Spaces:
Running
Running
Upload 16 files
Browse files- .gitattributes +1 -0
- README.md +5 -7
- data/MercadoLibre Data Scientist Technical Challenge - Dataset.csv +3 -0
- data/processed/selected_features.csv +14 -0
- models/feature_engineering_pipeline.joblib +3 -0
- models/final_pipeline.joblib +3 -0
- notebooks/01-eda.ipynb +0 -0
- notebooks/02-feature_rngineering.ipynb +1293 -0
- notebooks/03-feature_selection.ipynb +837 -0
- notebooks/04-model _training.ipynb +0 -0
- notebooks/__pycache__/utils.cpython-310.pyc +0 -0
- notebooks/logs.log +808 -0
- notebooks/utils.py +29 -0
- requirements.txt +6 -0
- src/__pycache__/utils.cpython-310.pyc +0 -0
- src/app.py +70 -0
- src/utils.py +29 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
data/MercadoLibre[[:space:]]Data[[:space:]]Scientist[[:space:]]Technical[[:space:]]Challenge[[:space:]]-[[:space:]]Dataset.csv filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
@@ -1,13 +1,11 @@
|
|
1 |
---
|
2 |
-
title: Fraud
|
3 |
-
emoji:
|
4 |
-
colorFrom:
|
5 |
colorTo: gray
|
6 |
sdk: gradio
|
7 |
-
sdk_version: 3.
|
8 |
-
app_file: app.py
|
9 |
pinned: false
|
10 |
license: mit
|
11 |
---
|
12 |
-
|
13 |
-
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|
|
|
1 |
---
|
2 |
+
title: Fraud App - MELI
|
3 |
+
emoji: π
|
4 |
+
colorFrom: green
|
5 |
colorTo: gray
|
6 |
sdk: gradio
|
7 |
+
sdk_version: 3.35.2
|
8 |
+
app_file: src/app.py
|
9 |
pinned: false
|
10 |
license: mit
|
11 |
---
|
|
|
|
data/MercadoLibre Data Scientist Technical Challenge - Dataset.csv
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9bfee87615b97787cfdbfe1798ec56d2de52a05d73c818bc836fa2168440c8ab
|
3 |
+
size 18390780
|
data/processed/selected_features.csv
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
0
|
2 |
+
b
|
3 |
+
c
|
4 |
+
h
|
5 |
+
j
|
6 |
+
k
|
7 |
+
l
|
8 |
+
m
|
9 |
+
o
|
10 |
+
monto
|
11 |
+
score
|
12 |
+
fecha_hour
|
13 |
+
fecha_minute
|
14 |
+
fecha_second
|
models/feature_engineering_pipeline.joblib
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:501863a278dd5e6cf3597123afbcacd4ed25eca8a27cf3259f3e7989236f7fdf
|
3 |
+
size 9157
|
models/final_pipeline.joblib
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5ccc8788d5fa15337b2ee31b0c95e6c86cc7da346c5b305d4c4b089725c7d1b
|
3 |
+
size 433034
|
notebooks/01-eda.ipynb
ADDED
The diff for this file is too large to render.
See raw diff
|
|
notebooks/02-feature_rngineering.ipynb
ADDED
@@ -0,0 +1,1293 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cells": [
|
3 |
+
{
|
4 |
+
"cell_type": "code",
|
5 |
+
"execution_count": 1,
|
6 |
+
"metadata": {},
|
7 |
+
"outputs": [],
|
8 |
+
"source": [
|
9 |
+
"%load_ext autoreload\n",
|
10 |
+
"%autoreload 2\n",
|
11 |
+
"import pandas as pd\n",
|
12 |
+
"from sklearn.model_selection import train_test_split\n",
|
13 |
+
"from feature_engine.imputation import AddMissingIndicator, MeanMedianImputer, CategoricalImputer\n",
|
14 |
+
"from feature_engine.transformation import LogTransformer\n",
|
15 |
+
"from feature_engine.discretisation import ArbitraryDiscretiser\n",
|
16 |
+
"from feature_engine.encoding import RareLabelEncoder, OrdinalEncoder\n",
|
17 |
+
"from feature_engine.datetime import DatetimeFeatures\n",
|
18 |
+
"from utils import ScalerDf\n",
|
19 |
+
"from sklearn.pipeline import Pipeline\n",
|
20 |
+
"import joblib\n",
|
21 |
+
"import numpy as np"
|
22 |
+
]
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"cell_type": "code",
|
26 |
+
"execution_count": 2,
|
27 |
+
"metadata": {},
|
28 |
+
"outputs": [
|
29 |
+
{
|
30 |
+
"name": "stdout",
|
31 |
+
"output_type": "stream",
|
32 |
+
"text": [
|
33 |
+
"(150000, 19)\n"
|
34 |
+
]
|
35 |
+
},
|
36 |
+
{
|
37 |
+
"data": {
|
38 |
+
"text/html": [
|
39 |
+
"<div>\n",
|
40 |
+
"<style scoped>\n",
|
41 |
+
" .dataframe tbody tr th:only-of-type {\n",
|
42 |
+
" vertical-align: middle;\n",
|
43 |
+
" }\n",
|
44 |
+
"\n",
|
45 |
+
" .dataframe tbody tr th {\n",
|
46 |
+
" vertical-align: top;\n",
|
47 |
+
" }\n",
|
48 |
+
"\n",
|
49 |
+
" .dataframe thead th {\n",
|
50 |
+
" text-align: right;\n",
|
51 |
+
" }\n",
|
52 |
+
"</style>\n",
|
53 |
+
"<table border=\"1\" class=\"dataframe\">\n",
|
54 |
+
" <thead>\n",
|
55 |
+
" <tr style=\"text-align: right;\">\n",
|
56 |
+
" <th></th>\n",
|
57 |
+
" <th>a</th>\n",
|
58 |
+
" <th>b</th>\n",
|
59 |
+
" <th>c</th>\n",
|
60 |
+
" <th>d</th>\n",
|
61 |
+
" <th>e</th>\n",
|
62 |
+
" <th>f</th>\n",
|
63 |
+
" <th>g</th>\n",
|
64 |
+
" <th>h</th>\n",
|
65 |
+
" <th>j</th>\n",
|
66 |
+
" <th>k</th>\n",
|
67 |
+
" <th>l</th>\n",
|
68 |
+
" <th>m</th>\n",
|
69 |
+
" <th>n</th>\n",
|
70 |
+
" <th>o</th>\n",
|
71 |
+
" <th>p</th>\n",
|
72 |
+
" <th>fecha</th>\n",
|
73 |
+
" <th>monto</th>\n",
|
74 |
+
" <th>score</th>\n",
|
75 |
+
" <th>fraude</th>\n",
|
76 |
+
" </tr>\n",
|
77 |
+
" </thead>\n",
|
78 |
+
" <tbody>\n",
|
79 |
+
" <tr>\n",
|
80 |
+
" <th>0</th>\n",
|
81 |
+
" <td>4</td>\n",
|
82 |
+
" <td>0.6812</td>\n",
|
83 |
+
" <td>50084.12</td>\n",
|
84 |
+
" <td>50.0</td>\n",
|
85 |
+
" <td>0.000000</td>\n",
|
86 |
+
" <td>20.0</td>\n",
|
87 |
+
" <td>AR</td>\n",
|
88 |
+
" <td>1</td>\n",
|
89 |
+
" <td>cat_d26ab52</td>\n",
|
90 |
+
" <td>0.365475</td>\n",
|
91 |
+
" <td>2479.0</td>\n",
|
92 |
+
" <td>952.0</td>\n",
|
93 |
+
" <td>1</td>\n",
|
94 |
+
" <td>NaN</td>\n",
|
95 |
+
" <td>Y</td>\n",
|
96 |
+
" <td>2020-03-20 09:28:19</td>\n",
|
97 |
+
" <td>57.63</td>\n",
|
98 |
+
" <td>100</td>\n",
|
99 |
+
" <td>0</td>\n",
|
100 |
+
" </tr>\n",
|
101 |
+
" <tr>\n",
|
102 |
+
" <th>1</th>\n",
|
103 |
+
" <td>4</td>\n",
|
104 |
+
" <td>0.6694</td>\n",
|
105 |
+
" <td>66005.49</td>\n",
|
106 |
+
" <td>0.0</td>\n",
|
107 |
+
" <td>0.000000</td>\n",
|
108 |
+
" <td>2.0</td>\n",
|
109 |
+
" <td>AR</td>\n",
|
110 |
+
" <td>1</td>\n",
|
111 |
+
" <td>cat_ea962fb</td>\n",
|
112 |
+
" <td>0.612728</td>\n",
|
113 |
+
" <td>2603.0</td>\n",
|
114 |
+
" <td>105.0</td>\n",
|
115 |
+
" <td>1</td>\n",
|
116 |
+
" <td>Y</td>\n",
|
117 |
+
" <td>Y</td>\n",
|
118 |
+
" <td>2020-03-09 13:58:28</td>\n",
|
119 |
+
" <td>40.19</td>\n",
|
120 |
+
" <td>25</td>\n",
|
121 |
+
" <td>0</td>\n",
|
122 |
+
" </tr>\n",
|
123 |
+
" <tr>\n",
|
124 |
+
" <th>2</th>\n",
|
125 |
+
" <td>4</td>\n",
|
126 |
+
" <td>0.4718</td>\n",
|
127 |
+
" <td>7059.05</td>\n",
|
128 |
+
" <td>4.0</td>\n",
|
129 |
+
" <td>0.463488</td>\n",
|
130 |
+
" <td>92.0</td>\n",
|
131 |
+
" <td>BR</td>\n",
|
132 |
+
" <td>25</td>\n",
|
133 |
+
" <td>cat_4c2544e</td>\n",
|
134 |
+
" <td>0.651835</td>\n",
|
135 |
+
" <td>2153.0</td>\n",
|
136 |
+
" <td>249.0</td>\n",
|
137 |
+
" <td>1</td>\n",
|
138 |
+
" <td>Y</td>\n",
|
139 |
+
" <td>Y</td>\n",
|
140 |
+
" <td>2020-04-08 12:25:55</td>\n",
|
141 |
+
" <td>5.77</td>\n",
|
142 |
+
" <td>23</td>\n",
|
143 |
+
" <td>0</td>\n",
|
144 |
+
" </tr>\n",
|
145 |
+
" <tr>\n",
|
146 |
+
" <th>3</th>\n",
|
147 |
+
" <td>4</td>\n",
|
148 |
+
" <td>0.7260</td>\n",
|
149 |
+
" <td>10043.10</td>\n",
|
150 |
+
" <td>24.0</td>\n",
|
151 |
+
" <td>0.046845</td>\n",
|
152 |
+
" <td>43.0</td>\n",
|
153 |
+
" <td>BR</td>\n",
|
154 |
+
" <td>43</td>\n",
|
155 |
+
" <td>cat_1b59ee3</td>\n",
|
156 |
+
" <td>0.692728</td>\n",
|
157 |
+
" <td>4845.0</td>\n",
|
158 |
+
" <td>141.0</td>\n",
|
159 |
+
" <td>1</td>\n",
|
160 |
+
" <td>N</td>\n",
|
161 |
+
" <td>Y</td>\n",
|
162 |
+
" <td>2020-03-14 11:46:13</td>\n",
|
163 |
+
" <td>40.89</td>\n",
|
164 |
+
" <td>23</td>\n",
|
165 |
+
" <td>0</td>\n",
|
166 |
+
" </tr>\n",
|
167 |
+
" <tr>\n",
|
168 |
+
" <th>4</th>\n",
|
169 |
+
" <td>4</td>\n",
|
170 |
+
" <td>0.7758</td>\n",
|
171 |
+
" <td>16584.42</td>\n",
|
172 |
+
" <td>2.0</td>\n",
|
173 |
+
" <td>0.154616</td>\n",
|
174 |
+
" <td>54.0</td>\n",
|
175 |
+
" <td>BR</td>\n",
|
176 |
+
" <td>0</td>\n",
|
177 |
+
" <td>cat_9bacaa5</td>\n",
|
178 |
+
" <td>0.201354</td>\n",
|
179 |
+
" <td>2856.0</td>\n",
|
180 |
+
" <td>18.0</td>\n",
|
181 |
+
" <td>1</td>\n",
|
182 |
+
" <td>Y</td>\n",
|
183 |
+
" <td>N</td>\n",
|
184 |
+
" <td>2020-03-23 14:17:13</td>\n",
|
185 |
+
" <td>18.98</td>\n",
|
186 |
+
" <td>71</td>\n",
|
187 |
+
" <td>0</td>\n",
|
188 |
+
" </tr>\n",
|
189 |
+
" </tbody>\n",
|
190 |
+
"</table>\n",
|
191 |
+
"</div>"
|
192 |
+
],
|
193 |
+
"text/plain": [
|
194 |
+
" a b c d e f g h j k \\\n",
|
195 |
+
"0 4 0.6812 50084.12 50.0 0.000000 20.0 AR 1 cat_d26ab52 0.365475 \n",
|
196 |
+
"1 4 0.6694 66005.49 0.0 0.000000 2.0 AR 1 cat_ea962fb 0.612728 \n",
|
197 |
+
"2 4 0.4718 7059.05 4.0 0.463488 92.0 BR 25 cat_4c2544e 0.651835 \n",
|
198 |
+
"3 4 0.7260 10043.10 24.0 0.046845 43.0 BR 43 cat_1b59ee3 0.692728 \n",
|
199 |
+
"4 4 0.7758 16584.42 2.0 0.154616 54.0 BR 0 cat_9bacaa5 0.201354 \n",
|
200 |
+
"\n",
|
201 |
+
" l m n o p fecha monto score fraude \n",
|
202 |
+
"0 2479.0 952.0 1 NaN Y 2020-03-20 09:28:19 57.63 100 0 \n",
|
203 |
+
"1 2603.0 105.0 1 Y Y 2020-03-09 13:58:28 40.19 25 0 \n",
|
204 |
+
"2 2153.0 249.0 1 Y Y 2020-04-08 12:25:55 5.77 23 0 \n",
|
205 |
+
"3 4845.0 141.0 1 N Y 2020-03-14 11:46:13 40.89 23 0 \n",
|
206 |
+
"4 2856.0 18.0 1 Y N 2020-03-23 14:17:13 18.98 71 0 "
|
207 |
+
]
|
208 |
+
},
|
209 |
+
"execution_count": 2,
|
210 |
+
"metadata": {},
|
211 |
+
"output_type": "execute_result"
|
212 |
+
}
|
213 |
+
],
|
214 |
+
"source": [
|
215 |
+
"data = pd.read_csv('../data/MercadoLibre Data Scientist Technical Challenge - Dataset.csv')\n",
|
216 |
+
"print(data.shape)\n",
|
217 |
+
"data.head()"
|
218 |
+
]
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"cell_type": "code",
|
222 |
+
"execution_count": 3,
|
223 |
+
"metadata": {},
|
224 |
+
"outputs": [
|
225 |
+
{
|
226 |
+
"data": {
|
227 |
+
"text/plain": [
|
228 |
+
"((135000, 18), (15000, 18))"
|
229 |
+
]
|
230 |
+
},
|
231 |
+
"execution_count": 3,
|
232 |
+
"metadata": {},
|
233 |
+
"output_type": "execute_result"
|
234 |
+
}
|
235 |
+
],
|
236 |
+
"source": [
|
237 |
+
"X_train, X_test, y_train, y_test = train_test_split(\n",
|
238 |
+
" data.drop(['fraude'], axis=1), # predictive variables\n",
|
239 |
+
" data['fraude'], # target\n",
|
240 |
+
" test_size=0.1, # portion of dataset to allocate to test set\n",
|
241 |
+
" random_state=0, # we are setting the seed here\n",
|
242 |
+
")\n",
|
243 |
+
"\n",
|
244 |
+
"X_train.shape, X_test.shape"
|
245 |
+
]
|
246 |
+
},
|
247 |
+
{
|
248 |
+
"attachments": {},
|
249 |
+
"cell_type": "markdown",
|
250 |
+
"metadata": {},
|
251 |
+
"source": [
|
252 |
+
"## missing indicator"
|
253 |
+
]
|
254 |
+
},
|
255 |
+
{
|
256 |
+
"cell_type": "code",
|
257 |
+
"execution_count": 4,
|
258 |
+
"metadata": {},
|
259 |
+
"outputs": [],
|
260 |
+
"source": [
|
261 |
+
"## Vars with na\n",
|
262 |
+
"vars_with_na = [var for var in data.columns if data[var].isnull().sum() > 0]\n",
|
263 |
+
"indicator = AddMissingIndicator(variables=vars_with_na)\n",
|
264 |
+
"indicator.fit(X_train)\n",
|
265 |
+
"transform_data =indicator.transform(X_train)"
|
266 |
+
]
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"attachments": {},
|
270 |
+
"cell_type": "markdown",
|
271 |
+
"metadata": {},
|
272 |
+
"source": [
|
273 |
+
"## Imputation on numerical vars"
|
274 |
+
]
|
275 |
+
},
|
276 |
+
{
|
277 |
+
"cell_type": "code",
|
278 |
+
"execution_count": 5,
|
279 |
+
"metadata": {},
|
280 |
+
"outputs": [],
|
281 |
+
"source": [
|
282 |
+
"# make list of numerical variables\n",
|
283 |
+
"num_vars = [var for var in data.columns if data[var].dtypes != 'O' and 'fraude' not in var]\n",
|
284 |
+
"num_vars_na = [var for var in num_vars if var in vars_with_na]\n",
|
285 |
+
"\n",
|
286 |
+
"imputer = MeanMedianImputer(imputation_method='median', variables=num_vars_na)\n",
|
287 |
+
"imputer.fit(transform_data)\n",
|
288 |
+
"transform_data =imputer.transform(transform_data)"
|
289 |
+
]
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"attachments": {},
|
293 |
+
"cell_type": "markdown",
|
294 |
+
"metadata": {},
|
295 |
+
"source": [
|
296 |
+
"## Transformation of numerical vars"
|
297 |
+
]
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"cell_type": "code",
|
301 |
+
"execution_count": 6,
|
302 |
+
"metadata": {},
|
303 |
+
"outputs": [],
|
304 |
+
"source": [
|
305 |
+
"log_vars =['c','monto']"
|
306 |
+
]
|
307 |
+
},
|
308 |
+
{
|
309 |
+
"cell_type": "code",
|
310 |
+
"execution_count": 7,
|
311 |
+
"metadata": {},
|
312 |
+
"outputs": [],
|
313 |
+
"source": [
|
314 |
+
"logtranformer = LogTransformer(variables=log_vars)\n",
|
315 |
+
"logtranformer.fit(transform_data)\n",
|
316 |
+
"transform_data = logtranformer.transform(transform_data)"
|
317 |
+
]
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"attachments": {},
|
321 |
+
"cell_type": "markdown",
|
322 |
+
"metadata": {},
|
323 |
+
"source": [
|
324 |
+
"### Discretizacion"
|
325 |
+
]
|
326 |
+
},
|
327 |
+
{
|
328 |
+
"cell_type": "code",
|
329 |
+
"execution_count": 8,
|
330 |
+
"metadata": {},
|
331 |
+
"outputs": [
|
332 |
+
{
|
333 |
+
"data": {
|
334 |
+
"text/html": [
|
335 |
+
"<div>\n",
|
336 |
+
"<style scoped>\n",
|
337 |
+
" .dataframe tbody tr th:only-of-type {\n",
|
338 |
+
" vertical-align: middle;\n",
|
339 |
+
" }\n",
|
340 |
+
"\n",
|
341 |
+
" .dataframe tbody tr th {\n",
|
342 |
+
" vertical-align: top;\n",
|
343 |
+
" }\n",
|
344 |
+
"\n",
|
345 |
+
" .dataframe thead th {\n",
|
346 |
+
" text-align: right;\n",
|
347 |
+
" }\n",
|
348 |
+
"</style>\n",
|
349 |
+
"<table border=\"1\" class=\"dataframe\">\n",
|
350 |
+
" <thead>\n",
|
351 |
+
" <tr style=\"text-align: right;\">\n",
|
352 |
+
" <th></th>\n",
|
353 |
+
" <th>a</th>\n",
|
354 |
+
" <th>b</th>\n",
|
355 |
+
" <th>c</th>\n",
|
356 |
+
" <th>d</th>\n",
|
357 |
+
" <th>e</th>\n",
|
358 |
+
" <th>f</th>\n",
|
359 |
+
" <th>g</th>\n",
|
360 |
+
" <th>h</th>\n",
|
361 |
+
" <th>j</th>\n",
|
362 |
+
" <th>k</th>\n",
|
363 |
+
" <th>...</th>\n",
|
364 |
+
" <th>monto</th>\n",
|
365 |
+
" <th>score</th>\n",
|
366 |
+
" <th>b_na</th>\n",
|
367 |
+
" <th>c_na</th>\n",
|
368 |
+
" <th>d_na</th>\n",
|
369 |
+
" <th>f_na</th>\n",
|
370 |
+
" <th>g_na</th>\n",
|
371 |
+
" <th>l_na</th>\n",
|
372 |
+
" <th>m_na</th>\n",
|
373 |
+
" <th>o_na</th>\n",
|
374 |
+
" </tr>\n",
|
375 |
+
" </thead>\n",
|
376 |
+
" <tbody>\n",
|
377 |
+
" <tr>\n",
|
378 |
+
" <th>135569</th>\n",
|
379 |
+
" <td>4</td>\n",
|
380 |
+
" <td>0.5217</td>\n",
|
381 |
+
" <td>9.791941</td>\n",
|
382 |
+
" <td>1.0</td>\n",
|
383 |
+
" <td>1</td>\n",
|
384 |
+
" <td>1</td>\n",
|
385 |
+
" <td>BR</td>\n",
|
386 |
+
" <td>36</td>\n",
|
387 |
+
" <td>cat_4744ece</td>\n",
|
388 |
+
" <td>0.636610</td>\n",
|
389 |
