重命名 第十三组 为 共享单车数据集分析

共享单车数据集分析/src/main.py

@@ -0,0 +1,134 @@
+import torch
+import pandas as pd
+import numpy as np
+import os
+import time
+import torch.optim as optim
+import matplotlib.pyplot as plt
+
+train_data = pd.read_csv('../train.csv')
+test_data = pd.read_csv('../test.csv')
+#print(train_data)
+datetime=train_data['datetime'].values
+season=train_data['season'].values
+holiday=train_data['holiday'].values
+workingday=train_data['workingday'].values
+weather=train_data['weather'].values
+temp=train_data['temp'].values
+atemp=train_data['atemp'].values
+humidity=train_data['humidity'].values
+windspeed=train_data['windspeed'].values
+casual=train_data['casual'].values
+registered=train_data['registered'].values
+
+count=train_data['count'].values
+
+'''
+转换datetime,去掉不必要的符号和0
+'''
+def datetime_convert(datetime):
+    for i in range(len(datetime)):
+        datetime[i]=datetime[i].replace("-", "").replace(" ", "").replace(":00:00","")
+        datetime[i]=int(datetime[i])
+    return datetime
+datetime_convert(datetime)
+train_data['datetime']=datetime
+datetime_convert(test_data['datetime'].values)
+test_data['datetime']=test_data['datetime'].values
+'''
+标准化数据
+'''
+def normalize(ndarry):
+    ndarry=(ndarry-ndarry.mean())/ndarry.std()
+    return ndarry
+
+for i in range(12):
+    train_data.iloc[:,i]=normalize(train_data.iloc[:,i])
+
+
+
+
+X=torch.tensor(train_data.iloc[:,:9].to_numpy().astype(float),dtype=torch.float32)
+Y=torch.tensor(train_data.iloc[:,9:12].to_numpy().astype(float),dtype=torch.float32)
+X_test=torch.tensor(test_data.iloc[:,:9].to_numpy().astype(float),dtype=torch.float32)
+torch_train_dataset = torch.utils.data.TensorDataset(X, Y)
+batch_size = 10
+torch.manual_seed(seed=2023)
+
+training, vertification = torch.utils.data.random_split(torch_train_dataset, [10000, 886], )
+training_data = torch.utils.data.DataLoader(training,batch_size=batch_size,shuffle=True)
+vertification_data = torch.utils.data.DataLoader(training,batch_size=batch_size,shuffle=True)
+
+feature_number = 9  # 设置特征数目
+out_prediction = 3  # 设置输出数目
+learning_rate = 0.01  # 设置学习率
+epochs = 10 # 设置训练代数
+
+
+class Net(torch.nn.Module):
+    def __init__(self, n_feature, n_output, n_neuron1, n_neuron2,
+                 n_layer):  # n_feature为特征数目，这个数字不能随便取,n_output为特征对应的输出数目，也不能随便取
+        self.n_feature = n_feature
+        self.n_output = n_output
+        self.n_neuron1 = n_neuron1
+        self.n_neuron2 = n_neuron2
+        self.n_layer = n_layer
+        super(Net, self).__init__()
+        self.input_layer = torch.nn.Linear(self.n_feature, self.n_neuron1)  # 输入层
+        self.hidden1 = torch.nn.Linear(self.n_neuron1, self.n_neuron2)  # 1类隐藏层
+        self.hidden2 = torch.nn.Linear(self.n_neuron2, self.n_neuron2)  # 2类隐藏
+        self.predict = torch.nn.Linear(self.n_neuron2, self.n_output)  # 输出层
+
+    def forward(self, x):
+        '''定义前向传递过程'''
+        out = self.input_layer(x)
+        out = torch.relu(out)  # 使用relu函数非线性激活
+        out = self.hidden1(out)
+        out = torch.relu(out)
+        for i in range(self.n_layer):
+            out = self.hidden2(out)
+            out = torch.relu(out)
+        out = self.predict(  # 回归问题最后一层不需要激活函数
+            out
+        )  # 除去feature_number与out_prediction不能随便取，隐藏层数与其他神经元数目均可以适当调整以得到最佳预测效果
+        #print(out.shape)
+        return out
+
+net = Net(n_feature=feature_number,
+          n_output=out_prediction,
+          n_layer=1,
+          n_neuron1=20,
+          n_neuron2=20)  # 这里直接确定了隐藏层数目以及神经元数目，实际操作中需要遍历
+optimizer = optim.Adam(net.parameters(), learning_rate)  # 使用Adam算法更新参数
+criteon = torch.nn.MSELoss()  # 误差计算公式，回归问题采用均方误差
+average_losses=[]
+for epoch in range(epochs):  # 整个数据集迭代次数
+    net.train()  # 启动训练模式
+    for batch_idx, (data, target) in enumerate(training_data):
+        logits = net.forward(data)  # 前向计算结果（预测结果）
+        loss = criteon(logits, target)  # 计算损失
+        optimizer.zero_grad()  # 梯度清零
+        loss.backward()  # 后向传递过程
+        optimizer.step()  # 优化权重与偏差矩阵
+        #print(logits)
+
+    logit = []  # 这个是验证集，可以根据验证集的结果进行调参，这里根据验证集的结果选取最优的神经网络层数与神经元数目
+    target = []
+    net.eval()  # 启动测试模式
+    for data, targets in vertification:  # 输出验证集的平均误差
+        logits = net.forward(data).detach().numpy()
+        targets = targets.detach().numpy()
+        target.append(targets[0])
+        logit.append(logits[0])
+    average_loss = criteon(torch.tensor(logit), torch.tensor(target))
+    average_losses.append(average_loss)
+    print("epoch={},the average loss is {}".format(epoch,average_loss))
+
+Y_test=net.forward(X_test)
+print(Y_test)
+xx=range(epochs)
+yy=average_losses
+plt.xlim(0,epochs)
+plt.ylim(0,10)
+plt.plot(xx,yy)
+plt.show()

