add min_data, fix test

python-package/lightgbm/sklearn.py

@@ -80,7 +80,9 @@ class LGBMModel(LGBMModelBase):
     gamma : float
         Minimum loss reduction required to make a further partition on a leaf node of the tree.
     min_child_weight : int
-        Minimum sum of instance weight(hessian) needed in a child.
+        Minimum sum of instance weight(hessian) needed in a child(leaf)
+    min_data : int
+        Minimum number of data need in a child(leaf)
     subsample : float
         Subsample ratio of the training instance.
     subsample_freq : int
@@ -121,10 +123,10 @@ class LGBMModel(LGBMModelBase):
           and you should group grad and hess in this way as well
     """
 
-    def __init__(self, num_leaves=63, max_depth=-1, 
-                 learning_rate=0.1, n_estimators=100, max_bin=255,
+    def __init__(self, num_leaves=31, max_depth=-1, 
+                 learning_rate=0.1, n_estimators=10, max_bin=255,
                  silent=True, objective="regression",  
-                 nthread=-1, gamma=0, min_child_weight=1,
+                 nthread=-1, gamma=0, min_child_weight=5, min_data=10,
                  subsample=1, subsample_freq=1, colsample_bytree=1, colsample_byleaf=1, 
                  reg_alpha=0, reg_lambda=0, scale_pos_weight=1, 
                  is_unbalance=False, seed=0):
@@ -141,6 +143,7 @@ class LGBMModel(LGBMModelBase):
         self.nthread = nthread
         self.gamma = gamma
         self.min_child_weight = min_child_weight
+        self.min_data = min_data
         self.subsample = subsample
         self.subsample_freq = subsample_freq
         self.colsample_bytree = colsample_bytree

tests/python_package_test/test_sklearn.py

@@ -10,13 +10,13 @@ def test_binary_classification():
     from sklearn import datasets, metrics, model_selection
 
     X, y = datasets.make_classification(n_samples=10000, n_features=100)
-    x_train, x_test, y_train, y_test = model_selection.train_test_split(X, y, test_size=0.1)
+    x_train, x_test, y_train, y_test = model_selection.train_test_split(X, y, test_size=0.1, random_state=1)
     lgb_model = lgb.LGBMClassifier().fit(x_train, y_train)
     from sklearn.datasets import load_digits
     digits = load_digits(2)
     y = digits['target']
     X = digits['data']
-    x_train, x_test, y_train, y_test = model_selection.train_test_split(X, y, test_size=0.2)
+    x_train, x_test, y_train, y_test = model_selection.train_test_split(X, y, test_size=0.1, random_state=1)
     lgb_model = lgb.LGBMClassifier().fit(x_train, y_train)
     preds = lgb_model.predict(x_test)
     err = sum(1 for i in range(len(preds))
@@ -35,7 +35,7 @@ def test_multiclass_classification():
 
     X, y = datasets.make_classification(n_samples=10000, n_features=100, n_classes=4, n_informative=3)
 
-    x_train, x_test, y_train, y_test = model_selection.train_test_split(X, y, test_size=0.1)
+    x_train, x_test, y_train, y_test = model_selection.train_test_split(X, y, test_size=0.1, random_state=1)
 
     lgb_model = lgb.LGBMClassifier().fit(x_train, y_train)
     preds = lgb_model.predict(x_test)
@@ -51,10 +51,10 @@ def test_regression():
     boston = load_boston()
     y = boston['target']
     X = boston['data']
-    x_train, x_test, y_train, y_test = model_selection.train_test_split(X, y, test_size=0.1)
+    x_train, x_test, y_train, y_test = model_selection.train_test_split(X, y, test_size=0.1, random_state=1)
     lgb_model = lgb.LGBMRegressor().fit(x_train, y_train)
     preds = lgb_model.predict(x_test)
-    assert mean_squared_error(preds, y_test) < 40
+    assert mean_squared_error(preds, y_test) < 100
 
 def test_regression_with_custom_objective():
     from sklearn.metrics import mean_squared_error
@@ -68,10 +68,10 @@ def test_regression_with_custom_objective():
     boston = load_boston()
     y = boston['target']
     X = boston['data']
-    x_train, x_test, y_train, y_test = model_selection.train_test_split(X, y, test_size=0.1)
+    x_train, x_test, y_train, y_test = model_selection.train_test_split(X, y, test_size=0.1, random_state=1)
     lgb_model = lgb.LGBMRegressor(objective=objective_ls).fit(x_train, y_train)
     preds = lgb_model.predict(x_test)
-    assert mean_squared_error(preds, y_test) < 40
+    assert mean_squared_error(preds, y_test) < 100
 
 
 def test_binary_classification_with_custom_objective():
@@ -83,13 +83,13 @@ def test_binary_classification_with_custom_objective():
         hess = y_pred * (1.0 - y_pred)
         return grad, hess
     X, y = datasets.make_classification(n_samples=10000, n_features=100)
-    x_train, x_test, y_train, y_test = model_selection.train_test_split(X, y, test_size=0.1)
+    x_train, x_test, y_train, y_test = model_selection.train_test_split(X, y, test_size=0.1, random_state=1)
     lgb_model = lgb.LGBMClassifier(objective=logregobj).fit(x_train, y_train)
     from sklearn.datasets import load_digits
     digits = load_digits(2)
     y = digits['target']
     X = digits['data']
-    x_train, x_test, y_train, y_test = model_selection.train_test_split(X, y, test_size=0.2)
+    x_train, x_test, y_train, y_test = model_selection.train_test_split(X, y, test_size=0.2, random_state=1)
     lgb_model = lgb.LGBMClassifier(objective=logregobj).fit(x_train, y_train)
     preds = lgb_model.predict(x_test)
     err = sum(1 for i in range(len(preds))