+
" <td>...</td>\n",
|
390 |
+
" <td>3.214466</td>\n",
|
391 |
+
" <td>93</td>\n",
|
392 |
+
" <td>0</td>\n",
|
393 |
+
" <td>0</td>\n",
|
394 |
+
" <td>0</td>\n",
|
395 |
+
" <td>0</td>\n",
|
396 |
+
" <td>0</td>\n",
|
397 |
+
" <td>0</td>\n",
|
398 |
+
" <td>0</td>\n",
|
399 |
+
" <td>1</td>\n",
|
400 |
+
" </tr>\n",
|
401 |
+
" <tr>\n",
|
402 |
+
" <th>78656</th>\n",
|
403 |
+
" <td>2</td>\n",
|
404 |
+
" <td>0.7554</td>\n",
|
405 |
+
" <td>10.686472</td>\n",
|
406 |
+
" <td>1.0</td>\n",
|
407 |
+
" <td>0</td>\n",
|
408 |
+
" <td>1</td>\n",
|
409 |
+
" <td>AR</td>\n",
|
410 |
+
" <td>8</td>\n",
|
411 |
+
" <td>cat_3203c7c</td>\n",
|
412 |
+
" <td>0.633266</td>\n",
|
413 |
+
" <td>...</td>\n",
|
414 |
+
" <td>3.364188</td>\n",
|
415 |
+
" <td>6</td>\n",
|
416 |
+
" <td>1</td>\n",
|
417 |
+
" <td>1</td>\n",
|
418 |
+
" <td>0</td>\n",
|
419 |
+
" <td>0</td>\n",
|
420 |
+
" <td>0</td>\n",
|
421 |
+
" <td>0</td>\n",
|
422 |
+
" <td>0</td>\n",
|
423 |
+
" <td>1</td>\n",
|
424 |
+
" </tr>\n",
|
425 |
+
" <tr>\n",
|
426 |
+
" <th>87437</th>\n",
|
427 |
+
" <td>4</td>\n",
|
428 |
+
" <td>0.5437</td>\n",
|
429 |
+
" <td>11.717906</td>\n",
|
430 |
+
" <td>1.0</td>\n",
|
431 |
+
" <td>1</td>\n",
|
432 |
+
" <td>1</td>\n",
|
433 |
+
" <td>AR</td>\n",
|
434 |
+
" <td>46</td>\n",
|
435 |
+
" <td>cat_5b785c6</td>\n",
|
436 |
+
" <td>0.735749</td>\n",
|
437 |
+
" <td>...</td>\n",
|
438 |
+
" <td>3.106826</td>\n",
|
439 |
+
" <td>55</td>\n",
|
440 |
+
" <td>0</td>\n",
|
441 |
+
" <td>0</td>\n",
|
442 |
+
" <td>0</td>\n",
|
443 |
+
" <td>0</td>\n",
|
444 |
+
" <td>0</td>\n",
|
445 |
+
" <td>0</td>\n",
|
446 |
+
" <td>0</td>\n",
|
447 |
+
" <td>1</td>\n",
|
448 |
+
" </tr>\n",
|
449 |
+
" <tr>\n",
|
450 |
+
" <th>131674</th>\n",
|
451 |
+
" <td>4</td>\n",
|
452 |
+
" <td>0.7418</td>\n",
|
453 |
+
" <td>9.755215</td>\n",
|
454 |
+
" <td>50.0</td>\n",
|
455 |
+
" <td>1</td>\n",
|
456 |
+
" <td>1</td>\n",
|
457 |
+
" <td>BR</td>\n",
|
458 |
+
" <td>9</td>\n",
|
459 |
+
" <td>cat_a8c10a4</td>\n",
|
460 |
+
" <td>0.529367</td>\n",
|
461 |
+
" <td>...</td>\n",
|
462 |
+
" <td>2.867899</td>\n",
|
463 |
+
" <td>7</td>\n",
|
464 |
+
" <td>0</td>\n",
|
465 |
+
" <td>0</td>\n",
|
466 |
+
" <td>0</td>\n",
|
467 |
+
" <td>0</td>\n",
|
468 |
+
" <td>0</td>\n",
|
469 |
+
" <td>0</td>\n",
|
470 |
+
" <td>0</td>\n",
|
471 |
+
" <td>1</td>\n",
|
472 |
+
" </tr>\n",
|
473 |
+
" <tr>\n",
|
474 |
+
" <th>45535</th>\n",
|
475 |
+
" <td>4</td>\n",
|
476 |
+
" <td>0.6463</td>\n",
|
477 |
+
" <td>10.851127</td>\n",
|
478 |
+
" <td>4.0</td>\n",
|
479 |
+
" <td>1</td>\n",
|
480 |
+
" <td>1</td>\n",
|
481 |
+
" <td>AR</td>\n",
|
482 |
+
" <td>22</td>\n",
|
483 |
+
" <td>cat_edae169</td>\n",
|
484 |
+
" <td>0.049212</td>\n",
|
485 |
+
" <td>...</td>\n",
|
486 |
+
" <td>3.383712</td>\n",
|
487 |
+
" <td>32</td>\n",
|
488 |
+
" <td>0</td>\n",
|
489 |
+
" <td>0</td>\n",
|
490 |
+
" <td>0</td>\n",
|
491 |
+
" <td>0</td>\n",
|
492 |
+
" <td>0</td>\n",
|
493 |
+
" <td>0</td>\n",
|
494 |
+
" <td>0</td>\n",
|
495 |
+
" <td>0</td>\n",
|
496 |
+
" </tr>\n",
|
497 |
+
" </tbody>\n",
|
498 |
+
"</table>\n",
|
499 |
+
"<p>5 rows Γ 26 columns</p>\n",
|
500 |
+
"</div>"
|
501 |
+
],
|
502 |
+
"text/plain": [
|
503 |
+
" a b c d e f g h j k ... \\\n",
|
504 |
+
"135569 4 0.5217 9.791941 1.0 1 1 BR 36 cat_4744ece 0.636610 ... \n",
|
505 |
+
"78656 2 0.7554 10.686472 1.0 0 1 AR 8 cat_3203c7c 0.633266 ... \n",
|
506 |
+
"87437 4 0.5437 11.717906 1.0 1 1 AR 46 cat_5b785c6 0.735749 ... \n",
|
507 |
+
"131674 4 0.7418 9.755215 50.0 1 1 BR 9 cat_a8c10a4 0.529367 ... \n",
|
508 |
+
"45535 4 0.6463 10.851127 4.0 1 1 AR 22 cat_edae169 0.049212 ... \n",
|
509 |
+
"\n",
|
510 |
+
" monto score b_na c_na d_na f_na g_na l_na m_na o_na \n",
|
511 |
+
"135569 3.214466 93 0 0 0 0 0 0 0 1 \n",
|
512 |
+
"78656 3.364188 6 1 1 0 0 0 0 0 1 \n",
|
513 |
+
"87437 3.106826 55 0 0 0 0 0 0 0 1 \n",
|
514 |
+
"131674 2.867899 7 0 0 0 0 0 0 0 1 \n",
|
515 |
+
"45535 3.383712 32 0 0 0 0 0 0 0 0 \n",
|
516 |
+
"\n",
|
517 |
+
"[5 rows x 26 columns]"
|
518 |
+
]
|
519 |
+
},
|
520 |
+
"execution_count": 8,
|
521 |
+
"metadata": {},
|
522 |
+
"output_type": "execute_result"
|
523 |
+
}
|
524 |
+
],
|
525 |
+
"source": [
|
526 |
+
"skewed_vars = ['e', 'f']\n",
|
527 |
+
"discretizer = ArbitraryDiscretiser( binning_dict= dict(e =[-np.inf,0,np.inf], f=[-np.inf,0,np.inf]) )\n",
|
528 |
+
"discretizer.fit(transform_data)\n",
|
529 |
+
"transform_data = discretizer.transform(transform_data)\n",
|
530 |
+
"transform_data.head()"
|
531 |
+
]
|
532 |
+
},
|
533 |
+
{
|
534 |
+
"attachments": {},
|
535 |
+
"cell_type": "markdown",
|
536 |
+
"metadata": {},
|
537 |
+
"source": [
|
538 |
+
"# Transformacion variables categoricas"
|
539 |
+
]
|
540 |
+
},
|
541 |
+
{
|
542 |
+
"cell_type": "code",
|
543 |
+
"execution_count": 9,
|
544 |
+
"metadata": {},
|
545 |
+
"outputs": [],
|
546 |
+
"source": [
|
547 |
+
"# capture categorical variables in a list\n",
|
548 |
+
"cat_vars = [var for var in data.columns if data[var].dtypes == 'O' and 'fecha' not in var]\n",
|
549 |
+
"cat_vars_na = [var for var in cat_vars if var in vars_with_na]\n",
|
550 |
+
"categorical_imputer = CategoricalImputer(variables=cat_vars_na, imputation_method='missing', fill_value='missing')\n",
|
551 |
+
"categorical_imputer.fit(transform_data)\n",
|
552 |
+
"transform_data = categorical_imputer.transform(transform_data)"
|
553 |
+
]
|
554 |
+
},
|
555 |
+
{
|
556 |
+
"cell_type": "code",
|
557 |
+
"execution_count": 10,
|
558 |
+
"metadata": {},
|
559 |
+
"outputs": [],
|
560 |
+
"source": [
|
561 |
+
"## Encode rare labels\n",
|
562 |
+
"rarelabel = RareLabelEncoder(variables=cat_vars, tol=0.001, n_categories=1)\n",
|
563 |
+
"rarelabel.fit(transform_data)\n",
|
564 |
+
"transform_data = rarelabel.transform(transform_data)\n"
|
565 |
+
]
|
566 |
+
},
|
567 |
+
{
|
568 |
+
"cell_type": "code",
|
569 |
+
"execution_count": 11,
|
570 |
+
"metadata": {},
|
571 |
+
"outputs": [],
|
572 |
+
"source": [
|
573 |
+
"## ordinal encoders\n",
|
574 |
+
"ordinal_encoder = OrdinalEncoder(variables=cat_vars)\n",
|
575 |
+
"ordinal_encoder.fit(transform_data, y_train)\n",
|
576 |
+
"transform_data = ordinal_encoder.transform(transform_data)"
|
577 |
+
]
|
578 |
+
},
|
579 |
+
{
|
580 |
+
"attachments": {},
|
581 |
+
"cell_type": "markdown",
|
582 |
+
"metadata": {},
|
583 |
+
"source": [
|
584 |
+
"## Datetime Features"
|
585 |
+
]
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"cell_type": "code",
|
589 |
+
"execution_count": 12,
|
590 |
+
"metadata": {},
|
591 |
+
"outputs": [],
|
592 |
+
"source": [
|
593 |
+
"dt_features = DatetimeFeatures(variables='fecha', features_to_extract='all')\n",
|
594 |
+
"dt_features.fit(transform_data)\n",
|
595 |
+
"transform_data = dt_features.transform(transform_data)"
|
596 |
+
]
|
597 |
+
},
|
598 |
+
{
|
599 |
+
"attachments": {},
|
600 |
+
"cell_type": "markdown",
|
601 |
+
"metadata": {},
|
602 |
+
"source": [
|
603 |
+
"## Scaler data"
|
604 |
+
]
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"cell_type": "code",
|
608 |
+
"execution_count": 13,
|
609 |
+
"metadata": {},
|
610 |
+
"outputs": [],
|
611 |
+
"source": [
|
612 |
+
"scaler = ScalerDf(method='minmax')\n",
|
613 |
+
"scaler.fit(transform_data)\n",
|
614 |
+
"transform_data = scaler.transform(transform_data)"
|
615 |
+
]
|
616 |
+
},
|
617 |
+
{
|
618 |
+
"cell_type": "code",
|
619 |
+
"execution_count": 14,
|
620 |
+
"metadata": {},
|
621 |
+
"outputs": [
|
622 |
+
{
|
623 |
+
"data": {
|
624 |
+
"text/plain": [
|
625 |
+
"Index(['a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'j', 'k', 'l', 'm', 'n', 'o',\n",
|
626 |
+
" 'p', 'monto', 'score', 'b_na', 'c_na', 'd_na', 'f_na', 'g_na', 'l_na',\n",
|
627 |
+
" 'm_na', 'o_na', 'fecha_month', 'fecha_quarter', 'fecha_semester',\n",
|
628 |
+
" 'fecha_year', 'fecha_week', 'fecha_day_of_week', 'fecha_day_of_month',\n",
|
629 |
+
" 'fecha_day_of_year', 'fecha_weekend', 'fecha_month_start',\n",
|
630 |
+
" 'fecha_month_end', 'fecha_quarter_start', 'fecha_quarter_end',\n",
|
631 |
+
" 'fecha_year_start', 'fecha_year_end', 'fecha_leap_year',\n",
|
632 |
+
" 'fecha_days_in_month', 'fecha_hour', 'fecha_minute', 'fecha_second'],\n",
|
633 |
+
" dtype='object')"
|
634 |
+
]
|
635 |
+
},
|
636 |
+
"execution_count": 14,
|
637 |
+
"metadata": {},
|
638 |
+
"output_type": "execute_result"
|
639 |
+
}
|
640 |
+
],
|
641 |
+
"source": [
|
642 |
+
"transform_data.columns"
|
643 |
+
]
|
644 |
+
},
|
645 |
+
{
|
646 |
+
"attachments": {},
|
647 |
+
"cell_type": "markdown",
|
648 |
+
"metadata": {},
|
649 |
+
"source": [
|
650 |
+
"# Pongamos todo junto"
|
651 |
+
]
|
652 |
+
},
|
653 |
+
{
|
654 |
+
"cell_type": "code",
|
655 |
+
"execution_count": 15,
|
656 |
+
"metadata": {},
|
657 |
+
"outputs": [],
|
658 |
+
"source": [
|
659 |
+
"pipeline_steps = [\n",
|
660 |
+
" ('missing_indicator',AddMissingIndicator(variables=vars_with_na)),\n",
|
661 |
+
" ('numerical_imputer', MeanMedianImputer(imputation_method='median', variables=num_vars_na)),\n",
|
662 |
+
" ('categorical_imputer', CategoricalImputer(variables=cat_vars_na, imputation_method='missing', fill_value='missing')),\n",
|
663 |
+
" ('numerical_transformation', LogTransformer(variables=log_vars)),\n",
|
664 |
+
" ('binarizer', ArbitraryDiscretiser( binning_dict= dict(e =[-np.inf,0,np.inf], f=[-np.inf,0,np.inf]))),\n",
|
665 |
+
" ('rare_label_encoder', RareLabelEncoder(variables=cat_vars, tol=0.001, n_categories=1)),\n",
|
666 |
+
" ('ordinal_encoder', OrdinalEncoder(variables=cat_vars)),\n",
|
667 |
+
" ('datetime_features', DatetimeFeatures(variables='fecha', features_to_extract='all')),\n",
|
668 |
+
" ('scaler', ScalerDf(method='minmax'))\n",
|
669 |
+
" \n",
|
670 |
+
"]"
|
671 |
+
]
|
672 |
+
},
|
673 |
+
{
|
674 |
+
"cell_type": "code",
|
675 |
+
"execution_count": 16,
|
676 |
+
"metadata": {},
|
677 |
+
"outputs": [],
|
678 |
+
"source": [
|
679 |
+
"fraud_pipeline = Pipeline(pipeline_steps)"
|
680 |
+
]
|
681 |
+
},
|
682 |
+
{
|
683 |
+
"cell_type": "code",
|
684 |
+
"execution_count": 17,
|
685 |
+
"metadata": {},
|
686 |
+
"outputs": [
|
687 |
+
{
|
688 |
+
"data": {
|
689 |
+
"text/html": [
|
690 |
+
"<style>#sk-container-id-1 {color: black;}#sk-container-id-1 pre{padding: 0;}#sk-container-id-1 div.sk-toggleable {background-color: white;}#sk-container-id-1 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-1 label.sk-toggleable__label-arrow:before {content: \"βΈ\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-1 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-1 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-1 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"βΎ\";}#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-1 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-1 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-1 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-1 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-1 div.sk-item {position: relative;z-index: 1;}#sk-container-id-1 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-1 div.sk-item::before, #sk-container-id-1 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-1 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-1 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-1 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-1 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-1 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-1 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-1 div.sk-label-container {text-align: center;}#sk-container-id-1 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-1 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>Pipeline(steps=[('missing_indicator',\n",
|
691 |
+
" AddMissingIndicator(variables=['b', 'c', 'd', 'f', 'g', 'l',\n",
|
692 |
+
" 'm', 'o'])),\n",
|
693 |
+
" ('numerical_imputer',\n",
|
694 |
+
" MeanMedianImputer(variables=['b', 'c', 'd', 'f', 'l', 'm'])),\n",
|
695 |
+
" ('categorical_imputer',\n",
|
696 |
+
" CategoricalImputer(fill_value='missing',\n",
|
697 |
+
" variables=['g', 'o'])),\n",
|
698 |
+
" ('numerical_transformation',\n",
|
699 |
+
" LogTransformer(variables=['c', 'monto'])),\n",
|
700 |
+
" ('binarizer',\n",
|
701 |
+
" ArbitraryDiscretiser(binning_dict={'e': [-inf, 0, inf],\n",
|
702 |
+
" 'f': [-inf, 0, inf]})),\n",
|
703 |
+
" ('rare_label_encoder',\n",
|
704 |
+
" RareLabelEncoder(n_categories=1, tol=0.001,\n",
|
705 |
+
" variables=['g', 'j', 'o', 'p'])),\n",
|
706 |
+
" ('ordinal_encoder',\n",
|
707 |
+
" OrdinalEncoder(variables=['g', 'j', 'o', 'p'])),\n",
|
708 |
+
" ('datetime_features',\n",
|
709 |
+
" DatetimeFeatures(features_to_extract='all',\n",
|
710 |
+
" variables='fecha')),\n",
|
711 |
+
" ('scaler', ScalerDf(method='minmax'))])</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" ><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">Pipeline</label><div class=\"sk-toggleable__content\"><pre>Pipeline(steps=[('missing_indicator',\n",
|
712 |
+
" AddMissingIndicator(variables=['b', 'c', 'd', 'f', 'g', 'l',\n",
|
713 |
+
" 'm', 'o'])),\n",
|
714 |
+
" ('numerical_imputer',\n",
|
715 |
+
" MeanMedianImputer(variables=['b', 'c', 'd', 'f', 'l', 'm'])),\n",
|
716 |
+
" ('categorical_imputer',\n",
|
717 |
+
" CategoricalImputer(fill_value='missing',\n",
|
718 |
+
" variables=['g', 'o'])),\n",
|
719 |
+
" ('numerical_transformation',\n",
|
720 |
+
" LogTransformer(variables=['c', 'monto'])),\n",
|
721 |
+
" ('binarizer',\n",
|
722 |
+
" ArbitraryDiscretiser(binning_dict={'e': [-inf, 0, inf],\n",
|
723 |
+
" 'f': [-inf, 0, inf]})),\n",
|
724 |
+
" ('rare_label_encoder',\n",
|
725 |
+
" RareLabelEncoder(n_categories=1, tol=0.001,\n",
|
726 |
+
" variables=['g', 'j', 'o', 'p'])),\n",
|
727 |
+
" ('ordinal_encoder',\n",
|
728 |
+
" OrdinalEncoder(variables=['g', 'j', 'o', 'p'])),\n",
|
729 |
+
" ('datetime_features',\n",
|
730 |
+
" DatetimeFeatures(features_to_extract='all',\n",
|
731 |
+
" variables='fecha')),\n",
|
732 |
+
