编写pytorch代码,将格式为nadarrdy格式的数据集data_set,将其转换为DataFrame对象
时间: 2024-03-27 14:40:46 浏览: 101
好的,以下是可以将格式为nadarrdy格式的数据集data_set转换为DataFrame对象的PyTorch代码:
```python
import pandas as pd
import torch
# 读取nadarrdy格式数据集
with open('data_set', 'r') as f:
data = f.read().splitlines()
# 将数据按逗号分隔,并转换为DataFrame
df = pd.DataFrame([x.split(',') for x in data])
```
这段代码与前面的代码几乎相同,唯一的区别是我们将打开的文件名更改为data_set。我们使用`open()`函数读取文件,并使用`splitlines()`方法将文件分成行。然后,我们使用列表推导式将每一行按逗号分割,并将其转换为列表。最后,我们使用Pandas的`pd.DataFrame()`方法将列表转换为DataFrame。
现在,你可以使用Pandas的DataFrame对象对数据进行进一步的处理和分析了。
相关问题
编写一段pytorch程序,定义一个稀疏堆叠自编码器SSAE,将带有时间列的多特征的数据集training_set.csv、test_set.csv和pred_set.csv加载到SSAE中,将数据集转换为pytorch张量,对数据进行特征提取和归一化、标准化以后,将处理好的数据对应放入new_training_set、new_test_set和new_pred_set三个文件夹中,最后一列是标签列
好的,以下是使用PyTorch编写稀疏堆叠自编码器SSAE的代码,可以将带有时间列的多特征数据集进行特征提取和归一化、标准化处理,将处理好的数据保存到new_training_set、new_test_set和new_pred_set中:
```python
import torch
import torch.nn as nn
import torch.optim as optim
import pandas as pd
from sklearn.preprocessing import StandardScaler, MinMaxScaler
# 定义稀疏堆叠自编码器SSAE模型
class SSAE(nn.Module):
def __init__(self, input_dim, hidden_dim, output_dim):
super(SSAE, self).__init__()
self.encoder = nn.Sequential(
nn.Linear(input_dim, hidden_dim),
nn.ReLU(),
nn.Linear(hidden_dim, output_dim),
nn.Sigmoid(),
)
self.decoder = nn.Sequential(
nn.Linear(output_dim, hidden_dim),
nn.ReLU(),
nn.Linear(hidden_dim, input_dim),
nn.Sigmoid(),
)
def forward(self, x):
encoded = self.encoder(x)
decoded = self.decoder(encoded)
return encoded, decoded
# 加载数据集
train_data = pd.read_csv("training_set.csv")
test_data = pd.read_csv("test_set.csv")
pred_data = pd.read_csv("pred_set.csv")
# 将数据集转换为PyTorch张量
train_tensor = torch.tensor(train_data.values.astype(float))
test_tensor = torch.tensor(test_data.values.astype(float))
pred_tensor = torch.tensor(pred_data.values.astype(float))
# 特征提取和归一化、标准化
scaler = StandardScaler()
train_tensor[:, :-1] = torch.tensor(scaler.fit_transform(train_tensor[:, :-1]))
test_tensor[:, :-1] = torch.tensor(scaler.transform(test_tensor[:, :-1]))
pred_tensor = torch.tensor(scaler.transform(pred_tensor))
# 训练模型
input_dim = train_tensor.shape[1] - 1
hidden_dim = 10
output_dim = 5
model = SSAE(input_dim, hidden_dim, output_dim)
criterion = nn.MSELoss()
optimizer = optim.Adam(model.parameters(), lr=0.01)
num_epochs = 100
batch_size = 16
for epoch in range(num_epochs):
running_loss = 0.0
for i in range(0, len(train_tensor), batch_size):
batch_data = train_tensor[i:i+batch_size, :-1]
batch_label = train_tensor[i:i+batch_size, -1]
optimizer.zero_grad()
encoded, decoded = model(batch_data)
loss = criterion(decoded, batch_data)
loss.backward()
optimizer.step()
running_loss += loss.item() * batch_data.shape[0]
print(f"Epoch {epoch+1} loss: {running_loss / len(train_tensor)}")
# 对数据进行编码
train_encoded, _ = model(torch.tensor(train_data.values.astype(float))[:, :-1])
test_encoded, _ = model(torch.tensor(test_data.values.astype(float))[:, :-1])
pred_encoded, _ = model(torch.tensor(pred_data.values.astype(float))[:, :-1])
# 将数据保存到new_training_set、new_test_set和new_pred_set中
train_encoded = pd.concat([pd.DataFrame(train_encoded.detach().numpy()), train_data.iloc[:, -1]], axis=1)
test_encoded = pd.concat([pd.DataFrame(test_encoded.detach().numpy()), test_data.iloc[:, -1]], axis=1)
pred_encoded = pd.DataFrame(pred_encoded.detach().numpy())
train_encoded.to_csv("new_training_set.csv", index=False)
test_encoded.to_csv("new_test_set.csv", index=False)
pred_encoded.to_csv("new_pred_set.csv", index=False)
```
以上代码可以将训练集、测试集和预测集中的数据进行特征提取和归一化、标准化处理,并使用稀疏堆叠自编码器SSAE模型对数据进行编码,最后将处理好的数据保存到new_training_set、new_test_set和new_pred_set三个文件夹中。
写一个python Flask销售预测系统,系统有一个suanfa.py文件,该文件的作用:先读取shuju.csv(共有24条数据,包含Year、Month和TotalPrice三个属性),然后用scaler将TotalPrice进行归一化处理,之后定义一个函数def split_data(data, lookback):将数据集划分为测试集(0.2)和训练集(0.8),data_raw = data.to_numpy(),lookback = 4,然后再将划分完成后的测试集和训练集转换为PyTorch张量,然后定义超参数,定义算法模型model=LSTM()、损失函数和优化器(Adam)然后训练模型求出MSE,保存模型。有一个predict.html文件:里面有一个日期选择框和一个销售额预测按钮,用户选择好年份和月份后点击预测按钮系统就开始调用保存好的模型来对所选月份的销售额进行预测,然后将预测结果返回到日期选择框下面的结果返回框中;有一个app.py文件:定义路径。用flask和bootstrap、LayUI写出完整详细代码
对于这个任务,我们需要完成以下几个步骤:
1. 编写算法脚本 suanfa.py,用于数据处理、模型训练和预测。
2. 编写 Flask 应用 app.py,用于处理用户请求并返回结果。
3. 编写 HTML 页面 predict.html,用于获取用户输入并向后端发送请求。
下面是详细的代码:
suanfa.py
```python
import pandas as pd
import numpy as np
import torch
import torch.nn as nn
from sklearn.preprocessing import MinMaxScaler
def split_data(data, lookback):
"""
划分数据集为训练集和测试集
:param data: DataFrame格式的原始数据集
:param lookback: 窗口大小,即用前几个月的销售额来预测下一个月的销售额
:return: (训练集输入数据, 训练集输出数据, 测试集输入数据, 测试集输出数据, scaler)
"""
data_raw = data.to_numpy()
scaler = MinMaxScaler(feature_range=(-1, 1))
data_scaled = scaler.fit_transform(data_raw)
result = []
for index in range(len(data_scaled) - lookback):
result.append(data_scaled[index: index + lookback])
result = np.array(result)
row = round(0.8 * result.shape[0])
train = result[:int(row), :]
np.random.shuffle(train)
x_train = train[:, :-1]
y_train = train[:, -1][:, -1]
x_test = result[int(row):, :-1]
y_test = result[int(row):, -1][:, -1]
x_train = torch.from_numpy(x_train).type(torch.Tensor)
x_test = torch.from_numpy(x_test).type(torch.Tensor)
y_train = torch.from_numpy(y_train).type(torch.Tensor)
y_test = torch.from_numpy(y_test).type(torch.Tensor)
return x_train, y_train, x_test, y_test, scaler
class LSTM(nn.Module):
def __init__(self, input_size=1, hidden_layer_size=100, output_size=1):
super().__init__()
self.hidden_layer_size = hidden_layer_size
self.lstm = nn.LSTM(input_size, hidden_layer_size)
self.linear = nn.Linear(hidden_layer_size, output_size)
self.hidden_cell = (torch.zeros(1, 1, self.hidden_layer_size),
torch.zeros(1, 1, self.hidden_layer_size))
def forward(self, input_seq):
lstm_out, self.hidden_cell = self.lstm(input_seq.view(len(input_seq), 1, -1), self.hidden_cell)
predictions = self.linear(lstm_out.view(len(input_seq), -1))
return predictions[-1]
def train_model(data, lookback, model_path):
"""
训练模型并保存
:param data: DataFrame格式的原始数据集
:param lookback: 窗口大小,即用前几个月的销售额来预测下一个月的销售额
:param model_path: 保存模型的路径
"""
x_train, y_train, x_test, y_test, scaler = split_data(data, lookback)
model = LSTM()
