Describe

데이터를 요약해주는 함수.

정의

describe(percentiles=None, include=None, exclude=None, datetime_is_numeric=False)

• percentiles : 구하는 퍼센트를 설정한다. 기본값은 [.25, .5, .75]
  0~1 사이 값을 입력할 수 있다.

예제

	               A	       B	       C	       D
2020-01-01	0.512982	0.311998	0.477444	0.778334
2020-01-02	0.434501	0.972884	0.440614	0.669061
2020-01-03	0.114673	0.045798	0.316773	0.299701
2020-01-04	0.199141	0.136117	0.999228	0.384082
2020-01-05	0.308763	0.605563	0.058273	0.966189

위 데이터를 df_A라고 할때

df_A.describe()

▶ 결과

	       A	       B	       C	       D
count	5.000000	5.000000	5.000000	5.000000
mean	0.601574	0.615313	0.342169	0.504192
std	0.322117	0.260882	0.375071	0.404038
min	0.169650	0.347747	0.008279	0.069692
25%	0.370939	0.410226	0.183893	0.170404
50%	0.698545	0.599367	0.234197	0.446965
75%	0.829877	0.720031	0.299867	0.850727
max	0.938858	0.999196	0.984611	0.983172

df_A.describe(percentiles=[.2,.7,.9])

▶ 결과

	       A	       B	       C	       D
count	5.000000	5.000000	5.000000	5.000000
mean	0.721119	0.443119	0.620851	0.530456
std	0.187987	0.242385	0.344823	0.305627
min	0.516323	0.228463	0.234772	0.031075
20%	0.524430	0.283625	0.257040	0.411653
50%	0.782229	0.394757	0.776356	0.581903
70%	0.855455	0.435114	0.872741	0.673251
90%	0.893600	0.687934	0.918945	0.780283
max	0.906827	0.849754	0.933685	0.836414

참고 자료

• https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.describe.html