我下载了最新版本的H2O（3.18.0.1），XGboost仍然失败 . 我不确定是否要发布到JIRA问题或这里 .
h2o.init()
from h2o.estimators import H2OXGBoostEstimator
is_xgboost_available = H2OXGBoostEstimator.available()
train_path = 'https://s3.amazonaws.com/h2o-public-test-data/bigdata/laptop/higgs_train_imbalance_100k.csv'
test_path = 'https://s3.amazonaws.com/h2o-public-test-data/bigdata/laptop/higgs_test_imbalance_100k.csv'
df_train = h2o.import_file(train_path)
df_test = h2o.import_file(test_path)
# Transform first feature into categorical feature
df_train[0] = df_train[0].asfactor()
df_test[0] = df_test[0].asfactor()
param = {
"ntrees" : 500
}
model = H2OXGBoostEstimator(**param)
model.train(x = list(range(1, df_train.shape[1])), y = 0, training_frame = df_train)
我可以运行随机林，GBM没有问题，但xgboost一直在失败 .
我在Ubuntu 16.04上运行 . Java版本：java版“1.8.0_161”; Java（TM）SE运行时环境（版本1.8.0_161-b12）; Java HotSpot（TM）64位服务器VM（内置25.161-b12，混合模式） . Anaconda Python 3.6
我重新安装了Anaconda并重新安装了JRE，但我仍然遇到同样的问题 .
它一直给我以下错误：
xgboost Model Build progress: |████████████████████████████████████████
---------------------------------------------------------------------------
ConnectionResetError Traceback (most recent call last)
~/anaconda3/lib/python3.6/site-packages/urllib3/connectionpool.py in urlopen(self, method, url, body, headers, retries, redirect, assert_same_host, timeout, pool_timeout, release_conn, chunked, body_pos, **response_kw)
600 body=body, headers=headers,
--> 601 chunked=chunked)
602
~/anaconda3/lib/python3.6/site-packages/urllib3/connectionpool.py in _make_request(self, conn, method, url, timeout, chunked, **httplib_request_kw)
386 # otherwise it looks like a programming error was the cause.
--> 387 six.raise_from(e, None)
388 except (SocketTimeout, BaseSSLError, SocketError) as e:
~/anaconda3/lib/python3.6/site-packages/urllib3/packages/six.py in raise_from(value, from_value)
~/anaconda3/lib/python3.6/site-packages/urllib3/connectionpool.py in _make_request(self, conn, method, url, timeout, chunked, **httplib_request_kw)
382 try:
--> 383 httplib_response = conn.getresponse()
384 except Exception as e:
~/anaconda3/lib/python3.6/http/client.py in getresponse(self)
1330 try:
-> 1331 response.begin()
1332 except ConnectionError:
~/anaconda3/lib/python3.6/http/client.py in begin(self)
296 while True:
--> 297 version, status, reason = self._read_status()
298 if status != CONTINUE:
~/anaconda3/lib/python3.6/http/client.py in _read_status(self)
257 def _read_status(self):
--> 258 line = str(self.fp.readline(_MAXLINE + 1), "iso-8859-1")
259 if len(line) > _MAXLINE:
~/anaconda3/lib/python3.6/socket.py in readinto(self, b)
585 try:
--> 586 return self._sock.recv_into(b)
587 except timeout:
ConnectionResetError: [Errno 104] Connection reset by peer
During handling of the above exception, another exception occurred:
ProtocolError Traceback (most recent call last)
~/anaconda3/lib/python3.6/site-packages/requests/adapters.py in send(self, request, stream, timeout, verify, cert, proxies)
439 retries=self.max_retries,
--> 440 timeout=timeout
441 )
~/anaconda3/lib/python3.6/site-packages/urllib3/connectionpool.py in urlopen(self, method, url, body, headers, retries, redirect, assert_same_host, timeout, pool_timeout, release_conn, chunked, body_pos, **response_kw)
638 retries = retries.increment(method, url, error=e, _pool=self,
--> 639 _stacktrace=sys.exc_info()[2])
640 retries.sleep()
~/anaconda3/lib/python3.6/site-packages/urllib3/util/retry.py in increment(self, method, url, response, error, _pool, _stacktrace)
356 if read is False or not self._is_method_retryable(method):
--> 357 raise six.reraise(type(error), error, _stacktrace)
358 elif read is not None:
~/anaconda3/lib/python3.6/site-packages/urllib3/packages/six.py in reraise(tp, value, tb)
684 if value.__traceback__ is not tb:
--> 685 raise value.with_traceback(tb)
686 raise value
~/anaconda3/lib/python3.6/site-packages/urllib3/connectionpool.py in urlopen(self, method, url, body, headers, retries, redirect, assert_same_host, timeout, pool_timeout, release_conn, chunked, body_pos, **response_kw)
600 body=body, headers=headers,
--> 601 chunked=chunked)
602
~/anaconda3/lib/python3.6/site-packages/urllib3/connectionpool.py in _make_request(self, conn, method, url, timeout, chunked, **httplib_request_kw)
386 # otherwise it looks like a programming error was the cause.
--> 387 six.raise_from(e, None)
388 except (SocketTimeout, BaseSSLError, SocketError) as e:
~/anaconda3/lib/python3.6/site-packages/urllib3/packages/six.py in raise_from(value, from_value)
~/anaconda3/lib/python3.6/site-packages/urllib3/connectionpool.py in _make_request(self, conn, method, url, timeout, chunked, **httplib_request_kw)
382 try:
--> 383 httplib_response = conn.getresponse()
384 except Exception as e:
~/anaconda3/lib/python3.6/http/client.py in getresponse(self)
1330 try:
-> 1331 response.begin()
1332 except ConnectionError:
~/anaconda3/lib/python3.6/http/client.py in begin(self)
296 while True:
--> 297 version, status, reason = self._read_status()
298 if status != CONTINUE:
~/anaconda3/lib/python3.6/http/client.py in _read_status(self)
257 def _read_status(self):
--> 258 line = str(self.fp.readline(_MAXLINE + 1), "iso-8859-1")
259 if len(line) > _MAXLINE:
~/anaconda3/lib/python3.6/socket.py in readinto(self, b)
585 try:
--> 586 return self._sock.recv_into(b)
587 except timeout:
ProtocolError: ('Connection aborted.', ConnectionResetError(104, 'Connection reset by peer'))
During handling of the above exception, another exception occurred:
ConnectionError Traceback (most recent call last)
~/anaconda3/lib/python3.6/site-packages/h2o/backend/connection.py in request(self, endpoint, data, json, filename, save_to)
399 headers=headers, timeout=self._timeout, stream=stream,
--> 400 auth=self._auth, verify=self._verify_ssl_cert, proxies=self._proxies)
401 self._log_end_transaction(start_time, resp)
~/anaconda3/lib/python3.6/site-packages/requests/api.py in request(method, url, **kwargs)
57 with sessions.Session() as session:
---> 58 return session.request(method=method, url=url, **kwargs)
59
~/anaconda3/lib/python3.6/site-packages/requests/sessions.py in request(self, method, url, params, data, headers, cookies, files, auth, timeout, allow_redirects, proxies, hooks, stream, verify, cert, json)
507 send_kwargs.update(settings)
--> 508 resp = self.send(prep, **send_kwargs)
509
~/anaconda3/lib/python3.6/site-packages/requests/sessions.py in send(self, request, **kwargs)
617 # Send the request
--> 618 r = adapter.send(request, **kwargs)
619
~/anaconda3/lib/python3.6/site-packages/requests/adapters.py in send(self, request, stream, timeout, verify, cert, proxies)
489 except (ProtocolError, socket.error) as err:
--> 490 raise ConnectionError(err, request=request)
491
ConnectionError: ('Connection aborted.', ConnectionResetError(104, 'Connection reset by peer'))
During handling of the above exception, another exception occurred:
H2OConnectionError Traceback (most recent call last)
<ipython-input-22-37b26d4dfbfd> in <module>()
1 start = time.time()
----> 2 model.train(x = list(range(1, df_train.shape[1])), y = 0, training_frame = df_train)
3 end = time.time()
4 print(end - start)
~/anaconda3/lib/python3.6/site-packages/h2o/estimators/estimator_base.py in train(self, x, y, training_frame, offset_column, fold_column, weights_column, validation_frame, max_runtime_secs, ignored_columns, model_id, verbose)
229 return
230
--> 231 model.poll(verbose_model_scoring_history=verbose)
232 model_json = h2o.api("GET /%d/Models/%s" % (rest_ver, model.dest_key))["models"][0]
233 self._resolve_model(model.dest_key, model_json)
~/anaconda3/lib/python3.6/site-packages/h2o/job.py in poll(self, verbose_model_scoring_history)
56 pb.execute(self._refresh_job_status, print_verbose_info=lambda x: self._print_verbose_info() if int(x * 10) % 5 == 0 else " ")
57 else:
---> 58 pb.execute(self._refresh_job_status)
59 except StopIteration as e:
60 if str(e) == "cancelled":
~/anaconda3/lib/python3.6/site-packages/h2o/utils/progressbar.py in execute(self, progress_fn, print_verbose_info)
167 # Query the progress level, but only if it's time already
168 if self._next_poll_time <= now:
--> 169 res = progress_fn() # may raise StopIteration
170 assert_is_type(res, (numeric, numeric), numeric)
171 if not isinstance(res, tuple):
~/anaconda3/lib/python3.6/site-packages/h2o/job.py in _refresh_job_status(self)
91 def _refresh_job_status(self):
92 if self._poll_count <= 0: raise StopIteration("")
---> 93 jobs = h2o.api("GET /3/Jobs/%s" % self.job_key)
94 self.job = jobs["jobs"][0] if "jobs" in jobs else jobs["job"][0]
95 self.status = self.job["status"]
~/anaconda3/lib/python3.6/site-packages/h2o/h2o.py in api(endpoint, data, json, filename, save_to)
101 # type checks are performed in H2OConnection class
102 _check_connection()
--> 103 return h2oconn.request(endpoint, data=data, json=json, filename=filename, save_to=save_to)
104
105
~/anaconda3/lib/python3.6/site-packages/h2o/backend/connection.py in request(self, endpoint, data, json, filename, save_to)
408 else:
409 self._log_end_exception(e)
--> 410 raise H2OConnectionError("Unexpected HTTP error: %s" % e)
411 except requests.exceptions.Timeout as e:
412 self._log_end_exception(e)
H2OConnectionError: Unexpected HTTP error: ('Connection aborted.', ConnectionResetError(104, 'Connection reset by peer'))