I have 400 columns and I am trying to do min-max normalization (row-wise). For the first 200 points I want to do min-max normalization and scale it between 0 and 500 and do the same for the next two hundred points but scale it between 0 and 10.
import pandas as pd
import numpy as np
df = pd.DataFrame(np.random.randint(500,1000,size=(5, 400)))
def normalize(ds,value):
normalizedds = []
normalizedds.extend((ds[:value] - np.min(ds[:value])) / np.max(ds[:value] - np.min(ds[:value])) * 500)
normalizedds.extend(ds[value:value*2] / np.max(ds[value:value*2]) * 10)
return normalizedds
normalizeddsList = pd.DataFrame.from_records(df.apply(normalize, value=200, axis=1))
I get the following error!
ValueError Traceback (most recent call last)
~\AppData\Roaming\Python\Python37\site-packages\pandas\core\indexes\base.py in get_slice_bound(self, label, side, kind)
5166 try:
-> 5167 return self._searchsorted_monotonic(label, side)
5168 except ValueError:
~\AppData\Roaming\Python\Python37\site-packages\pandas\core\indexes\base.py in _searchsorted_monotonic(self, label, side)
5127
-> 5128 raise ValueError("index must be monotonic increasing or decreasing")
5129
ValueError: index must be monotonic increasing or decreasing
During handling of the above exception, another exception occurred:
KeyError Traceback (most recent call last)
in
----> 1 scaledCardList = pd.DataFrame.from_records(originalCardList.apply(scale, pointCount=200, axis=1))
~\AppData\Roaming\Python\Python37\site-packages\pandas\core\frame.py in apply(self, func, axis, broadcast, raw, reduce, result_type, args, **kwds)
6926 kwds=kwds,
6927 )
-> 6928 return op.get_result()
6929
6930 def applymap(self, func):
~\AppData\Roaming\Python\Python37\site-packages\pandas\core\apply.py in get_result(self)
184 return self.apply_raw()
185
--> 186 return self.apply_standard()
187
188 def apply_empty_result(self):
~\AppData\Roaming\Python\Python37\site-packages\pandas\core\apply.py in apply_standard(self)
290
291 # compute the result using the series generator
--> 292 self.apply_series_generator()
293
294 # wrap results
~\AppData\Roaming\Python\Python37\site-packages\pandas\core\apply.py in apply_series_generator(self)
319 try:
320 for i, v in enumerate(series_gen):
--> 321 results[i] = self.f(v)
322 keys.append(v.name)
323 except Exception as e:
~\AppData\Roaming\Python\Python37\site-packages\pandas\core\apply.py in f(x)
110
111 def f(x):
--> 112 return func(x, *args, **kwds)
113
114 else:
in scale(card, pointCount)
1 def scale(card, pointCount):
2 scaledCard = []
----> 3 scaledCard.extend((card[:pointCount] - np.min(card[:pointCount])) / np.max(card[:pointCount] - np.min(card[:pointCount])) * 10000)
4 scaledCard.extend(card[pointCount:pointCount*2] / np.max(card[pointCount:pointCount*2]) * 100)
5 return scaledCard
~\AppData\Roaming\Python\Python37\site-packages\pandas\core\series.py in getitem(self, key)
1111 key = check_bool_indexer(self.index, key)
1112
-> 1113 return self._get_with(key)
1114
1115 def _get_with(self, key):
~\AppData\Roaming\Python\Python37\site-packages\pandas\core\series.py in _get_with(self, key)
1116 # other: fancy integer or otherwise
1117 if isinstance(key, slice):
-> 1118 indexer = self.index._convert_slice_indexer(key, kind="getitem")
1119 return self._get_values(indexer)
1120 elif isinstance(key, ABCDataFrame):
~\AppData\Roaming\Python\Python37\site-packages\pandas\core\indexes\numeric.py in _convert_slice_indexer(self, key, kind)
395
396 # translate to locations
--> 397 return self.slice_indexer(key.start, key.stop, key.step, kind=kind)
