jokodm 0.1.0__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- jokodm-0.1.0/LICENSE +13 -0
- jokodm-0.1.0/PKG-INFO +124 -0
- jokodm-0.1.0/README.md +100 -0
- jokodm-0.1.0/pyproject.toml +35 -0
- jokodm-0.1.0/setup.cfg +4 -0
- jokodm-0.1.0/src/jokodm/__init__.py +12 -0
- jokodm-0.1.0/src/jokodm/_dasar.py +117 -0
- jokodm-0.1.0/src/jokodm/_warna.py +20 -0
- jokodm-0.1.0/src/jokodm/svm.py +382 -0
- jokodm-0.1.0/src/jokodm/tree.py +375 -0
- jokodm-0.1.0/src/jokodm.egg-info/PKG-INFO +124 -0
- jokodm-0.1.0/src/jokodm.egg-info/SOURCES.txt +14 -0
- jokodm-0.1.0/src/jokodm.egg-info/dependency_links.txt +1 -0
- jokodm-0.1.0/src/jokodm.egg-info/requires.txt +7 -0
- jokodm-0.1.0/src/jokodm.egg-info/top_level.txt +1 -0
- jokodm-0.1.0/tests/test_jokodm.py +115 -0
jokodm-0.1.0/LICENSE
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
1
|
+
Hak Cipta (c) 2026 Joko Suntoro
|
|
2
|
+
|
|
3
|
+
Library jokodm boleh dipasang dan dipakai secara gratis untuk belajar, mengajar, penelitian,
|
|
4
|
+
dan pekerjaan, termasuk di dalam kode atau tugas milik Anda sendiri.
|
|
5
|
+
|
|
6
|
+
Tanpa izin tertulis dari pemegang hak cipta, Anda tidak boleh:
|
|
7
|
+
1. menjual ulang library ini, baik utuh maupun sebagian;
|
|
8
|
+
2. menerbitkan ulang kode library ini atas nama orang lain atau mengakuinya sebagai karya sendiri.
|
|
9
|
+
|
|
10
|
+
Library ini diberikan "apa adanya", tanpa jaminan apa pun. Pemegang hak cipta tidak bertanggung jawab
|
|
11
|
+
atas kerugian yang timbul dari pemakaiannya.
|
|
12
|
+
|
|
13
|
+
Kontak: jokosuntoro@gmail.com
|
jokodm-0.1.0/PKG-INFO
ADDED
|
@@ -0,0 +1,124 @@
|
|
|
1
|
+
Metadata-Version: 2.4
|
|
2
|
+
Name: jokodm
|
|
3
|
+
Version: 0.1.0
|
|
4
|
+
Summary: Algoritma data mining yang ditulis dari nol (SVM, Decision Tree) lengkap dengan visualisasi, bergaya scikit-learn.
|
|
5
|
+
Author-email: Joko Suntoro <jokosuntoro@gmail.com>
|
|
6
|
+
License-Expression: LicenseRef-Jokodm
|
|
7
|
+
Keywords: data mining,machine learning,svm,decision tree,pembelajaran,visualisasi
|
|
8
|
+
Classifier: Programming Language :: Python :: 3
|
|
9
|
+
Classifier: Operating System :: OS Independent
|
|
10
|
+
Classifier: Intended Audience :: Education
|
|
11
|
+
Classifier: Intended Audience :: Science/Research
|
|
12
|
+
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
|
|
13
|
+
Classifier: Natural Language :: Indonesian
|
|
14
|
+
Requires-Python: >=3.8
|
|
15
|
+
Description-Content-Type: text/markdown
|
|
16
|
+
License-File: LICENSE
|
|
17
|
+
Requires-Dist: matplotlib>=3.3
|
|
18
|
+
Provides-Extra: uji
|
|
19
|
+
Requires-Dist: pytest; extra == "uji"
|
|
20
|
+
Requires-Dist: scikit-learn>=1.3; extra == "uji"
|
|
21
|
+
Requires-Dist: numpy; extra == "uji"
|
|
22
|
+
Requires-Dist: pandas; extra == "uji"
|
|
23
|
+
Dynamic: license-file
|
|
24
|
+
|
|
25
|
+
# jokodm
|
|
26
|
+
|
|
27
|
+
Algoritma data mining yang **ditulis dari nol** (tanpa scikit-learn dan tanpa numpy), lengkap dengan
|
|
28
|
+
**visualisasi** untuk memahami cara kerjanya. Cara pakainya mengikuti gaya scikit-learn (`fit`, `predict`),
|
|
29
|
+
jadi pembagian data dan evaluasi tetap bisa memakai scikit-learn.
