pymc3: Disaster example with deterministic switchpoint function - python
I'm trying to reproduce coal mining example with deterministic function for switchpoint instead of using theano's switch function. Code:
%matplotlib inline
import matplotlib.pyplot as plt
import pymc3
import numpy as np
import theano.tensor as t
import theano
data = np.hstack((np.random.poisson(15,1000),np.random.poisson(2,100)))
plt.plot(data)
#theano.compile.ops.as_op(itypes=[t.lscalar, t.dscalar,t.dscalar],otypes=[t.dvector])
def rate1(sw,mu1,mu2):
n = len(data)
out = np.empty(n)
out[:sw] = mu1
out[sw:] = mu2
return out
with pymc3.Model() as dis:
switchpoint = pymc3.DiscreteUniform('switchpoint',lower=0, upper=len(data)-1)
mu1 = pymc3.Exponential('mu1', lam=1.)
mu2 = pymc3.Exponential('mu2',lam=1.)
disasters=pymc3.Poisson('disasters', mu=rate1, observed = data)
But this code rise an error:
--------------------------------------------------------------------------- KeyError Traceback (most recent call
last) c:\program files\git\theano\theano\tensor\type.py in
dtype_specs(self)
266 'complex64': (complex, 'theano_complex64', 'NPY_COMPLEX64')
--> 267 }[self.dtype]
268 except KeyError:
KeyError: 'object'
During handling of the above exception, another exception occurred:
TypeError Traceback (most recent call
last) c:\program files\git\theano\theano\tensor\basic.py in
constant_or_value(x, rtype, name, ndim, dtype)
407 rval = rtype(
--> 408 TensorType(dtype=x_.dtype, broadcastable=bcastable),
409 x_.copy(),
c:\program files\git\theano\theano\tensor\type.py in init(self,
dtype, broadcastable, name, sparse_grad)
49 self.broadcastable = tuple(bool(b) for b in broadcastable)
---> 50 self.dtype_specs() # error checking is done there
51 self.name = name
c:\program files\git\theano\theano\tensor\type.py in dtype_specs(self)
269 raise TypeError("Unsupported dtype for %s: %s"
--> 270 % (self.class.name, self.dtype))
271
TypeError: Unsupported dtype for TensorType: object
During handling of the above exception, another exception occurred:
TypeError Traceback (most recent call
last) c:\program files\git\theano\theano\tensor\basic.py in
as_tensor_variable(x, name, ndim)
201 try:
--> 202 return constant(x, name=name, ndim=ndim)
203 except TypeError:
c:\program files\git\theano\theano\tensor\basic.py in constant(x,
name, ndim, dtype)
421 ret = constant_or_value(x, rtype=TensorConstant, name=name, ndim=ndim,
--> 422 dtype=dtype)
423
c:\program files\git\theano\theano\tensor\basic.py in
constant_or_value(x, rtype, name, ndim, dtype)
416 except Exception:
--> 417 raise TypeError("Could not convert %s to TensorType" % x, type(x))
418
TypeError: ('Could not convert FromFunctionOp{rate1} to TensorType',
)
During handling of the above exception, another exception occurred:
AsTensorError Traceback (most recent call
last) in ()
14 mu2 = pymc3.Exponential('mu2',lam=1.)
15 #rate1 = pymc3.switch(switchpoint >= np.arange(len(data)), mu1,mu2)
---> 16 disasters=pymc3.Poisson('disasters', mu=rate1, observed = data)
C:\Users\User\Anaconda3\lib\site-packages\pymc3\distributions\distribution.py
in new(cls, name, *args, **kwargs)
19 if isinstance(name, str):
20 data = kwargs.pop('observed', None)
---> 21 dist = cls.dist(*args, **kwargs)
22 return model.Var(name, dist, data)
23 elif name is None:
C:\Users\User\Anaconda3\lib\site-packages\pymc3\distributions\distribution.py
in dist(cls, *args, **kwargs)
32 def dist(cls, *args, **kwargs):
33 dist = object.new(cls)
---> 34 dist.init(*args, **kwargs)
35 return dist
36
C:\Users\User\Anaconda3\lib\site-packages\pymc3\distributions\discrete.py
in init(self, mu, *args, **kwargs)
185 super(Poisson, self).init(*args, **kwargs)
186 self.mu = mu
--> 187 self.mode = floor(mu).astype('int32')
188
189 def random(self, point=None, size=None, repeat=None):
c:\program files\git\theano\theano\gof\op.py in call(self,
*inputs, **kwargs)
598 """
599 return_list = kwargs.pop('return_list', False)
--> 600 node = self.make_node(*inputs, **kwargs)
601
602 if config.compute_test_value != 'off':
c:\program files\git\theano\theano\tensor\elemwise.py in
make_node(self, *inputs)
540 using DimShuffle.