398
399 def _format_native_types(
~\AppData\Roaming\Python\Python37\site-packages\pandas\core\indexes\base.py in slice_indexer(self, start, end, step, kind)
5032 slice(1, 3)
5033 """
-> 5034 start_slice, end_slice = self.slice_locs(start, end, step=step, kind=kind)
5035
5036 # return a slice
~\AppData\Roaming\Python\Python37\site-packages\pandas\core\indexes\base.py in slice_locs(self, start, end, step, kind)
5252 end_slice = None
5253 if end is not None:
-> 5254 end_slice = self.get_slice_bound(end, "right", kind)
5255 if end_slice is None:
5256 end_slice = len(self)
~\AppData\Roaming\Python\Python37\site-packages\pandas\core\indexes\base.py in get_slice_bound(self, label, side, kind)
5168 except ValueError:
5169 # raise the original KeyError
-> 5170 raise err
5171
5172 if isinstance(slc, np.ndarray):
~\AppData\Roaming\Python\Python37\site-packages\pandas\core\indexes\base.py in get_slice_bound(self, label, side, kind)
5162 # we need to look up the label
5163 try:
-> 5164 slc = self.get_loc(label)
5165 except KeyError as err:
5166 try:
~\AppData\Roaming\Python\Python37\site-packages\pandas\core\indexes\numeric.py in get_loc(self, key, method, tolerance)
477 except (TypeError, NotImplementedError):
478 pass
--> 479 return super().get_loc(key, method=method, tolerance=tolerance)
480
481 #cache_readonly
~\AppData\Roaming\Python\Python37\site-packages\pandas\core\indexes\base.py in get_loc(self, key, method, tolerance)
2897 return self._engine.get_loc(key)
2898 except KeyError:
-> 2899 return self._engine.get_loc(self._maybe_cast_indexer(key))
2900 indexer = self.get_indexer([key], method=method, tolerance=tolerance)
2901 if indexer.ndim > 1 or indexer.size > 1:
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.Float64HashTable.get_item()
pandas/_libs/hashtable_class_helper.pxi in pandas._libs.hashtable.Float64HashTable.get_item()
KeyError: (200.0, 'occurred at index 0')
Related
I have data, which has 2 input columns and 42 output columns. Here is what my code looks like:
data_columns=["value","average"]
prediction_columns=[]
for i in range(43):
prediction_columns.append("s"+str(i))
from keras.preprocessing.sequence import TimeseriesGenerator
n_input = 24*4 #how many samples/rows/timesteps to look in the past in order to forecast the next sample
n_features= len(prediction_columns)#X_train.shape[1] # how many predictors/Xs/features we have to predict y
b_size = 7 # Number of timeseries samples in each batch
generator = TimeseriesGenerator(columns[data_columns], columns[prediction_columns], length=n_input, batch_size=b_size)
print(generator[0][0].shape)
This fails with following:
---------------------------------------------------------------------------
KeyError Traceback (most recent call last)
File /usr/lib/python3.10/site-packages/pandas/core/indexes/base.py:3621, in Index.get_loc(self, key, method, tolerance)
3620 try:
-> 3621 return self._engine.get_loc(casted_key)
3622 except KeyError as err:
File /usr/lib/python3.10/site-packages/pandas/_libs/index.pyx:136, in pandas._libs.index.IndexEngine.get_loc()
File /usr/lib/python3.10/site-packages/pandas/_libs/index.pyx:163, in pandas._libs.index.IndexEngine.get_loc()
File pandas/_libs/hashtable_class_helper.pxi:5198, in pandas._libs.hashtable.PyObjectHashTable.get_item()
File pandas/_libs/hashtable_class_helper.pxi:5206, in pandas._libs.hashtable.PyObjectHashTable.get_item()
KeyError: 96
The above exception was the direct cause of the following exception:
KeyError Traceback (most recent call last)
Input In [38], in <cell line: 8>()