" ('scaler', ScalerDf(method='minmax'))])</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" ><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">AddMissingIndicator</label><div class=\"sk-toggleable__content\"><pre>AddMissingIndicator(variables=['b', 'c', 'd', 'f', 'g', 'l', 'm', 'o'])</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-3\" type=\"checkbox\" ><label for=\"sk-estimator-id-3\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">MeanMedianImputer</label><div class=\"sk-toggleable__content\"><pre>MeanMedianImputer(variables=['b', 'c', 'd', 'f', 'l', 'm'])</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-4\" type=\"checkbox\" ><label for=\"sk-estimator-id-4\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">CategoricalImputer</label><div class=\"sk-toggleable__content\"><pre>CategoricalImputer(fill_value='missing', variables=['g', 'o'])</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-5\" type=\"checkbox\" ><label for=\"sk-estimator-id-5\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">LogTransformer</label><div class=\"sk-toggleable__content\"><pre>LogTransformer(variables=['c', 'monto'])</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-6\" type=\"checkbox\" ><label for=\"sk-estimator-id-6\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">ArbitraryDiscretiser</label><div class=\"sk-toggleable__content\"><pre>ArbitraryDiscretiser(binning_dict={'e': [-inf, 0, inf], 'f': [-inf, 0, inf]})</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-7\" type=\"checkbox\" ><label for=\"sk-estimator-id-7\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">RareLabelEncoder</label><div class=\"sk-toggleable__content\"><pre>RareLabelEncoder(n_categories=1, tol=0.001, variables=['g', 'j', 'o', 'p'])</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-8\" type=\"checkbox\" ><label for=\"sk-estimator-id-8\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">OrdinalEncoder</label><div class=\"sk-toggleable__content\"><pre>OrdinalEncoder(variables=['g', 'j', 'o', 'p'])</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-9\" type=\"checkbox\" ><label for=\"sk-estimator-id-9\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">DatetimeFeatures</label><div class=\"sk-toggleable__content\"><pre>DatetimeFeatures(features_to_extract='all', variables='fecha')</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-10\" type=\"checkbox\" ><label for=\"sk-estimator-id-10\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">ScalerDf</label><div class=\"sk-toggleable__content\"><pre>ScalerDf(method='minmax')</pre></div></div></div></div></div></div></div>"
|
733 |
+
],
|
734 |
+
"text/plain": [
|
735 |
+
"Pipeline(steps=[('missing_indicator',\n",
|
736 |
+
" AddMissingIndicator(variables=['b', 'c', 'd', 'f', 'g', 'l',\n",
|
737 |
+
" 'm', 'o'])),\n",
|
738 |
+
" ('numerical_imputer',\n",
|
739 |
+
" MeanMedianImputer(variables=['b', 'c', 'd', 'f', 'l', 'm'])),\n",
|
740 |
+
" ('categorical_imputer',\n",
|
741 |
+
" CategoricalImputer(fill_value='missing',\n",
|
742 |
+
" variables=['g', 'o'])),\n",
|
743 |
+
" ('numerical_transformation',\n",
|
744 |
+
" LogTransformer(variables=['c', 'monto'])),\n",
|
745 |
+
" ('binarizer',\n",
|
746 |
+
" ArbitraryDiscretiser(binning_dict={'e': [-inf, 0, inf],\n",
|
747 |
+
" 'f': [-inf, 0, inf]})),\n",
|
748 |
+
" ('rare_label_encoder',\n",
|
749 |
+
" RareLabelEncoder(n_categories=1, tol=0.001,\n",
|
750 |
+
" variables=['g', 'j', 'o', 'p'])),\n",
|
751 |
+
" ('ordinal_encoder',\n",
|
752 |
+
" OrdinalEncoder(variables=['g', 'j', 'o', 'p'])),\n",
|
753 |
+
" ('datetime_features',\n",
|
754 |
+
" DatetimeFeatures(features_to_extract='all',\n",
|
755 |
+
" variables='fecha')),\n",
|
756 |
+
" ('scaler', ScalerDf(method='minmax'))])"
|
757 |
+
]
|
758 |
+
},
|
759 |
+
"execution_count": 17,
|
760 |
+
"metadata": {},
|
761 |
+
"output_type": "execute_result"
|
762 |
+
}
|
763 |
+
],
|
764 |
+
"source": [
|
765 |
+
"fraud_pipeline"
|
766 |
+
]
|
767 |
+
},
|
768 |
+
{
|
769 |
+
"cell_type": "code",
|
770 |
+
"execution_count": 18,
|
771 |
+
"metadata": {},
|
772 |
+
"outputs": [
|
773 |
+
{
|
774 |
+
"data": {
|
775 |
+
"text/html": [
|
776 |
+
"<style>#sk-container-id-2 {color: black;}#sk-container-id-2 pre{padding: 0;}#sk-container-id-2 div.sk-toggleable {background-color: white;}#sk-container-id-2 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-2 label.sk-toggleable__label-arrow:before {content: \"βΈ\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-2 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-2 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-2 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-2 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-2 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-2 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"βΎ\";}#sk-container-id-2 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-2 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-2 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-2 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-2 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-2 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-2 div.sk-item {position: relative;z-index: 1;}#sk-container-id-2 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-2 div.sk-item::before, #sk-container-id-2 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-2 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-2 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-2 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-2 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-2 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-2 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-2 div.sk-label-container {text-align: center;}#sk-container-id-2 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-2 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-2\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>Pipeline(steps=[('missing_indicator',\n",
|
777 |
+
" AddMissingIndicator(variables=['b', 'c', 'd', 'f', 'g', 'l',\n",
|
778 |
+
" 'm', 'o'])),\n",
|
779 |
+
" ('numerical_imputer',\n",
|
780 |
+
" MeanMedianImputer(variables=['b', 'c', 'd', 'f', 'l', 'm'])),\n",
|
781 |
+
" ('categorical_imputer',\n",
|
782 |
+
" CategoricalImputer(fill_value='missing',\n",
|
783 |
+
" variables=['g', 'o'])),\n",
|
784 |
+
" ('numerical_transformation',\n",
|
785 |
+
" LogTransformer(variables=['c', 'monto'])),\n",
|
786 |
+
" ('binarizer',\n",
|
787 |
+
" ArbitraryDiscretiser(binning_dict={'e': [-inf, 0, inf],\n",
|
788 |
+
" 'f': [-inf, 0, inf]})),\n",
|
789 |
+
" ('rare_label_encoder',\n",
|
790 |
+
" RareLabelEncoder(n_categories=1, tol=0.001,\n",
|
791 |
+
" variables=['g', 'j', 'o', 'p'])),\n",
|
792 |
+
" ('ordinal_encoder',\n",
|
793 |
+
" OrdinalEncoder(variables=['g', 'j', 'o', 'p'])),\n",
|
794 |
+
" ('datetime_features',\n",
|
795 |
+
" DatetimeFeatures(features_to_extract='all',\n",
|
796 |
+
" variables='fecha')),\n",
|
797 |
+
" ('scaler', ScalerDf(method='minmax'))])</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-11\" type=\"checkbox\" ><label for=\"sk-estimator-id-11\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">Pipeline</label><div class=\"sk-toggleable__content\"><pre>Pipeline(steps=[('missing_indicator',\n",
|
798 |
+
" AddMissingIndicator(variables=['b', 'c', 'd', 'f', 'g', 'l',\n",
|
799 |
+
" 'm', 'o'])),\n",
|
800 |
+
" ('numerical_imputer',\n",
|
801 |
+
" MeanMedianImputer(variables=['b', 'c', 'd', 'f', 'l', 'm'])),\n",
|
802 |
+
" ('categorical_imputer',\n",
|
803 |
+
" CategoricalImputer(fill_value='missing',\n",
|
804 |
+
" variables=['g', 'o'])),\n",
|
805 |
+
" ('numerical_transformation',\n",
|
806 |
+
" LogTransformer(variables=['c', 'monto'])),\n",
|
807 |
+
" ('binarizer',\n",
|
808 |
+
" ArbitraryDiscretiser(binning_dict={'e': [-inf, 0, inf],\n",
|
809 |
+
" 'f': [-inf, 0, inf]})),\n",
|
810 |
+
" ('rare_label_encoder',\n",
|
811 |
+
" RareLabelEncoder(n_categories=1, tol=0.001,\n",
|
812 |
+
" variables=['g', 'j', 'o', 'p'])),\n",
|
813 |
+
" ('ordinal_encoder',\n",
|
814 |
+
" OrdinalEncoder(variables=['g', 'j', 'o', 'p'])),\n",
|
815 |
+
" ('datetime_features',\n",
|
816 |
+
" DatetimeFeatures(features_to_extract='all',\n",
|
817 |
+
" variables='fecha')),\n",
|
818 |
+
" ('scaler', ScalerDf(method='minmax'))])</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-12\" type=\"checkbox\" ><label for=\"sk-estimator-id-12\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">AddMissingIndicator</label><div class=\"sk-toggleable__content\"><pre>AddMissingIndicator(variables=['b', 'c', 'd', 'f', 'g', 'l', 'm', 'o'])</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-13\" type=\"checkbox\" ><label for=\"sk-estimator-id-13\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">MeanMedianImputer</label><div class=\"sk-toggleable__content\"><pre>MeanMedianImputer(variables=['b', 'c', 'd', 'f', 'l', 'm'])</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-14\" type=\"checkbox\" ><label for=\"sk-estimator-id-14\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">CategoricalImputer</label><div class=\"sk-toggleable__content\"><pre>CategoricalImputer(fill_value='missing', variables=['g', 'o'])</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-15\" type=\"checkbox\" ><label for=\"sk-estimator-id-15\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">LogTransformer</label><div class=\"sk-toggleable__content\"><pre>LogTransformer(variables=['c', 'monto'])</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-16\" type=\"checkbox\" ><label for=\"sk-estimator-id-16\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">ArbitraryDiscretiser</label><div class=\"sk-toggleable__content\"><pre>ArbitraryDiscretiser(binning_dict={'e': [-inf, 0, inf], 'f': [-inf, 0, inf]})</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-17\" type=\"checkbox\" ><label for=\"sk-estimator-id-17\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">RareLabelEncoder</label><div class=\"sk-toggleable__content\"><pre>RareLabelEncoder(n_categories=1, tol=0.001, variables=['g', 'j', 'o', 'p'])</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-18\" type=\"checkbox\" ><label for=\"sk-estimator-id-18\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">OrdinalEncoder</label><div class=\"sk-toggleable__content\"><pre>OrdinalEncoder(variables=['g', 'j', 'o', 'p'])</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-19\" type=\"checkbox\" ><label for=\"sk-estimator-id-19\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">DatetimeFeatures</label><div class=\"sk-toggleable__content\"><pre>DatetimeFeatures(features_to_extract='all', variables='fecha')</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-20\" type=\"checkbox\" ><label for=\"sk-estimator-id-20\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">ScalerDf</label><div class=\"sk-toggleable__content\"><pre>ScalerDf(method='minmax')</pre></div></div></div></div></div></div></div>"
|
819 |
+
],
|
820 |
+
"text/plain": [
|
821 |
+
"Pipeline(steps=[('missing_indicator',\n",
|
822 |
+
" AddMissingIndicator(variables=['b', 'c', 'd', 'f', 'g', 'l',\n",
|
823 |
+
" 'm', 'o'])),\n",
|
824 |
+
" ('numerical_imputer',\n",
|
825 |
+
" MeanMedianImputer(variables=['b', 'c', 'd', 'f', 'l', 'm'])),\n",
|
826 |
+
" ('categorical_imputer',\n",
|
827 |
+
" CategoricalImputer(fill_value='missing',\n",
|
828 |
+
" variables=['g', 'o'])),\n",
|
829 |
+
" ('numerical_transformation',\n",
|
830 |
+
" LogTransformer(variables=['c', 'monto'])),\n",
|
831 |
+
" ('binarizer',\n",
|
832 |
+
" ArbitraryDiscretiser(binning_dict={'e': [-inf, 0, inf],\n",
|
833 |
+
" 'f': [-inf, 0, inf]})),\n",
|
834 |
+
" ('rare_label_encoder',\n",
|
835 |
+
" RareLabelEncoder(n_categories=1, tol=0.001,\n",
|
836 |
+
" variables=['g', 'j', 'o', 'p'])),\n",
|
837 |
+
" ('ordinal_encoder',\n",
|
838 |
+
" OrdinalEncoder(variables=['g', 'j', 'o', 'p'])),\n",
|
839 |
+
" ('datetime_features',\n",
|
840 |
+
" DatetimeFeatures(features_to_extract='all',\n",
|
841 |
+
" variables='fecha')),\n",
|
842 |
+
" ('scaler', ScalerDf(method='minmax'))])"
|
843 |
+
]
|
844 |
+
},
|
845 |
+
"execution_count": 18,
|
846 |
+
"metadata": {},
|
847 |
+
"output_type": "execute_result"
|
848 |
+
}
|
849 |
+
],
|
850 |
+
"source": [
|
851 |
+
"fraud_pipeline.fit(X_train, y_train)"
|
852 |
+
]
|
853 |
+
},
|
854 |
+
{
|
855 |
+
"cell_type": "code",
|
856 |
+
"execution_count": 19,
|
857 |
+
"metadata": {},
|
858 |
+
"outputs": [
|
859 |
+
{
|
860 |
+
"data": {
|
861 |
+
"text/html": [
|
862 |
+
"<div>\n",
|
863 |
+
"<style scoped>\n",
|
864 |
+
" .dataframe tbody tr th:only-of-type {\n",
|
865 |
+
" vertical-align: middle;\n",
|
866 |
+
" }\n",
|
867 |
+
"\n",
|
868 |
+
" .dataframe tbody tr th {\n",
|
869 |
+
" vertical-align: top;\n",
|
870 |
+
" }\n",
|
871 |
+
"\n",
|
872 |
+
" .dataframe thead th {\n",
|
873 |
+
" text-align: right;\n",
|
874 |
+
" }\n",
|
875 |
+
"</style>\n",
|
876 |
+
"<table border=\"1\" class=\"dataframe\">\n",
|
877 |
+
" <thead>\n",
|
878 |
+
" <tr style=\"text-align: right;\">\n",
|
879 |
+
" <th></th>\n",
|
880 |
+
" <th>a</th>\n",
|
881 |
+
" <th>b</th>\n",
|
882 |
+
" <th>c</th>\n",
|
883 |
+
" <th>d</th>\n",
|
884 |
+
" <th>e</th>\n",
|
885 |
+
" <th>f</th>\n",
|
886 |
+
" <th>g</th>\n",
|
887 |
+
" <th>h</th>\n",
|
888 |
+
" <th>j</th>\n",
|
889 |
+
" <th>k</th>\n",
|
890 |
+
" <th>...</th>\n",
|
891 |
+
" <th>fecha_month_end</th>\n",
|
892 |
+
" <th>fecha_quarter_start</th>\n",
|
893 |
+
" <th>fecha_quarter_end</th>\n",
|
894 |
+
" <th>fecha_year_start</th>\n",
|
895 |
+
" <th>fecha_year_end</th>\n",
|
896 |
+
" <th>fecha_leap_year</th>\n",
|
897 |
+
" <th>fecha_days_in_month</th>\n",
|
898 |
+
" <th>fecha_hour</th>\n",
|
899 |
+
" <th>fecha_minute</th>\n",
|
900 |
+
" <th>fecha_second</th>\n",
|
901 |
+
" </tr>\n",
|
902 |
+
" </thead>\n",
|
903 |
+
" <tbody>\n",
|
904 |
+
" <tr>\n",
|
905 |
+
" <th>135569</th>\n",
|
906 |
+
" <td>1.000000</td>\n",
|
907 |
+
" <td>0.5217</td>\n",
|
908 |
+
" <td>0.635969</td>\n",
|
909 |
+
" <td>0.02</td>\n",
|
910 |
+
" <td>1.0</td>\n",
|
911 |
+
" <td>1.0</td>\n",
|
912 |
+
" <td>0.714286</td>\n",
|
913 |
+
" <td>0.620690</td>\n",
|
914 |
+
" <td>0.458599</td>\n",
|
915 |
+
" <td>0.636612</td>\n",
|
916 |
+
" <td>...</td>\n",
|
917 |
+
" <td>0.0</td>\n",
|
918 |
+
" <td>0.0</td>\n",
|
919 |
+
" <td>0.0</td>\n",
|
920 |
+
" <td>0.0</td>\n",
|
921 |
+
" <td>0.0</td>\n",
|
922 |
+
" <td>0.0</td>\n",
|
923 |
+
" <td>1.0</td>\n",
|
924 |
+
" <td>0.391304</td>\n",
|
925 |
+
" <td>0.525424</td>\n",
|
926 |
+
" <td>0.881356</td>\n",
|
927 |
+
" </tr>\n",
|
928 |
+
" <tr>\n",
|
929 |
+
" <th>78656</th>\n",
|
930 |
+
" <td>0.333333</td>\n",
|
931 |
+
" <td>0.7554</td>\n",
|
932 |
+
" <td>0.684908</td>\n",
|
933 |
+
" <td>0.02</td>\n",
|
934 |
+
" <td>0.0</td>\n",
|
935 |
+
" <td>1.0</td>\n",
|
936 |
+
" <td>0.428571</td>\n",
|
937 |
+
" <td>0.137931</td>\n",
|
938 |
+
" <td>0.133758</td>\n",
|
939 |
+
