准确率为0.81的程序

因为我观察了baseline错误分类数据的频域发现，他们的振幅所处的频率相同，因此我想用振幅比较大对应的频率来分。我选择这些数据中振幅大于0.1的振幅对应的频率。需要改进的地方可能是应该采取所有训练集中大于0.1振幅的频率。

 

 

import matplotlib.pyplot as plt

import numpy as np

import pandas as pd

import torch

import torch.fft as fft

df = pd.read_csv('train.csv')

df=df.drop(['ID'],axis=1)

nmp=df.to_numpy()

feature=nmp[:-20,:-1]

label=nmp[:-20,-1]#（210，240）

feature=torch.fft.fft(torch.Tensor(feature))

feature=torch.abs(feature)/240*2

feature=feature[:,[0, 1, 60, 180, 239, 59, 120, 181, 61, 179, 119, 121, 58, 182, 57, 183, 62, 178]]

test_feature=nmp[-20:,:-1]

test_label=nmp[-20:,-1]#（210，240）

test_feature=torch.fft.fft(torch.Tensor(test_feature))

test_feature=torch.abs(test_feature)/240*2

test_feature=test_feature[:,[0, 1, 60, 180, 239, 59, 120, 181, 61, 179, 119, 121, 58, 182, 57, 183, 62, 178]]

from torch import nn

import torch

loss=nn.MSELoss()

feature=torch.Tensor(feature)

label=torch.Tensor(label)

label=label.reshape(-1,1)

test_feature=torch.Tensor(test_feature)

test_label=torch.Tensor(test_label)

test_label=test_label.reshape(-1,1)

network=nn.Sequential(nn.Linear(18,5),nn.Sigmoid(),nn.Linear(5,1),nn.Sigmoid())

import torch.optim as optim

optimizer = optim.Adam(network.parameters(), lr=0.004)

for epoch in range(10000):

    optimizer.zero_grad()

    out=network(feature)

    l=loss(out,label)

    l.backward()

    optimizer.step()

    Y = torch.ge(out, 0.5).float()

    acc=Y.eq(label).float().sum()/len(label)

    out=network(test_feature)

    Y = torch.ge(out, 0.5).float()

    test_acc=Y.eq(test_label).float().sum()/len(test_label)

    print(epoch,l,acc,test_acc)

    #if test_acc==0.50 and acc>0.93:

    if acc>0.83 and test_acc==0.85:

        break

df = pd.read_csv('test.csv')

df=df.drop(['ID'],axis=1)

nmp=df.to_numpy()

feature=nmp[:,:]

feature=torch.fft.fft(torch.Tensor(feature))

feature=torch.abs(feature)/240*2

feature=torch.Tensor(feature[:,[0, 1, 60, 180, 239, 59, 120, 181, 61, 179, 119, 121, 58, 182, 57, 183, 62, 178]])

out=network(feature)

out=out.detach().numpy()

out=out>0.5

out=out.astype(np.int)

out=pd.DataFrame(out)

out.columns = ['CLASS']

w=[]

for k in range(out.shape[0]):

    w.append(k+210)

out['ID']=np.reshape(w,(-1,1))

out[['ID','CLASS']].to_csv('out.csv',index=False)