天气预测1

• 🍨 本文为[🔗365天深度学习训练营]中的学习记录博客
• 🍖 原作者：[K同学啊]

运行代码为：

import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
import warnings
import torch
import torch.nn as nn
import torch.optim as optim
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import MinMaxScaler, LabelEncoder
from sklearn.metrics import classification_report, confusion_matrix, r2_score, mean_absolute_error, \
    mean_absolute_percentage_error, mean_squared_error

warnings.filterwarnings('ignore')

# 导入数据
data = pd.read_csv("D:/研究生课题/深度学习-代码/weatherAUS.csv")
df = data.copy()
print(data.head())
print(data.describe())
print(data.dtypes)
data['Date'] = pd.to_datetime(data['Date'])
print(data['Date'])

# 增加年、月、日三个时间特征
data['year'] = data['Date'].dt.year
data['Month'] = data['Date'].dt.month
data['day'] = data['Date'].dt.day
print(data.head())
data.drop('Date', axis=1, inplace=True)
print(data.columns)

# 可视化相关性矩阵
plt.figure(figsize=(15, 13))
ax = sns.heatmap(data.corr(), square=True, annot=True, fmt='.2f')
ax.set_xticklabels(ax.get_xticklabels(), rotation=90)
plt.show()
plt.savefig('相关性分析.png')

# 是否会下雨的统计图
sns.set(style="darkgrid")
plt.figure(figsize=(4, 3))
sns.countplot(x='RainTomorrow', data=data)
plt.savefig('明天下雨与否数量统计.png')
plt.figure(figsize=(4, 3))
sns.countplot(x='RainToday', data=data)
plt.savefig('今天下雨与否数量统计.png', bbox_inches='tight')

# 地理位置与下雨的关系
x = pd.crosstab(data['RainTomorrow'], data['RainToday'])
print(x)
y = x / x.transpose().sum().values.reshape(2, 1) * 100
print(y)
y.plot(kind="bar", figsize=(4, 3), color=['#006666', '#d279a6'])
plt.savefig('是否会下雨条形图.png', bbox_inches='tight')

x = pd.crosstab(data['Location'], data['RainToday'])
y = x / x.transpose().sum().values.reshape(-1, 1) * 100
y = y.sort_values(by='Yes', ascending=True)
print(y)
fig, ax = plt.subplots(figsize=(15, 20))
color = ['#cc6699', '#006699', '#006666', '#862d86', '#ff9966']
y['Yes'].plot(kind='barh', ax=ax, color=color)
plt.savefig('地理位置与下雨的关系.png')

# 湿度和压力对下雨的影响
plt.figure(figsize=(8, 6))
sns.scatterplot(data=data, x='Pressure9am', y='Pressure3pm', hue='RainTomorrow')
plt.savefig('压力对下雨的影响.png')
plt.figure(figsize=(8, 6))
sns.scatterplot(data=data, x='Humidity9am', y='Humidity3pm', hue='RainTomorrow')
plt.savefig('湿度对下雨的影响.png')

# 气温对下雨的影响
plt.figure(figsize=(8, 6))
sns.scatterplot(x='MaxTemp', y='MinTemp', data=data, hue='RainTomorrow')
plt.savefig('气温对下雨的影响.png')

# 处理缺失值
data.isnull().sum() / data.shape[0] * 100

lst = ['Evaporation', 'Sunshine', 'Cloud9am', 'Cloud3pm']
for col in lst:
    fill_list = data[col].dropna()
    data[col] = data[col].fillna(pd.Series(np.random.choice(fill_list, size=len(data.index))))

s = (data.dtypes == "object")
object_cols = list(s[s].index)
print(object_cols)
for i in object_cols:
    data[i].fillna(data[i].mode()[0], inplace=True)

t = (data.dtypes == "float64")
num_cols = list(t[t].index)
print(num_cols)
for i in num_cols:
    data[i].fillna(data[i].median(), inplace=True)

print(data.isnull().sum())

# 构建数据集
label_encoder = LabelEncoder()
for i in object_cols:
    data[i] = label_encoder.fit_transform(data[i])

X = data.drop(['RainTomorrow', 'day'], axis=1).values
y = data['RainTomorrow'].values

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=101)

scaler = MinMaxScaler()
scaler.fit(X_train)
X_train = scaler.transform(X_train)
X_test = scaler.transform(X_test)

X_train = torch.tensor(X_train, dtype=torch.float32)
y_train = torch.tensor(y_train, dtype=torch.float32).unsqueeze(1)
X_test = torch.tensor(X_test, dtype=torch.float32)
y_test = torch.tensor(y_test, dtype=torch.float32).unsqueeze(1)