541 """
--> 542 inputs = list(map(as_tensor_variable, inputs))
543 shadow = self.scalar_op.make_node(
544 *[get_scalar_type(dtype=i.type.dtype).make_variable()
c:\program files\git\theano\theano\tensor\basic.py in
as_tensor_variable(x, name, ndim)
206 except Exception:
207 str_x = repr(x)
--> 208 raise AsTensorError("Cannot convert %s to TensorType" % str_x, type(x))
209
210 # this has a different name, because _as_tensor_variable is the
AsTensorError: ('Cannot convert FromFunctionOp{rate1} to TensorType',
)
How i handle this?
The second thing - when i'm using the pymc3.switch function like this:
with pymc3.Model() as dis:
switchpoint = pymc3.DiscreteUniform('switchpoint',lower=0, upper=len(data)-1)
mu1 = pymc3.Exponential('mu1', lam=1.)
mu2 = pymc3.Exponential('mu2',lam=1.)
rate1 = pymc3.switch(switchpoint >= np.arange(len(data)), mu1,mu2)
disasters=pymc3.Poisson('disasters', mu=rate1, observed = data)
And next try to sample:
with dis:
step1 = pymc3.NUTS([mu1, mu2])
step2 = pymc3.Metropolis([switchpoint])
trace = pymc3.sample(10000, step = [step1,step2])
I get an error:
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
c:\program files\git\theano\theano\compile\function_module.py in __call__(self, *args, **kwargs)
858 try:
--> 859 outputs = self.fn()
860 except Exception:
TypeError: expected type_num 9 (NPY_INT64) got 7
During handling of the above exception, another exception occurred:
TypeError Traceback (most recent call last)
<ipython-input-4-3247d908f897> in <module>()
2 step1 = pymc3.NUTS([mu1, mu2])
3 step2 = pymc3.Metropolis([switchpoint])
----> 4 trace = pymc3.sample(10000, step = [step1,step2])
C:\Users\User\Anaconda3\lib\site-packages\pymc3\sampling.py in sample(draws, step, start, trace, chain, njobs, tune, progressbar, model, random_seed)
153 sample_args = [draws, step, start, trace, chain,
154 tune, progressbar, model, random_seed]
--> 155 return sample_func(*sample_args)
156
157
C:\Users\User\Anaconda3\lib\site-packages\pymc3\sampling.py in _sample(draws, step, start, trace, chain, tune, progressbar, model, random_seed)
162 progress = progress_bar(draws)
163 try:
--> 164 for i, strace in enumerate(sampling):
165 if progressbar:
166 progress.update(i)
C:\Users\User\Anaconda3\lib\site-packages\pymc3\sampling.py in _iter_sample(draws, step, start, trace, chain, tune, model, random_seed)
244 if i == tune:
245 step = stop_tuning(step)
--> 246 point = step.step(point)
247 strace.record(point)
248 yield strace
C:\Users\User\Anaconda3\lib\site-packages\pymc3\step_methods\compound.py in step(self, point)
11 def step(self, point):
12 for method in self.methods:
---> 13 point = method.step(point)
14 return point
C:\Users\User\Anaconda3\lib\site-packages\pymc3\step_methods\arraystep.py in step(self, point)
116 bij = DictToArrayBijection(self.ordering, point)
117
--> 118 apoint = self.astep(bij.map(point))
119 return bij.rmap(apoint)
120
C:\Users\User\Anaconda3\lib\site-packages\pymc3\step_methods\metropolis.py in astep(self, q0)
123
124
--> 125 q_new = metrop_select(self.delta_logp(q,q0), q, q0)
126
127 if q_new is q:
c:\program files\git\theano\theano\compile\function_module.py in __call__(self, *args, **kwargs)
869 node=self.fn.nodes[self.fn.position_of_error],
870 thunk=thunk,
--> 871 storage_map=getattr(self.fn, 'storage_map', None))
872 else:
873 # old-style linkers raise their own exceptions
c:\program files\git\theano\theano\gof\link.py in raise_with_op(node, thunk, exc_info, storage_map)
312 # extra long error message in that case.
