srome / pykliep Goto Github PK

Traceback (most recent call last):
File "challenge.py", line 187, in
weights = kliep.predict(X)
File "challenge.py", line 180, in predict
return np.dot(self._phi(X, sigma=sigma), self._alpha).reshape((X.shape[0],))
File "challenge.py", line 150, in _phi
sigma = self._sigma
AttributeError: DensityRatioEstimator instance has no attribute '_sigma'

As I execute:

kliep.fit(X_train, X_test)

AttributeError: 'dict' object has no attribute 'iteritems' come. How to resolve this.

Bothe X_train and X_test sets have shape of (5000, 256)

This function returns a zero matrix

def _phi(self, X, sigma=None):

    if sigma is None:
        sigma = self._sigma
    print(sigma , "****** sigma");
    print(X.shape)
    print((X-self._test_vectors).shape)
    #exit(-1)

    if self._phi_fitted:
        #print(np.exp(-np.sum((X-self._test_vectors)**2, axis=-1)/(2*sigma**2)))
        return np.exp(-np.sum((X-self._test_vectors)**2, axis=-1)/(2*sigma**2))
    raise Exception('Phi not fitted.')

'

Thanks for your implementation. I run the code in a training set of ~ 150k rows and a test set of ~ 80k rows with ~24 features and get Memory Error. The stack trace is:

  File "modeling.py", line 552, in score
    kliep.fit(X_train, X_test) # keyword arguments are X_train and X_test
  File "pykliep.py", line 83, in fit
    sigma=sigma)
  File "pykliep.py", line 124, in _fit
    sigma=sigma)
  File "pykliep.py", line 162, in _find_alpha
    b = self._phi(X_train, sigma).sum(axis=0) / X_train.shape[0]
  File "pykliep.py", line 154, in _phi
    return np.exp(-np.sum((X-self._test_vectors)**2, axis=-1)/(2*sigma**2))
MemoryError```

What is the possible cause of this error?

Just like it.

I am trying to follow the example and fit the model but keep getting the below error

My code looks like below

kliep = DensityRatioEstimator()
kliep.fit(X_train.values, X_test.values) # keyword arguments are X_train and X_test
weights = kliep.predict(X_train.values)

So, I went to the code file and replaced iteritems with items for python 3 but that still doesn't solve the error

---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
Input In [83], in <cell line: 2>()
      1 kliep = DensityRatioEstimator()
----> 2 kliep.fit(X_train.values, X_test.values) # keyword arguments are X_train and X_test
      3 weights = kliep.predict(X_train.values)

File ~\Downloads\pykliep.py:85, in DensityRatioEstimator.fit(self, X_train, X_test, alpha_0)
     79             j_scores[(num_param,sigma)][k-1] = self._fit(X_train=X_train, 
     80                                              X_test=X_test_fold,
     81                                              num_parameters = num_param,
     82                                              sigma=sigma)
     83         j_scores[(num_param,sigma)] = np.mean(j_scores[(num_param,sigma)])
---> 85 sorted_scores = sorted([x for x in j_scores.iteritems() if np.isfinite(x[1])], key=lambda x :x[1], reverse=True)
     86 if len(sorted_scores) == 0:
     87     warnings.warn('LCV failed to converge for all values of sigma.')

AttributeError: 'dict' object has no attribute 'iteritems'

I am getting keyerror while running the code. What could be the issue ?

`KeyError Traceback (most recent call last)
/Application/DataScience/Anaconda/anaconda3/lib/python3.6/site-packages/pandas/core/indexes/base.py in get_loc(self, key, method, tolerance)
3077 try:
-> 3078 return self._engine.get_loc(key)
3079 except KeyError:

pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_loc()

pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_loc()

pandas/_libs/hashtable_class_helper.pxi in pandas._libs.hashtable.PyObjectHashTable.get_item()

pandas/_libs/hashtable_class_helper.pxi in pandas._libs.hashtable.PyObjectHashTable.get_item()

KeyError: 44

During handling of the above exception, another exception occurred:

KeyError Traceback (most recent call last)
in ()
2
3 kliep = DensityRatioEstimator()
----> 4 kliep.fit(X_train, X_test) # keyword arguments are X_train and X_test
5 # weights = kliep.predict(X_train)
6

~/nma/Shankar/pykliep.py in fit(self, X_train, X_test, alpha_0)
59 np.random.seed(self.random_state)
60 X_test_shuffled = X_test.copy()
---> 61 np.random.shuffle(X_test_shuffled)
62
63 j_scores = {}

mtrand.pyx in mtrand.RandomState.shuffle()

mtrand.pyx in mtrand.RandomState.shuffle()

/Application/DataScience/Anaconda/anaconda3/lib/python3.6/site-packages/pandas/core/frame.py in getitem(self, key)
2686 return self._getitem_multilevel(key)
2687 else:
-> 2688 return self._getitem_column(key)
2689
2690 def _getitem_column(self, key):

/Application/DataScience/Anaconda/anaconda3/lib/python3.6/site-packages/pandas/core/frame.py in _getitem_column(self, key)
2693 # get column
2694 if self.columns.is_unique:
-> 2695 return self._get_item_cache(key)
2696
2697 # duplicate columns & possible reduce dimensionality

/Application/DataScience/Anaconda/anaconda3/lib/python3.6/site-packages/pandas/core/generic.py in _get_item_cache(self, item)
2487 res = cache.get(item)
2488 if res is None:
-> 2489 values = self._data.get(item)
2490 res = self._box_item_values(item, values)
2491 cache[item] = res

/Application/DataScience/Anaconda/anaconda3/lib/python3.6/site-packages/pandas/core/internals.py in get(self, item, fastpath)
4113
4114 if not isna(item):
-> 4115 loc = self.items.get_loc(item)
4116 else:
4117 indexer = np.arange(len(self.items))[isna(self.items)]

/Application/DataScience/Anaconda/anaconda3/lib/python3.6/site-packages/pandas/core/indexes/base.py in get_loc(self, key, method, tolerance)
3078 return self._engine.get_loc(key)
3079 except KeyError:
-> 3080 return self._engine.get_loc(self._maybe_cast_indexer(key))
3081
3082 indexer = self.get_indexer([key], method=method, tolerance=tolerance)

pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_loc()

pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_loc()

pandas/_libs/hashtable_class_helper.pxi in pandas._libs.hashtable.PyObjectHashTable.get_item()

pandas/_libs/hashtable_class_helper.pxi in pandas._libs.hashtable.PyObjectHashTable.get_item()

KeyError: 44`