loss_function = nn.MSELoss()
optimizer = torch.optim.Adam(model.parameters(), lr=0.001)
epochs = 150
for i in range(epochs):
for j in range(x_train.size()[0]):
optimizer.zero_grad()
model.hidden_cell = (torch.zeros(1, 1, model.hidden_layer_size),
torch.zeros(1, 1, model.hidden_layer_size))
y_pred = model(x_train[j])
single_loss = loss_function(y_pred, y_train[j])
single_loss.backward()
optimizer.step()
if i % 25 == 1:
print(f'epoch: {i:3} loss: {single_loss.item():10.8f}')
torch.save(model.state_dict(), model_path)
print("Model saved")
def predict(model_path, input_date):
"""
使用保存的模型预测销售额
:param model_path: 保存模型的路径
:param input_date: 用户选择的日期,格式为'YYYY-MM'
:return: 预测销售额
"""
model = LSTM()
model.load_state_dict(torch.load(model_path))
model.eval()
data = pd.read_csv('shuju.csv')
data = data.set_index('Year-Month')
# 将输入的日期转换为对应的行数
row_num = data.index.get_loc(input_date)
x = data.iloc[row_num - 4:row_num + 1]['TotalPrice'].values
x = scaler.transform(x.reshape(-1, 1))
x = torch.from_numpy(x).type(torch.Tensor)
with torch.no_grad():
model.hidden = (torch.zeros(1, 1, model.hidden_layer_size),
torch.zeros(1, 1, model.hidden_layer_size))
pred = model(x)
pred = scaler.inverse_transform(pred.reshape(-1, 1))
return round(pred[0][0])
```
app.py
```python
from flask import Flask, render_template, request
from suanfa import predict
app = Flask(__name__)
# 预测模型保存路径
model_path = 'model.pth'
@app.route('/')
def index():
return render_template('predict.html')
@app.route('/predict', methods=['POST'])
def predict_sales():
# 获取用户输入的日期
input_date = request.form['input_date']
# 调用预测函数得到预测结果
pred = predict(model_path, input_date)
return render_template('predict.html', prediction=pred)
```
predict.html
```html
<!DOCTYPE html>
<html>
<head>
<meta charset="UTF-8">
<title>销售额预测系统</title>
<link rel="stylesheet" href="https://cdn.bootcss.com/bootstrap/3.3.7/css/bootstrap.min.css">
<link rel="stylesheet" href="https://cdn.bootcss.com/bootstrap/3.3.7/css/bootstrap-theme.min.css">
<link rel="stylesheet" href="https://cdn.bootcss.com/layer/2.3/skin/default/layer.css">
<script src="https://cdn.bootcss.com/jquery/3.2.1/jquery.min.js"></script>
<script src="https://cdn.bootcss.com/bootstrap/3.3.7/js/bootstrap.min.js"></script>
<script src="https://cdn.bootcss.com/layer/2.3/layer.js"></script>
</head>
<body>
<div class="container">
<div class="page-header">
<h1>销售额预测系统</h1>
</div>
<div class="row">
<div class="col-md-6 col-md-offset-3">
<form class="form-inline" action="/predict" method="POST">
<div class="form-group">
<label for="input_date">日期:</label>
<input type="month" class="form-control" id="input_date" name="input_date" required>
</div>
<button type="submit" class="btn btn-primary">预测</button>
</form>
{% if prediction %}
<div class="alert alert-success" role="alert">
预测结果:{{ prediction }} 元
</div>
{% endif %}
</div>
</div>
</div>
</body>
</html>
```
在运行应用之前,需要在命令行中安装以下依赖:
```bash
pip install Flask pandas numpy torch sklearn
```
接下来,在命令行中输入以下命令启动应用:
```bash
export FLASK_APP=app.py
flask run
```
然后在浏览器中访问 http://127.0.0.1:5000/ 即可使用销售额预测系统。
阅读全文