encoder = joblib.load('models/encoder.pkl')
# Load data
X_train = encoder.transform(pd.read_csv('data/X_train.csv'))
y_train = pd.read_csv('data/y_train.csv')['Survived']
# Determine categorical features
cat_features = np.where(X_train.dtypes == int)[0]
# Create a validation set with 20% of the training set
X_fit, X_val, y_fit, y_val = model_selection.train_test_split(X_train, y_train, test_size=0.2)
# Initialize stage 0 models
models = {
'rf': ensemble.RandomForestClassifier(random_state=1),
'catboost': catboost.CatBoostClassifier()
}
# Initialize stack
stack = xam.stacking.StackingClassifier(
models=models,
meta_model=linear_model.LogisticRegression(),
cv=model_selection.StratifiedKFold(n_splits=10),
use_base_features=True,
use_proba=True
)
stack.fit(
X=X_train,
y=y_train,
fit_params={
return X, y
def read_yaml(path):
with open(path, "r") as f:
return yaml.safe_load(f)
MODEL_PARAMS = {"allow_writing_files": False, "iterations": 10}
@pytest.fixture(
scope="module",
params=[
cb.CatBoost(MODEL_PARAMS),
cb.CatBoostClassifier(**MODEL_PARAMS),
cb.CatBoostRegressor(**MODEL_PARAMS),
],
ids=["CatBoost", "CatBoostClassifier", "CatBoostRegressor"],
)
def cb_model(request):
model = request.param
X, y = get_iris()
return ModelWithData(model=model.fit(X, y), inference_dataframe=X)
@pytest.fixture
def reg_model():
model = cb.CatBoostRegressor(**MODEL_PARAMS)
X, y = get_iris()
return ModelWithData(model=model.fit(X, y), inference_dataframe=X)
from sklearn.metrics import roc_auc_score
tr_index = ~all_data['label'].isnull()
X_train = all_data[tr_index][list(set(feature_name))].reset_index(drop=True)
y = all_data[tr_index]['label'].reset_index(drop=True).astype(int)
X_test = all_data[~tr_index][list(set(feature_name))].reset_index(drop=True)
print(X_train.shape,X_test.shape)
random_seed = 2019
final_pred = []
cv_score = []
cv_model = []
skf = StratifiedKFold(n_splits=5, random_state=random_seed, shuffle=True)
for index, (train_index, test_index) in enumerate(skf.split(X_train, y)):
print(index)
train_x, test_x, train_y, test_y = X_train[feature_name].iloc[train_index], X_train[feature_name].iloc[test_index], y.iloc[train_index], y.iloc[test_index]
cbt_model = cbt.CatBoostClassifier(iterations=3000,learning_rate=0.1,max_depth=7,l2_leaf_reg=10,verbose=10,early_stopping_rounds=100,devices='GPU',eval_metric='F1')
cbt_model.fit(train_x[feature_name], train_y,eval_set=(test_x[feature_name],test_y))
cv_model.append(cbt_model)
y_test = cbt_model.predict(X_test[feature_name])
y_val = cbt_model.predict_proba(test_x[feature_name])
print(Counter(np.argmax(y_val,axis=1)))
cv_score.append(f1_score(test_y,np.round(y_val[:,1])))
# Catboost比较适合类别较多的场景
# GPU结果五折
# 第一折
# bestTest = 0.9358583857
# bestIteration = 1437
# 第二折
model1.predict_proba(X.iloc[val_idx, :])[:, 1]))
preds[:, i] = model1.predict_proba(public)[:, 1]
# ================= CatBoost ===================== #
cat_feature_inds = []
for i, c in enumerate(X.columns.values):
num_uniques = len(X[c].unique())
if num_uniques < 3:
cat_feature_inds.append(i)
preds = np.zeros((len(public), 5))
for i, (train_idx, val_idx) in enumerate(kf.split(X)):
cat_model = catboost.CatBoostClassifier(iterations=600,
learning_rate=0.03,
depth=6,
l2_leaf_reg=1,
eval_metric='Logloss',
random_seed=4 * 100 + 6)
cat_model.fit(X.iloc[train_idx, :],
y[train_idx],
cat_features=cat_feature_inds)
print("Train Log loss is %.4f" %
log_loss(y[train_idx],
cat_model.predict_proba(X.iloc[train_idx, :])[:, 1]))
print("Validation Log loss is %.4f" %
log_loss(y[val_idx],
cat_model.predict_proba(X.iloc[val_idx, :])[:, 1]))
preds[:, i] = cat_model.predict_proba(public)[:, 1]
# lightgbm
def main():
# Load cli params
parser = argparse.ArgumentParser(prog="grid")
parser.add_argument("-d", "--data", dest="data", required=True)
parser.add_argument("-m",
"--model",
dest="model",
required=True,
choices=["xgboost", "lightgbm", "catboost"])
parser.add_argument("-t", "--tag", dest="tag", required=True)
parser.add_argument("-n", "--number", dest="number", type=int, default=-1)
args = parser.parse_args()
# Load config
cf = c.Config(args.data, args.model, args.tag)
grid_params = cf.load_config_file("grid")
hyper_params = cf.load_config_file("hyper")
fit_params = {}
# Load data
features_to_load = list(cf.features.keys())
source_file = os.path.join(c.DATA_FOLDER, args.data)
data = pd.read_csv(source_file,
usecols=features_to_load,
sep=";",
decimal=".",
encoding="latin1",
keep_default_na=False,
na_values=[""])
# Preprocessing
group_categoricals_tail(data, cf.classes["categorical"])
if args.model == "xgboost":
import xgboost as xgb
estimator = xgb.XGBClassifier()
data = pd.get_dummies(data, columns=cf.classes["categorical"]).copy()
elif args.model == "lightgbm":
import lightgbm as lgb
from sklearn.preprocessing import LabelEncoder
estimator = lgb.LGBMClassifier()
label_encoding = {}
for col in cf.classes["categorical"]:
unique_values = data[col].unique().tolist()
label_encoding[col] = LabelEncoder()
label_encoding[col].fit(sorted(unique_values))
data[col] = label_encoding[col].transform(data[col].values)
fit_params = {"categorical_feature": cf.classes["categorical"]}
elif args.model == "catboost":
import catboost as cb
estimator = cb.CatBoostClassifier()
else: # This code should never end up here
raise ValueError(
"Something went wrong: {} is not a feasible model.".format(
args.model))
features = [
x for x in sorted(data.columns.tolist())
if x not in cf.classes["label"] + cf.classes["index"]
]
if args.model == "lightgbm":
fit_params["feature_name"] = features
elif args.model == "catboost":
fit_params["cat_features"] = [
i for i, f in enumerate(features) if f in cf.classes["categorical"]
]
# Sampling
if not args.number == -1 or args.number <= data.shape[0]:
data = data.sample(args.number)
d = data.loc[:, features].values
# Prepare to save
output = "_".join([args.model, args.tag, "grid"]) + ".xlsx"
excel_writer = pd.ExcelWriter(os.path.join(c.RESULTS_FOLDER, output),
engine="xlsxwriter")
# Grid
results = {}
for label in cf.classes["label"]:
print("----------------------------", end="\n")
print(label, end="\n")
print("----------------------------", end="\n\n")
y = data.loc[:, label].values
rand_grid_cv = RandomizedSearchCV(estimator,
param_distributions=hyper_params,
**grid_params)
rand_grid_cv.fit(d, y, **fit_params)
results[label] = rand_grid_cv.best_params_
results_df = pd.DataFrame(rand_grid_cv.cv_results_)
results_df.to_excel(excel_writer, sheet_name=label, index=False)
# Save
excel_writer.save()
file_name = "best"
cf.save_config_file(file_name, results)
# Define hyperparameters
params = {
"depth": [1, 3, 7],
"iterations": [100],
"learning_rate": [0.01, 0.1, 0.2],
"l2_leaf_reg": [1, 5, 10],
}
# Step 1: set up target metrics for evaluating training
# Define target loss metric to aim for
target_f1 = 0.7
# Instantiate classifier and run grid search to find best parameters
clf = catboost.CatBoostClassifier()
grid_clf = GridSearchCV(clf, params, scoring="neg_log_loss")
grid_clf.fit(X_train, y_train)
# Set the clf to the best combination of parameters
clf = grid_clf.best_estimator_
clf.fit(X_train, y_train)
# Step 3: Evaluate the quality of the trained model
y_pred = clf.predict(X_test)
y_pred_proba = clf.predict_proba(X_test)
# print classification report of classifier
print(classification_report(y_test, y_pred, target_names=class_names))
# evaluate the quality of the trained model using weighted f1 score
from sklearn import metrics
import catboost
import multiprocessing
d_train = pd.read_csv("train-1m.csv")
d_test = pd.read_csv("test.csv")
X_train = d_train.drop(['dep_delayed_15min'], axis=1)
X_test = d_test.drop(['dep_delayed_15min'], axis=1)
y_train = np.where(d_train["dep_delayed_15min"]=="Y",1,0)