313 pass
--> 314 reraise(exc_type, exc_value, exc_trace)
315
316
C:\Users\User\Anaconda3\lib\site-packages\six.py in reraise(tp, value, tb)
656 value = tp()
657 if value.__traceback__ is not tb:
--> 658 raise value.with_traceback(tb)
659 raise value
660
c:\program files\git\theano\theano\compile\function_module.py in __call__(self, *args, **kwargs)
857 t0_fn = time.time()
858 try:
--> 859 outputs = self.fn()
860 except Exception:
861 if hasattr(self.fn, 'position_of_error'):
TypeError: expected type_num 9 (NPY_INT64) got 7
Apply node that caused the error: Elemwise{Composite{Switch(GE(i0, i1), i2, i3)}}(InplaceDimShuffle{x}.0, TensorConstant{[ 0 1..1098 1099]}, InplaceDimShuffle{x}.0, InplaceDimShuffle{x}.0)
Toposort index: 11
Inputs types: [TensorType(int64, (True,)), TensorType(int32, vector), TensorType(float64, (True,)), TensorType(float64, (True,))]
Inputs shapes: [(1,), (1100,), (1,), (1,)]
Inputs strides: [(4,), (4,), (8,), (8,)]
Inputs values: [array([549]), 'not shown', array([ 1.07762995]), array([ 1.01502801])]
Outputs clients: [[Elemwise{eq,no_inplace}(Elemwise{Composite{Switch(GE(i0, i1), i2, i3)}}.0, TensorConstant{(1,) of 0}), Elemwise{Composite{Switch(GE(i0, i1), ((Switch(i2, i3, (i4 * log(i0))) - i5) - i0), i3)}}[(0, 0)](Elemwise{Composite{Switch(GE(i0, i1), i2, i3)}}.0, TensorConstant{(1,) of 0}, InplaceDimShuffle{x}.0, TensorConstant{(1,) of -inf}, TensorConstant{[ 13. 13... 0. 1.]}, TensorConstant{[ 22.55216... ]})]]
HINT: Re-running with most Theano optimization disabled could give you a back-trace of when this node was created. This can be done with by setting the Theano flag 'optimizer=fast_compile'. If that does not work, Theano optimizations can be disabled with 'optimizer=None'.
HINT: Use the Theano flag 'exception_verbosity=high' for a debugprint and storage map footprint of this apply node.
Being simple analyst, should i learn all this stuff about theano to being able to work with my statistical problems? Is a new mcmc sampler with gradient feature is only one thing that should motivates me to switch from pymc2 to pymc3?
For your first question, it looks like you're trying to pass a theano function as a variable. You need to call the function with the other variables as arguments, which will then return a theano variable. Try changing your line to
disasters=pymc3.Poisson('disasters', mu=rate1(switchpoint, mu1, mu2), observed = data)
I couldn't reproduce the error in your second part; the sampling worked just fine for me.
Related
Custom scaler transformer fit error only when used in ColumnTransformer pipeline
I have a df with some columns target time series which I need to scale as 1D array and as two thus defining custom wrapper to extend scikit-learn scalers with optional preprocessing as flatten. transform and inverse_transform are not posted for simplicity
import copy
class ScalerOptFlatten( TransformerMixin,
BaseEstimator ):
def __init__( self, instance, flatten , **kwargs):
#super().__init__(**kwargs)
self.scaler = instance
self.flatten = flatten
def get_params(self, deep=True):
cp = copy.copy(self.scaler)
cp.__class__ = type(self.scaler)
params = type(self.scaler).get_params(cp, deep)
return params
def fit( self, X, y = None ):
if self.flatten:
scale_in = X.reshape(-1).reshape(-1, 1)
else:
scale_in = X
if y==None:
self.scaler.fit(scale_in)
else:
self.scaler.fit(scale_in,y)
return self
It works when used on its own
scaler_transformer = ScalerOptFlatten( instance = StandardScaler(),
flatten = True )
scaler_transformer.fit(df_unstack)
But fails when stacked in
preprocessor = ColumnTransformer(
transformers=[
("ts", scaler_transformer, target_feature_names)
]
)
preprocessor.fit(df_unstack)
With
---------------------------------------------------------------------------
Empty Traceback (most recent call last)
~/anaconda3/envs/tf_2_2_0/lib/python3.8/site-packages/joblib/parallel.py in dispatch_one_batch(self, iterator)
826 try:
--> 827 tasks = self._ready_batches.get(block=False)
828 except queue.Empty:
~/anaconda3/envs/tf_2_2_0/lib/python3.8/queue.py in get(self, block, timeout)
166 if not self._qsize():
--> 167 raise Empty
168 elif timeout is None:
Empty:
During handling of the above exception, another exception occurred:
TypeError Traceback (most recent call last)
<ipython-input-494-0eb4b591d8a6> in <module>
----> 1 ts_scaler_step.fit(df_unstack)
~/anaconda3/envs/tf_2_2_0/lib/python3.8/site-packages/sklearn/compose/_column_transformer.py in fit(self, X, y)
492 # we use fit_transform to make sure to set sparse_output_ (for which we
493 # need the transformed data) to have consistent output type in predict
--> 494 self.fit_transform(X, y=y)
495 return self
496
~/anaconda3/envs/tf_2_2_0/lib/python3.8/site-packages/sklearn/compose/_column_transformer.py in fit_transform(self, X, y)
529 self._validate_remainder(X)
530
--> 531 result = self._fit_transform(X, y, _fit_transform_one)
532
533 if not result:
~/anaconda3/envs/tf_2_2_0/lib/python3.8/site-packages/sklearn/compose/_column_transformer.py in _fit_transform(self, X, y, func, fitted)
456 self._iter(fitted=fitted, replace_strings=True))
457 try:
--> 458 return Parallel(n_jobs=self.n_jobs)(
459 delayed(func)(
460 transformer=clone(trans) if not fitted else trans,
~/anaconda3/envs/tf_2_2_0/lib/python3.8/site-packages/joblib/parallel.py in __call__(self, iterable)
1046 # remaining jobs.
