PyTorch一小時掌握之神經(jīng)網(wǎng)絡(luò)氣溫預(yù)測篇

import numpy as np
import pandas as pd
import datetime
import matplotlib.pyplot as plt
from pandas.plotting import register_matplotlib_converters
from sklearn.preprocessing import StandardScaler
import torch

# ------------------1. 數(shù)據(jù)讀取------------------

# 讀取數(shù)據(jù)
data = pd.read_csv("temps.csv")

# 看看數(shù)據(jù)長什么樣子
print(data.head())

# 查看數(shù)據(jù)維度
print("數(shù)據(jù)維度:", data.shape)

# 產(chǎn)看數(shù)據(jù)類型
print("數(shù)據(jù)類型:", type(data))

# ------------------2. 數(shù)據(jù)預(yù)處理------------------

# 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])

# 編碼轉(zhuǎn)換
data = pd.get_dummies(data)
print(data.head())

# 畫圖
plt.style.use("fivethirtyeight")
register_matplotlib_converters()

# 標(biāo)簽
labels = np.array(data["actual"])

# 取消標(biāo)簽
data = data.drop(["actual"], axis= 1)
print(data.head())

# 保存一下列名
feature_list = list(data.columns)

# 格式轉(zhuǎn)換
data_new = np.array(data)

data_new  = StandardScaler().fit_transform(data_new)
print(data_new[:5])

# ------------------3. 構(gòu)建網(wǎng)絡(luò)模型------------------

x = torch.tensor(data_new)
y = torch.tensor(labels)

# 權(quán)重參數(shù)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 = 0.001
losses = []

for i in range(1000):
    # 計算隱層
    hidden = x.mm(weights1) + biases1
    # 加入激活函數(shù)
    hidden = torch.relu(hidden)
    # 預(yù)測結(jié)果
    predictions = hidden.mm(weights2) + biases2
    # 計算損失
    loss = torch.mean((predictions - y) ** 2)

    # 打印損失值
    if i % 100 == 0:
        print("loss:", loss)
    # 反向傳播計算
    loss.backward()

    # 更新參數(shù)
    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. 數(shù)據(jù)可視化------------------

def graph1():
    # 創(chuàng)建子圖
    f, ax = plt.subplots(2, 2, figsize=(10, 10))

    # 標(biāo)簽值
    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()

import numpy as np
import pandas as pd
import datetime
import matplotlib.pyplot as plt
from pandas.plotting import register_matplotlib_converters
from sklearn.preprocessing import StandardScaler
import torch


# ------------------1. 數(shù)據(jù)讀取------------------

# 讀取數(shù)據(jù)
data = pd.read_csv("temps.csv")

# 看看數(shù)據(jù)長什么樣子
print(data.head())

# 查看數(shù)據(jù)維度
print("數(shù)據(jù)維度:", data.shape)

# 產(chǎn)看數(shù)據(jù)類型
print("數(shù)據(jù)類型:", type(data))

# ------------------2. 數(shù)據(jù)預(yù)處理------------------

# 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])

# 編碼轉(zhuǎn)換
data = pd.get_dummies(data)
print(data.head())

# 畫圖
plt.style.use("fivethirtyeight")
register_matplotlib_converters()

# 標(biāo)簽
labels = np.array(data["actual"])

# 取消標(biāo)簽
data = data.drop(["actual"], axis= 1)
print(data.head())

# 保存一下列名
feature_list = list(data.columns)

# 格式轉(zhuǎn)換
data_new = np.array(data)

data_new  = StandardScaler().fit_transform(data_new)
print(data_new[:5])

# ------------------3. 構(gòu)建網(wǎng)絡(luò)模型------------------

x = torch.tensor(data_new)
y = torch.tensor(labels)

# 權(quán)重參數(shù)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 = 0.001
losses = []

for i in range(1000):
    # 計算隱層
    hidden = x.mm(weights1) + biases1
    # 加入激活函數(shù)
    hidden = torch.relu(hidden)
    # 預(yù)測結(jié)果
    predictions = hidden.mm(weights2) + biases2
    # 計算損失
    loss = torch.mean((predictions - y) ** 2)

    # 打印損失值
    if i % 100 == 0:
        print("loss:", loss)
    # 反向傳播計算
    loss.backward()

    # 更新參數(shù)
    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. 數(shù)據(jù)可視化------------------

def graph1():
    # 創(chuàng)建子圖
    f, ax = plt.subplots(2, 2, figsize=(10, 10))

    # 標(biāo)簽值
    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()