y_test = np.where(d_test["dep_delayed_15min"]=="Y",1,0)
cat_cols = np.where(X_train.dtypes == np.object)[0]
md = catboost.CatBoostClassifier(iterations = 100, depth = 10, learning_rate = 0.1,
task_type = "GPU")
## thread_count = multiprocessing.cpu_count())
%time md.fit(X_train, y_train, cat_features = cat_cols)
y_pred = md.predict_proba(X_test)[:,1]
metrics.roc_auc_score(y_test, y_pred)
X_test = data[~tr_index][list(set(feature_name))].reset_index(drop=True)
print(X_train.shape, X_test.shape)
oof = np.zeros(X_train.shape[0])
prediction = np.zeros(X_test.shape[0])
seeds = [19970412, 2019 * 2 + 1024, 4096, 2048, 1024]
num_model_seed = 1
for model_seed in range(num_model_seed):
oof_cat = np.zeros(X_train.shape[0])
prediction_cat = np.zeros(X_test.shape[0])
skf = StratifiedKFold(n_splits=5, random_state=seeds[model_seed], shuffle=True)
for index, (train_index, test_index) in enumerate(skf.split(X_train, y)):
print(index)
train_x, test_x, train_y, test_y = X_train[feature_name].iloc[train_index], X_train[feature_name].iloc[
test_index], y.iloc[train_index], y.iloc[test_index]
cbt_model = cbt.CatBoostClassifier(iterations=7000, learning_rate=0.1, max_depth=7, verbose=100,
early_stopping_rounds=500, eval_metric='F1', task_type='GPU',
cat_features=cat_list)
cbt_model.fit(train_x[feature_name], train_y, eval_set=(test_x[feature_name], test_y))
gc.collect()
oof_cat[test_index] += cbt_model.predict_proba(test_x)[:, 1]
prediction_cat += cbt_model.predict_proba(X_test[feature_name])[:, 1] / 5
print('F1', f1_score(y, np.round(oof_cat)))
oof += oof_cat / num_model_seed
prediction += prediction_cat / num_model_seed
print('score', f1_score(y, np.round(oof)))
# write to csv
submit = test[['sid']]
submit['label'] = (prediction >= 0.499).astype(int)
print(submit['label'].value_counts())
submit.to_csv("round2_A_submission.csv", index=False)
num_model_seed = 5
for model_seed in range(num_model_seed):
print(model_seed + 1)
oof_cat = np.zeros((X_train.shape[0], 4))
prediction_cat = np.zeros((X_test.shape[0], 4))
skf = StratifiedKFold(n_splits=5,
random_state=seeds[model_seed],
shuffle=True)
for index, (train_index, test_index) in enumerate(skf.split(X_train, y)):
print(index)
train_x, test_x, train_y, test_y = X_train.iloc[train_index], X_train.iloc[
test_index], y.iloc[train_index], y.iloc[test_index]
gc.collect()
cbt_model = cbt.CatBoostClassifier(iterations=800,
learning_rate=0.01,
verbose=300,
early_stopping_rounds=200,
loss_function='MultiClass')
cbt_model.fit(train_x, train_y, eval_set=(train_x, train_y))
oof_cat[test_index] += cbt_model.predict_proba(test_x)
prediction_cat += cbt_model.predict_proba(X_test) / 5
gc.collect()
oof += oof_cat / num_model_seed
prediction += prediction_cat / num_model_seed
print('logloss', log_loss(pd.get_dummies(y).values, oof_cat))
print('ac', accuracy_score(y, np.argmax(oof_cat, axis=1)))
print('mae', 1 / (1 + np.sum(np.absolute(np.eye(4)[y] - oof_cat)) / 480))
print('logloss', log_loss(pd.get_dummies(y).values, oof))
print('ac', accuracy_score(y, np.argmax(oof, axis=1)))
print('mae', 1 / (1 + np.sum(np.absolute(np.eye(4)[y] - oof)) / 480))
sub = test[['Group']]
def test_check_mask_params(self, check_consistency_model_label,
check_consistency_model_features,
check_preprocessing_options, check_explainer,
check_model):
"""
Unit test check mask params
"""
train = pd.DataFrame({
'Onehot1': ['A', 'B', 'A', 'B'],
'Onehot2': ['C', 'D', 'C', 'D'],
'Binary1': ['E', 'F', 'E', 'F'],
'Binary2': ['G', 'H', 'G', 'H'],
'Ordinal1': ['I', 'J', 'I', 'J'],
'Ordinal2': ['K', 'L', 'K', 'L'],
'BaseN1': ['M', 'N', 'M', 'N'],
'BaseN2': ['O', 'P', 'O', 'P'],
'Target1': ['Q', 'R', 'Q', 'R'],
'Target2': ['S', 'T', 'S', 'T'],
'other': ['other', np.nan, 'other', 'other']
})
features_dict = None
columns_dict = {
i: features
for i, features in enumerate(train.columns)
}
features_types = {
features: str(train[features].dtypes)
for features in train.columns
}
label_dict = None
enc_ordinal = ce.OrdinalEncoder(cols=[
'Onehot1', 'Onehot2', 'Binary1', 'Binary2', 'Ordinal1', 'Ordinal2',
'BaseN1', 'BaseN2', 'Target1', 'Target2', 'other'
]).fit(train)
train_ordinal = enc_ordinal.transform(train)
y = pd.DataFrame({'y_class': [0, 0, 0, 1]})
model = cb.CatBoostClassifier(n_estimators=1).fit(train_ordinal, y)
clf_explainer = shap.TreeExplainer(model)
check_preprocessing_options.return_value = True
check_consistency_model_features.return_value = True
check_consistency_model_label.return_value = True
check_explainer.return_value = clf_explainer
check_model.return_value = "classification", [0, 1]
wrong_mask_params_1 = list()
wrong_mask_params_2 = None
wrong_mask_params_3 = {
"features_to_hide": None,
"threshold": None,
"positive": None
}
wright_mask_params = {
"features_to_hide": None,
"threshold": None,
"positive": True,
"max_contrib": 5
}
with self.assertRaises(ValueError):
predictor_1 = SmartPredictor(features_dict,
model,
columns_dict,
clf_explainer,
features_types,
label_dict,
mask_params=wrong_mask_params_1)
predictor_1 = SmartPredictor(features_dict,
model,
columns_dict,
clf_explainer,
features_types,
label_dict,
mask_params=wrong_mask_params_2)
predictor_1 = SmartPredictor(features_dict,
model,
columns_dict,
clf_explainer,
features_types,
label_dict,
mask_params=wrong_mask_params_3)
predictor_1 = SmartPredictor(features_dict,
model,
columns_dict,
clf_explainer,
features_types,
label_dict,
mask_params=wright_mask_params)
def test_summarize_2(self):
"""
Unit test 2 summarize method
"""
predictor_1 = self.predictor_3
predictor_1._case = "classification"
predictor_1._classes = [0, 1]
clf = cb.CatBoostClassifier(n_estimators=1).fit(
self.df_3[['x1', 'x2']], self.df_3['y'])
clf_explainer = shap.TreeExplainer(clf)
predictor_1.model = clf
predictor_1.explainer = clf_explainer
with self.assertRaises(ValueError):
predictor_1.summarize()
predictor_1.data = {
"x": None,
"x_preprocessed": None,
"x_postprocessed": None,
"ypred": None,
"contributions": None
}
predictor_1.data["x"] = self.df_3[["x1", "x2"]]
predictor_1.data["x_preprocessed"] = self.df_3[["x1", "x2"]]
predictor_1.data["x_postprocessed"] = self.df_3[["x1", "x2"]]
predictor_1.data["ypred"] = pd.DataFrame({
"y": ["Yes", "Yes", "No", "No", "No"],
"proba": [0.519221, 0.468791, 0.531209, 0.531209, 0.531209]
})
predictor_1.data["contributions"] = pd.DataFrame({
"x1": [0, 0, -0, -0, -0],
"x2": [0.161538, -0.0403846, 0.0403846, 0.0403846, 0.0403846]
})
output = predictor_1.summarize()
expected_output = pd.DataFrame(
{
"y": ["Yes", "Yes", "No", "No", "No"],
"proba": [0.519221, 0.468791, 0.531209, 0.531209, 0.531209],
"feature_1":
["weight", "weight", "weight", "weight", "weight"],
"value_1": ["90", "78", "84", "85", "53"],
"contribution_1": [
"0.161538", "-0.0403846", "0.0403846", "0.0403846",
"0.0403846"
],
"feature_2": ["age", "age", "age", "age", "age"],
"value_2": ["25", "39", "50", "43", "67"],
"contribution_2": ["0", "0", "0", "0", "0"]
},
dtype=object)
expected_output["proba"] = expected_output["proba"].astype(float)
feature_expected = [
column for column in expected_output.columns
if column.startswith("feature_")
]
feature_output = [
column for column in output.columns
if column.startswith("feature_")
]
value_expected = [
column for column in expected_output.columns
if column.startswith("value_")
]
value_output = [
column for column in output.columns if column.startswith("value_")
]
contribution_expected = [
column for column in expected_output.columns
if column.startswith("contribution_")
]
contribution_output = [
column for column in output.columns
if column.startswith("contribution_")
]
assert expected_output.shape == output.shape
assert len(feature_expected) == len(feature_output)
assert len(value_expected) == len(value_output)