1047 self._iterating = False
-> 1048 if self.dispatch_one_batch(iterator):
1049 self._iterating = self._original_iterator is not None
1050
~/anaconda3/envs/tf_2_2_0/lib/python3.8/site-packages/joblib/parallel.py in dispatch_one_batch(self, iterator)
836 big_batch_size = batch_size * n_jobs
837
--> 838 islice = list(itertools.islice(iterator, big_batch_size))
839 if len(islice) == 0:
840 return False
~/anaconda3/envs/tf_2_2_0/lib/python3.8/site-packages/sklearn/compose/_column_transformer.py in <genexpr>(.0)
458 return Parallel(n_jobs=self.n_jobs)(
459 delayed(func)(
--> 460 transformer=clone(trans) if not fitted else trans,
461 X=_safe_indexing(X, column, axis=1),
462 y=y,
~/anaconda3/envs/tf_2_2_0/lib/python3.8/site-packages/sklearn/utils/validation.py in inner_f(*args, **kwargs)
70 FutureWarning)
71 kwargs.update({k: arg for k, arg in zip(sig.parameters, args)})
---> 72 return f(**kwargs)
73 return inner_f
74
~/anaconda3/envs/tf_2_2_0/lib/python3.8/site-packages/sklearn/base.py in clone(estimator, safe)
86 for name, param in new_object_params.items():
87 new_object_params[name] = clone(param, safe=False)
---> 88 new_object = klass(**new_object_params)
89 params_set = new_object.get_params(deep=False)
90
TypeError: __init__() missing 2 required positional arguments: 'instance' and 'flatten'
I suspect that error is in get_param method
Simple code for phi(k) correlation matrix in Python
I am looking for a simple way (2 or 3 lines of code) to generate a Phi(k) correlation matrix in Python. That should be possible since pandas_profiling is doing it, and it works fine. But I want to be able to do it without pandas_profiling which is too heavy and computes things I don't need. pandas_profiling is using phik library. I tried phik library (didn't find anything else) I don't understand the error I got : TypeError: sequence item 0: expected str instance, int found I have no int in my dataframe. Seems like a bug in phik, but then how does pandas profiling do, since it's using it too ? What's happening here ? Many thanks I have this code : import numpy as np import pandas as pd import phik NB_SAMPLES = 200 NB_VARIABLES = 3 rand_mat = np.random.uniform(low=0.5, high=15, size=(NB_SAMPLES,NB_VARIABLES)) df = pd.DataFrame(rand_mat) df['cat_column'] = pd.cut(df[0], bins=5, labels=['F1','F2','F3','F4','F5']) print(df) df.phik_matrix() Result : 0 1 2 cat_column 0 0.911098 8.549206 9.270484 F1 1 13.591250 9.161498 5.614470 F5 2 3.308305 1.589402 5.394675 F1 3 12.031064 9.968686 7.519628 F5 4 14.427813 1.533533 2.352659 F5 .. ... ... ... ... 195 10.556285 3.541869 4.804826 F4 196 5.721784 11.783908 13.104844 F2 197 7.336637 14.512256 14.993096 F3 198 4.375895 11.881784 1.129816 F2 199 0.519900 6.624423 9.239070 F1 [200 rows x 4 columns] interval_cols not set, guessing: [0, 1, 2] --------------------------------------------------------------------------- _RemoteTraceback Traceback (most recent call last) _RemoteTraceback: """ Traceback (most recent call last): File "/opt/conda/lib/python3.7/site-packages/joblib/externals/loky/process_executor.py", line 418, in _process_worker r = call_item() File "/opt/conda/lib/python3.7/site-packages/joblib/externals/loky/process_executor.py", line 272, in __call__ return self.fn(*self.args, **self.kwargs) File "/opt/conda/lib/python3.7/site-packages/joblib/_parallel_backends.py", line 608, in __call__ return self.func(*args, **kwargs) File "/opt/conda/lib/python3.7/site-packages/joblib/parallel.py", line 256, in __call__ for func, args, kwargs in self.items] File "/opt/conda/lib/python3.7/site-packages/joblib/parallel.py", line 256, in <listcomp> for func, args, kwargs in self.items] File "/opt/conda/lib/python3.7/site-packages/phik/phik.py", line 162, in _calc_phik combi = ':'.join(comb) TypeError: sequence item 0: expected str instance, int found """ The above exception was the direct cause of the following exception: TypeError Traceback (most recent call last) <ipython-input-31-398c72b34799> in <module> 11 df['cat_column'] = pd.cut(df[0], bins=5, labels=['F1','F2','F3','F4','F5']) 12 print(df) ---> 13 df.phik_matrix() /opt/conda/lib/python3.7/site-packages/phik/phik.py in phik_matrix(df, interval_cols, bins, quantile, noise_correction, dropna, drop_underflow, drop_overflow) 215 data_binned, binning_dict = bin_data(df_clean, cols=interval_cols_clean, bins=bins, quantile=quantile, retbins=True) 216 return phik_from_rebinned_df(data_binned, noise_correction, dropna=dropna, drop_underflow=drop_underflow, --> 217 drop_overflow=drop_overflow) 218 219 /opt/conda/lib/python3.7/site-packages/phik/phik.py in phik_from_rebinned_df(data_binned, noise_correction, dropna, drop_underflow, drop_overflow) 145 146 phik_list = Parallel(n_jobs=NCORES)(delayed(_calc_phik)(co, data_binned[list(co)], noise_correction) --> 147 for co in itertools.combinations_with_replacement(data_binned.columns.values, 2)) 148 149 phik_overview = create_correlation_overview_table(dict(phik_list)) /opt/conda/lib/python3.7/site-packages/joblib/parallel.py in __call__(self, iterable) 1015 1016 with self._backend.retrieval_context(): -> 1017 self.retrieve() 1018 # Make sure that we get a last message telling us we are done 1019 elapsed_time = time.time() - self._start_time /opt/conda/lib/python3.7/site-packages/joblib/parallel.py in retrieve(self) 907 try: 908 if getattr(self._backend, 'supports_timeout', False): --> 909 self._output.extend(job.get(timeout=self.timeout)) 910 else: 911 self._output.extend(job.get()) /opt/conda/lib/python3.7/site-packages/joblib/_parallel_backends.py in wrap_future_result(future, timeout) 560 AsyncResults.get from multiprocessing.""" 561 try: --> 562 return future.result(timeout=timeout) 563 except LokyTimeoutError: 564 raise TimeoutError() /opt/conda/lib/python3.7/concurrent/futures/_base.py in result(self, timeout) 433 raise CancelledError() 434 elif self._state == FINISHED: --> 435 return self.__get_result() 436 else: 437 raise TimeoutError() /opt/conda/lib/python3.7/concurrent/futures/_base.py in __get_result(self) 382 def __get_result(self): 383 if self._exception: --> 384 raise self._exception 385 else: 386 return self._result TypeError: sequence item 0: expected str instance, int found
Try to reinstall the phik module as the following: pip install phik==0.10.0 Then, your code together with sns.heatmap results the following:
Pipeline error (ValueError: Specifying the columns using strings is only supported for pandas DataFrames)
The example is fully reproducible. Here is full notebook (which downloads data too): https://github.com/ageron/handson-ml2/blob/master/02_end_to_end_machine_learning_project.ipynb
After this part in notebook above:
full_pipeline_with_predictor = Pipeline([
("preparation", full_pipeline),
("linear", LinearRegression())
])
full_pipeline_with_predictor.fit(housing, housing_labels)
full_pipeline_with_predictor.predict(some_data)
I am trying to get predictions on the test set with this code:
X_test_prepared = full_pipeline.transform(X_test)
final_predictions = full_pipeline_with_predictor.predict(X_test_prepared)
But I am receiving error:
C:\Users\Alex\AppData\Local\Continuum\anaconda3\lib\site-packages\sklearn\compose\_column_transformer.py:430: FutureWarning: Given feature/column names or counts do not match the ones for the data given during fit. This will fail from v0.24.
