[Python知识库]02.pandas

数据预处理

import os

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')

import pandas as pd

data = pd.read_csv(data_file)
data

处理缺失值

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


C:\Users\lucifer\AppData\Local\Temp/ipykernel_17604/2223495382.py:2: FutureWarning: Dropping of nuisance columns in DataFrame reductions (with 'numeric_only=None') is deprecated; in a future version this will raise TypeError.  Select only valid columns before calling the reduction.
  inputs=inputs.fillna(inputs.mean())

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

转换为张量

import torch

X, y = torch.tensor(inputs.values), torch.tensor(outputs.values)
X, y

(tensor([[3., 1., 0.],
         [2., 0., 1.],
         [4., 0., 1.],
         [3., 0., 1.]], dtype=torch.float64),
 tensor([127500, 106000, 178100, 140000]))