5 b_size = 7 # Number of timeseries samples in each batch
6 generator = TimeseriesGenerator(columns[data_columns], columns[prediction_columns], length=n_input, batch_size=b_size)
----> 8 print(generator[0][0].shape)
File /usr/lib/python3.10/site-packages/keras/preprocessing/sequence.py:176, in __getitem__(self, index)
172 rows = np.random.randint(
173 self.start_index, self.end_index + 1, size=self.batch_size
174 )
175 else:
--> 176 i = self.start_index + self.batch_size * self.stride * index
177 rows = np.arange(
178 i,
179 min(i + self.batch_size * self.stride, self.end_index + 1),
180 self.stride,
181 )
183 samples = np.array(
184 [
185 self.data[row - self.length : row : self.sampling_rate]
186 for row in rows
187 ]
188 )
File /usr/lib/python3.10/site-packages/keras/preprocessing/sequence.py:176, in <listcomp>(.0)
172 rows = np.random.randint(
173 self.start_index, self.end_index + 1, size=self.batch_size
174 )
175 else:
--> 176 i = self.start_index + self.batch_size * self.stride * index
177 rows = np.arange(
178 i,
179 min(i + self.batch_size * self.stride, self.end_index + 1),
180 self.stride,
181 )
183 samples = np.array(
184 [
185 self.data[row - self.length : row : self.sampling_rate]
186 for row in rows
187 ]
188 )
File /usr/lib/python3.10/site-packages/pandas/core/frame.py:3505, in DataFrame.__getitem__(self, key)
3503 if self.columns.nlevels > 1:
3504 return self._getitem_multilevel(key)
-> 3505 indexer = self.columns.get_loc(key)
3506 if is_integer(indexer):
3507 indexer = [indexer]
File /usr/lib/python3.10/site-packages/pandas/core/indexes/base.py:3623, in Index.get_loc(self, key, method, tolerance)
3621 return self._engine.get_loc(casted_key)
3622 except KeyError as err:
-> 3623 raise KeyError(key) from err
3624 except TypeError:
3625 # If we have a listlike key, _check_indexing_error will raise
3626 # InvalidIndexError. Otherwise we fall through and re-raise
3627 # the TypeError.
3628 self._check_indexing_error(key)
KeyError: 96
I thought that maybe I'm providing invalid column names, but both columns[data_columns].head() and columns[prediction_columns].head() execute without issues
Columns shape is (42749, 45)
What could be the source of the problem?
Problem went away after I converted dataframes to numpy
generator = TimeseriesGenerator(work[data_columns].to_numpy(), work[prediction_columns].to_numpy(), length=n_input, batch_size=b_size)
Currently if i run some error code in IPython with Pandas, for example, a script named temp.py
import pandas as pd
temp = pd.Series(range(5))
print(temp.loc[6])
then run command %run temp.py in IPython console, I get some error info like
KeyError Traceback (most recent call last)
D:\codes\python\test.py in <module>
2
3 temp = pd.Series(range(5))
----> 4 print(temp.loc[6])
C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\indexing.py in __getitem__(self, key)
929
930 maybe_callable = com.apply_if_callable(key, self.obj)
--> 931 return self._getitem_axis(maybe_callable, axis=axis)
932
933 def _is_scalar_access(self, key: tuple):
C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\indexing.py in _getitem_axis(self, key, axis)
1162 # fall thru to straight lookup
1163 self._validate_key(key, axis)
-> 1164 return self._get_label(key, axis=axis)
1165
1166 def _get_slice_axis(self, slice_obj: slice, axis: int):
C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\indexing.py in _get_label(self, label, axis)
1111 def _get_label(self, label, axis: int):
1112 # GH#5667 this will fail if the label is not present in the axis.
-> 1113 return self.obj.xs(label, axis=axis)
1114
1115 def _handle_lowerdim_multi_index_axis0(self, tup: tuple):
C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\generic.py in xs(self, key, axis, level, drop_level)
3774 raise TypeError(f"Expected label or tuple of labels, got {key}") from e
3775 else:
-> 3776 loc = index.get_loc(key)
3777
3778 if isinstance(loc, np.ndarray):
C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\indexes\range.py in get_loc(self, key, method, tolerance)
385 return self._range.index(new_key)
386 except ValueError as err:
--> 387 raise KeyError(key) from err
388 raise KeyError(key)
389 return super().get_loc(key, method=method, tolerance=tolerance)
KeyError: 6
the error info here is too long and useless, if I want to get the error code of my own, I need to scroll up to find what is the error place of my own.
Also after that when I run %debug command, I also got into the pandas function and local vars instead of my own code.
So is there a way to make IPython show error info and debug just in my own code?
preprocess_train ran successfully.
Has anyone encountered similar KeyError when using preprocess_test / ktrain (0.18.5)?
preprocessing test...
language: en
test sequence lengths:
mean : 608
95percentile : 2102
99percentile : 4783
---------------------------------------------------------------------------
KeyError Traceback (most recent call last)
in
----> 1 val = t.preprocess_test(X_test, y_test)
~/.local/lib/python3.6/site-packages/ktrain/text/preprocessor.py in preprocess_test(self, texts, y, verbose)
1172 """
1173 self.check_trained()
-> 1174 return self.preprocess_train(texts, y=y, mode='test', verbose=verbose)
1175
1176
~/.local/lib/python3.6/site-packages/ktrain/text/preprocessor.py in preprocess_train(self, texts, y, mode, verbose)
1142 TransformerDataset if self.use_with_learner = True else tf.Dataset
1143 """
-> 1144 tseq = super().preprocess_train(texts, y=y, mode=mode, verbose=verbose)
1145 if self.use_with_learner: return tseq
1146 tseq.batch_size = self.batch_size
~/.local/lib/python3.6/site-packages/ktrain/text/preprocessor.py in preprocess_train(self, texts, y, mode, verbose)
910 elif y is None:
911 y = np.array([1] * len(texts))
--> 912 y = self._transform_y(y, verbose=verbose)
913
914 # convert examples
~/.local/lib/python3.6/site-packages/ktrain/text/preprocessor.py in _transform_y(self, y_data, verbose)
505
506 # check for errors and warnings
--> 507 if not isinstance(y_data[0], str) and len(y_data.shape) ==1 and not self.get_classes():
508 if verbose:
509 warnings.warn('Task is being treated as TEXT REGRESSION because ' +\
~/.local/lib/python3.6/site-packages/pandas/core/series.py in __getitem__(self, key)
869 key = com.apply_if_callable(key, self)
870 try:
--> 871 result = self.index.get_value(self, key)
872
873 if not is_scalar(result):
~/.local/lib/python3.6/site-packages/pandas/core/indexes/base.py in get_value(self, series, key)
4403 k = self._convert_scalar_indexer(k, kind="getitem")
4404 try:
-> 4405 return self._engine.get_value(s, k, tz=getattr(series.dtype, "tz", None))
4406 except KeyError as e1:
4407 if len(self) > 0 and (self.holds_integer() or self.is_boolean()):
pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_value()
pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_value()
pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_loc()
pandas/_libs/hashtable_class_helper.pxi in pandas._libs.hashtable.Int64HashTable.get_item()
pandas/_libs/hashtable_class_helper.pxi in pandas._libs.hashtable.Int64HashTable.get_item()
KeyError: 0
It looks like you're supplying a pandas Series to preprocess_test instead of NumPy arrays or Python lists. If X_test and y_test are pandas Series, supply X_test.values and y_test.values to preprocess_test.
I have a series of SKUs in a DataFrame: [35641, 265689494123, 36492, 56526246546, 26412...].
The problem is that the long barcodes (like 56526246546) in the DataFrame need to be truncated at certain points. The length over 5 should trigger the deletion process, which truncates like [7:12] in a list.
I tried using the following code without any prevail:
if df.loc[len(df['SKU']) > 5]:
df.loc[df['SKU'].df.slice(start=7,stop=12)]
I get following error messages:
KeyError Traceback (most recent call last)
c:\users\User\appdata\local\programs\python\python37\lib\site-packages\pandas\core\indexes\base.py in get_loc(self, key, method, tolerance)
2656 try:
-> 2657 return self._engine.get_loc(key)
2658 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\index_class_helper.pxi in pandas._libs.index.Int64Engine._check_type()
KeyError: True
During handling of the above exception, another exception occurred:
KeyError Traceback (most recent call last)
<ipython-input-64-cea7b4ca2640> in <module>
1 #g[:] = (elem[:12] for elem in g)
----> 2 if df.loc[len(df['SKU']) > 5]:
3 df.loc[df['SKU'].df.slice(start=7,stop=12)]
c:\users\User\appdata\local\programs\python\python37\lib\site-packages\pandas\core\indexing.py in __getitem__(self, key)
1498
1499 maybe_callable = com.apply_if_callable(key, self.obj)
-> 1500 return self._getitem_axis(maybe_callable, axis=axis)
1501
1502 def _is_scalar_access(self, key):
c:\users\User\appdata\local\programs\python\python37\lib\site-packages\pandas\core\indexing.py in _getitem_axis(self, key, axis)
1911 # fall thru to straight lookup
1912 self._validate_key(key, axis)
-> 1913 return self._get_label(key, axis=axis)
1914
1915
c:\users\User\appdata\local\programs\python\python37\lib\site-packages\pandas\core\indexing.py in _get_label(self, label, axis)
139 raise IndexingError('no slices here, handle elsewhere')
140
--> 141 return self.obj._xs(label, axis=axis)
142
143 def _get_loc(self, key, axis=None):
c:\users\User\appdata\local\programs\python\python37\lib\site-packages\pandas\core\generic.py in xs(self, key, axis, level, drop_level)
3583 drop_level=drop_level)
3584 else:
-> 3585 loc = self.index.get_loc(key)
3586
3587 if isinstance(loc, np.ndarray):
c:\users\User\appdata\local\programs\python\python37\lib\site-packages\pandas\core\indexes\base.py in get_loc(self, key, method, tolerance)
2657 return self._engine.get_loc(key)
2658 except KeyError:
-> 2659 return self._engine.get_loc(self._maybe_cast_indexer(key))
2660 indexer = self.get_indexer([key], method=method, tolerance=tolerance)
2661 if indexer.ndim > 1 or indexer.size > 1:
pandas\_libs\index.pyx in pandas._libs.index.IndexEngine.get_loc()
pandas\_libs\index.pyx in pandas._libs.index.IndexEngine.get_loc()
pandas\_libs\index_class_helper.pxi in pandas._libs.index.Int64Engine._check_type()
KeyError: True
How do I fix this code?
P.S Some of the error messages seem to be popping up due to the fact that I've added the code BEFORE converting the dict into a DataFrame.
According to the output you want, I think you can use:
df['SKU'] = df['SKU'].apply(lambda x: int(str(x)[6:11]) if len(str(x)) > 5 else x)
Output:
SKU
0 35641
1 49412
2 36492
3 46546
4 26412
Here is my suggestion:
df.loc[:, 'SKU'] = df.loc[:, 'SKU'].astype(str).apply(lambda x: x[7:12] if len(x) > 5 else x)
I am attaching the code . I am trying to replicate the code given in the link link. I am trying this code on my data. Below is the code and error that i am getting. Sorry for the bad formation of the question I tried to insert the code in a proper way but it doesnt seem to work for some commands.
search = {'algorithm': {'k-nn': {'n_neighbors': [1, 5]},
'SVM': {'kernel': {'linear': {'C': [0, 2]},
'rbf': {'gamma': [0, 1], 'C': [0, 10]},
'poly': {'degree': [2, 5], 'C': [0, 50], 'coef0': [0, 1]}
}
},
'naive-bayes': None,
'random-forest': {'n_estimators': [10, 30],
'max_features': [5, 20]}
}
}
#optunity.cross_validated(x=data, y=labels, num_folds=5)
def performance(x_train, y_train, x_test, y_test,
algorithm, n_neighbors=None, n_estimators=None, max_features=None,
kernel=None, C=None, gamma=None, degree=None, coef0=None):
# fit the model
if algorithm == 'k-nn':
model = KNeighborsClassifier(n_neighbors=int(n_neighbors))
model.fit(x_train, y_train)
elif algorithm == 'naive-bayes':
model = GaussianNB()
model.fit(x_train, y_train)
elif algorithm == 'random-forest':
model = RandomForestClassifier(n_estimators=int(n_estimators),
max_features=int(max_features))
model.fit(x_train, y_train)
# predict the test set
if algorithm == 'k-nn':
predictions = model.predict_proba(x_test)[:, 1]
else:
predictions = model.predict_proba(x_test)[:, 1]
return optunity.metrics.roc_auc(y_test, predictions, positive=True)
optimal_configuration, info, _ = optunity.maximize_structured(performance,
search_space=search,
num_evals=300)
This is the error message that I am getting
TypeError Traceback (most recent call last)
C:\ProgramData\Anaconda3\lib\site-packages\optunity\cross_validation.py in select(collection, indices)
76 try:
---> 77 return collection[indices, ...]
78 except IndexError: # caused by scipy.sparse in some versions
C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\frame.py in __getitem__(self, key)
1963 else:
-> 1964 return self._getitem_column(key)
1965
C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\frame.py in _getitem_column(self, key)
1970 if self.columns.is_unique:
-> 1971 return self._get_item_cache(key)
1972
C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\generic.py in _get_item_cache(self, item)
1642 cache = self._item_cache
-> 1643 res = cache.get(item)
1644 if res is None:
TypeError: unhashable type: 'list'
During handling of the above exception, another exception occurred:
KeyError Traceback (most recent call last)
C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\indexes\base.py in get_loc(self, key, method, tolerance)
2441 try:
-> 2442 return self._engine.get_loc(key)
2443 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: 26770
During handling of the above exception, another exception occurred:
KeyError Traceback (most recent call last)
<ipython-input-153-3d5c9d0e2047> in <module>()
1 optimal_configuration, info, _ = optunity.maximize_structured(performance,
2 search_space=search,
----> 3 num_evals=300)
C:\ProgramData\Anaconda3\lib\site-packages\optunity\api.py in maximize_structured(f, search_space, num_evals, pmap)
368 solver = make_solver(**suggestion)
369 solution, details = optimize(solver, f, maximize=True, max_evals=num_evals,
--> 370 pmap=pmap, decoder=tree.decode)
371 return solution, details, suggestion
372
C:\ProgramData\Anaconda3\lib\site-packages\optunity\api.py in optimize(solver, func, maximize, max_evals, pmap, decoder)
243 time = timeit.default_timer()
244 try:
--> 245 solution, report = solver.optimize(f, maximize, pmap=pmap)
246 except fun.MaximumEvaluationsException:
247 # early stopping because maximum number of evaluations is reached
C:\ProgramData\Anaconda3\lib\site-packages\optunity\solvers\ParticleSwarm.py in optimize(self, f, maximize, pmap)
269 for g in range(self.num_generations):
270 fitnesses = pmap(evaluate, list(map(self.particle2dict, pop)))
--> 271 for part, fitness in zip(pop, fitnesses):
272 part.fitness = fit * util.score(fitness)
273 if not part.best or part.best_fitness < part.fitness:
C:\ProgramData\Anaconda3\lib\site-packages\optunity\solvers\ParticleSwarm.py in evaluate(d)