|
|
30
|
+
|
|
31
|
+
Versi ini berisi:
|
|
32
|
+
|
|
33
|
+
| Algoritma | Visualisasi | Informasi lain |
|
|
34
|
+
|---|---|---|
|
|
35
|
+
| `SVM` (klasifikasi 2 kelas, kernel linear / rbf / poly) | data, hyperplane, garis margin, support vector, titik baru | `ringkasan()`: persamaan f(x), lebar margin, daftar support vector |
|
|
36
|
+
| `DecisionTree` (Gini, information gain, gain ratio) | pohon keputusan berwarna per kelas | `teks()`, `aturan()` (JIKA ... MAKA ...), `feature_importances_` |
|
|
37
|
+
|
|
38
|
+
## Pemasangan
|
|
39
|
+
|
|
40
|
+
```python
|
|
41
|
+
!pip install jokodm # di Google Colab / Jupyter
|
|
42
|
+
```
|
|
43
|
+
|
|
44
|
+
atau di terminal: `pip install jokodm`
|
|
45
|
+
|
|
46
|
+
## SVM
|
|
47
|
+
|
|
48
|
+
```python
|
|
49
|
+
import pandas as pd
|
|
50
|
+
from jokodm import SVM
|
|
51
|
+
|
|
52
|
+
df = pd.DataFrame({
|
|
53
|
+
"skor_omzet": [4, 0, 5, 2, 4, 1, 5, 0, 3, 1],
|
|
54
|
+
"skor_bayar": [2, 2, 2, 1, 4, 0, 3, 4, 5, 2],
|
|
55
|
+
"kelayakan": ["Layak", "Tidak Layak", "Layak", "Tidak Layak", "Layak",
|
|
56
|
+
"Tidak Layak", "Layak", "Tidak Layak", "Layak", "Tidak Layak"],
|
|
57
|
+
})
|
|
58
|
+
X, y = df[["skor_omzet", "skor_bayar"]], df["kelayakan"]
|
|
59
|
+
|
|
60
|
+
model = SVM(C=1e6, kelas_positif="Layak") # C sangat besar = hard margin
|
|
61
|
+
model.fit(X, y)
|
|
62
|
+
model.ringkasan() # f(x) = 0.8000*skor_omzet + 0.4000*skor_bayar - 3.0000, margin 2.2361
|
|
63
|
+
model.plot(baru=[[3, 3]]) # hyperplane, margin, support vector, dan titik baru
|
|
64
|
+
model.predict([[3, 3]]) # ['Layak']
|
|
65
|
+
```
|
|
66
|
+
|
|
67
|
+
Atribut setelah `fit`: `coef_`, `intercept_`, `margin_`, `support_`, `support_vectors_`, `n_support_`,
|
|
68
|
+
`alpha_`, `persamaan_`. Untuk data yang tidak lurus, pakai `SVM(kernel="rbf", C=5)`; `plot()` menggambar
|
|
69
|
+
batas keputusan yang melengkung.
|
|
70
|
+
|
|
71
|
+
Parameter: `C` (bawaan 1.0), `kernel` (`"linear"`, `"rbf"`, `"poly"`), `gamma` (`"scale"`, `"auto"`, angka),
|
|
72
|
+
`degree`, `coef0`, `tol`, `max_iter`, `kelas_positif`.
|
|
73
|
+
|
|
74
|
+
## Decision Tree
|
|
75
|
+
|
|
76
|
+
```python
|
|
77
|
+
import pandas as pd
|
|
78
|
+
from jokodm import DecisionTree
|
|
79
|
+
|
|
80
|
+
df = pd.read_csv("play-tennis.csv") # outlook, temperature, humidity, windy, play
|
|
81
|
+
X, y = df.drop(columns=["play"]), df["play"]
|
|
82
|
+
|
|
83
|
+
pohon = DecisionTree(criterion="entropy") # "gini", "entropy" (ID3), "gain_ratio" (C4.5)
|
|
84
|
+
pohon.fit(X, y) # atribut teks dipakai langsung, tanpa one-hot
|
|
85
|
+
pohon.plot() # gambar pohon keputusan
|
|
86
|
+
pohon.aturan() # JIKA outlook = sunny DAN humidity = high MAKA play = no ...
|
|
87
|
+
pohon.teks()
|
|
88
|
+
pohon.feature_importances_
|
|
89
|
+
```
|
|
90
|
+
|
|
91
|
+
Atribut kategorik (teks) dipecah menjadi satu cabang per nilai; atribut numerik dipecah menjadi
|
|
92
|
+
`<= ambang` dan `> ambang`. Parameter: `criterion`, `max_depth`, `min_samples_split`, `min_samples_leaf`,
|
|
93
|
+
`min_gain`, `atribut_kategorik`.
|
|
94
|
+
|
|
95
|
+
## Bersama scikit-learn
|
|
96
|
+
|
|
97
|
+
```python
|
|
98
|
+
from sklearn.model_selection import train_test_split, cross_val_score
|
|
99
|
+
from sklearn.metrics import accuracy_score, confusion_matrix, classification_report
|
|
100
|
+
from jokodm import DecisionTree
|
|
101
|
+
|
|
102
|
+
X_latih, X_uji, y_latih, y_uji = train_test_split(X, y, test_size=0.2, random_state=42, stratify=y)
|
|
103
|
+
model = DecisionTree(max_depth=3).fit(X_latih, y_latih)
|
|
104
|
+
y_pred = model.predict(X_uji)
|
|
105
|
+
|
|
106
|
+
print(accuracy_score(y_uji, y_pred))
|
|
107
|
+
print(confusion_matrix(y_uji, y_pred))
|
|
108
|
+
print(classification_report(y_uji, y_pred))
|
|
109
|
+
print(cross_val_score(DecisionTree(max_depth=3), X, y, cv=5))
|
|
110
|
+
```
|
|
111
|
+
|
|
112
|
+
Model jokodm juga bisa dipakai di `GridSearchCV`. Untuk normalisasi data sebelum SVM, pakai
|
|
113
|
+
`MinMaxScaler` atau `StandardScaler` dari scikit-learn.
|
|
114
|
+
|
|
115
|
+
## Ketepatan
|
|
116
|
+
|
|
117
|
+
Hasil jokodm diuji terhadap scikit-learn: SVM menghasilkan prediksi yang sama dengan `sklearn.svm.SVC`
|
|
118
|
+
(kernel linear, rbf, poly), dan Decision Tree menghasilkan pohon dengan jumlah daun dan akurasi yang sama
|
|
119
|
+
dengan `DecisionTreeClassifier` pada data iris, wine, dan breast cancer.
