seasonal_decompose¶

In [ ]:

seasonal_decompose(vdf: vDataFrame,
                   column: str,
                   ts: str,
                   by: list = [],
                   period: int = -1,
                   polynomial_order: int = 1,
                   estimate_seasonality: bool = True,
                   rule: (str, datetime.timedelta) = None,
                   mult: bool = False,
                   two_sided: bool = False,)

Performs a seasonal time series decomposition.

Parameters¶

Name	Type	Optional	Description
vdf	vDataFrame	❌	input vDataFrame.
column	str	❌	Input vcolumn to decompose.
ts	str	❌	vcolumn used as timeline. It will be to use to order the data. It can be a numerical or type date like (date, datetime, timestamp...) vcolumn.
by	list	✓	vcolumns used in the partition.
period	int	✓	Time Series period. It is used to retrieve the seasonality component. if period is lesser or equal to 0, the seasonal component will be estimated using ACF. In this case, polynomial_order must be greater than 0.
polynomial_order	int	✓	If greater than 0, the trend will be estimated using a polynomial of degree 'polynomial_order'. The parameter 'two_sided' will be ignored. If equal to 0, the trend will be estimated using Moving Averages.
estimate_seasonality	bool	✓	If set to True, the seasonality will be estimated using cosine and sine functions.
rule	str / time	✓	Interval to use to slice the time. For example, '5 minutes' will create records separated by '5 minutes' time interval.
mult	bool	✓	If set to True, the decomposition type will be 'multiplicative'. Otherwise, it is 'additive'.
two_sided	bool	✓	If set to True, a centered moving average is used for the trend isolation. Otherwise only past values are used.

Returns¶

tablesample : An object containing the result. For more information, see utilities.tablesample.

Example¶

In [2]:

%matplotlib inline
from verticapy.datasets import load_airline_passengers
passengers = load_airline_passengers()
passengers.plot(ts = "date", columns = ["passengers"])

Out[2]:

<AxesSubplot:xlabel='"date"', ylabel='"passengers"'>

In [5]:

from verticapy.stats import seasonal_decompose

decomposition = seasonal_decompose(passengers, 
                                   "passengers", 
                                   "date",
                                   polynomial_order = 2,
                                   mult = True)
display(decomposition)