# 定义神经网络模型
class NeuralNet(nn.Module):
    def __init__(self):
        super(NeuralNet, self).__init__()
        self.fc1 = nn.Linear(X_train.shape[1], 24)
        self.fc2 = nn.Linear(24, 18)
        self.fc3 = nn.Linear(18, 23)
        self.dropout1 = nn.Dropout(0.5)
        self.fc4 = nn.Linear(23, 12)
        self.dropout2 = nn.Dropout(0.2)
        self.fc5 = nn.Linear(12, 1)
        self.sigmoid = nn.Sigmoid()

    def forward(self, x):
        x = torch.tanh(self.fc1(x))
        x = torch.tanh(self.fc2(x))
        x = torch.tanh(self.fc3(x))
        x = self.dropout1(x)
        x = torch.tanh(self.fc4(x))
        x = self.dropout2(x)
        x = self.sigmoid(self.fc5(x))
        return x


model = NeuralNet()

# 定义损失函数和优化器
criterion = nn.BCELoss()
optimizer = optim.Adam(model.parameters(), lr=1e-4)

# 模型训练
num_epochs = 10
for epoch in range(num_epochs):
    model.train()
    optimizer.zero_grad()
    outputs = model(X_train)
    loss = criterion(outputs, y_train)
    loss.backward()
    optimizer.step()

    if epoch % 2 == 0:
        print(f'Epoch {epoch}/{num_epochs}, Loss: {loss.item()}')

# 模型评估
model.eval()
with torch.no_grad():
    train_outputs = model(X_train)
    test_outputs = model(X_test)

train_loss = criterion(train_outputs, y_train).item()
test_loss = criterion(test_outputs, y_test).item()

print(f'Training Loss: {train_loss}')
print(f'Test Loss: {test_loss}')

# 可视化结果
train_acc = ((train_outputs > 0.5).float() == y_train).float().mean().item()
test_acc = ((test_outputs > 0.5).float() == y_test).float().mean().item()

print(f'Training Accuracy: {train_acc}')
print(f'Test Accuracy: {test_acc}')

 运行结果

 

 

 

运行结果代码

C:\Users\dell\anaconda3\envs\pytorch-gpu\python.exe C:\Users\dell\PycharmProjects\pythonProject5\rnn.py 
         Date Location  MinTemp  ...  Temp3pm  RainToday  RainTomorrow
0  2008-12-01   Albury     13.4  ...     21.8         No            No
1  2008-12-02   Albury      7.4  ...     24.3         No            No
2  2008-12-03   Albury     12.9  ...     23.2         No            No
3  2008-12-04   Albury      9.2  ...     26.5         No            No
4  2008-12-05   Albury     17.5  ...     29.7         No            No

[5 rows x 23 columns]
             MinTemp        MaxTemp  ...        Temp9am       Temp3pm
count  143975.000000  144199.000000  ...  143693.000000  141851.00000
mean       12.194034      23.221348  ...      16.990631      21.68339
std         6.398495       7.119049  ...       6.488753       6.93665
min        -8.500000      -4.800000  ...      -7.200000      -5.40000
25%         7.600000      17.900000  ...      12.300000      16.60000
50%        12.000000      22.600000  ...      16.700000      21.10000
75%        16.900000      28.200000  ...      21.600000      26.40000
max        33.900000      48.100000  ...      40.200000      46.70000

[8 rows x 16 columns]
Date              object
Location          object
MinTemp          float64
MaxTemp          float64
Rainfall         float64
Evaporation      float64
Sunshine         float64
WindGustDir       object
WindGustSpeed    float64
WindDir9am        object
WindDir3pm        object
WindSpeed9am     float64
WindSpeed3pm     float64
Humidity9am      float64
Humidity3pm      float64
Pressure9am      float64
Pressure3pm      float64
Cloud9am         float64
Cloud3pm         float64
Temp9am          float64
Temp3pm          float64
RainToday         object
RainTomorrow      object
dtype: object
0        2008-12-01
1        2008-12-02
2        2008-12-03
3        2008-12-04
4        2008-12-05
            ...    
145455   2017-06-21
145456   2017-06-22
145457   2017-06-23
145458   2017-06-24
145459   2017-06-25
Name: Date, Length: 145460, dtype: datetime64[ns]
        Date Location  MinTemp  MaxTemp  ...  RainTomorrow  year  Month day
0 2008-12-01   Albury     13.4     22.9  ...            No  2008     12   1
1 2008-12-02   Albury      7.4     25.1  ...            No  2008     12   2
2 2008-12-03   Albury     12.9     25.7  ...            No  2008     12   3
3 2008-12-04   Albury      9.2     28.0  ...            No  2008     12   4
4 2008-12-05   Albury     17.5     32.3  ...            No  2008     12   5

[5 rows x 26 columns]
Index(['Location', 'MinTemp', 'MaxTemp', 'Rainfall', 'Evaporation', 'Sunshine',
       'WindGustDir', 'WindGustSpeed', 'WindDir9am', 'WindDir3pm',
       'WindSpeed9am', 'WindSpeed3pm', 'Humidity9am', 'Humidity3pm',
       'Pressure9am', 'Pressure3pm', 'Cloud9am', 'Cloud3pm', 'Temp9am',
       'Temp3pm', 'RainToday', 'RainTomorrow', 'year', 'Month', 'day'],
      dtype='object')
RainToday        No    Yes
RainTomorrow              
No            92728  16858
Yes           16604  14597
RainToday            No        Yes
RainTomorrow                      
No            84.616648  15.383352
Yes           53.216243  46.783757
RainToday                No        Yes
Location                              
Woomera           93.246406   6.753594
Uluru             92.378449   7.621551
AliceSprings      91.952507   8.047493
Mildura           89.125374  10.874626
Cobar             87.081660  12.918340
Moree             86.194814  13.805186
Nhil              84.576163  15.423837
SalmonGums        84.027073  15.972927
Katherine         83.012821  16.987179
Townsville        82.855259  17.144741
WaggaWagga        81.989247  18.010753
PearceRAAF        81.716148  18.283852
Canberra          81.597425  18.402575
Bendigo           81.476599  18.523401
PerthAirport      81.156530  18.843470
Tuggeranong       81.054036  18.945964
Richmond          81.023382  18.976618
Nuriootpa         80.286380  19.713620
BadgerysCreek     80.088798  19.911202
Penrith           79.925776  20.074224
Perth             79.799562  20.200438
Albury            79.508469  20.491531
Sale              78.566667  21.433333
MelbourneAirport  78.298438  21.701562
Adelaide          77.709479  22.290521
Brisbane          77.570389  22.429611
Launceston        76.882431  23.117569
Hobart            76.097867  23.902133
Wollongong        76.089873  23.910127
Watsonia          75.391797  24.608203
Newcastle         75.262267  24.737733
SydneyAirport     74.242928  25.757072
Ballarat          74.207398  25.792602
Sydney            74.048547  25.951453
GoldCoast         73.993289  26.006711
Melbourne         73.880903  26.119097
Darwin            73.316630  26.683370
Williamtown       72.581277  27.418723
NorahHead         72.413793  27.586207
MountGinini       71.826625  28.173375
CoffsHarbour      70.572299  29.427701
Witchcliffe       70.223577  29.776423
Albany            70.092838  29.907162
MountGambier      69.613989  30.386011
NorfolkIsland     68.994602  31.005398
Dartmoor          68.694765  31.305235
Cairns            68.206158  31.793842
Walpole           66.335580  33.664420
Portland          63.484646  36.515354
['Location', 'WindGustDir', 'WindDir9am', 'WindDir3pm', 'RainToday', 'RainTomorrow']
['MinTemp', 'MaxTemp', 'Rainfall', 'Evaporation', 'Sunshine', 'WindGustSpeed', 'WindSpeed9am', 'WindSpeed3pm', 'Humidity9am', 'Humidity3pm', 'Pressure9am', 'Pressure3pm', 'Cloud9am', 'Cloud3pm', 'Temp9am', 'Temp3pm']
Location         0
MinTemp          0
MaxTemp          0
Rainfall         0
Evaporation      0
Sunshine         0
WindGustDir      0
WindGustSpeed    0
WindDir9am       0
WindDir3pm       0
WindSpeed9am     0
WindSpeed3pm     0
Humidity9am      0
Humidity3pm      0
Pressure9am      0
Pressure3pm      0
Cloud9am         0
Cloud3pm         0
Temp9am          0
Temp3pm          0
RainToday        0
RainTomorrow     0
year             0
Month            0
day              0
dtype: int64
Epoch 0/10, Loss: 0.7397468686103821
Epoch 2/10, Loss: 0.7384240031242371
Epoch 4/10, Loss: 0.7370564341545105
Epoch 6/10, Loss: 0.7355726361274719
Epoch 8/10, Loss: 0.7342917919158936
Training Loss: 0.7325757741928101
Test Loss: 0.7322903275489807
Training Accuracy: 0.21866263449192047
Test Accuracy: 0.22059673070907593

进程已结束，退出代码为 0

心得总结

本实验使用PyTorch构建了一个多层感知器模型，预测天气数据中“明天是否会下雨”。通过数据预处理、特征工程和模型训练，模型在二分类任务中表现良好。