metric-learn
metric-learn copied to clipboard
scikit-learn-contrib
TypeError: _inplace_paired_L2() missing 2 required positional arguments: 'A' and 'B'
Description
I get this error TypeError: _inplace_paired_L2() missing 2 required positional arguments: 'A' and 'B'
Steps/Code to Reproduce
Example:
from sklearn.datasets import make_friedman1
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
def friedman_np_to_df(X,y):
return pd.DataFrame(X,columns=['x0','x1', 'x2', 'x3', 'x4']), pd.Series(y)
# Make training set
X_train, NA = make_friedman1(n_samples=1000, n_features=5, random_state = 1) #dont care about Y so call it NA
X_train, NA = friedman_np_to_df(X_train,NA)
#categorize training set based off of x0
domain_list = []
for i in range(len(X_train)):
if X_train.iloc[i]['x0'] < 0.6:
domain_list.append(1)
else:
domain_list.append(0)
X_train['domain'] = domain_list
# Set training set to where domain == 1 (x0 < 0.5)
X_train = X_train[X_train['domain']==1]
y_train = X_train.copy()
X_train = X_train.drop(columns = ['domain'])
y_train = y_train['domain']
# Make testing set with a different random_state
X_test, NA2 = make_friedman1(n_samples=1000, n_features=5, random_state = 3)
X_test, NA2 = friedman_np_to_df(X_test,NA2)
#categorize testing set based off of x0
domain_list = []
for i in range(len(X_test)):
if X_test.iloc[i]['x0'] < 0.6:
domain_list.append(1)
else:
domain_list.append(0)
X_test['domain'] = domain_list
y_test = X_test['domain'].copy()
X_test = X_test.drop(columns = ['domain'])
from sklearn.neighbors import KNeighborsClassifier
from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.pipeline import Pipeline
from metric_learn import LMNN
lmnn_knn = Pipeline(steps=[('lmnn', LMNN()), ('knn', KNeighborsClassifier())])
parameters = {'lmnn__k':[1, 2,3], 'knn__n_neighbors':[1 , 2]}
grid_lmnn_knn = GridSearchCV(lmnn_knn, parameters, n_jobs=-1, verbose=True)
grid_lmnn_knn.fit(X_train,y_train)
grid_lmnn_knn.score(X_test, y_test)
Expected Results
Example: No error is thrown. Score is calculated
Actual Results
Fitting 5 folds for each of 6 candidates, totalling 30 fits
[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done 30 out of 30 | elapsed: 0.5s finished
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-54-e89c6a61ea02> in <module>()
6 parameters = {'lmnn__k':[1, 2,3], 'knn__n_neighbors':[1 , 2]}
7 grid_lmnn_knn = GridSearchCV(lmnn_knn, parameters, n_jobs=-1, verbose=True)
----> 8 grid_lmnn_knn.fit(X_train,y_train)
9 grid_lmnn_knn.score(X_test, y_test)
10
7 frames
/usr/local/lib/python3.7/dist-packages/sklearn/model_selection/_search.py in fit(self, X, y, groups, **fit_params)
737 refit_start_time = time.time()
738 if y is not None:
--> 739 self.best_estimator_.fit(X, y, **fit_params)
740 else:
741 self.best_estimator_.fit(X, **fit_params)
/usr/local/lib/python3.7/dist-packages/sklearn/pipeline.py in fit(self, X, y, **fit_params)
348 This estimator
349 """
--> 350 Xt, fit_params = self._fit(X, y, **fit_params)
351 with _print_elapsed_time('Pipeline',
352 self._log_message(len(self.steps) - 1)):
/usr/local/lib/python3.7/dist-packages/sklearn/pipeline.py in _fit(self, X, y, **fit_params)
313 message_clsname='Pipeline',
314 message=self._log_message(step_idx),
--> 315 **fit_params_steps[name])
316 # Replace the transformer of the step with the fitted
317 # transformer. This is necessary when loading the transformer
/usr/local/lib/python3.7/dist-packages/joblib/memory.py in __call__(self, *args, **kwargs)
350
351 def __call__(self, *args, **kwargs):
--> 352 return self.func(*args, **kwargs)
353
354 def call_and_shelve(self, *args, **kwargs):
/usr/local/lib/python3.7/dist-packages/sklearn/pipeline.py in _fit_transform_one(transformer, X, y, weight, message_clsname, message, **fit_params)
726 with _print_elapsed_time(message_clsname, message):
727 if hasattr(transformer, 'fit_transform'):
--> 728 res = transformer.fit_transform(X, y, **fit_params)
729 else:
730 res = transformer.fit(X, y, **fit_params).transform(X)
/usr/local/lib/python3.7/dist-packages/sklearn/base.py in fit_transform(self, X, y, **fit_params)
572 else:
573 # fit method of arity 2 (supervised transformation)
--> 574 return self.fit(X, y, **fit_params).transform(X)
575
576
/usr/local/lib/python3.7/dist-packages/metric_learn/lmnn.py in fit(self, X, y)
180 G, objective, total_active = self._loss_grad(X, L, dfG, k,
181 reg, target_neighbors,
--> 182 label_inds)
183
184 it = 1 # we already made one iteration
/usr/local/lib/python3.7/dist-packages/metric_learn/lmnn.py in _loss_grad(self, X, L, dfG, k, reg, target_neighbors, label_inds)
246 label_inds, L)
247
--> 248 g0 = _inplace_paired_L2(*Lx[impostors])
249
250 # we reorder the target neighbors
TypeError: _inplace_paired_L2() missing 2 required positional arguments: 'A' and 'B'
Versions
Linux-4.19.112+-x86_64-with-Ubuntu-18.04-bionic Python 3.7.10 (default, Feb 20 2021, 21:17:23) [GCC 7.5.0] NumPy 1.19.5 SciPy 1.4.1 Scikit-Learn 0.22.2.post1 Metric-Learn 0.6.2
Looks like either Lx or impostors was empty when computing the gradient of the loss.
