本文整理汇总了Python中odps.df.DataFrame.roles方法的典型用法代码示例。如果您正苦于以下问题：Python DataFrame.roles方法的具体用法？Python DataFrame.roles怎么用？Python DataFrame.roles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.roles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 roles [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: test_df_combined
# 需要导入模块: from odps.df import DataFrame [as 别名]
# 或者: from odps.df.DataFrame import roles [as 别名]
def test_df_combined(self):
self.create_ionosphere(IONOSPHERE_TABLE)
df = DataFrame(self.odps.get_table(IONOSPHERE_TABLE))
df = df[df['a04'] != 0]
df = df['a01', df.a05.map(lambda v: v * 2).rename('a05'), 'a06', 'class']
df = df.roles(label='class')
df = df[df.a05 != 0].cache()
df = df[df.a05, ((df.a06 + 1) / 2).rename('a06'), 'class']
train, test = df.split(0.6)
lr = LogisticRegression(epsilon=0.01)
model = lr.train(train)
predicted = model.predict(test)
(- 1.0 * ((predicted['class'] * predicted.prediction_score.log().rename('t')).rename('t1') + (
(1 - predicted['class']) * (1 - predicted.prediction_score).log().rename('t0')).rename('t2')).rename(
't3').sum() / predicted.prediction_score.count()).rename('t4').execute()示例3: Test
# 需要导入模块: from odps.df import DataFrame [as 别名]
# 或者: from odps.df.DataFrame import roles [as 别名]
class Test(MLTestBase):
def setUp(self):
super(Test, self).setUp()
self.create_iris(IRIS_TABLE)
self.df = DataFrame(self.odps.get_table(IRIS_TABLE))
def test_coll_field_operations(self):
# select_features
self.assertRaises(ValueError, lambda: self.df.select_features())
df2 = self.df.select_features("sepal_length sepal_width petal_length")
self.assertEqual(
_df_roles(df2),
dict(category="", sepal_width="FEATURE", sepal_length="FEATURE", petal_length="FEATURE", petal_width=""),
)
df3 = df2.select_features("petal_width", add=True)
self.assertEqual(
_df_roles(df3),
dict(
category="",
sepal_width="FEATURE",
sepal_length="FEATURE",
petal_length="FEATURE",
petal_width="FEATURE",
),
)
# exclude_fields
self.assertRaises(ValueError, lambda: self.df.exclude_fields())
df4 = df3.exclude_fields("sepal_length sepal_width")
self.assertEqual(
_df_roles(df4),
dict(category="", sepal_width="", sepal_length="", petal_length="FEATURE", petal_width="FEATURE"),
)
# weight_field
self.assertRaises(ValueError, lambda: self.df.weight_field(None))
df5 = df3.weight_field("sepal_width")
self.assertEqual(
_df_roles(df5),
dict(
category="", sepal_width="WEIGHT", sepal_length="FEATURE", petal_length="FEATURE", petal_width="FEATURE"
),
)
# label_field
self.assertRaises(ValueError, lambda: self.df.label_field(None))
df6 = self.df.label_field("category")
self.assertEqual(
_df_roles(df6),
dict(
category="LABEL",
sepal_width="FEATURE",
sepal_length="FEATURE",
petal_length="FEATURE",
petal_width="FEATURE",
),
)
# roles
self.assertIs(self.df, self.df.roles())
df7 = self.df.roles(label="category", weight="sepal_width")
self.assertEqual(
_df_roles(df7),
dict(
category="LABEL",
petal_length="FEATURE",
petal_width="FEATURE",
sepal_width="WEIGHT",
sepal_length="FEATURE",
),
)
# discrete
df8 = self.df.discrete("sepal_width, sepal_length")
self.assertEqual(
_df_continuity(df8),
dict(
category="DISCRETE",
sepal_width="DISCRETE",
sepal_length="DISCRETE",
petal_length="CONTINUOUS",
petal_width="CONTINUOUS",
),
)
# continuous
df9 = df8.continuous("sepal_width")
self.assertEqual(
_df_continuity(df9),
dict(
category="DISCRETE",
sepal_width="CONTINUOUS",
sepal_length="DISCRETE",
petal_length="CONTINUOUS",
petal_width="CONTINUOUS",
),
)
# key_value
df10 = self.df.key_value("sepal_length sepal_width")
self.assertEqual(
_df_key_value(df10),
dict(
category="",
petal_length="",
petal_width="",
sepal_width="KVConfig(kv=:, item=,)",
#.........这里部分代码省略.........
示例4: test_dynamic_output
# 需要导入模块: from odps.df import DataFrame [as 别名]
# 或者: from odps.df.DataFrame import roles [as 别名]
def test_dynamic_output(self):
self.create_ionosphere(IONOSPHERE_TABLE)
df = DataFrame(self.odps.get_table(IONOSPHERE_TABLE))
df = df.roles(label=df['class'])
filtered, importance = select_features(df)
print(filtered.describe().execute())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 roles [as 别名]
class Test(MLTestBase):
def setUp(self):
super(Test, self).setUp()
self.create_corpus(CORPUS_TABLE)
self.df = DataFrame(self.odps.get_table(CORPUS_TABLE)).roles(doc_id='id', doc_content='content')
options.runner.dry_run = True
def _create_str_compare_table(self, table_name):
data_rows = [
['inputTableName', 'inputTableName'], ['outputTableName', 'mapTableName'],
['inputSelectedColName1', 'outputTableName'], ['inputSelectedColName2', 'inputSelectedColName'],
['inputAppendColNames', 'mapSelectedColName'], ['inputTablePartitions', 'inputAppendColNames'],
['outputColName', 'inputAppendRenameColNames'], ['method', 'mapAppendColNames'],
['lambda', 'mapAppendRenameColNames'], ['k', 'inputTablePartitions'],
['lifecycle', 'mapTablePartitions'], ['coreNum', 'outputColName'], ['memSizePerCore', 'method'],
]
for idx, r in enumerate(data_rows):
data_rows[idx] = [idx] + r
self.odps.execute_sql('drop table if exists ' + table_name)
self.odps.execute_sql('create table %s (str_id bigint, col1 string, col2 string)' % table_name)
self.odps.write_table(table_name, data_rows)
def _create_noise_table(self, table_name):
data_rows = (u'，', u'。', u'《', u'》', u'的', u'是')
data_rows = [[v] for v in data_rows]
self.odps.execute_sql('drop table if exists ' + table_name)
self.odps.execute_sql('create table %s (noise_col string)' % table_name)
self.odps.write_table(table_name, data_rows)
def test_tf_idf(self):
splited = SplitWord().transform(self.df)
freq, _ = DocWordStat().transform(splited)
tf_set = TFIDF().transform(freq)
tf_set._add_case(self.gen_check_params_case({
'docIdCol': 'id', 'inputTableName': TEMP_TABLE_PREFIX + '0_doc_word_stat_3_1', 'countCol': 'count',
'outputTableName': TFIDF_TABLE, 'wordCol': 'word'}))
tf_set.persist(TFIDF_TABLE)
def test_str_diff(self):
self._create_str_compare_table(STR_COMP_TABLE)
df = DataFrame(self.odps.get_table(STR_COMP_TABLE))
diff_df = str_diff(df, col1='col1', col2='col2')
diff_df._add_case(self.gen_check_params_case({
'inputTableName': STR_COMP_TABLE, 'k': '2', 'outputTableName': COMP_RESULT_TABLE,
'inputSelectedColName2': 'col2', 'inputSelectedColName1': 'col1', 'method': 'levenshtein_sim',
'lambda': '0.5', 'outputColName': 'output'}))
diff_df.persist(COMP_RESULT_TABLE)
def test_top_n(self):
self._create_str_compare_table(STR_COMP_TABLE)
df = DataFrame(self.odps.get_table(STR_COMP_TABLE))
top_n_df = top_n_similarity(df, df, col='col1', map_col='col1')
top_n_df._add_case(self.gen_check_params_case({
'inputTableName': STR_COMP_TABLE, 'k': '2', 'outputColName': 'output',
'mapSelectedColName': 'col1', 'topN': '10', 'inputSelectedColName': 'col1',
'outputTableName': TOP_N_TABLE, 'mapTableName': STR_COMP_TABLE,
'method': 'levenshtein_sim', 'lambda': '0.5'}))
top_n_df.persist(TOP_N_TABLE)
def test_filter_noises(self):
self.odps.delete_table(FILTERED_WORDS_TABLE, if_exists=True)
self.create_splited_words(SPLITED_TABLE)
self._create_noise_table(NOISE_TABLE)
df = DataFrame(self.odps.get_table(SPLITED_TABLE)).roles(doc_content='content')
ndf = DataFrame(self.odps.get_table(NOISE_TABLE))
filtered = filter_noises(df, ndf)
filtered._add_case(self.gen_check_params_case({
'noiseTableName': NOISE_TABLE, 'outputTableName': FILTERED_WORDS_TABLE,
'selectedColNames': 'content', 'inputTableName': SPLITED_TABLE}))
filtered.persist(FILTERED_WORDS_TABLE)
def test_keywords_extraction(self):
self.odps.delete_table(KW_EXTRACTED_TABLE, if_exists=True)
self.create_splited_words(SPLITED_TABLE)
df = DataFrame(self.odps.get_table(SPLITED_TABLE)).roles(doc_id='doc_id', doc_content='content')
extracted = extract_keywords(df)
extracted._add_case(self.gen_check_params_case(
{'dumpingFactor': '0.85', 'inputTableName': SPLITED_TABLE, 'epsilon': '0.000001', 'windowSize': '2',
'topN': '5', 'outputTableName': KW_EXTRACTED_TABLE, 'docIdCol': 'doc_id', 'maxIter': '100',
'docContent': 'content'}))
extracted.persist(KW_EXTRACTED_TABLE)
def test_summarize_text(self):
self.create_corpus(CORPUS_TABLE)
summarized = summarize_text(self.df.roles(sentence='content'))
summarized._add_case(self.gen_check_params_case(
{'dumpingFactor': '0.85', 'inputTableName': CORPUS_TABLE, 'sentenceCol': 'content',
'epsilon': '0.000001', 'k': '2', 'topN': '3', 'outputTableName': TEXT_SUMMARIZED_TABLE,
'docIdCol': 'id', 'maxIter': '100', 'similarityType': 'lcs_sim', 'lambda': '0.5'}))
summarized.persist(TEXT_SUMMARIZED_TABLE)
def test_count_ngram(self):
self.create_word_triple(WORD_TRIPLE_TABLE)
word_triple_df = DataFrame(self.odps.get_table(WORD_TRIPLE_TABLE)).select_features('word')
counted = count_ngram(word_triple_df)
counted._add_case(self.gen_check_params_case({
'outputTableName': COUNT_NGRAM_TABLE, 'inputSelectedColNames': 'word', 'order': '3',
'inputTableName': WORD_TRIPLE_TABLE}))
#.........这里部分代码省略.........