|
|
120
|
+
|
|
121
|
+
## Lisensi
|
|
122
|
+
|
|
123
|
+
Hak Cipta (c) 2026 Joko Suntoro. Gratis dipakai untuk belajar, mengajar, penelitian, dan pekerjaan;
|
|
124
|
+
tidak boleh dijual ulang. Lihat berkas LICENSE. Kontak: jokosuntoro@gmail.com
|
jokodm-0.1.0/README.md
ADDED
|
@@ -0,0 +1,100 @@
|
|
|
1
|
+
# jokodm
|
|
2
|
+
|
|
3
|
+
Algoritma data mining yang **ditulis dari nol** (tanpa scikit-learn dan tanpa numpy), lengkap dengan
|
|
4
|
+
**visualisasi** untuk memahami cara kerjanya. Cara pakainya mengikuti gaya scikit-learn (`fit`, `predict`),
|
|
5
|
+
jadi pembagian data dan evaluasi tetap bisa memakai scikit-learn.
|
|
6
|
+
|
|
7
|
+
Versi ini berisi:
|
|
8
|
+
|
|
9
|
+
| Algoritma | Visualisasi | Informasi lain |
|
|
10
|
+
|---|---|---|
|
|
11
|
+
| `SVM` (klasifikasi 2 kelas, kernel linear / rbf / poly) | data, hyperplane, garis margin, support vector, titik baru | `ringkasan()`: persamaan f(x), lebar margin, daftar support vector |
|
|
12
|
+
| `DecisionTree` (Gini, information gain, gain ratio) | pohon keputusan berwarna per kelas | `teks()`, `aturan()` (JIKA ... MAKA ...), `feature_importances_` |
|
|
13
|
+
|
|
14
|
+
## Pemasangan
|
|
15
|
+
|
|
16
|
+
```python
|
|
17
|
+
!pip install jokodm # di Google Colab / Jupyter
|
|
18
|
+
```
|
|
19
|
+
|
|
20
|
+
atau di terminal: `pip install jokodm`
|
|
21
|
+
|
|
22
|
+
## SVM
|
|
23
|
+
|
|
24
|
+
```python
|
|
25
|
+
import pandas as pd
|
|
26
|
+
from jokodm import SVM
|
|
27
|
+
|
|
28
|
+
df = pd.DataFrame({
|
|
29
|
+
"skor_omzet": [4, 0, 5, 2, 4, 1, 5, 0, 3, 1],
|
|
30
|
+
"skor_bayar": [2, 2, 2, 1, 4, 0, 3, 4, 5, 2],
|
|
31
|
+
"kelayakan": ["Layak", "Tidak Layak", "Layak", "Tidak Layak", "Layak",
|
|
32
|
+
"Tidak Layak", "Layak", "Tidak Layak", "Layak", "Tidak Layak"],
|
|
33
|
+
})
|
|
34
|
+
X, y = df[["skor_omzet", "skor_bayar"]], df["kelayakan"]
|
|
35
|
+
|
|
36
|
+
model = SVM(C=1e6, kelas_positif="Layak") # C sangat besar = hard margin
|
|
37
|
+
model.fit(X, y)
|
|
38
|
+
model.ringkasan() # f(x) = 0.8000*skor_omzet + 0.4000*skor_bayar - 3.0000, margin 2.2361
|
|
39
|
+
model.plot(baru=[[3, 3]]) # hyperplane, margin, support vector, dan titik baru
|
|
40
|
+
model.predict([[3, 3]]) # ['Layak']
|
|
41
|
+
```
|
|
42
|
+
|
|
43
|
+
Atribut setelah `fit`: `coef_`, `intercept_`, `margin_`, `support_`, `support_vectors_`, `n_support_`,
|
|
44
|
+
`alpha_`, `persamaan_`. Untuk data yang tidak lurus, pakai `SVM(kernel="rbf", C=5)`; `plot()` menggambar
|
|
45
|
+
batas keputusan yang melengkung.
|
|
46
|
+
|
|
47
|
+
Parameter: `C` (bawaan 1.0), `kernel` (`"linear"`, `"rbf"`, `"poly"`), `gamma` (`"scale"`, `"auto"`, angka),
|
|
48
|
+
`degree`, `coef0`, `tol`, `max_iter`, `kelas_positif`.