Is X_train a numpy array of Pandas dataframe in your call to grid_lmnn_knn.fit(X_train,y_train)? If it's a dataframe, could you try again using a plain numpy array?
In any case, we should do better checking to surface a less-opaque error message.
Yep, I have tried that .
Replaced last 2 lines with this:
grid_lmnn_knn.fit(np.array(X_train),np.array(y_train))
grid_lmnn_knn.score(np.array(X_test), np.array(y_test))
Any other thoughts you can think of?
I reproduced the issue locally, and it turns out that impostors is indeed empty when computing the gradient. See similar issue gh-17 which apparently didn't result in a fix for this same issue.
I haven't verified yet, but I suspect the new LMNN implementation coming in gh-309 will solve this for you. We should also make sure we add test coverage for the no-impostors case.
Sounds good. I will patiently wait for that. If you have any workaround until then, let me know as I have to present on my findings by next Wednesday to my research group lol
Here's a workaround. It just bails out entirely if no impostors can be found: https://github.com/scikit-learn-contrib/metric-learn/commit/612fcc4c74991dd377bc7aa9ea1741b9e8bc4f14
Not super elegant, but it should work okay.
Thank you for your work @perimosocordiae .
We are trying to apply metric learning to the materials sciences space, but trying to apply this work to Friedman dataset first before going all in on the diffusion datasets. Super weird that my pipeline is now not predicting any of the 0s correctly in my test set. I am not sure if this is a correct approach. In case you were interested in our use case: my PI is telling me to frame a classification problem with the Friedman dataset. Categorize the dataset and set samples where x0 < 0.6 to 1 (sample is within domain), else 0. Then apply metric-learning to that and see if it performs well.
Code so far:
from sklearn.datasets import make_friedman1
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
def friedman_np_to_df(X,y):
return pd.DataFrame(X,columns=['x0','x1', 'x2', 'x3', 'x4']), pd.Series(y)
# Make training set
X_train, NA = make_friedman1(n_samples=1000, n_features=5, random_state = 1) #dont care about Y so call it NA
X_train, NA = friedman_np_to_df(X_train,NA)
#categorize training set based off of x0
domain_list = []
for i in range(len(X_train)):
if X_train.iloc[i]['x0'] < 0.6 :
domain_list.append(1)
else:
domain_list.append(0)
X_train['domain'] = domain_list
# Set training set to where domain == 1 (x0 < 0.6)
X_train = X_train[X_train['domain']==1]
y_train = X_train.copy()
X_train = X_train.drop(columns = ['domain'])
y_train = y_train['domain']
# Make testing set with a different random_state
X_test, NA2 = make_friedman1(n_samples=1000, n_features=5, random_state = 3)
X_test, NA2 = friedman_np_to_df(X_test,NA2)
#categorize testing set based off of x0
domain_list = []
for i in range(len(X_test)):
if X_test.iloc[i]['x0'] < 0.6:
domain_list.append(1)
else:
domain_list.append(0)
X_test['domain'] = domain_list
y_test = X_test['domain'].copy()
X_test = X_test.drop(columns = ['domain'])
from sklearn.neighbors import KNeighborsClassifier
from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.pipeline import Pipeline
from metric_learn import LMNN
lmnn_knn = Pipeline(steps=[('lmnn', LMNN()), ('knn', KNeighborsClassifier())])
parameters = {'lmnn__init': ['pca', 'lda', 'identity', 'random'],
'lmnn__k':[2,3],
'knn__n_neighbors':[2,3],
'knn__weights': ['uniform','distance'],
'knn__algorithm': ['auto', 'ball_tree', 'kd_tree', 'brute'],
'knn__leaf_size': [x for x in np.arange(1,30,5)],
'knn__metric': ['euclidian', 'manhattan', 'mahalanobis', 'seuclidian', 'minkowski']}
grid_lmnn_knn = GridSearchCV(lmnn_knn, parameters,cv = 3, n_jobs=-1, verbose=True, scoring='f1')
grid_lmnn_knn.fit(np.array(X_train),np.array(y_train))
# grid_lmnn_knn.score(np.array(X_test), np.array(y_test))
predictions = grid_lmnn_knn.predict(X_test)
print(grid_lmnn_knn.best_estimator_)
from sklearn.metrics import classification_report
print(classification_report(y_test, predictions))
output is:
Pipeline(memory=None,
steps=[('lmnn',
LMNN(convergence_tol=0.001, init='pca', k=2, learn_rate=1e-07,
max_iter=1000, min_iter=50, n_components=None,
preprocessor=None, random_state=None, regularization=0.5,
verbose=False)),
('knn',
KNeighborsClassifier(algorithm='auto', leaf_size=1,
metric='manhattan', metric_params=None,
n_jobs=None, n_neighbors=2, p=2,
weights='uniform'))],
verbose=False)
precision recall f1-score support
0 0.00 0.00 0.00 387
1 0.61 1.00 0.76 613
accuracy 0.61 1000
macro avg 0.31 0.50 0.38 1000
weighted avg 0.38 0.61 0.47 1000
/usr/local/lib/python3.7/dist-packages/sklearn/metrics/_classification.py:1272: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.
_warn_prf(average, modifier, msg_start, len(result))
So yeah. Not sure why f1-score is 0 for my 0 cases. Maybe I am doing it wrong haha.
So I think the reason why my last attempt had bad performance on the Friedman dataset was because there were no examples of 0-labeled data in the training set. Now, I include samples of 0-labeled data in the training set. @perimosocordiae I found another issue with your branch:
from sklearn.datasets import make_friedman1
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
def friedman_np_to_df(X,y):
return pd.DataFrame(X,columns=['x0','x1', 'x2', 'x3', 'x4']), pd.Series(y)
# Make training set
X_train, NA = make_friedman1(n_samples=1000, n_features=5, random_state = 1) #dont care about Y so call it NA
X_train, NA = friedman_np_to_df(X_train,NA)
#categorize training set based off of x0
domain_list = []
for i in range(len(X_train)):
if X_train.iloc[i]['x0'] < 0.6 :
domain_list.append(1)
else:
domain_list.append(0)
X_train['domain'] = domain_list
# Set training set to where domain == 1 (x0 < 0.6)
out_of_domain = X_train[X_train['domain'] == 0][:60]
X_train = X_train[X_train['domain']==1]
X_train = pd.concat([out_of_domain, X_train])
y_train = X_train.copy()
X_train = X_train.drop(columns = ['domain'])
y_train = y_train['domain']
# Make testing set with a different random_state
X_test, NA2 = make_friedman1(n_samples=1000, n_features=5, random_state = 3)
X_test, NA2 = friedman_np_to_df(X_test,NA2)
#categorize testing set based off of x0
domain_list = []
for i in range(len(X_test)):
if X_test.iloc[i]['x0'] < 0.6:
domain_list.append(1)
else:
domain_list.append(0)
X_test['domain'] = domain_list
y_test = X_test['domain'].copy()
X_test = X_test.drop(columns = ['domain'])
from sklearn.neighbors import KNeighborsClassifier
from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.pipeline import Pipeline
from metric_learn import LMNN
lmnn_knn = Pipeline(steps=[('lmnn', LMNN()), ('knn', KNeighborsClassifier())])
parameters = {'lmnn__init': ['pca', 'lda', 'identity', 'random'],
'lmnn__k':[2,3],
'knn__n_neighbors':[2,3],
'knn__weights': ['uniform','distance'],
'knn__algorithm': ['auto', 'ball_tree', 'kd_tree', 'brute'],
'knn__leaf_size': [x for x in np.arange(1,30,5)],
'knn__metric': [ 'manhattan', 'mahalanobis', 'minkowski']}
grid_lmnn_knn = GridSearchCV(lmnn_knn, parameters,cv = 5, n_jobs=-1, verbose=True, scoring='f1')
grid_lmnn_knn.fit(np.array(X_train),np.array(y_train))
grid_lmnn_knn.score(np.array(X_test), np.array(y_test))
Output:
Fitting 5 folds for each of 2304 candidates, totalling 11520 fits
[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.