" <td>0.633268</td>\n",
|
940 |
+
" <td>...</td>\n",
|
941 |
+
" <td>0.0</td>\n",
|
942 |
+
" <td>0.0</td>\n",
|
943 |
+
" <td>0.0</td>\n",
|
944 |
+
" <td>0.0</td>\n",
|
945 |
+
" <td>0.0</td>\n",
|
946 |
+
" <td>0.0</td>\n",
|
947 |
+
" <td>1.0</td>\n",
|
948 |
+
" <td>0.347826</td>\n",
|
949 |
+
" <td>0.254237</td>\n",
|
950 |
+
" <td>0.288136</td>\n",
|
951 |
+
" </tr>\n",
|
952 |
+
" <tr>\n",
|
953 |
+
" <th>87437</th>\n",
|
954 |
+
" <td>1.000000</td>\n",
|
955 |
+
" <td>0.5437</td>\n",
|
956 |
+
" <td>0.741337</td>\n",
|
957 |
+
" <td>0.02</td>\n",
|
958 |
+
" <td>1.0</td>\n",
|
959 |
+
" <td>1.0</td>\n",
|
960 |
+
" <td>0.428571</td>\n",
|
961 |
+
" <td>0.793103</td>\n",
|
962 |
+
" <td>0.458599</td>\n",
|
963 |
+
" <td>0.735751</td>\n",
|
964 |
+
" <td>...</td>\n",
|
965 |
+
" <td>0.0</td>\n",
|
966 |
+
" <td>1.0</td>\n",
|
967 |
+
" <td>0.0</td>\n",
|
968 |
+
" <td>0.0</td>\n",
|
969 |
+
" <td>0.0</td>\n",
|
970 |
+
" <td>0.0</td>\n",
|
971 |
+
" <td>0.0</td>\n",
|
972 |
+
" <td>0.391304</td>\n",
|
973 |
+
" <td>0.050847</td>\n",
|
974 |
+
" <td>0.338983</td>\n",
|
975 |
+
" </tr>\n",
|
976 |
+
" <tr>\n",
|
977 |
+
" <th>131674</th>\n",
|
978 |
+
" <td>1.000000</td>\n",
|
979 |
+
" <td>0.7418</td>\n",
|
980 |
+
" <td>0.633959</td>\n",
|
981 |
+
" <td>1.00</td>\n",
|
982 |
+
" <td>1.0</td>\n",
|
983 |
+
" <td>1.0</td>\n",
|
984 |
+
" <td>0.714286</td>\n",
|
985 |
+
" <td>0.155172</td>\n",
|
986 |
+
" <td>0.458599</td>\n",
|
987 |
+
" <td>0.529368</td>\n",
|
988 |
+
" <td>...</td>\n",
|
989 |
+
" <td>0.0</td>\n",
|
990 |
+
" <td>0.0</td>\n",
|
991 |
+
" <td>0.0</td>\n",
|
992 |
+
" <td>0.0</td>\n",
|
993 |
+
" <td>0.0</td>\n",
|
994 |
+
" <td>0.0</td>\n",
|
995 |
+
" <td>0.0</td>\n",
|
996 |
+
" <td>0.782609</td>\n",
|
997 |
+
" <td>0.915254</td>\n",
|
998 |
+
" <td>0.101695</td>\n",
|
999 |
+
" </tr>\n",
|
1000 |
+
" <tr>\n",
|
1001 |
+
" <th>45535</th>\n",
|
1002 |
+
" <td>1.000000</td>\n",
|
1003 |
+
" <td>0.6463</td>\n",
|
1004 |
+
" <td>0.693916</td>\n",
|
1005 |
+
" <td>0.08</td>\n",
|
1006 |
+
" <td>1.0</td>\n",
|
1007 |
+
" <td>1.0</td>\n",
|
1008 |
+
" <td>0.428571</td>\n",
|
1009 |
+
" <td>0.379310</td>\n",
|
1010 |
+
" <td>0.458599</td>\n",
|
1011 |
+
" <td>0.049208</td>\n",
|
1012 |
+
" <td>...</td>\n",
|
1013 |
+
" <td>0.0</td>\n",
|
1014 |
+
" <td>0.0</td>\n",
|
1015 |
+
" <td>0.0</td>\n",
|
1016 |
+
" <td>0.0</td>\n",
|
1017 |
+
" <td>0.0</td>\n",
|
1018 |
+
" <td>0.0</td>\n",
|
1019 |
+
" <td>0.0</td>\n",
|
1020 |
+
" <td>0.913043</td>\n",
|
1021 |
+
" <td>0.406780</td>\n",
|
1022 |
+
" <td>0.508475</td>\n",
|
1023 |
+
" </tr>\n",
|
1024 |
+
" <tr>\n",
|
1025 |
+
" <th>...</th>\n",
|
1026 |
+
" <td>...</td>\n",
|
1027 |
+
" <td>...</td>\n",
|
1028 |
+
" <td>...</td>\n",
|
1029 |
+
" <td>...</td>\n",
|
1030 |
+
" <td>...</td>\n",
|
1031 |
+
" <td>...</td>\n",
|
1032 |
+
" <td>...</td>\n",
|
1033 |
+
" <td>...</td>\n",
|
1034 |
+
" <td>...</td>\n",
|
1035 |
+
" <td>...</td>\n",
|
1036 |
+
" <td>...</td>\n",
|
1037 |
+
" <td>...</td>\n",
|
1038 |
+
" <td>...</td>\n",
|
1039 |
+
" <td>...</td>\n",
|
1040 |
+
" <td>...</td>\n",
|
1041 |
+
" <td>...</td>\n",
|
1042 |
+
" <td>...</td>\n",
|
1043 |
+
" <td>...</td>\n",
|
1044 |
+
" <td>...</td>\n",
|
1045 |
+
" <td>...</td>\n",
|
1046 |
+
" <td>...</td>\n",
|
1047 |
+
" </tr>\n",
|
1048 |
+
" <tr>\n",
|
1049 |
+
" <th>41993</th>\n",
|
1050 |
+
" <td>1.000000</td>\n",
|
1051 |
+
" <td>0.8063</td>\n",
|
1052 |
+
" <td>0.831573</td>\n",
|
1053 |
+
" <td>0.06</td>\n",
|
1054 |
+
" <td>1.0</td>\n",
|
1055 |
+
" <td>0.0</td>\n",
|
1056 |
+
" <td>0.714286</td>\n",
|
1057 |
+
" <td>0.155172</td>\n",
|
1058 |
+
" <td>0.312102</td>\n",
|
1059 |
+
" <td>0.164571</td>\n",
|
1060 |
+
" <td>...</td>\n",
|
1061 |
+
" <td>0.0</td>\n",
|
1062 |
+
" <td>0.0</td>\n",
|
1063 |
+
" <td>0.0</td>\n",
|
1064 |
+
" <td>0.0</td>\n",
|
1065 |
+
" <td>0.0</td>\n",
|
1066 |
+
" <td>0.0</td>\n",
|
1067 |
+
" <td>0.0</td>\n",
|
1068 |
+
" <td>0.826087</td>\n",
|
1069 |
+
" <td>0.067797</td>\n",
|
1070 |
+
" <td>0.762712</td>\n",
|
1071 |
+
" </tr>\n",
|
1072 |
+
" <tr>\n",
|
1073 |
+
" <th>97639</th>\n",
|
1074 |
+
" <td>1.000000</td>\n",
|
1075 |
+
" <td>0.5046</td>\n",
|
1076 |
+
" <td>0.618473</td>\n",
|
1077 |
+
" <td>0.04</td>\n",
|
1078 |
+
" <td>0.0</td>\n",
|
1079 |
+
" <td>1.0</td>\n",
|
1080 |
+
" <td>0.428571</td>\n",
|
1081 |
+
" <td>0.155172</td>\n",
|
1082 |
+
" <td>0.458599</td>\n",
|
1083 |
+
" <td>0.288001</td>\n",
|
1084 |
+
" <td>...</td>\n",
|
1085 |
+
" <td>0.0</td>\n",
|
1086 |
+
" <td>0.0</td>\n",
|
1087 |
+
" <td>0.0</td>\n",
|
1088 |
+
" <td>0.0</td>\n",
|
1089 |
+
" <td>0.0</td>\n",
|
1090 |
+
" <td>0.0</td>\n",
|
1091 |
+
" <td>0.0</td>\n",
|
1092 |
+
" <td>0.826087</td>\n",
|
1093 |
+
" <td>0.169492</td>\n",
|
1094 |
+
" <td>0.186441</td>\n",
|
1095 |
+
" </tr>\n",
|
1096 |
+
" <tr>\n",
|
1097 |
+
" <th>95939</th>\n",
|
1098 |
+
" <td>1.000000</td>\n",
|
1099 |
+
" <td>0.7233</td>\n",
|
1100 |
+
" <td>0.686591</td>\n",
|
1101 |
+
" <td>0.02</td>\n",
|
1102 |
+
" <td>0.0</td>\n",
|
1103 |
+
" <td>0.0</td>\n",
|
1104 |
+
" <td>0.714286</td>\n",
|
1105 |
+
" <td>0.034483</td>\n",
|
1106 |
+
" <td>0.866242</td>\n",
|
1107 |
+
" <td>0.585850</td>\n",
|
1108 |
+
" <td>...</td>\n",
|
1109 |
+
" <td>0.0</td>\n",
|
1110 |
+
" <td>0.0</td>\n",
|
1111 |
+
" <td>0.0</td>\n",
|
1112 |
+
" <td>0.0</td>\n",
|
1113 |
+
" <td>0.0</td>\n",
|
1114 |
+
" <td>0.0</td>\n",
|
1115 |
+
" <td>1.0</td>\n",
|
1116 |
+
" <td>0.869565</td>\n",
|
1117 |
+
" <td>0.372881</td>\n",
|
1118 |
+
" <td>0.847458</td>\n",
|
1119 |
+
" </tr>\n",
|
1120 |
+
" <tr>\n",
|
1121 |
+
" <th>117952</th>\n",
|
1122 |
+
" <td>1.000000</td>\n",
|
1123 |
+
" <td>0.7824</td>\n",
|
1124 |
+
" <td>0.710351</td>\n",
|
1125 |
+
" <td>0.96</td>\n",
|
1126 |
+
" <td>1.0</td>\n",
|
1127 |
+
" <td>1.0</td>\n",
|
1128 |
+
" <td>0.714286</td>\n",
|
1129 |
+
" <td>0.086207</td>\n",
|
1130 |
+
" <td>0.458599</td>\n",
|
1131 |
+
" <td>0.007728</td>\n",
|
1132 |
+
" <td>...</td>\n",
|
1133 |
+
" <td>0.0</td>\n",
|
1134 |
+
" <td>0.0</td>\n",
|
1135 |
+
" <td>0.0</td>\n",
|
1136 |
+
" <td>0.0</td>\n",
|
1137 |
+
" <td>0.0</td>\n",
|
1138 |
+
" <td>0.0</td>\n",
|
1139 |
+
" <td>0.0</td>\n",
|
1140 |
+
" <td>0.000000</td>\n",
|
1141 |
+
" <td>0.406780</td>\n",
|
1142 |
+
" <td>0.779661</td>\n",
|
1143 |
+
" </tr>\n",
|
1144 |
+
" <tr>\n",
|
1145 |
+
" <th>43567</th>\n",
|
1146 |
+
" <td>1.000000</td>\n",
|
1147 |
+
" <td>0.7225</td>\n",
|
1148 |
+
" <td>0.468508</td>\n",
|
1149 |
+
" <td>1.00</td>\n",
|
1150 |
+
" <td>0.0</td>\n",
|
1151 |
+
" <td>1.0</td>\n",
|
1152 |
+
" <td>0.714286</td>\n",
|
1153 |
+
" <td>0.051724</td>\n",
|
1154 |
+
" <td>0.458599</td>\n",
|
1155 |
+
" <td>0.617746</td>\n",
|
1156 |
+
" <td>...</td>\n",
|
1157 |
+
" <td>0.0</td>\n",
|
1158 |
+
" <td>0.0</td>\n",
|
1159 |
+
" <td>0.0</td>\n",
|
1160 |
+
" <td>0.0</td>\n",
|
1161 |
+
" <td>0.0</td>\n",
|
1162 |
+
" <td>0.0</td>\n",
|
1163 |
+
" <td>1.0</td>\n",
|
1164 |
+
" <td>0.913043</td>\n",
|
1165 |
+
" <td>0.288136</td>\n",
|
1166 |
+
" <td>0.305085</td>\n",
|
1167 |
+
" </tr>\n",
|
1168 |
+
" </tbody>\n",
|
1169 |
+
"</table>\n",
|
1170 |
+
"<p>135000 rows Γ 45 columns</p>\n",
|
1171 |
+
"</div>"
|
1172 |
+
],
|
1173 |
+
"text/plain": [
|
1174 |
+
" a b c d e f g h \\\n",
|
1175 |
+
"135569 1.000000 0.5217 0.635969 0.02 1.0 1.0 0.714286 0.620690 \n",
|
1176 |
+
"78656 0.333333 0.7554 0.684908 0.02 0.0 1.0 0.428571 0.137931 \n",
|
1177 |
+
"87437 1.000000 0.5437 0.741337 0.02 1.0 1.0 0.428571 0.793103 \n",
|
1178 |
+
"131674 1.000000 0.7418 0.633959 1.00 1.0 1.0 0.714286 0.155172 \n",
|
1179 |
+
"45535 1.000000 0.6463 0.693916 0.08 1.0 1.0 0.428571 0.379310 \n",
|
1180 |
+
"... ... ... ... ... ... ... ... ... \n",
|
1181 |
+
"41993 1.000000 0.8063 0.831573 0.06 1.0 0.0 0.714286 0.155172 \n",
|
1182 |
+
"97639 1.000000 0.5046 0.618473 0.04 0.0 1.0 0.428571 0.155172 \n",
|
1183 |
+
"95939 1.000000 0.7233 0.686591 0.02 0.0 0.0 0.714286 0.034483 \n",
|
1184 |
+
"117952 1.000000 0.7824 0.710351 0.96 1.0 1.0 0.714286 0.086207 \n",
|
1185 |
+
"43567 1.000000 0.7225 0.468508 1.00 0.0 1.0 0.714286 0.051724 \n",
|
1186 |
+
"\n",
|
1187 |
+
" j k ... fecha_month_end fecha_quarter_start \\\n",
|
1188 |
+
"135569 0.458599 0.636612 ... 0.0 0.0 \n",
|
1189 |
+
"78656 0.133758 0.633268 ... 0.0 0.0 \n",
|
1190 |
+
"87437 0.458599 0.735751 ... 0.0 1.0 \n",
|
1191 |
+
"131674 0.458599 0.529368 ... 0.0 0.0 \n",
|
1192 |
+
"45535 0.458599 0.049208 ... 0.0 0.0 \n",
|
1193 |
+
"... ... ... ... ... ... \n",
|
1194 |
+
"41993 0.312102 0.164571 ... 0.0 0.0 \n",
|
1195 |
+
"97639 0.458599 0.288001 ... 0.0 0.0 \n",
|
1196 |
+
"95939 0.866242 0.585850 ... 0.0 0.0 \n",
|
1197 |
+
"117952 0.458599 0.007728 ... 0.0 0.0 \n",
|
1198 |
+
"43567 0.458599 0.617746 ... 0.0 0.0 \n",
|
1199 |
+
"\n",
|
1200 |
+
" fecha_quarter_end fecha_year_start fecha_year_end fecha_leap_year \\\n",
|
1201 |
+
"135569 0.0 0.0 0.0 0.0 \n",
|
1202 |
+
"78656 0.0 0.0 0.0 0.0 \n",
|
1203 |
+
"87437 0.0 0.0 0.0 0.0 \n",
|
1204 |
+
"131674 0.0 0.0 0.0 0.0 \n",
|
1205 |
+
"45535 0.0 0.0 0.0 0.0 \n",
|
1206 |
+
"... ... ... ... ... \n",
|
1207 |
+
"41993 0.0 0.0 0.0 0.0 \n",
|
1208 |
+
"97639 0.0 0.0 0.0 0.0 \n",
|
1209 |
+
"95939 0.0 0.0 0.0 0.0 \n",
|
1210 |
+
"117952 0.0 0.0 0.0 0.0 \n",
|
1211 |
+
"43567 0.0 0.0 0.0 0.0 \n",
|
1212 |
+
"\n",
|
1213 |
+
" fecha_days_in_month fecha_hour fecha_minute fecha_second \n",
|
1214 |
+
"135569 1.0 0.391304 0.525424 0.881356 \n",
|
1215 |
+
"78656 1.0 0.347826 0.254237 0.288136 \n",
|
1216 |
+
"87437 0.0 0.391304 0.050847 0.338983 \n",
|
1217 |
+
"131674 0.0 0.782609 0.915254 0.101695 \n",
|
1218 |
+
"45535 0.0 0.913043 0.406780 0.508475 \n",
|
1219 |
+
"... ... ... ... ... \n",
|
1220 |
+
"41993 0.0 0.826087 0.067797 0.762712 \n",
|
1221 |
+
"97639 0.0 0.826087 0.169492 0.186441 \n",
|
1222 |
+
"95939 1.0 0.869565 0.372881 0.847458 \n",
|
1223 |
+
"117952 0.0 0.000000 0.406780 0.779661 \n",
|
1224 |
+
"43567 1.0 0.913043 0.288136 0.305085 \n",
|
1225 |
+
"\n",
|
1226 |
+
"[135000 rows x 45 columns]"
|
1227 |
+
]
|
1228 |
+
},
|
1229 |
+
"execution_count": 19,
|
1230 |
+
"metadata": {},
|
1231 |
+
"output_type": "execute_result"
|
1232 |
+
}
|
1233 |
+
],
|
1234 |
+
"source": [
|
1235 |
+
"fraud_pipeline.transform(X_train)"
|
1236 |
+
]
|
1237 |
+
},
|
1238 |
+
{
|
1239 |
+
"cell_type": "code",
|
1240 |
+
"execution_count": 20,
|
1241 |
+
"metadata": {},
|
1242 |
+
"outputs": [
|
1243 |
+
{
|
1244 |
+
"data": {
|
1245 |
+
"text/plain": [
|
1246 |
+
"['../models/feature_engineering_pipeline.joblib']"
|
1247 |
+
]
|
1248 |
+
},
|
1249 |
+
"execution_count": 20,
|
1250 |
+
"metadata": {},
|
1251 |
+
"output_type": "execute_result"
|
1252 |
+
}
|
1253 |
+
],
|
1254 |
+
"source": [
|
1255 |
+
"joblib.dump(fraud_pipeline, '../models/feature_engineering_pipeline.joblib')"
|
1256 |
+
]
|
1257 |
+
},
|
1258 |
+
{
|
1259 |
+
"cell_type": "code",
|
1260 |
+
"execution_count": null,
|
1261 |
+
"metadata": {},
|
1262 |
+
"outputs": [],
|
1263 |
+
"source": []
|
1264 |
+
}
|
1265 |
+
],
|
1266 |
+
"metadata": {
|
1267 |
+
"kernelspec": {
|
1268 |
+
"display_name": "fraud-detection",
|
1269 |
+
"language": "python",
|
1270 |
+
"name": "python3"
|
1271 |
+
},
|
1272 |
+
"language_info": {
|
1273 |
+
"codemirror_mode": {
|
1274 |
+
"name": "ipython",
|
1275 |
+
"version": 3
|
1276 |
+
},
|
1277 |
+
"file_extension": ".py",
|
1278 |
+
"mimetype": "text/x-python",
|
1279 |
+
"name": "python",
|
1280 |
+
"nbconvert_exporter": "python",
|
1281 |
+
"pygments_lexer": "ipython3",
|
1282 |
+
"version": "3.10.12"
|
1283 |
+
},
|
1284 |
+
"orig_nbformat": 4,
|
1285 |
+
"vscode": {
|
1286 |
+
"interpreter": {
|
1287 |
+
"hash": "45e631c81adbf0cb55b2526738ae1a14c53cfa3f28a6ae1bee5619daf3ab935d"
|
1288 |
+
}
|
1289 |
+
}
|
1290 |
+
},
|
1291 |
+
"nbformat": 4,
|
1292 |
+
"nbformat_minor": 2
|
1293 |
+
}
|
notebooks/03-feature_selection.ipynb
ADDED
@@ -0,0 +1,837 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cells": [
|
3 |
+
{
|
4 |
+
"cell_type": "code",
|
5 |
+
"execution_count": 1,
|
6 |
+
"metadata": {},
|
7 |
+
"outputs": [],
|
8 |
+
"source": [
|
9 |
+
"import joblib\n",
|
10 |
+
"import pandas as pd\n",
|
11 |
+
"from feature_engine.selection import ProbeFeatureSelection\n",
|
12 |
+
"from sklearn.model_selection import train_test_split\n",
|
13 |
+
"from sklearn.ensemble import RandomForestClassifier\n",
|
14 |
+
"from sklearn.linear_model import LogisticRegression"
|
15 |
+
]
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"cell_type": "code",
|
19 |
+
"execution_count": 2,
|
20 |
+
"metadata": {},
|
21 |
+
"outputs": [
|
22 |
+
{
|
23 |
+
"name": "stdout",
|
24 |
+
"output_type": "stream",
|
25 |
+
"text": [
|
26 |
+
"(150000, 19)\n"
|
27 |
+
]
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"data": {
|
31 |
+
"text/html": [
|
32 |
+
"<div>\n",
|
33 |
+
"<style scoped>\n",
|
34 |
+
" .dataframe tbody tr th:only-of-type {\n",
|
35 |
+
" vertical-align: middle;\n",
|
36 |
+
" }\n",
|
37 |
+
"\n",
|
38 |
+
" .dataframe tbody tr th {\n",
|
39 |
+
" vertical-align: top;\n",
|
40 |
+
" }\n",
|
41 |
+
"\n",
|
42 |
+
" .dataframe thead th {\n",
|
43 |
+
" text-align: right;\n",
|
44 |
+
" }\n",
|
45 |
+
"</style>\n",
|
46 |
+
"<table border=\"1\" class=\"dataframe\">\n",
|
47 |
+
" <thead>\n",
|
48 |
+
" <tr style=\"text-align: right;\">\n",
|
49 |
+
" <th></th>\n",
|
50 |
+
" <th>a</th>\n",
|
51 |
+
" <th>b</th>\n",
|
52 |
+
" <th>c</th>\n",
|
53 |
+
" <th>d</th>\n",
|
54 |
+
" <th>e</th>\n",
|
55 |
+
" <th>f</th>\n",
|
56 |
+
" <th>g</th>\n",
|
57 |
+
" <th>h</th>\n",
|
58 |
+
" <th>j</th>\n",
|
59 |
+
" <th>k</th>\n",
|
60 |
+
" <th>l</th>\n",
|
61 |
+
" <th>m</th>\n",
|
62 |
+
" <th>n</th>\n",
|
63 |
+
" <th>o</th>\n",
|
64 |
+
" <th>p</th>\n",
|
65 |
+
" <th>fecha</th>\n",
|
66 |
+
" <th>monto</th>\n",
|
67 |
+
" <th>score</th>\n",
|
68 |
+
" <th>fraude</th>\n",
|
69 |
+
" </tr>\n",
|
70 |
+
" </thead>\n",
|
71 |
+
" <tbody>\n",
|
72 |
+
" <tr>\n",
|
73 |
+
" <th>0</th>\n",
|
74 |
+
" <td>4</td>\n",
|
75 |
+
" <td>0.6812</td>\n",
|
76 |
+
" <td>50084.12</td>\n",
|
77 |
+
" <td>50.0</td>\n",
|
78 |
+
" <td>0.000000</td>\n",
|
79 |
+
" <td>20.0</td>\n",
|
80 |
+
" <td>AR</td>\n",
|
81 |
+
" <td>1</td>\n",
|
82 |
+
" <td>cat_d26ab52</td>\n",
|
83 |
+
" <td>0.365475</td>\n",
|
84 |
+
" <td>2479.0</td>\n",
|
85 |
+
" <td>952.0</td>\n",
|
86 |
+
" <td>1</td>\n",
|
87 |
+
" <td>NaN</td>\n",
|
88 |
+
" <td>Y</td>\n",
|
89 |
+
" <td>2020-03-20 09:28:19</td>\n",
|
90 |
+
" <td>57.63</td>\n",
|
91 |
+
