adsa/ensemble at main · RogerKrizz/adsa · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
# ==========================================================
# 1. IMPORT LIBRARIES
# ==========================================================
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

# Models
from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClassifier
from sklearn.svm import SVC

# Ensemble methods
from sklearn.ensemble import VotingClassifier, BaggingClassifier, AdaBoostClassifier

# Preprocessing
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler

# Evaluation
from sklearn.metrics import accuracy_score, confusion_matrix, classification_report


# ==========================================================
# 2. LOAD DATASET
# ==========================================================
data = pd.read_csv('your_file.csv')

print("\nFirst 5 rows:\n", data.head())
print("\nDataset Info:\n")
print(data.info())


# ==========================================================
# 3. DATA CLEANING
# ==========================================================
data = data.drop_duplicates()

print("\nMissing Values:\n", data.isnull().sum())

num_cols = data.select_dtypes(include=np.number).columns
data[num_cols] = data[num_cols].fillna(data[num_cols].mean())


# ==========================================================
# 4. FEATURES & TARGET
# ==========================================================
X = data.iloc[:, :-1]
y = data.iloc[:, -1]


# ==========================================================
# 5. TRAIN-TEST SPLIT
# ==========================================================
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.2, random_state=42
)


# ==========================================================
# 6. FEATURE SCALING
# ==========================================================
scaler = StandardScaler()

X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)


# ==========================================================
# 7. BASE MODELS
# ==========================================================
model1 = LogisticRegression(max_iter=1000)
model2 = DecisionTreeClassifier()
model3 = SVC(probability=True)


# ==========================================================
# 8. VOTING ENSEMBLE
# ==========================================================
voting_model = VotingClassifier(
    estimators=[
        ('lr', model1),
        ('dt', model2),
        ('svm', model3)
    ],
    voting='soft'   # soft voting uses probabilities
)

voting_model.fit(X_train, y_train)

y_pred_vote = voting_model.predict(X_test)


# ==========================================================
# 9. BAGGING
# ==========================================================
bagging_model = BaggingClassifier(
    estimator=DecisionTreeClassifier(),
    n_estimators=50,
    random_state=42
)

bagging_model.fit(X_train, y_train)

y_pred_bag = bagging_model.predict(X_test)


# ==========================================================
# 10. BOOSTING (AdaBoost)
# ==========================================================
boost_model = AdaBoostClassifier(
    n_estimators=50,
    random_state=42
)

boost_model.fit(X_train, y_train)

y_pred_boost = boost_model.predict(X_test)


# ==========================================================
# 11. EVALUATION
# ==========================================================
print("\n--- Voting Classifier ---")
print("Accuracy:", accuracy_score(y_test, y_pred_vote))

print("\n--- Bagging ---")
print("Accuracy:", accuracy_score(y_test, y_pred_bag))

print("\n--- Boosting ---")
print("Accuracy:", accuracy_score(y_test, y_pred_boost))


# ==========================================================
# 12. CONFUSION MATRIX (example: voting)
# ==========================================================
print("\nConfusion Matrix (Voting):\n", confusion_matrix(y_test, y_pred_vote))
print("\nClassification Report:\n", classification_report(y_test, y_pred_vote))


# ==========================================================
# 13. PREDICT NEW DATA
# ==========================================================
# new_data = np.array([[val1, val2, ...]])
# new_data_scaled = scaler.transform(new_data)
# prediction = voting_model.predict(new_data_scaled)

# print("Predicted Class:", prediction)