|
|
49
|
+
|
|
50
|
+
## Decision Tree
|
|
51
|
+
|
|
52
|
+
```python
|
|
53
|
+
import pandas as pd
|
|
54
|
+
from jokodm import DecisionTree
|
|
55
|
+
|
|
56
|
+
df = pd.read_csv("play-tennis.csv") # outlook, temperature, humidity, windy, play
|
|
57
|
+
X, y = df.drop(columns=["play"]), df["play"]
|
|
58
|
+
|
|
59
|
+
pohon = DecisionTree(criterion="entropy") # "gini", "entropy" (ID3), "gain_ratio" (C4.5)
|
|
60
|
+
pohon.fit(X, y) # atribut teks dipakai langsung, tanpa one-hot
|
|
61
|
+
pohon.plot() # gambar pohon keputusan
|
|
62
|
+
pohon.aturan() # JIKA outlook = sunny DAN humidity = high MAKA play = no ...
|
|
63
|
+
pohon.teks()
|
|
64
|
+
pohon.feature_importances_
|
|
65
|
+
```
|
|
66
|
+
|
|
67
|
+
Atribut kategorik (teks) dipecah menjadi satu cabang per nilai; atribut numerik dipecah menjadi
|
|
68
|
+
`<= ambang` dan `> ambang`. Parameter: `criterion`, `max_depth`, `min_samples_split`, `min_samples_leaf`,
|
|
69
|
+
`min_gain`, `atribut_kategorik`.
|
|
70
|
+
|
|
71
|
+
## Bersama scikit-learn
|
|
72
|
+
|
|
73
|
+
```python
|
|
74
|
+
from sklearn.model_selection import train_test_split, cross_val_score
|
|
75
|
+
from sklearn.metrics import accuracy_score, confusion_matrix, classification_report
|
|
76
|
+
from jokodm import DecisionTree
|
|
77
|
+
|
|
78
|
+
X_latih, X_uji, y_latih, y_uji = train_test_split(X, y, test_size=0.2, random_state=42, stratify=y)
|
|
79
|
+
model = DecisionTree(max_depth=3).fit(X_latih, y_latih)
|
|
80
|
+
y_pred = model.predict(X_uji)
|
|
81
|
+
|
|
82
|
+
print(accuracy_score(y_uji, y_pred))
|
|
83
|
+
print(confusion_matrix(y_uji, y_pred))
|
|
84
|
+
print(classification_report(y_uji, y_pred))
|
|
85
|
+
print(cross_val_score(DecisionTree(max_depth=3), X, y, cv=5))
|
|
86
|
+
```
|
|
87
|
+
|
|
88
|
+
Model jokodm juga bisa dipakai di `GridSearchCV`. Untuk normalisasi data sebelum SVM, pakai
|
|
89
|
+
`MinMaxScaler` atau `StandardScaler` dari scikit-learn.
|
|
90
|
+
|
|
91
|
+
## Ketepatan
|
|
92
|
+
|
|
93
|
+
Hasil jokodm diuji terhadap scikit-learn: SVM menghasilkan prediksi yang sama dengan `sklearn.svm.SVC`
|
|
94
|
+
(kernel linear, rbf, poly), dan Decision Tree menghasilkan pohon dengan jumlah daun dan akurasi yang sama
|
|
95
|
+
dengan `DecisionTreeClassifier` pada data iris, wine, dan breast cancer.
|
|
96
|
+
|
|
97
|
+
## Lisensi
|
|
98
|
+
|
|
99
|
+
Hak Cipta (c) 2026 Joko Suntoro. Gratis dipakai untuk belajar, mengajar, penelitian, dan pekerjaan;
|
|
100
|
+
tidak boleh dijual ulang. Lihat berkas LICENSE. Kontak: jokosuntoro@gmail.com
|
|
@@ -0,0 +1,35 @@
|
|
|
1
|
+
[build-system]
|
|
2
|
+
requires = ["setuptools>=77"]
|
|
3
|
+
build-backend = "setuptools.build_meta"
|
|
4
|
+
|
|
5
|
+
[project]
|
|
6
|
+
name = "jokodm"
|
|
7
|
+
dynamic = ["version"]
|
|
8
|
+
description = "Algoritma data mining yang ditulis dari nol (SVM, Decision Tree) lengkap dengan visualisasi, bergaya scikit-learn."