FutureWarning)
---------------------------------------------------------------------------
Empty Traceback (most recent call last)
~\AppData\Local\Continuum\anaconda3\lib\site-packages\joblib\parallel.py in dispatch_one_batch(self, iterator)
796 try:
--> 797 tasks = self._ready_batches.get(block=False)
798 except queue.Empty:
~\AppData\Local\Continuum\anaconda3\lib\queue.py in get(self, block, timeout)
166 if not self._qsize():
--> 167 raise Empty
168 elif timeout is None:
Empty:
During handling of the above exception, another exception occurred:
ValueError Traceback (most recent call last)
<ipython-input-141-dc87b1c9e658> in <module>
5
6 X_test_prepared = full_pipeline.transform(X_test)
----> 7 final_predictions = full_pipeline_with_predictor.predict(X_test_prepared)
8
9 final_mse = mean_squared_error(y_test, final_predictions)
~\AppData\Local\Continuum\anaconda3\lib\site-packages\sklearn\utils\metaestimators.py in <lambda>(*args, **kwargs)
114
115 # lambda, but not partial, allows help() to work with update_wrapper
--> 116 out = lambda *args, **kwargs: self.fn(obj, *args, **kwargs)
117 # update the docstring of the returned function
118 update_wrapper(out, self.fn)
~\AppData\Local\Continuum\anaconda3\lib\site-packages\sklearn\pipeline.py in predict(self, X, **predict_params)
417 Xt = X
418 for _, name, transform in self._iter(with_final=False):
--> 419 Xt = transform.transform(Xt)
420 return self.steps[-1][-1].predict(Xt, **predict_params)
421
~\AppData\Local\Continuum\anaconda3\lib\site-packages\sklearn\compose\_column_transformer.py in transform(self, X)
586
587 self._validate_features(X.shape[1], X_feature_names)
--> 588 Xs = self._fit_transform(X, None, _transform_one, fitted=True)
589 self._validate_output(Xs)
590
~\AppData\Local\Continuum\anaconda3\lib\site-packages\sklearn\compose\_column_transformer.py in _fit_transform(self, X, y, func, fitted)
455 message=self._log_message(name, idx, len(transformers)))
456 for idx, (name, trans, column, weight) in enumerate(
--> 457 self._iter(fitted=fitted, replace_strings=True), 1))
458 except ValueError as e:
459 if "Expected 2D array, got 1D array instead" in str(e):
~\AppData\Local\Continuum\anaconda3\lib\site-packages\joblib\parallel.py in __call__(self, iterable)
1002 # remaining jobs.
1003 self._iterating = False
-> 1004 if self.dispatch_one_batch(iterator):
1005 self._iterating = self._original_iterator is not None
1006
~\AppData\Local\Continuum\anaconda3\lib\site-packages\joblib\parallel.py in dispatch_one_batch(self, iterator)
806 big_batch_size = batch_size * n_jobs
807
--> 808 islice = list(itertools.islice(iterator, big_batch_size))
809 if len(islice) == 0:
810 return False
~\AppData\Local\Continuum\anaconda3\lib\site-packages\sklearn\compose\_column_transformer.py in <genexpr>(.0)
454 message_clsname='ColumnTransformer',
455 message=self._log_message(name, idx, len(transformers)))
--> 456 for idx, (name, trans, column, weight) in enumerate(
457 self._iter(fitted=fitted, replace_strings=True), 1))
458 except ValueError as e:
~\AppData\Local\Continuum\anaconda3\lib\site-packages\sklearn\utils\__init__.py in _safe_indexing(X, indices, axis)
404 if axis == 1 and indices_dtype == 'str' and not hasattr(X, 'loc'):
405 raise ValueError(
--> 406 "Specifying the columns using strings is only supported for "
407 "pandas DataFrames"
408 )
ValueError: Specifying the columns using strings is only supported for pandas DataFrames
Question: How can I correct that error? And why that error happens?
Since your final pipeline:
full_pipeline_with_predictor = Pipeline([
("preparation", full_pipeline),
("linear", LinearRegression())
])
clearly contains already the full_pipeline, you should not "prepare" again your X_test; doing so, you are "preparing" X_test twice, which is wrong. So, your code should be simply
final_predictions = full_pipeline_with_predictor.predict(X_test)
exactly as it is for getting predictions for some_data, i.e.
full_pipeline_with_predictor.predict(some_data)
which some_data you correctly do not "prepare" before feeding them into the final pipeline.
The whole point of using pipelines is exactly this, i.e. to avoid having to run separately fit-predict for possibly several preparation steps, having wrapped all of them into a single pipeline instead. You correctly apply this process here when you predict some_data, but you somehow seem to have forgotten it in the next step, when you try to predict X_test.
How can I load sklearn data in Jupyter Python 3?
Hey I have a very short question. I need to load data for my machine learning course, but it does not work for me and I have no idea why. Im using Jupyter with Python 3.
My Code:
from sklearn.datasets import fetch_covtype
forest = fetch_covtype()
For my friend it works fine with the same conditions. I already tried to update sklearn with pip install -U scikit-learn, but it did not solve the problem. I hope somebody can help me.
