In [2]:
%load_ext autoreload
%autoreload 2
import numpy as np
from vflow import Vset, init_args, dict_to_df, perturbation_stats
from functools import partial
from sklearn.linear_model import LassoCV
from sklearn.metrics import r2_score, explained_variance_score
from sklearn.model_selection import train_test_split
from sklearn.decomposition import PCA

The autoreload extension is already loaded. To reload it, use:
  %reload_ext autoreload

fMRI Voxel Prediction¶

This vflow pipeline predicts using fMRI voxels.

In [3]:
ind = {}

def top_n_features(X, Y, n, i):
    if i not in ind:
        corr = np.abs(np.apply_along_axis(lambda x: np.corrcoef(x, Y[:, i])[0, 1], 0, X))
        ind[i] = np.argsort(corr[~np.isnan(corr)])[::-1][:n]
    return X[:, ind[i]]


def pca(X, n):
    return PCA(n_components=n, copy=True).fit(X).transform(X)
In [4]:
# load data
data_dir = "./data/fmri/"
X = np.load(data_dir + "fit_feat.npy")
Y = np.load(data_dir + "resp_dat.npy")
In [5]:
np.random.seed(14)
X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.33, random_state=14)
X_train, X_test, y_train, y_test = init_args((X_train, X_test, y_train, y_test),
                                             names=['X_train', 'X_test', 'y_train', 'y_test'])

# split y_train by voxel and extract top 500 correlated features per voxel
voxel_extract_funcs = [partial(lambda x, y, i: (top_n_features(x, y, 20, i), y[:, i]), i=i) for i in range(20)]
voxel_extract_set = Vset(name='voxel_extract', vfuncs=voxel_extract_funcs, output_matching=True)
X_trains, y_trains = voxel_extract_set(X_train, y_train)
X_tests, y_tests = voxel_extract_set(X_test, y_test)

/home/james/.local/share/virtualenvs/veridical-flow-zFhOijFB/lib/python3.10/site-packages/numpy/lib/function_base.py:2853: RuntimeWarning: invalid value encountered in divide
  c /= stddev[:, None]
/home/james/.local/share/virtualenvs/veridical-flow-zFhOijFB/lib/python3.10/site-packages/numpy/lib/function_base.py:2854: RuntimeWarning: invalid value encountered in divide
  c /= stddev[None, :]
In [6]:
# modeling
modeling_set = Vset(name='modeling', vfuncs=[LassoCV()], vfunc_keys=["Lasso"])
modeling_set.fit(X_trains, y_trains)
Out[6]:
<vflow.vset.Vset at 0x7f6ed36529e0>
In [7]:
preds = modeling_set.predict(X_trains)

hard_metrics_set = Vset(name='hard_metrics', vfuncs=[r2_score, explained_variance_score],
                             vfunc_keys=["R2", "EV"])
hard_metrics = hard_metrics_set.evaluate(y_trains, preds)

