실습데이터 파일

walmart_cleaned.csv

필요한 라이브러리 불러오기

from statsmodels.tsa.seasonal import seasonal_decompose
import statsmodels.api as sm
from statsmodels.tsa.stattools import adfuller
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split
from statsmodels.tsa.arima.model import ARIMA
import pmdarima as pm
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
import seaborn as sns
import numpy as np # linear algebra
from prophet import Prophet
from prophet.plot import plot_plotly, plot_components_plotly
from prophet.diagnostics import cross_validation
from prophet.diagnostics import performance_metrics
import warnings
warnings.filterwarnings('ignore')  # Hide warnings
warnings.simplefilter(action = "ignore", category = RuntimeWarning)
import datetime as dt
import pandas as pd
pd.core.common.is_list_like = pd.api.types.is_list_like
#import pandas_datareader.data as web
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import matplotlib.dates as mdates
import pandas as pd
#from plotnine import *
import io
# we'll use the statistics package to conduct some predictive analytics
import statistics as st
%matplotlib inline
import matplotlib.dates as mdates
from pandas import DataFrame
from pandas import to_datetime
from statsmodels.tsa.stattools import kpss
from statsmodels.tsa.stattools import adfuller
from  sklearn.metrics import mean_absolute_error

데이터 전처리

df = pd.read_csv("walmart_cleaned.csv")

# 주별 집계 데이터 테이블을 만들기!

df['Date2']= pd.to_datetime(df['Date'])
#날짜 정렬하기
df = df.sort_values(by='Date2')

#연도 컬럼 빼기 
df['year'] = df['Date2'].dt.year # 시계열 데이터인 경우는 dt.year, month 요일 별 값을 추출 가능하다!

# 집계 컬럼만들기
def func(df):
    df_sum={}
    df_sum['Weekly_Sales'] = df['Weekly_Sales'].sum()
    df_sum['Temperature'] = df['Temperature'].mean()
    df_sum['Fuel_Price'] = df['Fuel_Price'].mean()
    df_sum['IsHoliday'] = df['IsHoliday'].max()
    df_sum['CPI'] = df['CPI'].mean()
    df_sum['Unemployment'] = df['Unemployment'].mean()
    return pd.Series(df_sum, index=['Weekly_Sales','Temperature','Fuel_Price','IsHoliday','CPI','Unemployment'])

df_agg = df.groupby(['year','Date2']).apply(func).reset_index()
df_agg

추세와 변동성 시각화

plt.figure(figsize=(27,10))
plt.plot(df_agg.Date2, df_agg.Weekly_Sales)
plt.title('Weekly Sales')

시계열 데이터 분해

#decomp 간단하게 분해하기!
timeseries_decomp = df_agg.loc[:, ['Date2','Weekly_Sales']]
timeseries_decomp.index = timeseries_decomp.Date2
ts_decomp = timeseries_decomp.drop('Date2',axis=1)

decomp = seasonal_decompose(ts_decomp['Weekly_Sales'], model= 'additive', period = 4)

fig = plt.figure()
fig = decomp.plot()
fig.set_size_inches(20,15)
plt.show()

ACF, PACF 시각화