" <td>100</td>\n",
|
92 |
+
" <td>0</td>\n",
|
93 |
+
" </tr>\n",
|
94 |
+
" <tr>\n",
|
95 |
+
" <th>1</th>\n",
|
96 |
+
" <td>4</td>\n",
|
97 |
+
" <td>0.6694</td>\n",
|
98 |
+
" <td>66005.49</td>\n",
|
99 |
+
" <td>0.0</td>\n",
|
100 |
+
" <td>0.000000</td>\n",
|
101 |
+
" <td>2.0</td>\n",
|
102 |
+
" <td>AR</td>\n",
|
103 |
+
" <td>1</td>\n",
|
104 |
+
" <td>cat_ea962fb</td>\n",
|
105 |
+
" <td>0.612728</td>\n",
|
106 |
+
" <td>2603.0</td>\n",
|
107 |
+
" <td>105.0</td>\n",
|
108 |
+
" <td>1</td>\n",
|
109 |
+
" <td>Y</td>\n",
|
110 |
+
" <td>Y</td>\n",
|
111 |
+
" <td>2020-03-09 13:58:28</td>\n",
|
112 |
+
" <td>40.19</td>\n",
|
113 |
+
" <td>25</td>\n",
|
114 |
+
" <td>0</td>\n",
|
115 |
+
" </tr>\n",
|
116 |
+
" <tr>\n",
|
117 |
+
" <th>2</th>\n",
|
118 |
+
" <td>4</td>\n",
|
119 |
+
" <td>0.4718</td>\n",
|
120 |
+
" <td>7059.05</td>\n",
|
121 |
+
" <td>4.0</td>\n",
|
122 |
+
" <td>0.463488</td>\n",
|
123 |
+
" <td>92.0</td>\n",
|
124 |
+
" <td>BR</td>\n",
|
125 |
+
" <td>25</td>\n",
|
126 |
+
" <td>cat_4c2544e</td>\n",
|
127 |
+
" <td>0.651835</td>\n",
|
128 |
+
" <td>2153.0</td>\n",
|
129 |
+
" <td>249.0</td>\n",
|
130 |
+
" <td>1</td>\n",
|
131 |
+
" <td>Y</td>\n",
|
132 |
+
" <td>Y</td>\n",
|
133 |
+
" <td>2020-04-08 12:25:55</td>\n",
|
134 |
+
" <td>5.77</td>\n",
|
135 |
+
" <td>23</td>\n",
|
136 |
+
" <td>0</td>\n",
|
137 |
+
" </tr>\n",
|
138 |
+
" <tr>\n",
|
139 |
+
" <th>3</th>\n",
|
140 |
+
" <td>4</td>\n",
|
141 |
+
" <td>0.7260</td>\n",
|
142 |
+
" <td>10043.10</td>\n",
|
143 |
+
" <td>24.0</td>\n",
|
144 |
+
" <td>0.046845</td>\n",
|
145 |
+
" <td>43.0</td>\n",
|
146 |
+
" <td>BR</td>\n",
|
147 |
+
" <td>43</td>\n",
|
148 |
+
" <td>cat_1b59ee3</td>\n",
|
149 |
+
" <td>0.692728</td>\n",
|
150 |
+
" <td>4845.0</td>\n",
|
151 |
+
" <td>141.0</td>\n",
|
152 |
+
" <td>1</td>\n",
|
153 |
+
" <td>N</td>\n",
|
154 |
+
" <td>Y</td>\n",
|
155 |
+
" <td>2020-03-14 11:46:13</td>\n",
|
156 |
+
" <td>40.89</td>\n",
|
157 |
+
" <td>23</td>\n",
|
158 |
+
" <td>0</td>\n",
|
159 |
+
" </tr>\n",
|
160 |
+
" <tr>\n",
|
161 |
+
" <th>4</th>\n",
|
162 |
+
" <td>4</td>\n",
|
163 |
+
" <td>0.7758</td>\n",
|
164 |
+
" <td>16584.42</td>\n",
|
165 |
+
" <td>2.0</td>\n",
|
166 |
+
" <td>0.154616</td>\n",
|
167 |
+
" <td>54.0</td>\n",
|
168 |
+
" <td>BR</td>\n",
|
169 |
+
" <td>0</td>\n",
|
170 |
+
" <td>cat_9bacaa5</td>\n",
|
171 |
+
" <td>0.201354</td>\n",
|
172 |
+
" <td>2856.0</td>\n",
|
173 |
+
" <td>18.0</td>\n",
|
174 |
+
" <td>1</td>\n",
|
175 |
+
" <td>Y</td>\n",
|
176 |
+
" <td>N</td>\n",
|
177 |
+
" <td>2020-03-23 14:17:13</td>\n",
|
178 |
+
" <td>18.98</td>\n",
|
179 |
+
" <td>71</td>\n",
|
180 |
+
" <td>0</td>\n",
|
181 |
+
" </tr>\n",
|
182 |
+
" </tbody>\n",
|
183 |
+
"</table>\n",
|
184 |
+
"</div>"
|
185 |
+
],
|
186 |
+
"text/plain": [
|
187 |
+
" a b c d e f g h j k \\\n",
|
188 |
+
"0 4 0.6812 50084.12 50.0 0.000000 20.0 AR 1 cat_d26ab52 0.365475 \n",
|
189 |
+
"1 4 0.6694 66005.49 0.0 0.000000 2.0 AR 1 cat_ea962fb 0.612728 \n",
|
190 |
+
"2 4 0.4718 7059.05 4.0 0.463488 92.0 BR 25 cat_4c2544e 0.651835 \n",
|
191 |
+
"3 4 0.7260 10043.10 24.0 0.046845 43.0 BR 43 cat_1b59ee3 0.692728 \n",
|
192 |
+
"4 4 0.7758 16584.42 2.0 0.154616 54.0 BR 0 cat_9bacaa5 0.201354 \n",
|
193 |
+
"\n",
|
194 |
+
" l m n o p fecha monto score fraude \n",
|
195 |
+
"0 2479.0 952.0 1 NaN Y 2020-03-20 09:28:19 57.63 100 0 \n",
|
196 |
+
"1 2603.0 105.0 1 Y Y 2020-03-09 13:58:28 40.19 25 0 \n",
|
197 |
+
"2 2153.0 249.0 1 Y Y 2020-04-08 12:25:55 5.77 23 0 \n",
|
198 |
+
"3 4845.0 141.0 1 N Y 2020-03-14 11:46:13 40.89 23 0 \n",
|
199 |
+
"4 2856.0 18.0 1 Y N 2020-03-23 14:17:13 18.98 71 0 "
|
200 |
+
]
|
201 |
+
},
|
202 |
+
"execution_count": 2,
|
203 |
+
"metadata": {},
|
204 |
+
"output_type": "execute_result"
|
205 |
+
}
|
206 |
+
],
|
207 |
+
"source": [
|
208 |
+
"data = pd.read_csv('../data/MercadoLibre Data Scientist Technical Challenge - Dataset.csv')\n",
|
209 |
+
"print(data.shape)\n",
|
210 |
+
"data.head()"
|
211 |
+
]
|
212 |
+
},
|
213 |
+
{
|
214 |
+
"cell_type": "code",
|
215 |
+
"execution_count": 3,
|
216 |
+
"metadata": {},
|
217 |
+
"outputs": [
|
218 |
+
{
|
219 |
+
"data": {
|
220 |
+
"text/plain": [
|
221 |
+
"((135000, 18), (15000, 18))"
|
222 |
+
]
|
223 |
+
},
|
224 |
+
"execution_count": 3,
|
225 |
+
"metadata": {},
|
226 |
+
"output_type": "execute_result"
|
227 |
+
}
|
228 |
+
],
|
229 |
+
"source": [
|
230 |
+
"X_train, X_test, y_train, y_test = train_test_split(\n",
|
231 |
+
" data.drop(['fraude'], axis=1), # predictive variables\n",
|
232 |
+
" data['fraude'], # target\n",
|
233 |
+
" test_size=0.1, # portion of dataset to allocate to test set\n",
|
234 |
+
" random_state=0, # we are setting the seed here\n",
|
235 |
+
")\n",
|
236 |
+
"\n",
|
237 |
+
"X_train.shape, X_test.shape"
|
238 |
+
]
|
239 |
+
},
|
240 |
+
{
|
241 |
+
"cell_type": "code",
|
242 |
+
"execution_count": 4,
|
243 |
+
"metadata": {},
|
244 |
+
"outputs": [],
|
245 |
+
"source": [
|
246 |
+
"fraud_pipeline = joblib.load('../models/feature_engineering_pipeline.joblib')"
|
247 |
+
]
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"cell_type": "code",
|
251 |
+
"execution_count": 5,
|
252 |
+
"metadata": {},
|
253 |
+
"outputs": [
|
254 |
+
{
|
255 |
+
"data": {
|
256 |
+
"text/html": [
|
257 |
+
"<style>#sk-container-id-1 {color: black;}#sk-container-id-1 pre{padding: 0;}#sk-container-id-1 div.sk-toggleable {background-color: white;}#sk-container-id-1 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-1 label.sk-toggleable__label-arrow:before {content: \"βΈ\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-1 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-1 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-1 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"βΎ\";}#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-1 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-1 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-1 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-1 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-1 div.sk-item {position: relative;z-index: 1;}#sk-container-id-1 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-1 div.sk-item::before, #sk-container-id-1 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-1 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-1 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-1 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-1 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-1 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-1 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-1 div.sk-label-container {text-align: center;}#sk-container-id-1 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-1 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>Pipeline(steps=[('missing_indicator',\n",
|
258 |
+
" AddMissingIndicator(variables=['b', 'c', 'd', 'f', 'g', 'l',\n",
|
259 |
+
" 'm', 'o'])),\n",
|
260 |
+
" ('numerical_imputer',\n",
|
261 |
+
" MeanMedianImputer(variables=['b', 'c', 'd', 'f', 'l', 'm'])),\n",
|
262 |
+
" ('categorical_imputer',\n",
|
263 |
+
" CategoricalImputer(fill_value='missing',\n",
|
264 |
+
" variables=['g', 'o'])),\n",
|
265 |
+
" ('numerical_transformation',\n",
|
266 |
+
" LogTransformer(variables=['c', 'monto'])),\n",
|
267 |
+
" ('binarizer',\n",
|
268 |
+
" ArbitraryDiscretiser(binning_dict={'e': [-inf, 0, inf],\n",
|
269 |
+
" 'f': [-inf, 0, inf]})),\n",
|
270 |
+
" ('rare_label_encoder',\n",
|
271 |
+
" RareLabelEncoder(n_categories=1, tol=0.001,\n",
|
272 |
+
" variables=['g', 'j', 'o', 'p'])),\n",
|
273 |
+
" ('ordinal_encoder',\n",
|
274 |
+
" OrdinalEncoder(variables=['g', 'j', 'o', 'p'])),\n",
|
275 |
+
" ('datetime_features',\n",
|
276 |
+
" DatetimeFeatures(features_to_extract='all',\n",
|
277 |
+
" variables='fecha')),\n",
|
278 |
+
" ('scaler', ScalerDf(method='minmax'))])</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" ><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">Pipeline</label><div class=\"sk-toggleable__content\"><pre>Pipeline(steps=[('missing_indicator',\n",
|
279 |
+
" AddMissingIndicator(variables=['b', 'c', 'd', 'f', 'g', 'l',\n",
|
280 |
+
" 'm', 'o'])),\n",
|
281 |
+
" ('numerical_imputer',\n",
|
282 |
+
" MeanMedianImputer(variables=['b', 'c', 'd', 'f', 'l', 'm'])),\n",
|
283 |
+
" ('categorical_imputer',\n",
|
284 |
+
" CategoricalImputer(fill_value='missing',\n",
|
285 |
+
" variables=['g', 'o'])),\n",
|
286 |
+
" ('numerical_transformation',\n",
|
287 |
+
" LogTransformer(variables=['c', 'monto'])),\n",
|
288 |
+
" ('binarizer',\n",
|
289 |
+
" ArbitraryDiscretiser(binning_dict={'e': [-inf, 0, inf],\n",
|
290 |
+
" 'f': [-inf, 0, inf]})),\n",
|
291 |
+
" ('rare_label_encoder',\n",
|
292 |
+
" RareLabelEncoder(n_categories=1, tol=0.001,\n",
|
293 |
+
" variables=['g', 'j', 'o', 'p'])),\n",
|
294 |
+
" ('ordinal_encoder',\n",
|
295 |
+
" OrdinalEncoder(variables=['g', 'j', 'o', 'p'])),\n",
|
296 |
+
" ('datetime_features',\n",
|
297 |
+
" DatetimeFeatures(features_to_extract='all',\n",
|
298 |
+
" variables='fecha')),\n",
|
299 |
+
" ('scaler', ScalerDf(method='minmax'))])</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" ><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">AddMissingIndicator</label><div class=\"sk-toggleable__content\"><pre>AddMissingIndicator(variables=['b', 'c', 'd', 'f', 'g', 'l', 'm', 'o'])</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-3\" type=\"checkbox\" ><label for=\"sk-estimator-id-3\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">MeanMedianImputer</label><div class=\"sk-toggleable__content\"><pre>MeanMedianImputer(variables=['b', 'c', 'd', 'f', 'l', 'm'])</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-4\" type=\"checkbox\" ><label for=\"sk-estimator-id-4\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">CategoricalImputer</label><div class=\"sk-toggleable__content\"><pre>CategoricalImputer(fill_value='missing', variables=['g', 'o'])</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-5\" type=\"checkbox\" ><label for=\"sk-estimator-id-5\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">LogTransformer</label><div class=\"sk-toggleable__content\"><pre>LogTransformer(variables=['c', 'monto'])</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-6\" type=\"checkbox\" ><label for=\"sk-estimator-id-6\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">ArbitraryDiscretiser</label><div class=\"sk-toggleable__content\"><pre>ArbitraryDiscretiser(binning_dict={'e': [-inf, 0, inf], 'f': [-inf, 0, inf]})</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-7\" type=\"checkbox\" ><label for=\"sk-estimator-id-7\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">RareLabelEncoder</label><div class=\"sk-toggleable__content\"><pre>RareLabelEncoder(n_categories=1, tol=0.001, variables=['g', 'j', 'o', 'p'])</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-8\" type=\"checkbox\" ><label for=\"sk-estimator-id-8\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">OrdinalEncoder</label><div class=\"sk-toggleable__content\"><pre>OrdinalEncoder(variables=['g', 'j', 'o', 'p'])</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-9\" type=\"checkbox\" ><label for=\"sk-estimator-id-9\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">DatetimeFeatures</label><div class=\"sk-toggleable__content\"><pre>DatetimeFeatures(features_to_extract='all', variables='fecha')</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-10\" type=\"checkbox\" ><label for=\"sk-estimator-id-10\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">ScalerDf</label><div class=\"sk-toggleable__content\"><pre>ScalerDf(method='minmax')</pre></div></div></div></div></div></div></div>"
|
300 |
+
],
|
301 |
+
"text/plain": [
|
302 |
+
"Pipeline(steps=[('missing_indicator',\n",
|
303 |
+
" AddMissingIndicator(variables=['b', 'c', 'd', 'f', 'g', 'l',\n",
|
304 |
+
" 'm', 'o'])),\n",
|
305 |
+
" ('numerical_imputer',\n",
|
306 |
+
" MeanMedianImputer(variables=['b', 'c', 'd', 'f', 'l', 'm'])),\n",
|
307 |
+
" ('categorical_imputer',\n",
|
308 |
+
" CategoricalImputer(fill_value='missing',\n",
|
309 |
+
" variables=['g', 'o'])),\n",
|
310 |
+
" ('numerical_transformation',\n",
|
311 |
+
" LogTransformer(variables=['c', 'monto'])),\n",
|
312 |
+
" ('binarizer',\n",
|
313 |
+
" ArbitraryDiscretiser(binning_dict={'e': [-inf, 0, inf],\n",
|
314 |
+
" 'f': [-inf, 0, inf]})),\n",
|
315 |
+
" ('rare_label_encoder',\n",
|
316 |
+
" RareLabelEncoder(n_categories=1, tol=0.001,\n",
|
317 |
+
" variables=['g', 'j', 'o', 'p'])),\n",
|
318 |
+
" ('ordinal_encoder',\n",
|
319 |
+
" OrdinalEncoder(variables=['g', 'j', 'o', 'p'])),\n",
|
320 |
+
" ('datetime_features',\n",
|
321 |
+
" DatetimeFeatures(features_to_extract='all',\n",
|
322 |
+
" variables='fecha')),\n",
|
323 |
+
" ('scaler', ScalerDf(method='minmax'))])"
|
324 |
+
]
|
325 |
+
},
|
326 |
+
"execution_count": 5,
|
327 |
+
"metadata": {},
|
328 |
+
"output_type": "execute_result"
|
329 |
+
}
|
330 |
+
],
|
331 |
+
"source": [
|
332 |
+
"fraud_pipeline"
|
333 |
+
]
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"cell_type": "code",
|
337 |
+
"execution_count": 6,
|
338 |
+
"metadata": {},
|
339 |
+
"outputs": [],
|
340 |
+
"source": [
|
341 |
+
"X_train_transformed = fraud_pipeline.transform(X_train)"
|
342 |
+
]
|
343 |
+
},
|
344 |
+
{
|
345 |
+
"cell_type": "code",
|
346 |
+
"execution_count": 7,
|
347 |
+
"metadata": {},
|
348 |
+
"outputs": [
|
349 |
+
{
|
350 |
+
"data": {
|
351 |
+
"text/html": [
|
352 |
+
"<div>\n",
|
353 |
+
"<style scoped>\n",
|
354 |
+
" .dataframe tbody tr th:only-of-type {\n",
|
355 |
+
" vertical-align: middle;\n",
|
356 |
+
" }\n",
|
357 |
+
"\n",
|
358 |
+
" .dataframe tbody tr th {\n",
|
359 |
+
" vertical-align: top;\n",
|
360 |
+
" }\n",
|
361 |
+
"\n",
|
362 |
+
" .dataframe thead th {\n",
|
363 |
+
" text-align: right;\n",
|
364 |
+
" }\n",
|
365 |
+
"</style>\n",
|
366 |
+
"<table border=\"1\" class=\"dataframe\">\n",
|
367 |
+
" <thead>\n",
|
368 |
+
" <tr style=\"text-align: right;\">\n",
|
369 |
+
" <th></th>\n",
|
370 |
+
" <th>a</th>\n",
|
371 |
+
" <th>b</th>\n",
|
372 |
+
" <th>c</th>\n",
|
373 |
+
" <th>d</th>\n",
|
374 |
+
" <th>e</th>\n",
|
375 |
+
" <th>f</th>\n",
|
376 |
+
" <th>g</th>\n",
|
377 |
+
" <th>h</th>\n",
|
378 |
+
" <th>j</th>\n",
|
379 |
+
" <th>k</th>\n",
|
380 |
+
" <th>...</th>\n",
|
381 |
+
" <th>fecha_month_end</th>\n",
|
382 |
+
" <th>fecha_quarter_start</th>\n",
|
383 |
+
" <th>fecha_quarter_end</th>\n",
