torch神經網路溫度預測

星空28發表於2024-10-06
神經網路

資料件檔案temp.csv


"""
氣溫預測
"""
import datetime
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')

features = pd.read_csv('temps.csv')
features.head()
# --------資料說明--------
# temp_2：前天的最高溫度值
# temp_1：昨天的最高溫度值
# average：在歷史中，每年這一天的平均最高溫度值
# actual：這就是我們的標籤，當天的真實最高溫度
# friend：朋友猜測的可能值
print(features.shape)
years = features['year']
months = features['month']
days = features['day']

# datetime格式
dates = [str(int(year)) + '-' + str(int(month)) + '-' + str(int(day)) for year, month, day in zip(years, months, days)]
dates = [datetime.datetime.strptime(date, '%Y-%m-%d') for date in dates]
print(dates[:5])

# -----------畫圖看資料-----------
plt.style.use('fivethirtyeight')
# 設定佈局
fig, ((ax1, ax2), (ax3, ax4)) = plt.subplots(nrows=2, ncols=2, figsize=(10, 10))
fig.autofmt_xdate(rotation=45)

# 標籤值
ax1.plot(dates, features['actual'])
ax1.set_xlabel('');ax1.set_ylabel('Temp');ax1.set_title('Max Temp')
# 昨天
ax2.plot(dates, features['temp_1'])
ax2.set_xlabel('');ax2.set_ylabel('Temp');ax2.set_title('Previous Max Temp')
# 前天
ax3.plot(dates, features['temp_2'])
ax3.set_xlabel('Date');ax3.set_ylabel('Temp');ax3.set_title('Two Days Prior Max Temp')
# 我的朋友
ax4.plot(dates, features['friend'])
ax4.set_xlabel('Date');ax4.set_ylabel('Temp');ax4.set_title('Friend Estimate')
plt.tight_layout(pad=2)
plt.show()

# week列為字串不是數值，利用獨熱編碼，將資料中非字串轉換為數值，並拼接到資料中
features = pd.get_dummies(features)
# 看獨熱編碼的效果
print(features.head(5))

# 標籤
labels = np.array(features['actual'])

# 去掉標籤用作特徵
features = features.drop('actual', axis=1)

# 儲存列名用於展示
features_list = list(features.columns)

# 轉換為合適的格式
features = np.array(features)
print(features.shape)

# 資料標準化
from sklearn import preprocessing

input_features = preprocessing.StandardScaler().fit_transform(features)

# 看一下數字標準化的效果
print(input_features[0])

# =======================構建神經網路模型=============================== #
# 將輸入和預測轉為tensor
x = torch.tensor(input_features, dtype=float)
y = torch.tensor(labels, dtype=float)

# 權重引數初始化
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):
    # 前向傳播
    # 計算隱藏層
    hidden = x.mm(weights) + biases
    # 加入啟用函式
    hidden = torch.relu(hidden)
    # 預測結果
    predictions = hidden.mm(weights2) + biases2
    # 計算損失
    loss = torch.mean((predictions - y)**2)
    losses.append(loss.data.numpy())

    # 列印損失
    if i % 100 == 0:
        print('loss:', loss)
    # 反向傳播
    loss.backward()
    # 更新引數
    weights.data.add_(- learning_rate * weights.grad.data)
    biases.data.add_(- learning_rate * biases.grad.data)
    weights2.data.add_(- learning_rate * weights2.grad.data)
    biases2.data.add_(- learning_rate * biases2.grad.data)

    # 梯度清零
    weights.grad.data.zero_()
    biases.grad.data.zero_()
    weights2.grad.data.zero_()
    biases2.grad.data.zero_()


# -----或者我們使用簡化的方法----
input_size = input_features.shape[1]
hidden_size = 128
output_size = 1
batch_size = 16
my_nn = torch.nn.Sequential(
    torch.nn.Linear(input_size, hidden_size),
    torch.nn.Sigmoid(),
    torch.nn.Linear(hidden_size, output_size),
)

# 指定損失函式
cost = torch.nn.MSELoss(reduction='mean')

# 指定最佳化器
optimizer = torch.optim.Adam(my_nn.parameters(), lr=0.001)

# 訓練網路
losses = []
for i in range(1000):
    batch_loss = []
    for start in range(0, len(input_features), batch_size):
        end = start + batch_size if start + batch_size < len(input_features) else len(input_features)
        xx = torch.tensor(input_features[start:end], dtype=torch.float, requires_grad=True)
        yy = torch.tensor(labels[start:end], dtype=torch.float, requires_grad=True)
        prediction = my_nn(xx)
        loss = cost(prediction, yy)
        optimizer.zero_grad()
        loss.backward(retain_graph=True)
        optimizer.step()
        batch_loss.append(loss.data.numpy())

    if i % 100 == 0:
        losses.append(np.mean(batch_loss))
        print(i, np.mean(batch_loss))


# 預測，並以圖片的形式展示
# 預測結果
x = torch.tensor(input_features, dtype=torch.float)
predict = my_nn(x).data.numpy() # 轉化為numpy格式，tensor格式畫不了圖

# 轉換日期格式
dates = [str(int(year)) + '-' + str(int(month)) + '-' + str(int(day)) for year, month, day in zip(years, months, days)]
dates = [datetime.datetime.strptime(date, '%Y-%m-%d') for date in dates]

# 建立一個表格來儲存日期和其對應的標籤數值
true_data = pd.DataFrame(data={'date': dates, 'actual': labels})

# 再建立一個來存日期和其對應的模型預測值
months = features[:, features_list.index('month')]
days = features[:, features_list.index('day')]
years = features[:, features_list.index('year')]

test_dates = [str(int(year)) + '-' + str(int(month)) + '-' + str(int(day)) for year, month, day in zip(years, months, days)]
test_dates = dates

predictions_data = pd.DataFrame(data={'date': test_dates, 'prediction': predict.reshape(-1)})

# 真實值
plt.plot(true_data['date'], true_data['actual'], 'b-', label='actual')

# 預測值
plt.plot(predictions_data['date'], predictions_data['prediction'], 'ro', label='prediction')
plt.xticks(rotation='vertical');
plt.legend()

# 圖名
plt.xlabel('Date')
plt.ylabel('Maximum Temperature (F)')
plt.title('Actual and Predicted Values')
plt.show()

相關文章