257 #functools.wraps(f)
258 def evaluate(d):
--> 259 return f(**d)
260
261 if maximize:
C:\ProgramData\Anaconda3\lib\site-packages\optunity\functions.py in wrapped_f(*args, **kwargs)
354 else:
355 wrapped_f.num_evals += 1
--> 356 return f(*args, **kwargs)
357 wrapped_f.num_evals = 0
358 return wrapped_f
C:\ProgramData\Anaconda3\lib\site-packages\optunity\constraints.py in wrapped_f(*args, **kwargs)
149 def wrapped_f(*args, **kwargs):
150 try:
--> 151 return f(*args, **kwargs)
152 except ConstraintViolation:
153 return default
C:\ProgramData\Anaconda3\lib\site-packages\optunity\constraints.py in wrapped_f(*args, **kwargs)
127 if violations:
128 raise ConstraintViolation(violations, *args, **kwargs)
--> 129 return f(*args, **kwargs)
130 wrapped_f.constraints = constraints
131 return wrapped_f
C:\ProgramData\Anaconda3\lib\site-packages\optunity\constraints.py in func(*args, **kwargs)
264 #functions.wraps(f)
265 def func(*args, **kwargs):
--> 266 return f(*args, **kwargs)
267 return func
268
C:\ProgramData\Anaconda3\lib\site-packages\optunity\search_spaces.py in wrapped(**kwargs)
324 def wrapped(**kwargs):
325 decoded = self.decode(kwargs)
--> 326 return f(**decoded)
327 return wrapped
328
C:\ProgramData\Anaconda3\lib\site-packages\optunity\functions.py in wrapped_f(*args, **kwargs)
299 value = wrapped_f.call_log.get(*args, **kwargs)
300 if value is None:
--> 301 value = f(*args, **kwargs)
302 wrapped_f.call_log.insert(value, *args, **kwargs)
303 return value
C:\ProgramData\Anaconda3\lib\site-packages\optunity\cross_validation.py in __call__(self, *args, **kwargs)
396 for i in range(self.num_folds)
397 if not i == fold]))
--> 398 kwargs['x_train'] = select(self.x, rows_train)
399 kwargs['x_test'] = select(self.x, rows_test)
400 if not self.y is None: # dealing with a supervised algorithm
C:\ProgramData\Anaconda3\lib\site-packages\optunity\cross_validation.py in select(collection, indices)
82 indexset = set(indices)
83 return collection.zipWithIndex().filter(lambda x: x[1] in indexset).map(lambda x: x[0])
---> 84 return [collection[i] for i in indices]
85
86
C:\ProgramData\Anaconda3\lib\site-packages\optunity\cross_validation.py in <listcomp>(.0)
82 indexset = set(indices)
83 return collection.zipWithIndex().filter(lambda x: x[1] in indexset).map(lambda x: x[0])
---> 84 return [collection[i] for i in indices]
85
86
C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\frame.py in __getitem__(self, key)
1962 return self._getitem_multilevel(key)
1963 else:
-> 1964 return self._getitem_column(key)
1965
1966 def _getitem_column(self, key):
C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\frame.py in _getitem_column(self, key)
1969 # get column
1970 if self.columns.is_unique:
-> 1971 return self._get_item_cache(key)
1972
1973 # duplicate columns & possible reduce dimensionality
C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\generic.py in _get_item_cache(self, item)
1643 res = cache.get(item)
1644 if res is None:
-> 1645 values = self._data.get(item)
1646 res = self._box_item_values(item, values)
1647 cache[item] = res
C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\internals.py in get(self, item, fastpath)
3588
3589 if not isnull(item):
-> 3590 loc = self.items.get_loc(item)
3591 else:
3592 indexer = np.arange(len(self.items))[isnull(self.items)]
C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\indexes\base.py in get_loc(self, key, method, tolerance)
2442 return self._engine.get_loc(key)
2443 except KeyError:
-> 2444 return self._engine.get_loc(self._maybe_cast_indexer(key))
2445
2446 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: 26770
So I got the answer.The format of input data set needed to be in array and the label as a boolean list.