|
384 |
+
" <th>fecha_year_start</th>\n",
|
385 |
+
" <th>fecha_year_end</th>\n",
|
386 |
+
" <th>fecha_leap_year</th>\n",
|
387 |
+
" <th>fecha_days_in_month</th>\n",
|
388 |
+
" <th>fecha_hour</th>\n",
|
389 |
+
" <th>fecha_minute</th>\n",
|
390 |
+
" <th>fecha_second</th>\n",
|
391 |
+
" </tr>\n",
|
392 |
+
" </thead>\n",
|
393 |
+
" <tbody>\n",
|
394 |
+
" <tr>\n",
|
395 |
+
" <th>135569</th>\n",
|
396 |
+
" <td>1.000000</td>\n",
|
397 |
+
" <td>0.5217</td>\n",
|
398 |
+
" <td>0.635969</td>\n",
|
399 |
+
" <td>0.02</td>\n",
|
400 |
+
" <td>1.0</td>\n",
|
401 |
+
" <td>1.0</td>\n",
|
402 |
+
" <td>0.714286</td>\n",
|
403 |
+
" <td>0.620690</td>\n",
|
404 |
+
" <td>0.458599</td>\n",
|
405 |
+
" <td>0.636612</td>\n",
|
406 |
+
" <td>...</td>\n",
|
407 |
+
" <td>0.0</td>\n",
|
408 |
+
" <td>0.0</td>\n",
|
409 |
+
" <td>0.0</td>\n",
|
410 |
+
" <td>0.0</td>\n",
|
411 |
+
" <td>0.0</td>\n",
|
412 |
+
" <td>0.0</td>\n",
|
413 |
+
" <td>1.0</td>\n",
|
414 |
+
" <td>0.391304</td>\n",
|
415 |
+
" <td>0.525424</td>\n",
|
416 |
+
" <td>0.881356</td>\n",
|
417 |
+
" </tr>\n",
|
418 |
+
" <tr>\n",
|
419 |
+
" <th>78656</th>\n",
|
420 |
+
" <td>0.333333</td>\n",
|
421 |
+
" <td>0.7554</td>\n",
|
422 |
+
" <td>0.684908</td>\n",
|
423 |
+
" <td>0.02</td>\n",
|
424 |
+
" <td>0.0</td>\n",
|
425 |
+
" <td>1.0</td>\n",
|
426 |
+
" <td>0.428571</td>\n",
|
427 |
+
" <td>0.137931</td>\n",
|
428 |
+
" <td>0.133758</td>\n",
|
429 |
+
" <td>0.633268</td>\n",
|
430 |
+
" <td>...</td>\n",
|
431 |
+
" <td>0.0</td>\n",
|
432 |
+
" <td>0.0</td>\n",
|
433 |
+
" <td>0.0</td>\n",
|
434 |
+
" <td>0.0</td>\n",
|
435 |
+
" <td>0.0</td>\n",
|
436 |
+
" <td>0.0</td>\n",
|
437 |
+
" <td>1.0</td>\n",
|
438 |
+
" <td>0.347826</td>\n",
|
439 |
+
" <td>0.254237</td>\n",
|
440 |
+
" <td>0.288136</td>\n",
|
441 |
+
" </tr>\n",
|
442 |
+
" <tr>\n",
|
443 |
+
" <th>87437</th>\n",
|
444 |
+
" <td>1.000000</td>\n",
|
445 |
+
" <td>0.5437</td>\n",
|
446 |
+
" <td>0.741337</td>\n",
|
447 |
+
" <td>0.02</td>\n",
|
448 |
+
" <td>1.0</td>\n",
|
449 |
+
" <td>1.0</td>\n",
|
450 |
+
" <td>0.428571</td>\n",
|
451 |
+
" <td>0.793103</td>\n",
|
452 |
+
" <td>0.458599</td>\n",
|
453 |
+
" <td>0.735751</td>\n",
|
454 |
+
" <td>...</td>\n",
|
455 |
+
" <td>0.0</td>\n",
|
456 |
+
" <td>1.0</td>\n",
|
457 |
+
" <td>0.0</td>\n",
|
458 |
+
" <td>0.0</td>\n",
|
459 |
+
" <td>0.0</td>\n",
|
460 |
+
" <td>0.0</td>\n",
|
461 |
+
" <td>0.0</td>\n",
|
462 |
+
" <td>0.391304</td>\n",
|
463 |
+
" <td>0.050847</td>\n",
|
464 |
+
" <td>0.338983</td>\n",
|
465 |
+
" </tr>\n",
|
466 |
+
" <tr>\n",
|
467 |
+
" <th>131674</th>\n",
|
468 |
+
" <td>1.000000</td>\n",
|
469 |
+
" <td>0.7418</td>\n",
|
470 |
+
" <td>0.633959</td>\n",
|
471 |
+
" <td>1.00</td>\n",
|
472 |
+
" <td>1.0</td>\n",
|
473 |
+
" <td>1.0</td>\n",
|
474 |
+
" <td>0.714286</td>\n",
|
475 |
+
" <td>0.155172</td>\n",
|
476 |
+
" <td>0.458599</td>\n",
|
477 |
+
" <td>0.529368</td>\n",
|
478 |
+
" <td>...</td>\n",
|
479 |
+
" <td>0.0</td>\n",
|
480 |
+
" <td>0.0</td>\n",
|
481 |
+
" <td>0.0</td>\n",
|
482 |
+
" <td>0.0</td>\n",
|
483 |
+
" <td>0.0</td>\n",
|
484 |
+
" <td>0.0</td>\n",
|
485 |
+
" <td>0.0</td>\n",
|
486 |
+
" <td>0.782609</td>\n",
|
487 |
+
" <td>0.915254</td>\n",
|
488 |
+
" <td>0.101695</td>\n",
|
489 |
+
" </tr>\n",
|
490 |
+
" <tr>\n",
|
491 |
+
" <th>45535</th>\n",
|
492 |
+
" <td>1.000000</td>\n",
|
493 |
+
" <td>0.6463</td>\n",
|
494 |
+
" <td>0.693916</td>\n",
|
495 |
+
" <td>0.08</td>\n",
|
496 |
+
" <td>1.0</td>\n",
|
497 |
+
" <td>1.0</td>\n",
|
498 |
+
" <td>0.428571</td>\n",
|
499 |
+
" <td>0.379310</td>\n",
|
500 |
+
" <td>0.458599</td>\n",
|
501 |
+
" <td>0.049208</td>\n",
|
502 |
+
" <td>...</td>\n",
|
503 |
+
" <td>0.0</td>\n",
|
504 |
+
" <td>0.0</td>\n",
|
505 |
+
" <td>0.0</td>\n",
|
506 |
+
" <td>0.0</td>\n",
|
507 |
+
" <td>0.0</td>\n",
|
508 |
+
" <td>0.0</td>\n",
|
509 |
+
" <td>0.0</td>\n",
|
510 |
+
" <td>0.913043</td>\n",
|
511 |
+
" <td>0.406780</td>\n",
|
512 |
+
" <td>0.508475</td>\n",
|
513 |
+
" </tr>\n",
|
514 |
+
" <tr>\n",
|
515 |
+
" <th>...</th>\n",
|
516 |
+
" <td>...</td>\n",
|
517 |
+
" <td>...</td>\n",
|
518 |
+
" <td>...</td>\n",
|
519 |
+
" <td>...</td>\n",
|
520 |
+
" <td>...</td>\n",
|
521 |
+
" <td>...</td>\n",
|
522 |
+
" <td>...</td>\n",
|
523 |
+
" <td>...</td>\n",
|
524 |
+
" <td>...</td>\n",
|
525 |
+
" <td>...</td>\n",
|
526 |
+
" <td>...</td>\n",
|
527 |
+
" <td>...</td>\n",
|
528 |
+
" <td>...</td>\n",
|
529 |
+
" <td>...</td>\n",
|
530 |
+
" <td>...</td>\n",
|
531 |
+
" <td>...</td>\n",
|
532 |
+
" <td>...</td>\n",
|
533 |
+
" <td>...</td>\n",
|
534 |
+
" <td>...</td>\n",
|
535 |
+
" <td>...</td>\n",
|
536 |
+
" <td>...</td>\n",
|
537 |
+
" </tr>\n",
|
538 |
+
" <tr>\n",
|
539 |
+
" <th>41993</th>\n",
|
540 |
+
" <td>1.000000</td>\n",
|
541 |
+
" <td>0.8063</td>\n",
|
542 |
+
" <td>0.831573</td>\n",
|
543 |
+
" <td>0.06</td>\n",
|
544 |
+
" <td>1.0</td>\n",
|
545 |
+
" <td>0.0</td>\n",
|
546 |
+
" <td>0.714286</td>\n",
|
547 |
+
" <td>0.155172</td>\n",
|
548 |
+
" <td>0.312102</td>\n",
|
549 |
+
" <td>0.164571</td>\n",
|
550 |
+
" <td>...</td>\n",
|
551 |
+
" <td>0.0</td>\n",
|
552 |
+
" <td>0.0</td>\n",
|
553 |
+
" <td>0.0</td>\n",
|
554 |
+
" <td>0.0</td>\n",
|
555 |
+
" <td>0.0</td>\n",
|
556 |
+
" <td>0.0</td>\n",
|
557 |
+
" <td>0.0</td>\n",
|
558 |
+
" <td>0.826087</td>\n",
|
559 |
+
" <td>0.067797</td>\n",
|
560 |
+
" <td>0.762712</td>\n",
|
561 |
+
" </tr>\n",
|
562 |
+
" <tr>\n",
|
563 |
+
" <th>97639</th>\n",
|
564 |
+
" <td>1.000000</td>\n",
|
565 |
+
" <td>0.5046</td>\n",
|
566 |
+
" <td>0.618473</td>\n",
|
567 |
+
" <td>0.04</td>\n",
|
568 |
+
" <td>0.0</td>\n",
|
569 |
+
" <td>1.0</td>\n",
|
570 |
+
" <td>0.428571</td>\n",
|
571 |
+
" <td>0.155172</td>\n",
|
572 |
+
" <td>0.458599</td>\n",
|
573 |
+
" <td>0.288001</td>\n",
|
574 |
+
" <td>...</td>\n",
|
575 |
+
" <td>0.0</td>\n",
|
576 |
+
" <td>0.0</td>\n",
|
577 |
+
" <td>0.0</td>\n",
|
578 |
+
" <td>0.0</td>\n",
|
579 |
+
" <td>0.0</td>\n",
|
580 |
+
" <td>0.0</td>\n",
|
581 |
+
" <td>0.0</td>\n",
|
582 |
+
" <td>0.826087</td>\n",
|
583 |
+
" <td>0.169492</td>\n",
|
584 |
+
" <td>0.186441</td>\n",
|
585 |
+
" </tr>\n",
|
586 |
+
" <tr>\n",
|
587 |
+
" <th>95939</th>\n",
|
588 |
+
" <td>1.000000</td>\n",
|
589 |
+
" <td>0.7233</td>\n",
|
590 |
+
" <td>0.686591</td>\n",
|
591 |
+
" <td>0.02</td>\n",
|
592 |
+
" <td>0.0</td>\n",
|
593 |
+
" <td>0.0</td>\n",
|
594 |
+
" <td>0.714286</td>\n",
|
595 |
+
" <td>0.034483</td>\n",
|
596 |
+
" <td>0.866242</td>\n",
|
597 |
+
" <td>0.585850</td>\n",
|
598 |
+
" <td>...</td>\n",
|
599 |
+
" <td>0.0</td>\n",
|
600 |
+
" <td>0.0</td>\n",
|
601 |
+
" <td>0.0</td>\n",
|
602 |
+
" <td>0.0</td>\n",
|
603 |
+
" <td>0.0</td>\n",
|
604 |
+
" <td>0.0</td>\n",
|
605 |
+
" <td>1.0</td>\n",
|
606 |
+
" <td>0.869565</td>\n",
|
607 |
+
" <td>0.372881</td>\n",
|
608 |
+
" <td>0.847458</td>\n",
|
609 |
+
" </tr>\n",
|
610 |
+
" <tr>\n",
|
611 |
+
" <th>117952</th>\n",
|
612 |
+
" <td>1.000000</td>\n",
|
613 |
+
" <td>0.7824</td>\n",
|
614 |
+
" <td>0.710351</td>\n",
|
615 |
+
" <td>0.96</td>\n",
|
616 |
+
" <td>1.0</td>\n",
|
617 |
+
" <td>1.0</td>\n",
|
618 |
+
" <td>0.714286</td>\n",
|
619 |
+
" <td>0.086207</td>\n",
|
620 |
+
" <td>0.458599</td>\n",
|
621 |
+
" <td>0.007728</td>\n",
|
622 |
+
" <td>...</td>\n",
|
623 |
+
" <td>0.0</td>\n",
|
624 |
+
" <td>0.0</td>\n",
|
625 |
+
" <td>0.0</td>\n",
|
626 |
+
" <td>0.0</td>\n",
|
627 |
+
" <td>0.0</td>\n",
|
628 |
+
" <td>0.0</td>\n",
|
629 |
+
" <td>0.0</td>\n",
|
630 |
+
" <td>0.000000</td>\n",
|
631 |
+
" <td>0.406780</td>\n",
|
632 |
+
" <td>0.779661</td>\n",
|
633 |
+
" </tr>\n",
|
634 |
+
" <tr>\n",
|
635 |
+
" <th>43567</th>\n",
|
636 |
+
" <td>1.000000</td>\n",
|
637 |
+
" <td>0.7225</td>\n",
|
638 |
+
" <td>0.468508</td>\n",
|
639 |
+
" <td>1.00</td>\n",
|
640 |
+
" <td>0.0</td>\n",
|
641 |
+
" <td>1.0</td>\n",
|
642 |
+
" <td>0.714286</td>\n",
|
643 |
+
" <td>0.051724</td>\n",
|
644 |
+
" <td>0.458599</td>\n",
|
645 |
+
" <td>0.617746</td>\n",
|
646 |
+
" <td>...</td>\n",
|
647 |
+
" <td>0.0</td>\n",
|
648 |
+
" <td>0.0</td>\n",
|
649 |
+
" <td>0.0</td>\n",
|
650 |
+
" <td>0.0</td>\n",
|
651 |
+
" <td>0.0</td>\n",
|
652 |
+
" <td>0.0</td>\n",
|
653 |
+
" <td>1.0</td>\n",
|
654 |
+
" <td>0.913043</td>\n",
|
655 |
+
" <td>0.288136</td>\n",
|
656 |
+
" <td>0.305085</td>\n",
|
657 |
+
" </tr>\n",
|
658 |
+
" </tbody>\n",
|
659 |
+
"</table>\n",
|
660 |
+
"<p>135000 rows Γ 45 columns</p>\n",
|
661 |
+
"</div>"
|
662 |
+
],
|
663 |
+
"text/plain": [
|
664 |
+
" a b c d e f g h \\\n",
|
665 |
+
"135569 1.000000 0.5217 0.635969 0.02 1.0 1.0 0.714286 0.620690 \n",
|
666 |
+
"78656 0.333333 0.7554 0.684908 0.02 0.0 1.0 0.428571 0.137931 \n",
|
667 |
+
"87437 1.000000 0.5437 0.741337 0.02 1.0 1.0 0.428571 0.793103 \n",
|
668 |
+
"131674 1.000000 0.7418 0.633959 1.00 1.0 1.0 0.714286 0.155172 \n",
|
669 |
+
"45535 1.000000 0.6463 0.693916 0.08 1.0 1.0 0.428571 0.379310 \n",
|
670 |
+
"... ... ... ... ... ... ... ... ... \n",
|
671 |
+
"41993 1.000000 0.8063 0.831573 0.06 1.0 0.0 0.714286 0.155172 \n",
|
672 |
+
"97639 1.000000 0.5046 0.618473 0.04 0.0 1.0 0.428571 0.155172 \n",
|
673 |
+
"95939 1.000000 0.7233 0.686591 0.02 0.0 0.0 0.714286 0.034483 \n",
|
674 |
+
"117952 1.000000 0.7824 0.710351 0.96 1.0 1.0 0.714286 0.086207 \n",
|
675 |
+
"43567 1.000000 0.7225 0.468508 1.00 0.0 1.0 0.714286 0.051724 \n",
|
676 |
+
"\n",
|
677 |
+
" j k ... fecha_month_end fecha_quarter_start \\\n",
|
678 |
+
"135569 0.458599 0.636612 ... 0.0 0.0 \n",
|
679 |
+
"78656 0.133758 0.633268 ... 0.0 0.0 \n",
|
680 |
+
"87437 0.458599 0.735751 ... 0.0 1.0 \n",
|
681 |
+
"131674 0.458599 0.529368 ... 0.0 0.0 \n",
|
682 |
+
"45535 0.458599 0.049208 ... 0.0 0.0 \n",
|
683 |
+
"... ... ... ... ... ... \n",
|
684 |
+
"41993 0.312102 0.164571 ... 0.0 0.0 \n",
|
685 |
+
"97639 0.458599 0.288001 ... 0.0 0.0 \n",
|
686 |
+
"95939 0.866242 0.585850 ... 0.0 0.0 \n",
|
687 |
+
"117952 0.458599 0.007728 ... 0.0 0.0 \n",
|
688 |
+
"43567 0.458599 0.617746 ... 0.0 0.0 \n",
|
689 |
+
"\n",
|
690 |
+
" fecha_quarter_end fecha_year_start fecha_year_end fecha_leap_year \\\n",
|
691 |
+
"135569 0.0 0.0 0.0 0.0 \n",
|
692 |
+
"78656 0.0 0.0 0.0 0.0 \n",
|
693 |
+
"87437 0.0 0.0 0.0 0.0 \n",
|
694 |
+
"131674 0.0 0.0 0.0 0.0 \n",
|
695 |
+
"45535 0.0 0.0 0.0 0.0 \n",
|
696 |
+
"... ... ... ... ... \n",
|
697 |
+
"41993 0.0 0.0 0.0 0.0 \n",
|
698 |
+
"97639 0.0 0.0 0.0 0.0 \n",
|
699 |
+
"95939 0.0 0.0 0.0 0.0 \n",
|
700 |
+
"117952 0.0 0.0 0.0 0.0 \n",
|
701 |
+
"43567 0.0 0.0 0.0 0.0 \n",
|
702 |
+
"\n",
|
703 |
+
" fecha_days_in_month fecha_hour fecha_minute fecha_second \n",
|
704 |
+
"135569 1.0 0.391304 0.525424 0.881356 \n",
|
705 |
+
"78656 1.0 0.347826 0.254237 0.288136 \n",
|
706 |
+
"87437 0.0 0.391304 0.050847 0.338983 \n",
|
707 |
+
"131674 0.0 0.782609 0.915254 0.101695 \n",
|
708 |
+
"45535 0.0 0.913043 0.406780 0.508475 \n",
|
709 |
+
"... ... ... ... ... \n",
|
710 |
+
"41993 0.0 0.826087 0.067797 0.762712 \n",
|
711 |
+
"97639 0.0 0.826087 0.169492 0.186441 \n",
|
712 |
+
"95939 1.0 0.869565 0.372881 0.847458 \n",
|
713 |
+
"117952 0.0 0.000000 0.406780 0.779661 \n",
|
714 |
+
"43567 1.0 0.913043 0.288136 0.305085 \n",
|
715 |
+
"\n",
|
716 |
+
"[135000 rows x 45 columns]"
|
717 |
+
]
|
718 |
+
},
|
719 |
+
"execution_count": 7,
|
720 |
+
"metadata": {},
|
721 |
+
"output_type": "execute_result"
|
722 |
+
}
|
723 |
+
],
|
724 |
+
"source": [
|
725 |
+
"X_train_transformed"
|
726 |
+
]
|
727 |
+
},
|
728 |
+
{
|
729 |
+
"cell_type": "code",
|
730 |
+
"execution_count": 8,
|
731 |
+
"metadata": {},
|
732 |
+
"outputs": [],
|
733 |
+
"source": [
|
734 |
+
"sel = ProbeFeatureSelection(\n",
|
735 |
+
" estimator=RandomForestClassifier(),\n",
|
736 |
+
" scoring=\"roc_auc\",\n",
|
737 |
+
" n_probes=3,\n",
|
738 |
+
" distribution=\"all\",\n",
|
739 |
+
" cv=3,\n",
|
740 |
+
" random_state=150\n",
|
741 |
+
")"
|
742 |
+
]
|
743 |
+
},
|
744 |
+
{
|
745 |
+
"cell_type": "code",
|
746 |
+
"execution_count": 9,
|
747 |
+
"metadata": {},
|
748 |
+
"outputs": [],
|
749 |
+
"source": [
|
750 |
+
"X_tr = sel.fit_transform(X_train_transformed, y_train)"
|
751 |
+
]
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"cell_type": "code",
|
755 |
+
"execution_count": 10,
|
756 |
+
"metadata": {},
|
757 |
+
"outputs": [
|
758 |
+
{
|
759 |
+
"name": "stdout",
|
760 |
+
"output_type": "stream",
|
761 |
+
"text": [
|
762 |
+
"(135000, 45) (135000, 13)\n"
|
763 |
+
]
|
764 |
+
}
|
765 |
+
],
|
766 |
+
"source": [
|
767 |
+
"print(X_train_transformed.shape, X_tr.shape)\n"
|
768 |
+
]
|
769 |
+
},
|
770 |
+
{
|
771 |
+
"cell_type": "code",
|
772 |
+
"execution_count": null,
|
773 |
+
"metadata": {},
|
774 |
+
"outputs": [],
|
775 |
+
"source": []
|
776 |
+
},
|
777 |
+
{
|
778 |
+
"cell_type": "code",
|
779 |
+
"execution_count": 11,
|
780 |
+
"metadata": {},
|
781 |
+
"outputs": [],
|
782 |
+
"source": [
|
783 |
+
"selected_features = X_tr.columns"
|
784 |
+
]
|
785 |
+
},
|
786 |
+
{
|
787 |
+
"cell_type": "code",
|
788 |
+
"execution_count": 12,
|
789 |
+
"metadata": {},
|
790 |
+
"outputs": [],
|
791 |
+
"source": [
|
792 |
+
"pd.Series(selected_features).to_csv('../data/processed/selected_features.csv', index=False)"
|
793 |
+
]
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"cell_type": "code",
|
797 |
+
"execution_count": null,
|
798 |
+
"metadata": {},
|
799 |
+
"outputs": [],
|
800 |
+
"source": []
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"cell_type": "code",
|
804 |
+
"execution_count": null,
|
805 |
+
"metadata": {},
|
806 |
+
"outputs": [],
|
807 |
+
"source": []
|
808 |
+
}
|
809 |
+
],
|
810 |
+
"metadata": {
|
811 |
+
"kernelspec": {
|
812 |
+
"display_name": "fraud-detection",
|
813 |
+
"language": "python",
|
814 |
+
"name": "python3"
|
815 |
+
},
|
816 |
+
"language_info": {
|
817 |
+
"codemirror_mode": {
|
818 |
+
"name": "ipython",
|
819 |
+
"version": 3
|
820 |
+
},
|
821 |
+
"file_extension": ".py",
|
822 |
+
"mimetype": "text/x-python",
|
823 |
+
"name": "python",
|
824 |
+
"nbconvert_exporter": "python",
|
825 |
+
"pygments_lexer": "ipython3",
|
826 |
+
"version": "3.10.12"
|
827 |
+
},
|
828 |
+
"orig_nbformat": 4,
|
829 |
+
"vscode": {
|
830 |
+
"interpreter": {
|
831 |
+
"hash": "45e631c81adbf0cb55b2526738ae1a14c53cfa3f28a6ae1bee5619daf3ab935d"
|
832 |
+
}
|
833 |
+
}
|
834 |
+
},
|
835 |
+
"nbformat": 4,
|
836 |
+
"nbformat_minor": 2
|
837 |
+
}
|
notebooks/04-model _training.ipynb
ADDED
The diff for this file is too large to render.
