import os, math, subprocess
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
# some settings for displaying Pandas results
pd.set_option('display.width', 2000)
pd.set_option('display.max_rows', 500)
pd.set_option('display.max_columns', 500)
pd.set_option('display.precision', 4)
pd.set_option('display.max_colwidth', -1)
!ls -lah home-credit-default-risk/
total 2.5G drwxrwsr-x 2 hong ubuntu 4.0K Apr 16 16:38 . drwxrwsr-x 4 hong ubuntu 4.0K Apr 16 16:39 .. -rw-rw-r-- 1 hong ubuntu 26M Jun 26 2018 application_test.csv -rw-rw-r-- 1 hong ubuntu 159M Jun 26 2018 application_train.csv -rw-rw-r-- 1 hong ubuntu 359M Jun 26 2018 bureau_balance.csv -rw-rw-r-- 1 hong ubuntu 163M Jun 26 2018 bureau.csv -rw-rw-r-- 1 hong ubuntu 405M Jun 26 2018 credit_card_balance.csv -rw-rw-r-- 1 hong ubuntu 37K Jun 26 2018 HomeCredit_columns_description.csv -rw-rw-r-- 1 hong ubuntu 690M Jun 26 2018 installments_payments.csv -rw-rw-r-- 1 hong ubuntu 375M Jun 26 2018 POS_CASH_balance.csv -rw-rw-r-- 1 hong ubuntu 387M Jun 26 2018 previous_application.csv -rw-rw-r-- 1 hong ubuntu 524K Jun 26 2018 sample_submission.csv
ls_files = subprocess.check_output(["ls", "-lah", "home-credit-default-risk/"]).decode("utf-8").splitlines()[3:]
ls_files = [f.split()[-1] for f in ls_files]
ls_files = sorted([f for f in ls_files if f not in ["HomeCredit_columns_description.csv"]])
ls_files
[u'POS_CASH_balance.csv', u'application_test.csv', u'application_train.csv', u'bureau.csv', u'bureau_balance.csv', u'credit_card_balance.csv', u'installments_payments.csv', u'previous_application.csv', u'sample_submission.csv']
def exploring_stats(pdf_input):
# check rows, cols
total_records = pdf_input.shape[0]
total_columns = pdf_input.shape[1]
print("Total records:", total_records)
print("Total columns:", total_columns)
# check dtypes
name = []
sub_type = []
for n, t in pdf_input.dtypes.iteritems():
name.append(n)
sub_type.append(t)
# check distinct
ls_ndist = []
for cname in pdf_input.columns:
ndist = pdf_input[cname].nunique()
pct_dist = ndist * 100.0 / total_records
ls_ndist.append("{} ({:0.2f}%)".format(ndist, pct_dist))
# check missing
ls_nmiss = []
for cname in pdf_input.columns:
nmiss = pdf_input[cname].isnull().sum()
pct_miss = nmiss * 100.0 / total_records
ls_nmiss.append("{} ({:0.2f}%)".format(nmiss, pct_miss))
# check zeros
ls_zeros = []
for cname in pdf_input.columns:
try:
nzeros = (pdf_input[cname] == 0).sum()
pct_zeros = nzeros * 100.0 / total_records
ls_zeros.append("{} ({:0.2f}%)".format(nzeros, pct_zeros))
except:
ls_zeros.append("{} ({:0.2f}%)".format(0, 0))
continue
# check negative
ls_neg = []
for cname in pdf_input.columns:
try:
nneg = (pdf_input[cname].astype("float") < 0).sum()
pct_neg = nneg * 100.0 / total_records
ls_neg.append("{} ({:0.2f}%)".format(nneg, pct_neg))
except:
ls_neg.append("{} ({:0.2f}%)".format(0, 0))
continue
# prepare output
data = {
"name": name,
"sub_type": sub_type,
"n_distinct": ls_ndist,
"n_miss": ls_nmiss,
"n_zeros": ls_zeros,
"n_negative": ls_neg,
}
# check stats
pdf_stats = pdf_input.describe().transpose()
ls_stats = []
for stat in pdf_stats.columns:
data[stat] = []
for cname in pdf_input.columns:
try:
data[stat].append(pdf_stats.loc[cname, stat])
except:
data[stat].append(0.0)
# take samples
nsample = 10
pdf_sample = pdf_input.sample(frac=.5).head(nsample).transpose()
pdf_sample.columns = ["sample_{}".format(i) for i in range(nsample)]
# output
col_ordered = ["sub_type", "n_distinct", "n_miss", "n_negative", "n_zeros",
"25%", "50%", "75%", "count", "max", "mean", "min", "std"] + list(pdf_sample.columns)
pdf_data = pd.DataFrame(data).set_index("name")
pdf_data = pd.concat([pdf_data, pdf_sample], axis=1)
pdf_data = pdf_data[col_ordered]
return pdf_data
%%time
ls_report = {}
for f in ls_files:
print("Exploring {}".format(f))
data_path = os.path.join("home-credit-default-risk", f)
pdf_data = pd.read_csv(data_path)
ls_report[f] = exploring_stats(pdf_data)
display(ls_report[f])
Exploring POS_CASH_balance.csv ('Total records:', 10001358) ('Total columns:', 8)
sub_type | n_distinct | n_miss | n_negative | n_zeros | 25% | 50% | 75% | count | max | mean | min | std | sample_0 | sample_1 | sample_2 | sample_3 | sample_4 | sample_5 | sample_6 | sample_7 | sample_8 | sample_9 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
name | |||||||||||||||||||||||
SK_ID_PREV | int64 | 936325 (9.36%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 1434405.0 | 1896565.0 | 2368963.0 | 1.0001e+07 | 2843499.0 | 1.9032e+06 | 1000001.0 | 535846.5307 | 2749119 | 1439762 | 2404083 | 1417828 | 1975679 | 2465369 | 2059772 | 1570568 | 2313395 | 2556181 |
SK_ID_CURR | int64 | 337252 (3.37%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 189550.0 | 278654.0 | 367429.0 | 1.0001e+07 | 456255.0 | 2.7840e+05 | 100001.0 | 102763.7451 | 136725 | 412165 | 394468 | 230896 | 290188 | 301648 | 415723 | 432016 | 154158 | 280427 |
MONTHS_BALANCE | int64 | 96 (0.00%) | 0 (0.00%) | 10001358 (100.00%) | 0 (0.00%) | -54.0 | -28.0 | -13.0 | 1.0001e+07 | -1.0 | -3.5013e+01 | -96.0 | 26.0666 | -40 | -11 | -24 | -6 | -63 | -12 | -2 | -92 | -21 | -22 |
CNT_INSTALMENT | float64 | 73 (0.00%) | 26071 (0.26%) | 0 (0.00%) | 0 (0.00%) | 10.0 | 12.0 | 24.0 | 9.9753e+06 | 92.0 | 1.7090e+01 | 1.0 | 11.9951 | 12 | 12 | 10 | 8 | 10 | 36 | 12 | 10 | 60 | 18 |
CNT_INSTALMENT_FUTURE | float64 | 79 (0.00%) | 26087 (0.26%) | 0 (0.00%) | 1185960 (11.86%) | 3.0 | 7.0 | 14.0 | 9.9753e+06 | 85.0 | 1.0484e+01 | 0.0 | 11.1091 | 1 | 3 | 10 | 8 | 1 | 17 | 1 | 10 | 51 | 17 |
NAME_CONTRACT_STATUS | object | 9 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0.0 | 0.0 | 0.0 | 0.0000e+00 | 0.0 | 0.0000e+00 | 0.0 | 0.0000 | Active | Active | Active | Active | Active | Active | Active | Active | Active | Active |
SK_DPD | int64 | 3400 (0.03%) | 0 (0.00%) | 0 (0.00%) | 9706131 (97.05%) | 0.0 | 0.0 | 0.0 | 1.0001e+07 | 4231.0 | 1.1607e+01 | 0.0 | 132.7140 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
SK_DPD_DEF | int64 | 2307 (0.02%) | 0 (0.00%) | 0 (0.00%) | 9887389 (98.86%) | 0.0 | 0.0 | 0.0 | 1.0001e+07 | 3595.0 | 6.5447e-01 | 0.0 | 32.7625 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
Exploring application_test.csv ('Total records:', 48744) ('Total columns:', 121)
sub_type | n_distinct | n_miss | n_negative | n_zeros | 25% | 50% | 75% | count | max | mean | min | std | sample_0 | sample_1 | sample_2 | sample_3 | sample_4 | sample_5 | sample_6 | sample_7 | sample_8 | sample_9 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
name | |||||||||||||||||||||||
SK_ID_CURR | int64 | 48744 (100.00%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 188557.7500 | 277549.0000 | 367555.5000 | 48744.0 | 4.5625e+05 | 2.7780e+05 | 1.0000e+05 | 103169.5473 | 413769 | 267284 | 260484 | 359319 | 152020 | 211553 | 183878 | 303497 | 285833 | 261749 |
NAME_CONTRACT_TYPE | object | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0.0000 | 0.0000 | 0.0000 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | Cash loans | Cash loans | Cash loans | Cash loans | Cash loans | Cash loans | Cash loans | Cash loans | Cash loans | Cash loans |
CODE_GENDER | object | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0.0000 | 0.0000 | 0.0000 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | F | F | F | F | F | M | F | M | F | F |
FLAG_OWN_CAR | object | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0.0000 | 0.0000 | 0.0000 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | Y | N | N | N | N | N | Y | Y | N | N |
FLAG_OWN_REALTY | object | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0.0000 | 0.0000 | 0.0000 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | Y | N | Y | N | N | N | N | Y | N | Y |
CNT_CHILDREN | int64 | 11 (0.02%) | 0 (0.00%) | 0 (0.00%) | 34685 (71.16%) | 0.0000 | 0.0000 | 1.0000 | 48744.0 | 2.0000e+01 | 3.9705e-01 | 0.0000e+00 | 0.7090 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 |
AMT_INCOME_TOTAL | float64 | 606 (1.24%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 112500.0000 | 157500.0000 | 225000.0000 | 48744.0 | 4.4100e+06 | 1.7843e+05 | 2.6942e+04 | 101522.5915 | 1.125e+05 | 9e+04 | 3.375e+05 | 1.8e+05 | 9e+04 | 1.35e+05 | 1.125e+05 | 2.475e+05 | 6.75e+04 | 8.1e+04 |
AMT_CREDIT | float64 | 2937 (6.03%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 260640.0000 | 450000.0000 | 675000.0000 | 48744.0 | 2.2455e+06 | 5.1674e+05 | 4.5000e+04 | 365397.0042 | 3.769e+05 | 2.725e+05 | 1.305e+06 | 3.6e+05 | 2.37e+05 | 2.7e+05 | 6.75e+05 | 3.820e+05 | 6.75e+05 | 3.644e+05 |
AMT_ANNUITY | float64 | 7491 (15.37%) | 24 (0.05%) | 0 (0.00%) | 0 (0.00%) | 17973.0000 | 26199.0000 | 37390.5000 | 48720.0 | 1.8058e+05 | 2.9426e+04 | 2.2950e+03 | 16016.3683 | 1.937e+04 | 2.166e+04 | 4.21e+04 | 2.202e+04 | 1.528e+04 | 2.476e+04 | 3.46e+04 | 2.35e+04 | 2.545e+04 | 1.545e+04 |
AMT_GOODS_PRICE | float64 | 677 (1.39%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 225000.0000 | 396000.0000 | 630000.0000 | 48744.0 | 2.2455e+06 | 4.6262e+05 | 4.5000e+04 | 336710.2150 | 2.7e+05 | 2.25e+05 | 1.305e+06 | 3.6e+05 | 1.8e+05 | 2.7e+05 | 6.75e+05 | 3.375e+05 | 6.75e+05 | 2.385e+05 |
NAME_TYPE_SUITE | object | 7 (0.01%) | 911 (1.87%) | 0 (0.00%) | 0 (0.00%) | 0.0000 | 0.0000 | 0.0000 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | Unaccompanied | Unaccompanied | Unaccompanied | Unaccompanied | Unaccompanied | Unaccompanied | Unaccompanied | Unaccompanied | Unaccompanied | Unaccompanied |
NAME_INCOME_TYPE | object | 7 (0.01%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0.0000 | 0.0000 | 0.0000 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | Commercial associate | Working | State servant | Working | Working | Working | Working | Commercial associate | Pensioner | Commercial associate |
NAME_EDUCATION_TYPE | object | 5 (0.01%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0.0000 | 0.0000 | 0.0000 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | Secondary / secondary special | Higher education | Higher education | Higher education | Secondary / secondary special | Secondary / secondary special | Secondary / secondary special | Secondary / secondary special | Secondary / secondary special | Secondary / secondary special |
NAME_FAMILY_STATUS | object | 5 (0.01%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0.0000 | 0.0000 | 0.0000 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | Married | Single / not married | Married | Single / not married | Civil marriage | Single / not married | Married | Married | Married | Single / not married |
NAME_HOUSING_TYPE | object | 6 (0.01%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0.0000 | 0.0000 | 0.0000 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | House / apartment | House / apartment | House / apartment | House / apartment | House / apartment | House / apartment | House / apartment | Office apartment | House / apartment | House / apartment |
REGION_POPULATION_RELATIVE | float64 | 81 (0.17%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0.0100 | 0.0188 | 0.0287 | 48744.0 | 7.2508e-02 | 2.1226e-02 | 2.5300e-04 | 0.0144 | 0.00702 | 0.00702 | 0.01821 | 0.03133 | 0.04622 | 0.01028 | 0.02866 | 0.01661 | 0.01885 | 0.01969 |
DAYS_BIRTH | int64 | 15477 (31.75%) | 0 (0.00%) | 48744 (100.00%) | 0 (0.00%) | -19637.0000 | -15785.0000 | -12496.0000 | 48744.0 | -7.3380e+03 | -1.6068e+04 | -2.5195e+04 | 4325.9004 | -13446 | -13328 | -13049 | -22112 | -14100 | -10439 | -19194 | -17876 | -19439 | -18497 |
