动手学习深度学习pytorch最新版-数据处理

#!H:\pytorch
# -*- coding:utf-8 -*- 
#Author: Tangzhao
#content:pytorch

"""
we begin by creating an artificial dataset that is stored in a csv (comma-separated values)
file ../data/house_tiny.csv. Data
"""
import os

def mkdir_if_not_exist(path):  #@save
    if not isinstance(path,str):
        path = os.path.join(*path)
    if not os.path.exists(path):
        os.makedirs(path)

# Below we write the dataset row by row into a csv file.
data_file = '../data/house_tiny.csv'
mkdir_if_not_exist('../data')
with open(data_file, 'w') as f:
    f.write('NumRooms,Alley,Price\n')  # Column names
    f.write('NA,Pave,127500\n')  # Each row is a data instance
    f.write('2,NA,106000\n')
    f.write('4,NA,178100\n')
    f.write('NA,NA,140000\n')

# 导入pandas一行一行的读取数据，该数据有4行3列
#  each row describes the number of rooms (“NumRooms”), the alley type (“Alley”), and the price (“Price”) of a house.
import pandas as pd
data=pd.read_csv(data_file)
print(data)

"""
   NumRooms Alley   Price
0       NaN  Pave  127500
1       2.0   NaN  106000
2       4.0   NaN  178100
3       NaN   NaN  140000
"""

# 2.2.2、处理丢失的数据
"""
我们注意到NaN是丢失的数据，常见的处理方法是：假设和删除，假设方法用1代替原来的数据，删除忽略丢失的数据
我们采用的是前一种方法，先把数据集划分为输入和输出，前两列为输入，最后一列为输出，并取第一列已经存在的数据平均值作为替代丢失的数据
"""
inputs,outputs = data.iloc[:,0:2],data.iloc[:,2]
inputs = inputs.fillna(inputs.mean())
print(inputs)
"""
  NumRooms Alley
0       3.0  Pave
1       2.0   NaN
2       4.0   NaN
3       3.0   NaN
"""

"""
For categorical or discrete values in inputs, we consider “NaN” as a category. Since the “Alley” column only 
takes two types of categorical values “Pave” and “NaN”, pandas can automatically convert this column to two 
columns “Alley_Pave” and “Alley_nan”. A row whose alley type is “Pave” will set values of “Alley_Pave” and “Alley_nan” 
to 1 and 0. A row with a missing alley type will set their values to 0 and 1.
"""
inputs = pd.get_dummies(inputs, dummy_na=True)
print(inputs)
"""
   NumRooms  Alley_Pave  Alley_nan
0       3.0           1          0
1       2.0           0          1
2       4.0           0          1
3       3.0           0          1
"""

# 2.2.3、数据转换
# 现在数据都是数值的，可以进行数据转换
import torch
X,y = torch.tensor(inputs.values),torch.tensor(outputs.values)
print(X,y)
"""
tensor([[3., 1., 0.],
        [2., 0., 1.],
        [4., 0., 1.],
        [3., 0., 1.]], dtype=torch.float64) tensor([127500, 106000, 178100, 140000])

"""