1

我正在尝试将一些 MRI 灰质图图像作为 numpy 数组加载，以便它们可以在 sklearn 中进行处理。我的代码导入它们并使用 NiftiMasker 加载它们（NiftiMasker 对图像应用掩码以提取时间序列，我认为这是导致错误的 numpy 数组中的第 4 维）。当我尝试运行此代码时出现 ValueError ，因为由于某种原因，当我只需要一个 3D 数组时，数据被加载为 4D numpy 数组。有没有办法减少数组的维度或其他方法来解决这个错误？这是代码： 

import nibabel
import numpy as np
import matplotlib.pyplot as plt
from nilearn.input_data import NiftiMasker
import pandas as pd
import pdb
import os

def getgm(path):
    """Gets the subject number on the folder that contains the scans
     and appends them on a list called dirnames"""  
    gmnames = []
    paths = []
    for root, dirs, files in os.walk(path):
        for filename in files:
            gmnames.append(filename)
    for gmname in gmnames:
        path = os.path.join('Z:\Projects\MTS_Project\spm\dataset', gmname)
        paths.append(path)
    return paths
print(getgm('Z:\Projects\MTS_Project\spm\dataset'))

#loads MTSData as a list of paths
MTS_data = getgm('Z:\Projects\MTS_Project\spm\dataset')
print(MTS_data[0])

#loads side data from mtsdata.csv
fields = ['ID', 'SIDE']
csv = pd.read_csv('mtsdata.csv', skipinitialspace = True, usecols = fields)
age = csv.SIDE

nifti_masker = NiftiMasker(standardize = False, smoothing_fwhm=2, verbose=1)

gm_maps_masked = []

for data in MTS_data:
    gm_maps_masked.append(nifti_masker.fit_transform(data))


#nifti_masker.fit(MTS_data)
#gm_maps_masked = nifti_masker.transform(MTS_data)
#print(gm_maps_masked)




#n_features = gm_maps_masked.shape
#print(n_features)



print("ANOVA + SVR")
# Define the prediction function to be used.
# Here we use a Support Vector Classification, with a linear kernel
from sklearn.svm import SVR
svr = SVR(kernel='linear')

# Dimension reduction
from sklearn.feature_selection import VarianceThreshold, SelectKBest, \
        f_regression

# Remove features with too low between-subject variance
variance_threshold = VarianceThreshold(threshold=1)

# Here we use a classical univariate feature selection based on F-test,
# namely Anova.
feature_selection = SelectKBest(f_regression, k=2000)

# We have our predictor (SVR), our feature selection (SelectKBest), and now,
# we can plug them together in a *pipeline* that performs the two operations
# successively:
from sklearn.pipeline import Pipeline
anova_svr = Pipeline([
            ('variance_threshold', variance_threshold),
            ('anova', feature_selection),
            ('svr', svr)])


### Fit and predict
for gmmap in gm_maps_masked:
    anova_svr.fit(gm_maps_masked,age)
pdb.set_trace()
age_pred = anova_svr.predict(gm_maps_masked)

这是错误和回溯：

Traceback (most recent call last):
  File "learn.py", line 81, in <module>
    anova_svr.fit(gm_maps_masked,age)
  File "C:\Program Files\Python36\lib\site-packages\sklearn\pipeline.py", line 248, in fit
    Xt, fit_params = self._fit(X, y, **fit_params)
  File "C:\Program Files\Python36\lib\site-packages\sklearn\pipeline.py", line 213, in _fit
    **fit_params_steps[name])
  File "C:\Program Files\Python36\lib\site-packages\sklearn\externals\joblib\memory.py", line 362, in __call__
    return self.func(*args, **kwargs)
  File "C:\Program Files\Python36\lib\site-packages\sklearn\pipeline.py", line 581, in _fit_transform_one
    res = transformer.fit_transform(X, y, **fit_params)
  File "C:\Program Files\Python36\lib\site-packages\sklearn\base.py", line 520, in fit_transform
    return self.fit(X, y, **fit_params).transform(X)
  File "C:\Program Files\Python36\lib\site-packages\sklearn\feature_selection\variance_threshold.py", line 64, in fit
    X = check_array(X, ('csr', 'csc'), dtype=np.float64)
  File "C:\Program Files\Python36\lib\site-packages\sklearn\utils\validation.py", line 433, in check_array
    array = np.array(array, dtype=dtype, order=order, copy=copy)
ValueError: could not broadcast input array from shape (4518515) into shape (1)
4

0 回答 0