Question

我想知道如何将不同的数据存储到numpy数组中，以便将其提供给机器学习SVC算法。我的目标是获得大小的数据框（示例*功能），如下所示：

使用：

灰色的要素1包含大小为n的列表
功能2为红色，包含 2D numpy array 的形状（i，k）
功能...... 其他内容（pwelch频谱数组，整数，浮点数......）
功能n为蓝色，包含整数。

我怎样才能在Python中做到这一点？这对sklearn来说是否合适？

以下代码中的当前错误：

ValueError: setting an array element with a sequence.

代码：

# -*- coding: utf-8 -*-

"""----------------------------------------------------------------------------
-------------------------------- Imports --------------------------------------
----------------------------------------------------------------------------"""

import os
import pandas as pd
import numpy as np
from scipy import io as sio
from scipy import signal

from sklearn.model_selection import train_test_split
from sklearn.svm import SVC

"""----------------------------------------------------------------------------
------------------------------ Parameters -------------------------------------
----------------------------------------------------------------------------"""

# Path to the clean EEG .mat files
EEG_path = "data"   

# Listing of the .mat files
EEG = list()
for elt in os.listdir(EEG_path):
    if os.path.isfile(os.path.join(EEG_path, elt)):
        if '.mat' in elt[len(elt)-4:]:
            EEG.append(elt)

# Spectrum used
spectrum = ['all', (1,45), (8,12)]

nb_features = 3

"""----------------------------------------------------------------------------
------------------------------ Functions --------------------------------------
----------------------------------------------------------------------------"""

# Function on 1 channel
# Input: All points from one channel, for one epoch
def filter(x, n, fs, fc1, fc2):
    b, a = signal.butter(n, [fc1/(fs/2), fc2/(fs/2)], 'bandpass')
    y = signal.filtfilt(b, a, x)
    return y

def haming(x, L):
    # Symetric L-points hamming window
    window = signal.hamming(L)
    y = x * window.T                            # Element wise multiplication
    return y

# Function on one epoch
# Input is a matrix of size (channel * length)
def amp_mean(x):
    size = x.shape
    y = list()
    for i in range(size[0]):
        y.append(np.mean(x[i,:]))
    return y

def amp_max(x):
    size = x.shape
    y = list()
    for i in range(size[0]):
        y.append(np.max(abs(x[i,:])))
    return y

"""----------------------------------------------------------------------------
-------------------------------- Script ---------------------------------------
----------------------------------------------------------------------------"""

# Load data          
s_EEG = "{}/{}".format(EEG_path, EEG[4])
data = sio.loadmat(s_EEG)['s_EEG']['data'][0][0].astype(float)     # data[i, j ,k]
labels = sio.loadmat(s_EEG)['s_EEG']['labels'][0][0][0]            # labels[k]
fs = sio.loadmat(s_EEG)['s_EEG']['sampling_rate'][0][0][0][0]      # 500 Hz
size = data.shape

# Creates an empty data frame of size (epoch * features)
df = np.empty(shape = (size[2], nb_features * len(spectrum)))

# Filling the dataframe with features
# for every epoch
for k in range(size[2]):
    for freq in spectrum:
        data_to_compute = np.empty(shape = size, dtype = float)

        # Apply hamming
        if freq == 'all':
            for i in range(size[0]):
                data_to_compute[i,:,k] = haming(data[i,:,k], size[1])

        # Apply hamming after filtering
        else:
            for i in range(size[0]):
                data_to_compute[i,:,k] = haming(filter(data[i,:,k], 
                               15, fs, freq[0], freq[1]), size[1])

        # data_to_compute is ready to have feature extracted

        for n in range(0, df.shape[1], nb_features):
            df[k, n] = data_to_compute[:,:,k]
            df[k, n+1] = amp_mean(data_to_compute[:,:,k])
            df[k, n+2] = amp_max(data_to_compute[:,:,k])

# X signal / Y label
X_train, X_test, Y_train, Y_test = train_test_split(data, 
                                                    list(labels), 
                                                    test_size=0.15, 
                                                    random_state=42)

clf = SVC()
clf.fit(X_train, Y_train)

变量类型：

谢谢！

将不同类型的数据存入2D numpy数组

0 个答案: