline = np.array(base_model.predict(pool, prediction_type='RawFormulaVal'))
eval_baseline = np.array(base_model.predict(eval_pool, prediction_type='RawFormulaVal'))
eval_pool.set_baseline(eval_baseline)
model = CatBoostClassifier(iterations=2, random_seed=0, loss_function="MultiClass")
data = map_cat_features(pool.get_features(), pool.get_cat_feature_indices())
model.fit(data, pool.get_label(), pool.get_cat_feature_indices(), sample_weight=np.arange(1, pool.num_row()+1), baseline=baseline, use_best_model=True, eval_set=eval_pool)
model.save_model(OUTPUT_MODEL_PATH)
return compare_canonical_models(OUTPUT_MODEL_PATH)
def hp_tuning(train, test, validate, column_description, algo_name, result_path):
train_pool = Pool(train, column_description=column_description)
val_pool = Pool(validate, column_description=column_description)
test_pool = Pool(test, column_description=column_description)
cat_features = train_pool.get_cat_feature_indices()
n_estimators = 1000
max_evals = 50
task_type = 'CPU'
if algo_name == 'classic':
func = choose_classic
elif algo_name == 'hyperopt':
func = choose_hyperOpt
elif algo_name == 'gaussian':
func = choose_gaussian
elif algo_name == 'optuna':
func = choose_optuna
elif algo_name == 'hyperband':
func = choose_hyperband2
else:
print("INCORRECT ALGO NAME!!!")
return
start = time.time()
results = func(train_pool,
val_pool,
test_pool,
cat_features,
n_estimators=n_estimators,
max_evals=max_evals,
task_type=task_type)
end = time.time()
results["time"] = end - start
with open(result_path, 'w') as outfile:
json.dump(results, outfile)
def test_export_to_python_after_load():
train_pool = Pool(TRAIN_FILE, column_description=CD_FILE)
test_pool = Pool(TEST_FILE, column_description=CD_FILE)
model = CatBoostClassifier(iterations=40, random_seed=0)
model.fit(train_pool)
pred_model = model.predict(test_pool, prediction_type='RawFormulaVal')
model.save_model(OUTPUT_MODEL_PATH)
model_loaded = CatBoostClassifier()
model_loaded.load_model(OUTPUT_MODEL_PATH)
model_loaded.save_model(OUTPUT_PYTHON_MODEL_PATH,
format="python",
pool=train_pool)
pred_model_loaded = model_loaded.predict(test_pool,
prediction_type='RawFormulaVal')
import sys
import os.path
module_dir = os.path.dirname(OUTPUT_PYTHON_MODEL_PATH)
sys.path.insert(0, module_dir)
from model import apply_catboost_model as apply_catboost_model_from_python
pred_python = []
for test_line in test_pool.get_features():
float_features, cat_features = _split_features(
test_line, train_pool.get_cat_feature_indices(),
test_pool.get_cat_feature_hash_to_string())
pred_python.append(
apply_catboost_model_from_python(float_features, cat_features))
assert _check_data(pred_model, pred_python)
assert _check_data(pred_model_loaded, pred_python)
def test_load_df_vs_load_from_file():
pool1 = Pool(TRAIN_FILE, column_description=CD_FILE)
data = read_table(TRAIN_FILE, header=None, dtype=str)
label = DataFrame(data.iloc[:, TARGET_IDX])
data.drop([TARGET_IDX], axis=1, inplace=True)
cat_features = pool1.get_cat_feature_indices()
pool2 = Pool(np.array(data), label, cat_features)
assert pool1 == pool2
def test_load_df_vs_load_from_file():
pool1 = Pool(TRAIN_FILE, column_description=CD_FILE)
data = read_table(TRAIN_FILE, header=None, dtype=str)
label = DataFrame(data.iloc[:, TARGET_IDX])
data.drop([TARGET_IDX], axis=1, inplace=True)
cat_features = pool1.get_cat_feature_indices()
pool2 = Pool(np.array(data), label, cat_features)
assert pool1 == pool2
def test_load_df():
pool = Pool(NAN_TRAIN_FILE, column_description=NAN_CD_FILE)
data = read_table(NAN_TRAIN_FILE, header=None)
label = DataFrame(data.iloc[:, TARGET_IDX])
data.drop([TARGET_IDX], axis=1, inplace=True)
cat_features = pool.get_cat_feature_indices()
pool2 = Pool(data, label, cat_features)
assert _check_data(pool.get_features(), pool2.get_features())
assert _check_data(pool.get_label(), pool2.get_label())
def test_load_df():
pool = Pool(NAN_TRAIN_FILE, column_description=NAN_CD_FILE)
data = read_table(NAN_TRAIN_FILE, header=None)
label = DataFrame(data.iloc[:, TARGET_IDX])
data.drop([TARGET_IDX], axis=1, inplace=True)
cat_features = pool.get_cat_feature_indices()
pool2 = Pool(data, label, cat_features)
assert _check_data(pool.get_features(), pool2.get_features())
assert _check_data(pool.get_label(), pool2.get_label())
def test_load_series():