See raw diff
|
|
notebooks/__pycache__/utils.cpython-310.pyc
ADDED
Binary file (1.19 kB). View file
|
|
notebooks/logs.log
ADDED
@@ -0,0 +1,808 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
2023-10-08 15:23:18,818:WARNING:
|
2 |
+
'cuml' is a soft dependency and not included in the pycaret installation. Please run: `pip install cuml` to install.
|
3 |
+
2023-10-08 15:23:18,819:WARNING:
|
4 |
+
'cuml' is a soft dependency and not included in the pycaret installation. Please run: `pip install cuml` to install.
|
5 |
+
2023-10-08 15:23:18,819:WARNING:
|
6 |
+
'cuml' is a soft dependency and not included in the pycaret installation. Please run: `pip install cuml` to install.
|
7 |
+
2023-10-08 15:23:18,819:WARNING:
|
8 |
+
'cuml' is a soft dependency and not included in the pycaret installation. Please run: `pip install cuml` to install.
|
9 |
+
2023-10-08 15:38:13,449:WARNING:
|
10 |
+
'cuml' is a soft dependency and not included in the pycaret installation. Please run: `pip install cuml` to install.
|
11 |
+
2023-10-08 15:38:13,449:WARNING:
|
12 |
+
'cuml' is a soft dependency and not included in the pycaret installation. Please run: `pip install cuml` to install.
|
13 |
+
2023-10-08 15:38:13,449:WARNING:
|
14 |
+
'cuml' is a soft dependency and not included in the pycaret installation. Please run: `pip install cuml` to install.
|
15 |
+
2023-10-08 15:38:13,449:WARNING:
|
16 |
+
'cuml' is a soft dependency and not included in the pycaret installation. Please run: `pip install cuml` to install.
|
17 |
+
2023-10-08 15:40:39,103:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/sklearn/linear_model/_logistic.py:460: ConvergenceWarning: lbfgs failed to converge (status=1):
|
18 |
+
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
19 |
+
|
20 |
+
Increase the number of iterations (max_iter) or scale the data as shown in:
|
21 |
+
https://scikit-learn.org/stable/modules/preprocessing.html
|
22 |
+
Please also refer to the documentation for alternative solver options:
|
23 |
+
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
|
24 |
+
n_iter_i = _check_optimize_result(
|
25 |
+
|
26 |
+
2023-10-08 15:40:41,463:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/sklearn/linear_model/_logistic.py:460: ConvergenceWarning: lbfgs failed to converge (status=1):
|
27 |
+
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
28 |
+
|
29 |
+
Increase the number of iterations (max_iter) or scale the data as shown in:
|
30 |
+
https://scikit-learn.org/stable/modules/preprocessing.html
|
31 |
+
Please also refer to the documentation for alternative solver options:
|
32 |
+
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
|
33 |
+
n_iter_i = _check_optimize_result(
|
34 |
+
|
35 |
+
2023-10-08 15:40:43,785:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/sklearn/linear_model/_logistic.py:460: ConvergenceWarning: lbfgs failed to converge (status=1):
|
36 |
+
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
37 |
+
|
38 |
+
Increase the number of iterations (max_iter) or scale the data as shown in:
|
39 |
+
https://scikit-learn.org/stable/modules/preprocessing.html
|
40 |
+
Please also refer to the documentation for alternative solver options:
|
41 |
+
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
|
42 |
+
n_iter_i = _check_optimize_result(
|
43 |
+
|
44 |
+
2023-10-08 15:40:46,764:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/sklearn/linear_model/_logistic.py:460: ConvergenceWarning: lbfgs failed to converge (status=1):
|
45 |
+
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
46 |
+
|
47 |
+
Increase the number of iterations (max_iter) or scale the data as shown in:
|
48 |
+
https://scikit-learn.org/stable/modules/preprocessing.html
|
49 |
+
Please also refer to the documentation for alternative solver options:
|
50 |
+
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
|
51 |
+
n_iter_i = _check_optimize_result(
|
52 |
+
|
53 |
+
2023-10-08 15:40:48,451:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/sklearn/linear_model/_logistic.py:460: ConvergenceWarning: lbfgs failed to converge (status=1):
|
54 |
+
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
55 |
+
|
56 |
+
Increase the number of iterations (max_iter) or scale the data as shown in:
|
57 |
+
https://scikit-learn.org/stable/modules/preprocessing.html
|
58 |
+
Please also refer to the documentation for alternative solver options:
|
59 |
+
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
|
60 |
+
n_iter_i = _check_optimize_result(
|
61 |
+
|
62 |
+
2023-10-08 15:40:51,170:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/sklearn/linear_model/_logistic.py:460: ConvergenceWarning: lbfgs failed to converge (status=1):
|
63 |
+
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
64 |
+
|
65 |
+
Increase the number of iterations (max_iter) or scale the data as shown in:
|
66 |
+
https://scikit-learn.org/stable/modules/preprocessing.html
|
67 |
+
Please also refer to the documentation for alternative solver options:
|
68 |
+
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
|
69 |
+
n_iter_i = _check_optimize_result(
|
70 |
+
|
71 |
+
2023-10-08 15:40:53,845:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/sklearn/linear_model/_logistic.py:460: ConvergenceWarning: lbfgs failed to converge (status=1):
|
72 |
+
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
73 |
+
|
74 |
+
Increase the number of iterations (max_iter) or scale the data as shown in:
|
75 |
+
https://scikit-learn.org/stable/modules/preprocessing.html
|
76 |
+
Please also refer to the documentation for alternative solver options:
|
77 |
+
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
|
78 |
+
n_iter_i = _check_optimize_result(
|
79 |
+
|
80 |
+
2023-10-08 15:40:56,184:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/sklearn/linear_model/_logistic.py:460: ConvergenceWarning: lbfgs failed to converge (status=1):
|
81 |
+
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
82 |
+
|
83 |
+
Increase the number of iterations (max_iter) or scale the data as shown in:
|
84 |
+
https://scikit-learn.org/stable/modules/preprocessing.html
|
85 |
+
Please also refer to the documentation for alternative solver options:
|
86 |
+
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
|
87 |
+
n_iter_i = _check_optimize_result(
|
88 |
+
|
89 |
+
2023-10-08 15:40:59,289:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/sklearn/linear_model/_logistic.py:460: ConvergenceWarning: lbfgs failed to converge (status=1):
|
90 |
+
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
91 |
+
|
92 |
+
Increase the number of iterations (max_iter) or scale the data as shown in:
|
93 |
+
https://scikit-learn.org/stable/modules/preprocessing.html
|
94 |
+
Please also refer to the documentation for alternative solver options:
|
95 |
+
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
|
96 |
+
n_iter_i = _check_optimize_result(
|
97 |
+
|
98 |
+
2023-10-08 15:41:02,358:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/sklearn/linear_model/_logistic.py:460: ConvergenceWarning: lbfgs failed to converge (status=1):
|
99 |
+
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
100 |
+
|
101 |
+
Increase the number of iterations (max_iter) or scale the data as shown in:
|
102 |
+
https://scikit-learn.org/stable/modules/preprocessing.html
|
103 |
+
Please also refer to the documentation for alternative solver options:
|
104 |
+
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
|
105 |
+
n_iter_i = _check_optimize_result(
|
106 |
+
|
107 |
+
2023-10-08 15:41:04,033:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/sklearn/linear_model/_logistic.py:460: ConvergenceWarning: lbfgs failed to converge (status=1):
|
108 |
+
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
109 |
+
|
110 |
+
Increase the number of iterations (max_iter) or scale the data as shown in:
|
111 |
+
https://scikit-learn.org/stable/modules/preprocessing.html
|
112 |
+
Please also refer to the documentation for alternative solver options:
|
113 |
+
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
|
114 |
+
n_iter_i = _check_optimize_result(
|
115 |
+
|
116 |
+
2023-10-08 15:49:53,461:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
117 |
+
if is_sparse(dtype):
|
118 |
+
|
119 |
+
2023-10-08 15:49:53,461:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
120 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
121 |
+
|
122 |
+
2023-10-08 15:49:53,462:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
123 |
+
if is_categorical_dtype(dtype):
|
124 |
+
|
125 |
+
2023-10-08 15:49:53,463:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
126 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
127 |
+
|
128 |
+
2023-10-08 15:51:35,340:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
129 |
+
if is_sparse(dtype):
|
130 |
+
|
131 |
+
2023-10-08 15:51:35,340:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
132 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
133 |
+
|
134 |
+
2023-10-08 15:51:35,341:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
135 |
+
if is_categorical_dtype(dtype):
|
136 |
+
|
137 |
+
2023-10-08 15:51:35,342:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
138 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
139 |
+
|
140 |
+
2023-10-08 15:51:35,411:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
141 |
+
if is_sparse(dtype):
|
142 |
+
|
143 |
+
2023-10-08 15:51:35,411:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
144 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
145 |
+
|
146 |
+
2023-10-08 15:51:35,413:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
147 |
+
if is_categorical_dtype(dtype):
|
148 |
+
|
149 |
+
2023-10-08 15:51:35,413:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
150 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
151 |
+
|
152 |
+
2023-10-08 15:51:35,498:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
153 |
+
if is_sparse(dtype):
|
154 |
+
|
155 |
+
2023-10-08 15:51:35,498:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
156 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
157 |
+
|
158 |
+
2023-10-08 15:51:35,501:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
159 |
+
if is_categorical_dtype(dtype):
|
160 |
+
|
161 |
+
2023-10-08 15:51:35,501:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
162 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
163 |
+
|
164 |
+
2023-10-08 15:53:16,848:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
165 |
+
if is_sparse(dtype):
|
166 |
+
|
167 |
+
2023-10-08 15:53:16,848:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
168 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
169 |
+
|
170 |
+
2023-10-08 15:53:16,849:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
171 |
+
if is_categorical_dtype(dtype):
|
172 |
+
|
173 |
+
2023-10-08 15:53:16,849:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
174 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
175 |
+
|
176 |
+
2023-10-08 15:53:16,922:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
177 |
+
if is_sparse(dtype):
|
178 |
+
|
179 |
+
2023-10-08 15:53:16,922:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
180 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
181 |
+
|
182 |
+
2023-10-08 15:53:16,923:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
183 |
+
if is_categorical_dtype(dtype):
|
184 |
+
|
185 |
+
2023-10-08 15:53:16,923:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
186 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
187 |
+
|
188 |
+
2023-10-08 15:53:17,013:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
189 |
+
if is_sparse(dtype):
|
190 |
+
|
191 |
+
2023-10-08 15:53:17,013:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
192 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
193 |
+
|
194 |
+
2023-10-08 15:53:17,014:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
195 |
+
if is_categorical_dtype(dtype):
|
196 |
+
|
197 |
+
2023-10-08 15:53:17,014:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
198 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
199 |
+
|
200 |
+
2023-10-08 15:54:59,320:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
201 |
+
if is_sparse(dtype):
|
202 |
+
|
203 |
+
2023-10-08 15:54:59,320:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
204 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
205 |
+
|
206 |
+
2023-10-08 15:54:59,321:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
207 |
+
if is_categorical_dtype(dtype):
|
208 |
+
|
209 |
+
2023-10-08 15:54:59,321:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
210 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
211 |
+
|
212 |
+
2023-10-08 15:54:59,383:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
213 |
+
if is_sparse(dtype):
|
214 |
+
|
215 |
+
2023-10-08 15:54:59,383:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
216 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
217 |
+
|
218 |
+
2023-10-08 15:54:59,384:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
219 |
+
if is_categorical_dtype(dtype):
|
220 |
+
|
221 |
+
2023-10-08 15:54:59,385:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
222 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
223 |
+
|
224 |
+
2023-10-08 15:54:59,453:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
225 |
+
if is_sparse(dtype):
|
226 |
+
|
227 |
+
2023-10-08 15:54:59,453:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
228 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
229 |
+
|
230 |
+
2023-10-08 15:54:59,454:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
231 |
+
if is_categorical_dtype(dtype):
|
232 |
+
|
233 |
+
2023-10-08 15:54:59,454:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
234 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
235 |
+
|
236 |
+
2023-10-08 15:56:41,633:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
237 |
+
if is_sparse(dtype):
|
238 |
+
|
239 |
+
2023-10-08 15:56:41,633:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
240 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
241 |
+
|
242 |
+
2023-10-08 15:56:41,635:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
243 |
+
if is_categorical_dtype(dtype):
|
244 |
+
|
245 |
+
2023-10-08 15:56:41,635:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
246 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
247 |
+
|
248 |
+
2023-10-08 15:56:41,710:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
249 |
+
if is_sparse(dtype):
|
250 |
+
|
251 |
+
2023-10-08 15:56:41,710:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
252 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
253 |
+
|
254 |
+
2023-10-08 15:56:41,712:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
255 |
+
if is_categorical_dtype(dtype):
|
256 |
+
|
257 |
+
2023-10-08 15:56:41,712:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
258 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
259 |
+
|
260 |
+
2023-10-08 15:56:41,800:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
261 |
+
if is_sparse(dtype):
|
262 |
+
|
263 |
+
2023-10-08 15:56:41,800:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
264 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
265 |
+
|
266 |
+
2023-10-08 15:56:41,802:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
267 |
+
if is_categorical_dtype(dtype):
|
268 |
+
|
269 |
+
2023-10-08 15:56:41,802:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
270 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
271 |
+
|
272 |
+
2023-10-08 15:58:23,396:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
273 |
+
if is_sparse(dtype):
|
274 |
+
|
275 |
+
2023-10-08 15:58:23,396:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
276 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
277 |
+
|
278 |
+
2023-10-08 15:58:23,398:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
279 |
+
if is_categorical_dtype(dtype):
|
280 |
+
|
281 |
+
2023-10-08 15:58:23,398:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
282 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
283 |
+
|
284 |
+
2023-10-08 15:58:23,460:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
285 |
+
if is_sparse(dtype):
|
286 |
+
|
287 |
+
2023-10-08 15:58:23,460:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
288 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
289 |
+
|
290 |
+
2023-10-08 15:58:23,461:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
291 |
+
if is_categorical_dtype(dtype):
|
292 |
+
|
293 |
+
2023-10-08 15:58:23,462:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
294 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
295 |
+
|
296 |
+
2023-10-08 15:58:23,549:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
297 |
+
if is_sparse(dtype):
|
298 |
+
|
299 |
+
2023-10-08 15:58:23,549:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
300 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
301 |
+
|
302 |
+
2023-10-08 15:58:23,551:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
303 |
+
if is_categorical_dtype(dtype):
|
304 |
+
|
305 |
+
2023-10-08 15:58:23,551:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
306 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
307 |
+
|
308 |
+
2023-10-08 16:00:04,973:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
309 |
+
if is_sparse(dtype):
|
310 |
+
|
311 |
+
2023-10-08 16:00:04,973:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
312 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
313 |
+
|
314 |
+
2023-10-08 16:00:04,975:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
315 |
+
if is_categorical_dtype(dtype):
|
316 |
+
|
317 |
+
2023-10-08 16:00:04,975:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
318 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
319 |
+
|
320 |
+
2023-10-08 16:00:05,073:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
321 |
+
if is_sparse(dtype):
|
322 |
+
|
323 |
+
2023-10-08 16:00:05,073:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
324 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
325 |
+
|
326 |
+
2023-10-08 16:00:05,075:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
327 |
+
if is_categorical_dtype(dtype):
|
328 |
+
|
329 |
+
2023-10-08 16:00:05,075:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
330 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
331 |
+
|
332 |
+
2023-10-08 16:00:05,163:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
333 |
+
if is_sparse(dtype):
|
334 |
+
|
335 |
+
2023-10-08 16:00:05,163:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
336 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
337 |
+
|
338 |
+
2023-10-08 16:00:05,165:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
339 |
+
if is_categorical_dtype(dtype):
|
340 |
+
|
341 |
+
2023-10-08 16:00:05,165:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
342 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
343 |
+
|
344 |
+
2023-10-08 16:01:42,577:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
345 |
+
if is_sparse(dtype):
|
346 |
+
|
347 |
+
2023-10-08 16:01:42,577:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
348 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
349 |
+
|
350 |
+
2023-10-08 16:01:42,579:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
351 |
+
if is_categorical_dtype(dtype):
|
352 |
+
|
353 |
+
2023-10-08 16:01:42,579:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
354 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
355 |
+
|
356 |
+
2023-10-08 16:01:42,643:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
357 |
+
if is_sparse(dtype):
|
358 |
+
|
359 |
+
2023-10-08 16:01:42,643:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
360 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
361 |
+
|
362 |
+
2023-10-08 16:01:42,645:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
363 |
+
if is_categorical_dtype(dtype):
|
364 |
+
|
365 |
+
2023-10-08 16:01:42,645:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
366 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
367 |
+
|
368 |
+
2023-10-08 16:01:42,725:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
369 |
+
if is_sparse(dtype):
|
370 |
+
|
371 |
+
2023-10-08 16:01:42,725:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
372 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
373 |
+
|
374 |
+
2023-10-08 16:01:42,726:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
375 |
+
if is_categorical_dtype(dtype):
|
376 |
+
|
377 |
+
2023-10-08 16:01:42,726:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
378 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
379 |
+
|
380 |
+
2023-10-08 16:03:23,976:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
381 |
+
if is_sparse(dtype):
|
382 |
+
|
383 |
+
2023-10-08 16:03:23,977:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
384 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
385 |
+
|
386 |
+
2023-10-08 16:03:23,978:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
387 |
+
if is_categorical_dtype(dtype):
|
388 |
+
|
389 |
+
2023-10-08 16:03:23,979:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
390 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
391 |
+
|
392 |
+
2023-10-08 16:03:24,050:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
393 |
+
if is_sparse(dtype):
|
394 |
+
|
395 |
+
2023-10-08 16:03:24,050:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
396 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
397 |
+
|
398 |
+
2023-10-08 16:03:24,051:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
399 |
+
if is_categorical_dtype(dtype):
|
400 |
+
|
401 |
+
2023-10-08 16:03:24,051:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
402 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
403 |
+
|
404 |
+
2023-10-08 16:03:24,153:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
405 |
+
if is_sparse(dtype):
|
406 |
+
|
407 |
+
2023-10-08 16:03:24,153:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
408 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
409 |
+
|
410 |
+
2023-10-08 16:03:24,154:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
411 |
+
if is_categorical_dtype(dtype):
|
412 |
+
|
413 |
+
2023-10-08 16:03:24,154:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
414 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
415 |
+
|
416 |
+
2023-10-08 16:05:05,773:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
417 |
+
if is_sparse(dtype):
|
418 |
+
|
419 |
+
2023-10-08 16:05:05,773:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
420 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
421 |
+
|
422 |
+
2023-10-08 16:05:05,775:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
423 |
+
if is_categorical_dtype(dtype):
|
424 |
+
|
425 |
+
2023-10-08 16:05:05,775:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
426 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
427 |
+
|
428 |
+
2023-10-08 16:05:05,839:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
429 |
+
if is_sparse(dtype):
|
430 |
+
|
431 |
+
2023-10-08 16:05:05,839:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
432 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
433 |
+
|
434 |
+
2023-10-08 16:05:05,841:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
435 |
+
if is_categorical_dtype(dtype):
|
436 |
+
|
437 |
+
2023-10-08 16:05:05,841:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
438 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
439 |
+
|
440 |
+
2023-10-08 16:05:05,917:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
441 |
+
if is_sparse(dtype):
|
442 |
+
|
443 |
+
2023-10-08 16:05:05,918:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
444 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
445 |
+
|
446 |
+
2023-10-08 16:05:05,919:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
