Mixed
# numerical calculation & data frames
import numpy as np
import pandas as pd
# visualization
import matplotlib.pyplot as plt
import seaborn as sns
import seaborn.objects as so
import plotly.express as px
# statistics
import statsmodels.api as sm# pandas options
pd.options.display.precision = 2
pd.options.display.float_format = '{:.2f}'.format # pd.reset_option('display.float_format')
pd.options.display.max_rows = 8
# Numpy options
np.set_printoptions(precision = 2, suppress=True).head(), .tail(), .sample()
.info(), .describe(),
.value_counts(),
.sort_values(), .nlargest(), .nsmallest()
Data: Tips
일정기간 한 웨이터가 얻은 팁에 대한 데이터
# load a dataset
tips = sns.load_dataset("tips")
tips total_bill tip sex smoker day time size
0 16.99 1.01 Female No Sun Dinner 2
1 10.34 1.66 Male No Sun Dinner 3
2 21.01 3.50 Male No Sun Dinner 3
3 23.68 3.31 Male No Sun Dinner 2
.. ... ... ... ... ... ... ...
240 27.18 2.00 Female Yes Sat Dinner 2
241 22.67 2.00 Male Yes Sat Dinner 2
242 17.82 1.75 Male No Sat Dinner 2
243 18.78 3.00 Female No Thur Dinner 2
[244 rows x 7 columns]# DataFrame의 값들: ndarray
tips.values # or tips.to_numpy()array([[16.99, 1.01, 'Female', ..., 'Sun', 'Dinner', 2],
[10.34, 1.66, 'Male', ..., 'Sun', 'Dinner', 3],
[21.01, 3.5, 'Male', ..., 'Sun', 'Dinner', 3],
...,
[22.67, 2.0, 'Male', ..., 'Sat', 'Dinner', 2],
[17.82, 1.75, 'Male', ..., 'Sat', 'Dinner', 2],
[18.78, 3.0, 'Female', ..., 'Thur', 'Dinner', 2]], dtype=object)tips.head() # 처음 N개 나열 total_bill tip sex smoker day time size
0 16.99 1.01 Female No Sun Dinner 2
1 10.34 1.66 Male No Sun Dinner 3
2 21.01 3.50 Male No Sun Dinner 3
3 23.68 3.31 Male No Sun Dinner 2
4 24.59 3.61 Female No Sun Dinner 4tips.info()<class 'pandas.core.frame.DataFrame'>
RangeIndex: 244 entries, 0 to 243
Data columns (total 7 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 total_bill 244 non-null float64
1 tip 244 non-null float64
2 sex 244 non-null category
3 smoker 244 non-null category
4 day 244 non-null category
5 time 244 non-null category
6 size 244 non-null int64
dtypes: category(4), float64(2), int64(1)
memory usage: 7.4 KBtips.describe() # numerical type만 나열 total_bill tip size
count 244.00 244.00 244.00
mean 19.79 3.00 2.57
std 8.90 1.38 0.95
min 3.07 1.00 1.00
25% 13.35 2.00 2.00
50% 17.80 2.90 2.00
75% 24.13 3.56 3.00
max 50.81 10.00 6.00tips.describe(include="all") # all types 나열 total_bill tip sex smoker day time size
count 244.00 244.00 244 244 244 244 244.00
unique NaN NaN 2 2 4 2 NaN
top NaN NaN Male No Sat Dinner NaN
freq NaN NaN 157 151 87 176 NaN
... ... ... ... ... ... ... ...