DAYS_EMPLOYED | int64 | 7863 (16.13%) | 0 (0.00%) | 39470 (80.97%) | 0 (0.00%) | -2910.0000 | -1293.0000 | -296.0000 | 48744.0 | 3.6524e+05 | 6.7485e+04 | -1.7463e+04 | 144348.5071 | -1526 | -1264 | -4642 | -1423 | -129 | -644 | -5185 | -1054 | 365243 | -2819 |
DAYS_REGISTRATION | float64 | 12618 (25.89%) | 0 (0.00%) | 48731 (99.97%) | 13 (0.03%) | -7459.2500 | -4490.0000 | -1901.0000 | 48744.0 | 0.0000e+00 | -4.9677e+03 | -2.3722e+04 | 3552.6120 | -3286 | -9276 | -1224 | -9655 | -8233 | -6015 | -4543 | -608 | -9630 | -2260 |
DAYS_ID_PUBLISH | int64 | 5880 (12.06%) | 0 (0.00%) | 48739 (99.99%) | 5 (0.01%) | -4448.0000 | -3234.0000 | -1706.0000 | 48744.0 | 0.0000e+00 | -3.0517e+03 | -6.3480e+03 | 1569.2767 | -3524 | -4381 | -4892 | -4513 | -4191 | -2997 | -2734 | -1421 | -2991 | -2028 |
OWN_CAR_AGE | float64 | 52 (0.11%) | 32312 (66.29%) | 0 (0.00%) | 118 (0.24%) | 4.0000 | 9.0000 | 15.0000 | 16432.0 | 7.4000e+01 | 1.1786e+01 | 0.0000e+00 | 11.4629 | 10 | NaN | NaN | NaN | NaN | NaN | 17 | 6 | NaN | NaN |
FLAG_MOBIL | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 1 (0.00%) | 1.0000 | 1.0000 | 1.0000 | 48744.0 | 1.0000e+00 | 9.9998e-01 | 0.0000e+00 | 0.0045 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 |
FLAG_EMP_PHONE | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 9275 (19.03%) | 1.0000 | 1.0000 | 1.0000 | 48744.0 | 1.0000e+00 | 8.0972e-01 | 0.0000e+00 | 0.3925 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 0 | 1 |
FLAG_WORK_PHONE | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 38766 (79.53%) | 0.0000 | 0.0000 | 0.0000 | 48744.0 | 1.0000e+00 | 2.0470e-01 | 0.0000e+00 | 0.4035 | 0 | 0 | 1 | 1 | 1 | 0 | 0 | 0 | 0 | 1 |
FLAG_CONT_MOBILE | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 78 (0.16%) | 1.0000 | 1.0000 | 1.0000 | 48744.0 | 1.0000e+00 | 9.9840e-01 | 0.0000e+00 | 0.0400 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 |
FLAG_PHONE | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 35918 (73.69%) | 0.0000 | 0.0000 | 1.0000 | 48744.0 | 1.0000e+00 | 2.6313e-01 | 0.0000e+00 | 0.4403 | 0 | 0 | 1 | 0 | 0 | 0 | 1 | 0 | 1 | 0 |
FLAG_EMAIL | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 40816 (83.74%) | 0.0000 | 0.0000 | 0.0000 | 48744.0 | 1.0000e+00 | 1.6265e-01 | 0.0000e+00 | 0.3690 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
OCCUPATION_TYPE | object | 18 (0.04%) | 15605 (32.01%) | 0 (0.00%) | 0 (0.00%) | 0.0000 | 0.0000 | 0.0000 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | Laborers | Sales staff | Core staff | Medicine staff | Laborers | Laborers | Accountants | Drivers | NaN | Cleaning staff |
CNT_FAM_MEMBERS | float64 | 12 (0.02%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 2.0000 | 2.0000 | 3.0000 | 48744.0 | 2.1000e+01 | 2.1468e+00 | 1.0000e+00 | 0.8904 | 2 | 1 | 2 | 1 | 2 | 1 | 2 | 3 | 2 | 1 |
REGION_RATING_CLIENT | int64 | 3 (0.01%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 2.0000 | 2.0000 | 2.0000 | 48744.0 | 3.0000e+00 | 2.0382e+00 | 1.0000e+00 | 0.5227 | 2 | 2 | 3 | 2 | 1 | 2 | 2 | 2 | 2 | 2 |
REGION_RATING_CLIENT_W_CITY | int64 | 4 (0.01%) | 0 (0.00%) | 1 (0.00%) | 0 (0.00%) | 2.0000 | 2.0000 | 2.0000 | 48744.0 | 3.0000e+00 | 2.0126e+00 | -1.0000e+00 | 0.5158 | 2 | 2 | 3 | 2 | 1 | 2 | 2 | 2 | 2 | 2 |
WEEKDAY_APPR_PROCESS_START | object | 7 (0.01%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0.0000 | 0.0000 | 0.0000 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | FRIDAY | THURSDAY | MONDAY | MONDAY | SUNDAY | THURSDAY | WEDNESDAY | THURSDAY | TUESDAY | THURSDAY |
HOUR_APPR_PROCESS_START | int64 | 24 (0.05%) | 0 (0.00%) | 0 (0.00%) | 8 (0.02%) | 10.0000 | 12.0000 | 14.0000 | 48744.0 | 2.3000e+01 | 1.2007e+01 | 0.0000e+00 | 3.2782 | 16 | 17 | 11 | 9 | 14 | 9 | 11 | 18 | 12 | 11 |
REG_REGION_NOT_LIVE_REGION | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 47826 (98.12%) | 0.0000 | 0.0000 | 0.0000 | 48744.0 | 1.0000e+00 | 1.8833e-02 | 0.0000e+00 | 0.1359 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
REG_REGION_NOT_WORK_REGION | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 46055 (94.48%) | 0.0000 | 0.0000 | 0.0000 | 48744.0 | 1.0000e+00 | 5.5166e-02 | 0.0000e+00 | 0.2283 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 |
LIVE_REGION_NOT_WORK_REGION | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 46695 (95.80%) | 0.0000 | 0.0000 | 0.0000 | 48744.0 | 1.0000e+00 | 4.2036e-02 | 0.0000e+00 | 0.2007 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 |
REG_CITY_NOT_LIVE_CITY | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 44968 (92.25%) | 0.0000 | 0.0000 | 0.0000 | 48744.0 | 1.0000e+00 | 7.7466e-02 | 0.0000e+00 | 0.2673 | 0 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 |
REG_CITY_NOT_WORK_CITY | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 37793 (77.53%) | 0.0000 | 0.0000 | 0.0000 | 48744.0 | 1.0000e+00 | 2.2466e-01 | 0.0000e+00 | 0.4174 | 1 | 1 | 0 | 1 | 1 | 1 | 1 | 0 | 0 | 0 |
LIVE_CITY_NOT_WORK_CITY | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 40252 (82.58%) | 0.0000 | 0.0000 | 0.0000 | 48744.0 | 1.0000e+00 | 1.7422e-01 | 0.0000e+00 | 0.3793 | 1 | 0 | 0 | 0 | 1 | 1 | 1 | 0 | 0 | 0 |
ORGANIZATION_TYPE | object | 58 (0.12%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0.0000 | 0.0000 | 0.0000 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | Construction | Self-employed | School | Business Entity Type 3 | Business Entity Type 3 | Business Entity Type 3 | Business Entity Type 3 | Self-employed | XNA | Trade: type 7 |
EXT_SOURCE_1 | float64 | 27207 (55.82%) | 20532 (42.12%) | 0 (0.00%) | 0 (0.00%) | 0.3437 | 0.5068 | 0.6660 | 28212.0 | 9.3914e-01 | 5.0118e-01 | 1.3458e-02 | 0.2051 | 0.4513 | 0.02673 | 0.5048 | NaN | NaN | 0.1791 | 0.582 | 0.2933 | NaN | NaN |
EXT_SOURCE_2 | float64 | 38885 (79.77%) | 8 (0.02%) | 0 (0.00%) | 0 (0.00%) | 0.4081 | 0.5588 | 0.6585 | 48736.0 | 8.5500e-01 | 5.1802e-01 | 8.0979e-06 | 0.1813 | 0.4726 | 0.05605 | 0.4092 | 0.5969 | 0.4997 | 0.4574 | 0.5786 | 0.395 | 0.692 | 0.07601 |
EXT_SOURCE_3 | float64 | 702 (1.44%) | 8668 (17.78%) | 0 (0.00%) | 0 (0.00%) | 0.3639 | 0.5191 | 0.6529 | 40076.0 | 8.8253e-01 | 5.0011e-01 | 5.2727e-04 | 0.1895 | 0.633 | NaN | 0.3979 | 0.4849 | NaN | 0.2432 | 0.08846 | 0.592 | 0.5424 | 0.7477 |
APARTMENTS_AVG | float64 | 1543 (3.17%) | 23887 (49.01%) | 0 (0.00%) | 121 (0.25%) | 0.0619 | 0.0928 | 0.1485 | 24857.0 | 1.0000e+00 | 1.2239e-01 | 0.0000e+00 | 0.1131 | NaN | NaN | NaN | 0.0722 | 0.1399 | NaN | NaN | NaN | 0.132 | 0.1557 |
BASEMENTAREA_AVG | float64 | 2816 (5.78%) | 27641 (56.71%) | 0 (0.00%) | 2241 (4.60%) | 0.0467 | 0.0781 | 0.1134 | 21103.0 | 1.0000e+00 | 9.0065e-02 | 0.0000e+00 | 0.0815 | NaN | NaN | NaN | 0.0785 | 0.0738 | NaN | NaN | NaN | 0.1093 | 0.0097 |
YEARS_BEGINEXPLUATATION_AVG | float64 | 175 (0.36%) | 22856 (46.89%) | 0 (0.00%) | 58 (0.12%) | 0.9767 | 0.9816 | 0.9866 | 25888.0 | 1.0000e+00 | 9.7883e-01 | 0.0000e+00 | 0.0493 | NaN | NaN | NaN | 0.9776 | 0.9786 | NaN | NaN | NaN | 0.9866 | 0.9776 |
YEARS_BUILD_AVG | float64 | 130 (0.27%) | 31818 (65.28%) | 0 (0.00%) | 18 (0.04%) | 0.6872 | 0.7552 | 0.8164 | 16926.0 | 1.0000e+00 | 7.5114e-01 | 0.0000e+00 | 0.1132 | NaN | NaN | NaN | 0.694 | 0.7076 | NaN | NaN | NaN | 0.8164 | 0.694 |
COMMONAREA_AVG | float64 | 2042 (4.19%) | 33495 (68.72%) | 0 (0.00%) | 1373 (2.82%) | 0.0081 | 0.0227 | 0.0539 | 15249.0 | 1.0000e+00 | 4.7624e-02 | 0.0000e+00 | 0.0829 | NaN | NaN | NaN | 0.0079 | 0.0893 | NaN | NaN | NaN | 0.0164 | 0.0097 |
ELEVATORS_AVG | float64 | 181 (0.37%) | 25189 (51.68%) | 0 (0.00%) | 13467 (27.63%) | 0.0000 | 0.0000 | 0.1600 | 23555.0 | 1.0000e+00 | 8.5168e-02 | 0.0000e+00 | 0.1392 | NaN | NaN | NaN | 0 | 0.1864 | NaN | NaN | NaN | 0.16 | 0 |
ENTRANCES_AVG | float64 | 200 (0.41%) | 23579 (48.37%) | 0 (0.00%) | 38 (0.08%) | 0.0745 | 0.1379 | 0.2069 | 25165.0 | 1.0000e+00 | 1.5178e-01 | 0.0000e+00 | 0.1007 | NaN | NaN | NaN | 0.1034 | 0.1493 | NaN | NaN | NaN | 0.1379 | 0.1034 |
FLOORSMAX_AVG | float64 | 252 (0.52%) | 23321 (47.84%) | 0 (0.00%) | 417 (0.86%) | 0.1667 | 0.1667 | 0.3333 | 25423.0 | 1.0000e+00 | 2.3371e-01 | 0.0000e+00 | 0.1474 | NaN | NaN | NaN | 0.1667 | 0.2083 | NaN | NaN | NaN | 0.3333 | 0.1667 |
FLOORSMIN_AVG | float64 | 198 (0.41%) | 32466 (66.61%) | 0 (0.00%) | 391 (0.80%) | 0.1042 | 0.2083 | 0.3750 | 16278.0 | 1.0000e+00 | 2.3842e-01 | 0.0000e+00 | 0.1650 | NaN | NaN | NaN | 0.2083 | 0.2358 | NaN | NaN | NaN | NaN | 0.2083 |
LANDAREA_AVG | float64 | 2540 (5.21%) | 28254 (57.96%) | 0 (0.00%) | 2656 (5.45%) | 0.0190 | 0.0483 | 0.0868 | 20490.0 | 1.0000e+00 | 6.7192e-02 | 0.0000e+00 | 0.0819 | NaN | NaN | NaN | 0.0549 | 0.0754 | NaN | NaN | NaN | 0.0717 | 0 |
LIVINGAPARTMENTS_AVG | float64 | 1211 (2.48%) | 32780 (67.25%) | 0 (0.00%) | 46 (0.09%) | 0.0504 | 0.0756 | 0.1269 | 15964.0 | 1.0000e+00 | 1.0589e-01 | 0.0000e+00 | 0.0983 | NaN | NaN | NaN | 0.0555 | 0.1137 | NaN | NaN | NaN | 0.1076 | 0.1269 |
LIVINGAREA_AVG | float64 | 3848 (7.89%) | 23552 (48.32%) | 0 (0.00%) | 46 (0.09%) | 0.0486 | 0.0770 | 0.1376 | 25192.0 | 1.0000e+00 | 1.1229e-01 | 0.0000e+00 | 0.1149 | NaN | NaN | NaN | 0.0577 | 0.1223 | NaN | NaN | NaN | 0.0836 | 0.0423 |
NONLIVINGAPARTMENTS_AVG | float64 | 241 (0.49%) | 33347 (68.41%) | 0 (0.00%) | 8815 (18.08%) | 0.0000 | 0.0000 | 0.0051 | 15397.0 | 1.0000e+00 | 9.2315e-03 | 0.0000e+00 | 0.0487 | NaN | NaN | NaN | 0.0154 | 0.0013 | NaN | NaN | NaN | 0.0039 | 0 |
NONLIVINGAREA_AVG | float64 | 2026 (4.16%) | 26084 (53.51%) | 0 (0.00%) | 9469 (19.43%) | 0.0000 | 0.0038 | 0.0290 | 22660.0 | 1.0000e+00 | 2.9387e-02 | 0.0000e+00 | 0.0720 | NaN | NaN | NaN | 0.0144 | 0.0021 | NaN | NaN | NaN | 0.0985 | 0 |
APARTMENTS_MODE | float64 | 636 (1.30%) | 23887 (49.01%) | 0 (0.00%) | 148 (0.30%) | 0.0588 | 0.0851 | 0.1502 | 24857.0 | 1.0000e+00 | 1.1908e-01 | 0.0000e+00 | 0.1135 | NaN | NaN | NaN | 0.0735 | 0.0095 | NaN | NaN | NaN | 0.1345 | 0.1586 |
BASEMENTAREA_MODE | float64 | 2835 (5.82%) | 27641 (56.71%) | 0 (0.00%) | 2558 (5.25%) | 0.0425 | 0.0770 | 0.1136 | 21103.0 | 1.0000e+00 | 8.8998e-02 | 0.0000e+00 | 0.0827 | NaN | NaN | NaN | 0.0815 | 0.0048 | NaN | NaN | NaN | 0.1134 | 0.0101 |
YEARS_BEGINEXPLUATATION_MODE | float64 | 160 (0.33%) | 22856 (46.89%) | 0 (0.00%) | 76 (0.16%) | 0.9762 | 0.9816 | 0.9866 | 25888.0 | 1.0000e+00 | 9.7829e-01 | 0.0000e+00 | 0.0538 | NaN | NaN | NaN | 0.9777 | 0.9563 | NaN | NaN | NaN | 0.9866 | 0.9777 |
YEARS_BUILD_MODE | float64 | 132 (0.27%) | 31818 (65.28%) | 0 (0.00%) | 17 (0.03%) | 0.6929 | 0.7583 | 0.8236 | 16926.0 | 1.0000e+00 | 7.5833e-01 | 0.0000e+00 | 0.1101 | NaN | NaN | NaN | 0.706 | 0.425 | NaN | NaN | NaN | 0.8236 | 0.706 |
COMMONAREA_MODE | float64 | 2001 (4.11%) | 33495 (68.72%) | 0 (0.00%) | 1604 (3.29%) | 0.0076 | 0.0203 | 0.0517 | 15249.0 | 1.0000e+00 | 4.5223e-02 | 0.0000e+00 | 0.0812 | NaN | NaN | NaN | 0.0079 | 0 | NaN | NaN | NaN | 0.0166 | 0.0098 |
ELEVATORS_MODE | float64 | 26 (0.05%) | 25189 (51.68%) | 0 (0.00%) | 14170 (29.07%) | 0.0000 | 0.0000 | 0.1208 | 23555.0 | 1.0000e+00 | 8.0570e-02 | 0.0000e+00 | 0.1375 | NaN | NaN | NaN | 0 | 0 | NaN | NaN | NaN | 0.1611 | 0 |
ENTRANCES_MODE | float64 | 30 (0.06%) | 23579 (48.37%) | 0 (0.00%) | 54 (0.11%) | 0.0690 | 0.1379 | 0.2069 | 25165.0 | 1.0000e+00 | 1.4716e-01 | 0.0000e+00 | 0.1017 | NaN | NaN | NaN | 0.1034 | 0.069 | NaN | NaN | NaN | 0.1379 | 0.1034 |
FLOORSMAX_MODE | float64 | 25 (0.05%) | 23321 (47.84%) | 0 (0.00%) | 511 (1.05%) | 0.1667 | 0.1667 | 0.3333 | 25423.0 | 1.0000e+00 | 2.2939e-01 | 0.0000e+00 | 0.1465 | NaN | NaN | NaN | 0.1667 | 0.0833 | NaN | NaN | NaN | 0.3333 | 0.1667 |
