8.16 pytorch学习

import torch
# x = torch.arange(12)
# print(x)
#
# print(x.shape)
# print(x.numel())
#
# x=x.reshape(3,4)
# print(x)

# x = torch.arange(12,dtype=torch.float32).reshape((3,4))
# y = torch.tensor(([2.0,1,4,3],[1,2,3,4],[4,3,2,1]))
# torch.cat((x,y),dim=0),torch.cat((x,y),dim=1)

import os

# 创建一个人工数据集，并存储再csv（逗号分隔值）文件
os.makedirs(os.path.join('..','data'),exist_ok=True)
data_file = os.path.join('..','data','house_tiny.csv')
with open(data_file,'w') as f:
    f.write('NumRooms,Alley,Price\n')
    f.write('NA,Pave,127500\n')
    f.write('2,NA,106000\n')
    f.write('4,NA,178100\n')
    f.write('NA,NA,140000\n')

# 从创建的csv文件中加载原始数据集

import pandas as pd

data = pd.read_csv(data_file)
print(data)

# 从创建的csv文件中加载原始数据集

import pandas as pd

data = pd.read_csv(data_file)
print(data)

# 为了处理缺失的数据，典型的是插值和删除，这里，我们将考虑插值
inputs,outputs = data.iloc[:,0:2],data.iloc[:,2]
inputs = inputs.fillna(inputs.mean())
print(inputs)

inputs = pd.get_dummies(inputs,dummy_na=True)
print(inputs)

# 为了处理缺失的数据，典型的是插值和删除，这里，我们将考虑插值
inputs = data.iloc[:,0:2]
outputs = data.iloc[:,2]
inputs = inputs.fillna(inputs.mean())
print(inputs)

inputs = pd.get_dummies(inputs,dummy_na=True)
print(inputs)

import torch
x,y = torch.tensor(inputs.values),torch.tensor(outputs.values)
print(x,y)

import torch
a = torch.ones((2,5,4))
print(a.shape)

print(a.sum().shape)

print(a.sum(axis=1))

print(a.sum(axis=0).shape)
print(a.sum(axis=0))

print(a.sum(axis=[0,2]).shape)
print(a.sum(axis=[0,2]))

print(a.sum(axis=1,keepdims = True).shape)
print(a.sum(axis=1,keepdims = True))

print(a.sum(axis=[0,2],keepdims = True).shape)
print(a.sum(axis=[0,2],keepdims = True))

print(a.sum(axis=1,keepdims = True).shape)
print(a.sum(axis=1,keepdims = True))

print(a.sum(axis=[0,2],keepdims = True).shape)
print(a.sum(axis=[0,2],keepdims = True))

为什么会有20

print(a.sum(axis=[1,2]).shape)
print(a.sum(axis=[1,2]))

print(a.sum(axis=[1,2],keepdims = True).shape)
print(a.sum(axis=[1,2],keepdims = True))

print(a.sum(axis=[1,2]).shape)
print(a.sum(axis=[1,2]))


print(a.sum(axis=[0,1]).shape)
print(a.sum(axis=[0,1]))

print(a.sum(axis=[0,2]).shape)
print(a.sum(axis=[0,2]))

import numpy as np
arr = np.arange(24).reshape(2,3,4)
print(arr)

import numpy as np
arr = np.ones(24).reshape(2,3,4)
print(arr)

import numpy as np
arr = np.ones(24).reshape(2,3,4)
print(arr)
print("--------")
b = np.sum(arr,axis=0)
print(b)
print("--------")
b = np.sum(arr,axis=1)
print(b)
print("--------")
b = np.sum(arr,axis=2)
print(b)

import torch
a = torch.ones((2,3,4))
print(a)

print(a.sum(axis=0).shape)

print(a.sum(axis=0))

print(a.sum(axis=1).shape)
print(a.sum(axis=1))

print(a.sum(axis=2).shape)
print(a.sum(axis=2))

print(a.sum(axis=0,keepdims=True).shape)
print(a.sum(axis=0,keepdims=True))

print(a.sum(axis=1,keepdims=True).shape)
print(a.sum(axis=1,keepdims=True))

print(a.sum(axis=2,keepdims=True).shape)
print(a.sum(axis=2,keepdims=True))

print(a.sum(axis=(0,1)).shape)
print(a.sum(axis=(0,1)))

print(a.sum(axis=(0,2)).shape)
print(a.sum(axis=(0,2)))

print(a.sum(axis=(1,2)).shape)
print(a.sum(axis=(1,2)))

print(a.sum(axis=(0,1),keepdims=True).shape)
print(a.sum(axis=(0,1),keepdims=True))

print(a.sum(axis=(0,2),keepdims=True).shape)
print(a.sum(axis=(0,2),keepdims=True))

print(a.sum(axis=(1,2),keepdims=True).shape)
print(a.sum(axis=(1,2),keepdims=True))