神经网络笔记

from sklearn.model_selection import train_test_split

from sklearn.linear_model import LinearRegression

from sklearn.ensemble import RandomForestRegressor

import pandas as pd

import zipfile  

import re

import numpy as np

import torch

# 定义解压.zip包函数

def unzip_file(zip_filepath, dest_path):

    with zipfile.ZipFile(zip_filepath, 'r') as zip_ref:  

        zip_ref.extractall(dest_path)

# 对.zip进行解包

unzip_file('used_car_train_20200313.zip','./')

unzip_file('used_car_testB_20200421.zip','./')

test_data = pd.read_csv('used_car_testB_20200421.csv', sep=' ')

train_data = pd.read_csv('used_car_train_20200313.csv', sep=' ')

test_data.to_csv('used_car_testB.csv')

train_data.to_csv('used_car_train.csv')

data = pd.concat([train_data, test_data])

data = data.replace('-', '-1')

data.notRepairedDamage = data.notRepairedDamage.astype('float32')

data.loc[data['power']>600,'power'] = 600

cate_cols=['model', 'brand', 'bodyType', 'fuelType', 'gearbox', 'seller', 'notRepairedDamage']

num_cols=['regDate', 'creatDate', 'power', 'kilometer', 'v_0', 'v_1', 'v_2', 'v_3', 'v_4', 'v_5', 'v_6', 'v_7', 'v_8', 'v_9', 'v_10','v_11', 'v_12', 'v_13', 'v_14']

# 定义One-Hot编码函数

def oneHotEncode(df, colNames):

    for col in colNames:

        dummies = pd.get_dummies(df[col], prefix=col)

        df = pd.concat([df, dummies],axis=1)

        df.drop([col], axis=1, inplace=True)

    return df

# 处理离散数据

for col in cate_cols:

    data[col] = data[col].fillna('-1')

data = oneHotEncode(data, cate_cols)

# 处理连续数据

for col in num_cols:

    data[col] = data[col].fillna(0)

    data[col] = (data[col]-data[col].min()) / (data[col].max()-data[col].min())

# 处理(可能)无关数据

data.drop(['name', 'regionCode'], axis=1, inplace=True)

data.columns

# 拿出测试集

data=data.reset_index(drop=True)

data = data.astype(float)

test_data = data[pd.isna(data.price)]

X_id=test_data['SaleID']

del test_data['SaleID']

del test_data['price']

X_result=torch.tensor(test_data.values, dtype=torch.float32)

test_data.to_csv('one_hot_testB.csv')

# 拿出训练集

train_data = data.drop(data[pd.isna(data.price)].index)

train_data.to_csv('one_hot_train.csv')

y=train_data['price']

del train_data['price']

del train_data['SaleID']

X=torch.tensor(train_data.values, dtype=torch.float32)

y=torch.Tensor(y)