3  Time Series Graphics

import pandas as pd
from pandas import *
import numpy as np
import plotnine as p9
from plotnine import *
import seaborn as sns
import matplotlib.pyplot as plt
import datetime
from datetime import *

3.1 Task 1

  1. Get data from tsibbledata package in R and write it as a csv file

Following is an R code.

#install.packages("tsibbledata")
library(tsibbledata)
library(tidyverse)
data(olympic_running)
write_csv(olympic_running, file="data/olympic_running.csv")
  1. Read data
olympic_running = pd.read_csv('data/olympic_running.csv', parse_dates=['Year'])
olympic_running
Year Length Sex Time
0 1896-01-01 100 men 12.00
1 1900-01-01 100 men 11.00
2 1904-01-01 100 men 11.00
3 1908-01-01 100 men 10.80
4 1912-01-01 100 men 10.80
... ... ... ... ...
307 2000-01-01 10000 women 1817.49
308 2004-01-01 10000 women 1824.36
309 2008-01-01 10000 women 1794.66
310 2012-01-01 10000 women 1820.75
311 2016-01-01 10000 women 1757.45

312 rows × 4 columns

Task: Visualise data in a meaningful way.

3.2 Task 2

Obtain vic_elec data from the tsibbledata package in R and visualize.

Help

import pandas as pd
vic_elec = pd.read_csv('data/vic_elec.csv', parse_dates=['Time'])
vic_elec
Time Demand Temperature Date Holiday
0 2011-12-31 13:00:00+00:00 4382.825174 21.40 2012-01-01 True
1 2011-12-31 13:30:00+00:00 4263.365526 21.05 2012-01-01 True
2 2011-12-31 14:00:00+00:00 4048.966046 20.70 2012-01-01 True
3 2011-12-31 14:30:00+00:00 3877.563330 20.55 2012-01-01 True
4 2011-12-31 15:00:00+00:00 4036.229746 20.40 2012-01-01 True
... ... ... ... ... ...
52603 2014-12-31 10:30:00+00:00 3873.448714 19.00 2014-12-31 False
52604 2014-12-31 11:00:00+00:00 3791.637322 18.50 2014-12-31 False
52605 2014-12-31 11:30:00+00:00 3724.835666 17.70 2014-12-31 False
52606 2014-12-31 12:00:00+00:00 3761.886854 17.30 2014-12-31 False
52607 2014-12-31 12:30:00+00:00 3809.414586 17.10 2014-12-31 False

52608 rows × 5 columns

vic_elec.info()
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 52608 entries, 0 to 52607
Data columns (total 5 columns):
 #   Column       Non-Null Count  Dtype              
---  ------       --------------  -----              
 0   Time         52608 non-null  datetime64[ns, UTC]
 1   Demand       52608 non-null  float64            
 2   Temperature  52608 non-null  float64            
 3   Date         52608 non-null  object             
 4   Holiday      52608 non-null  bool               
dtypes: bool(1), datetime64[ns, UTC](1), float64(2), object(1)
memory usage: 1.7+ MB