df = dict_to_df(hard_metrics)
df

/home/james/repos/Yu-Group/veridical-flow/vflow/utils.py:225: FutureWarning: DataFrame.set_axis 'inplace' keyword is deprecated and will be removed in a future version. Use `obj = obj.set_axis(..., copy=False)` instead
  df.set_axis(cols, axis=1, inplace=True)
Out[7]:
init-voxel_extract voxel_extract init-modeling init-modeling init-modeling modeling hard_metrics out
0 y_train voxel_extract_0 X_train X_train y_train Lasso R2 0.203121
1 y_train voxel_extract_1 X_train X_train y_train Lasso R2 0.275898
2 y_train voxel_extract_2 X_train X_train y_train Lasso R2 0.224725
3 y_train voxel_extract_3 X_train X_train y_train Lasso R2 0.202630
4 y_train voxel_extract_4 X_train X_train y_train Lasso R2 0.167139
5 y_train voxel_extract_5 X_train X_train y_train Lasso R2 0.228424
6 y_train voxel_extract_6 X_train X_train y_train Lasso R2 0.247807
7 y_train voxel_extract_7 X_train X_train y_train Lasso R2 0.264284
8 y_train voxel_extract_8 X_train X_train y_train Lasso R2 0.178232
9 y_train voxel_extract_9 X_train X_train y_train Lasso R2 0.055822
10 y_train voxel_extract_10 X_train X_train y_train Lasso R2 0.045923
11 y_train voxel_extract_11 X_train X_train y_train Lasso R2 0.199126
12 y_train voxel_extract_12 X_train X_train y_train Lasso R2 0.032398
13 y_train voxel_extract_13 X_train X_train y_train Lasso R2 0.107258
14 y_train voxel_extract_14 X_train X_train y_train Lasso R2 0.188789
15 y_train voxel_extract_15 X_train X_train y_train Lasso R2 0.038167
16 y_train voxel_extract_16 X_train X_train y_train Lasso R2 0.089735
17 y_train voxel_extract_17 X_train X_train y_train Lasso R2 0.181334
18 y_train voxel_extract_18 X_train X_train y_train Lasso R2 0.122867
19 y_train voxel_extract_19 X_train X_train y_train Lasso R2 0.001247
20 y_train voxel_extract_0 X_train X_train y_train Lasso EV 0.203121
21 y_train voxel_extract_1 X_train X_train y_train Lasso EV 0.275898
22 y_train voxel_extract_2 X_train X_train y_train Lasso EV 0.224725
23 y_train voxel_extract_3 X_train X_train y_train Lasso EV 0.202630
24 y_train voxel_extract_4 X_train X_train y_train Lasso EV 0.167139
25 y_train voxel_extract_5 X_train X_train y_train Lasso EV 0.228424
26 y_train voxel_extract_6 X_train X_train y_train Lasso EV 0.247807
27 y_train voxel_extract_7 X_train X_train y_train Lasso EV 0.264284
28 y_train voxel_extract_8 X_train X_train y_train Lasso EV 0.178232
29 y_train voxel_extract_9 X_train X_train y_train Lasso EV 0.055822
30 y_train voxel_extract_10 X_train X_train y_train Lasso EV 0.045923
31 y_train voxel_extract_11 X_train X_train y_train Lasso EV 0.199126
32 y_train voxel_extract_12 X_train X_train y_train Lasso EV 0.032398
33 y_train voxel_extract_13 X_train X_train y_train Lasso EV 0.107258
34 y_train voxel_extract_14 X_train X_train y_train Lasso EV 0.188789
35 y_train voxel_extract_15 X_train X_train y_train Lasso EV 0.038167
36 y_train voxel_extract_16 X_train X_train y_train Lasso EV 0.089735
37 y_train voxel_extract_17 X_train X_train y_train Lasso EV 0.181334
38 y_train voxel_extract_18 X_train X_train y_train Lasso EV 0.122867
39 y_train voxel_extract_19 X_train X_train y_train Lasso EV 0.001247
In [8]:
metrics_stats = perturbation_stats(df, 'voxel_extract')
metrics_stats
Out[8]:
voxel_extract count mean std
0 voxel_extract_0 2 0.203121 7.850462e-17
1 voxel_extract_1 2 0.275898 0.000000e+00
2 voxel_extract_10 2 0.045923 7.850462e-17
3 voxel_extract_11 2 0.199126 7.850462e-17
4 voxel_extract_12 2 0.032398 0.000000e+00
5 voxel_extract_13 2 0.107258 1.570092e-16
6 voxel_extract_14 2 0.188789 0.000000e+00
7 voxel_extract_15 2 0.038167 0.000000e+00
8 voxel_extract_16 2 0.089735 0.000000e+00
9 voxel_extract_17 2 0.181334 0.000000e+00
10 voxel_extract_18 2 0.122867 7.850462e-17
11 voxel_extract_19 2 0.001247 7.850462e-17
12 voxel_extract_2 2 0.224725 0.000000e+00
13 voxel_extract_3 2 0.202630 7.850462e-17
14 voxel_extract_4 2 0.167139 0.000000e+00
15 voxel_extract_5 2 0.228424 0.000000e+00
16 voxel_extract_6 2 0.247807 0.000000e+00
17 voxel_extract_7 2 0.264284 0.000000e+00
18 voxel_extract_8 2 0.178232 0.000000e+00
19 voxel_extract_9 2 0.055822 7.850462e-17
In [ ]: