io_test.py 文件源码

def test_dask_iris_classification(self):
    if HAS_DASK and HAS_PANDAS:
      import pandas as pd  # pylint: disable=g-import-not-at-top
      import dask.dataframe as dd  # pylint: disable=g-import-not-at-top
      random.seed(42)
      iris = datasets.load_iris()
      data = pd.DataFrame(iris.data)
      data = dd.from_pandas(data, npartitions=2)
      labels = pd.DataFrame(iris.target)
      labels = dd.from_pandas(labels, npartitions=2)
      classifier = learn.LinearClassifier(
          feature_columns=learn.infer_real_valued_columns_from_input(data),
          n_classes=3)
      classifier.fit(data, labels, steps=100)
      predictions = data.map_partitions(classifier.predict).compute()
      score = accuracy_score(labels.compute(), predictions)
      self.assertGreater(score, 0.5, "Failed with score = {0}".format(score))