Classifiers.py

'''
Logistic Regression
'''
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score, confusion_matrix, f1_score, roc_curve, precision_score, classification_report
lgmodel = LogisticRegression(max_iter=100, C=1e5)
lgmodel.fit(X_train, y_train)
ypred=lgmodel.predict(X_test)
print(lgmodel.score(X_train, y_train))
print(confusion_matrix(y_test,ypred))
print(classification_report(y_test, ypred))

'''
0.8132022471910112
[[94 12]
 [31 42]]
             precision    recall  f1-score   support

          0       0.75      0.89      0.81       106
          1       0.78      0.58      0.66        73

avg / total       0.76      0.76      0.75       179
'''
########################################################
'''
SVM
'''
from sklearn.svm import SVC
modelsvc=SVC(probability=True, gamma='auto')
modelsvc.fit(X_train, y_train)
ypred=modelsvc.predict(X_test)
print(modelsvc.score(X_train, y_train))
print(confusion_matrix(y_test, ypred))
print(classification_report(y_test, ypred))

'''
0.7893258426966292
[[90 16]
 [24 49]]
             precision    recall  f1-score   support

          0       0.79      0.85      0.82       106
          1       0.75      0.67      0.71        73

avg / total       0.77      0.78      0.77       179
'''
########################################################
'''
Decision tree
'''
from sklearn.tree import DecisionTreeClassifier
dtmodel=DecisionTreeClassifier()
dtmodel.fit(X_train, y_train)
ypred=dtmodel.predict(X_test)
print(dtmodel.score(X_train, y_train))
print(confusion_matrix(y_test, ypred))
print(classification_report(y_test, ypred))

'''
0.8637640449438202
[[95 11]
 [35 38]]
             precision    recall  f1-score   support

          0       0.73      0.90      0.81       106
          1       0.78      0.52      0.62        73

avg / total       0.75      0.74      0.73       179
'''
########################################################
'''
Random Forest
'''
from sklearn.ensemble import RandomForestClassifier
rfmodel=RandomForestClassifier(n_estimators=60)
rfmodel.fit(X_train, y_train)
ypred=rfmodel.predict(X_test)
print(rfmodel.score(X_train, y_train))
print(confusion_matrix(y_test, ypred))
print(classification_report(y_test, ypred))
'''
0.8637640449438202
[[95 11]
 [33 40]]
             precision    recall  f1-score   support

          0       0.74      0.90      0.81       106
          1       0.78      0.55      0.65        73

avg / total       0.76      0.75      0.74       179
'''
########################################################
'''
Gradient Boosting
'''
from sklearn.ensemble import GradientBoostingClassifier
gbm=GradientBoostingClassifier(n_estimators=100)
gbm.fit(X_train, y_train)
ypred=gbm.predict(X_test)
print(gbm.score(X_train, y_train))
print(confusion_matrix(y_test, ypred))
print(classification_report(y_test, ypred))

'''
0.8455056179775281
[[96 10]
 [32 41]]
             precision    recall  f1-score   support

          0       0.75      0.91      0.82       106
          1       0.80      0.56      0.66        73

avg / total       0.77      0.77      0.76       179
'''
########################################################
'''
Ensemble Voting Classifier
'''
from sklearn.ensemble import VotingClassifier
votingmodel=VotingClassifier(estimators=[('Logis',lgmodel), ('svc',modelsvc), ('dt',dtmodel), \
                                         ('rf',rfmodel), ('gbm',gbm)], voting='soft', n_jobs=5)
voting=votingmodel.fit(X_train, y_train)

'''
[[256  10]
 [ 30 122]]
             precision    recall  f1-score   support

          0       0.90      0.96      0.93       266
          1       0.92      0.80      0.86       152

avg / total       0.91      0.90      0.90       418
'''