[FIXED] SVM code can't recognize the date time column

Issue

I followed this article to build an SVM model on my data. https://stackabuse.com/implementing-svm-and-kernel-svm-with-pythons-scikit-learn/

here a sample of my data: here

the problem is when I run the code this error appeared:

ValueError: could not convert string to float: '10/29/2020 8:30'

Solution

You can convert your date to timestamp and handle it accordingly.

import datetime

s = '10/29/2020 8:30'
date = datetime.datetime.strptime(s, "%m/%d/%Y %H:%M")
date = date.timestamp()

date will now be 1603953000.0.

Edit: if you want to covert pandas dataframe columns, here's a toy example.

import pandas as pd

s = '10/29/2020 8:30'
df = pd.DataFrame({'Date':[s, s, s]})
df['Date'] = pd.to_datetime(df['Date'])
df['Date'] = df['Date'].astype('int64')

output:

                  Date
0  1603960200000000000
1  1603960200000000000
2  1603960200000000000

Answered By - Alex Metsai