It creates the following error:
UnboundLocalError Traceback (most recent call last)
/opt/conda/lib/python3.7/site-packages/sklearn/datasets/covtype.py in fetch_covtype(data_home, download_if_missing, random_state, shuffle, return_X_y)
126 try:
--> 127 X, y
128 except NameError:
UnboundLocalError: local variable 'X' referenced before assignment
During handling of the above exception, another exception occurred:
ValueError Traceback (most recent call last)
<ipython-input-9-fb303a92b6ca> in <module>
----> 1 forest =fetch_covtype()
/opt/conda/lib/python3.7/site-packages/sklearn/datasets/covtype.py in fetch_covtype(data_home, download_if_missing, random_state, shuffle, return_X_y)
127 X, y
128 except NameError:
--> 129 X, y = _refresh_cache([samples_path, targets_path], 9)
130 # TODO: Revert to the following two lines in v0.23
131 # X = joblib.load(samples_path)
/opt/conda/lib/python3.7/site-packages/sklearn/datasets/base.py in _refresh_cache(files, compress)
928 msg = "sklearn.externals.joblib is deprecated in 0.21"
929 with warnings.catch_warnings(record=True) as warns:
--> 930 data = tuple([joblib.load(f) for f in files])
931
932 refresh_needed = any([str(x.message).startswith(msg) for x in warns])
/opt/conda/lib/python3.7/site-packages/sklearn/datasets/base.py in <listcomp>(.0)
928 msg = "sklearn.externals.joblib is deprecated in 0.21"
929 with warnings.catch_warnings(record=True) as warns:
--> 930 data = tuple([joblib.load(f) for f in files])
931
932 refresh_needed = any([str(x.message).startswith(msg) for x in warns])
/opt/conda/lib/python3.7/site-packages/joblib/numpy_pickle.py in load(filename, mmap_mode)
603 return load_compatibility(fobj)
604
--> 605 obj = _unpickle(fobj, filename, mmap_mode)
606
607 return obj
/opt/conda/lib/python3.7/site-packages/joblib/numpy_pickle.py in _unpickle(fobj, filename, mmap_mode)
527 obj = None
528 try:
--> 529 obj = unpickler.load()
530 if unpickler.compat_mode:
531 warnings.warn("The file '%s' has been generated with a "
/opt/conda/lib/python3.7/pickle.py in load(self)
1083 raise EOFError
1084 assert isinstance(key, bytes_types)
-> 1085 dispatch[key[0]](self)
1086 except _Stop as stopinst:
1087 return stopinst.value
/opt/conda/lib/python3.7/site-packages/joblib/numpy_pickle.py in load_build(self)
353 if isinstance(array_wrapper, NDArrayWrapper):
354 self.compat_mode = True
--> 355 self.stack.append(array_wrapper.read(self))
356
357 # Be careful to register our new method.
/opt/conda/lib/python3.7/site-packages/joblib/numpy_pickle.py in read(self, unpickler)
196 array = self.read_mmap(unpickler)
197 else:
--> 198 array = self.read_array(unpickler)
199
200 # Manage array subclass case
/opt/conda/lib/python3.7/site-packages/joblib/numpy_pickle.py in read_array(self, unpickler)
147 read_size = int(read_count * self.dtype.itemsize)
148 data = _read_bytes(unpickler.file_handle,
--> 149 read_size, "array data")
150 array[i:i + read_count] = \
151 unpickler.np.frombuffer(data, dtype=self.dtype,
/opt/conda/lib/python3.7/site-packages/joblib/numpy_pickle_utils.py in _read_bytes(fp, size, error_template)
241 if len(data) != size:
242 msg = "EOF: reading %s, expected %d bytes got %d"
--> 243 raise ValueError(msg % (error_template, size, len(data)))
244 else:
245 return data
ValueError: EOF: reading array data, expected 262144 bytes got 209661
NameError: name 'onset_to_death' is not defined. Works in Py2 but not Py3
I'm taking an online python course (EpiSkills, which uses the Jupyter notebook) that was written in Python 2.7, and I'm on Python 3.6.4 so I have run into a few compatibility issues along the way. Most of the time I've been able to stumble through, but can't figure out this one, so was hoping someone might be able to help.
I start with the following packages:
import pandas as pd
import epipy
import seaborn as sns
%pylab inline
import statsmodels.api as sm
from scipy import stats
import numpy as np
And use the following code to create a pandas series and model:
multivar_model = sm.formula.glm('age ~ onset_to_hospital + onset_to_death +
data=my_data).fit()
new_data = pd.Series([6, 8, 'male'], index=['onset_to_hospital', 'onset_to_death', 'sex'])
When I try to use this to the following code, I throw the error that I've attached:
multivar_model.predict(new_data)
NameError part1
NameError part2
The intended output is meant to be this:
array([ 60.6497459])
I know that a lot of NameErrors are because something has been specified in the local, not global, environment but I'm unsure how to correct it in this instance. Any help is much appreciated.
