s444421/ium_444421
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Update files

Browse Source
This commit is contained in:
Agata 2022-05-29 13:46:40 +02:00
parent 4905e68ac6
commit e8af09d8a7
8 changed files with 145 additions and 195 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
.dvc/config
View File

@ -0,0 +1,6 @@
[core]
remote = ium_ssh_remote
['remote "my_local_remote"']
url = /dvcstore
['remote "ium_ssh_remote"']
url = ssh://ium-sftp@tzietkiewicz.vm.wmi.amu.edu.pl

5
.gitignore vendored
View File

@ -12,3 +12,8 @@ ipython_config.py
# Remove previous ipynb_checkpoints # Remove previous ipynb_checkpoints
# git rm -r .ipynb_checkpoints/ # git rm -r .ipynb_checkpoints/
/X_train.csv
/X_test.csv
/y_train.csv
/y_test.csv
/model.pth

3
Dockerfile
View File

@ -13,5 +13,6 @@ WORKDIR /app
COPY ./body-performance-data.zip ./ COPY ./body-performance-data.zip ./
COPY ./classification_net.py ./ COPY ./prepare_datasets.py ./
COPY ./train.py ./

192
classification_net.py
View File

@ -1,192 +0,0 @@
#!/usr/bin/env python
# coding: utf-8
# In[ ]:
# get_ipython().system('kaggle datasets download -d kukuroo3/body-performance-data')
# In[ ]:
get_ipython().system('unzip -o body-performance-data.zip')
# In[114]:
import numpy as np
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report
import torch
from torch import nn, optim
import torch.nn.functional as F
# In[115]:
df = pd.read_csv('bodyPerformance.csv')
df.shape
# In[116]:
df.head()
# In[117]:
cols = ['gender', 'height_cm', 'weight_kg', 'body fat_%', 'sit-ups counts', 'broad jump_cm']
df = df[cols]
# male - 0, female - 1
df['gender'].replace({'M': 0, 'F': 1}, inplace = True)
df = df.dropna(how='any')
# In[118]:
df.gender.value_counts() / df.shape[0]
# In[119]:
X = df[['height_cm', 'weight_kg', 'body fat_%', 'sit-ups counts', 'broad jump_cm']]
y = df[['gender']]
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
# In[120]:
X_train = torch.from_numpy(np.array(X_train)).float()
y_train = torch.squeeze(torch.from_numpy(y_train.values).float())
X_test = torch.from_numpy(np.array(X_test)).float()
y_test = torch.squeeze(torch.from_numpy(y_test.values).float())
print(X_train.shape, y_train.shape)
print(X_test.shape, y_test.shape)
# In[121]:
class Net(nn.Module):
def __init__(self, n_features):
super(Net, self).__init__()
self.fc1 = nn.Linear(n_features, 5)
self.fc2 = nn.Linear(5, 3)
self.fc3 = nn.Linear(3, 1)
def forward(self, x):
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
return torch.sigmoid(self.fc3(x))
net = Net(X_train.shape[1])
# In[122]:
criterion = nn.BCELoss()
# In[123]:
optimizer = optim.Adam(net.parameters(), lr=0.001)
# In[124]:
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
# In[125]:
X_train = X_train.to(device)
y_train = y_train.to(device)
X_test = X_test.to(device)
y_test = y_test.to(device)
# In[126]:
net = net.to(device)
criterion = criterion.to(device)
# In[127]:
def calculate_accuracy(y_true, y_pred):
predicted = y_pred.ge(.5).view(-1)
return (y_true == predicted).sum().float() / len(y_true)
# In[128]:
def round_tensor(t, decimal_places=3):
return round(t.item(), decimal_places)
for epoch in range(1000):
y_pred = net(X_train)
y_pred = torch.squeeze(y_pred)
train_loss = criterion(y_pred, y_train)
if epoch % 100 == 0:
train_acc = calculate_accuracy(y_train, y_pred)
y_test_pred = net(X_test)
y_test_pred = torch.squeeze(y_test_pred)
test_loss = criterion(y_test_pred, y_test)
test_acc = calculate_accuracy(y_test, y_test_pred)
print(
f'''epoch {epoch}
Train set - loss: {round_tensor(train_loss)}, accuracy: {round_tensor(train_acc)}
Test set - loss: {round_tensor(test_loss)}, accuracy: {round_tensor(test_acc)}
''')
optimizer.zero_grad()
train_loss.backward()
optimizer.step()
# In[129]:
# torch.save(net, 'model.pth')
# In[130]:
# net = torch.load('model.pth')
# In[131]:
classes = ['Male', 'Female']
y_pred = net(X_test)
y_pred = y_pred.ge(.5).view(-1).cpu()
y_test = y_test.cpu()
print(classification_report(y_test, y_pred, target_names=classes))
# In[132]:
with open('test_out.csv', 'w') as file:
for y in y_pred:
file.write(classes[y.item()])
file.write('\n')

