本文整理汇总了Python中odps.df.DataFrame.head方法的典型用法代码示例。如果您正苦于以下问题：Python DataFrame.head方法的具体用法？Python DataFrame.head怎么用？Python DataFrame.head使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类odps.df.DataFrame的用法示例。
在下文中一共展示了DataFrame.head方法的5个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: test_df_consecutive
# 需要导入模块: from odps.df import DataFrame [as 别名]
# 或者: from odps.df.DataFrame import head [as 别名]
def test_df_consecutive(self):
self.create_ionosphere(IONOSPHERE_TABLE)
df = DataFrame(self.odps.get_table(IONOSPHERE_TABLE))
df = df[df['a04'] != 0]
df = df.roles(label='class')
df.head(10)
train, test = df.split(0.6)
lr = LogisticRegression(epsilon=0.01)
model = lr.train(train)
predicted = model.predict(test)
predicted.to_pandas()示例2: testHeadAndTail
# 需要导入模块: from odps.df import DataFrame [as 别名]
# 或者: from odps.df.DataFrame import head [as 别名]
def testHeadAndTail(self):
df = DataFrame(self.table)
self.assertEqual(1, len(df.head(1)))
self.assertEqual(2, len(df.head(2)))
self.assertEqual([3, 'name3'], list(df.tail(1)[0]))
r = df[df.name == 'name2'].head(1)
self.assertEqual(1, len(r))
self.assertEqual([2, 'name2'], list(r[0]))示例3: testHeadAndTail
# 需要导入模块: from odps.df import DataFrame [as 别名]
# 或者: from odps.df.DataFrame import head [as 别名]
def testHeadAndTail(self):
df = DataFrame(self.table)
self.assertEqual(1, len(df.head(1)))
self.assertEqual(2, len(df.head(2)))
self.assertEqual([3, 'name3'], list(df.tail(1)[0]))
r = df[df.name == 'name2'].head(1)
self.assertEqual(1, len(r))
self.assertEqual([2, 'name2'], list(r[0]))
self.assertRaises(NotImplementedError, lambda: df[df.name == 'name2'].tail(1))示例4: Test
# 需要导入模块: from odps.df import DataFrame [as 别名]
# 或者: from odps.df.DataFrame import head [as 别名]
#.........这里部分代码省略.........
try:
self.assertIsNotNone(new_df2.input._source_data)
finally:
[cb() for cb in cbs]
def testCacheTable(self):
df = self.odps_df.join(self.pd_df, 'name').cache()
df2 = df.sort('id_x')
dag = self.engine._compile_dag(df2)
self.assertEqual(len(dag.nodes()), 3)
result = self.engine.execute(df2).values
df3 = DataFrame(self.odps_df.to_pandas())
expected = self.pd_engine.execute(df3.join(self.pd_df, 'name').sort('id_x')).values
self.assertTrue(result.equals(expected))
self.assertEqual(len(self.engine._generated_table_names), 2)
table = df._cache_data
self.assertEqual(len(df.execute()), len(expected))
self.assertIs(df._cache_data, table)
df4 = df[df.id_x < 3].count()
result = self.engine.execute(df4)
self.assertEqual(result, 2)
self.assertEqual(df4._cache_data, 2)
def testUseCache(self):
df = self.odps_df[self.odps_df['name'] == 'name1']
self.assertEqual(len(df.head(10)), 2)
df._cache_data.drop()
self.assertRaises(ODPSError, lambda: self.engine.execute(df['name', 'id']))
def plot(**_):
pass
self.assertRaises(ODPSError, lambda: df.plot(x='id', plot_func=plot))
def testHeadAndTail(self):
res = self.odps_df.head(2)
self.assertEqual(len(res), 2)
df = self.odps_df[self.odps_df['name'] == 'name1']
res = df.head(1)
self.assertEqual(len(res), 1)
self.assertIsNotNone(df._cache_data)
res = self.odps_df.tail(2)
self.assertEqual(len(res), 2)
self.assertTrue(all(it > 1 for it in res.values['id']))
self.assertEqual(len(self.odps_df.name.head(2)), 2)
self.assertEqual(len(self.odps_df.name.tail(2)), 2)
res = self.pd_df.head(1)
self.assertEqual(len(res), 1)
df = self.pd_df[self.pd_df['name'] == 'name1']
res = df.head(1)
self.assertEqual(len(res), 1)
self.assertIsNotNone(df._cache_data)示例5: Test
# 需要导入模块: from odps.df import DataFrame [as 别名]
# 或者: from odps.df.DataFrame import head [as 别名]
#.........这里部分代码省略.........
try:
self.assertIsNotNone(new_df2.input._source_data)
finally:
[cb() for cb in cbs]
def testCacheTable(self):
df = self.odps_df.join(self.pd_df, "name").cache()
df2 = df.sort("id_x")
dag = self.engine._compile_dag(df2)
self.assertEqual(len(dag.nodes()), 3)
result = self.engine.execute(df2).values
df3 = DataFrame(self.odps_df.to_pandas())
expected = self.pd_engine.execute(df3.join(self.pd_df, "name").sort("id_x")).values
self.assertTrue(result.equals(expected))
self.assertEqual(len(self.engine._generated_table_names), 2)
table = df._cache_data
self.assertEqual(len(df.execute()), len(expected))
self.assertIs(df._cache_data, table)
df4 = df[df.id_x < 3].count()
result = self.engine.execute(df4)
self.assertEqual(result, 2)
self.assertEqual(df4._cache_data, 2)
def testUseCache(self):
df = self.odps_df[self.odps_df["name"] == "name1"]
self.assertEqual(len(df.head(10)), 2)
df._cache_data.drop()
self.assertRaises(ODPSError, lambda: self.engine.execute(df["name", "id"]))
def plot(**_):
pass
self.assertRaises(ODPSError, lambda: df.plot(x="id", plot_func=plot))
def testPivot(self):
data = [["name1", 1, 1.0, True], ["name1", 2, 2.0, True], ["name2", 1, 3.0, False], ["name2", 3, 4.0, False]]
table_name = tn("pyodps_test_mixed_engine_pivot")
self.odps.delete_table(table_name, if_exists=True)
table = self.odps.create_table(
name=table_name,
schema=Schema.from_lists(["name", "id", "fid", "ismale"], ["string", "bigint", "double", "boolean"]),
)
expr = DataFrame(table)
try:
self.odps.write_table(table, 0, data)
expr1 = expr.pivot(rows="id", columns="name", values="fid").distinct()
res = self.engine.execute(expr1)
result = self._get_result(res)
expected = [[1, 1.0, 3.0], [2, 2.0, None], [3, None, 4.0]]
self.assertEqual(sorted(result), sorted(expected))
expr2 = expr.pivot(rows="id", columns="name", values=["fid", "ismale"])
res = self.engine.execute(expr2)