FLOORSMIN_MODE | float64 | 25 (0.05%) | 32466 (66.61%) | 0 (0.00%) | 431 (0.88%) | 0.0833 | 0.2083 | 0.3750 | 16278.0 | 1.0000e+00 | 2.3385e-01 | 0.0000e+00 | 0.1650 | NaN | NaN | NaN | 0.2083 | 0.125 | NaN | NaN | NaN | NaN | 0.2083 |
LANDAREA_MODE | float64 | 2560 (5.25%) | 28254 (57.96%) | 0 (0.00%) | 2971 (6.10%) | 0.0165 | 0.0462 | 0.0856 | 20490.0 | 1.0000e+00 | 6.5914e-02 | 0.0000e+00 | 0.0829 | NaN | NaN | NaN | 0.0562 | 0.0179 | NaN | NaN | NaN | 0.0734 | 0 |
LIVINGAPARTMENTS_MODE | float64 | 602 (1.24%) | 32780 (67.25%) | 0 (0.00%) | 66 (0.14%) | 0.0551 | 0.0817 | 0.1322 | 15964.0 | 1.0000e+00 | 1.1087e-01 | 0.0000e+00 | 0.1040 | NaN | NaN | NaN | 0.0606 | 0.0083 | NaN | NaN | NaN | 0.1175 | 0.1387 |
LIVINGAREA_MODE | float64 | 3842 (7.88%) | 23552 (48.32%) | 0 (0.00%) | 69 (0.14%) | 0.0456 | 0.0751 | 0.1306 | 25192.0 | 1.0000e+00 | 1.1069e-01 | 0.0000e+00 | 0.1167 | NaN | NaN | NaN | 0.0601 | 0.0185 | NaN | NaN | NaN | 0.0871 | 0.0441 |
NONLIVINGAPARTMENTS_MODE | float64 | 106 (0.22%) | 33347 (68.41%) | 0 (0.00%) | 9638 (19.77%) | 0.0000 | 0.0000 | 0.0039 | 15397.0 | 1.0000e+00 | 8.3575e-03 | 0.0000e+00 | 0.0467 | NaN | NaN | NaN | 0.0156 | 0 | NaN | NaN | NaN | 0.0039 | 0 |
NONLIVINGAREA_MODE | float64 | 2025 (4.15%) | 26084 (53.51%) | 0 (0.00%) | 10922 (22.41%) | 0.0000 | 0.0012 | 0.0245 | 22660.0 | 1.0000e+00 | 2.8161e-02 | 0.0000e+00 | 0.0735 | NaN | NaN | NaN | 0.0152 | 0 | NaN | NaN | NaN | 0.1042 | 0 |
APARTMENTS_MEDI | float64 | 918 (1.88%) | 23887 (49.01%) | 0 (0.00%) | 123 (0.25%) | 0.0625 | 0.0926 | 0.1499 | 24857.0 | 1.0000e+00 | 1.2281e-01 | 0.0000e+00 | 0.1142 | NaN | NaN | NaN | 0.0729 | 0.0625 | NaN | NaN | NaN | 0.1332 | 0.1572 |
BASEMENTAREA_MEDI | float64 | 2805 (5.75%) | 27641 (56.71%) | 0 (0.00%) | 2279 (4.68%) | 0.0461 | 0.0778 | 0.1130 | 21103.0 | 1.0000e+00 | 8.9529e-02 | 0.0000e+00 | 0.0810 | NaN | NaN | NaN | 0.0785 | 0.0615 | NaN | NaN | NaN | 0.1093 | 0.0097 |
YEARS_BEGINEXPLUATATION_MEDI | float64 | 169 (0.35%) | 22856 (46.89%) | 0 (0.00%) | 61 (0.13%) | 0.9767 | 0.9816 | 0.9866 | 25888.0 | 1.0000e+00 | 9.7882e-01 | 0.0000e+00 | 0.0497 | NaN | NaN | NaN | 0.9776 | 0.9831 | NaN | NaN | NaN | 0.9866 | 0.9776 |
YEARS_BUILD_MEDI | float64 | 129 (0.26%) | 31818 (65.28%) | 0 (0.00%) | 19 (0.04%) | 0.6914 | 0.7585 | 0.8189 | 16926.0 | 1.0000e+00 | 7.5434e-01 | 0.0000e+00 | 0.1120 | NaN | NaN | NaN | 0.6981 | 0.7719 | NaN | NaN | NaN | 0.8189 | 0.6981 |
COMMONAREA_MEDI | float64 | 2034 (4.17%) | 33495 (68.72%) | 0 (0.00%) | 1425 (2.92%) | 0.0080 | 0.0223 | 0.0538 | 15249.0 | 1.0000e+00 | 4.7420e-02 | 0.0000e+00 | 0.0829 | NaN | NaN | NaN | 0.0079 | 0.047 | NaN | NaN | NaN | 0.0165 | 0.0098 |
ELEVATORS_MEDI | float64 | 43 (0.09%) | 25189 (51.68%) | 0 (0.00%) | 13738 (28.18%) | 0.0000 | 0.0000 | 0.1600 | 23555.0 | 1.0000e+00 | 8.4128e-02 | 0.0000e+00 | 0.1390 | NaN | NaN | NaN | 0 | 0 | NaN | NaN | NaN | 0.16 | 0 |
ENTRANCES_MEDI | float64 | 43 (0.09%) | 23579 (48.37%) | 0 (0.00%) | 38 (0.08%) | 0.0690 | 0.1379 | 0.2069 | 25165.0 | 1.0000e+00 | 1.5120e-01 | 0.0000e+00 | 0.1009 | NaN | NaN | NaN | 0.1034 | 0.1379 | NaN | NaN | NaN | 0.1379 | 0.1034 |
FLOORSMAX_MEDI | float64 | 47 (0.10%) | 23321 (47.84%) | 0 (0.00%) | 425 (0.87%) | 0.1667 | 0.1667 | 0.3333 | 25423.0 | 1.0000e+00 | 2.3315e-01 | 0.0000e+00 | 0.1476 | NaN | NaN | NaN | 0.1667 | 0.1667 | NaN | NaN | NaN | 0.3333 | 0.1667 |
FLOORSMIN_MEDI | float64 | 44 (0.09%) | 32466 (66.61%) | 0 (0.00%) | 397 (0.81%) | 0.0833 | 0.2083 | 0.3750 | 16278.0 | 1.0000e+00 | 2.3785e-01 | 0.0000e+00 | 0.1652 | NaN | NaN | NaN | 0.2083 | 0.2083 | NaN | NaN | NaN | NaN | 0.2083 |
LANDAREA_MEDI | float64 | 2562 (5.26%) | 28254 (57.96%) | 0 (0.00%) | 2708 (5.56%) | 0.0190 | 0.0488 | 0.0880 | 20490.0 | 1.0000e+00 | 6.8069e-02 | 0.0000e+00 | 0.0829 | NaN | NaN | NaN | 0.0559 | 0.0767 | NaN | NaN | NaN | 0.073 | 0 |
LIVINGAPARTMENTS_MEDI | float64 | 843 (1.73%) | 32780 (67.25%) | 0 (0.00%) | 47 (0.10%) | 0.0513 | 0.0770 | 0.1266 | 15964.0 | 1.0000e+00 | 1.0706e-01 | 0.0000e+00 | 0.0997 | NaN | NaN | NaN | 0.0564 | 0.0513 | NaN | NaN | NaN | 0.1095 | 0.1291 |
LIVINGAREA_MEDI | float64 | 3885 (7.97%) | 23552 (48.32%) | 0 (0.00%) | 49 (0.10%) | 0.0490 | 0.0776 | 0.1374 | 25192.0 | 1.0000e+00 | 1.1337e-01 | 0.0000e+00 | 0.1165 | NaN | NaN | NaN | 0.0587 | 0.0532 | NaN | NaN | NaN | 0.0851 | 0.043 |
NONLIVINGAPARTMENTS_MEDI | float64 | 134 (0.27%) | 33347 (68.41%) | 0 (0.00%) | 9117 (18.70%) | 0.0000 | 0.0000 | 0.0039 | 15397.0 | 1.0000e+00 | 8.9789e-03 | 0.0000e+00 | 0.0481 | NaN | NaN | NaN | 0.0155 | 0 | NaN | NaN | NaN | 0.0039 | 0 |
NONLIVINGAREA_MEDI | float64 | 2030 (4.16%) | 26084 (53.51%) | 0 (0.00%) | 9867 (20.24%) | 0.0000 | 0.0031 | 0.0280 | 22660.0 | 1.0000e+00 | 2.9296e-02 | 0.0000e+00 | 0.0730 | NaN | NaN | NaN | 0.0147 | 0 | NaN | NaN | NaN | 0.1005 | 0 |
FONDKAPREMONT_MODE | object | 4 (0.01%) | 32797 (67.28%) | 0 (0.00%) | 0 (0.00%) | 0.0000 | 0.0000 | 0.0000 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | NaN | NaN | NaN | reg oper account | reg oper account | NaN | NaN | NaN | reg oper account | reg oper account |
HOUSETYPE_MODE | object | 3 (0.01%) | 23619 (48.46%) | 0 (0.00%) | 0 (0.00%) | 0.0000 | 0.0000 | 0.0000 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | NaN | NaN | NaN | block of flats | block of flats | NaN | NaN | NaN | block of flats | block of flats |
TOTALAREA_MODE | float64 | 3820 (7.84%) | 22624 (46.41%) | 0 (0.00%) | 73 (0.15%) | 0.0432 | 0.0707 | 0.1357 | 26120.0 | 1.0000e+00 | 1.0713e-01 | 0.0000e+00 | 0.1114 | NaN | NaN | NaN | 0.0528 | 0.0158 | NaN | NaN | NaN | 0.1081 | 0.0565 |
WALLSMATERIAL_MODE | object | 7 (0.01%) | 23893 (49.02%) | 0 (0.00%) | 0 (0.00%) | 0.0000 | 0.0000 | 0.0000 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | NaN | NaN | NaN | Stone, brick | Stone, brick | NaN | NaN | NaN | Stone, brick | Stone, brick |
EMERGENCYSTATE_MODE | object | 2 (0.00%) | 22209 (45.56%) | 0 (0.00%) | 0 (0.00%) | 0.0000 | 0.0000 | 0.0000 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | NaN | NaN | NaN | No | No | NaN | NaN | NaN | No | No |
OBS_30_CNT_SOCIAL_CIRCLE | float64 | 28 (0.06%) | 29 (0.06%) | 0 (0.00%) | 26025 (53.39%) | 0.0000 | 0.0000 | 2.0000 | 48715.0 | 3.5400e+02 | 1.4476e+00 | 0.0000e+00 | 3.6081 | 1 | 0 | 3 | 2 | 0 | 0 | 0 | 0 | 5 | 0 |
DEF_30_CNT_SOCIAL_CIRCLE | float64 | 8 (0.02%) | 29 (0.06%) | 0 (0.00%) | 43195 (88.62%) | 0.0000 | 0.0000 | 0.0000 | 48715.0 | 3.4000e+01 | 1.4365e-01 | 0.0000e+00 | 0.5144 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0 |
OBS_60_CNT_SOCIAL_CIRCLE | float64 | 27 (0.06%) | 29 (0.06%) | 0 (0.00%) | 26140 (53.63%) | 0.0000 | 0.0000 | 2.0000 | 48715.0 | 3.5100e+02 | 1.4357e+00 | 0.0000e+00 | 3.5801 | 1 | 0 | 3 | 2 | 0 | 0 | 0 | 0 | 5 | 0 |
DEF_60_CNT_SOCIAL_CIRCLE | float64 | 7 (0.01%) | 29 (0.06%) | 0 (0.00%) | 44614 (91.53%) | 0.0000 | 0.0000 | 0.0000 | 48715.0 | 2.4000e+01 | 1.0114e-01 | 0.0000e+00 | 0.4038 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 0 |
DAYS_LAST_PHONE_CHANGE | float64 | 3579 (7.34%) | 0 (0.00%) | 42943 (88.10%) | 5801 (11.90%) | -1766.2500 | -863.0000 | -363.0000 | 48744.0 | 0.0000e+00 | -1.0778e+03 | -4.3610e+03 | 878.9207 | -663 | 0 | -1125 | -2471 | -497 | -495 | -2624 | 0 | -510 | -2540 |
FLAG_DOCUMENT_2 | int64 | 1 (0.00%) | 0 (0.00%) | 0 (0.00%) | 48744 (100.00%) | 0.0000 | 0.0000 | 0.0000 | 48744.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
FLAG_DOCUMENT_3 | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 10401 (21.34%) | 1.0000 | 1.0000 | 1.0000 | 48744.0 | 1.0000e+00 | 7.8662e-01 | 0.0000e+00 | 0.4097 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 |
FLAG_DOCUMENT_4 | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 48739 (99.99%) | 0.0000 | 0.0000 | 0.0000 | 48744.0 | 1.0000e+00 | 1.0258e-04 | 0.0000e+00 | 0.0101 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
FLAG_DOCUMENT_5 | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 48025 (98.52%) | 0.0000 | 0.0000 | 0.0000 | 48744.0 | 1.0000e+00 | 1.4751e-02 | 0.0000e+00 | 0.1206 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
FLAG_DOCUMENT_6 | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 44480 (91.25%) | 0.0000 | 0.0000 | 0.0000 | 48744.0 | 1.0000e+00 | 8.7477e-02 | 0.0000e+00 | 0.2825 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
FLAG_DOCUMENT_7 | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 48742 (100.00%) | 0.0000 | 0.0000 | 0.0000 | 48744.0 | 1.0000e+00 | 4.1031e-05 | 0.0000e+00 | 0.0064 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
FLAG_DOCUMENT_8 | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 44432 (91.15%) | 0.0000 | 0.0000 | 0.0000 | 48744.0 | 1.0000e+00 | 8.8462e-02 | 0.0000e+00 | 0.2840 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
FLAG_DOCUMENT_9 | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 48525 (99.55%) | 0.0000 | 0.0000 | 0.0000 | 48744.0 | 1.0000e+00 | 4.4929e-03 | 0.0000e+00 | 0.0669 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
FLAG_DOCUMENT_10 | int64 | 1 (0.00%) | 0 (0.00%) | 0 (0.00%) | 48744 (100.00%) | 0.0000 | 0.0000 | 0.0000 | 48744.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
FLAG_DOCUMENT_11 | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 48687 (99.88%) | 0.0000 | 0.0000 | 0.0000 | 48744.0 | 1.0000e+00 | 1.1694e-03 | 0.0000e+00 | 0.0342 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
FLAG_DOCUMENT_12 | int64 | 1 (0.00%) | 0 (0.00%) | 0 (0.00%) | 48744 (100.00%) | 0.0000 | 0.0000 | 0.0000 | 48744.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
FLAG_DOCUMENT_13 | int64 | 1 (0.00%) | 0 (0.00%) | 0 (0.00%) | 48744 (100.00%) | 0.0000 | 0.0000 | 0.0000 | 48744.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
FLAG_DOCUMENT_14 | int64 | 1 (0.00%) | 0 (0.00%) | 0 (0.00%) | 48744 (100.00%) | 0.0000 | 0.0000 | 0.0000 | 48744.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
FLAG_DOCUMENT_15 | int64 | 1 (0.00%) | 0 (0.00%) | 0 (0.00%) | 48744 (100.00%) | 0.0000 | 0.0000 | 0.0000 | 48744.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
FLAG_DOCUMENT_16 | int64 | 1 (0.00%) | 0 (0.00%) | 0 (0.00%) | 48744 (100.00%) | 0.0000 | 0.0000 | 0.0000 | 48744.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
FLAG_DOCUMENT_17 | int64 | 1 (0.00%) | 0 (0.00%) | 0 (0.00%) | 48744 (100.00%) | 0.0000 | 0.0000 | 0.0000 | 48744.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
FLAG_DOCUMENT_18 | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 48668 (99.84%) | 0.0000 | 0.0000 | 0.0000 | 48744.0 | 1.0000e+00 | 1.5592e-03 | 0.0000e+00 | 0.0395 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
FLAG_DOCUMENT_19 | int64 | 1 (0.00%) | 0 (0.00%) | 0 (0.00%) | 48744 (100.00%) | 0.0000 | 0.0000 | 0.0000 | 48744.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
FLAG_DOCUMENT_20 | int64 | 1 (0.00%) | 0 (0.00%) | 0 (0.00%) | 48744 (100.00%) | 0.0000 | 0.0000 | 0.0000 | 48744.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
FLAG_DOCUMENT_21 | int64 | 1 (0.00%) | 0 (0.00%) | 0 (0.00%) | 48744 (100.00%) | 0.0000 | 0.0000 | 0.0000 | 48744.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
AMT_REQ_CREDIT_BUREAU_HOUR | float64 | 3 (0.01%) | 6049 (12.41%) | 0 (0.00%) | 42606 (87.41%) | 0.0000 | 0.0000 | 0.0000 | 42695.0 | 2.0000e+00 | 2.1080e-03 | 0.0000e+00 | 0.0464 | 0 | 0 | 0 | 0 | NaN | 0 | 0 | 0 | 0 | 0 |