共享单车数据集分析/共享单车数据集/readme.md

@@ -0,0 +1,38 @@
+#通过历史租车数据并结合天气数据来预测租车需求
+
+### 目录结构
+```
+|-src
+|  |-main.py
+|-test.csv
+|-train.csv
+|-readme.md
+|-main.ipynb
+```
+src/main.py为前馈型神经网络对结果的预测
+
+### 数据集字段说明： 
+
+datetime：时间 
+
+season：季节，1=春，2=夏，3=秋，4=冬
+ 
+holiday：节假日，0：否，1：是 
+
+workingday：工作日，0：否，1：是 
+
+weather：天气，1:晴天，2:阴天 ，3:小雨或小雪 ，4:恶劣天气（大雨、冰雹、暴风雨或者大雪） 
+
+temp：实际温度，摄氏度 
+
+atemp：体感温度，摄氏度 
+
+humidity：湿度，相对湿度 
+
+windspeed：风速 
+
+casual：未注册用户租借数量 
+
+registered：注册用户租借数量 
+
+count：总租借数量

共享单车数据集分析/共享单车数据集/src/main.py

@@ -0,0 +1,135 @@
+import torch
+import pandas as pd
+import numpy as np
+import os
+import time
+import torch.optim as optim
+import matplotlib.pyplot as plt
+
+train_data = pd.read_csv('../train.csv')
+test_data = pd.read_csv('../test.csv')
+#print(train_data)
+datetime=train_data['datetime'].values
+season=train_data['season'].values
+holiday=train_data['holiday'].values
+workingday=train_data['workingday'].values
+weather=train_data['weather'].values
+temp=train_data['temp'].values
+atemp=train_data['atemp'].values
+humidity=train_data['humidity'].values
+windspeed=train_data['windspeed'].values
+casual=train_data['casual'].values
+registered=train_data['registered'].values
+
+count=train_data['count'].values
+
+'''
+转换datetime,去掉不必要的符号和0
+'''
+def datetime_convert(datetime):
+    for i in range(len(datetime)):
+        datetime[i]=datetime[i].replace("-", "").replace(" ", "").replace(":00:00","")
+        datetime[i]=int(datetime[i])
+    return datetime
+datetime_convert(datetime)
+train_data['datetime']=datetime
+datetime_convert(test_data['datetime'].values)
+test_data['datetime']=test_data['datetime'].values
+'''
+标准化数据
+'''
+def normalize(ndarry):
+    ndarry=(ndarry-ndarry.mean())/ndarry.std()
+    return ndarry
+
+for i in range(12):
+    train_data.iloc[:,i]=normalize(train_data.iloc[:,i])
+
+
+
+
+
+X=torch.tensor(train_data.iloc[:,:9].to_numpy().astype(float),dtype=torch.float32)
+Y=torch.tensor(train_data.iloc[:,9:12].to_numpy().astype(float),dtype=torch.float32)
+X_test=torch.tensor(test_data.iloc[:,:9].to_numpy().astype(float),dtype=torch.float32)
+torch_train_dataset = torch.utils.data.TensorDataset(X, Y)
+batch_size = 10
+torch.manual_seed(seed=2023)
+
+training, vertification = torch.utils.data.random_split(torch_train_dataset, [10000, 886], )
+training_data = torch.utils.data.DataLoader(training,batch_size=batch_size,shuffle=True)
+vertification_data = torch.utils.data.DataLoader(training,batch_size=batch_size,shuffle=True)
+
+feature_number = 9  # 设置特征数目
+out_prediction = 3  # 设置输出数目
+learning_rate = 0.01  # 设置学习率
+epochs = 10 # 设置训练代数
+
+
+class Net(torch.nn.Module):
