From d3ae31873d6e9296dc8d75819a737dfdf4468bad Mon Sep 17 00:00:00 2001
From: amilashanaka <dsa.amilashanaka@gmail.com>
Date: Tue, 29 Nov 2022 03:18:09 +0000
Subject: [PATCH] prepare data set change datset apperence
---
model.py | 25 +++++++++++++++++++++++++
1 file changed, 25 insertions(+)
diff --git a/model.py b/model.py
index 738ca0d..b9079bd 100644
--- a/model.py
+++ b/model.py
@@ -16,6 +16,8 @@ from keras.layers import Dense, LSTM, Dropout
import warnings
warnings.filterwarnings("ignore")
+from datetime import datetime as dt
+
data = pd.read_csv("data/product__demnd.csv")
print(data)
@@ -31,3 +33,26 @@ data.dropna(inplace=True)
print(data.isnull().sum())
+data.sort_values('Date', ignore_index=True, inplace=True)
+print(data.head())
+
+data['OrderDemand'] = data['OrderDemand'].str.replace('(',"")
+data['OrderDemand'] = data['OrderDemand'].str.replace(')',"")
+
+data['OrderDemand'] = data['OrderDemand'].astype('int64')
+
+
+# convert the 'Date' column to datetime format
+data['Date']= pd.to_datetime(data['Date'])
+
+
+# create Year, Month, Day columns
+data['Year'] = data["Date"].dt.year
+data['Month'] = data["Date"].dt.month
+data['Day'] = data["Date"].dt.day
+# i used second way because i think it is more usable for dtypes
+
+# information about data
+print(data.info())
+
+print(data["OrderDemand"].describe())
\ No newline at end of file
--
GitLab