36 lines
1.3 KiB
Python
36 lines
1.3 KiB
Python
|
import pandas as pd
|
||
|
|
import numpy as np
|
||
|
|
import os
|
||
|
|
from nltk import word_tokenize
|
||
|
|
|
||
|
|
|
||
|
|
def func(i, j):
|
||
|
|
directory_path = "//data/residential"
|
||
|
|
entries = os.listdir(directory_path)[i:j]
|
||
|
|
folders = [entry for entry in entries if os.path.join(directory_path, entry)]
|
||
|
|
entries = [os.path.join(directory_path, folder) for folder in folders]
|
||
|
|
combined_data = pd.DataFrame()
|
||
|
|
|
||
|
|
for file_path in entries:
|
||
|
|
current_data = pd.read_csv(file_path, encoding='utf-8')
|
||
|
|
tokenize_col = current_data.columns
|
||
|
|
tokenized_sentences_list = [word_tokenize(text) for text in tokenize_col]
|
||
|
|
|
||
|
|
occurrences_electricity = np.array(
|
||
|
|
[(i, j) for i, sublist in enumerate(tokenized_sentences_list) for j, word in enumerate(sublist) if
|
||
|
|
word == 'Electricity'])[:, 0]
|
||
|
|
|
||
|
|
Electricity_consumption_wind_solar = current_data[tokenize_col[occurrences_electricity]].sum(axis=1)
|
||
|
|
current_data = Electricity_consumption_wind_solar.to_frame("Household_load")
|
||
|
|
|
||
|
|
combined_data = pd.concat([combined_data, current_data], axis=1)
|
||
|
|
|
||
|
|
Series_type = combined_data.sum(axis=1)
|
||
|
|
Series_type.to_csv('houseload.csv', index=False)
|
||
|
|
total_energy = np.array(Series_type).ravel()
|
||
|
|
return total_energy
|
||
|
|
|
||
|
|
|
||
|
|
if __name__ == '__main__':
|
||
|
|
func(0, 38)
|