Time Series

import pandas as pd
import matplotlib.pyplot as plt

import data_describe as dd
from data_describe.core.time import plot_autocorrelation, stationarity_test

df = pd.read_csv("https://raw.githubusercontent.com/jbrownlee/Datasets/master/daily-total-female-births.csv")
df['Date'] = pd.to_datetime(df.Date, unit='ns')
df['Births_Multiplier'] = df['Births'] * 1.16
df.set_index("Date", inplace=True)
df.head(2)

	Births	Births_Multiplier
Date
1959-01-01	35	40.60
1959-01-02	32	37.12

Plot time series

dd.plot_time_series(df, col="Births")

<matplotlib.axes._subplots.AxesSubplot at 0x1f760802b08>

Plot interactive time series

dd.plot_time_series(df, col=["Births","Births_Multiplier"], viz_backend="plotly" )

Plot decomposition

dd.plot_time_series(df, col="Births", decompose=True)

dd.plot_time_series(df, col="Births", decompose=True, viz_backend="plotly")

Perform Stationarity Tests

stationarity_test(df, col='Births', test="dickey-fuller")

	stats
Test Statistic	-4.808291
p-value	0.000052
Lags Used	6.000000
Number of Observations Used	358.000000
Critical Value (1%)	-3.448749
Critical Value (5%)	-2.869647
Critical Value (10%)	-2.571089

Plot ACF

# Use seaborn by default
plot_autocorrelation(df, col='Births', plot_type="acf")

Plot PACF

plot_autocorrelation(df, col="Births", plot_type="pacf", n_lags=10, viz_backend="plotly")