|
|
9
|
+
readme = "README.md"
|
|
10
|
+
requires-python = ">=3.8"
|
|
11
|
+
license = "LicenseRef-Jokodm"
|
|
12
|
+
license-files = ["LICENSE"]
|
|
13
|
+
authors = [{ name = "Joko Suntoro", email = "jokosuntoro@gmail.com" }]
|
|
14
|
+
keywords = ["data mining", "machine learning", "svm", "decision tree", "pembelajaran", "visualisasi"]
|
|
15
|
+
dependencies = ["matplotlib>=3.3"]
|
|
16
|
+
classifiers = [
|
|
17
|
+
"Programming Language :: Python :: 3",
|
|
18
|
+
"Operating System :: OS Independent",
|
|
19
|
+
"Intended Audience :: Education",
|
|
20
|
+
"Intended Audience :: Science/Research",
|
|
21
|
+
"Topic :: Scientific/Engineering :: Artificial Intelligence",
|
|
22
|
+
"Natural Language :: Indonesian",
|
|
23
|
+
]
|
|
24
|
+
|
|
25
|
+
[project.optional-dependencies]
|
|
26
|
+
uji = ["pytest", "scikit-learn>=1.3", "numpy", "pandas"]
|
|
27
|
+
|
|
28
|
+
[tool.setuptools.dynamic]
|
|
29
|
+
version = { attr = "jokodm.__version__" }
|
|
30
|
+
|
|
31
|
+
[tool.setuptools.packages.find]
|
|
32
|
+
where = ["src"]
|
|
33
|
+
|
|
34
|
+
[tool.pytest.ini_options]
|
|
35
|
+
testpaths = ["tests"]
|
jokodm-0.1.0/setup.cfg
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
1
|
+
"""jokodm: algoritma data mining yang ditulis dari nol, lengkap dengan visualisasinya.
|
|
2
|
+
|
|
3
|
+
from jokodm import SVM, DecisionTree
|
|
4
|
+
|
|
5
|
+
Pembagian data dan evaluasi bisa memakai scikit-learn (train_test_split, accuracy_score, dan lain-lain).
|
|
6
|
+
"""
|
|
7
|
+
|
|
8
|
+
from .svm import SVM
|
|
9
|
+
from .tree import DecisionTree
|
|
10
|
+
|
|
11
|
+
__version__ = "0.1.0"
|
|
12
|
+
__all__ = ["SVM", "DecisionTree"]
|
|
@@ -0,0 +1,117 @@
|
|
|
1
|
+
"""Bagian bersama: konversi data masukan dan kelas dasar model bergaya scikit-learn.
|
|
2
|
+
|
|
3
|
+
Masukan boleh berupa list, array numpy, atau DataFrame/Series pandas. Di dalam library semua data
|
|
4
|
+
disimpan sebagai list Python biasa, jadi jokodm tidak bergantung pada numpy maupun scikit-learn.
|
|
5
|
+
"""
|
|
6
|
+
|
|
7
|
+
import inspect
|
|
8
|
+
import numbers
|
|
9
|
+
|
|
10
|
+
|
|
11
|
+
def ke_tabel(X):
|
|
12
|
+
"""Ubah X menjadi (baris, nama_kolom). baris = list of list; nama_kolom = list atau None."""
