ANOVA¶
Analysis of Variance models
Examples¶
In [1]: import statsmodels.api as sm
In [2]: from statsmodels.formula.api import ols
In [3]: moore = sm.datasets.get_rdataset("Moore", "car",
...: cache=True) # load data
...:
---------------------------------------------------------------------------
gaierror Traceback (most recent call last)
/usr/lib/python3.5/urllib/request.py in do_open(self, http_class, req, **http_conn_args)
1253 try:
-> 1254 h.request(req.get_method(), req.selector, req.data, headers)
1255 except OSError as err: # timeout error
/usr/lib/python3.5/http/client.py in request(self, method, url, body, headers)
1106 """Send a complete request to the server."""
-> 1107 self._send_request(method, url, body, headers)
1108
/usr/lib/python3.5/http/client.py in _send_request(self, method, url, body, headers)
1151 body = _encode(body, 'body')
-> 1152 self.endheaders(body)
1153
/usr/lib/python3.5/http/client.py in endheaders(self, message_body)
1102 raise CannotSendHeader()
-> 1103 self._send_output(message_body)
1104
/usr/lib/python3.5/http/client.py in _send_output(self, message_body)
933
--> 934 self.send(msg)
935 if message_body is not None:
/usr/lib/python3.5/http/client.py in send(self, data)
876 if self.auto_open:
--> 877 self.connect()
878 else:
/usr/lib/python3.5/http/client.py in connect(self)
1252
-> 1253 super().connect()
1254
/usr/lib/python3.5/http/client.py in connect(self)
848 self.sock = self._create_connection(
--> 849 (self.host,self.port), self.timeout, self.source_address)
850 self.sock.setsockopt(socket.IPPROTO_TCP, socket.TCP_NODELAY, 1)
/usr/lib/python3.5/socket.py in create_connection(address, timeout, source_address)
693 err = None
--> 694 for res in getaddrinfo(host, port, 0, SOCK_STREAM):
695 af, socktype, proto, canonname, sa = res
/usr/lib/python3.5/socket.py in getaddrinfo(host, port, family, type, proto, flags)
732 addrlist = []
--> 733 for res in _socket.getaddrinfo(host, port, family, type, proto, flags):
734 af, socktype, proto, canonname, sa = res
gaierror: [Errno -3] Temporary failure in name resolution
During handling of the above exception, another exception occurred:
URLError Traceback (most recent call last)
<ipython-input-3-924d52d36060> in <module>()
1 moore = sm.datasets.get_rdataset("Moore", "car",
----> 2 cache=True) # load data
/build/statsmodels-0.8.0/.pybuild/pythonX.Y_3.5/build/statsmodels/datasets/utils.py in get_rdataset(dataname, package, cache)
288 "master/doc/"+package+"/rst/")
289 cache = _get_cache(cache)
--> 290 data, from_cache = _get_data(data_base_url, dataname, cache)
291 data = read_csv(data, index_col=0)
292 data = _maybe_reset_index(data)
/build/statsmodels-0.8.0/.pybuild/pythonX.Y_3.5/build/statsmodels/datasets/utils.py in _get_data(base_url, dataname, cache, extension)
219 url = base_url + (dataname + ".%s") % extension
220 try:
--> 221 data, from_cache = _urlopen_cached(url, cache)
222 except HTTPError as err:
223 if '404' in str(err):
/build/statsmodels-0.8.0/.pybuild/pythonX.Y_3.5/build/statsmodels/datasets/utils.py in _urlopen_cached(url, cache)
210 # not using the cache or didn't find it in cache
211 if not from_cache:
--> 212 data = urlopen(url).read()
213 if cache is not None: # then put it in the cache
214 _cache_it(data, cache_path)
/usr/lib/python3.5/urllib/request.py in urlopen(url, data, timeout, cafile, capath, cadefault, context)
161 else:
162 opener = _opener
--> 163 return opener.open(url, data, timeout)
164
165 def install_opener(opener):
/usr/lib/python3.5/urllib/request.py in open(self, fullurl, data, timeout)
464 req = meth(req)
465
--> 466 response = self._open(req, data)
467
468 # post-process response
/usr/lib/python3.5/urllib/request.py in _open(self, req, data)
482 protocol = req.type
483 result = self._call_chain(self.handle_open, protocol, protocol +
--> 484 '_open', req)
485 if result:
486 return result
/usr/lib/python3.5/urllib/request.py in _call_chain(self, chain, kind, meth_name, *args)
442 for handler in handlers:
443 func = getattr(handler, meth_name)
--> 444 result = func(*args)
445 if result is not None:
446 return result
/usr/lib/python3.5/urllib/request.py in https_open(self, req)
1295 def https_open(self, req):
1296 return self.do_open(http.client.HTTPSConnection, req,
-> 1297 context=self._context, check_hostname=self._check_hostname)
1298
1299 https_request = AbstractHTTPHandler.do_request_
/usr/lib/python3.5/urllib/request.py in do_open(self, http_class, req, **http_conn_args)
1254 h.request(req.get_method(), req.selector, req.data, headers)
1255 except OSError as err: # timeout error
-> 1256 raise URLError(err)
1257 r = h.getresponse()
1258 except:
URLError: <urlopen error [Errno -3] Temporary failure in name resolution>
In [4]: data = moore.data
---------------------------------------------------------------------------
NameError Traceback (most recent call last)
<ipython-input-4-07b15baaa84d> in <module>()
----> 1 data = moore.data
NameError: name 'moore' is not defined
In [5]: data = data.rename(columns={"partner.status":
...: "partner_status"}) # make name pythonic
...:
---------------------------------------------------------------------------
NameError Traceback (most recent call last)
<ipython-input-5-76a0688779cd> in <module>()
----> 1 data = data.rename(columns={"partner.status":
2 "partner_status"}) # make name pythonic
3
NameError: name 'data' is not defined
In [6]: moore_lm = ols('conformity ~ C(fcategory, Sum)*C(partner_status, Sum)',
...: data=data).fit()
...:
---------------------------------------------------------------------------
NameError Traceback (most recent call last)
<ipython-input-6-0a291eef3047> in <module>()
1 moore_lm = ols('conformity ~ C(fcategory, Sum)*C(partner_status, Sum)',
----> 2 data=data).fit()
NameError: name 'data' is not defined
In [7]: table = sm.stats.anova_lm(moore_lm, typ=2) # Type 2 ANOVA DataFrame
---------------------------------------------------------------------------
NameError Traceback (most recent call last)
<ipython-input-7-4e32df33effd> in <module>()
----> 1 table = sm.stats.anova_lm(moore_lm, typ=2) # Type 2 ANOVA DataFrame
NameError: name 'moore_lm' is not defined
In [8]: print(table)
---------------------------------------------------------------------------
NameError Traceback (most recent call last)
<ipython-input-8-d1f157ed9e2f> in <module>()
----> 1 print(table)
NameError: name 'table' is not defined
A more detailed example can be found here: