How to fix the TypeError: G must be a 'd' matrix?
How to fix the TypeError: G must be a 'd' matrix?
Objective：尝试通过优化过程运行玩具数据集。
我遇到以下错误：
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-16-2706eba23671> in <module>()
50 # Solving the problem
51 problem = cvxpy.Problem(cvxpy.Minimize(cost), constraints=constraints)
---> 52 problem.solve(solver=cvxpy.GLPK_MI)
D:\Anaconda3\lib\site-packages\cvxpy\problems\problem.py in solve(self, *args, **kwargs)
193 return func(self, *args, **kwargs)
194 else:
--> 195 return self._solve(*args, **kwargs)
196
197 @classmethod
D:\Anaconda3\lib\site-packages\cvxpy\problems\problem.py in _solve(self, solver, ignore_dcp, warm_start, verbose, parallel, **kwargs)
319 results_dict = solver.solve(objective, constraints,
320 self._cached_data, warm_start, verbose,
--> 321 kwargs)
322 # Presolve determined problem was unbounded or infeasible.
323 else:
D:\Anaconda3\lib\site-packages\cvxpy\problems\solvers\glpk_mi_intf.py in solve(self, objective, constraints, cached_data, warm_start, verbose, solver_opts)
97 data[s.B],
98 set(data[s.INT_IDX]),
---> 99 set(data[s.BOOL_IDX]))
100 results_dict = {}
101 results_dict["status"] = results_tup[0]
TypeError: G must be a 'd' matrix
下面是我使用的代码：
from sklearn.datasets import make_classification
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
import numpy as np
import cvxpy
X, y = make_classification(n_samples=1000, n_features=20, n_classes=8,n_informative=5,
class_sep=0.2, random_state=2)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2,random_state=1)
model = RandomForestClassifier(random_state=1)
model.fit(X_train, y_train)
test_probs = model.predict_proba(X_test)
#clipping so that we don't take log of 0 or 1
test_probs = np.clip(test_probs, 0.0001, 0.9999)
#turning into costs
model_costs = -np.log10(test_probs)
# Our allocation cannot exceed our supply
# 150 flyers, 80 pamphlets, 25 bumper stickers
supply = np.atleast_2d([150, 80, 25])
# Creating our cvxpy variable of assignments
selection = cvxpy.Bool(*test_probs.shape)
# Constant matrix that counts how many of each
# material we sent to each constituent
TRANSFORMER = np.array([[1,0,0],
[0,1,0],
[0,0,1],
[1,1,0],
[1,0,1],
[0,1,1],
[1,1,1],
[0,0,0]])
supply_constraint = cvxpy.sum_entries(selection * TRANSFORMER, axis=0) <= supply
# We must make our choice per constituent
# remember that the last column is for "no materials"
feasibility_constraint = cvxpy.sum_entries(selection, axis=1) == 1
constraints = [supply_constraint, feasibility_constraint]
# Take the negative log of our probabilities to turn them into costs
cost = cvxpy.sum_entries(cvxpy.mul_elemwise(model_costs, selection))
# Solving the problem
problem = cvxpy.Problem(cvxpy.Minimize(cost), constraints=constraints)
problem.solve(solver=cvxpy.GLPK_MI)
如果更多上下文有帮助，我会在 here. I did find 上关注 SO，但无法理解我应该如何处理我的问题的当前状态。
尝试将 TRANSFORMER 转换为浮点数组。
对于它的价值，代码在 CVXPY v 1.0.11 中工作（有一些小的修改，包括在下面）：
from sklearn.datasets import make_classification
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
import numpy as np
import cvxpy
X, y = make_classification(n_samples=1000, n_features=20, n_classes=8,n_informative=5,
class_sep=0.2, random_state=2)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2,random_state=1)
model = RandomForestClassifier(random_state=1)
model.fit(X_train, y_train)
test_probs = model.predict_proba(X_test)
#clipping so that we don't take log of 0 or 1
test_probs = np.clip(test_probs, 0.0001, 0.9999)
#turning into costs
model_costs = -np.log10(test_probs)
# Our allocation cannot exceed our supply
# 150 flyers, 80 pamphlets, 25 bumper stickers
supply = np.array([150, 80, 25])
# Creating our cvxpy variable of assignments
selection = cvxpy.Variable(shape=test_probs.shape, boolean=True)
# Constant matrix that counts how many of each
# material we sent to each constituent
TRANSFORMER = np.array([[1,0,0],
[0,1,0],
[0,0,1],
[1,1,0],
[1,0,1],
[0,1,1],
[1,1,1],
[0,0,0]])
supply_constraint = cvxpy.sum(selection * TRANSFORMER, axis=0) <= supply
# We must make our choice per constituent
# remember that the last column is for "no materials"
feasibility_constraint = cvxpy.sum(selection, axis=1) == 1
constraints = [supply_constraint, feasibility_constraint]
# Take the negative log of our probabilities to turn them into costs
cost = cvxpy.sum(cvxpy.multiply(model_costs, selection))
# Solving the problem
problem = cvxpy.Problem(cvxpy.Minimize(cost), constraints=constraints)
problem.solve(solver=cvxpy.GLPK_MI)
print(problem.value)
print(selection.value[0:5])
print(np.dot(selection.value, TRANSFORMER).sum(axis=0))
Objective：尝试通过优化过程运行玩具数据集。
我遇到以下错误：
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-16-2706eba23671> in <module>()
50 # Solving the problem
51 problem = cvxpy.Problem(cvxpy.Minimize(cost), constraints=constraints)
---> 52 problem.solve(solver=cvxpy.GLPK_MI)
D:\Anaconda3\lib\site-packages\cvxpy\problems\problem.py in solve(self, *args, **kwargs)
193 return func(self, *args, **kwargs)
194 else:
--> 195 return self._solve(*args, **kwargs)
196
197 @classmethod
D:\Anaconda3\lib\site-packages\cvxpy\problems\problem.py in _solve(self, solver, ignore_dcp, warm_start, verbose, parallel, **kwargs)
319 results_dict = solver.solve(objective, constraints,
320 self._cached_data, warm_start, verbose,
--> 321 kwargs)
322 # Presolve determined problem was unbounded or infeasible.
323 else:
D:\Anaconda3\lib\site-packages\cvxpy\problems\solvers\glpk_mi_intf.py in solve(self, objective, constraints, cached_data, warm_start, verbose, solver_opts)
97 data[s.B],
98 set(data[s.INT_IDX]),
---> 99 set(data[s.BOOL_IDX]))
100 results_dict = {}
101 results_dict["status"] = results_tup[0]
TypeError: G must be a 'd' matrix
下面是我使用的代码：
from sklearn.datasets import make_classification
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
import numpy as np
import cvxpy
X, y = make_classification(n_samples=1000, n_features=20, n_classes=8,n_informative=5,
class_sep=0.2, random_state=2)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2,random_state=1)
model = RandomForestClassifier(random_state=1)
model.fit(X_train, y_train)
test_probs = model.predict_proba(X_test)
#clipping so that we don't take log of 0 or 1
test_probs = np.clip(test_probs, 0.0001, 0.9999)
#turning into costs
model_costs = -np.log10(test_probs)
# Our allocation cannot exceed our supply
# 150 flyers, 80 pamphlets, 25 bumper stickers
supply = np.atleast_2d([150, 80, 25])
# Creating our cvxpy variable of assignments
selection = cvxpy.Bool(*test_probs.shape)
# Constant matrix that counts how many of each
# material we sent to each constituent
TRANSFORMER = np.array([[1,0,0],
[0,1,0],
[0,0,1],
[1,1,0],
[1,0,1],
[0,1,1],
[1,1,1],
[0,0,0]])
supply_constraint = cvxpy.sum_entries(selection * TRANSFORMER, axis=0) <= supply
# We must make our choice per constituent
# remember that the last column is for "no materials"
feasibility_constraint = cvxpy.sum_entries(selection, axis=1) == 1
constraints = [supply_constraint, feasibility_constraint]
# Take the negative log of our probabilities to turn them into costs
cost = cvxpy.sum_entries(cvxpy.mul_elemwise(model_costs, selection))
# Solving the problem
problem = cvxpy.Problem(cvxpy.Minimize(cost), constraints=constraints)
problem.solve(solver=cvxpy.GLPK_MI)
如果更多上下文有帮助，我会在 here. I did find
尝试将 TRANSFORMER 转换为浮点数组。
对于它的价值，代码在 CVXPY v 1.0.11 中工作（有一些小的修改，包括在下面）：
from sklearn.datasets import make_classification
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
import numpy as np
import cvxpy
X, y = make_classification(n_samples=1000, n_features=20, n_classes=8,n_informative=5,
class_sep=0.2, random_state=2)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2,random_state=1)
model = RandomForestClassifier(random_state=1)
model.fit(X_train, y_train)
test_probs = model.predict_proba(X_test)
#clipping so that we don't take log of 0 or 1
test_probs = np.clip(test_probs, 0.0001, 0.9999)
#turning into costs
model_costs = -np.log10(test_probs)
# Our allocation cannot exceed our supply
# 150 flyers, 80 pamphlets, 25 bumper stickers
supply = np.array([150, 80, 25])
# Creating our cvxpy variable of assignments
selection = cvxpy.Variable(shape=test_probs.shape, boolean=True)
# Constant matrix that counts how many of each
# material we sent to each constituent
TRANSFORMER = np.array([[1,0,0],
[0,1,0],
[0,0,1],
[1,1,0],
[1,0,1],
[0,1,1],
[1,1,1],
[0,0,0]])
supply_constraint = cvxpy.sum(selection * TRANSFORMER, axis=0) <= supply
# We must make our choice per constituent
# remember that the last column is for "no materials"
feasibility_constraint = cvxpy.sum(selection, axis=1) == 1
constraints = [supply_constraint, feasibility_constraint]
# Take the negative log of our probabilities to turn them into costs
cost = cvxpy.sum(cvxpy.multiply(model_costs, selection))
# Solving the problem
problem = cvxpy.Problem(cvxpy.Minimize(cost), constraints=constraints)
problem.solve(solver=cvxpy.GLPK_MI)
print(problem.value)
print(selection.value[0:5])
print(np.dot(selection.value, TRANSFORMER).sum(axis=0))