AMT_REQ_CREDIT_BUREAU_DAY | float64 | 3 (0.01%) | 6049 (12.41%) | 0 (0.00%) | 42625 (87.45%) | 0.0000 | 0.0000 | 0.0000 | 42695.0 | 2.0000e+00 | 1.8035e-03 | 0.0000e+00 | 0.0461 | 0 | 0 | 0 | 0 | NaN | 0 | 0 | 0 | 0 | 0 |
AMT_REQ_CREDIT_BUREAU_WEEK | float64 | 3 (0.01%) | 6049 (12.41%) | 0 (0.00%) | 42579 (87.35%) | 0.0000 | 0.0000 | 0.0000 | 42695.0 | 2.0000e+00 | 2.7872e-03 | 0.0000e+00 | 0.0540 | 0 | 0 | 0 | 0 | NaN | 0 | 0 | 0 | 0 | 0 |
AMT_REQ_CREDIT_BUREAU_MON | float64 | 7 (0.01%) | 6049 (12.41%) | 0 (0.00%) | 42341 (86.86%) | 0.0000 | 0.0000 | 0.0000 | 42695.0 | 6.0000e+00 | 9.2985e-03 | 0.0000e+00 | 0.1109 | 0 | 0 | 0 | 0 | NaN | 0 | 0 | 0 | 0 | 0 |
AMT_REQ_CREDIT_BUREAU_QRT | float64 | 8 (0.02%) | 6049 (12.41%) | 0 (0.00%) | 23559 (48.33%) | 0.0000 | 0.0000 | 1.0000 | 42695.0 | 7.0000e+00 | 5.4690e-01 | 0.0000e+00 | 0.6933 | 1 | 1 | 2 | 0 | NaN | 1 | 0 | 1 | 1 | 0 |
AMT_REQ_CREDIT_BUREAU_YEAR | float64 | 16 (0.03%) | 6049 (12.41%) | 0 (0.00%) | 10839 (22.24%) | 0.0000 | 2.0000 | 3.0000 | 42695.0 | 1.7000e+01 | 1.9838e+00 | 0.0000e+00 | 1.8389 | 1 | 3 | 2 | 3 | NaN | 1 | 0 | 0 | 0 | 3 |
Exploring application_train.csv ('Total records:', 307511) ('Total columns:', 122)
sub_type | n_distinct | n_miss | n_negative | n_zeros | 25% | 50% | 75% | count | max | mean | min | std | sample_0 | sample_1 | sample_2 | sample_3 | sample_4 | sample_5 | sample_6 | sample_7 | sample_8 | sample_9 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
name | |||||||||||||||||||||||
SK_ID_CURR | int64 | 307511 (100.00%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 189145.5000 | 278202.0000 | 367142.5000 | 307511.0 | 4.5626e+05 | 2.7818e+05 | 1.0000e+05 | 102790.1753 | 326682 | 414578 | 432657 | 346257 | 169928 | 228494 | 305986 | 450918 | 393627 | 121604 |
TARGET | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 282686 (91.93%) | 0.0000 | 0.0000 | 0.0000 | 307511.0 | 1.0000e+00 | 8.0729e-02 | 0.0000e+00 | 0.2724 | 0 | 1 | 0 | 0 | 1 | 0 | 0 | 1 | 0 | 0 |
NAME_CONTRACT_TYPE | object | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0.0000 | 0.0000 | 0.0000 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | Cash loans | Cash loans | Revolving loans | Cash loans | Cash loans | Cash loans | Cash loans | Cash loans | Cash loans | Cash loans |
CODE_GENDER | object | 3 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0.0000 | 0.0000 | 0.0000 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | M | M | M | M | M | F | M | F | F | F |
FLAG_OWN_CAR | object | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0.0000 | 0.0000 | 0.0000 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | Y | Y | N | N | N | N | N | Y | N | N |
FLAG_OWN_REALTY | object | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0.0000 | 0.0000 | 0.0000 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | Y | N | Y | Y | Y | Y | Y | N | Y | Y |
CNT_CHILDREN | int64 | 15 (0.00%) | 0 (0.00%) | 0 (0.00%) | 215371 (70.04%) | 0.0000 | 0.0000 | 1.0000 | 307511.0 | 1.9000e+01 | 4.1705e-01 | 0.0000e+00 | 0.7221 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 2 | 0 |
AMT_INCOME_TOTAL | float64 | 2548 (0.83%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 112500.0000 | 147150.0000 | 202500.0000 | 307511.0 | 1.1700e+08 | 1.6880e+05 | 2.5650e+04 | 237123.1463 | 1.665e+05 | 4.5e+05 | 1.575e+05 | 1.35e+05 | 2.025e+05 | 1.17e+05 | 9e+04 | 1.8e+05 | 1.575e+05 | 9e+04 |
AMT_CREDIT | float64 | 5603 (1.82%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 270000.0000 | 513531.0000 | 808650.0000 | 307511.0 | 4.0500e+06 | 5.9903e+05 | 4.5000e+04 | 402490.7770 | 2.547e+05 | 1.381e+06 | 4.5e+05 | 1.764e+06 | 2.038e+05 | 2.547e+05 | 5.387e+05 | 6.3e+05 | 6.795e+05 | 7.552e+05 |
AMT_ANNUITY | float64 | 13672 (4.45%) | 12 (0.00%) | 0 (0.00%) | 0 (0.00%) | 16524.0000 | 24903.0000 | 34596.0000 | 307499.0 | 2.5803e+05 | 2.7109e+04 | 1.6155e+03 | 14493.7373 | 2.519e+04 | 3.971e+04 | 2.25e+04 | 4.851e+04 | 1.623e+04 | 2.519e+04 | 2.605e+04 | 2.327e+04 | 3.62e+04 | 3.646e+04 |
AMT_GOODS_PRICE | float64 | 1002 (0.33%) | 278 (0.09%) | 0 (0.00%) | 0 (0.00%) | 238500.0000 | 450000.0000 | 679500.0000 | 307233.0 | 4.0500e+06 | 5.3840e+05 | 4.0500e+04 | 369446.4605 | 2.25e+05 | 1.206e+06 | 4.5e+05 | 1.764e+06 | 1.8e+05 | 2.25e+05 | 4.815e+05 | 6.3e+05 | 6.795e+05 | 6.75e+05 |
NAME_TYPE_SUITE | object | 7 (0.00%) | 1292 (0.42%) | 0 (0.00%) | 0 (0.00%) | 0.0000 | 0.0000 | 0.0000 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | Unaccompanied | Unaccompanied | Unaccompanied | Unaccompanied | Unaccompanied | Unaccompanied | Unaccompanied | Unaccompanied | Family | Family |
NAME_INCOME_TYPE | object | 8 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0.0000 | 0.0000 | 0.0000 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | State servant | Working | Working | Commercial associate | Working | Pensioner | Working | Working | Working | Working |
NAME_EDUCATION_TYPE | object | 5 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0.0000 | 0.0000 | 0.0000 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | Higher education | Incomplete higher | Secondary / secondary special | Secondary / secondary special | Secondary / secondary special | Secondary / secondary special | Secondary / secondary special | Secondary / secondary special | Secondary / secondary special | Secondary / secondary special |
NAME_FAMILY_STATUS | object | 6 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0.0000 | 0.0000 | 0.0000 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | Married | Married | Married | Married | Separated | Married | Single / not married | Married | Married | Married |
NAME_HOUSING_TYPE | object | 6 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0.0000 | 0.0000 | 0.0000 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | House / apartment | House / apartment | House / apartment | House / apartment | House / apartment | House / apartment | House / apartment | House / apartment | House / apartment | With parents |
REGION_POPULATION_RELATIVE | float64 | 81 (0.03%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0.0100 | 0.0188 | 0.0287 | 307511.0 | 7.2508e-02 | 2.0868e-02 | 2.9000e-04 | 0.0138 | 0.02461 | 0.01863 | 0.01522 | 0.008019 | 0.0105 | 0.008866 | 0.01863 | 0.0105 | 0.01885 | 0.03076 |
DAYS_BIRTH | int64 | 17460 (5.68%) | 0 (0.00%) | 307511 (100.00%) | 0 (0.00%) | -19682.0000 | -15750.0000 | -12413.0000 | 307511.0 | -7.4890e+03 | -1.6037e+04 | -2.5229e+04 | 4363.9886 | -21882 | -14026 | -9905 | -11946 | -10493 | -24264 | -15251 | -14263 | -11179 | -10477 |
DAYS_EMPLOYED | int64 | 12574 (4.09%) | 0 (0.00%) | 252135 (81.99%) | 2 (0.00%) | -2760.0000 | -1213.0000 | -289.0000 | 307511.0 | 3.6524e+05 | 6.3815e+04 | -1.7912e+04 | 141275.7665 | -2987 | -270 | -2691 | -1526 | -656 | 365243 | -1984 | -481 | -687 | -1400 |
DAYS_REGISTRATION | float64 | 15688 (5.10%) | 0 (0.00%) | 307431 (99.97%) | 80 (0.03%) | -7479.5000 | -4504.0000 | -2010.0000 | 307511.0 | 0.0000e+00 | -4.9861e+03 | -2.4672e+04 | 3522.8863 | -1.112e+04 | -1625 | -4725 | -1513 | -2389 | -87 | -6933 | -1315 | -1491 | -5034 |
DAYS_ID_PUBLISH | int64 | 6168 (2.01%) | 0 (0.00%) | 307495 (99.99%) | 16 (0.01%) | -4299.0000 | -3254.0000 | -1720.0000 | 307511.0 | 0.0000e+00 | -2.9942e+03 | -7.1970e+03 | 1509.4504 | -3984 | -4768 | -2549 | -4392 | -2526 | -4388 | -4396 | -4830 | -2742 | -1625 |
OWN_CAR_AGE | float64 | 62 (0.02%) | 202929 (65.99%) | 0 (0.00%) | 2134 (0.69%) | 5.0000 | 9.0000 | 15.0000 | 104582.0 | 9.1000e+01 | 1.2061e+01 | 0.0000e+00 | 11.9448 | 4 | 1 | NaN | NaN | NaN | NaN | NaN | 18 | NaN | NaN |
FLAG_MOBIL | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 1 (0.00%) | 1.0000 | 1.0000 | 1.0000 | 307511.0 | 1.0000e+00 | 1.0000e+00 | 0.0000e+00 | 0.0018 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 |
FLAG_EMP_PHONE | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 55386 (18.01%) | 1.0000 | 1.0000 | 1.0000 | 307511.0 | 1.0000e+00 | 8.1989e-01 | 0.0000e+00 | 0.3843 | 1 | 1 | 1 | 1 | 1 | 0 | 1 | 1 | 1 | 1 |
FLAG_WORK_PHONE | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 246203 (80.06%) | 0.0000 | 0.0000 | 0.0000 | 307511.0 | 1.0000e+00 | 1.9937e-01 | 0.0000e+00 | 0.3995 | 1 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 1 | 1 |
FLAG_CONT_MOBILE | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 574 (0.19%) | 1.0000 | 1.0000 | 1.0000 | 307511.0 | 1.0000e+00 | 9.9813e-01 | 0.0000e+00 | 0.0432 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 |
FLAG_PHONE | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 221080 (71.89%) | 0.0000 | 0.0000 | 1.0000 | 307511.0 | 1.0000e+00 | 2.8107e-01 | 0.0000e+00 | 0.4495 | 1 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 1 | 0 |
FLAG_EMAIL | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 290069 (94.33%) | 0.0000 | 0.0000 | 0.0000 | 307511.0 | 1.0000e+00 | 5.6720e-02 | 0.0000e+00 | 0.2313 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
OCCUPATION_TYPE | object | 18 (0.01%) | 96391 (31.35%) | 0 (0.00%) | 0 (0.00%) | 0.0000 | 0.0000 | 0.0000 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | NaN | Drivers | Laborers | NaN | Laborers | NaN | Laborers | NaN | Managers | Laborers |
CNT_FAM_MEMBERS | float64 | 17 (0.01%) | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 2.0000 | 2.0000 | 3.0000 | 307509.0 | 2.0000e+01 | 2.1527e+00 | 1.0000e+00 | 0.9107 | 2 | 3 | 2 | 2 | 1 | 2 | 1 | 3 | 4 | 2 |
REGION_RATING_CLIENT | int64 | 3 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 2.0000 | 2.0000 | 2.0000 | 307511.0 | 3.0000e+00 | 2.0525e+00 | 1.0000e+00 | 0.5090 | 2 | 2 | 2 | 2 | 3 | 2 | 2 | 3 | 2 | 2 |
REGION_RATING_CLIENT_W_CITY | int64 | 3 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 2.0000 | 2.0000 | 2.0000 | 307511.0 | 3.0000e+00 | 2.0315e+00 | 1.0000e+00 | 0.5027 | 2 | 2 | 2 | 2 | 3 | 2 | 2 | 3 | 2 | 2 |
WEEKDAY_APPR_PROCESS_START | object | 7 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0.0000 | 0.0000 | 0.0000 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | THURSDAY | MONDAY | WEDNESDAY | FRIDAY | WEDNESDAY | MONDAY | FRIDAY | MONDAY | TUESDAY | FRIDAY |
HOUR_APPR_PROCESS_START | int64 | 24 (0.01%) | 0 (0.00%) | 0 (0.00%) | 40 (0.01%) | 10.0000 | 12.0000 | 14.0000 | 307511.0 | 2.3000e+01 | 1.2063e+01 | 0.0000e+00 | 3.2658 | 17 | 10 | 9 | 10 | 15 | 17 | 9 | 13 | 12 | 13 |
REG_REGION_NOT_LIVE_REGION | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 302854 (98.49%) | 0.0000 | 0.0000 | 0.0000 | 307511.0 | 1.0000e+00 | 1.5144e-02 | 0.0000e+00 | 0.1221 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
REG_REGION_NOT_WORK_REGION | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 291899 (94.92%) | 0.0000 | 0.0000 | 0.0000 | 307511.0 | 1.0000e+00 | 5.0769e-02 | 0.0000e+00 | 0.2195 | 0 | 0 | 0 | 1 | 1 | 0 | 0 | 0 | 0 | 0 |
LIVE_REGION_NOT_WORK_REGION | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 295008 (95.93%) | 0.0000 | 0.0000 | 0.0000 | 307511.0 | 1.0000e+00 | 4.0659e-02 | 0.0000e+00 | 0.1975 | 0 | 0 | 0 | 1 | 1 | 0 | 0 | 0 | 0 | 0 |
REG_CITY_NOT_LIVE_CITY | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 283472 (92.18%) | 0.0000 | 0.0000 | 0.0000 | 307511.0 | 1.0000e+00 | 7.8173e-02 | 0.0000e+00 | 0.2684 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
REG_CITY_NOT_WORK_CITY | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 236644 (76.95%) | 0.0000 | 0.0000 | 0.0000 | 307511.0 | 1.0000e+00 | 2.3045e-01 | 0.0000e+00 | 0.4211 | 0 | 0 | 1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 |
LIVE_CITY_NOT_WORK_CITY | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 252296 (82.04%) | 0.0000 | 0.0000 | 0.0000 | 307511.0 | 1.0000e+00 | 1.7955e-01 | 0.0000e+00 | 0.3838 | 0 | 0 | 0 | 1 | 1 | 0 | 0 | 0 | 0 | 0 |
ORGANIZATION_TYPE | object | 58 (0.02%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0.0000 | 0.0000 | 0.0000 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | Business Entity Type 2 | Business Entity Type 3 | Business Entity Type 2 | Business Entity Type 3 | Self-employed | XNA | Self-employed | Business Entity Type 3 | Trade: type 2 | Medicine |
EXT_SOURCE_1 | float64 | 114584 (37.26%) | 173378 (56.38%) | 0 (0.00%) | 0 (0.00%) | 0.3340 | 0.5060 | 0.6751 | 134133.0 | 9.6269e-01 | 5.0213e-01 | 1.4568e-02 | 0.2111 | NaN | 0.357 | NaN | 0.4949 | NaN | NaN | NaN | 0.5393 | 0.6575 | NaN |
EXT_SOURCE_2 | float64 | 119831 (38.97%) | 660 (0.21%) | 0 (0.00%) | 0 (0.00%) | 0.3925 | 0.5660 | 0.6636 | 306851.0 | 8.5500e-01 | 5.1439e-01 | 8.1736e-08 | 0.1911 | 0.5785 | 0.5153 | 0.4248 | 0.667 | 0.09625 | 0.3947 | 0.7881 | 0.558 | 0.5917 | 0.6676 |
EXT_SOURCE_3 | float64 | 814 (0.26%) | 60965 (19.83%) | 0 (0.00%) | 0 (0.00%) | 0.3706 | 0.5353 | 0.6691 | 246546.0 | 8.9601e-01 | 5.1085e-01 | 5.2727e-04 | 0.1948 | 0.5972 | 0.5227 | 0.3155 | NaN | 0.4171 | 0.6058 | NaN | 0.749 | 0.4957 | 0.7394 |
APARTMENTS_AVG | float64 | 2339 (0.76%) | 156061 (50.75%) | 0 (0.00%) | 751 (0.24%) | 0.0577 | 0.0876 | 0.1485 | 151450.0 | 1.0000e+00 | 1.1744e-01 | 0.0000e+00 | 0.1082 | NaN | 0.1485 | NaN | NaN | NaN | 0.2216 | 0.0629 | 0.0825 | 0.1031 | 0.1825 |
BASEMENTAREA_AVG | float64 | 3780 (1.23%) | 179943 (58.52%) | 0 (0.00%) | 14745 (4.79%) | 0.0442 | 0.0763 | 0.1122 | 127568.0 | 1.0000e+00 | 8.8442e-02 | 0.0000e+00 | 0.0824 | NaN | 0.0991 | NaN | NaN | NaN | 0.0776 | 0.0756 | 0.0788 | NaN | 0.1322 |
YEARS_BEGINEXPLUATATION_AVG | float64 | 285 (0.09%) | 150007 (48.78%) | 0 (0.00%) | 514 (0.17%) | 0.9767 | 0.9816 | 0.9866 | 157504.0 | 1.0000e+00 | 9.7773e-01 | 0.0000e+00 | 0.0592 | 0.9856 | 0.9871 | NaN | NaN | NaN | 0.9826 | 0.9831 | 0.9786 | 0.9771 | 0.9861 |
YEARS_BUILD_AVG | float64 | 149 (0.05%) | 204488 (66.50%) | 0 (0.00%) | 102 (0.03%) | 0.6872 | 0.7552 | 0.8232 | 103023.0 | 1.0000e+00 | 7.5247e-01 | 0.0000e+00 | 0.1133 | NaN | 0.8232 | NaN | NaN | NaN | NaN | 0.7688 | 0.7076 | 0.6872 | 0.8096 |
COMMONAREA_AVG | float64 | 3181 (1.03%) | 214865 (69.87%) | 0 (0.00%) | 8442 (2.75%) | 0.0078 | 0.0211 | 0.0515 | 92646.0 | 1.0000e+00 | 4.4621e-02 | 0.0000e+00 | 0.0760 | NaN | 0.0889 | NaN | NaN | NaN | NaN | NaN | 0.0079 | NaN | 0.0378 |
ELEVATORS_AVG | float64 | 257 (0.08%) | 163891 (53.30%) | 0 (0.00%) | 85718 (27.87%) | 0.0000 | 0.0000 | 0.1200 | 143620.0 | 1.0000e+00 | 7.8942e-02 | 0.0000e+00 | 0.1346 | 0.08 | 0.16 | NaN | NaN | NaN | 0.08 | 0 | 0 | NaN | 0.2 |
ENTRANCES_AVG | float64 | 285 (0.09%) | 154828 (50.35%) | 0 (0.00%) | 323 (0.11%) | 0.0690 | 0.1379 | 0.2069 | 152683.0 | 1.0000e+00 | 1.4972e-01 | 0.0000e+00 | 0.1000 | 0.069 | 0.1379 | NaN | NaN | NaN | 0.0345 | 0.1379 | 0.1379 | 0.2069 | 0.1724 |
FLOORSMAX_AVG | float64 | 403 (0.13%) | 153020 (49.76%) | 0 (0.00%) | 2938 (0.96%) | 0.1667 | 0.1667 | 0.3333 | 154491.0 | 1.0000e+00 | 2.2628e-01 | 0.0000e+00 | 0.1446 | 0.3333 | 0.3333 | NaN | NaN | NaN | 0.3333 | 0.1667 | 0.1667 | 0.1667 | 0.3333 |
FLOORSMIN_AVG | float64 | 305 (0.10%) | 208642 (67.85%) | 0 (0.00%) | 2320 (0.75%) | 0.0833 | 0.2083 | 0.3750 | 98869.0 | 1.0000e+00 | 2.3189e-01 | 0.0000e+00 | 0.1614 | NaN | 0.375 | NaN | NaN | NaN | NaN | NaN | 0.2083 | NaN | 0.375 |
LANDAREA_AVG | float64 | 3527 (1.15%) | 182590 (59.38%) | 0 (0.00%) | 15600 (5.07%) | 0.0187 | 0.0481 | 0.0856 | 124921.0 | 1.0000e+00 | 6.6333e-02 | 0.0000e+00 | 0.0812 | NaN | 0.1127 | NaN | NaN | NaN | 0.0911 | 0.0151 | 0.0203 | NaN | 0.1238 |
LIVINGAPARTMENTS_AVG | float64 | 1868 (0.61%) | 210199 (68.35%) | 0 (0.00%) | 418 (0.14%) | 0.0504 | 0.0756 | 0.1210 | 97312.0 | 1.0000e+00 | 1.0077e-01 | 0.0000e+00 | 0.0926 | NaN | 0.121 | NaN | NaN | NaN | NaN | 0.0504 | 0.0672 | 0.0807 | 0.1488 |
LIVINGAREA_AVG | float64 | 5199 (1.69%) | 154350 (50.19%) | 0 (0.00%) | 284 (0.09%) | 0.0453 | 0.0745 | 0.1299 | 153161.0 | 1.0000e+00 | 1.0740e-01 | 0.0000e+00 | 0.1106 | 0.0739 | 0.0915 | NaN | NaN | NaN | 0.0582 | 0.0556 | 0.0703 | 0.0841 | 0.1824 |
NONLIVINGAPARTMENTS_AVG | float64 | 386 (0.13%) | 213514 (69.43%) | 0 (0.00%) | 54549 (17.74%) | 0.0000 | 0.0000 | 0.0039 | 93997.0 | 1.0000e+00 | 8.8087e-03 | 0.0000e+00 | 0.0477 | NaN | 0 | NaN | NaN | NaN | NaN | 0.0039 | 0 | 0.0154 | 0 |
NONLIVINGAREA_AVG | float64 | 3290 (1.07%) | 169682 (55.18%) | 0 (0.00%) | 58735 (19.10%) | 0.0000 | 0.0036 | 0.0277 | 137829.0 | 1.0000e+00 | 2.8358e-02 | 0.0000e+00 | 0.0695 | NaN | 0 | NaN | NaN | NaN | 0.2242 | 0.0188 | 0 | 0.0128 | 0.0022 |
APARTMENTS_MODE | float64 | 760 (0.25%) | 156061 (50.75%) | 0 (0.00%) | 976 (0.32%) | 0.0525 | 0.0840 | 0.1439 | 151450.0 | 1.0000e+00 | 1.1423e-01 | 0.0000e+00 | 0.1079 | NaN | 0.1513 | NaN | NaN | NaN | 0.2258 | 0.0641 | 0.084 | 0.105 | 0.1859 |
BASEMENTAREA_MODE | float64 | 3841 (1.25%) | 179943 (58.52%) | 0 (0.00%) | 16598 (5.40%) | 0.0407 | 0.0746 | 0.1124 | 127568.0 | 1.0000e+00 | 8.7543e-02 | 0.0000e+00 | 0.0843 | NaN | 0.1028 | NaN | NaN | NaN | 0.0806 | 0.0785 | 0.0818 | NaN | 0.1372 |
YEARS_BEGINEXPLUATATION_MODE | float64 | 221 (0.07%) | 150007 (48.78%) | 0 (0.00%) | 142 (0.05%) | 0.9767 | 0.9816 | 0.9866 | 157504.0 | 1.0000e+00 | 9.7707e-01 | 0.0000e+00 | 0.0646 | 0.9856 | 0.9871 | NaN | NaN | NaN | 0.9826 | 0.9831 | 0.9786 | 0.9772 | 0.9861 |
YEARS_BUILD_MODE | float64 | 154 (0.05%) | 204488 (66.50%) | 0 (0.00%) | 103 (0.03%) | 0.6994 | 0.7648 | 0.8236 | 103023.0 | 1.0000e+00 | 7.5964e-01 | 0.0000e+00 | 0.1101 | NaN | 0.8301 | NaN | NaN | NaN | NaN | 0.7779 | 0.719 | 0.6994 | 0.8171 |
COMMONAREA_MODE | float64 | 3128 (1.02%) | 214865 (69.87%) | 0 (0.00%) | 9690 (3.15%) | 0.0072 | 0.0190 | 0.0490 | 92646.0 | 1.0000e+00 | 4.2553e-02 | 0.0000e+00 | 0.0744 | NaN | 0.0897 | NaN | NaN | NaN | NaN | NaN | 0.008 | NaN | 0.0382 |
ELEVATORS_MODE | float64 | 26 (0.01%) | 163891 (53.30%) | 0 (0.00%) | 89498 (29.10%) | 0.0000 | 0.0000 | 0.1208 | 143620.0 | 1.0000e+00 | 7.4490e-02 | 0.0000e+00 | 0.1323 | 0.0806 | 0.1611 | NaN | NaN | NaN | 0.0806 | 0 | 0 | NaN | 0.2014 |
ENTRANCES_MODE | float64 | 30 (0.01%) | 154828 (50.35%) | 0 (0.00%) | 387 (0.13%) | 0.0690 | 0.1379 | 0.2069 | 152683.0 | 1.0000e+00 | 1.4519e-01 | 0.0000e+00 | 0.1010 | 0.069 | 0.1379 | NaN | NaN | NaN | 0.0345 | 0.1379 | 0.1379 | 0.2069 | 0.1724 |
FLOORSMAX_MODE | float64 | 25 (0.01%) | 153020 (49.76%) | 0 (0.00%) | 3415 (1.11%) | 0.1667 | 0.1667 | 0.3333 | 154491.0 | 1.0000e+00 | 2.2232e-01 | 0.0000e+00 | 0.1437 | 0.3333 | 0.3333 | NaN | NaN | NaN | 0.3333 | 0.1667 | 0.1667 | 0.1667 | 0.3333 |
FLOORSMIN_MODE | float64 | 25 (0.01%) | 208642 (67.85%) | 0 (0.00%) | 2517 (0.82%) | 0.0833 | 0.2083 | 0.3750 | 98869.0 | 1.0000e+00 | 2.2806e-01 | 0.0000e+00 | 0.1612 | NaN | 0.375 | NaN | NaN | NaN | NaN | NaN | 0.2083 | NaN | 0.375 |
LANDAREA_MODE | float64 | 3563 (1.16%) | 182590 (59.38%) | 0 (0.00%) | 17453 (5.68%) | 0.0166 | 0.0458 | 0.0841 | 124921.0 | 1.0000e+00 | 6.4958e-02 | 0.0000e+00 | 0.0818 | NaN | 0.1153 | NaN | NaN | NaN | 0.0932 | 0.0155 | 0.0207 | NaN | 0.1266 |
LIVINGAPARTMENTS_MODE | float64 | 736 (0.24%) | 210199 (68.35%) | 0 (0.00%) | 519 (0.17%) | 0.0542 | 0.0771 | 0.1313 | 97312.0 | 1.0000e+00 | 1.0564e-01 | 0.0000e+00 | 0.0979 | NaN | 0.1322 | NaN | NaN | NaN | NaN | 0.0551 | 0.0735 | 0.0882 | 0.1625 |
LIVINGAREA_MODE | float64 | 5301 (1.72%) | 154350 (50.19%) | 0 (0.00%) | 444 (0.14%) | 0.0427 | 0.0731 | 0.1252 | 153161.0 | 1.0000e+00 | 1.0598e-01 | 0.0000e+00 | 0.1118 | 0.077 | 0.0953 | NaN | NaN | NaN | 0.0606 | 0.0579 | 0.0733 | 0.0876 | 0.1901 |
NONLIVINGAPARTMENTS_MODE | float64 | 167 (0.05%) | 213514 (69.43%) | 0 (0.00%) | 59255 (19.27%) | 0.0000 | 0.0000 | 0.0039 | 93997.0 | 1.0000e+00 | 8.0764e-03 | 0.0000e+00 | 0.0463 | NaN | 0 | NaN | NaN | NaN | NaN | 0.0039 | 0 | 0.0156 | 0 |
NONLIVINGAREA_MODE | float64 | 3327 (1.08%) | 169682 (55.18%) | 0 (0.00%) | 67126 (21.83%) | 0.0000 | 0.0011 | 0.0231 | 137829.0 | 1.0000e+00 | 2.7022e-02 | 0.0000e+00 | 0.0703 | NaN | 0 | NaN | NaN | NaN | 0.2373 | 0.0199 | 0 | 0.0136 | 0.0023 |
APARTMENTS_MEDI | float64 | 1148 (0.37%) | 156061 (50.75%) | 0 (0.00%) | 771 (0.25%) | 0.0583 | 0.0864 | 0.1489 | 151450.0 | 1.0000e+00 | 1.1785e-01 | 0.0000e+00 | 0.1091 | NaN | 0.1499 | NaN | NaN | NaN | 0.2238 | 0.0635 | 0.0833 | 0.1041 | 0.1842 |
BASEMENTAREA_MEDI | float64 | 3772 (1.23%) | 179943 (58.52%) | 0 (0.00%) | 14991 (4.87%) | 0.0437 | 0.0758 | 0.1116 | 127568.0 | 1.0000e+00 | 8.7955e-02 | 0.0000e+00 | 0.0822 | NaN | 0.0991 | NaN | NaN | NaN | 0.0776 | 0.0756 | 0.0788 | NaN | 0.1322 |
YEARS_BEGINEXPLUATATION_MEDI | float64 | 245 (0.08%) | 150007 (48.78%) | 0 (0.00%) | 548 (0.18%) | 0.9767 | 0.9816 | 0.9866 | 157504.0 | 1.0000e+00 | 9.7775e-01 | 0.0000e+00 | 0.0599 | 0.9856 | 0.9871 | NaN | NaN | NaN | 0.9826 | 0.9831 | 0.9786 | 0.9771 | 0.9861 |
YEARS_BUILD_MEDI | float64 | 151 (0.05%) | 204488 (66.50%) | 0 (0.00%) | 101 (0.03%) | 0.6914 | 0.7585 | 0.8256 | 103023.0 | 1.0000e+00 | 7.5575e-01 | 0.0000e+00 | 0.1121 | NaN | 0.8256 | NaN | NaN | NaN | NaN | 0.7719 | 0.7115 | 0.6914 | 0.8121 |
COMMONAREA_MEDI | float64 | 3202 (1.04%) | 214865 (69.87%) | 0 (0.00%) | 8691 (2.83%) | 0.0079 | 0.0208 | 0.0513 | 92646.0 | 1.0000e+00 | 4.4595e-02 | 0.0000e+00 | 0.0761 | NaN | 0.0895 | NaN | NaN | NaN | NaN | NaN | 0.008 | NaN | 0.0381 |
ELEVATORS_MEDI | float64 | 46 (0.01%) | 163891 (53.30%) | 0 (0.00%) | 87026 (28.30%) | 0.0000 | 0.0000 | 0.1200 | 143620.0 | 1.0000e+00 | 7.8078e-02 | 0.0000e+00 | 0.1345 | 0.08 | 0.16 | NaN | NaN | NaN | 0.08 | 0 | 0 | NaN | 0.2 |
ENTRANCES_MEDI | float64 | 46 (0.01%) | 154828 (50.35%) | 0 (0.00%) | 329 (0.11%) | 0.0690 | 0.1379 | 0.2069 | 152683.0 | 1.0000e+00 | 1.4921e-01 | 0.0000e+00 | 0.1004 | 0.069 | 0.1379 | NaN | NaN | NaN | 0.0345 | 0.1379 | 0.1379 | 0.2069 | 0.1724 |
FLOORSMAX_MEDI | float64 | 49 (0.02%) | 153020 (49.76%) | 0 (0.00%) | 2995 (0.97%) | 0.1667 | 0.1667 | 0.3333 | 154491.0 | 1.0000e+00 | 2.2590e-01 | 0.0000e+00 | 0.1451 | 0.3333 | 0.3333 | NaN | NaN | NaN | 0.3333 | 0.1667 | 0.1667 | 0.1667 | 0.3333 |
FLOORSMIN_MEDI | float64 | 47 (0.02%) | 208642 (67.85%) | 0 (0.00%) | 2351 (0.76%) | 0.0833 | 0.2083 | 0.3750 | 98869.0 | 1.0000e+00 | 2.3162e-01 | 0.0000e+00 | 0.1619 | NaN | 0.375 | NaN | NaN | NaN | NaN | NaN | 0.2083 | NaN | 0.375 |
LANDAREA_MEDI | float64 | 3560 (1.16%) | 182590 (59.38%) | 0 (0.00%) | 15919 (5.18%) | 0.0187 | 0.0487 | 0.0868 | 124921.0 | 1.0000e+00 | 6.7169e-02 | 0.0000e+00 | 0.0822 | NaN | 0.1147 | NaN | NaN | NaN | 0.0927 | 0.0154 | 0.0206 | NaN | 0.126 |
LIVINGAPARTMENTS_MEDI | float64 | 1097 (0.36%) | 210199 (68.35%) | 0 (0.00%) | 433 (0.14%) | 0.0513 | 0.0761 | 0.1231 | 97312.0 | 1.0000e+00 | 1.0195e-01 | 0.0000e+00 | 0.0936 | NaN | 0.1231 | NaN | NaN | NaN | NaN | 0.0513 | 0.0684 | 0.0821 | 0.1513 |
LIVINGAREA_MEDI | float64 | 5281 (1.72%) | 154350 (50.19%) | 0 (0.00%) | 299 (0.10%) | 0.0457 | 0.0749 | 0.1303 | 153161.0 | 1.0000e+00 | 1.0861e-01 | 0.0000e+00 | 0.1123 | 0.0752 | 0.0931 | NaN | NaN | NaN | 0.0592 | 0.0566 | 0.0716 | 0.0856 | 0.1857 |
NONLIVINGAPARTMENTS_MEDI | float64 | 214 (0.07%) | 213514 (69.43%) | 0 (0.00%) | 56097 (18.24%) | 0.0000 | 0.0000 | 0.0039 | 93997.0 | 1.0000e+00 | 8.6510e-03 | 0.0000e+00 | 0.0474 | NaN | 0 | NaN | NaN | NaN | NaN | 0.0039 | 0 | 0.0155 | 0 |
NONLIVINGAREA_MEDI | float64 | 3323 (1.08%) | 169682 (55.18%) | 0 (0.00%) | 60954 (19.82%) | 0.0000 | 0.0031 | 0.0266 | 137829.0 | 1.0000e+00 | 2.8236e-02 | 0.0000e+00 | 0.0702 | NaN | 0 | NaN | NaN | NaN | 0.2289 | 0.0192 | 0 | 0.0131 | 0.0022 |
FONDKAPREMONT_MODE | object | 4 (0.00%) | 210295 (68.39%) | 0 (0.00%) | 0 (0.00%) | 0.0000 | 0.0000 | 0.0000 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | NaN | reg oper account | NaN | NaN | NaN | NaN | reg oper spec account | reg oper account | reg oper account | reg oper account |
HOUSETYPE_MODE | object | 3 (0.00%) | 154297 (50.18%) | 0 (0.00%) | 0 (0.00%) | 0.0000 | 0.0000 | 0.0000 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | NaN | block of flats | NaN | NaN | NaN | block of flats | block of flats | block of flats | block of flats | block of flats |
TOTALAREA_MODE | float64 | 5116 (1.66%) | 148431 (48.27%) | 0 (0.00%) | 582 (0.19%) | 0.0412 | 0.0688 | 0.1276 | 159080.0 | 1.0000e+00 | 1.0255e-01 | 0.0000e+00 | 0.1075 | 0.0581 | 0.1206 | NaN | NaN | NaN | 0.0945 | 0.0475 | 0.0574 | 0.0689 | 0.1644 |
WALLSMATERIAL_MODE | object | 7 (0.00%) | 156341 (50.84%) | 0 (0.00%) | 0 (0.00%) | 0.0000 | 0.0000 | 0.0000 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | NaN | Panel | NaN | NaN | NaN | Stone, brick | Stone, brick | Panel | Stone, brick | Panel |
EMERGENCYSTATE_MODE | object | 2 (0.00%) | 145755 (47.40%) | 0 (0.00%) | 0 (0.00%) | 0.0000 | 0.0000 | 0.0000 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | No | No | NaN | NaN | NaN | No | No | No | No | No |
OBS_30_CNT_SOCIAL_CIRCLE | float64 | 33 (0.01%) | 1021 (0.33%) | 0 (0.00%) | 163910 (53.30%) | 0.0000 | 0.0000 | 2.0000 | 306490.0 | 3.4800e+02 | 1.4222e+00 | 0.0000e+00 | 2.4010 | 0 | 2 | 1 | 0 | 0 | 1 | 2 | 3 | 9 | 0 |
DEF_30_CNT_SOCIAL_CIRCLE | float64 | 10 (0.00%) | 1021 (0.33%) | 0 (0.00%) | 271324 (88.23%) | 0.0000 | 0.0000 | 0.0000 | 306490.0 | 3.4000e+01 | 1.4342e-01 | 0.0000e+00 | 0.4467 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 0 |
OBS_60_CNT_SOCIAL_CIRCLE | float64 | 33 (0.01%) | 1021 (0.33%) | 0 (0.00%) | 164666 (53.55%) | 0.0000 | 0.0000 | 2.0000 | 306490.0 | 3.4400e+02 | 1.4053e+00 | 0.0000e+00 | 2.3798 | 0 | 2 | 1 | 0 | 0 | 1 | 2 | 3 | 9 | 0 |
DEF_60_CNT_SOCIAL_CIRCLE | float64 | 9 (0.00%) | 1021 (0.33%) | 0 (0.00%) | 280721 (91.29%) | 0.0000 | 0.0000 | 0.0000 | 306490.0 | 2.4000e+01 | 1.0005e-01 | 0.0000e+00 | 0.3623 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 |
DAYS_LAST_PHONE_CHANGE | float64 | 3773 (1.23%) | 1 (0.00%) | 269838 (87.75%) | 37672 (12.25%) | -1570.0000 | -757.0000 | -274.0000 | 307510.0 | 0.0000e+00 | -9.6286e+02 | -4.2920e+03 | 826.8085 | -3143 | -2 | -1523 | -1224 | 0 | -201 | -1128 | -2959 | -1634 | -1258 |
FLAG_DOCUMENT_2 | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 307498 (100.00%) | 0.0000 | 0.0000 | 0.0000 | 307511.0 | 1.0000e+00 | 4.2275e-05 | 0.0000e+00 | 0.0065 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
FLAG_DOCUMENT_3 | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 89171 (29.00%) | 0.0000 | 1.0000 | 1.0000 | 307511.0 | 1.0000e+00 | 7.1002e-01 | 0.0000e+00 | 0.4538 | 1 | 1 | 1 | 1 | 1 | 0 | 1 | 1 | 1 | 1 |
FLAG_DOCUMENT_4 | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 307486 (99.99%) | 0.0000 | 0.0000 | 0.0000 | 307511.0 | 1.0000e+00 | 8.1298e-05 | 0.0000e+00 | 0.0090 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
FLAG_DOCUMENT_5 | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 302863 (98.49%) | 0.0000 | 0.0000 | 0.0000 | 307511.0 | 1.0000e+00 | 1.5115e-02 | 0.0000e+00 | 0.1220 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
FLAG_DOCUMENT_6 | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 280433 (91.19%) | 0.0000 | 0.0000 | 0.0000 | 307511.0 | 1.0000e+00 | 8.8055e-02 | 0.0000e+00 | 0.2834 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 |
FLAG_DOCUMENT_7 | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 307452 (99.98%) | 0.0000 | 0.0000 | 0.0000 | 307511.0 | 1.0000e+00 | 1.9186e-04 | 0.0000e+00 | 0.0139 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
FLAG_DOCUMENT_8 | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 282487 (91.86%) | 0.0000 | 0.0000 | 0.0000 | 307511.0 | 1.0000e+00 | 8.1376e-02 | 0.0000e+00 | 0.2734 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
FLAG_DOCUMENT_9 | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 306313 (99.61%) | 0.0000 | 0.0000 | 0.0000 | 307511.0 | 1.0000e+00 | 3.8958e-03 | 0.0000e+00 | 0.0623 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
FLAG_DOCUMENT_10 | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 307504 (100.00%) | 0.0000 | 0.0000 | 0.0000 | 307511.0 | 1.0000e+00 | 2.2763e-05 | 0.0000e+00 | 0.0048 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
FLAG_DOCUMENT_11 | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 306308 (99.61%) | 0.0000 | 0.0000 | 0.0000 | 307511.0 | 1.0000e+00 | 3.9121e-03 | 0.0000e+00 | 0.0624 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
FLAG_DOCUMENT_12 | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 307509 (100.00%) | 0.0000 | 0.0000 | 0.0000 | 307511.0 | 1.0000e+00 | 6.5038e-06 | 0.0000e+00 | 0.0026 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
FLAG_DOCUMENT_13 | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 306427 (99.65%) | 0.0000 | 0.0000 | 0.0000 | 307511.0 | 1.0000e+00 | 3.5251e-03 | 0.0000e+00 | 0.0593 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
FLAG_DOCUMENT_14 | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 306608 (99.71%) | 0.0000 | 0.0000 | 0.0000 | 307511.0 | 1.0000e+00 | 2.9365e-03 | 0.0000e+00 | 0.0541 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
FLAG_DOCUMENT_15 | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 307139 (99.88%) | 0.0000 | 0.0000 | 0.0000 | 307511.0 | 1.0000e+00 | 1.2097e-03 | 0.0000e+00 | 0.0348 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
FLAG_DOCUMENT_16 | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 304458 (99.01%) | 0.0000 | 0.0000 | 0.0000 | 307511.0 | 1.0000e+00 | 9.9281e-03 | 0.0000e+00 | 0.0991 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
FLAG_DOCUMENT_17 | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 307429 (99.97%) | 0.0000 | 0.0000 | 0.0000 | 307511.0 | 1.0000e+00 | 2.6666e-04 | 0.0000e+00 | 0.0163 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
FLAG_DOCUMENT_18 | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 305011 (99.19%) | 0.0000 | 0.0000 | 0.0000 | 307511.0 | 1.0000e+00 | 8.1298e-03 | 0.0000e+00 | 0.0898 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
FLAG_DOCUMENT_19 | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 307328 (99.94%) | 0.0000 | 0.0000 | 0.0000 | 307511.0 | 1.0000e+00 | 5.9510e-04 | 0.0000e+00 | 0.0244 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
FLAG_DOCUMENT_20 | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 307355 (99.95%) | 0.0000 | 0.0000 | 0.0000 | 307511.0 | 1.0000e+00 | 5.0730e-04 | 0.0000e+00 | 0.0225 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
FLAG_DOCUMENT_21 | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 307408 (99.97%) | 0.0000 | 0.0000 | 0.0000 | 307511.0 | 1.0000e+00 | 3.3495e-04 | 0.0000e+00 | 0.0183 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
AMT_REQ_CREDIT_BUREAU_HOUR | float64 | 5 (0.00%) | 41519 (13.50%) | 0 (0.00%) | 264366 (85.97%) | 0.0000 | 0.0000 | 0.0000 | 265992.0 | 4.0000e+00 | 6.4024e-03 | 0.0000e+00 | 0.0838 | 0 | 0 | 0 | NaN | 0 | 0 | NaN | 0 | 0 | 0 |
AMT_REQ_CREDIT_BUREAU_DAY | float64 | 9 (0.00%) | 41519 (13.50%) | 0 (0.00%) | 264503 (86.01%) | 0.0000 | 0.0000 | 0.0000 | 265992.0 | 9.0000e+00 | 7.0002e-03 | 0.0000e+00 | 0.1108 | 0 | 0 | 0 | NaN | 0 | 0 | NaN | 0 | 0 | 0 |
AMT_REQ_CREDIT_BUREAU_WEEK | float64 | 9 (0.00%) | 41519 (13.50%) | 0 (0.00%) | 257456 (83.72%) | 0.0000 | 0.0000 | 0.0000 | 265992.0 | 8.0000e+00 | 3.4362e-02 | 0.0000e+00 | 0.2047 | 0 | 0 | 0 | NaN | 0 | 0 | NaN | 0 | 0 | 0 |
AMT_REQ_CREDIT_BUREAU_MON | float64 | 24 (0.01%) | 41519 (13.50%) | 0 (0.00%) | 222233 (72.27%) | 0.0000 | 0.0000 | 0.0000 | 265992.0 | 2.7000e+01 | 2.6740e-01 | 0.0000e+00 | 0.9160 | 0 | 0 | 0 | NaN | 0 | 0 | NaN | 0 | 0 | 0 |
AMT_REQ_CREDIT_BUREAU_QRT | float64 | 11 (0.00%) | 41519 (13.50%) | 0 (0.00%) | 215417 (70.05%) | 0.0000 | 0.0000 | 0.0000 | 265992.0 | 2.6100e+02 | 2.6547e-01 | 0.0000e+00 | 0.7941 | 0 | 0 | 0 | NaN | 1 | 0 | NaN | 0 | 1 | 0 |
AMT_REQ_CREDIT_BUREAU_YEAR | float64 | 25 (0.01%) | 41519 (13.50%) | 0 (0.00%) | 71801 (23.35%) | 0.0000 | 1.0000 | 3.0000 | 265992.0 | 2.5000e+01 | 1.9000e+00 | 0.0000e+00 | 1.8693 | 1 | 0 | 5 | NaN | 1 | 3 | NaN | 1 | 1 | 1 |
Exploring bureau.csv ('Total records:', 1716428) ('Total columns:', 17)
sub_type | n_distinct | n_miss | n_negative | n_zeros | 25% | 50% | 75% | count | max | mean | min | std | sample_0 | sample_1 | sample_2 | sample_3 | sample_4 | sample_5 | sample_6 | sample_7 | sample_8 | sample_9 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
name | |||||||||||||||||||||||
SK_ID_CURR | int64 | 305811 (17.82%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 1.8887e+05 | 278055.0 | 3.6743e+05 | 1716428.0 | 4.5626e+05 | 2.7821e+05 | 1.0000e+05 | 1.0294e+05 | 226678 | 158734 | 202284 | 275757 | 308924 | 298539 | 220126 | 180625 | 152418 | 134343 |
SK_ID_BUREAU | int64 | 1716428 (100.00%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 5.4640e+06 | 5926303.5 | 6.3857e+06 | 1716428.0 | 6.8435e+06 | 5.9244e+06 | 5.0000e+06 | 5.3227e+05 | 6173729 | 6281010 | 6584010 | 6680033 | 5347959 | 5746640 | 6356593 | 6387149 | 6351262 | 5829930 |
CREDIT_ACTIVE | object | 4 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0.0000e+00 | 0.0 | 0.0000e+00 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | Closed | Closed | Closed | Active | Closed | Closed | Closed | Closed | Active | Active |
CREDIT_CURRENCY | object | 4 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0.0000e+00 | 0.0 | 0.0000e+00 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | currency 1 | currency 1 | currency 1 | currency 1 | currency 1 | currency 1 | currency 1 | currency 1 | currency 1 | currency 1 |
DAYS_CREDIT | int64 | 2923 (0.17%) | 0 (0.00%) | 1716403 (100.00%) | 25 (0.00%) | -1.6660e+03 | -987.0 | -4.7400e+02 | 1716428.0 | 0.0000e+00 | -1.1421e+03 | -2.9220e+03 | 7.9516e+02 | -1467 | -2507 | -643 | -924 | -304 | -711 | -2742 | -405 | -1615 | -16 |
CREDIT_DAY_OVERDUE | int64 | 942 (0.05%) | 0 (0.00%) | 0 (0.00%) | 1712211 (99.75%) | 0.0000e+00 | 0.0 | 0.0000e+00 | 1716428.0 | 2.7920e+03 | 8.1817e-01 | 0.0000e+00 | 3.6544e+01 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
DAYS_CREDIT_ENDDATE | float64 | 14096 (0.82%) | 105553 (6.15%) | 1007389 (58.69%) | 883 (0.05%) | -1.1380e+03 | -330.0 | 4.7400e+02 | 1610875.0 | 3.1199e+04 | 5.1052e+02 | -4.2060e+04 | 4.9942e+03 | -676 | -2202 | -97 | 163 | NaN | -619 | -2374 | 326 | 955 | 1068 |
DAYS_ENDDATE_FACT | float64 | 2917 (0.17%) | 633653 (36.92%) | 1082711 (63.08%) | 64 (0.00%) | -1.4890e+03 | -897.0 | -4.2500e+02 | 1082775.0 | 0.0000e+00 | -1.0174e+03 | -4.2023e+04 | 7.1401e+02 | -676 | -2230 | -97 | NaN | -279 | -619 | -2374 | -160 | NaN | NaN |
AMT_CREDIT_MAX_OVERDUE | float64 | 68251 (3.98%) | 1124488 (65.51%) | 0 (0.00%) | 470650 (27.42%) | 0.0000e+00 | 0.0 | 0.0000e+00 | 591940.0 | 1.1599e+08 | 3.8254e+03 | 0.0000e+00 | 2.0603e+05 | NaN | 0 | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
CNT_CREDIT_PROLONG | int64 | 10 (0.00%) | 0 (0.00%) | 0 (0.00%) | 1707314 (99.47%) | 0.0000e+00 | 0.0 | 0.0000e+00 | 1716428.0 | 9.0000e+00 | 6.4104e-03 | 0.0000e+00 | 9.6224e-02 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
AMT_CREDIT_SUM | float64 | 236708 (13.79%) | 13 (0.00%) | 0 (0.00%) | 66582 (3.88%) | 5.1300e+04 | 125518.5 | 3.1500e+05 | 1716415.0 | 5.8500e+08 | 3.5499e+05 | 0.0000e+00 | 1.1498e+06 | 1.114e+05 | 4.5e+04 | 2.378e+05 | 4.5e+05 | 2.925e+04 | 1.858e+04 | 6.75e+05 | 9.713e+04 | 2.7e+04 | 3.6e+04 |
AMT_CREDIT_SUM_DEBT | float64 | 226537 (13.20%) | 257669 (15.01%) | 8418 (0.49%) | 1016434 (59.22%) | 0.0000e+00 | 0.0 | 4.0154e+04 | 1458759.0 | 1.7010e+08 | 1.3709e+05 | -4.7056e+06 | 6.7740e+05 | 0 | 0 | NaN | 6.44e+04 | 0 | 0 | 0 | 0 | 2.885e+04 | 3.502e+04 |
AMT_CREDIT_SUM_LIMIT | float64 | 51726 (3.01%) | 591780 (34.48%) | 351 (0.02%) | 1050142 (61.18%) | 0.0000e+00 | 0.0 | 0.0000e+00 | 1124648.0 | 4.7056e+06 | 6.2295e+03 | -5.8641e+05 | 4.5032e+04 | NaN | 0 | NaN | 0 | NaN | 0 | 0 | NaN | NaN | 0 |
AMT_CREDIT_SUM_OVERDUE | float64 | 1616 (0.09%) | 0 (0.00%) | 0 (0.00%) | 1712270 (99.76%) | 0.0000e+00 | 0.0 | 0.0000e+00 | 1716428.0 | 3.7567e+06 | 3.7913e+01 | 0.0000e+00 | 5.9377e+03 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
CREDIT_TYPE | object | 15 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0.0000e+00 | 0.0 | 0.0000e+00 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | Consumer credit | Consumer credit | Consumer credit | Consumer credit | Microloan | Consumer credit | Consumer credit | Consumer credit | Credit card | Credit card |
DAYS_CREDIT_UPDATE | int64 | 2982 (0.17%) | 0 (0.00%) | 1715806 (99.96%) | 605 (0.04%) | -9.0800e+02 | -395.0 | -3.3000e+01 | 1716428.0 | 3.7200e+02 | -5.9375e+02 | -4.1947e+04 | 7.2075e+02 | -676 | -1535 | -92 | -8 | -279 | -601 | -1683 | -19 | -30 | -5 |
AMT_ANNUITY | float64 | 40321 (2.35%) | 1226791 (71.47%) | 0 (0.00%) | 256915 (14.97%) | 0.0000e+00 | 0.0 | 1.3500e+04 | 489637.0 | 1.1845e+08 | 1.5713e+04 | 0.0000e+00 | 3.2583e+05 | NaN | NaN | NaN | NaN | NaN | NaN | 0 | NaN | 4.076e+04 | 0 |
Exploring bureau_balance.csv ('Total records:', 27299925) ('Total columns:', 3)
sub_type | n_distinct | n_miss | n_negative | n_zeros | 25% | 50% | 75% | count | max | mean | min | std | sample_0 | sample_1 | sample_2 | sample_3 | sample_4 | sample_5 | sample_6 | sample_7 | sample_8 | sample_9 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
name | |||||||||||||||||||||||
SK_ID_BUREAU | int64 | 817395 (2.99%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 5730933.0 | 6070821.0 | 6431951.0 | 2.7300e+07 | 6842888.0 | 6.0363e+06 | 5001709.0 | 492348.8569 | 5162830 | 5115417 | 5999691 | 5898774 | 5797891 | 6492595 | 6809852 | 6053213 | 6169803 | 6686363 |
MONTHS_BALANCE | int64 | 97 (0.00%) | 0 (0.00%) | 26688960 (97.76%) | 610965 (2.24%) | -46.0 | -25.0 | -11.0 | 2.7300e+07 | 0.0 | -3.0742e+01 | -96.0 | 23.8645 | -26 | -39 | -69 | -25 | -36 | -1 | -43 | -27 | -15 | -30 |
STATUS | object | 8 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0.0 | 0.0 | 0.0 | 0.0000e+00 | 0.0 | 0.0000e+00 | 0.0 | 0.0000 | X | 1 | X | X | C | C | 0 | C | C | 0 |
Exploring credit_card_balance.csv ('Total records:', 3840312) ('Total columns:', 23)
sub_type | n_distinct | n_miss | n_negative | n_zeros | 25% | 50% | 75% | count | max | mean | min | std | sample_0 | sample_1 | sample_2 | sample_3 | sample_4 | sample_5 | sample_6 | sample_7 | sample_8 | sample_9 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
name | |||||||||||||||||||||||
SK_ID_PREV | int64 | 104307 (2.72%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 1.4344e+06 | 1897122.0 | 2.3693e+06 | 3840312.0 | 2.8435e+06 | 1.9045e+06 | 1.0000e+06 | 536469.4706 | 2033976 | 1298413 | 1590798 | 1979274 | 1903431 | 2022496 | 2498831 | 1235207 | 2837796 | 2399399 |
SK_ID_CURR | int64 | 103558 (2.70%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 1.8952e+05 | 278396.0 | 3.6758e+05 | 3840312.0 | 4.5625e+05 | 2.7832e+05 | 1.0001e+05 | 102704.4751 | 379258 | 281213 | 422598 | 393320 | 223935 | 240743 | 167235 | 359955 | 102048 | 387413 |
MONTHS_BALANCE | int64 | 96 (0.00%) | 0 (0.00%) | 3840312 (100.00%) | 0 (0.00%) | -5.5000e+01 | -28.0 | -1.1000e+01 | 3840312.0 | -1.0000e+00 | -3.4522e+01 | -9.6000e+01 | 26.6678 | -6 | -68 | -5 | -1 | -41 | -60 | -2 | -71 | -26 | -65 |
AMT_BALANCE | float64 | 1347904 (35.10%) | 0 (0.00%) | 2345 (0.06%) | 2156420 (56.15%) | 0.0000e+00 | 0.0 | 8.9047e+04 | 3840312.0 | 1.5059e+06 | 5.8300e+04 | -4.2025e+05 | 106307.0310 | 4.221e+04 | 0 | 0 | 0 | 1.817e+05 | 0 | 1.879e+05 | 0 | 0 | 1.717e+04 |
AMT_CREDIT_LIMIT_ACTUAL | int64 | 181 (0.00%) | 0 (0.00%) | 0 (0.00%) | 753823 (19.63%) | 4.5000e+04 | 112500.0 | 1.8000e+05 | 3840312.0 | 1.3500e+06 | 1.5381e+05 | 0.0000e+00 | 165145.6995 | 225000 | 67500 | 135000 | 0 | 180000 | 0 | 180000 | 0 | 90000 | 90000 |
AMT_DRAWINGS_ATM_CURRENT | float64 | 2267 (0.06%) | 749816 (19.52%) | 1 (0.00%) | 2665718 (69.41%) | 0.0000e+00 | 0.0 | 0.0000e+00 | 3090496.0 | 2.1150e+06 | 5.9613e+03 | -6.8273e+03 | 28225.6886 | 0 | 0 | NaN | 0 | 9000 | 0 | 2250 | 0 | 0 | 0 |
AMT_DRAWINGS_CURRENT | float64 | 187005 (4.87%) | 0 (0.00%) | 3 (0.00%) | 3223443 (83.94%) | 0.0000e+00 | 0.0 | 0.0000e+00 | 3840312.0 | 2.2871e+06 | 7.4334e+03 | -6.2116e+03 | 33846.0773 | 2601 | 0 | 0 | 0 | 9000 | 0 | 2250 | 0 | 0 | 0 |
AMT_DRAWINGS_OTHER_CURRENT | float64 | 1832 (0.05%) | 749816 (19.52%) | 0 (0.00%) | 3078163 (80.15%) | 0.0000e+00 | 0.0 | 0.0000e+00 | 3090496.0 | 1.5298e+06 | 2.8817e+02 | 0.0000e+00 | 8201.9893 | 0 | 0 | NaN | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
AMT_DRAWINGS_POS_CURRENT | float64 | 168748 (4.39%) | 749816 (19.52%) | 0 (0.00%) | 2825595 (73.58%) | 0.0000e+00 | 0.0 | 0.0000e+00 | 3090496.0 | 2.2393e+06 | 2.9688e+03 | 0.0000e+00 | 20796.8870 | 2601 | 0 | NaN | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
AMT_INST_MIN_REGULARITY | float64 | 312266 (8.13%) | 305236 (7.95%) | 0 (0.00%) | 1928864 (50.23%) | 0.0000e+00 | 0.0 | 6.6339e+03 | 3535076.0 | 2.0288e+05 | 3.5402e+03 | 0.0000e+00 | 5600.1541 | 2250 | 0 | 0 | 0 | 9000 | 0 | 9338 | 0 | 0 | 4500 |
AMT_PAYMENT_CURRENT | float64 | 163209 (4.25%) | 767988 (20.00%) | 0 (0.00%) | 390507 (10.17%) | 1.5237e+02 | 2702.7 | 9.0000e+03 | 3072324.0 | 4.2892e+06 | 1.0281e+04 | 0.0000e+00 | 36078.0850 | 7200 | 674.9 | NaN | 0 | 9000 | 8.64 | 9450 | 212.4 | 5823 | 4500 |
AMT_PAYMENT_TOTAL_CURRENT | float64 | 182957 (4.76%) | 0 (0.00%) | 0 (0.00%) | 2172223 (56.56%) | 0.0000e+00 | 0.0 | 6.7500e+03 | 3840312.0 | 4.2783e+06 | 7.5889e+03 | 0.0000e+00 | 32005.9878 | 4889 | 0 | 0 | 0 | 9000 | 0 | 9450 | 0 | 0 | 4500 |
AMT_RECEIVABLE_PRINCIPAL | float64 | 1195839 (31.14%) | 0 (0.00%) | 2428 (0.06%) | 2296167 (59.79%) | 0.0000e+00 | 0.0 | 8.5359e+04 | 3840312.0 | 1.4723e+06 | 5.5966e+04 | -4.2331e+05 | 102533.6168 | 4.162e+04 | 0 | 0 | 0 | 1.74e+05 | 0 | 1.796e+05 | 0 | 0 | 1.536e+04 |
AMT_RECIVABLE | float64 | 1338878 (34.86%) | 0 (0.00%) | 109338 (2.85%) | 2113816 (55.04%) | 0.0000e+00 | 0.0 | 8.8899e+04 | 3840312.0 | 1.4933e+06 | 5.8089e+04 | -4.2025e+05 | 105965.3699 | 4.221e+04 | 0 | 0 | 0 | 1.817e+05 | 0 | 1.861e+05 | 0 | 0 | 1.717e+04 |
AMT_TOTAL_RECEIVABLE | float64 | 1339008 (34.87%) | 0 (0.00%) | 109330 (2.85%) | 2113643 (55.04%) | 0.0000e+00 | 0.0 | 8.8915e+04 | 3840312.0 | 1.4933e+06 | 5.8098e+04 | -4.2025e+05 | 105971.8011 | 4.221e+04 | 0 | 0 | 0 | 1.817e+05 | 0 | 1.861e+05 | 0 | 0 | 1.717e+04 |
CNT_DRAWINGS_ATM_CURRENT | float64 | 44 (0.00%) | 749816 (19.52%) | 0 (0.00%) | 2665718 (69.41%) | 0.0000e+00 | 0.0 | 0.0000e+00 | 3090496.0 | 5.1000e+01 | 3.0945e-01 | 0.0000e+00 | 1.1004 | 0 | 0 | NaN | 0 | 2 | 0 | 1 | 0 | 0 | 0 |
CNT_DRAWINGS_CURRENT | int64 | 129 (0.00%) | 0 (0.00%) | 0 (0.00%) | 3229952 (84.11%) | 0.0000e+00 | 0.0 | 0.0000e+00 | 3840312.0 | 1.6500e+02 | 7.0314e-01 | 0.0000e+00 | 3.1903 | 3 | 0 | 0 | 0 | 2 | 0 | 1 | 0 | 0 | 0 |
CNT_DRAWINGS_OTHER_CURRENT | float64 | 11 (0.00%) | 749816 (19.52%) | 0 (0.00%) | 3077688 (80.14%) | 0.0000e+00 | 0.0 | 0.0000e+00 | 3090496.0 | 1.2000e+01 | 4.8125e-03 | 0.0000e+00 | 0.0826 | 0 | 0 | NaN | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
CNT_DRAWINGS_POS_CURRENT | float64 | 133 (0.00%) | 749816 (19.52%) | 0 (0.00%) | 2825594 (73.58%) | 0.0000e+00 | 0.0 | 0.0000e+00 | 3090496.0 | 1.6500e+02 | 5.5948e-01 | 0.0000e+00 | 3.2406 | 3 | 0 | NaN | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
CNT_INSTALMENT_MATURE_CUM | float64 | 121 (0.00%) | 305236 (7.95%) | 0 (0.00%) | 551467 (14.36%) | 4.0000e+00 | 15.0 | 3.2000e+01 | 3535076.0 | 1.2000e+02 | 2.0825e+01 | 0.0000e+00 | 20.0515 | 7 | 33 | 0 | 12 | 56 | 19 | 14 | 9 | 24 | 34 |
NAME_CONTRACT_STATUS | object | 7 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0.0000e+00 | 0.0 | 0.0000e+00 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | Active | Active | Active | Completed | Active | Active | Active | Active | Active | Active |
SK_DPD | int64 | 917 (0.02%) | 0 (0.00%) | 0 (0.00%) | 3686957 (96.01%) | 0.0000e+00 | 0.0 | 0.0000e+00 | 3840312.0 | 3.2600e+03 | 9.2837e+00 | 0.0000e+00 | 97.5157 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
SK_DPD_DEF | int64 | 378 (0.01%) | 0 (0.00%) | 0 (0.00%) | 3750972 (97.67%) | 0.0000e+00 | 0.0 | 0.0000e+00 | 3840312.0 | 3.2600e+03 | 3.3162e-01 | 0.0000e+00 | 21.4792 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
Exploring installments_payments.csv ('Total records:', 13605401) ('Total columns:', 8)
sub_type | n_distinct | n_miss | n_negative | n_zeros | 25% | 50% | 75% | count | max | mean | min | std | sample_0 | sample_1 | sample_2 | sample_3 | sample_4 | sample_5 | sample_6 | sample_7 | sample_8 | sample_9 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
name | |||||||||||||||||||||||
SK_ID_PREV | int64 | 997752 (7.33%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 1.4342e+06 | 1.8965e+06 | 2.3691e+06 | 1.3605e+07 | 2.8435e+06 | 1.9034e+06 | 1000001.0 | 536202.9055 | 1.4343e+06 | 1.6140e+06 | 1.5035e+06 | 2.6746e+06 | 2473148.0 | 1.2894e+06 | 2.1772e+06 | 1.1575e+06 | 1515366.0 | 1767561.0 |
SK_ID_CURR | int64 | 339587 (2.50%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 1.8964e+05 | 2.7868e+05 | 3.6753e+05 | 1.3605e+07 | 4.5626e+05 | 2.7844e+05 | 100001.0 | 102718.3104 | 1.4943e+05 | 1.7820e+05 | 3.7177e+05 | 1.2463e+05 | 355290.0 | 3.6956e+05 | 1.3184e+05 | 1.1488e+05 | 369258.0 | 315860.0 |
NUM_INSTALMENT_VERSION | float64 | 65 (0.00%) | 0 (0.00%) | 0 (0.00%) | 4082498 (30.01%) | 0.0000e+00 | 1.0000e+00 | 1.0000e+00 | 1.3605e+07 | 1.7800e+02 | 8.5664e-01 | 0.0 | 1.0352 | 1.0000e+00 | 1.0000e+00 | 1.0000e+00 | 1.0000e+00 | 0.0 | 1.0000e+00 | 1.0000e+00 | 1.0000e+00 | 2.0 | 1.0 |
NUM_INSTALMENT_NUMBER | int64 | 277 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 4.0000e+00 | 8.0000e+00 | 1.9000e+01 | 1.3605e+07 | 2.7700e+02 | 1.8871e+01 | 1.0 | 26.6641 | 5.0000e+00 | 7.0000e+00 | 8.0000e+00 | 1.0000e+00 | 63.0 | 5.0000e+00 | 3.0000e+00 | 1.0000e+00 | 15.0 | 5.0 |
DAYS_INSTALMENT | float64 | 2922 (0.02%) | 0 (0.00%) | 13605401 (100.00%) | 0 (0.00%) | -1.6540e+03 | -8.1800e+02 | -3.6100e+02 | 1.3605e+07 | -1.0000e+00 | -1.0423e+03 | -2922.0 | 800.9463 | -4.0100e+02 | -2.2580e+03 | -4.1000e+02 | -5.5300e+02 | -1816.0 | -7.7500e+02 | -3.9500e+02 | -6.1600e+02 | -450.0 | -727.0 |
