11.24每日总结

今天完成了大数据的测试，

这一次没有用hadoop用的

是python直接对数据的导入、

清洗、分析和可视化展示的操作，下面是所有的代码。

 

import torch
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import DataLoader, TensorDataset
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import mean_squared_error
import pandas as pd
import numpy as np



class LinearRegressionModel(nn.Module):
    def __init__(self, input_size):
        super(LinearRegressionModel, self).__init__()
        self.linear = nn.Linear(input_size, 1)

    def forward(self, x):
        return self.linear(x)

def dump_load_demo():
    # 1. 获取数据
    df = pd.read_csv('C:\\Users\\admin\\Desktop\\大数据竞赛练习题\\MathorCup大数据竞赛练习题1\\data\\data\\tmdb_1000_predict.csv',
                     sep=',', engine='python', header=[0])
    feature_arr = df[['budget', 'popularity', 'revenue', 'runtime']].values
    tag_arr = df['vote_count'].values
    print(len(tag_arr))


    # 2. 数据基本处理
    # 2.1 数据集划分
    x_train, x_test, y_train, y_test = train_test_split(feature_arr, tag_arr[:, np.newaxis], random_state=350,
                                                        test_size=0.2)

    # 3. 特征工程 --标准化
    transfer = StandardScaler()
    x_train = transfer.fit_transform(x_train)
    x_test = transfer.fit_transform(x_test)

    # 4. 机器学习(线性回归)
    # 4.1 模型训练
    input_size = x_train.shape[1]
    model = LinearRegressionModel(input_size)
    criterion = nn.MSELoss()
    optimizer = optim.SGD(model.parameters(), lr=0.01)

    x_train_tensor = torch.FloatTensor(x_train)
    y_train_tensor = torch.FloatTensor(y_train)
    x_test_tensor = torch.FloatTensor(x_test)

    # 转换为 PyTorch 的 DataLoader
    train_dataset = TensorDataset(x_train_tensor, y_train_tensor)
    train_loader = DataLoader(train_dataset, batch_size=32, shuffle=True)

    num_epochs = 100
    for epoch in range(num_epochs):
        for inputs, labels in train_loader:
            optimizer.zero_grad()
            outputs = model(inputs)
            loss = criterion(outputs, labels)
            loss.backward()
            optimizer.step()

    print("这个模型的偏置是:\n", model.linear.bias.item())

    import os

    if not os.path.exists("save"):
        os.makedirs("save")

    torch.save(model.state_dict(), "save/test.pth")

    # 4.2 模型保存
    torch.save(model.state_dict(), "save/test.pth")

    # 4.3 模型加载
    loaded_model = LinearRegressionModel(input_size)
    loaded_model.load_state_dict(torch.load("save/test.pth"))

    # 5. 模型评估
    # 5.1 预测值和准确率
    with torch.no_grad():
        y_pre = loaded_model(x_test_tensor).numpy()
        print("预测值是:\n", y_pre)
        import pandas as pd
        from sklearn.metrics import mean_squared_error

        # 假设y_test和y_pre是两个包含NaN值的DataFrame
        y_test = y_test.dropna()
        y_pre = y_pre.dropna()

        ret = mean_squared_error(y_test, y_pre)

        ret = mean_squared_error(y_test, y_pre)
        print("均方误差是:\n", ret)



if __name__ == '__main__':
    dump_load_demo()