Thanks!
C
---------------------------------------------------------------------------
NameError Traceback (most recent call last)
~\AppData\Local\Enthought\Canopy\edm\envs\User\lib\site-packages\patsy\compat.py in call_and_wrap_exc(msg, origin, f, *args, **kwargs)
116 try:
--> 117 return f(*args, **kwargs)
118 except Exception as e:
~\AppData\Local\Enthought\Canopy\edm\envs\User\lib\site-packages\patsy\eval.py in eval(self, expr, source_name, inner_namespace)
165 return eval(code, {}, VarLookupDict([inner_namespace]
--> 166 + self._namespaces))
167
<string> in <module>()
NameError: name 'onset_to_death' is not defined
The above exception was the direct cause of the following exception:
PatsyError Traceback (most recent call last)
<ipython-input-79-e0364e267da7> in <module>()
----> 1 multivar_model.predict(new_data)
~\AppData\Local\Enthought\Canopy\edm\envs\User\lib\site-packages\statsmodels\base\model.py in predict(self, exog, transform, *args, **kwargs)
774 exog_index = exog.index
775 exog = dmatrix(self.model.data.design_info.builder,
--> 776 exog, return_type="dataframe")
777 if len(exog) < len(exog_index):
778 # missing values, rows have been dropped
~\AppData\Local\Enthought\Canopy\edm\envs\User\lib\site-packages\patsy\highlevel.py in dmatrix(formula_like, data, eval_env, NA_action, return_type)
289 eval_env = EvalEnvironment.capture(eval_env, reference=1)
290 (lhs, rhs) = _do_highlevel_design(formula_like, data, eval_env,
--> 291 NA_action, return_type)
292 if lhs.shape[1] != 0:
293 raise PatsyError("encountered outcome variables for a model "
~\AppData\Local\Enthought\Canopy\edm\envs\User\lib\site-packages\patsy\highlevel.py in _do_highlevel_design(formula_like, data, eval_env, NA_action, return_type)
167 return build_design_matrices(design_infos, data,
168 NA_action=NA_action,
--> 169 return_type=return_type)
170 else:
171 # No builders, but maybe we can still get matrices
~\AppData\Local\Enthought\Canopy\edm\envs\User\lib\site-packages\patsy\build.py in build_design_matrices(design_infos, data, NA_action, return_type, dtype)
886 for factor_info in six.itervalues(design_info.factor_infos):
887 if factor_info not in factor_info_to_values:
--> 888 value, is_NA = _eval_factor(factor_info, data, NA_action)
889 factor_info_to_isNAs[factor_info] = is_NA
890 # value may now be a Series, DataFrame, or ndarray
~\AppData\Local\Enthought\Canopy\edm\envs\User\lib\site-packages\patsy\build.py in _eval_factor(factor_info, data, NA_action)
61 def _eval_factor(factor_info, data, NA_action):
62 factor = factor_info.factor
---> 63 result = factor.eval(factor_info.state, data)
64 # Returns either a 2d ndarray, or a DataFrame, plus is_NA mask
65 if factor_info.type == "numerical":
~\AppData\Local\Enthought\Canopy\edm\envs\User\lib\site-packages\patsy\eval.py in eval(self, memorize_state, data)
564 return self._eval(memorize_state["eval_code"],
565 memorize_state,
--> 566 data)
567
568 __getstate__ = no_pickling
~\AppData\Local\Enthought\Canopy\edm\envs\User\lib\site-packages\patsy\eval.py in _eval(self, code, memorize_state, data)
549 memorize_state["eval_env"].eval,
550 code,
--> 551 inner_namespace=inner_namespace)
552
553 def memorize_chunk(self, state, which_pass, data):
~\AppData\Local\Enthought\Canopy\edm\envs\User\lib\site-packages\patsy\compat.py in call_and_wrap_exc(msg, origin, f, *args, **kwargs)
122 origin)
123 # Use 'exec' to hide this syntax from the Python 2 parser:
--> 124 exec("raise new_exc from e")
125 else:
126 # In python 2, we just let the original exception escape -- better
~\AppData\Local\Enthought\Canopy\edm\envs\User\lib\site-packages\patsy\compat.py in <module>()
PatsyError: Error evaluating factor: NameError: name 'onset_to_death' is not defined
age ~ onset_to_hospital + onset_to_death + sex
^^^^^^^^^^^^^^