assert len(contribution_expected) == len(contribution_output)
assert all(output.columns == expected_output.columns)
def setUp(self):
df = pd.DataFrame(range(0, 5), columns=['id'])
df['y'] = df['id'].apply(lambda x: 1 if x < 2 else 0)
df['x1'] = np.random.randint(1, 123, df.shape[0])
df['x2'] = ["S", "M", "S", "D", "M"]
df = df.set_index('id')
encoder = ce.OrdinalEncoder(cols=["x2"], handle_unknown="None")
encoder_fitted = encoder.fit(df)
df_encoded = encoder_fitted.transform(df)
clf = cb.CatBoostClassifier(n_estimators=1).fit(
df_encoded[['x1', 'x2']], df_encoded['y'])
clf_explainer = shap.TreeExplainer(clf)
columns_dict = {0: "x1", 1: "x2"}
label_dict = {0: "Yes", 1: "No"}
postprocessing = {
"x2": {
"type": "transcoding",
"rule": {
"S": "single",
"M": "married",
"D": "divorced"
}
}
}
features_dict = {"x1": "age", "x2": "family_situation"}
features_types = {
features: str(df[features].dtypes)
for features in df[['x1', 'x2']]
}
self.df_1 = df
self.preprocessing_1 = encoder_fitted
self.df_encoded_1 = df_encoded
self.clf_1 = clf
self.clf_explainer_1 = clf_explainer
self.columns_dict_1 = columns_dict
self.label_dict_1 = label_dict
self.postprocessing_1 = postprocessing
self.features_dict_1 = features_dict
self.features_types_1 = features_types
self.predictor_1 = SmartPredictor(features_dict, clf, columns_dict,
clf_explainer, features_types,
label_dict, encoder_fitted,
postprocessing)
df['x2'] = np.random.randint(1, 100, df.shape[0])
encoder = ce.OrdinalEncoder(cols=["x2"], handle_unknown="None")
encoder_fitted = encoder.fit(df[["x1", "x2"]])
df_encoded = encoder_fitted.transform(df[["x1", "x2"]])
clf = cb.CatBoostClassifier(n_estimators=1).fit(
df[['x1', 'x2']], df['y'])
clf_explainer = shap.TreeExplainer(clf)
features_dict = {"x1": "age", "x2": "weight"}
features_types = {
features: str(df[features].dtypes)
for features in df[["x1", "x2"]].columns
}
self.df_2 = df
self.preprocessing_2 = encoder_fitted
self.df_encoded_2 = df_encoded
self.clf_2 = clf
self.clf_explainer_2 = clf_explainer
self.columns_dict_2 = columns_dict
self.label_dict_2 = label_dict
self.postprocessing_2 = postprocessing
self.features_dict_2 = features_dict
self.features_types_2 = features_types
self.predictor_2 = SmartPredictor(features_dict, clf, columns_dict,
clf_explainer, features_types,
label_dict, encoder_fitted,
postprocessing)
df['x1'] = [25, 39, 50, 43, 67]
df['x2'] = [90, 78, 84, 85, 53]
columns_dict = {0: "x1", 1: "x2"}
label_dict = {0: "No", 1: "Yes"}
features_dict = {"x1": "age", "x2": "weight"}
features_types = {
features: str(df[features].dtypes)
for features in df[['x1', 'x2']].columns
}
clf = cb.CatBoostRegressor(n_estimators=1).fit(df[['x1', 'x2']],
df['y'])
clf_explainer = shap.TreeExplainer(clf)
self.df_3 = df
self.preprocessing_3 = None
self.df_encoded_3 = df
self.clf_3 = clf
self.clf_explainer_3 = clf_explainer
self.columns_dict_3 = columns_dict
self.label_dict_3 = label_dict
self.postprocessing_3 = None
self.features_dict_3 = features_dict
self.features_types_3 = features_types
self.predictor_3 = SmartPredictor(features_dict, clf, columns_dict,
clf_explainer, features_types,
label_dict)
def test_check_preprocessing_1(self, check_consistency_model_label,
check_consistency_model_features,
check_preprocessing_options,
check_explainer, check_model):
"""
Test check preprocessing on multiple preprocessing
"""
train = pd.DataFrame({
'Onehot1': ['A', 'B', 'A', 'B'],
'Onehot2': ['C', 'D', 'C', 'D'],
'Binary1': ['E', 'F', 'E', 'F'],
'Binary2': ['G', 'H', 'G', 'H'],
'Ordinal1': ['I', 'J', 'I', 'J'],
'Ordinal2': ['K', 'L', 'K', 'L'],
'BaseN1': ['M', 'N', 'M', 'N'],
'BaseN2': ['O', 'P', 'O', 'P'],
'Target1': ['Q', 'R', 'Q', 'R'],
'Target2': ['S', 'T', 'S', 'T'],
'other': ['other', np.nan, 'other', 'other']
})
features_dict = None
columns_dict = {
i: features
for i, features in enumerate(train.columns)
}
features_types = {
features: str(train[features].dtypes)
for features in train.columns
}
label_dict = None
enc_ordinal_all = ce.OrdinalEncoder(cols=[
'Onehot1', 'Onehot2', 'Binary1', 'Binary2', 'Ordinal1', 'Ordinal2',
'BaseN1', 'BaseN2', 'Target1', 'Target2', 'other'
]).fit(train)
train_ordinal_all = enc_ordinal_all.transform(train)
y = pd.DataFrame({'y_class': [0, 0, 0, 1]})
model = cb.CatBoostClassifier(n_estimators=1).fit(train_ordinal_all, y)
clf_explainer = shap.TreeExplainer(model)
check_preprocessing_options.return_value = True
check_consistency_model_features.return_value = True
check_consistency_model_label.return_value = True
check_explainer.return_value = clf_explainer
check_model.return_value = "classification", [0, 1]
predictor_1 = SmartPredictor(features_dict, model, columns_dict,
clf_explainer, features_types, label_dict)
y = pd.DataFrame(data=[0, 1, 0, 0], columns=['y'])
enc_onehot = ce.OneHotEncoder(cols=['Onehot1', 'Onehot2']).fit(train)
train_onehot = enc_onehot.transform(train)
enc_binary = ce.BinaryEncoder(
cols=['Binary1', 'Binary2']).fit(train_onehot)
train_binary = enc_binary.transform(train_onehot)
enc_ordinal = ce.OrdinalEncoder(
cols=['Ordinal1', 'Ordinal2']).fit(train_binary)
train_ordinal = enc_ordinal.transform(train_binary)
enc_basen = ce.BaseNEncoder(
cols=['BaseN1', 'BaseN2']).fit(train_ordinal)
train_basen = enc_basen.transform(train_ordinal)
enc_target = ce.TargetEncoder(cols=['Target1', 'Target2']).fit(
train_basen, y)
input_dict1 = dict()
input_dict1['col'] = 'Onehot2'
input_dict1['mapping'] = pd.Series(data=['C', 'D', np.nan],
index=['C', 'D', 'missing'])
input_dict1['data_type'] = 'object'
input_dict2 = dict()
input_dict2['col'] = 'Binary2'
input_dict2['mapping'] = pd.Series(data=['G', 'H', np.nan],
index=['G', 'H', 'missing'])
input_dict2['data_type'] = 'object'
input_dict = dict()
input_dict['col'] = 'state'
input_dict['mapping'] = pd.Series(data=['US', 'FR-1', 'FR-2'],
index=['US', 'FR', 'FR'])
input_dict['data_type'] = 'object'
input_dict3 = dict()
input_dict3['col'] = 'Ordinal2'
input_dict3['mapping'] = pd.Series(data=['K', 'L', np.nan],
index=['K', 'L', 'missing'])
input_dict3['data_type'] = 'object'
list_dict = [input_dict2, input_dict3]
y = pd.DataFrame(data=[0, 1], columns=['y'])
train = pd.DataFrame({
'city': ['chicago', 'paris'],
'state': ['US', 'FR'],
'other': ['A', 'B']
})
enc = ColumnTransformer(transformers=[('onehot', skp.OneHotEncoder(),
['city', 'state'])],
remainder='drop')
enc.fit(train, y)
wrong_prepro = skp.OneHotEncoder().fit(train, y)
predictor_1.preprocessing = [
enc_onehot, enc_binary, enc_ordinal, enc_basen, enc_target,
input_dict1, list_dict
]
predictor_1.check_preprocessing()
for preprocessing in [
enc_onehot, enc_binary, enc_ordinal, enc_basen, enc_target
]:
predictor_1.preprocessing = preprocessing
predictor_1.check_preprocessing()
predictor_1.preprocessing = input_dict2
predictor_1.check_preprocessing()
predictor_1.preprocessing = enc
predictor_1.check_preprocessing()
predictor_1.preprocessing = None
predictor_1.check_preprocessing()
with self.assertRaises(Exception):
predictor_1.preprocessing = wrong_prepro
predictor_1.check_preprocessing()
from scoring import calculate_scores
VAL_SPLIT = 0.2
data = get_data(val_split=VAL_SPLIT, apply_label_encoding=True, fillna=True)
X_train, X_val, X_test, y_train, y_val, categorical_features = (
data["X_train"],
data["X_val"],
data["X_test"],
data["y_train"],
data["y_val"],
data["categorical_features"],
)
clf = cb.CatBoostClassifier(
n_estimators=200,
learning_rate=0.05,
metric_period=500,
od_wait=500,
task_type="CPU",
depth=8,
)
print("Fitting a catboost model...")
clf.fit(X_train, y_train, cat_features=categorical_features)
_ = calculate_scores(clf, X_val, y_val)
for scoring in SCORING_LIST:
print("Optimizing catboost params for", scoring, "with random search...")
best_estimator = perform_random_search(
estimator=clf,
X_train=X_train,
X_val=X_val,
def objective(trial):
#--------------------------------------------
# ベイズ最適化でのチューニングパイパーパラメーター
#--------------------------------------------
if (args.classifier == "logistic"):
params = {
'penalty': trial.suggest_categorical('penalty', ['l2']),
"solver": trial.suggest_categorical("solver", ['sag']),
'C': trial.suggest_discrete_uniform('C', 0.01, 100.0,
0.1), # 一様分布に従う。
'random_state': trial.suggest_int("random_state", 71, 71),
'n_jobs': trial.suggest_int("n_jobs", -1, -1),
}
elif (args.classifier == "knn"):
params = {
"metric": trial.suggest_categorical("metric", ['minkowski']),
"p": trial.suggest_int("p", 1, 2),
'n_neighbors': trial.suggest_int("n_neighbors", 1, 50),
'n_jobs': trial.suggest_int("n_jobs", -1, -1),
}
elif (args.classifier == "svm"):
params = {
"kernel": trial.suggest_categorical("kernel", ['rbf']),
'C': trial.suggest_loguniform('C', 0.1, 1000.0),
'gamma': trial.suggest_loguniform('gamma', 1e-8, 10.0),
'random_state': trial.suggest_int("random_state", 71, 71),
}
elif (args.classifier == "random_forest"):
params = {
"oob_score":
trial.suggest_int(
"oob_score", 0, 1
), # Whether to use out-of-bag samples to estimate the generalization accuracy.(default=False)
"n_estimators":
trial.suggest_int("n_estimators", 1000, 1000), # チューニングは固定
"criterion":
trial.suggest_categorical(
"criterion", ['gini', "entropy"]), # 不純度関数 [purity]
'max_features':
trial.suggest_categorical('max_features', [
'auto',
0.2,
0.4,
0.6,
0.8,
]),
'min_samples_split':
trial.suggest_int(
'min_samples_split', 2, 10
), # min_samples_split must be an integer greater than 1 or a float in (0.0, 1.0]; got the integer 1
'min_samples_leaf':
trial.suggest_int('min_samples_leaf', 1, 10),
"bootstrap":
trial.suggest_int(
"bootstrap", True,
True), # 決定木の構築に、ブートストラップサンプルを使用するか否か（default:True）
"oob_score":
trial.suggest_int(
"oob_score", False, True
), # Whether to use out-of-bag samples to estimate the generalization accuracy.(default=False)
'random_state':
trial.suggest_int("random_state", 71, 71),
'n_jobs':
trial.suggest_int("n_jobs", -1, -1),
}
elif (args.classifier == "bagging"):
params = {
"n_estimators":
trial.suggest_int("n_estimators", 1000, 1000), # チューニングは固定
'max_samples':
trial.suggest_float(
'max_samples', 0.0,
1.0), # base_estimator に設定した弱識別器の内, 使用するサンプルの割合
'max_features':
trial.suggest_float(
'max_features', 0.0, 1.0
), # The number of features to draw from X to train each base estimator.
"bootstrap":
trial.suggest_int(
"bootstrap", True,
True), # 決定木の構築に、ブートストラップサンプルを使用するか否か（default:True）
"bootstrap_features":
trial.suggest_int("bootstrap", False, True),
'random_state':
trial.suggest_int("random_state", 71, 71),
'n_jobs':
-1,
# 弱識別器のパラメータ（先頭に "base_estimator__" をつけることでアクセス可能 ）
'base_estimator__max_depth':
trial.suggest_int("base_estimator__random_state", 1, 8),
'base_estimator__max_features':
trial.suggest_float('base_estimator__max_features', 0.0, 1.0),
'base_estimator__min_samples_leaf':
trial.suggest_int('base_estimator__min_samples_leaf', 1, 10),
'base_estimator__min_samples_split':
trial.suggest_int('base_estimator__min_samples_split', 2, 10),
'base_estimator__random_state':
trial.suggest_int("base_estimator__random_state", 71, 71),
}
elif (args.classifier == "adaboost"):
params = {
"n_estimators":
trial.suggest_int("n_estimators", 1000, 1000), # チューニングは固定
"learning_rate":
trial.suggest_loguniform("learning_rate", 0.01,
0.01), # ハイパーパラメーターのチューニング時は固定
'random_state':
71,
# 弱識別器のパラメータ（先頭に "base_estimator__" をつけることでアクセス可能 ）
'base_estimator__max_depth':
trial.suggest_int("base_estimator__random_state", 1, 10),
'base_estimator__max_features':
trial.suggest_float('base_estimator__max_features', 0.0, 1.0),
'base_estimator__min_samples_leaf':
trial.suggest_int('base_estimator__min_samples_leaf', 1, 10),
'base_estimator__min_samples_split':
trial.suggest_int('base_estimator__min_samples_split', 2, 10),
'base_estimator__random_state':
trial.suggest_int("base_estimator__random_state", 71, 71),
}
elif (args.classifier == "xgboost"):
params = {
'booster':
trial.suggest_categorical('booster', ['gbtree']),
'objective':
trial.suggest_categorical('objective', ['binary:logistic']),
"learning_rate":
trial.suggest_loguniform("learning_rate", 0.01,
0.01), # ハイパーパラメーターのチューニング時は固定
"n_estimators":
trial.suggest_int("n_estimators", 1000,
1000), # ハイパーパラメーターのチューニング時は固定
'max_depth':
trial.suggest_int("max_depth", 3, 9), # 3 ~ 9 : 一様分布に従う。1刻み
'min_child_weight':
trial.suggest_loguniform('min_child_weight', 0.1,
10.0), # 0.1 ~ 10.0 : 対数が一様分布に従う
'subsample':
trial.suggest_discrete_uniform(
'subsample', 0.6, 0.95,
0.05), # 0.6 ~ 0.95 : 一様分布に従う。0.05 刻み
'colsample_bytree':
trial.suggest_discrete_uniform(
'colsample_bytree', 0.6, 0.95,
0.05), # 0.6 ~ 0.95 : 一様分布に従う。0.05 刻み
'gamma':
trial.suggest_loguniform("gamma", 1e-8,
1.0), # 1e-8 ~ 1.0 : 対数が一様分布に従う
'alpha':
trial.suggest_float("alpha", 0.0, 0.0), # デフォルト値としておく。余裕があれば変更
'reg_lambda':
trial.suggest_float("reg_lambda", 1.0,
1.0), # デフォルト値としておく。余裕があれば変更
'random_state':
trial.suggest_int("random_state", 71, 71),
}
elif (args.classifier == "lightgbm"):
params = {
'boosting_type':
trial.suggest_categorical('boosting',
['gbdt', 'dart', 'goss']),
'objective':
'binary',
'metric':
'binary_logloss',
'num_class':
1,
'num_leaves':
trial.suggest_int("num_leaves", 10, 500),
'learning_rate':
trial.suggest_loguniform("learning_rate", 0.01, 0.01),
'max_depth':
trial.suggest_int("max_depth", 1, 5),
'reg_alpha':
trial.suggest_uniform("reg_alpha", 0, 100),
'reg_lambda':
trial.suggest_uniform("reg_lambda", 1, 5),
'num_leaves':
trial.suggest_int("num_leaves", 10, 500),
'verbose':
0,
}
elif (args.classifier == "catboost"):
params = {
'eval_metric':
trial.suggest_categorical('eval_metric', ['Accuracy']),
'iterations':
trial.suggest_int('iterations', 1000, 1000), # まず大きな数を設定しておく
'learning_rate':
trial.suggest_loguniform('learning_rate', 0.01, 0.01),
'depth':
trial.suggest_int('depth', 4, 10),
'random_strength':
trial.suggest_int('random_strength', 0, 100),
'bagging_temperature':
trial.suggest_loguniform('bagging_temperature', 0.01, 100.00),
'od_type':
trial.suggest_categorical('od_type', ['IncToDec', 'Iter']),
'od_wait':
trial.suggest_int('od_wait', 100,
100), # 最適な指標値に達した後、iterationを続ける数。
'random_state':
trial.suggest_int("random_state", 71, 71),
}
#--------------------------------------------
# stratified k-fold CV での評価
#--------------------------------------------
y_preds_train = np.zeros((len(y_train), ))
# k-hold cross validation で、学習用データセットを学習用と検証用に分割したもので評価
kf = StratifiedKFold(n_splits=args.n_splits_gs,
shuffle=True,
random_state=args.seed)
k = 0
for fold_id, (train_index,
valid_index) in enumerate(kf.split(X_train, y_train)):
# seed 値の固定
np.random.seed(args.seed + k)
random.seed(args.seed + k)
#--------------------
# データセットの分割
#--------------------
X_train_fold, X_valid_fold = X_train.iloc[
train_index], X_train.iloc[valid_index]
y_train_fold, y_valid_fold = y_train.iloc[
train_index], y_train.iloc[valid_index]
#--------------------
# モデルの定義
#--------------------
if (args.classifier == "logistic"):
model = SklearnClassifier(
LogisticRegression(penalty='l2',
solver="sag",
random_state=args.seed))
elif (args.classifier == "knn"):
model = SklearnClassifier(
KNeighborsClassifier(n_neighbors=3,
p=2,
metric='minkowski'))
elif (args.classifier == "svm"):
model = SklearnClassifier(SVC(kernel='rbf', gamma=0.1, C=10.0))
elif (args.classifier == "random_forest"):
model = SklearnClassifier(
RandomForestClassifier(criterion="gini",
bootstrap=True,
oob_score=True,
n_estimators=1000,
n_jobs=-1,
random_state=args.seed))
elif (args.classifier == "bagging"):
model = SklearnClassifier(
BaggingClassifier(
DecisionTreeClassifier(criterion='entropy',
max_depth=None,
random_state=args.seed)))
elif (args.classifier == "adaboost"):
model = SklearnClassifier(
AdaBoostClassifier(
DecisionTreeClassifier(criterion='entropy',
max_depth=None,
random_state=args.seed)))
elif (args.classifier == "xgboost"):
model = XGBoostClassifier(model=xgb.XGBClassifier(
booster='gbtree',
objective='binary:logistic',
eval_metric='logloss',
learning_rate=0.01),
train_type=args.train_type,
use_valid=True,
debug=args.debug)
elif (args.classifier == "lightgbm"):
model = LightGBMClassifier(model=lgb.LGBMClassifier(
objective='binary', metric='binary_logloss'),
train_type=args.train_type,
use_valid=True,
debug=args.debug)
elif (args.classifier == "catboost"):
model = CatBoostClassifier(
model=catboost.CatBoostClassifier(loss_function="Logloss"),
