PyTorch一小时掌握之神经网络气温预测篇 PyTorch一小时掌握之神经网络气

概述
导包
数据读取
数据预处理
构建网络模型
数据可视化
完整代码

概述具体的案例描述在此就不多赘述. 同一数据集我们在机器学习里的随机森林模型中已经讨论过.
【PyTorch一小时掌握之神经网络气温预测篇】
导包

import numpy as npimport pandas as pdimport datetimeimport matplotlib.pyplot as pltfrom pandas.plotting import register_matplotlib_convertersfrom sklearn.preprocessing import StandardScalerimport torch

数据读取

# ------------------1. 数据读取------------------# 读取数据data = https://www.it610.com/article/pd.read_csv("temps.csv")# 看看数据长什么样子print(data.head())# 查看数据维度print("数据维度:", data.shape)# 产看数据类型print("数据类型:", type(data))

输出结果:
year month day week temp_2 temp_1 average actual friend
0 2016 1 1 Fri 45 45 45.6 45 29
1 2016 1 2 Sat 44 45 45.7 44 61
2 2016 1 3 Sun 45 44 45.8 41 56
3 2016 1 4 Mon 44 41 45.9 40 53
4 2016 1 5 Tues 41 40 46.0 44 41
数据维度: (348, 9)
数据类型:

数据预处理

# ------------------2. 数据预处理------------------# datetime 格式dates = pd.PeriodIndex(year=data["year"], month=data["month"], day=data["day"], freq="D").astype(str)dates = [datetime.datetime.strptime(date, "%Y-%m-%d") for date in dates]print(dates[:5])# 编码转换data = https://www.it610.com/article/pd.get_dummies(data)print(data.head())# 画图plt.style.use("fivethirtyeight")register_matplotlib_converters()# 标签labels = np.array(data["actual"])# 取消标签data = https://www.it610.com/article/data.drop(["actual"], axis= 1)print(data.head())# 保存一下列名feature_list = list(data.columns)# 格式转换data_new = np.array(data)data_new= StandardScaler().fit_transform(data_new)print(data_new[:5])

输出结果:
[datetime.datetime(2016, 1, 1, 0, 0), datetime.datetime(2016, 1, 2, 0, 0), datetime.datetime(2016, 1, 3, 0, 0), datetime.datetime(2016, 1, 4, 0, 0), datetime.datetime(2016, 1, 5, 0, 0)]
year month day temp_2 ... week_Sun week_Thurs week_Tues week_Wed
0 2016 1 1 45 ... 0 0 0 0
1 2016 1 2 44 ... 0 0 0 0
2 2016 1 3 45 ... 1 0 0 0
3 2016 1 4 44 ... 0 0 0 0
4 2016 1 5 41 ... 0 0 1 0
[5 rows x 15 columns]
year month day temp_2 ... week_Sun week_Thurs week_Tues week_Wed
0 2016 1 1 45 ... 0 0 0 0
1 2016 1 2 44 ... 0 0 0 0
2 2016 1 3 45 ... 1 0 0 0
3 2016 1 4 44 ... 0 0 0 0
4 2016 1 5 41 ... 0 0 1 0
[5 rows x 14 columns]
[[ 0. -1.5678393 -1.65682171 -1.48452388 -1.49443549 -1.3470703
-1.98891668 2.44131112 -0.40482045 -0.40961596 -0.40482045 -0.40482045
-0.41913682 -0.40482045]
[ 0. -1.5678393 -1.54267126 -1.56929813 -1.49443549 -1.33755752
0.06187741 -0.40961596 -0.40482045 2.44131112 -0.40482045 -0.40482045
-0.41913682 -0.40482045]
[ 0. -1.5678393 -1.4285208 -1.48452388 -1.57953835 -1.32804474
-0.25855917 -0.40961596 -0.40482045 -0.40961596 2.47023092 -0.40482045
-0.41913682 -0.40482045]
[ 0. -1.5678393 -1.31437034 -1.56929813 -1.83484692 -1.31853195
-0.45082111 -0.40961596 2.47023092 -0.40961596 -0.40482045 -0.40482045
-0.41913682 -0.40482045]
[ 0. -1.5678393 -1.20021989 -1.8236209 -1.91994977 -1.30901917
-1.2198689 -0.40961596 -0.40482045 -0.40961596 -0.40482045 -0.40482045
2.38585576 -0.40482045]]

构建网络模型

# ------------------3. 构建网络模型------------------x = torch.tensor(data_new)y = torch.tensor(labels)# 权重参数初始化weights1 = torch.randn((14,128), dtype=float, requires_grad= True)biases1 = torch.randn(128, dtype=float, requires_grad= True)weights2 = torch.randn((128,1), dtype=float, requires_grad= True)biases2 = torch.randn(1, dtype=float, requires_grad= True)learning_rate = 0.001losses = []for i in range(1000):# 计算隐层hidden = x.mm(weights1) + biases1# 加入激活函数hidden = torch.relu(hidden)# 预测结果predictions = hidden.mm(weights2) + biases2# 计算损失loss = torch.mean((predictions - y) ** 2)# 打印损失值if i % 100 == 0:print("loss:", loss)# 反向传播计算loss.backward()# 更新参数weights1.data.add_(-learning_rate * weights1.grad.data)biases1.data.add_(-learning_rate * biases1.grad.data)weights2.data.add_(-learning_rate * weights2.grad.data)biases2.data.add_(-learning_rate * biases2.grad.data)# 每次迭代清空weights1.grad.data.zero_()biases1.grad.data.zero_()weights2.grad.data.zero_()biases2.grad.data.zero_()

