imports

import sklearn
from sklearn import model_selection

from autogluon.tabular import TabularDataset, TabularPredictor

/home/coco/anaconda3/envs/ag/lib/python3.10/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html
  from .autonotebook import tqdm as notebook_tqdm

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt 
import networkx as nx
import sklearn
import xgboost as xgb

# sklearn
from sklearn import model_selection # split함수이용
from sklearn import ensemble # RF,GBM
from sklearn import metrics
from sklearn.metrics import precision_score, recall_score, f1_score
from sklearn.svm import SVC
from sklearn.ensemble import RandomForestClassifier
from sklearn.naive_bayes import GaussianNB

# gnn
import torch
import torch.nn.functional as F
import torch_geometric
from torch_geometric.nn import GCNConv

# autogluon

def down_sample_textbook(df):
    df_majority = df[df.is_fraud==0].copy()
    df_minority = df[df.is_fraud==1].copy()
    df_maj_dowsampled = sklearn.utils.resample(df_majority, n_samples=len(df_minority), replace=False, random_state=42)
    df_downsampled = pd.concat([df_minority, df_maj_dowsampled])
    return df_downsampled

import pandas as pd

fraudTrain = pd.read_csv("~/Desktop/fraudTrain.csv").iloc[:,1:]

fraudTrain = fraudTrain.assign(trans_date_trans_time= list(map(lambda x: pd.to_datetime(x), fraudTrain.trans_date_trans_time)))
fraudTrain

	trans_date_trans_time	cc_num	merchant	category	amt	first	last	gender	street	city	...	lat	long	city_pop	job	dob	trans_num	unix_time	merch_lat	merch_long	is_fraud
0	2019-01-01 00:00:00	2.703190e+15	fraud_Rippin, Kub and Mann	misc_net	4.97	Jennifer	Banks	F	561 Perry Cove	Moravian Falls	...	36.0788	-81.1781	3495	Psychologist, counselling	1988-03-09	0b242abb623afc578575680df30655b9	1325376018	36.011293	-82.048315	0
1	2019-01-01 00:00:00	6.304230e+11	fraud_Heller, Gutmann and Zieme	grocery_pos	107.23	Stephanie	Gill	F	43039 Riley Greens Suite 393	Orient	...	48.8878	-118.2105	149	Special educational needs teacher	1978-06-21	1f76529f8574734946361c461b024d99	1325376044	49.159047	-118.186462	0
2	2019-01-01 00:00:00	3.885950e+13	fraud_Lind-Buckridge	entertainment	220.11	Edward	Sanchez	M	594 White Dale Suite 530	Malad City	...	42.1808	-112.2620	4154	Nature conservation officer	1962-01-19	a1a22d70485983eac12b5b88dad1cf95	1325376051	43.150704	-112.154481	0
3	2019-01-01 00:01:00	3.534090e+15	fraud_Kutch, Hermiston and Farrell	gas_transport	45.00	Jeremy	White	M	9443 Cynthia Court Apt. 038	Boulder	...	46.2306	-112.1138	1939	Patent attorney	1967-01-12	6b849c168bdad6f867558c3793159a81	1325376076	47.034331	-112.561071	0
4	2019-01-01 00:03:00	3.755340e+14	fraud_Keeling-Crist	misc_pos	41.96	Tyler	Garcia	M	408 Bradley Rest	Doe Hill	...	38.4207	-79.4629	99	Dance movement psychotherapist	1986-03-28	a41d7549acf90789359a9aa5346dcb46	1325376186	38.674999	-78.632459	0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
1048570	2020-03-10 16:07:00	6.011980e+15	fraud_Fadel Inc	health_fitness	77.00	Haley	Wagner	F	05561 Farrell Crescent	Annapolis	...	39.0305	-76.5515	92106	Accountant, chartered certified	1943-05-28	45ecd198c65e81e597db22e8d2ef7361	1362931649	38.779464	-76.317042	0
1048571	2020-03-10 16:07:00	4.839040e+15	fraud_Cremin, Hamill and Reichel	misc_pos	116.94	Meredith	Campbell	F	043 Hanson Turnpike	Hedrick	...	41.1826	-92.3097	1583	Geochemist	1999-06-28	c00ce51c6ebb7657474a77b9e0b51f34	1362931670	41.400318	-92.726724	0
1048572	2020-03-10 16:08:00	5.718440e+11	fraud_O'Connell, Botsford and Hand	home	21.27	Susan	Mills	F	005 Cody Estates	Louisville	...	38.2507	-85.7476	736284	Engineering geologist	1952-04-02	17c9dc8b2a6449ca2473726346e58e6c	1362931711	37.293339	-84.798122	0
1048573	2020-03-10 16:08:00	4.646850e+18	fraud_Thompson-Gleason	health_fitness	9.52	Julia	Bell	F	576 House Crossroad	West Sayville	...	40.7320	-73.1000	4056	Film/video editor	1990-06-25	5ca650881b48a6a38754f841c23b77ab	1362931718	39.773077	-72.213209	0
1048574	2020-03-10 16:08:00	2.283740e+15	fraud_Buckridge PLC	misc_pos	6.81	Shannon	Williams	F	9345 Spencer Junctions Suite 183	Alpharetta	...	34.0770	-84.3033	165556	Prison officer	1997-12-27	8d0a575fe635bbde12f1a2bffc126731	1362931730	33.601468	-83.891921	0