pool = Pool(TRAIN_FILE, column_description=CD_FILE)
data = read_table(TRAIN_FILE, header=None)
label = Series(data.iloc[:, TARGET_IDX])
data.drop([TARGET_IDX], axis=1, inplace=True)
data = Series(list(data.values))
cat_features = pool.get_cat_feature_indices()
pool2 = Pool(data, label, cat_features)
assert _check_data(pool.get_features(), pool2.get_features())
assert _check_data(pool.get_label(), pool2.get_label())
def test_load_series():
pool = Pool(TRAIN_FILE, column_description=CD_FILE)
data = read_table(TRAIN_FILE, header=None)
label = Series(data.iloc[:, TARGET_IDX])
data.drop([TARGET_IDX], axis=1, inplace=True)
data = Series(list(data.values))
cat_features = pool.get_cat_feature_indices()
pool2 = Pool(data, label, cat_features)
assert _check_data(pool.get_features(), pool2.get_features())
assert _check_data(pool.get_label(), pool2.get_label())
def test_one_doc_feature_importance():
pool = Pool(TRAIN_FILE, column_description=CD_FILE)
model = CatBoostClassifier(iterations=5, random_seed=0)
model.fit(pool)
np.save(
FIMP_PATH,
np.array(
model.get_feature_importance(
np.ones(pool.num_col(), dtype=int),
0,
cat_features=pool.get_cat_feature_indices(),
fstr_type='Doc')))
return local_canonical_file(FIMP_PATH)
def test_export_model_with_cat_features_to_python_from_app():
test_pool = Pool(TEST_FILE, column_description=CD_FILE)
model = CatBoost()
with open(OUTPUT_MODEL_PATH, "w") as model_file:
model_file.write(resource.find("cb_adult_model_bin"))
model.load_model(OUTPUT_MODEL_PATH)
pred_model = model.predict(test_pool, prediction_type='RawFormulaVal')
from adult_model import apply_catboost_model as apply_catboost_model_from_app
pred_python = []
for test_line in test_pool.get_features():
float_features, cat_features = _split_features(
test_line, test_pool.get_cat_feature_indices(),
test_pool.get_cat_feature_hash_to_string())
pred_python.append(
apply_catboost_model_from_app(float_features, cat_features))
assert _check_data(pred_model, pred_python)
print('测试集 Y_CAT_test 的shape是',Y_CAT_test.shape)
print('训练集中label的正负比例分布如下：\n',Y_CAT_train.value_counts())
print('测试集中label的正负比例分布如下：\n',Y_CAT_test.value_counts())
print('可以看出在划分训练集和测试集时设定strtify参数为Y_CAT；使得在训练测试集中正负例所占比例一致。')
## catboost建模
### Step1: Pool Initialize
from catboost import Pool
pool_data = Pool(data = X_CAT,
label = Y_CAT,
cat_features = CAT_features)
print('pool_data的 type 是：', type(pool_data))
print('pool_data的 shpe 是：', pool_data.shape)
print('pool_data.get_features()返回的是list类型，其长度是：',len(pool_data.get_features()))
print('pool_data.get_label()返回的是list类型，其长度是：', len(pool_data.get_label()))
print('pool_data中类别变量所在的索引位置是 pool_data.get_cat_feature_indices() ：', pool_data.get_cat_feature_indices())
#print('生成的pool_data的各观测的weight：', pool_data.get_weight())
#print('生成的pool_data的各观测的baseline：', pool_data.get_baseline())
#### Step2.1 自定义metric类。用以做最优模型选择和过拟合检测
# **************Custom metric for overfitting detector and best model selection******
import math
from catboost import Pool, CatBoostClassifier
class Recall_1_Metric(object):
def get_final_error(self, error, weight):
return error / (weight + 1e-38)
def test_pool_cat_features():
pool = Pool(TRAIN_FILE, column_description=CD_FILE)
assert np.all(pool.get_cat_feature_indices() == CAT_FEATURES)
def test_load_ndarray():
pool = Pool(TRAIN_FILE, column_description=CD_FILE)
cat_features = pool.get_cat_feature_indices()
data = np.array(map_cat_features(pool.get_features(), cat_features))
label = np.array(pool.get_label())
assert _check_shape(Pool(data, label, cat_features))
def test_one_doc_feature_importance():
pool = Pool(TRAIN_FILE, column_description=CD_FILE)
model = CatBoostClassifier(iterations=5, random_seed=0)
model.fit(pool)
np.save(FIMP_PATH, np.array(model.get_feature_importance(np.ones(pool.num_col(), dtype=int), 0, cat_features=pool.get_cat_feature_indices(), fstr_type='Doc')))
return local_canonical_file(FIMP_PATH)
def test_pool_cat_features():
pool = Pool(TRAIN_FILE, column_description=CD_FILE)
assert np.all(pool.get_cat_feature_indices() == CAT_FEATURES)
def test_load_ndarray():
pool = Pool(TRAIN_FILE, column_description=CD_FILE)
cat_features = pool.get_cat_feature_indices()
data = np.array(map_cat_features(pool.get_features(), cat_features))
label = np.array(pool.get_label())
assert _check_shape(Pool(data, label, cat_features))
