将数据保存为CSV形式存储

将数据保存为CSV形式存储

可以使用pandas.Dataframe.to_csv()函数来储存数据为csv文件。

以下展示为自定义函数实现数据存储为csv文件： 函数标注已经写在代码中： 代码示例：

import numpy as np
import sklearn   
import pandas as pd 
import os 
import sys 
import tensorflow as tf 
from tensorflow import keras

from sklearn.datasets import fetch_california_housing #从sklearn中引用加州的房价数据

housing = fetch_california_housing()
print(housing.DESCR)
print(housing.data.shape)
print(housing.target.shape)

#引用train_test_split对数据集进行拆分
# test_size 控制切分比例，默认切分比例3:1
from sklearn.model_selection import train_test_split  

#拆分数据集，加载数据集后返回训练集以及测试集
x_train_all, x_test, y_train_all, y_test = train_test_split(housing.data, housing.target, random_state = 1) 

#将训练集进行一次拆分为验证集和测试集
x_train, x_valid, y_train, y_valid = train_test_split(x_train_all, y_train_all, random_state=2)

print(x_train.shape, y_train.shape)
print(x_valid.shape, y_valid.shape)
print(x_test.shape, y_test.shape)

(11610, 8) (11610,) (3870, 8) (3870,) (5160, 8) (5160,)

from sklearn.preprocessing import StandardScaler

scaler = StandardScaler()
#对数据进行归一化处理

#由于transform处理处理数据时二维数组，所以要将数据转化一下
#x_train: [none, 28, 28] -> [none, 784]
#对于使用fit_transform 和transform 请参考我的TensorFlow中的博客
x_train_scaled = scaler.fit_transform(x_train)
x_valid_scaled = scaler.transform(x_valid)
x_test_scaled = scaler.transform(x_test)

from sklearn.preprocessing import StandardScaler

scaler = StandardScaler()
#对数据进行归一化处理

#由于transform处理处理数据时二维数组，所以要将数据转化一下
#x_train: [none, 28, 28] -> [none, 784]
#对于使用fit_transform 和transform 请参考我的TensorFlow中的博客
x_train_scaled = scaler.fit_transform(x_train)
x_valid_scaled = scaler.transform(x_valid)
x_test_scaled = scaler.transform(x_test)

from sklearn.preprocessing import StandardScaler

scaler = StandardScaler()
#对数据进行归一化处理

#由于transform处理处理数据时二维数组，所以要将数据转化一下
#x_train: [none, 28, 28] -> [none, 784]
#对于使用fit_transform 和transform 请参考我的TensorFlow中的博客
x_train_scaled = scaler.fit_transform(x_train)
x_valid_scaled = scaler.transform(x_valid)
x_test_scaled = scaler.transform(x_test)

# np.c_[] : 按照列连接字符串
train_data = np.c_[x_train_scaled, y_train]
valid_data = np.c_[x_valid_scaled, y_valid]
test_data = np.c_[x_test_scaled, y_test]

#将添加的新的一列Y值添加一个列名
header_cols = housing.feature_names + ["MidanHouseValue"]
header_str = ",".join(header_cols)

#生成csv文件
train_filenames = save_to_csv(output_dir, train_data, "train", header_str, n_parts=20)
valid_filenames = save_to_csv(output_dir, valid_data, "valid", header_str, n_parts=10)
test_filenames = save_to_csv(output_dir, test_data, "test", header_str, n_parts=10)