447 |
+
if is_categorical_dtype(dtype):
|
448 |
+
|
449 |
+
2023-10-08 16:05:05,919:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
450 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
451 |
+
|
452 |
+
2023-10-08 16:06:47,939:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
453 |
+
if is_sparse(dtype):
|
454 |
+
|
455 |
+
2023-10-08 16:06:47,940:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
456 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
457 |
+
|
458 |
+
2023-10-08 16:06:47,941:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
459 |
+
if is_categorical_dtype(dtype):
|
460 |
+
|
461 |
+
2023-10-08 16:06:47,941:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
462 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
463 |
+
|
464 |
+
2023-10-08 16:06:47,995:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
465 |
+
if is_sparse(dtype):
|
466 |
+
|
467 |
+
2023-10-08 16:06:47,995:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
468 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
469 |
+
|
470 |
+
2023-10-08 16:06:47,996:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
471 |
+
if is_categorical_dtype(dtype):
|
472 |
+
|
473 |
+
2023-10-08 16:06:47,996:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
474 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
475 |
+
|
476 |
+
2023-10-08 16:06:48,040:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
477 |
+
if is_sparse(dtype):
|
478 |
+
|
479 |
+
2023-10-08 16:06:48,040:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
480 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
481 |
+
|
482 |
+
2023-10-08 16:06:48,041:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
483 |
+
if is_categorical_dtype(dtype):
|
484 |
+
|
485 |
+
2023-10-08 16:06:48,042:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
486 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
487 |
+
|
488 |
+
2023-10-08 16:08:29,796:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
489 |
+
if is_sparse(dtype):
|
490 |
+
|
491 |
+
2023-10-08 16:08:29,796:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
492 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
493 |
+
|
494 |
+
2023-10-08 16:08:29,798:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
495 |
+
if is_categorical_dtype(dtype):
|
496 |
+
|
497 |
+
2023-10-08 16:08:29,798:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
498 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
499 |
+
|
500 |
+
2023-10-08 17:48:44,232:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/sklearn/linear_model/_logistic.py:460: ConvergenceWarning: lbfgs failed to converge (status=1):
|
501 |
+
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
502 |
+
|
503 |
+
Increase the number of iterations (max_iter) or scale the data as shown in:
|
504 |
+
https://scikit-learn.org/stable/modules/preprocessing.html
|
505 |
+
Please also refer to the documentation for alternative solver options:
|
506 |
+
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
|
507 |
+
n_iter_i = _check_optimize_result(
|
508 |
+
|
509 |
+
2023-10-08 17:48:46,174:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/sklearn/linear_model/_logistic.py:460: ConvergenceWarning: lbfgs failed to converge (status=1):
|
510 |
+
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
511 |
+
|
512 |
+
Increase the number of iterations (max_iter) or scale the data as shown in:
|
513 |
+
https://scikit-learn.org/stable/modules/preprocessing.html
|
514 |
+
Please also refer to the documentation for alternative solver options:
|
515 |
+
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
|
516 |
+
n_iter_i = _check_optimize_result(
|
517 |
+
|
518 |
+
2023-10-08 17:48:48,326:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/sklearn/linear_model/_logistic.py:460: ConvergenceWarning: lbfgs failed to converge (status=1):
|
519 |
+
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
520 |
+
|
521 |
+
Increase the number of iterations (max_iter) or scale the data as shown in:
|
522 |
+
https://scikit-learn.org/stable/modules/preprocessing.html
|
523 |
+
Please also refer to the documentation for alternative solver options:
|
524 |
+
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
|
525 |
+
n_iter_i = _check_optimize_result(
|
526 |
+
|
527 |
+
2023-10-08 17:48:49,750:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/sklearn/linear_model/_logistic.py:460: ConvergenceWarning: lbfgs failed to converge (status=1):
|
528 |
+
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
529 |
+
|
530 |
+
Increase the number of iterations (max_iter) or scale the data as shown in:
|
531 |
+
https://scikit-learn.org/stable/modules/preprocessing.html
|
532 |
+
Please also refer to the documentation for alternative solver options:
|
533 |
+
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
|
534 |
+
n_iter_i = _check_optimize_result(
|
535 |
+
|
536 |
+
2023-10-08 17:48:52,626:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/sklearn/linear_model/_logistic.py:460: ConvergenceWarning: lbfgs failed to converge (status=1):
|
537 |
+
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
538 |
+
|
539 |
+
Increase the number of iterations (max_iter) or scale the data as shown in:
|
540 |
+
https://scikit-learn.org/stable/modules/preprocessing.html
|
541 |
+
Please also refer to the documentation for alternative solver options:
|
542 |
+
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
|
543 |
+
n_iter_i = _check_optimize_result(
|
544 |
+
|
545 |
+
2023-10-08 17:48:55,008:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/sklearn/linear_model/_logistic.py:460: ConvergenceWarning: lbfgs failed to converge (status=1):
|
546 |
+
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
|
547 |
+
|
548 |
+
Increase the number of iterations (max_iter) or scale the data as shown in:
|
549 |
+
https://scikit-learn.org/stable/modules/preprocessing.html
|
550 |
+
Please also refer to the documentation for alternative solver options:
|
551 |
+
https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
|
552 |
+
n_iter_i = _check_optimize_result(
|
553 |
+
|
554 |
+
2023-10-08 17:54:25,847:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
555 |
+
if is_sparse(dtype):
|
556 |
+
|
557 |
+
2023-10-08 17:54:25,847:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
558 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
559 |
+
|
560 |
+
2023-10-08 17:54:25,848:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
561 |
+
if is_categorical_dtype(dtype):
|
562 |
+
|
563 |
+
2023-10-08 17:54:25,848:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
564 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
565 |
+
|
566 |
+
2023-10-08 17:55:54,180:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
567 |
+
if is_sparse(dtype):
|
568 |
+
|
569 |
+
2023-10-08 17:55:54,181:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
570 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
571 |
+
|
572 |
+
2023-10-08 17:55:54,182:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
573 |
+
if is_categorical_dtype(dtype):
|
574 |
+
|
575 |
+
2023-10-08 17:55:54,183:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
576 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
577 |
+
|
578 |
+
2023-10-08 17:55:54,249:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
579 |
+
if is_sparse(dtype):
|
580 |
+
|
581 |
+
2023-10-08 17:55:54,250:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
582 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
583 |
+
|
584 |
+
2023-10-08 17:55:54,251:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
585 |
+
if is_categorical_dtype(dtype):
|
586 |
+
|
587 |
+
2023-10-08 17:55:54,251:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
588 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
589 |
+
|
590 |
+
2023-10-08 17:55:54,332:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
591 |
+
if is_sparse(dtype):
|
592 |
+
|
593 |
+
2023-10-08 17:55:54,332:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
594 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
595 |
+
|
596 |
+
2023-10-08 17:55:54,334:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
597 |
+
if is_categorical_dtype(dtype):
|
598 |
+
|
599 |
+
2023-10-08 17:55:54,334:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
600 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
601 |
+
|
602 |
+
2023-10-08 17:57:34,908:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
603 |
+
if is_sparse(dtype):
|
604 |
+
|
605 |
+
2023-10-08 17:57:34,908:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
606 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
607 |
+
|
608 |
+
2023-10-08 17:57:34,909:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
609 |
+
if is_categorical_dtype(dtype):
|
610 |
+
|
611 |
+
2023-10-08 17:57:34,909:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
612 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
613 |
+
|
614 |
+
2023-10-08 17:57:34,982:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
615 |
+
if is_sparse(dtype):
|
616 |
+
|
617 |
+
2023-10-08 17:57:34,982:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
618 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
619 |
+
|
620 |
+
2023-10-08 17:57:34,983:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
621 |
+
if is_categorical_dtype(dtype):
|
622 |
+
|
623 |
+
2023-10-08 17:57:34,983:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
624 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
625 |
+
|
626 |
+
2023-10-08 17:57:35,076:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
627 |
+
if is_sparse(dtype):
|
628 |
+
|
629 |
+
2023-10-08 17:57:35,076:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
630 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
631 |
+
|
632 |
+
2023-10-08 17:57:35,078:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
633 |
+
if is_categorical_dtype(dtype):
|
634 |
+
|
635 |
+
2023-10-08 17:57:35,078:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
636 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
637 |
+
|
638 |
+
2023-10-08 17:59:19,597:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
639 |
+
if is_sparse(dtype):
|
640 |
+
|
641 |
+
2023-10-08 17:59:19,598:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
642 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
643 |
+
|
644 |
+
2023-10-08 17:59:19,600:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
645 |
+
if is_categorical_dtype(dtype):
|
646 |
+
|
647 |
+
2023-10-08 17:59:19,601:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
648 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
649 |
+
|
650 |
+
2023-10-08 17:59:19,692:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
651 |
+
if is_sparse(dtype):
|
652 |
+
|
653 |
+
2023-10-08 17:59:19,692:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
654 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
655 |
+
|
656 |
+
2023-10-08 17:59:19,695:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
657 |
+
if is_categorical_dtype(dtype):
|
658 |
+
|
659 |
+
2023-10-08 17:59:19,695:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
660 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
661 |
+
|
662 |
+
2023-10-08 17:59:19,800:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
663 |
+
if is_sparse(dtype):
|
664 |
+
|
665 |
+
2023-10-08 17:59:19,800:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
666 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
667 |
+
|
668 |
+
2023-10-08 17:59:19,801:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
669 |
+
if is_categorical_dtype(dtype):
|
670 |
+
|
671 |
+
2023-10-08 17:59:19,801:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
672 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
673 |
+
|
674 |
+
2023-10-08 18:01:03,749:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
675 |
+
if is_sparse(dtype):
|
676 |
+
|
677 |
+
2023-10-08 18:01:03,749:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
678 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
679 |
+
|
680 |
+
2023-10-08 18:01:03,750:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
681 |
+
if is_categorical_dtype(dtype):
|
682 |
+
|
683 |
+
2023-10-08 18:01:03,751:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
684 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
685 |
+
|
686 |
+
2023-10-08 18:01:03,849:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
687 |
+
if is_sparse(dtype):
|
688 |
+
|
689 |
+
2023-10-08 18:01:03,850:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
690 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
691 |
+
|
692 |
+
2023-10-08 18:01:03,851:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
693 |
+
if is_categorical_dtype(dtype):
|
694 |
+
|
695 |
+
2023-10-08 18:01:03,851:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
696 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
697 |
+
|
698 |
+
2023-10-08 18:01:03,972:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
699 |
+
if is_sparse(dtype):
|
700 |
+
|
701 |
+
2023-10-08 18:01:03,972:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
702 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
703 |
+
|
704 |
+
2023-10-08 18:01:03,974:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
705 |
+
if is_categorical_dtype(dtype):
|
706 |
+
|
707 |
+
2023-10-08 18:01:03,974:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
708 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
709 |
+
|
710 |
+
2023-10-08 18:02:46,388:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
711 |
+
if is_sparse(dtype):
|
712 |
+
|
713 |
+
2023-10-08 18:02:46,388:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
714 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
715 |
+
|
716 |
+
2023-10-08 18:02:46,389:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
717 |
+
if is_categorical_dtype(dtype):
|
718 |
+
|
719 |
+
2023-10-08 18:02:46,389:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
720 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
721 |
+
|
722 |
+
2023-10-08 18:02:46,460:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
723 |
+
if is_sparse(dtype):
|
724 |
+
|
725 |
+
2023-10-08 18:02:46,460:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
726 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
727 |
+
|
728 |
+
2023-10-08 18:02:46,461:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
729 |
+
if is_categorical_dtype(dtype):
|
730 |
+
|
731 |
+
2023-10-08 18:02:46,461:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
732 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
733 |
+
|
734 |
+
2023-10-08 18:02:46,520:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
735 |
+
if is_sparse(dtype):
|
736 |
+
|
737 |
+
2023-10-08 18:02:46,520:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
738 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
739 |
+
|
740 |
+
2023-10-08 18:02:46,521:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
741 |
+
if is_categorical_dtype(dtype):
|
742 |
+
|
743 |
+
2023-10-08 18:02:46,521:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
744 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
745 |
+
|
746 |
+
2023-10-08 18:04:29,787:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
747 |
+
if is_sparse(dtype):
|
748 |
+
|
749 |
+
2023-10-08 18:04:29,788:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
750 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
751 |
+
|
752 |
+
2023-10-08 18:04:29,789:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
753 |
+
if is_categorical_dtype(dtype):
|
754 |
+
|
755 |
+
2023-10-08 18:04:29,789:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
756 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
757 |
+
|
758 |
+
2023-10-08 18:23:23,859:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
759 |
+
if is_sparse(dtype):
|
760 |
+
|
761 |
+
2023-10-08 18:23:23,860:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
762 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
763 |
+
|
764 |
+
2023-10-08 18:23:23,861:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
765 |
+
if is_categorical_dtype(dtype):
|
766 |
+
|
767 |
+
2023-10-08 18:23:23,861:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
768 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
769 |
+
|
770 |
+
2023-10-08 18:23:23,863:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:520: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
771 |
+
if is_sparse(data):
|
772 |
+
|
773 |
+
2023-10-08 18:25:09,016:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
774 |
+
if is_sparse(dtype):
|
775 |
+
|
776 |
+
2023-10-08 18:25:09,016:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
777 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
778 |
+
|
779 |
+
2023-10-08 18:25:09,019:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
780 |
+
if is_categorical_dtype(dtype):
|
781 |
+
|
782 |
+
2023-10-08 18:25:09,019:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
783 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
784 |
+
|
785 |
+
2023-10-08 20:08:20,046:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
786 |
+
if is_sparse(dtype):
|
787 |
+
|
788 |
+
2023-10-08 20:08:20,055:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
789 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
790 |
+
|
791 |
+
2023-10-08 20:08:20,057:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
792 |
+
if is_categorical_dtype(dtype):
|
793 |
+
|
794 |
+
2023-10-08 20:08:20,058:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
795 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
796 |
+
|
797 |
+
2023-10-08 20:08:26,350:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:335: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.
|
798 |
+
if is_sparse(dtype):
|
799 |
+
|
800 |
+
2023-10-08 20:08:26,351:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:338: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
801 |
+
is_categorical_dtype(dtype) or is_pa_ext_categorical_dtype(dtype)
|
802 |
+
|
803 |
+
2023-10-08 20:08:26,352:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:384: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
804 |
+
if is_categorical_dtype(dtype):
|
805 |
+
|
806 |
+
2023-10-08 20:08:26,352:WARNING:/home/wilmarsepulveda/anaconda3/envs/fraud-detection/lib/python3.10/site-packages/xgboost/data.py:359: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
|
807 |
+
return is_int or is_bool or is_float or is_categorical_dtype(dtype)
|
808 |
+
|
notebooks/utils.py
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from sklearn.base import BaseEstimator, TransformerMixin
|
2 |
+
from sklearn.preprocessing import MinMaxScaler, StandardScaler
|
3 |
+
import pandas as pd
|
4 |
+
|
5 |
+
class ScalerDf(BaseEstimator, TransformerMixin):
|
6 |
+
|
7 |
+
def __init__(self, method):
|
8 |
+
self.method = method
|
9 |
+
|
10 |
+
def transform(self, X):
|
11 |
+
X = pd.DataFrame(
|
12 |
+
self.scaler.transform(X),
|
13 |
+
columns=X.columns,
|
14 |
+
index=X.index
|
15 |
+
)
|
16 |
+
return X
|
17 |
+
|
18 |
+
def fit(self, X, y=None):
|
19 |
+
if self.method == 'minmax':
|
20 |
+
self.scaler = MinMaxScaler()
|
21 |
+
elif self.method == 'standard':
|
22 |
+
self.scaler = StandardScaler()
|
23 |
+
elif self.method == 'none':
|
24 |
+
return self
|
25 |
+
else:
|
26 |
+
raise ValueError("Invalid scaling method. Supported methods are 'minmax', 'standard', and 'none'.")
|
27 |
+
|
28 |
+
self.scaler.fit(X)
|
29 |
+
return self
|
requirements.txt
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
## python 3.10
|
2 |
+
pandas==2.1.1
|
3 |
+
scikit-learn==1.3.1
|
4 |
+
feature_engine==1.6.2
|
5 |
+
xgboost==2.0.0
|
6 |
+
gradio==3.35.2
|
src/__pycache__/utils.cpython-310.pyc
ADDED
Binary file (1.19 kB). View file
|
|
src/app.py
ADDED
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import gradio as gr
|
2 |
+
import pandas as pd
|
3 |
+
import joblib
|
4 |
+
import numpy as np
|
5 |
+
import json
|
6 |
+
|
7 |
+
data = pd.read_csv('data/MercadoLibre Data Scientist Technical Challenge - Dataset.csv')
|
8 |
+
pipeline = joblib.load('models/final_pipeline.joblib')
|
9 |
+
ls = ['a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'j', 'k', 'l', 'm', 'n', 'o','p', 'fecha', 'monto', 'score']
|
10 |
+
data = data[ls]
|
11 |
+
def sentence_builder(a, b, c, d, e, f, g, h, j, k, l, m, n, o, p, fecha, monto, score):
|
12 |
+
|
13 |
+
ls = [a, b, c, d, e, f, g, h, j, k, l, m, n, o, p, fecha, monto, score]
|
14 |
+
df = pd.DataFrame(ls).T
|
15 |
+
|
16 |
+
df.columns = data.columns
|
17 |
+
df['a'] = df['a'].astype('int64')
|
18 |
+
df['b'] = df['b'].astype('float64')
|
19 |
+
df['c'] = df['c'].astype('float64')
|
20 |
+
df['d'] = df['d'].astype('float64')
|
21 |
+
df['e'] = df['e'].astype('float64')
|
22 |
+
df['f'] = df['f'].astype('float64')
|
23 |
+
df['g'] = df['g'].astype('object')
|
24 |
+
df['h'] = df['h'].astype('int64')
|
25 |
+
df['j'] = df['j'].astype('object')
|
26 |
+
df['k'] = df['k'].astype('float64')
|
27 |
+
df['l'] = df['l'].astype('float64')
|
28 |
+
df['m'] = df['m'].astype('float64')
|
29 |
+
df['n'] = df['n'].astype('int64')
|
30 |
+
df['o'] = df['o'].astype('object')
|
31 |
+
df['p'] = df['p'].astype('object')
|
32 |
+
df['fecha'] = df['fecha'].astype('object')
|
33 |
+
df['monto'] = df['monto'].astype('float64')
|
34 |
+
df['score'] = df['score'].astype('int64')
|
35 |
+
predict_proba = pipeline.predict_proba(df)[:, 1]
|
36 |
+
predict = np.where(predict_proba<0.05018921, 'No fraude', 'Fraude')
|
37 |
+
print(predict)
|
38 |
+
output = {'probability':str(predict_proba[0]),
|
39 |
+
'prediction':predict[0]}
|
40 |
+
print(output)
|
41 |
+
return json.dumps(output)
|
42 |
+
|
43 |
+
|
44 |
+
demo = gr.Interface(
|
45 |
+
fn = sentence_builder,
|
46 |
+
inputs=[
|
47 |
+
gr.Number(value=4, label="a"),
|
48 |
+
gr.Number(value=0.5217, label="b"),
|
49 |
+
gr.Number(value=17889.0, label="c"),
|
50 |
+
gr.Number(value=1.0, label="d"),
|
51 |
+
gr.Number(value=0.2830350998, label="e"),
|
52 |
+
gr.Number(value=12.0, label="f"),
|
53 |
+
gr.Textbox(value="BR", label="g"),
|
54 |
+
gr.Number(value=36, label="h"),
|
55 |
+
gr.Textbox(value="cat_4744ece", label="j"),
|
56 |
+
gr.Number(value=0.6366103624, label="k"),
|
57 |
+
gr.Number(value=2470.0, label="l"),
|
58 |
+
gr.Number(value=308.0, label="m"),
|
59 |
+
gr.Number(value=1, label="n"),
|
60 |
+
gr.Textbox(value='Y', label="o"),
|
61 |
+
gr.Textbox(value="Y", label="p"),
|
62 |
+
gr.Textbox(value="2020-03-18 09:31:52", label="fecha"),
|
63 |
+
gr.Number(value=24.89, label="monto"),
|
64 |
+
gr.Number(value=93, label="score")
|
65 |
+
],
|
66 |
+
outputs="json"
|
67 |
+
)
|
68 |
+
|
69 |
+
if __name__ == "__main__":
|
70 |
+
demo.launch()
|
src/utils.py
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from sklearn.base import BaseEstimator, TransformerMixin
|
2 |
+
from sklearn.preprocessing import MinMaxScaler, StandardScaler
|
3 |
+
import pandas as pd
|
4 |
+
|
5 |
+
class ScalerDf(BaseEstimator, TransformerMixin):
|
6 |
+
|
7 |
+
def __init__(self, method):
|
8 |
+
self.method = method
|
9 |
+
|
10 |
+
def transform(self, X):
|
11 |
+
X = pd.DataFrame(
|
12 |
+
self.scaler.transform(X),
|
13 |
+
columns=X.columns,
|
14 |
+
index=X.index
|
15 |
+
)
|
16 |
+
return X
|
17 |
+
|
18 |
+
def fit(self, X, y=None):
|
19 |
+
if self.method == 'minmax':
|
20 |
+
self.scaler = MinMaxScaler()
|
21 |
+
elif self.method == 'standard':
|
22 |
+
self.scaler = StandardScaler()
|
23 |
+
elif self.method == 'none':
|
24 |
+
return self
|
25 |
+
else:
|
26 |
+
raise ValueError("Invalid scaling method. Supported methods are 'minmax', 'standard', and 'none'.")
|
27 |
+
|
28 |
+
self.scaler.fit(X)
|
29 |
+
return self
|