It’s a code that fills the missing values in the form of bringing in the most recently recorded sunlight values.
I can’t solve the problem because of infinite loading.
import pandas as pd
import numpy as np
import math
#Visualizing
import matplotlib.pyplot as plt
plt.rcParams[‘font.family’] = ‘Malgun Gothic’; plt.rcParams[‘axes.unicode_minus’] = False;
import seaborn as sns; #sns.set_style(‘whitegrid’)
#Time Series Analysis
import statsmodels.api as sm
from statsmodels.tsa.stattools import adfuller, kpss, ccf
from statsmodels.graphics.tsaplots import plot_acf, plot_pacf
#Clustering (+α)
from sklearn.metrics import mean_squared_error, mean_absolute_error
from sklearn.preprocessing import StandardScaler, MinMaxScaler
from tslearn.clustering import TimeSeriesKMeans, silhouette_score
from minisom import MiniSom
#Modeling
from keras.models import Sequential
from keras.layers import LSTM
from keras.layers import Dense, Dropout
from sklearn.model_selection import train_test_split
from xgboost import XGBRegressor
from sklearn.model_selection import KFold
from sklearn.metrics import mean_absolute_error
#System
from ipywidgets import interact
from tqdm.notebook import tqdm
import warnings
warnings.filterwarnings(‘ignore’)
train = pd.read_csv(‘train.csv’, encoding=‘euc-kr’, parse_dates=[‘date_time’])
test = pd.read_csv(‘test.csv’, encoding=‘euc-kr’, parse_dates=[‘date_time’])
submission = pd.read_csv(‘sample_submission.csv’, encoding=‘euc-kr’)
train[‘일조(hr)’].value_counts()