--------教程摘自b站【不愧是计算机博士唐宇迪128集课程一套搞定了我大学4年没学会的PyTorch】PyTorch从入门到实战全套课程(附带课程学习资料 )_哔哩哔哩_bilibili
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import torch
import torch.optim as optim
import warnings
warnings.filterwarnings("ignore")
%matplotlib inline
features = pd.read_csv('temps.csv')#数据读取
features.head() #看看数据
#
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 |
数据表中
- year,moth,day,week分别表示的具体的时间
- temp_2:前天的最高温度值
- temp_1:昨天的最高温度值
- average:在历史中,每年这一天的平均最高温度值
- actual:这就是我们的标签值了,当天的真实最高温度
- friend:这一列可能是凑热闹的,你的朋友猜测的可能值,咱们不管它就好了
print('数据维度:', features.shape)
数据维度: (348, 9)
# 处理时间数据
import datetime
years = features['year'] # 分别得到年,月,日
months = features['month']
days = features['day']
dates = [str(int(year)) + '-' + str(int(month)) + '-' + str(int(day)) for year, month, day in zip(years, months, days)] #将数据改成 datetime格式
dates = [datetime.datetime.strptime(date, '%Y-%m-%d') for date in dates]
dates[:5]
#
[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)]
# 准备画图
# 指定默认风格
plt.style.use('fivethirtyeight')
# 设置布局
fig, ((ax1, ax2), (ax3, ax4)) = plt.subplots(nrows=2, ncols=2, figsize = (10,10))
fig.autofmt_xdate(rotation = 45)
# 标签值
ax1.plot(dates, features['actual'])
ax1.set_xlabel(''); ax1.set_ylabel('Temperature'); ax1.set_title('Max Temp')
# 昨天
ax2.plot(dates, features['temp_1'])
ax2.set_xlabel(''); ax2.set_ylabel('Temperature'); ax2.set_title('Previous Max Temp')
# 前天
ax3.plot(dates, features['temp_2'])
ax3.set_xlabel('Date'); ax3.set_ylabel('Temperature'); ax3.set_title('Two Days Prior Max Temp')
# 我的逗逼朋友
ax4.plot(dates, features['friend'])
ax4.set_xlabel('Date'); ax4.set_ylabel('Temperature'); ax4.set_title('Friend Estimate')
plt.tight_layout(pad=2)
# 独热编码 数据中week那一列为字符串
features = pd.get_dummies(features) #将字符串转换成数值的形式 直接将数据读入即可
features.head(5)
#表格中y是actual那一列,其余的是x
labels = np.array(features['actual']) #构建标签
# 在特征中去掉标签
features= features.drop('actual', axis = 1)
# 名字单独保存一下,以备后患
feature_list = list(features.columns)
# 转换成合适的格式
features = np.array(features)
#标准化
from sklearn import preprocessing
input_features = preprocessing.StandardScaler().fit_transform(features)
###fit_transform(trainData)对部分数据先拟合fit,找到该part的整体指标,如均值、方差、最大值最小值等等(根据具体转换的目的),然后对该trainData进行转换transform,从而实现数据的标准化、归一化等等。
构建网络模型
x = torch.tensor(input_features, dtype = float) #将x转换成tensor格式
y = torch.tensor(labels, dtype = float)
# 权重参数初始化
weights = torch.randn((14, 128), dtype = float, requires_grad = True)
biases = 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 = 0.001
losses = []
for i in range(1000):
hidden = x.mm(weights) + biases #X与权重进行矩阵乘法+偏置项
hidden = torch.relu(hidden) #加入激活函数
# 预测结果
predictions = hidden.mm(weights2) + biases2 #第二层
# 通计算损失
loss = torch.mean((predictions - y) ** 2) #预测-真实
losses.append(loss.data.numpy())
# 打印损失值
if i % 100 == 0:
print('loss:', loss)
#返向传播计算
loss.backward()
#更新参数 w1 b1 w2 b2
weights.data.add_(- learning_rate * weights.grad.data) #负号为反方向 梯度下降
biases.data.add_(- learning_rate * biases.grad.data)
weights2.data.add_(- learning_rate * weights2.grad.data)
biases2.data.add_(- learning_rate * biases2.grad.data)
# 每次迭代都得记得清空相应的梯度值
weights.grad.data.zero_()
biases.grad.data.zero_()
weights2.grad.data.zero_()
biases2.grad.data.zero_()