	📅 date Date	123 passengers Int	123 passengers_trend Float	123 passengers_seasonal Float	123 passengers_epsilon Float
1	1949-01-01	112	114.028040859707	0.850135342325453	1.15536255667615
2	1949-02-01	118	115.690060606611	0.882131323741451	1.15625258033391
3	1949-03-01	132	117.366096750151	0.945710121773853	1.1892501982632
4	1949-04-01	129	119.056149290327	1.02383584883414	1.05829695500561
5	1949-05-01	121	120.760218227138	1.0955747794484	0.914575272399499
6	1949-06-01	135	122.478303560585	1.14170452509268	0.96543020834606
7	1949-07-01	148	124.210405290668	1.14986465767455	1.0362320267397
8	1949-08-01	148	125.956523417387	1.11786867625855	1.05111507184691
9	1949-09-01	136	127.716657940742	1.05428987822615	1.01002314478973
10	1949-10-01	119	129.490808860732	0.976164151165865	0.941423777800471
11	1949-11-01	104	131.278976177358	0.9044252205516	0.875922119767362
12	1949-12-01	118	133.08115989062	0.858295474907316	1.03306728138343
13	1950-01-01	115	134.897360000518	0.850135342325453	1.00278151254438
14	1950-02-01	126	136.727576507052	0.882131323741451	1.04467496042437
15	1950-03-01	141	138.571809410221	0.945710121773853	1.07593537733039
16	1950-04-01	135	140.430058710027	1.02383584883414	0.938951930312987
17	1950-05-01	125	142.302324406468	1.0955747794484	0.80178142914427
18	1950-06-01	149	144.188606499545	1.14170452509268	0.905110496502086
19	1950-07-01	170	146.088904989257	1.14986465767455	1.01201036804486
20	1950-08-01	170	148.003219875606	1.11786867625855	1.02751216102852
21	1950-09-01	158	149.93155115859	1.05428987822615	0.999548831409235
22	1950-10-01	133	151.87389883821	0.976164151165865	0.897109889738009
23	1950-11-01	114	153.830262914466	0.9044252205516	0.819389519154582
24	1950-12-01	140	155.800643387357	0.858295474907316	1.04694041708226
25	1951-01-01	145	157.785040256885	0.850135342325453	1.08097115679071
26	1951-02-01	150	159.783453523048	0.882131323741451	1.06420724593379
27	1951-03-01	178	161.795883185847	0.945710121773853	1.16330741963279
28	1951-04-01	163	163.822329245282	1.02383584883414	0.971816292961965
29	1951-05-01	172	165.862791701353	1.0955747794484	0.946536683551796
30	1951-06-01	178	167.917270554059	1.14170452509268	0.928476494746238
31	1951-07-01	199	169.985765803402	1.14986465767455	1.0181078700925
32	1951-08-01	199	172.06827744938	1.11786867625855	1.03457380574925
33	1951-09-01	184	174.164805491994	1.05428987822615	1.00206844586813
34	1951-10-01	162	176.275349931243	0.976164151165865	0.941457185706776
35	1951-11-01	146	178.399910767129	0.9044252205516	0.904868684520885
36	1951-12-01	166	180.53848799965	0.858295474907316	1.07127621905567
37	1952-01-01	171	182.691081628807	0.850135342325453	1.10100855124648
38	1952-02-01	180	184.8576916546	0.882131323741451	1.10382883718317
39	1952-03-01	193	187.038318077029	0.945710121773853	1.09111036979155
40	1952-04-01	181	189.232960896093	1.02383584883414	0.934224942460824
41	1952-05-01	183	191.441620111793	1.0955747794484	0.872514599777302
42	1952-06-01	218	193.66429572413	1.14170452509268	0.98594618389933
43	1952-07-01	230	195.900987733102	1.14986465767455	1.02104406353842
44	1952-08-01	242	198.151696138709	1.11786867625855	1.09251343123325
45	1952-09-01	209	200.416420940953	1.05428987822615	0.989129026987771
46	1952-10-01	191	202.695162139832	0.976164151165865	0.965310720813758
47	1952-11-01	172	204.987919735347	0.9044252205516	0.927742632802777
48	1952-12-01	194	207.294693727498	0.858295474907316	1.09037709971173
49	1953-01-01	196	209.615484116285	0.850135342325453	1.09987831484757
50	1953-02-01	196	211.950290901707	0.882131323741451	1.04830778405767
51	1953-03-01	236	214.299114083766	0.945710121773853	1.16448417255751
52	1953-04-01	235	216.66195366246	1.02383584883414	1.05938757592082
53	1953-05-01	229	219.03880963779	1.0955747794484	0.954272449518939
54	1953-06-01	243	221.429682009755	1.14170452509268	0.961206535149543
55	1953-07-01	264	223.834570778357	1.14986465767455	1.02572286787026
56	1953-08-01	272	226.253475943594	1.11786867625855	1.07543175747877
57	1953-09-01	237	228.686397505467	1.05428987822615	0.982987456097118
58	1953-10-01	211	231.133335463976	0.976164151165865	0.935183884342593
59	1953-11-01	180	233.594289819121	0.9044252205516	0.851996122660106
60	1953-12-01	201	236.069260570902	0.858295474907316	0.992018553768322
61	1954-01-01	204	238.558247719318	0.850135342325453	1.00588344387249
62	1954-02-01	188	241.06125126437	0.882131323741451	0.884091467154869
63	1954-03-01	235	243.578271206058	0.945710121773853	1.02016702411449
64	1954-04-01	227	246.109307544382	1.02383584883414	0.90088112279118
65	1954-05-01	234	248.654360279341	1.0955747794484	0.858969517422285
66	1954-06-01	264	251.213429410937	1.14170452509268	0.920465154301832
67	1954-07-01	302	253.786514939168	1.14986465767455	1.03488400674893
68	1954-08-01	293	256.373616864035	1.11786867625855	1.02235918479967
69	1954-09-01	259	258.974735185538	1.05428987822615	0.948598272370131
70	1954-10-01	229	261.589869903676	0.976164151165865	0.896791959861755
71	1954-11-01	203	264.219021018451	0.904425220551599	0.849492002088961
72	1954-12-01	229	266.862188529861	0.858295474907316	0.999796509368645
73	1955-01-01	242	269.519372437907	0.850135342325453	1.05617846442999
74	1955-02-01	233	272.190572742588	0.882131323741451	0.970397340910711
75	1955-03-01	267	274.875789443906	0.945710121773853	1.02710947237432
76	1955-04-01	269	277.575022541859	1.02383584883414	0.946545650691677
77	1955-05-01	270	280.288272036449	1.0955747794484	0.879258978768822
78	1955-06-01	315	283.015537927674	1.14170452509268	0.97486965430864
79	1955-07-01	364	285.756820215534	1.14986465767455	1.10779156345745
80	1955-08-01	347	288.512118900031	1.11786867625855	1.0759067383181
81	1955-09-01	312	291.281433981163	1.05428987822615	1.01597203262628
82	1955-10-01	274	294.064765458932	0.976164151165865	0.954519307335023
83	1955-11-01	237	296.862113333336	0.904425220551599	0.882715813208691
84	1955-12-01	278	299.673477604375	0.858295474907316	1.0808356610778
85	1956-01-01	284	302.498858272051	0.850135342325453	1.10434947467745
86	1956-02-01	277	305.338255336362	0.882131323741451	1.0284076664753
87	1956-03-01	317	308.19166879731	0.945710121773853	1.08762787713421
88	1956-04-01	313	311.059098654893	1.02383584883414	0.982813461528788
89	1956-05-01	318	313.940544909111	1.0955747794484	0.924565505078088
90	1956-06-01	374	316.836007559966	1.14170452509268	1.03391145664116
91	1956-07-01	413	319.745486607456	1.14986465767455	1.12330813254738
92	1956-08-01	405	322.668982051583	1.11786867625855	1.12281192700754
93	1956-09-01	355	325.606493892345	1.05428987822615	1.03413028805787
94	1956-10-01	306	328.558022129742	0.976164151165865	0.954083744566332
95	1956-11-01	271	331.523566763776	0.904425220551599	0.903820567972856
96	1956-12-01	306	334.503127794446	0.858295474907316	1.06582136238505
97	1957-01-01	315	337.496705221751	0.850135342325453	1.09787512462987
98	1957-02-01	301	340.504299045692	0.882131323741451	1.00209905441883
99	1957-03-01	356	343.525909266269	0.945710121773853	1.09580294411067
100	1957-04-01	348	346.561535883481	1.02383584883414	0.980773114758087

Rows: 1-100 | Columns: 5

In [6]:

decomposition["passengers_trend"].plot(ts = "date",)
decomposition["passengers_seasonal"].plot(ts = "date",)
decomposition["passengers_epsilon"].plot(ts = "date",)

Out[6]:

<AxesSubplot:xlabel='"date"', ylabel='"passengers_epsilon"'>