From 4c8b74ad749ccdb745c1af1a3665638d04c50610 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E5=82=85=E5=AE=87=E9=B9=8F?=
 <13911091+fusir7@user.noreply.gitee.com>
Date: Mon, 1 Jan 2024 14:53:55 +0000
Subject: [PATCH] =?UTF-8?q?=E6=95=B0=E6=8D=AE=E9=A2=84=E5=A4=84=E7=90=86?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: 傅宇鹏 <13911091+fusir7@user.noreply.gitee.com>
---
 lstm/Data_preprocessing.py | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)
 create mode 100644 lstm/Data_preprocessing.py

diff --git a/lstm/Data_preprocessing.py b/lstm/Data_preprocessing.py
new file mode 100644
index 0000000..8a064fb
--- /dev/null
+++ b/lstm/Data_preprocessing.py
@@ -0,0 +1,16 @@
+import pandas as pd
+from sklearn.preprocessing import MinMaxScaler
+
+df = pd.read_csv('../dataset/GOOG-year.csv') #读取文件
+df.head()
+
+minmax = MinMaxScaler().fit(df.iloc[:, 4:5].astype('float32')) # Close index  #对原始数据中的第5列（Close index）进行归一化处理，并将结果保存在df_log中
+df_log = minmax.transform(df.iloc[:, 4:5].astype('float32')) # Close index
+df_log = pd.DataFrame(df_log)
+df_log.head()
+
+test_size = 30               # 数据集与测试集的划分
+simulation_size = 10       #训练10次
+
+df_train = df_log.iloc[:-test_size]
+df_test = df_log.iloc[-test_size:]
\ No newline at end of file
-- 
Gitee