17
dvc.Jenkinsfile Normal file
View File

@ -0,0 +1,17 @@
pipeline {
agent {
dockerfile true
}
stages {
stage('Dvc pull and reproduce') {
steps {
checkout([$class: 'GitSCM', branches: [[name: '*/master']], extensions: [], userRemoteConfigs: [[credentialsId: 's444421', url: 'https://git.wmi.amu.edu.pl/s444421/ium_444421.git']]])
withCredentials([string(credentialsId: 'ium-sftp-password', variable: 'IUM_SFTP_PASS')]) {
sh 'dvc remote add -d ium_ssh_remote ssh://ium-sftp@tzietkiewicz.vm.wmi.amu.edu.pl/ium-sftp'
sh 'dvc remote modify --local ium_ssh_remote password $IUM_SFTP_KEY'
sh 'dvc pull'
}
}
}
}
}

19
dvc.yaml Normal file
View File

@ -0,0 +1,19 @@
stages:
prepare_datasets:
cmd: python prepare_datasets.py X_train.csv X_test.csv y_train.csv y_test.csv
deps:
- data/bodyPerformance.csv
- prepare_datasets.py
outs:
- X_test.csv
- X_train.csv
- y_test.csv
- y_train.csv
train:
cmd: python train.py model.pth
deps:
- X_train.csv
- train.py
- y_train.csv
outs:
- model.pth

4
prepare_datasets.py
View File

@ -4,7 +4,7 @@
# In[ ]: # In[ ]:
get_ipython().system('unzip -o body-performance-data.zip') # get_ipython().system('unzip -o body-performance-data.zip')
# In[4]: # In[4]:
@ -17,7 +17,7 @@ from sklearn.model_selection import train_test_split
# In[21]: # In[21]:
df = pd.read_csv('bodyPerformance.csv') df = pd.read_csv('data/bodyPerformance.csv')
# In[22]: # In[22]:

94
train.py Normal file
View File

@ -0,0 +1,94 @@
#!/usr/bin/env python
# coding: utf-8
# In[ ]:
import numpy as np
import pandas as pd
import torch
from torch import nn, optim
import torch.nn.functional as F
import sys
# In[ ]:
X_train = pd.read_csv('X_train.csv')
y_train = pd.read_csv('y_train.csv')
# In[ ]:
X_train = torch.from_numpy(np.array(X_train)).float()
y_train = torch.squeeze(torch.from_numpy(y_train.values).float())
# In[ ]:
class Net(nn.Module):
def __init__(self, n_features):
super(Net, self).__init__()
self.fc1 = nn.Linear(n_features, 5)
self.fc2 = nn.Linear(5, 3)
self.fc3 = nn.Linear(3, 1)
def forward(self, x):
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
return torch.sigmoid(self.fc3(x))
# In[ ]:
net = Net(X_train.shape[1])
criterion = nn.BCELoss()
optimizer = optim.Adam(net.parameters(), lr=0.001)
# In[ ]:
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
X_train = X_train.to(device)
y_train = y_train.to(device)
net = net.to(device)
criterion = criterion.to(device)
# In[ ]:
def calculate_accuracy(y_true, y_pred):
predicted = y_pred.ge(.5).view(-1)
return (y_true == predicted).sum().float() / len(y_true)
def round_tensor(t, decimal_places=3):
return round(t.item(), decimal_places)
for epoch in range(1000):
y_pred = net(X_train)
y_pred = torch.squeeze(y_pred)
train_loss = criterion(y_pred, y_train)
if epoch % 100 == 0:
train_acc = calculate_accuracy(y_train, y_pred)
print(
f'''epoch {epoch}
Train set - loss: {round_tensor(train_loss)}, accuracy: {round_tensor(train_acc)}
''')
optimizer.zero_grad()
train_loss.backward()
optimizer.step()
# In[ ]:
torch.save(net, 'model.pth')