+    def __init__(self, n_feature, n_output, n_neuron1, n_neuron2,
+                 n_layer):  # n_feature为特征数目，这个数字不能随便取,n_output为特征对应的输出数目，也不能随便取
+        self.n_feature = n_feature
+        self.n_output = n_output
+        self.n_neuron1 = n_neuron1
+        self.n_neuron2 = n_neuron2
+        self.n_layer = n_layer
+        super(Net, self).__init__()
+        self.input_layer = torch.nn.Linear(self.n_feature, self.n_neuron1)  # 输入层
+        self.hidden1 = torch.nn.Linear(self.n_neuron1, self.n_neuron2)  # 1类隐藏层
+        self.hidden2 = torch.nn.Linear(self.n_neuron2, self.n_neuron2)  # 2类隐藏
+        self.predict = torch.nn.Linear(self.n_neuron2, self.n_output)  # 输出层
+
+    def forward(self, x):
+        '''定义前向传递过程'''
+        out = self.input_layer(x)
+        out = torch.relu(out)  # 使用relu函数非线性激活
+        out = self.hidden1(out)
+        out = torch.relu(out)
+        for i in range(self.n_layer):
+            out = self.hidden2(out)
+            out = torch.relu(out)
+        out = self.predict(  # 回归问题最后一层不需要激活函数
+            out
+        )  # 除去feature_number与out_prediction不能随便取，隐藏层数与其他神经元数目均可以适当调整以得到最佳预测效果
+        #print(out.shape)
+        return out
+
+net = Net(n_feature=feature_number,
+          n_output=out_prediction,
+          n_layer=1,
+          n_neuron1=20,
+          n_neuron2=20)  # 这里直接确定了隐藏层数目以及神经元数目，实际操作中需要遍历
+optimizer = optim.Adam(net.parameters(), learning_rate)  # 使用Adam算法更新参数
+criteon = torch.nn.MSELoss()  # 误差计算公式，回归问题采用均方误差
+average_losses=[]
+for epoch in range(epochs):  # 整个数据集迭代次数
+    net.train()  # 启动训练模式
+    for batch_idx, (data, target) in enumerate(training_data):
+        logits = net.forward(data)  # 前向计算结果（预测结果）
+        loss = criteon(logits, target)  # 计算损失
+        optimizer.zero_grad()  # 梯度清零
+        loss.backward()  # 后向传递过程
+        optimizer.step()  # 优化权重与偏差矩阵
+        #print(logits)
+
+    logit = []  # 这个是验证集，可以根据验证集的结果进行调参，这里根据验证集的结果选取最优的神经网络层数与神经元数目
+    target = []
+    net.eval()  # 启动测试模式
+    for data, targets in vertification:  # 输出验证集的平均误差
+        logits = net.forward(data).detach().numpy()
+        targets = targets.detach().numpy()
+        target.append(targets[0])
+        logit.append(logits[0])
+    average_loss = criteon(torch.tensor(logit), torch.tensor(target))
+    average_losses.append(average_loss)
+    print("epoch={},the average loss is {}".format(epoch,average_loss))
+
+Y_test=net.forward(X_test)
+print(Y_test)
+xx=range(epochs)
+yy=average_losses
+plt.xlim(0,epochs)
+plt.ylim(0,10)
+plt.plot(xx,yy)
+plt.show()

共享单车数据集分析/第十三组 组员信息

@@ -0,0 +1,8 @@
+小组成员
+刘闻一 应数001班 组长
+张怡欣 强基数学001 组员
+张妙妙 强基数学001 组员
+甘梓鸣 统计001 组员
+李泽坤 强基数学002 组员
+杨文博 应数001班 组员
+薛森垚 信计001 组员