Transformer-time-series-forecasting/load_data.py at main · zareenrahman/Transformer-time-series-forecasting · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23

# Step 1: Downloading zip file
import os
import pandas as pd

def download_and_load_data():
    # Download only if not already present
    if not os.path.exists('LD2011_2014.txt'):
        import urllib.request, zipfile
        print("Downloading...")
        url = 'https://archive.ics.uci.edu/static/public/321/electricityloaddiagrams20112014.zip'
        urllib.request.urlretrieve(url, 'LD2011_2014.txt.zip')
        print("Unzipping...")
        with zipfile.ZipFile('LD2011_2014.txt.zip', 'r') as zip_ref:
            zip_ref.extractall()

    # Step 2: Load dataset
    df = pd.read_csv('LD2011_2014.txt', sep=';', index_col=0, parse_dates=True, decimal=',')

    # Optional: convert to hourly
    df = df.resample('1h').mean()

    return df