鸢尾花书系列学习记录——Book_1 ＜编程不难＞ 源码Bk1_Cho5_18

鸢尾花书籍源码链接

问题：jupyter 导入seaborn数据集失败

报错内容（可以跳过）：

---------------------------------------------------------------------------
ConnectionRefusedError                    Traceback (most recent call last)
File /usr/lib/python3.10/urllib/request.py:1348, in AbstractHTTPHandler.do_open(self, http_class, req, **http_conn_args)
   1347 try:
-> 1348     h.request(req.get_method(), req.selector, req.data, headers,
   1349               encode_chunked=req.has_header('Transfer-encoding'))
   1350 except OSError as err: # timeout error

File /usr/lib/python3.10/http/client.py:1283, in HTTPConnection.request(self, method, url, body, headers, encode_chunked)
   1282 """Send a complete request to the server."""
-> 1283 self._send_request(method, url, body, headers, encode_chunked)

File /usr/lib/python3.10/http/client.py:1329, in HTTPConnection._send_request(self, method, url, body, headers, encode_chunked)
   1328     body = _encode(body, 'body')
-> 1329 self.endheaders(body, encode_chunked=encode_chunked)

File /usr/lib/python3.10/http/client.py:1278, in HTTPConnection.endheaders(self, message_body, encode_chunked)
   1277     raise CannotSendHeader()
-> 1278 self._send_output(message_body, encode_chunked=encode_chunked)

File /usr/lib/python3.10/http/client.py:1038, in HTTPConnection._send_output(self, message_body, encode_chunked)
   1037 del self._buffer[:]
-> 1038 self.send(msg)
   1040 if message_body is not None:
   1041 
   1042     # create a consistent interface to message_body

File /usr/lib/python3.10/http/client.py:976, in HTTPConnection.send(self, data)
    975 if self.auto_open:
--> 976     self.connect()
    977 else:

File /usr/lib/python3.10/http/client.py:1448, in HTTPSConnection.connect(self)
   1446 "Connect to a host on a given (SSL) port."
-> 1448 super().connect()
   1450 if self._tunnel_host:

File /usr/lib/python3.10/http/client.py:942, in HTTPConnection.connect(self)
    941 sys.audit("http.client.connect", self, self.host, self.port)
--> 942 self.sock = self._create_connection(
    943     (self.host,self.port), self.timeout, self.source_address)
    944 # Might fail in OSs that don't implement TCP_NODELAY

File /usr/lib/python3.10/socket.py:845, in create_connection(address, timeout, source_address)
    844 try:
--> 845     raise err
    846 finally:
    847     # Break explicitly a reference cycle

File /usr/lib/python3.10/socket.py:833, in create_connection(address, timeout, source_address)
    832     sock.bind(source_address)
--> 833 sock.connect(sa)
    834 # Break explicitly a reference cycle

ConnectionRefusedError: [Errno 111] Connection refused

During handling of the above exception, another exception occurred:

URLError                                  Traceback (most recent call last)
Cell In[8], line 2
      1 # 使用seaborn.load_dataset函数加载Iris数据集
----> 2 iris_df = sns.load_dataset("iris")

File ~/pyenv/Visualize-ML/lib/python3.10/site-packages/seaborn/utils.py:573, in load_dataset(name, cache, data_home, **kws)
    571 print(cache_path)
    572 if not os.path.exists(cache_path):
--> 573     if name not in get_dataset_names():
    574         raise ValueError(f"'{name}' is not one of the example datasets.")
    575     urlretrieve(url, cache_path)

File ~/pyenv/Visualize-ML/lib/python3.10/site-packages/seaborn/utils.py:499, in get_dataset_names()
    493 def get_dataset_names():
    494     """Report available example datasets, useful for reporting issues.
    495 
    496     Requires an internet connection.
    497 
    498     """
--> 499     with urlopen(DATASET_NAMES_URL) as resp:
    500         txt = resp.read()
    502     dataset_names = [name.strip() for name in txt.decode().split("\n")]

File /usr/lib/python3.10/urllib/request.py:216, in urlopen(url, data, timeout, cafile, capath, cadefault, context)
    214 else:
    215     opener = _opener
--> 216 return opener.open(url, data, timeout)

File /usr/lib/python3.10/urllib/request.py:519, in OpenerDirector.open(self, fullurl, data, timeout)
    516     req = meth(req)
    518 sys.audit('urllib.Request', req.full_url, req.data, req.headers, req.get_method())
--> 519 response = self._open(req, data)
    521 # post-process response
    522 meth_name = protocol+"_response"

File /usr/lib/python3.10/urllib/request.py:536, in OpenerDirector._open(self, req, data)
    533     return result
    535 protocol = req.type
--> 536 result = self._call_chain(self.handle_open, protocol, protocol +
    537                           '_open', req)
    538 if result:
    539     return result

File /usr/lib/python3.10/urllib/request.py:496, in OpenerDirector._call_chain(self, chain, kind, meth_name, *args)
    494 for handler in handlers:
    495     func = getattr(handler, meth_name)
--> 496     result = func(*args)
    497     if result is not None:
    498         return result

File /usr/lib/python3.10/urllib/request.py:1391, in HTTPSHandler.https_open(self, req)
   1390 def https_open(self, req):
-> 1391     return self.do_open(http.client.HTTPSConnection, req,
   1392         context=self._context, check_hostname=self._check_hostname)

File /usr/lib/python3.10/urllib/request.py:1351, in AbstractHTTPHandler.do_open(self, http_class, req, **http_conn_args)
   1348         h.request(req.get_method(), req.selector, req.data, headers,
   1349                   encode_chunked=req.has_header('Transfer-encoding'))
   1350     except OSError as err: # timeout error
-> 1351         raise URLError(err)
   1352     r = h.getresponse()
   1353 except:

URLError: <urlopen error [Errno 111] Connection refused>

解决方法：下载数据集到本地

1. 下载数据并解压

数据集下载

2. 查找数据集加载路径

找到源码文件：seaborn/utils.py
在第571行加入打印路径代码：

print(cache_path)

再次运行程序，报错前会打印一个路径，这个路径就是存储seaborn数据集的地方。我这里是/home/xx/.cache/seaborn/iris.csv

3.拷贝数据集到路径

将刚解压的文件拷贝到之前打印出来的目录。