1048575 rows × 22 columns

데이터정리

_df1 = fraudTrain[fraudTrain["is_fraud"] == 0].sample(frac=0.20, random_state=42)
_df2 = fraudTrain[fraudTrain["is_fraud"] == 1]
df02 = pd.concat([_df1,_df2])
df02.shape

(214520, 22)

df50 = down_sample_textbook(df02)
df50.shape

(12012, 22)

df50 = df50.reset_index()

N = len(df50)

df50 = df50[["amt","is_fraud"]]

df50["amt"].mean()

297.4638911088911

df50["amt"].describe()

count    12012.000000
mean       297.463891
std        384.130842
min          1.010000
25%         19.917500
50%         84.680000
75%        468.295000
max      12025.300000
Name: amt, dtype: float64

tr/test

df50_tr,df50_test = sklearn.model_selection.train_test_split(df50, random_state=42)

autogluon

A. 데이터

tr = TabularDataset(df50_tr)
tst = TabularDataset(df50_test)

B. predictor 생성

ㅇㅇㅇㅇㅇㅇㅇㅇ으잉?

predictr = TabularPredictor("is_fraud")

No path specified. Models will be saved in: "AutogluonModels/ag-20231002_072102"

C.적합(fit)

> seed 적

seed = 202250926

predictr.fit(tr,seed=seed)

ValueError: Unknown `.fit` keyword argument specified: 'seed'
Valid kwargs: ['ag_args', 'ag_args_ensemble', 'ag_args_fit', 'auto_stack', 'calibrate', 'excluded_model_types', 'feature_generator', 'feature_prune_kwargs', 'holdout_frac', 'hyperparameter_tune_kwargs', 'included_model_types', 'keep_only_best', 'name_suffix', 'num_bag_folds', 'num_bag_sets', 'num_stack_levels', 'pseudo_data', 'refit_full', 'save_space', 'set_best_to_refit_full', 'unlabeled_data', 'use_bag_holdout', 'verbosity']

predictr.leaderboard()

AssertionError: Predictor is not fit. Call `.fit` before calling `.leaderboard`.

D. 예측(predict)

(tr.is_fraud == predictr.predict(tr)).mean()

0.9102009102009102

(tst.is_fraud == predictr.predict(tst)).mean()

0.8904428904428905

yyhat = predictr.predict(tr)

autogluon이렇게 하는게 맞는감…;;;