[PSDS] 두 개 이상의 변수 탐색하기 실습

육각형 구간. 등고선 | 분할표 | 상자그림, 바이올린 도표 | 조건화¶

1단계 : 데이터 로드하기¶

In [ ]:

from google.colab import drive
drive.mount('/content/drive')

Mounted at /content/drive

2단계: 데이터 확인하기¶

In [ ]:

KC_TAX_CSV = '/content/drive/MyDrive/통계공부/PSDS/data/kc_tax.csv.gz'

In [ ]:

import pandas as pd

kc_tax = pd.read_csv(KC_TAX_CSV)

In [ ]:

#데이터 필터링하기
kc_tax0 = kc_tax.loc[(kc_tax.TaxAssessedValue < 750000) &
                     (kc_tax.SqFtTotLiving > 100) &
                     (kc_tax.SqFtTotLiving < 3500), :]
print(kc_tax0.shape)

(432693, 3)

In [ ]:

LC_LOANS_CSV = '/content/drive/MyDrive/통계공부/PSDS/data/lc_loans.csv'
lc_loans = pd.read_csv(LC_LOANS_CSV)

In [ ]:

AIRLINE_STATS_CSV = '/content/drive/MyDrive/통계공부/PSDS/data/airline_stats.csv'
airline_stats = pd.read_csv(AIRLINE_STATS_CSV)

3단계: 계산하기¶

In [ ]:

#육각형 구간
import matplotlib.pylab as plt

ax = kc_tax0.plot.hexbin(x='SqFtTotLiving', y='TaxAssessedValue',
                         gridsize=30, sharex=False, figsize=(5, 4))
ax.set_xlabel('Finished Square Feet')
ax.set_ylabel('Tax Assessed Value')

plt.tight_layout()
plt.show()

In [ ]:

#등고선
import seaborn as sns

fig, ax = plt.subplots(figsize=(4, 4))
sns.kdeplot(data=kc_tax0.sample(10000), x='SqFtTotLiving', y='TaxAssessedValue', ax=ax)
ax.set_xlabel('Finished Square Feet')
ax.set_ylabel('Tax Assessed Value')

plt.tight_layout()
plt.show()

In [ ]:

#분할표

crosstab = lc_loans.pivot_table(index='grade', columns='status',
                                aggfunc=lambda x: len(x), margins=True)
print(crosstab)
print("\n")
df = crosstab.copy().loc['A':'G',:]
df.loc[:,'Charged Off':'Late'] = df.loc[:,'Charged Off':'Late'].div(df['All'], axis=0)
df['All'] = df['All'] / sum(df['All'])
perc_crosstab = df
print(perc_crosstab)

status  Charged Off  Current  Fully Paid  Late     All
grade                                                 
A              1562    50051       20408   469   72490
B              5302    93852       31160  2056  132370
C              6023    88928       23147  2777  120875
D              5007    53281       13681  2308   74277
E              2842    24639        5949  1374   34804
F              1526     8444        2328   606   12904
G               409     1990         643   199    3241
All           22671   321185       97316  9789  450961


status  Charged Off   Current  Fully Paid      Late       All
grade                                                        
A          0.021548  0.690454    0.281528  0.006470  0.160746
B          0.040054  0.709013    0.235401  0.015532  0.293529
C          0.049828  0.735702    0.191495  0.022974  0.268039
D          0.067410  0.717328    0.184189  0.031073  0.164708
E          0.081657  0.707936    0.170929  0.039478  0.077177
F          0.118258  0.654371    0.180409  0.046962  0.028614
G          0.126196  0.614008    0.198396  0.061401  0.007187

In [ ]:

#상자그림

airline_stats.head()
ax = airline_stats.boxplot(by='airline', column='pct_carrier_delay',
                           figsize=(5, 5))
ax.set_xlabel('')
ax.set_ylabel('Daily % of Delayed Flights')
plt.suptitle('')

plt.tight_layout()
plt.show()

In [ ]:

#바이올린 도표
fig, ax = plt.subplots(figsize=(5, 5))
sns.violinplot(data=airline_stats, x='airline', y='pct_carrier_delay',
               ax=ax, inner='quartile', color='white')
ax.set_xlabel('')
ax.set_ylabel('Daily % of Delayed Flights')

plt.tight_layout()
plt.show()

In [ ]:

#조건화
zip_codes = [98188, 98105, 98108, 98126]
kc_tax_zip = kc_tax0.loc[kc_tax0.ZipCode.isin(zip_codes),:]
kc_tax_zip

def hexbin(x, y, color, **kwargs):
    cmap = sns.light_palette(color, as_cmap=True)
    plt.hexbin(x, y, gridsize=25, cmap=cmap, **kwargs)

g = sns.FacetGrid(kc_tax_zip, col='ZipCode', col_wrap=2)
g.map(hexbin, 'SqFtTotLiving', 'TaxAssessedValue',
      extent=[0, 3500, 0, 700000])
g.set_axis_labels('Finished Square Feet', 'Tax Assessed Value')
g.set_titles('Zip code {col_name:.0f}')

plt.tight_layout()
plt.show()