Fungsi rolling window dengan pandas

Memanipulasi Data Deret Waktu di Python

Stefan Jansen

Founder & Lead Data Scientist at Applied Artificial Intelligence

Fungsi window di pandas

Window mengidentifikasi sub-periode deret waktu
Hitung metrik untuk sub-periode dalam window
Buat deret waktu baru berisi metrik
Dua jenis window:
- Rolling: ukuran tetap, bergeser (video ini)
- Expanding: memuat semua nilai sebelumnya (video berikutnya)

Menghitung rata-rata rolling

data = pd.read_csv('google.csv', parse_dates=['date'], index_col='date')

DatetimeIndex: 1761 entries, 2010-01-04 to 2016-12-30
Data columns (total 1 columns):
price     1761 non-null float64
dtypes: float64(1)

ch3_1_v2 - Rolling Window Functions with Pandas.010.png

Menghitung rata-rata rolling

# Ukuran window berbasis integer
data.rolling(window=30).mean() # jumlah observasi tetap

DatetimeIndex: 1761 entries, 2010-01-04 to 2017-05-24
Data columns (total 1 columns):
price    1732 non-null float64
dtypes: float64(1)

window=30: jumlah hari kerja
min_periods: pilih nilai < 30 untuk hasil di hari awal

Menghitung rata-rata rolling

# Ukuran window berbasis offset
data.rolling(window='30D').mean() # panjang periode tetap

DatetimeIndex: 1761 entries, 2010-01-04 to 2017-05-24
Data columns (total 1 columns):
price    1761 non-null float64
dtypes: float64(1)

30D: jumlah hari kalender

Rata-rata rolling 90 hari

r90 = data.rolling(window='90D').mean()

google.join(r90.add_suffix('_mean_90')).plot()

ch3_1_v2 - Rolling Window Functions with Pandas.017.png

Rata-rata rolling 90 & 360 hari

data['mean90'] = r90

r360 = data['price'].rolling(window='360D'.mean()

data['mean360'] = r360; data.plot()

ch3_1_v2 - Rolling Window Functions with Pandas.020.png

Beberapa metrik rolling (1)

r = data.price.rolling('90D').agg(['mean', 'std'])

r.plot(subplots = True)

ch3_1_v2 - Rolling Window Functions with Pandas.022.png

Beberapa metrik rolling (2)

rolling = data.google.rolling('360D')

q10 = rolling.quantile(0.1).to_frame('q10')

median = rolling.median().to_frame('median')

q90 = rolling.quantile(0.9).to_frame('q90')

pd.concat([q10, median, q90], axis=1).plot()

ch3_1_v2 - Rolling Window Functions with Pandas.024.png

Ayo berlatih!

Memanipulasi Data Deret Waktu di Python