25% 13.35 2.00 NaN NaN NaN NaN 2.00
50% 17.80 2.90 NaN NaN NaN NaN 2.00
75% 24.13 3.56 NaN NaN NaN NaN 3.00
max 50.81 10.00 NaN NaN NaN NaN 6.00
[11 rows x 7 columns]tips.describe(include="category") sex smoker day time
count 244 244 244 244
unique 2 2 4 2
top Male No Sat Dinner
freq 157 151 87 176s1 = tips["day"].value_counts() # "day" 칼럼을 선택 후 각 카테고리별 counts
s2 = tips["day"].value_counts(sort=False) # default: sort is true
s3 = tips["day"].value_counts(normalize=True) # 카테고리별 비율
s4 = tips[["sex", "smoker"]].value_counts() # "sex", "smoker" 칼럼을 선택 후 유니크한 카테고리별 countsSat 87
Sun 76
Thur 62
Fri 19
Name: day, dtype: int64Thur 62
Fri 19
Sat 87
Sun 76
Name: day, dtype: int64Sat 0.36
Sun 0.31
Thur 0.25
Fri 0.08
Name: day, dtype: float64sex smoker
Male No 97
Yes 60
Female No 54
Yes 33
dtype: int64다음 두 가지 형태도 가능하며, 차이에 유의
tips[["day"]].value_counts() # double bracket
tips.value_counts("day") # argument
tips.value_counts(["day", "time"])Data: palmerpenguins
# load a dataset
penguins = sns.load_dataset("penguins")
penguins species island bill_length_mm bill_depth_mm flipper_length_mm \
0 Adelie Torgersen 39.10 18.70 181.00
1 Adelie Torgersen 39.50 17.40 186.00
2 Adelie Torgersen 40.30 18.00 195.00
3 Adelie Torgersen NaN NaN NaN
.. ... ... ... ... ...
340 Gentoo Biscoe 46.80 14.30 215.00
341 Gentoo Biscoe 50.40 15.70 222.00
342 Gentoo Biscoe 45.20 14.80 212.00
343 Gentoo Biscoe 49.90 16.10 213.00
body_mass_g sex
0 3750.00 Male
1 3800.00 Female
2 3250.00 Female
3 NaN NaN
.. ... ...
340 4850.00 Female
341 5750.00 Male
342 5200.00 Female
343 5400.00 Male
[344 rows x 7 columns]penguins.info()<class 'pandas.core.frame.DataFrame'>
RangeIndex: 344 entries, 0 to 343
Data columns (total 7 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 species 344 non-null object
1 island 344 non-null object
2 bill_length_mm 342 non-null float64
3 bill_depth_mm 342 non-null float64
4 flipper_length_mm 342 non-null float64
5 body_mass_g 342 non-null float64
6 sex 333 non-null object
dtypes: float64(4), object(3)
memory usage: 18.9+ KBpenguins.describe(include="object") species island sex
count 344 344 333
unique 3 3 2
top Adelie Biscoe Male
freq 152 168 168penguins[["island", "species"]].value_counts()island species
Biscoe Gentoo 124
Dream Chinstrap 68
Adelie 56
Torgersen Adelie 52
Biscoe Adelie 44
dtype: int64penguins[["sex", "species"]].value_counts(dropna=False) # NA은 기본적으로 생략sex species
Female Adelie 73
Male Adelie 73
Gentoo 61
Female Gentoo 58
Chinstrap 34
Male Chinstrap 34
NaN Adelie 6
Gentoo 5
dtype: int64penguins.isna().sum() # NA의 개수species 0
island 0
bill_length_mm 2
bill_depth_mm 2
flipper_length_mm 2
body_mass_g 2
sex 11
dtype: int64tips.sort_values("tip", ascending=False) total_bill tip sex smoker day time size
170 50.81 10.00 Male Yes Sat Dinner 3
212 48.33 9.00 Male No Sat Dinner 4
23 39.42 7.58 Male No Sat Dinner 4
59 48.27 6.73 Male No Sat Dinner 4
.. ... ... ... ... ... ... ...
236 12.60 1.00 Male Yes Sat Dinner 2
111 7.25 1.00 Female No Sat Dinner 1
67 3.07 1.00 Female Yes Sat Dinner 1
92 5.75 1.00 Female Yes Fri Dinner 2
[244 rows x 7 columns]tips.sort_values(["size", "tip"], ascending=[False, True]) total_bill tip sex smoker day time size
125 29.80 4.20 Female No Thur Lunch 6
143 27.05 5.00 Female No Thur Lunch 6
156 48.17 5.00 Male No Sun Dinner 6
141 34.30 6.70 Male No Thur Lunch 6
.. ... ... ... ... ... ... ...
67 3.07 1.00 Female Yes Sat Dinner 1
111 7.25 1.00 Female No Sat Dinner 1
82 10.07 1.83 Female No Thur Lunch 1
222 8.58 1.92 Male Yes Fri Lunch 1
[244 rows x 7 columns]tips.nlargest(3, "tip") # keep="first", "last", "all" total_bill tip sex smoker day time size
170 50.81 10.00 Male Yes Sat Dinner 3
212 48.33 9.00 Male No Sat Dinner 4
23 39.42 7.58 Male No Sat Dinner 4