DAYS_ENTRY_PAYMENT | float64 | 3039 (0.02%) | 2905 (0.02%) | 13602496 (99.98%) | 0 (0.00%) | -1.6620e+03 | -8.2700e+02 | -3.7000e+02 | 1.3602e+07 | -1.0000e+00 | -1.0511e+03 | -4921.0 | 800.5859 | -4.1300e+02 | -2.2640e+03 | -4.1200e+02 | -5.5800e+02 | -1829.0 | -7.9100e+02 | -3.9900e+02 | -6.3000e+02 | -466.0 | -735.0 |
AMT_INSTALMENT | float64 | 902539 (6.63%) | 0 (0.00%) | 0 (0.00%) | 290 (0.00%) | 4.2261e+03 | 8.8841e+03 | 1.6710e+04 | 1.3605e+07 | 3.7715e+06 | 1.7051e+04 | 0.0 | 50570.2544 | 1.1093e+04 | 2.4050e+04 | 4.7840e+03 | 2.0124e+04 | 7875.0 | 1.6709e+04 | 1.1969e+04 | 1.2441e+04 | 294150.6 | 10495.8 |
AMT_PAYMENT | float64 | 944235 (6.94%) | 2905 (0.02%) | 0 (0.00%) | 1440 (0.01%) | 3.3983e+03 | 8.1255e+03 | 1.6108e+04 | 1.3602e+07 | 3.7715e+06 | 1.7238e+04 | 0.0 | 54735.7840 | 1.1093e+04 | 2.4050e+04 | 4.7840e+03 | 2.0124e+04 | 7875.0 | 1.6709e+04 | 1.1969e+04 | 1.2441e+04 | 294150.6 | 10495.8 |
Exploring previous_application.csv ('Total records:', 1670214) ('Total columns:', 37)
sub_type | n_distinct | n_miss | n_negative | n_zeros | 25% | 50% | 75% | count | max | mean | min | std | sample_0 | sample_1 | sample_2 | sample_3 | sample_4 | sample_5 | sample_6 | sample_7 | sample_8 | sample_9 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
name | |||||||||||||||||||||||
SK_ID_PREV | int64 | 1670214 (100.00%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 1.4619e+06 | 1.9231e+06 | 2.3843e+06 | 1670214.0 | 2.8454e+06 | 1.9231e+06 | 1.0000e+06 | 532597.9587 | 1092395 | 1252745 | 1426776 | 1649070 | 1937880 | 2786742 | 2369053 | 2100244 | 2751684 | 1685570 |
SK_ID_CURR | int64 | 338857 (20.29%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 1.8933e+05 | 2.7871e+05 | 3.6751e+05 | 1670214.0 | 4.5626e+05 | 2.7836e+05 | 1.0000e+05 | 102814.8238 | 334586 | 307326 | 164677 | 289639 | 316386 | 325443 | 329812 | 151568 | 184899 | 428430 |
NAME_CONTRACT_TYPE | object | 4 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | Revolving loans | Cash loans | Cash loans | Consumer loans | Consumer loans | Cash loans | Consumer loans | Revolving loans | Cash loans | Consumer loans |
AMT_ANNUITY | float64 | 357959 (21.43%) | 372235 (22.29%) | 0 (0.00%) | 1637 (0.10%) | 6.3218e+03 | 1.1250e+04 | 2.0658e+04 | 1297979.0 | 4.1806e+05 | 1.5955e+04 | 0.0000e+00 | 14782.1373 | 2250 | NaN | NaN | 6263 | 7556 | NaN | 1.26e+04 | 2.025e+04 | 2.758e+04 | 1.289e+04 |
AMT_APPLICATION | float64 | 93885 (5.62%) | 0 (0.00%) | 0 (0.00%) | 392402 (23.49%) | 1.8720e+04 | 7.1046e+04 | 1.8036e+05 | 1670214.0 | 6.9052e+06 | 1.7523e+05 | 0.0000e+00 | 292779.7624 | 4.5e+04 | 0 | 0 | 4.364e+04 | 7.308e+04 | 0 | 1.35e+05 | 0 | 4.5e+05 | 1.179e+05 |
AMT_CREDIT | float64 | 86803 (5.20%) | 1 (0.00%) | 0 (0.00%) | 336768 (20.16%) | 2.4160e+04 | 8.0541e+04 | 2.1642e+05 | 1670213.0 | 6.9052e+06 | 1.9611e+05 | 0.0000e+00 | 318574.6165 | 4.5e+04 | 0 | 0 | 5.328e+04 | 7.308e+04 | 0 | 1.35e+05 | 4.05e+05 | 4.916e+05 | 1.146e+05 |
AMT_DOWN_PAYMENT | float64 | 29278 (1.75%) | 895844 (53.64%) | 2 (0.00%) | 369854 (22.14%) | 0.0000e+00 | 1.6380e+03 | 7.7400e+03 | 774370.0 | 3.0600e+06 | 6.6974e+03 | -9.0000e-01 | 20921.4954 | NaN | NaN | NaN | 0 | 0 | NaN | 0 | NaN | NaN | 2.357e+04 |
AMT_GOODS_PRICE | float64 | 93885 (5.62%) | 385515 (23.08%) | 0 (0.00%) | 6869 (0.41%) | 5.0841e+04 | 1.1232e+05 | 2.3400e+05 | 1284699.0 | 6.9052e+06 | 2.2785e+05 | 0.0000e+00 | 315396.5579 | 4.5e+04 | NaN | NaN | 4.364e+04 | 7.308e+04 | NaN | 1.35e+05 | NaN | 4.5e+05 | 1.179e+05 |
WEEKDAY_APPR_PROCESS_START | object | 7 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | WEDNESDAY | FRIDAY | WEDNESDAY | SUNDAY | SATURDAY | FRIDAY | TUESDAY | MONDAY | SATURDAY | FRIDAY |
HOUR_APPR_PROCESS_START | int64 | 24 (0.00%) | 0 (0.00%) | 0 (0.00%) | 109 (0.01%) | 1.0000e+01 | 1.2000e+01 | 1.5000e+01 | 1670214.0 | 2.3000e+01 | 1.2484e+01 | 0.0000e+00 | 3.3340 | 12 | 16 | 11 | 7 | 10 | 16 | 21 | 17 | 13 | 17 |
FLAG_LAST_APPL_PER_CONTRACT | object | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | Y | Y | Y | Y | Y | Y | Y | Y | Y | Y |
NFLAG_LAST_APPL_IN_DAY | int64 | 2 (0.00%) | 0 (0.00%) | 0 (0.00%) | 5900 (0.35%) | 1.0000e+00 | 1.0000e+00 | 1.0000e+00 | 1670214.0 | 1.0000e+00 | 9.9647e-01 | 0.0000e+00 | 0.0593 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 |
RATE_DOWN_PAYMENT | float64 | 207033 (12.40%) | 895844 (53.64%) | 2 (0.00%) | 369854 (22.14%) | 0.0000e+00 | 5.1605e-02 | 1.0891e-01 | 774370.0 | 1.0000e+00 | 7.9637e-02 | -1.4979e-05 | 0.1078 | NaN | NaN | NaN | 0 | 0 | NaN | 0 | NaN | NaN | 0.1858 |
RATE_INTEREST_PRIMARY | float64 | 148 (0.01%) | 1664263 (99.64%) | 0 (0.00%) | 0 (0.00%) | 1.6072e-01 | 1.8912e-01 | 1.9333e-01 | 5951.0 | 1.0000e+00 | 1.8836e-01 | 3.4781e-02 | 0.0877 | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
RATE_INTEREST_PRIVILEGED | float64 | 25 (0.00%) | 1664263 (99.64%) | 0 (0.00%) | 0 (0.00%) | 7.1564e-01 | 8.3510e-01 | 8.5254e-01 | 5951.0 | 1.0000e+00 | 7.7350e-01 | 3.7315e-01 | 0.1009 | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
NAME_CASH_LOAN_PURPOSE | object | 25 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | XAP | XNA | XNA | XAP | XAP | XNA | XAP | XAP | XNA | XAP |
NAME_CONTRACT_STATUS | object | 4 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | Approved | Canceled | Canceled | Approved | Approved | Refused | Approved | Approved | Approved | Approved |
DAYS_DECISION | int64 | 2922 (0.17%) | 0 (0.00%) | 1670214 (100.00%) | 0 (0.00%) | -1.3000e+03 | -5.8100e+02 | -2.8000e+02 | 1670214.0 | -1.0000e+00 | -8.8068e+02 | -2.9220e+03 | 779.0997 | -212 | -217 | -361 | -545 | -1371 | -561 | -625 | -703 | -775 | -1021 |
NAME_PAYMENT_TYPE | object | 4 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | XNA | XNA | XNA | Cash through the bank | Cash through the bank | XNA | Cash through the bank | XNA | Cash through the bank | Cash through the bank |
CODE_REJECT_REASON | object | 9 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | XAP | XAP | XAP | XAP | XAP | HC | XAP | XAP | XAP | XAP |
NAME_TYPE_SUITE | object | 7 (0.00%) | 820405 (49.12%) | 0 (0.00%) | 0 (0.00%) | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | Unaccompanied | NaN | NaN | NaN | Other_A | NaN | NaN | NaN | Unaccompanied | Unaccompanied |
NAME_CLIENT_TYPE | object | 4 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | Repeater | Repeater | Repeater | Repeater | Repeater | Repeater | New | Repeater | Repeater | Repeater |
NAME_GOODS_CATEGORY | object | 28 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | XNA | XNA | XNA | Audio/Video | Furniture | XNA | Audio/Video | XNA | XNA | Computers |
NAME_PORTFOLIO | object | 5 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | Cards | XNA | XNA | POS | POS | XNA | POS | Cards | Cash | POS |
NAME_PRODUCT_TYPE | object | 3 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | walk-in | XNA | XNA | XNA | XNA | XNA | XNA | x-sell | x-sell | XNA |
CHANNEL_TYPE | object | 8 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | Credit and cash offices | Credit and cash offices | Credit and cash offices | Country-wide | Stone | Credit and cash offices | Country-wide | Country-wide | Credit and cash offices | Regional / Local |
SELLERPLACE_AREA | int64 | 2097 (0.13%) | 0 (0.00%) | 762675 (45.66%) | 60523 (3.62%) | -1.0000e+00 | 3.0000e+00 | 8.2000e+01 | 1670214.0 | 4.0000e+06 | 3.1395e+02 | -1.0000e+00 | 7127.4435 | -1 | -1 | -1 | 1000 | 238 | 0 | 1000 | 154 | -1 | 168 |
NAME_SELLER_INDUSTRY | object | 11 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | XNA | XNA | XNA | Consumer electronics | Furniture | XNA | Consumer electronics | Furniture | XNA | Consumer electronics |
CNT_PAYMENT | float64 | 49 (0.00%) | 372230 (22.29%) | 0 (0.00%) | 144985 (8.68%) | 6.0000e+00 | 1.2000e+01 | 2.4000e+01 | 1297984.0 | 8.4000e+01 | 1.6054e+01 | 0.0000e+00 | 14.5673 | 0 | NaN | NaN | 10 | 12 | NaN | 12 | 0 | 24 | 10 |
NAME_YIELD_GROUP | object | 5 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | XNA | XNA | XNA | middle | middle | XNA | low_normal | XNA | low_normal | low_normal |
PRODUCT_COMBINATION | object | 17 (0.00%) | 346 (0.02%) | 0 (0.00%) | 0 (0.00%) | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0 | 0.0000e+00 | 0.0000e+00 | 0.0000e+00 | 0.0000 | Card Street | Cash | Cash | POS household with interest | POS industry with interest | Cash | POS household with interest | Card X-Sell | Cash X-Sell: low | POS household with interest |
DAYS_FIRST_DRAWING | float64 | 2838 (0.17%) | 673065 (40.30%) | 62705 (3.75%) | 0 (0.00%) | 3.6524e+05 | 3.6524e+05 | 3.6524e+05 | 997149.0 | 3.6524e+05 | 3.4221e+05 | -2.9220e+03 | 88916.1158 | 3.652e+05 | NaN | NaN | 3.652e+05 | 3.652e+05 | NaN | 3.652e+05 | -599 | 3.652e+05 | 3.652e+05 |
DAYS_FIRST_DUE | float64 | 2892 (0.17%) | 673065 (40.30%) | 956504 (57.27%) | 0 (0.00%) | -1.6280e+03 | -8.3100e+02 | -4.1100e+02 | 997149.0 | 3.6524e+05 | 1.3826e+04 | -2.8920e+03 | 72444.8697 | 3.652e+05 | NaN | NaN | -514 | -1322 | NaN | -594 | -553 | -745 | -990 |
DAYS_LAST_DUE_1ST_VERSION | float64 | 4605 (0.28%) | 673065 (40.30%) | 678188 (40.60%) | 705 (0.04%) | -1.2420e+03 | -3.6100e+02 | 1.2900e+02 | 997149.0 | 3.6524e+05 | 3.3768e+04 | -2.8010e+03 | 106857.0348 | 3.652e+05 | NaN | NaN | -244 | -992 | NaN | -264 | 3.652e+05 | -55 | -720 |
DAYS_LAST_DUE | float64 | 2873 (0.17%) | 673065 (40.30%) | 785928 (47.06%) | 0 (0.00%) | -1.3140e+03 | -5.3700e+02 | -7.4000e+01 | 997149.0 | 3.6524e+05 | 7.6582e+04 | -2.8890e+03 | 149647.4151 | 3.652e+05 | NaN | NaN | -364 | -992 | NaN | -324 | 3.652e+05 | -625 | -720 |
DAYS_TERMINATION | float64 | 2830 (0.17%) | 673065 (40.30%) | 771236 (46.18%) | 0 (0.00%) | -1.2700e+03 | -4.9900e+02 | -4.4000e+01 | 997149.0 | 3.6524e+05 | 8.1992e+04 | -2.8740e+03 | 153303.5167 | 3.652e+05 | NaN | NaN | -356 | -985 | NaN | -319 | 3.652e+05 | -612 | -710 |
NFLAG_INSURED_ON_APPROVAL | float64 | 2 (0.00%) | 673065 (40.30%) | 0 (0.00%) | 665527 (39.85%) | 0.0000e+00 | 0.0000e+00 | 1.0000e+00 | 997149.0 | 1.0000e+00 | 3.3257e-01 | 0.0000e+00 | 0.4711 | 0 | NaN | NaN | 0 | 0 | NaN | 0 | 0 | 1 | 0 |
Exploring sample_submission.csv ('Total records:', 48744) ('Total columns:', 2)
sub_type | n_distinct | n_miss | n_negative | n_zeros | 25% | 50% | 75% | count | max | mean | min | std | sample_0 | sample_1 | sample_2 | sample_3 | sample_4 | sample_5 | sample_6 | sample_7 | sample_8 | sample_9 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
name | |||||||||||||||||||||||
SK_ID_CURR | int64 | 48744 (100.00%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 188557.75 | 277549.0 | 367555.5 | 48744.0 | 456250.0 | 277796.6763 | 100001.0 | 103169.5473 | 262887.0 | 279679.0 | 340511.0 | 256663.0 | 261967.0 | 359353.0 | 364403.0 | 423087.0 | 115680.0 | 370913.0 |
TARGET | float64 | 1 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0 (0.00%) | 0.50 | 0.5 | 0.5 | 48744.0 | 0.5 | 0.5000 | 0.5 | 0.0000 | 0.5 | 0.5 | 0.5 | 0.5 | 0.5 | 0.5 | 0.5 | 0.5 | 0.5 | 0.5 |
CPU times: user 6min 36s, sys: 16 s, total: 6min 52s Wall time: 1min 39s
%%time
# save reports
for k, v in ls_report.items():
print("Saving {}".format(k))
ls_report[k].to_csv(os.path.join("reports", "report_{}".format(k)))
Saving previous_application.csv Saving application_test.csv Saving installments_payments.csv Saving sample_submission.csv Saving credit_card_balance.csv Saving bureau.csv Saving application_train.csv Saving POS_CASH_balance.csv Saving bureau_balance.csv CPU times: user 14.3 ms, sys: 8.26 ms, total: 22.6 ms Wall time: 26.1 ms