use_valid=True,
debug=args.debug)
# モデルのチューニングパラメータ設定
model.set_params(**params)
#--------------------
# モデルの学習処理
#--------------------
model.fit(X_train_fold, y_train_fold, X_valid_fold, y_valid_fold)
#--------------------
# モデルの推論処理
#--------------------
y_pred_train[valid_index] = model.predict(X_valid_fold)
k += 1
accuracy = (y_train == y_pred_train).sum() / len(y_pred_train)
return accuracy
train3 = data[(data['date']>=20170929)&(data['date']<20171011)] train4 = data[(data['date']>=20171011)&(data['date']<20171023)] train5 = data[(data['date']>=20171023)&(data['date']<=20171105)] gbm1 = lgb.LGBMClassifier(max_depth=7, n_estimators = 110, min_child_samples=100) gbm2 = lgb.LGBMClassifier(max_depth=7, n_estimators = 110, min_child_samples=100) gbm3 = lgb.LGBMClassifier(max_depth=7, n_estimators = 110, min_child_samples=100) gbm4 = lgb.LGBMClassifier(max_depth=7, n_estimators = 110, min_child_samples=100) gbm5 = lgb.LGBMClassifier(max_depth=7, n_estimators = 110, min_child_samples=100) gbm1.fit(train1[feat_name], train1['label']) gbm2.fit(train2[feat_name], train2['label']) gbm3.fit(train3[feat_name], train3['label']) gbm4.fit( train4[feat_name], train4['label']) gbm5.fit( train5[feat_name], train5['label']) cb1 = cat.CatBoostClassifier(iterations=110,learning_rate=0.1,depth=7) cb2 = cat.CatBoostClassifier(iterations=110,learning_rate=0.1,depth=7) cb3 = cat.CatBoostClassifier(iterations=110,learning_rate=0.1,depth=7) cb4 = cat.CatBoostClassifier(iterations=110,learning_rate=0.1,depth=7) cb5 = cat.CatBoostClassifier(iterations=110,learning_rate=0.1,depth=7) cb1.fit(train1[feat_name], train1['label'],verbose=20) cb2.fit(train2[feat_name], train2['label'],verbose=20) cb3.fit(train3[feat_name], train3['label'],verbose=20) cb4.fit(train4[feat_name], train4['label'],verbose=20) cb5.fit(train5[feat_name], train5['label'],verbose=20) xg1 = xgb.XGBClassifier(max_depth=7, n_estimators=110, silent=False) xg2 = xgb.XGBClassifier(max_depth=7, n_estimators=110, silent=False) xg3 = xgb.XGBClassifier(max_depth=7, n_estimators=110, silent=False) xg4 = xgb.XGBClassifier(max_depth=7, n_estimators=110, silent=False) xg5 = xgb.XGBClassifier(max_depth=7, n_estimators=110, silent=False)
return result
# In[ ]:
# In[26]:
df_res = pd.DataFrame()
# In[27]:
import catboost as cat
clf_cbt = cat.CatBoostClassifier(iterations=2500,
learning_rate=0.01,
depth=6,
verbose=True,
thread_count=12,
colsample_bylevel=0.8,
l2_leaf_reg=1,
random_seed=1024)
df_res['result_1'] = cbt_model(clf_cbt, model_train_s_1, online_train,
feature_list)
df_res['result_2'] = cbt_model(clf_cbt, model_train_s_2, online_train,
feature_list)
df_res['result_3'] = cbt_model(clf_cbt, model_train_s_3, online_train,
feature_list)
df_res['result_4'] = cbt_model(clf_cbt, model_train_s_4, online_train,
feature_list)
skf = StratifiedKFold(n_splits=N_SPLITS, shuffle=True, random_state=SEED)
for fold, (train_idx,
valid_idx) in enumerate(skf.split(all_df, all_df[TARGET])):
print(f"===== FOLD {fold} =====")
oof_idx = np.array([idx for idx in valid_idx if idx < train_df.shape[0]])
preds_idx = np.array(
[idx for idx in valid_idx if idx >= train_df.shape[0]])
X_train, y_train = all_df.iloc[train_idx].drop(
TARGET, axis=1), all_df.iloc[train_idx][TARGET]
X_valid, y_valid = all_df.iloc[oof_idx].drop(
TARGET, axis=1), all_df.iloc[oof_idx][TARGET]
X_test = all_df.iloc[preds_idx].drop(TARGET, axis=1)
model = ctb.CatBoostClassifier(**params)
model.fit(X_train,
y_train,
eval_set=[(X_valid, y_valid)],
use_best_model=True,
early_stopping_rounds=EARLY_STOPPING_ROUNDS,
verbose=VERBOSE)
fi_tmp = pd.DataFrame()
fi_tmp["feature"] = X_test.columns.to_list()
fi_tmp["importance"] = model.get_feature_importance()
fi_tmp["fold"] = fold
fi_tmp["seed"] = SEED
feature_importances = feature_importances.append(fi_tmp)
ctb_oof[oof_idx] = model.predict(X_valid)
if( args.debug ):
print( "X_train_fold.shape : ", X_train_fold.shape )
print( "X_valid_fold.shape : ", X_valid_fold.shape )
print( "y_train_fold.shape : ", y_train_fold.shape )
print( "y_valid_fold.shape : ", y_valid_fold.shape )
#--------------------
# モデルの定義
#--------------------
models = []
for c, classifier in enumerate(args.classifiers):
if( classifier == "svm" ):
model = SklearnImageClassifier( SVC( kernel = 'rbf', gamma = 0.1, C = 10.0 ) )
elif( classifier == "catboost" ):
if( args.device == "gpu" ):
model = CatBoostImageClassifier( model = catboost.CatBoostClassifier( loss_function="MultiClass", iterations = 1000, task_type="GPU", devices='0:1' ), use_valid = True, debug = args.debug ) # iterations = (trees / (epochs * batches)
else:
model = CatBoostImageClassifier( model = catboost.CatBoostClassifier( loss_function="MultiClass", iterations = 1000 ), use_valid = True, debug = args.debug )
elif( classifier == "mlp" ):
model = KerasMLPImageClassifier(
n_input_dim = X_train_fold.shape[1] * X_train_fold.shape[2] * X_train_fold.shape[3], n_classes = args.n_classes,
n_epoches = args.n_epoches, batch_size = args.batch_size, lr = args.lr, beta1 = args.beta1, beta2 = args.beta2,
use_valid = True, one_hot_encode = True, callbacks = None, use_datagen = False, datagen = datagen, debug = args.debug
)
elif( classifier == "resnet50" ):
model = KerasResNet50ImageClassifier(
image_height = args.image_height, image_width = args.image_width, n_channles = 3, n_classes = args.n_classes,
n_epoches = args.n_epoches, batch_size = args.batch_size, lr = args.lr, beta1 = args.beta1, beta2 = args.beta2,
pretrained = False, train_only_fc = False,
use_valid = True, one_hot_encode = True, callbacks = None, use_datagen = True, datagen = datagen, debug = args.debug
)
def Catboost_crossvalidated_model(max_depths,
n_estimators,
colsample_bytrees,
Xtrain,
Ytrain,
nfold,
feature_selection=0,
nthread=8):
'''Function returns a cross-validated hyper parameter tuned model for the training data
Arguments:
max_depths: options for maximum depth eg: input [6,10,13], this will choose the best max_depth among the three
n_estimators: best number of estimators to be chosen from this. eg: [200,150,100]
colsample_bytrees: eg. input [0.4,0.8]
nfold: Number of folds for cross-validated
Xtrain, Ytrain: Training features and labels
feature_selection : 0 means feature_selection diabled and 1 otherswise. If 1 then a second output is returned which consists of the selected features
Output:
model: Trained model with good hyper-parameters
features : Coordinates of selected features, if feature_selection = 0
bp: Dictionary of tuned parameters
This procedure is CPU intensive. So, it is advised to not provide too many choices of hyper-parameters
'''
classifiers = {}
model = catboost.CatBoostClassifier(thread_count=nthread,
learning_rate=0.02,
iterations=100,
depth=6,
subsample=0.8,
random_seed=11)
#model = xgb.XGBClassifier( nthread=nthread, learning_rate =0.02, n_estimators=100, max_depth=6,min_child_weight=1, gamma=0, subsample=0.8, colsample_bytree=0.8,objective= 'binary:logistic',scale_pos_weight=1, seed=11)
model.fit(Xtrain, Ytrain)
m, n = Xtrain.shape
bp = {'max_depth': [0], 'n_estimator': [0]}
classifiers['model'] = catboost.CatBoostClassifier(thread_count=nthread,
learning_rate=0.02,
iterations=100,
depth=6,
subsample=0.8,
random_seed=11)
#classifiers['model'] = xgb.XGBClassifier( nthread = nthread, learning_rate =0.02, n_estimators=100, max_depth=6,min_child_weight=1, gamma=0, subsample=0.8, colsample_bytree=0.9,objective= 'binary:logistic',scale_pos_weight=1, seed=11)
classifiers['train_X'] = Xtrain
classifiers['train_y'] = Ytrain
maxi = 0
pos = 0
for r in max_depths:
classifiers['model'] = catboost.CatBoostClassifier(
thread_count=nthread,
learning_rate=0.02,
iterations=100,
depth=r,
subsample=0.8,
random_seed=11)
#classifiers['model'] = xgb.XGBClassifier( nthread=nthread,learning_rate =0.02, n_estimators=100, max_depth=r,min_child_weight=1, gamma=0, subsample=0.8, colsample_bytree=0.8,objective= 'binary:logistic',scale_pos_weight=1, seed=11)
score = cross_validate(classifiers, nfold)
if maxi < score:
maxi = score
pos = r
bp['max_depth'] = pos
#print pos
maxi = 0
pos = 0
for r in n_estimators:
classifiers['model'] = catboost.CatBoostClassifier(
thread_count=nthread,
learning_rate=0.02,
iterations=r,
depth=bp['max_depth'],
subsample=0.8,
random_seed=11)
#classifiers['model'] = xgb.XGBClassifier( nthread=nthread,learning_rate =0.02, n_estimators=r, max_depth=bp['max_depth'],min_child_weight=1, gamma=0, subsample=0.8, colsample_bytree=0.8,objective= 'binary:logistic',scale_pos_weight=1, seed=11)
score = cross_validate(classifiers, nfold)
if maxi < score:
maxi = score
pos = r
bp['n_estimator'] = pos
#print pos
classifiers['model'] = catboost.CatBoostClassifier(
thread_count=nthread,
learning_rate=0.02,
iterations=bp['n_estimator'],
depth=bp['max_depth'],
subsample=0.8,
random_seed=11)
#model = xgb.XGBClassifier( nthread=nthread,learning_rate =0.02, n_estimators=bp['n_estimator'], max_depth=bp['max_depth'],min_child_weight=1, gamma=0, subsample=0.8, colsample_bytree=bp['colsample_bytree'],objective= 'binary:logistic',scale_pos_weight=1, seed=11).fit(Xtrain,Ytrain)
return model, bp
verbose_eval = 30
num_rounds = 800
folds = 3
kf = KFold(n_splits=folds, shuffle=True, random_state=seed + 1)
y_preds3 = np.zeros(X_test.shape[0])
feature_importance_df = pd.DataFrame()
i = 0
for tr_idx, val_idx in kf.split(X_train, y_train):
X_tr = X_train[features].iloc[tr_idx, :].fillna(-1)
y_tr = y_train.iloc[tr_idx]
model = cb.CatBoostClassifier(iterations=num_rounds,
depth=14,
learning_rate=0.04,
loss_function='Logloss',
eval_metric='Logloss',
task_type="GPU")
if debug:
model.fit(X_tr, y_tr, cat_features=cate, verbose_eval=30)
else:
model.fit(X_tr, y_tr, cat_features=cate, verbose_eval=30)
del X_tr
y_preds3 += model.predict_proba(X_test[features].fillna(-1))[:, 1] / folds
if debug:
print(
"debug:",
roc_auc_score(
y_test,
def CatBoost_CV():
# Get csv data
data = pd.read_csv(cf.base_dir + cf.prepared_data_real_comb)
X = data.drop(['0'], axis=1)
y = data[['0']].values.ravel()
# Feature Scaling
StdScaler = StandardScaler()
X_scaled = StdScaler.fit_transform(X)
# Splitting the dataset into the Training set and Test set
X_Train, x_test, Y_Train, y_test = train_test_split(X_scaled,
y,
test_size=0.5,
random_state=0)
# Number of trees in random forest
iterations = [int(x) for x in np.linspace(start=200, stop=2000, num=5)]
# Number of features to consider at every split
learning_rate = [x for x in np.linspace(start=0.01, stop=0.1, num=5)]
# Maximum number of levels in tree
depth = [int(x) for x in np.linspace(6, 10, num=4)]
# Minimum number of samples required to split a node
l2_leaf_reg = [x for x in np.linspace(start=0.01, stop=0.1, num=5)]
# Minimum number of samples required at each leaf node
# per_float_feature_quantization = ['0:border_count=1024', '1:border_count=1024']
# Method of selecting samples for training each tree
bootstrap = [True, False]
random_grid = {
'iterations': iterations,
'learning_rate': learning_rate,
'depth': depth,
'l2_leaf_reg': l2_leaf_reg
}
#'per_float_feature_quantization': per_float_feature_quantization}
clf = cb.CatBoostClassifier(random_state=0,
border_count=255,
task_type='GPU')
# import multiprocessing
# cores = multiprocessing.cpu_count()-1
rf_random = RandomizedSearchCV(estimator=clf,
param_distributions=random_grid,
n_iter=5,
cv=3,
verbose=10,
random_state=42,
n_jobs=1)
# Fit the random search model
start_time = time.time() # Time counter
print(
"Started at ",
datetime.utcfromtimestamp(int(
time.time())).strftime('%Y-%m-%d %H:%M:%S'))
rf_random.fit(X_Train, Y_Train)
best_p = rf_random.best_params_
best_r = rf_random.best_score_
print(best_p, best_r)
train_pred3 = (model.predict_proba(X))[:,1]
train_pred3.shape
# In[356]:
params = {'depth': [2, 4, 7, 10],
'learning_rate' : [0.03, 0.1, 0.15],
'l2_leaf_reg': [1,4,9],
'iterations': [300]
'loss_function': 'logloss'
}
#如果选取的参数组比较多的话，需要的时间特别久，以此模型下的ks值为例可以明显看出过拟合严重，
#故手动调整参数在实际应用中更为合适
cb = ct.CatBoostClassifier(eval_metric="AUC", random_seed=741)
cb_model = GridSearchCV(cb, params, scoring="roc_auc", cv = 3)
cb_model.fit(X, Y)
#clf = ct.CatBoostClassifier(eval_metric="AUC", depth=10, iterations= 300, l2_leaf_reg= 9, learning_rate= 0.15)
#clf.fit(X,Y)
# In[382]:
cat_features_index = 2
clf = ct.CatBoostClassifier(eval_metric="AUC", depth=8, iterations= 300, l2_leaf_reg= 10, learning_rate= 0.008)#学习率越大越过拟
clf.fit(X,Y)
preds_class = clf.predict(P_test)
preds_probs = clf.predict_proba(P_test)
print('class = ',preds_class)
def model_cbt(features, test_features, encoding='ohe', n_folds=5):
# 提取ID
train_ids = features['cust_no']
test_ids = test_features['cust_no']
# 提取训练集的结果
labels = features['label']
# 移除ID和target
features = features.drop(columns=['cust_no', 'label'])
test_features = test_features.drop(columns=['cust_no'])
one_hot = OneHotEncoder(3, sparse=False)
# One Hot Encoding
if encoding == 'ohe':
features = pd.get_dummies(features)
test_features = pd.get_dummies(test_features)
features, test_features = features.align(test_features,
join='inner',
axis=1)
cat_indices = 'auto'
# Integer label encoding
elif encoding == 'le':
label_encoder = LabelEncoder()
cat_indices = []
for i, col in enumerate(features):
if features[col].dtype == 'object':
features[col] = label_encoder.fit_transform(
np.array(features[col].astype(str)).reshape((-1, )))
test_features[col] = label_encoder.transform(
np.array(test_features[col].astype(str)).reshape((-1, )))
cat_indices.append(i)
else:
raise ValueError("Encoding must be either 'ohe' or 'le'")
features = features[important_features]
test_features = test_features[important_features]
print('Training Data Shape: ', features.shape)
print('Testing Data Shape: ', test_features.shape)
feature_names = list(features.columns)
features = np.array(features)
test_features = np.array(test_features)
features[np.isnan(features)] = -1000000
features[np.where(features >= np.finfo(np.float64).max)] = -1000000
test_features[np.isnan(test_features)] = -1000000
test_features[np.where(
test_features >= np.finfo(np.float64).max)] = -1000000
k_fold = StratifiedKFold(n_splits=n_folds, shuffle=True, random_state=50)
feature_importance_values = np.zeros(len(feature_names))
test_predictions = np.zeros((test_features.shape[0], 3))
out_of_fold = np.zeros((features.shape[0], 3))
# print(out_of_fold)
valid_scores = []
train_scores = []
for train_indices, valid_indices in k_fold.split(features, labels):
train_features, train_labels = features[train_indices], labels[
train_indices]
valid_features, valid_labels = features[valid_indices], labels[
valid_indices]
train_labels += 1
valid_labels += 1
train_features, train_labels = SMOTE().fit_sample(
train_features, train_labels)
# 建模
model = cbt.CatBoostClassifier(random_seed=2020,
iterations=1500,
learning_rate=0.1,
max_depth=11,
l2_leaf_reg=1,
verbose=1,
early_stopping_rounds=20,
task_type='CPU',
eval_metric='Kappa')
# 训练模型 eval_metric=lambda y_true, y_pred: [custom_kappa_eval(y_true, y_pred)]
model.fit(train_features,
train_labels,
eval_set=[(valid_features, valid_labels)],
early_stopping_rounds=20,
verbose=True)
# 特征重要性
feature_importance_values += model.feature_importances_ / k_fold.n_splits
# 做预测
test_predictions += model.predict_proba(
test_features)[:, :] / k_fold.n_splits
out_of_fold[valid_indices] = model.predict_proba(valid_features)[:, :]
valid_score = accuracy_score(
valid_labels, np.argmax(out_of_fold[valid_indices], axis=1))
train_score = accuracy_score(
train_labels,
np.argmax(model.predict_proba(train_features)[:, :], axis=1))
valid_scores.append(valid_score)
train_scores.append(train_score)
gc.enable()
del model, train_features, valid_features
gc.collect()
y_pred = np.argmax(test_predictions, axis=1) - 1
test_predictions = pd.DataFrame({
'cust_no': test_ids,
'-1': test_predictions[:, 0],
'0': test_predictions[:, 1],
'1': test_predictions[:, 2]
})
print(y_pred)
submission = pd.DataFrame({'cust_no': test_ids, 'label': y_pred})
feature_importances = pd.DataFrame({
'feature': feature_names,
'importance': feature_importance_values
})
fold_names = list(range(n_folds))
fold_names.append('overall')
valid_auc = accuracy_score(labels + 1, np.argmax(out_of_fold, axis=1))
valid_scores.append(valid_auc)
train_scores.append(np.mean(train_scores))
metrics = pd.DataFrame({
'fold': fold_names,
'train': train_scores,
'valid': valid_scores
})
return submission, feature_importances, metrics, test_predictions
def Model_Search_Catboost_cv(X,
y,
cat_features=None,
model='binary',
folds=5,
sklearn_metric=None,
catboost_metric=None,
step_wise_start_at=0,
final_learning_rate=0.01,
use_optuna=False,
direction='minimize',
n_trials=20,
load_study_from=None,
save_study_as=None,
n_jobs=4):
# model
if isinstance(model, str):
if model == 'binary':
model = catboost.CatBoostClassifier(loss_function='Logloss',
thread_count=n_jobs)
elif model == 'multiclass':
model = catboost.CatBoostClassifier(loss_function='MultiClass',
thread_count=n_jobs)
elif model == 'regression':
model = catboost.CatBoostRegressor(loss_function='RMSE',
thread_count=n_jobs)
else:
sys.exit('Error: Unkown model type.')
# sklearn_metric
if sklearn_metric is None: # https://scikit-learn.org/stable/modules/model_evaluation.html
if isinstance(model, catboost.CatBoostClassifier):
sklearn_metric = 'neg_log_loss'
elif isinstance(model, catboost.CatBoostRegressor):
sklearn_metric = 'neg_root_mean_squared_error'
else:
sys.exit('Error: Sklearn score metric needs to be provided.')
# catboost_metric
if catboost_metric is not None: # https://catboost.ai/docs/concepts/loss-functions.html
model.set_params(loss_function=catboost_metric)
# folds
if isinstance(folds, int):
if isinstance(model, lightgbm.LGBMClassifier):
folds = StratifiedKFold(n_splits=folds,
shuffle=True,
random_state=42)
else:
folds = KFold(n_splits=folds, shuffle=True, random_state=42)
# ------------------------------------------------------------------------------------------------
# Set fixed params
fixed_params = {
"verbose": False,
"random_state": 42,
"iterations": 10000,
}
model.set_params(**fixed_params)
# Set dataset for .cv
d_train = catboost.Pool(X, label=y, cat_features=cat_features)
# ------------------------------------------------------------------------------------------------
if use_optuna:
print("Searching for a Catboost model with optuna \n")
params = model.get_params()
if load_study_from is not None:
study = joblib.load(load_study_from)
else:
study = optuna.create_study(
direction=direction,
pruner=optuna.pruners.SuccessiveHalvingPruner())
def objetive(trial):
params.update({
"boosting_type":
trial.suggest_categorical("boosting_type",
['Ordered', 'Plain']),
"learning_rate":
trial.suggest_loguniform("learning_rate", 0.005, 0.1),
"max_depth":
trial.suggest_int("max_depth", 4, 12),
"l2_leaf_reg":
trial.suggest_loguniform("l2_leaf_reg", 1e-4, 1e4),
"border_count":
trial.suggest_int('border_count', 1, 255),
"random_strength":
trial.suggest_loguniform("random_strength", 1e-4, 1e4),
"bagging_temperature":
trial.suggest_loguniform("bagging_temperature", 1e-4, 1e4),
})
cv_results = catboost.cv(params=params,
pool=d_train,
iterations=10000,
early_stopping_rounds=50,
folds=folds,
verbose_eval=None,
as_pandas=False)
rmetric_name = list(cv_results.keys())[1]
score = cv_results[rmetric_name][
-1] # np.min(cv_results[rmetric_name])
print("Num_boost_round: " + str(len(cv_results[rmetric_name])))
if save_study_as is not None:
joblib.dump(study, save_study_as)
return score
study.optimize(objetive, n_trials=n_trials, n_jobs=1)
print(
"------------------------------------------------------------------------"
)
print("Best parameters found: " + str(study.best_params))
print("Best score achived: " + str(study.best_value))
print(
"------------------------------------------------------------------------"
)
model.set_params(**study.best_params)
# num_boost_round optimization
cv_results = catboost.cv(params=model.get_params(),
pool=d_train,
iterations=10000,
early_stopping_rounds=50,
folds=folds,
verbose_eval=None,
as_pandas=False)
rmetric_name = list(cv_results.keys())[1]
best_boost_round = len(cv_results[rmetric_name])
best_score_achived = cv_results[rmetric_name][-1]
print("Best num_boost_round: " + str(best_boost_round))
print("Best score achived: " + str(best_score_achived))
print(
"------------------------------------------------------------------------"
)
model.set_params(iterations=best_boost_round)
else:
print("Searching for a Catboost model with the step wise method \n")
if step_wise_start_at <= 0:
# num_boost_round optimization
cv_results = catboost.cv(params=model.get_params(),
pool=d_train,
iterations=10000,
early_stopping_rounds=50,
folds=folds,
verbose_eval=None,
as_pandas=False)
rmetric_name = list(cv_results.keys())[1]
best_boost_round = len(cv_results[rmetric_name])
best_score_achived = cv_results[rmetric_name][-1]
print(
"------------------------------------------------------------------------"
)
print("Best num_boost_round: " + str(best_boost_round))
print("Best score achived: " + str(best_score_achived))
print(
"------------------------------------------------------------------------"
)
model.set_params(iterations=best_boost_round)
# Param search
if step_wise_start_at <= 1:
param_test = {'max_depth': range(2, 11, 1)}
search = GridSearchCV(estimator=model,
param_grid=param_test,
scoring=sklearn_metric,
n_jobs=n_jobs,
iid=False,
cv=folds,
verbose=True)
search.fit(X, y, cat_features=cat_features)
print("Best params encountered: " + str(search.best_params_))
print("Best score achived: " + str(search.best_score_))
print(
"------------------------------------------------------------------------"
)
pipe_model = search.best_estimator_
if step_wise_start_at <= 2:
param_test = {
'l2_leaf_reg': [
0, 0.0001, 0.001, 0.004, 0.007, 0.01, 0.04, 0.07, 1, 2, 3,
4, 7, 10
]
}
search = GridSearchCV(estimator=model,
param_grid=param_test,
scoring=sklearn_metric,
n_jobs=n_jobs,
iid=False,
cv=folds,
verbose=True)
search.fit(X, y, cat_features=cat_features)
print("Best params encountered: " + str(search.best_params_))
print("Best score achived: " + str(search.best_score_))
print(
"------------------------------------------------------------------------"
)
pipe_model = search.best_estimator_
if step_wise_start_at <= 3:
param_test = {
'random_strength':
[0, 0.001, 0.01, 0.04, 0.07, 0.1, 0.4, 0.7, 1, 4, 7, 10]
}
search = GridSearchCV(estimator=model,
param_grid=param_test,
scoring=sklearn_metric,
n_jobs=n_jobs,
iid=False,
cv=folds,
verbose=True)
search.fit(X, y, cat_features=cat_features)
print("Best params encountered: " + str(search.best_params_))
print("Best score achived: " + str(search.best_score_))
print(
"------------------------------------------------------------------------"
)
pipe_model = search.best_estimator_
if step_wise_start_at <= 4:
param_test = {
'bagging_temperature': [
0, 0.001, 0.01, 0.04, 0.07, 0.1, 0.4, 0.7, 1, 4, 7, 10, 30,
60, 90, 120
]
}
search = GridSearchCV(estimator=model,
param_grid=param_test,
scoring=sklearn_metric,
n_jobs=n_jobs,
iid=False,
cv=folds,
verbose=True)
search.fit(X, y, cat_features=cat_features)
print("Best params encountered: " + str(search.best_params_))
print("Best score achived: " + str(search.best_score_))
print(
"------------------------------------------------------------------------"
)
pipe_model = search.best_estimator_
if step_wise_start_at <= 5:
param_test = {
'border_count': [32, 5, 10, 20, 50, 100, 150, 200, 255]
}
search = GridSearchCV(estimator=model,
param_grid=param_test,
scoring=sklearn_metric,
n_jobs=n_jobs,
iid=False,
cv=folds,
verbose=True)
search.fit(X, y, cat_features=cat_features)
print("Best params encountered: " + str(search.best_params_))
print("Best score achived: " + str(search.best_score_))
print(
"------------------------------------------------------------------------"
)
pipe_model = search.best_estimator_
if step_wise_start_at <= 6:
param_test = {
'ctr_border_count': [50, 5, 10, 20, 100, 150, 200, 255]
}
search = GridSearchCV(estimator=model,
param_grid=param_test,
scoring=sklearn_metric,
n_jobs=n_jobs,
iid=False,
cv=folds,
verbose=True)
search.fit(X, y, cat_features=cat_features)
print("Best params encountered: " + str(search.best_params_))
print("Best score achived: " + str(search.best_score_))
print(
"------------------------------------------------------------------------"
)
pipe_model = search.best_estimator_
# Get model from pipeline
model = pipe_model.named_steps['model']
# Set final learning rate
model.set_params(learning_rate=final_learning_rate)
# num_boost_round optimization
cv_results = catboost.cv(params=model.get_params(),
pool=d_train,
iterations=10000,
early_stopping_rounds=50,
folds=folds,
verbose_eval=None,
as_pandas=False)
rmetric_name = list(cv_results.keys())[1]
best_boost_round = len(cv_results[rmetric_name])
best_score_achived = cv_results[rmetric_name][-1]
print("Best num_boost_round: " + str(best_boost_round))
print("Best score achived: " + str(best_score_achived))
print(
"------------------------------------------------------------------------"
)
model.set_params(iterations=best_boost_round)
return model
n_estimators=999999,
learning_rate=0.02,
colsample_bytree=0.3,
num_leaves=2,
metric='auc',
objective='binary',
n_jobs=-1)
modelxgb = xgb.XGBClassifier(max_depth=2,
n_estimators=999999,
colsample_bytree=0.3,
learning_rate=0.02,
objective='binary:logistic',
n_jobs=-1)
modelcb = cb.CatBoostClassifier(iterations=999999,
max_depth=2,
learning_rate=0.02,
colsample_bylevel=0.03,
objective="Logloss")
train_path = '../input/train.csv'
test_path = '../input/test.csv'
lgb_path = './lgb_models_stack/'
xgb_path = './xgb_models_stack/'
cb_path = './cb_models_stack/'
#Create dir for models
for filename in [lgb_path, xgb_path, cb_path]:
if os.path.exists(filename) == False:
os.mkdir(filename)
print('Load Train Data.')