输出结果:
loss: tensor(4746.8598, dtype=torch.float64, grad_fn=)
loss: tensor(156.5691, dtype=torch.float64, grad_fn=)
loss: tensor(148.9419, dtype=torch.float64, grad_fn=)
loss: tensor(146.1035, dtype=torch.float64, grad_fn=)
loss: tensor(144.5652, dtype=torch.float64, grad_fn=)
loss: tensor(143.5376, dtype=torch.float64, grad_fn=)
loss: tensor(142.7823, dtype=torch.float64, grad_fn=)
loss: tensor(142.2151, dtype=torch.float64, grad_fn=)
loss: tensor(141.7770, dtype=torch.float64, grad_fn=)
loss: tensor(141.4294, dtype=torch.float64, grad_fn=)

数据可视化

# ------------------4. 数据可视化------------------def graph1():# 创建子图f, ax = plt.subplots(2, 2, figsize=(10, 10))# 标签值ax[0, 0].plot(dates, labels, color="#ADD8E6")ax[0, 0].set_xticks([""])ax[0, 0].set_ylabel("Temperature")ax[0, 0].set_title("Max Temp")# 昨天ax[0, 1].plot(dates, data["temp_1"], color="#87CEFA")ax[0, 1].set_xticks([""])ax[0, 1].set_ylabel("Temperature")ax[0, 1].set_title("Previous Max Temp")# 前天ax[1, 0].plot(dates, data["temp_2"], color="#00BFFF")ax[1, 0].set_xticks([""])ax[1, 0].set_xlabel("Date")ax[1, 0].set_ylabel("Temperature")ax[1, 0].set_title("Two Days Prior Max Temp")# 朋友ax[1, 1].plot(dates, data["friend"], color="#1E90FF")ax[1, 1].set_xticks([""])ax[1, 1].set_xlabel("Date")ax[1, 1].set_ylabel("Temperature")ax[1, 1].set_title("Friend Estimate")plt.show()

输出结果:

文章图片

完整代码

import numpy as npimport pandas as pdimport datetimeimport matplotlib.pyplot as pltfrom pandas.plotting import register_matplotlib_convertersfrom sklearn.preprocessing import StandardScalerimport torch# ------------------1. 数据读取------------------# 读取数据data = https://www.it610.com/article/pd.read_csv("temps.csv")# 看看数据长什么样子print(data.head())# 查看数据维度print("数据维度:", data.shape)# 产看数据类型print("数据类型:", type(data))# ------------------2. 数据预处理------------------# datetime 格式dates = pd.PeriodIndex(year=data["year"], month=data["month"], day=data["day"], freq="D").astype(str)dates = [datetime.datetime.strptime(date, "%Y-%m-%d") for date in dates]print(dates[:5])# 编码转换data = https://www.it610.com/article/pd.get_dummies(data)print(data.head())# 画图plt.style.use("fivethirtyeight")register_matplotlib_converters()# 标签labels = np.array(data["actual"])# 取消标签data = https://www.it610.com/article/data.drop(["actual"], axis= 1)print(data.head())# 保存一下列名feature_list = list(data.columns)# 格式转换data_new = np.array(data)data_new= StandardScaler().fit_transform(data_new)print(data_new[:5])# ------------------3. 构建网络模型------------------x = torch.tensor(data_new)y = torch.tensor(labels)# 权重参数初始化weights1 = torch.randn((14,128), dtype=float, requires_grad= True)biases1 = torch.randn(128, dtype=float, requires_grad= True)weights2 = torch.randn((128,1), dtype=float, requires_grad= True)biases2 = torch.randn(1, dtype=float, requires_grad= True)learning_rate = 0.001losses = []for i in range(1000):# 计算隐层hidden = x.mm(weights1) + biases1# 加入激活函数hidden = torch.relu(hidden)# 预测结果predictions = hidden.mm(weights2) + biases2# 计算损失loss = torch.mean((predictions - y) ** 2)# 打印损失值if i % 100 == 0:print("loss:", loss)# 反向传播计算loss.backward()# 更新参数weights1.data.add_(-learning_rate * weights1.grad.data)biases1.data.add_(-learning_rate * biases1.grad.data)weights2.data.add_(-learning_rate * weights2.grad.data)biases2.data.add_(-learning_rate * biases2.grad.data)# 每次迭代清空weights1.grad.data.zero_()biases1.grad.data.zero_()weights2.grad.data.zero_()biases2.grad.data.zero_()# ------------------4. 数据可视化------------------def graph1():# 创建子图f, ax = plt.subplots(2, 2, figsize=(10, 10))# 标签值ax[0, 0].plot(dates, labels, color="#ADD8E6")ax[0, 0].set_xticks([""])ax[0, 0].set_ylabel("Temperature")ax[0, 0].set_title("Max Temp")# 昨天ax[0, 1].plot(dates, data["temp_1"], color="#87CEFA")ax[0, 1].set_xticks([""])ax[0, 1].set_ylabel("Temperature")ax[0, 1].set_title("Previous Max Temp")# 前天ax[1, 0].plot(dates, data["temp_2"], color="#00BFFF")ax[1, 0].set_xticks([""])ax[1, 0].set_xlabel("Date")ax[1, 0].set_ylabel("Temperature")ax[1, 0].set_title("Two Days Prior Max Temp")# 朋友ax[1, 1].plot(dates, data["friend"], color="#1E90FF")ax[1, 1].set_xticks([""])ax[1, 1].set_xlabel("Date")ax[1, 1].set_ylabel("Temperature")ax[1, 1].set_title("Friend Estimate")plt.show()if __name__ == "__main__":graph1()

到此这篇关于PyTorch一小时掌握之神经网络气温预测篇的文章就介绍到这了,更多相关PyTorch 神经网络气温预测内容请搜索脚本之家以前的文章或继续浏览下面的相关文章希望大家以后多多支持脚本之家！