1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
| import torch
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from torch.utils.data import Dataset
from torch.utils.data import DataLoader
class TitanicDataset(Dataset):
def __init__(self, filepath):
features = ["Pclass", "Sex", "Age", "SibSp", "Parch", "Fare", "Cabin", "Embarked"]
df = pd.read_csv(filepath)
df.loc[df["Sex"] == "male", "Sex"] = 0
df.loc[df["Sex"] == "female", "Sex"] = 1
df["Age"] = df["Age"].fillna(df["Age"].median())
df.loc[df.Cabin.notnull(), 'Cabin'] = 1
df.loc[df.Cabin.isnull(), 'Cabin'] = 0
df["Embarked"] = df["Embarked"].fillna("S")
df.loc[df["Embarked"] == "S", "Embarked"] = 0
df.loc[df["Embarked"] == "C", "Embarked"] = 1
df.loc[df["Embarked"] == "Q", "Embarked"] = 2
self.len = df.shape[0]
self.x_data = torch.from_numpy(np.array(pd.get_dummies(df[features])))
self.y_data = torch.from_numpy(np.array(df["Survived"]))
def __getitem__(self, index):
return self.x_data[index], self.y_data[index]
def __len__(self):
return self.len
train_df = TitanicDataset('./dataset/train.csv')
train_loader = DataLoader(dataset=train_df, batch_size=32, shuffle=True, num_workers=0)
class TitanicModel(torch.nn.Module):
def __init__(self):
super(TitanicModel, self).__init__()
self.linear1 = torch.nn.Linear(12, 9)
self.linear2 = torch.nn.Linear(9, 6)
self.linear3 = torch.nn.Linear(6, 3)
self.linear4 = torch.nn.Linear(3, 1)
self.relu = torch.nn.ReLU()
self.sigmoid = torch.nn.Sigmoid()
def forward(self, x):
x = self.relu(self.linear1(x))
x = self.relu(self.linear2(x))
x = self.relu(self.linear3(x))
x = self.sigmoid(self.linear4(x))
return x
def predict(self, x):
with torch.no_grad():
x = self.relu(self.linear1(x))
x = self.relu(self.linear2(x))
x = self.relu(self.linear3(x))
x = self.sigmoid(self.linear4(x))
y = []
for i in x:
print(i)
if i >= 0.5:
y.append(1)
else:
y.append(0)
return y
model = TitanicModel()
criterion = torch.nn.BCELoss()
optimizer = torch.optim.SGD(model.parameters(), lr=0.005)
if __name__ == "__main__":
epoch_list = []
loss_list = []
for epoch in range(1000):
loss_sum = 0
for idx, (inputs, labels) in enumerate(train_loader):
inputs = inputs.float()
labels = labels.float()
y_pred = model(inputs)
y_pred = y_pred.squeeze(-1)
loss = criterion(y_pred, labels)
loss_sum += loss.item()
print(epoch, idx, loss.item())
optimizer.zero_grad()
loss.backward()
optimizer.step()
epoch_list.append(epoch)
loss_list.append(loss_sum)
plt.plot(epoch_list, loss_list)
plt.ylabel('loss')
plt.xlabel('epoch')
plt.show()
min_loss = min(loss_list)
test_df = pd.read_csv("./dataset/test.csv")
features = ["Pclass", "Sex", "Age", "SibSp", "Parch", "Fare", "Cabin", "Embarked"]
test_df.loc[test_df["Sex"] == "male", "Sex"] = 0
test_df.loc[test_df["Sex"] == "female", "Sex"] = 1
test_df["Age"] = test_df["Age"].fillna(test_df["Age"].median())
test_df["Fare"] = test_df["Fare"].fillna(test_df["Fare"].median())
test_df.loc[test_df.Cabin.notnull(), 'Cabin'] = 1
test_df.loc[test_df.Cabin.isnull(), 'Cabin'] = 0
test_df["Embarked"] = test_df["Embarked"].fillna("S")
test_df.loc[test_df["Embarked"] == "S", "Embarked"] = 0
test_df.loc[test_df["Embarked"] == "C", "Embarked"] = 1
test_df.loc[test_df["Embarked"] == "Q", "Embarked"] = 2
test = torch.from_numpy(np.array(pd.get_dummies(test_df[features])))
y = model.predict(test.float())
output = pd.DataFrame({'PassengerId': test_df.PassengerId, 'Survived': y})
output.to_csv('./titanic_dataset/my_predict' + str(min_loss) + '.csv', index=False)
|