train_x = pd.read_csv(train_path)
import time
import os
red_data_training, red_data_test, red_quality_training, red_quality_test, white_data_training, white_data_test, white_quality_training, white_quality_test = wines_import.read_data(
False)
if (os.path.exists("./catboost modele i wyniki/CPU WHITE MultiClass")):
os.remove("./catboost modele i wyniki/CPU WHITE MultiClass")
if (os.path.exists("./catboost modele i wyniki/GPU WHITE MultiClass")):
os.remove("./catboost modele i wyniki/GPU WHITE MultiClass")
messages_file = open(
"./catboost modele i wyniki/models WHITE MultiClass verification",
mode="w+")
model_white = catboost.CatBoostClassifier(task_type="CPU",
random_seed=42,
objective="MultiClass",
iterations=2000)
time_before = time.time()
model_white.fit(white_data_training,
white_quality_training,
eval_set=catboost.Pool(white_data_test,
white_quality_test,
has_header=True))
time_after = time.time()
model_white.save_model(
"./catboost modele i wyniki/CPU WHITE MultiClass verification")
messages_file.write("Uczenie na CPU wina biale trwalo:\n")
messages_file.write(str(time_after - time_before))
model_white_GPU = catboost.CatBoostClassifier(task_type="GPU",
random_seed=42,
objective="MultiClass",
booster='gbtree',
objective='binary:logistic',
eval_metric='logloss',
learning_rate=0.01),
train_type=args.train_type,
use_valid=True,
debug=args.debug)
elif (args.classifier == "lightgbm"):
model = LightGBMClassifier(model=lgb.LGBMClassifier(
objective='binary', metric='binary_logloss'),
train_type=args.train_type,
use_valid=True,
debug=args.debug)
elif (args.classifier == "catboost"):
model = CatBoostClassifier(
model=catboost.CatBoostClassifier(loss_function="Logloss"),
use_valid=True,
debug=args.debug)
# モデルのパラメータ設定
model.set_params(**study.best_params)
#--------------------
# モデルの学習処理
#--------------------
model.fit(X_train_fold, y_train_fold, X_valid_fold, y_valid_fold)
#--------------------
# モデルの推論処理
#--------------------
y_pred_train[valid_index] = model.predict(X_valid_fold)
def train_catboost(self):
# self.ct = bcolz.open(datadir, mode='r')
# ct = self.ct
time_start = datetime.datetime.now()
print("catboost training start", datetime.datetime.now(),
datetime.datetime.now() - time_start)
time_start = datetime.datetime.now()
y_train = pickle.load(open("train-label-2-0.pickle", "rb"))
y_test1 = pickle.load(open("train-label-4-1.pickle", "rb"))
y_test2 = pickle.load(open("train-label-4-3.pickle", "rb"))
gc.collect()
print("labels loaded", datetime.datetime.now(),
datetime.datetime.now() - time_start)
time_start = datetime.datetime.now()
X_train = pickle.load(open("train-features-2-0.pickle", "rb"))
X_test1 = pickle.load(open("train-features-4-1.pickle", "rb"))
X_test2 = pickle.load(open("train-features-4-3.pickle", "rb"))
gc.collect()
print("CSR loaded", datetime.datetime.now(),
datetime.datetime.now() - time_start)
time_start = datetime.datetime.now()
print("start learning ", datetime.datetime.now(),
datetime.datetime.now() - time_start)
time_start = datetime.datetime.now()
self.ml_params = {
"loss_function": 'Logloss',
#RMSE, MAE, Quantile, LogLinQuantile, Poisson, MAPE, Lq
"eval_metric": "Logloss",
"random_strength": 90,
"boosting_type": "Plain",
"bootstrap_type": "Bernoulli",
"od_type": 'Iter',
"od_wait": 800,
"depth": 5,
"learning_rate": 0.2,
#"learning_rate": 0.1,
#"iterations": 45,
"iterations": 10,
}
time_start = datetime.datetime.now()
print("before import catboost", datetime.datetime.now(),
datetime.datetime.now() - time_start)
time_start = datetime.datetime.now()
import catboost
print("after import catboost", datetime.datetime.now(),
datetime.datetime.now() - time_start)
time_start = datetime.datetime.now()
def Pool(X, y):
cols = self.num_feature_names + self.cat_feature_names
cb = catboost.Pool(X, label=y, feature_names=cols, cat_features=[])
return cb
# cbtrain = get_pool(0, self.rows_num-1000)
# try:
# pickle.dump(cbtrain, open('cbtrain-pool.pickle', 'wb'), protocol=4)
# except Exception as ex:
# print(ex)
# cbtest = get_pool(self.rows_num-1000, self.rows_num)
# model = catboost.CatBoostRegressor(**self.ml_params)
model = catboost.CatBoostClassifier(**self.ml_params)
self.model = model
# eval_set_ = [cbtest]
model.fit(Pool(X_train, y_train),
eval_set=[
Pool(X_train, y_train),
Pool(X_test1, y_test1),
Pool(X_test2, y_test2)
],
use_best_model=True,
verbose=True)
print("end learning ", datetime.datetime.now(),
datetime.datetime.now() - time_start)
time_start = datetime.datetime.now()
pickle.dump(model, open('model-catboost.pickle', 'wb'), protocol=4)
gc.collect()
feature_name = ['Parameter{0}'.format(i) for i in range(5, 11)]
tr_index = ~data['label'].isnull()
X_train = data[tr_index][feature_name].reset_index(drop=True)
y = data[tr_index]['label'].reset_index(drop=True).astype(int)
X_test = data[~tr_index][feature_name].reset_index(drop=True)
print(X_train.shape, X_test.shape)
oof = np.zeros((X_train.shape[0], 4))
prediction = np.zeros((X_test.shape[0], 4))
# cbt_model = cbt.CatBoostClassifier(iterations=800,verbose=300,learning_rate=0.01,
# task_type='GPU',
# loss_function='MultiClass')
cbt_model = cbt.CatBoostClassifier(iterations=1000,
verbose=300,
task_type='GPU',
loss_function='MultiClass',
random_state=303)
cbt_model.fit(X_train, y, eval_set=(X_train, y))
oof = cbt_model.predict_proba(X_test)
prediction = cbt_model.predict_proba(X_test)
gc.collect() #垃圾回收
print('logloss', log_loss(pd.get_dummies(y).values, oof))
print('ac', accuracy_score(y, np.argmax(oof, axis=1)))
print('mae', 1 / (1 + np.sum(np.absolute(np.eye(4)[y] - oof)) / 480))
print('-' * 80)
sub = test[['Group']]
prob_cols = [i for i in submit.columns if i not in ['Group']]
for i, f in enumerate(prob_cols):
sub[f] = prediction[:, i]
