Python Time Series Datasets

timeseriesdata.py

# ------- STATSMODELS ---------
# Statsmodels has a few built in datasets as well as a utility for R-Datasets

# Yearly Nile River flows at Ashwan 1871-1970
import statsmodels.api as sm
df = sm.datasets.nile.load().data
df['ds'] = pd.date_range(start='1871', end='1970', freq='AS')

# Mauna Loa Weekly Atmospheric CO2 Data
import statsmodels.api as sm
df = sm.datasets.co2.load_pandas().data

# Air Passengers
## Monthly International Air Passengers (in thousands)
## Classic Box & Jenkins, of ARIMA fame
import statsmodels.api as sm
df = sm.datasets.get_rdataset('AirPassengers').data
df['ds'] = pd.date_range(start='1949', end='1960-12-31', freq='MS')

# Annual Lynx trappings
import statsmodels.api as sm
df = sm.datasets.get_rdataset('lynx').data
df['ds'] = pd.date_range(start='1821', end='1934', freq='AS')

# ------- ORBIT ---------
# !pip install orbit-ml
## Air Passengers
from orbit.utils.dataset import load_air_passengers
df = load_air_passengers()

## Unemployment Claims (mimic the data from the original BSTS paper)
from orbit.utils.dataset import load_iclaims
df = load_iclaims() # (443, 7)

## M3 Competition
from orbit.utils.dataset import load_m3monthly
df = load_m3monthly() # (165503, 3)

## M4 Weekly data
from orbit.utils.dataset import load_m4weekly
df = load_m4weekly() # (6106, 4)

## M5 Aggregated daily dataset 
from orbit.utils.dataset import load_m5daily
df = load_m5daily() # (1913, 42)

# --------- UTILSFORECAST (NIXTLA) ---------------
## Nixtla has the `utilsforecast` library to help simulate time series

## Generating Data with utilsforecast
## https://nixtla.github.io/utilsforecast/data.html
## !pip install utilsforecast
from utilsforecast.data import generate_series
# Generate a long dataframe with daily data for 3 unique series
df = generate_series(n_series=3, with_trend=True, static_as_categorical=False)

## M4 Hourly data with 414 unique series, each with ~900 obs
df = pd.read_parquet('https://datasets-nixtla.s3.amazonaws.com/m4-hourly.parquet') 
df.shape # (373372, 3)

A list of built-in time series datasets commonly used for teaching forecasting and testing various time series forecasting methods in Python.

list of R datasets: https://vincentarelbundock.github.io/Rdatasets/datasets.html