[Parallel(n_jobs=-1)]: Done 202 tasks | elapsed: 4.6s
[Parallel(n_jobs=-1)]: Done 1402 tasks | elapsed: 23.9s
[Parallel(n_jobs=-1)]: Done 3402 tasks | elapsed: 55.9s
[Parallel(n_jobs=-1)]: Done 6202 tasks | elapsed: 1.7min
[Parallel(n_jobs=-1)]: Done 9802 tasks | elapsed: 2.6min
[Parallel(n_jobs=-1)]: Done 11520 out of 11520 | elapsed: 3.1min finished
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-4-945bbdb8e331> in <module>()
64 'knn__metric': [ 'manhattan', 'mahalanobis', 'minkowski']}
65 grid_lmnn_knn = GridSearchCV(lmnn_knn, parameters,cv = 5, n_jobs=-1, verbose=True, scoring='f1')
---> 66 grid_lmnn_knn.fit(np.array(X_train),np.array(y_train))
67 grid_lmnn_knn.score(np.array(X_test), np.array(y_test))
68
7 frames
/usr/local/lib/python3.7/dist-packages/sklearn/model_selection/_search.py in fit(self, X, y, groups, **fit_params)
737 refit_start_time = time.time()
738 if y is not None:
--> 739 self.best_estimator_.fit(X, y, **fit_params)
740 else:
741 self.best_estimator_.fit(X, **fit_params)
/usr/local/lib/python3.7/dist-packages/sklearn/pipeline.py in fit(self, X, y, **fit_params)
348 This estimator
349 """
--> 350 Xt, fit_params = self._fit(X, y, **fit_params)
351 with _print_elapsed_time('Pipeline',
352 self._log_message(len(self.steps) - 1)):
/usr/local/lib/python3.7/dist-packages/sklearn/pipeline.py in _fit(self, X, y, **fit_params)
313 message_clsname='Pipeline',
314 message=self._log_message(step_idx),
--> 315 **fit_params_steps[name])
316 # Replace the transformer of the step with the fitted
317 # transformer. This is necessary when loading the transformer
/usr/local/lib/python3.7/dist-packages/joblib/memory.py in __call__(self, *args, **kwargs)
350
351 def __call__(self, *args, **kwargs):
--> 352 return self.func(*args, **kwargs)
353
354 def call_and_shelve(self, *args, **kwargs):
/usr/local/lib/python3.7/dist-packages/sklearn/pipeline.py in _fit_transform_one(transformer, X, y, weight, message_clsname, message, **fit_params)
726 with _print_elapsed_time(message_clsname, message):
727 if hasattr(transformer, 'fit_transform'):
--> 728 res = transformer.fit_transform(X, y, **fit_params)
729 else:
730 res = transformer.fit(X, y, **fit_params).transform(X)
/usr/local/lib/python3.7/dist-packages/sklearn/base.py in fit_transform(self, X, y, **fit_params)
572 else:
573 # fit method of arity 2 (supervised transformation)
--> 574 return self.fit(X, y, **fit_params).transform(X)
575
576
/usr/local/lib/python3.7/dist-packages/metric_learn/lmnn.py in fit(self, X, y)
180 G, objective, total_active = self._loss_grad(X, L, dfG, k,
181 reg, target_neighbors,
--> 182 label_inds)
183 if G is None:
184 # TODO: raise a warning
/usr/local/lib/python3.7/dist-packages/metric_learn/lmnn.py in _loss_grad(self, X, L, dfG, k, reg, target_neighbors, label_inds)
249 impostors = self._find_impostors(furthest_neighbors.ravel(), X,
250 label_inds, L)
--> 251 if not impostors:
252 return None, 0, 0
253
ValueError: The truth value of an array with more than one element is ambiguous. Use a.any() or a.all()
Tried swapping it to the following, but it now goes into an infinite loop 😂
if not impostors.any():
return None, 0, 0
Sorry, try if len(impostors) == 0: instead.
On Sun, Apr 4, 2021 at 2:31 PM Angelo Cortez @.***> wrote:
Tried swapping it to the following, but it now goes into an infinite loop 😂
if not impostors.any():
return None, 0, 0
— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/scikit-learn-contrib/metric-learn/issues/312#issuecomment-813079329, or unsubscribe https://github.com/notifications/unsubscribe-auth/AAAUHJ3SQS4227W2QJ7FR4DTHCWARANCNFSM42FZLVAQ .
Super weird.
Were you able to try the code from gh-309? I'm curious to see how it would handle this case.
The code from the PR doesn't work as well 🤣I will post my results on that thread.