|
|
13
|
+
nama = None
|
|
14
|
+
if hasattr(X, "columns") and hasattr(X, "values"): # DataFrame pandas
|
|
15
|
+
nama = [str(c) for c in X.columns]
|
|
16
|
+
baris = X.values.tolist()
|
|
17
|
+
elif hasattr(X, "tolist"): # array numpy
|
|
18
|
+
baris = X.tolist()
|
|
19
|
+
else:
|
|
20
|
+
baris = [list(r) if isinstance(r, (list, tuple)) else r for r in X]
|
|
21
|
+
if not baris:
|
|
22
|
+
raise ValueError("Data X kosong.")
|
|
23
|
+
if not isinstance(baris[0], (list, tuple)):
|
|
24
|
+
raise ValueError("X harus 2 dimensi (baris x atribut). Untuk satu atribut pakai X = df[['nama_kolom']] "
|
|
25
|
+
"atau [[nilai], [nilai], ...].")
|
|
26
|
+
lebar = len(baris[0])
|
|
27
|
+
for i, r in enumerate(baris):
|
|
28
|
+
if len(r) != lebar:
|
|
29
|
+
raise ValueError(f"Baris ke-{i} punya {len(r)} nilai, padahal baris pertama punya {lebar}.")
|
|
30
|
+
return [list(r) for r in baris], nama
|
|
31
|
+
|
|
32
|
+
|
|
33
|
+
def ke_list(y):
|
|
34
|
+
"""Ubah y (list/array/Series) menjadi list 1 dimensi."""
|
|
35
|
+
if hasattr(y, "values") and hasattr(y, "index"): # Series pandas
|
|
36
|
+
y = y.values
|
|
37
|
+
if hasattr(y, "tolist"):
|
|
38
|
+
y = y.tolist()
|
|
39
|
+
y = list(y)
|
|
40
|
+
if y and isinstance(y[0], (list, tuple)):
|
|
41
|
+
if all(len(v) == 1 for v in y):
|
|
42
|
+
return [v[0] for v in y]
|
|
43
|
+
raise ValueError("y harus 1 dimensi (satu label per baris).")
|
|
44
|
+
return y
|
|
45
|
+
|
|
46
|
+
|
|
47
|
+
def angka(v):
|
|
48
|
+
"""True bila v angka (bukan bool)."""
|
|
49
|
+
return isinstance(v, numbers.Number) and not isinstance(v, bool)
|
|
50
|
+
|
|
51
|
+
|
|
52
|
+
def ke_float(baris):
|
|
53
|
+
out = []
|
|
54
|
+
for i, r in enumerate(baris):
|
|
55
|
+
try:
|
|
56
|
+
out.append([float(v) for v in r])
|
|
57
|
+
except (TypeError, ValueError):
|
|
58
|
+
raise ValueError(f"Baris ke-{i} berisi nilai bukan angka: {r}. Algoritma ini butuh atribut numerik.")
|
|
59
|
+
return out
|
|
60
|
+
|
|
61
|
+
|
|
62
|
+
def bersih(v):
|
|
63
|
+
"""Nilai numpy (misal numpy.int64) menjadi nilai Python biasa agar tampilan rapi."""
|
|
64
|
+
if hasattr(v, "item") and not isinstance(v, (str, bytes)):
|
|
65
|
+
try:
|
|
66
|
+
return v.item()
|
|
67
|
+
except (ValueError, AttributeError):
|
|
68
|
+
return v
|
|
69
|
+
return v
|
|
70
|
+
|
|
71
|
+
|
|
72
|
+
class ModelDasar:
|
|
73
|
+
"""Kelas dasar: get_params / set_params / __repr__ seperti estimator scikit-learn,
|
|
74
|
+
sehingga model jokodm bisa dipakai di cross_val_score dan GridSearchCV."""
|
|
75
|
+
|
|
76
|
+
_estimator_type = "classifier"
|
|
77
|
+
|
|
78
|
+
@classmethod
|
|
79
|
+
def _nama_param(cls):
|
|
80
|
+
sig = inspect.signature(cls.__init__)
|
|
81
|
+
return [p.name for p in sig.parameters.values() if p.name != "self" and p.kind != p.VAR_KEYWORD]
|
|
82
|
+
|
|
83
|
+
def get_params(self, deep=True):
|
|
84
|
+
return {k: getattr(self, k) for k in self._nama_param()}
|
|
85
|
+
|
|
86
|
+
def set_params(self, **params):
|
|
87
|
+
sah = self._nama_param()
|
|
88
|
+
for k, v in params.items():
|
|
89
|
+
if k not in sah:
|
|
90
|
+
raise ValueError(f"Parameter '{k}' tidak dikenal. Parameter yang ada: {', '.join(sah)}.")
|
|
91
|
+
setattr(self, k, v)
|
|
92
|
+
return self
|
|
93
|
+
|
|
94
|
+
def __sklearn_tags__(self):
|
|
95
|
+
"""Label model untuk scikit-learn >= 1.6 (dipanggil oleh cross_val_score, GridSearchCV, dan sejenisnya).
|
|
96
|
+
scikit-learn hanya di-import saat fungsi ini dipanggil, jadi jokodm tetap bisa dipakai tanpa scikit-learn."""
|
|
97
|
+
from sklearn.utils import ClassifierTags, InputTags, Tags, TargetTags
|
|
98
|
+
|
|
99
|
+
return Tags(estimator_type="classifier", target_tags=TargetTags(required=True),
|
|
100
|
+
classifier_tags=ClassifierTags(), input_tags=InputTags(string=self._terima_teks))
|
|
101
|
+
|
|
102
|
+
_terima_teks = False
|
|
103
|
+
|
|
104
|
+
def __repr__(self):
|
|
105
|
+
bawaan = {p.name: p.default for p in inspect.signature(type(self).__init__).parameters.values() if p.name != "self"}
|
|
106
|
+
isi = [f"{k}={v!r}" for k, v in self.get_params().items() if bawaan.get(k, object()) != v]
|
|
107
|
+
return f"{type(self).__name__}({', '.join(isi)})"
|
|
108
|
+
|
|
109
|
+
def _cek_terlatih(self):
|
|
110
|
+
if not getattr(self, "terlatih_", False):
|
|
111
|
+
raise RuntimeError(f"Model {type(self).__name__} belum dilatih. Jalankan .fit(X, y) dulu.")
|
|
112
|
+
|
|
113
|
+
def score(self, X, y):
|
|
114
|
+
"""Akurasi pada data (X, y)."""
|
|
115
|
+
y = ke_list(y)
|
|
116
|
+
p = self.predict(X)
|
|
117
|
+
return sum(1 for a, b in zip(y, p) if a == b) / len(y)
|
|
@@ -0,0 +1,20 @@
|
|
|
1
|
+
"""Palet warna grafik jokodm (tetradic, biru dominan)."""
|
|
2
|
+
|
|
3
|
+
KELAS = ["#1F7AE0", "#F0882A", "#7B57D1", "#4E9A2E", "#155BB0", "#C2621A", "#5A3BA8", "#36721D"]
|
|
4
|
+
MUDA = ["#D6E7FB", "#FCE3CC", "#E4DBF6", "#DCEED3", "#CFDDF0", "#F3D8C2", "#DCD3EF", "#D3E3CA"]
|
|
5
|
+
PENANDA = ["o", "s", "^", "D", "v", "P", "X", "h"]
|
|
6
|
+
TINTA = "#10233F"
|
|
7
|
+
REDUP = "#5B6B82"
|
|
8
|
+
GARIS = "#DCE5F0"
|
|
9
|
+
|
|
10
|
+
|
|
11
|
+
def warna(i):
|
|
12
|
+
return KELAS[i % len(KELAS)]
|
|
13
|
+
|
|
14
|
+
|
|
15
|
+
def muda(i):
|
|
16
|
+
return MUDA[i % len(MUDA)]
|
|
17
|
+
|
|
18
|
+
|
|
19
|
+
def penanda(i):
|
|
20
|
+
return PENANDA[i % len(PENANDA)]
|