Cover approx tree method for categorical data tests. (#7569)

* Add tree to df tests.
* Add plotting tests.
* Add histogram tests.

tests/python-gpu/test_gpu_parse_tree.py

@@ -1,25 +1,14 @@
 import sys
-import pytest
-import xgboost as xgb
 
 sys.path.append("tests/python")
-import testing as tm
+from test_parse_tree import TestTreesToDataFrame
 
 
 def test_tree_to_df_categorical():
- X, y = tm.make_categorical(100, 10, 31, False)
- Xy = xgb.DMatrix(X, y, enable_categorical=True)
- booster = xgb.train({"tree_method": "gpu_hist"}, Xy, num_boost_round=10)
- df = booster.trees_to_dataframe()
- for _, x in df.iterrows():
- if x["Feature"] != "Leaf":
- assert len(x["Category"]) == 1
+ cputest = TestTreesToDataFrame()
+ cputest.run_tree_to_df_categorical("gpu_hist")
 
 
 def test_split_value_histograms():
- X, y = tm.make_categorical(1000, 10, 13, False)
- reg = xgb.XGBRegressor(tree_method="gpu_hist", enable_categorical=True)
- reg.fit(X, y)
-
- with pytest.raises(ValueError, match="doesn't"):
- reg.get_booster().get_split_value_histogram("3", bins=5)
+ cputest = TestTreesToDataFrame()
+ cputest.run_split_value_histograms("gpu_hist")

tests/python-gpu/test_gpu_plotting.py

@@ -1,40 +1,17 @@
 import sys
-import xgboost as xgb
 import pytest
-import json
 
 sys.path.append("tests/python")
 import testing as tm
-
-try:
- import matplotlib
-
- matplotlib.use("Agg")
- from matplotlib.axes import Axes
- from graphviz import Source
-except ImportError:
- pass
+import test_plotting as tp
 
 
 pytestmark = pytest.mark.skipif(**tm.no_multiple(tm.no_matplotlib(), tm.no_graphviz()))
 
 
 class TestPlotting:
+ cputest = tp.TestPlotting()
+
  @pytest.mark.skipif(**tm.no_pandas())
  def test_categorical(self):
- X, y = tm.make_categorical(1000, 31, 19, onehot=False)
- reg = xgb.XGBRegressor(
- enable_categorical=True, n_estimators=10, tree_method="gpu_hist"
- )
- reg.fit(X, y)
- trees = reg.get_booster().get_dump(dump_format="json")
- for tree in trees:
- j_tree = json.loads(tree)
- assert "leaf" in j_tree.keys() or isinstance(
- j_tree["split_condition"], list
- )
-
- graph = xgb.to_graphviz(reg, num_trees=len(j_tree) - 1)
- assert isinstance(graph, Source)
- ax = xgb.plot_tree(reg, num_trees=len(j_tree) - 1)
- assert isinstance(ax, Axes)
+ self.cputest.run_categorical("gpu_hist")

tests/python/test_parse_tree.py

@@ -12,7 +12,6 @@
 
 
 class TestTreesToDataFrame:
-
  def build_model(self, max_depth, num_round):
  dtrain = xgb.DMatrix(dpath + 'agaricus.txt.train')
  param = {'max_depth': max_depth, 'objective': 'binary:logistic',
@@ -48,3 +47,26 @@ def test_trees_to_dataframe(self):
  # test for equality of covers
  cover_from_df = df.Cover.sum()
  assert np.allclose(cover_from_dump, cover_from_df)
+
+ def run_tree_to_df_categorical(self, tree_method: str) -> None:
+ X, y = tm.make_categorical(100, 10, 31, False)
+ Xy = xgb.DMatrix(X, y, enable_categorical=True)
+ booster = xgb.train({"tree_method": tree_method}, Xy, num_boost_round=10)
+ df = booster.trees_to_dataframe()
+ for _, x in df.iterrows():
+ if x["Feature"] != "Leaf":
+ assert len(x["Category"]) >= 1
+
+ def test_tree_to_df_categorical(self) -> None:
+ self.run_tree_to_df_categorical("approx")
+
+ def run_split_value_histograms(self, tree_method) -> None:
+ X, y = tm.make_categorical(1000, 10, 13, False)
+ reg = xgb.XGBRegressor(tree_method=tree_method, enable_categorical=True)
+ reg.fit(X, y)
+
+ with pytest.raises(ValueError, match="doesn't"):
+ reg.get_booster().get_split_value_histogram("3", bins=5)
+
+ def test_split_value_histograms(self):
+ self.run_split_value_histograms("approx")

tests/python/test_plotting.py

@@ -1,4 +1,4 @@
-# -*- coding: utf-8 -*-
+import json
 import numpy as np
 import xgboost as xgb
 import testing as tm
@@ -73,3 +73,25 @@ def test_importance_plot_lim(self):
  ax = xgb.plot_importance(bst, xlim=(0, 5), ylim=(10, 71))
  assert ax.get_xlim() == (0., 5.)
  assert ax.get_ylim() == (10., 71.)
+
+ def run_categorical(self, tree_method: str) -> None:
+ X, y = tm.make_categorical(1000, 31, 19, onehot=False)
+ reg = xgb.XGBRegressor(
+ enable_categorical=True, n_estimators=10, tree_method=tree_method
+ )
+ reg.fit(X, y)
+ trees = reg.get_booster().get_dump(dump_format="json")
+ for tree in trees:
+ j_tree = json.loads(tree)
+ assert "leaf" in j_tree.keys() or isinstance(
+ j_tree["split_condition"], list
+ )
+
+ graph = xgb.to_graphviz(reg, num_trees=len(j_tree) - 1)
+ assert isinstance(graph, Source)
+ ax = xgb.plot_tree(reg, num_trees=len(j_tree) - 1)
+ assert isinstance(ax, Axes)
+
+ @pytest.mark.skipif(**tm.no_pandas())
+ def test_categorical(self) -> None:
+ self.run_categorical("approx")