oguzhari

#Model Eğitimleri.

#MultinomialNB Best random_state=3305
X_train, X_test, y_train, y_test = train_test_split(ogrenme_seti.iloc[:, 0:4], ogrenme_seti.iloc[:,-1:], test_size=0.25,random_state=3305)
clf.fit(X_train,y_train.values.ravel())
y_pred_test = clf.predict(X_test)
print("Naive Bayes::\n", confusion_matrix(y_test,y_pred_test), "\n")
f1_1 = f1_score(y_test,y_pred_test,average='macro')
print(classification_report(y_test,y_pred_test))
print("Accuracy: ",accuracy_score(y_test,y_pred_test))

oguzhari

#Model Tanımları
clf = MultinomialNB()
lr = LogisticRegression()
dtc = DecisionTreeClassifier()
rfc = RandomForestClassifier()
gradient = GradientBoostingClassifier()
xgb = XGBClassifier()

oguzhari

#Feature Normalization
#Kelime Sayısı Normalizasiyonu        
kelsay_normal = []
for i in ogrenme_seti['kelsay']:
    normal = (i - ogrenme_seti['kelsay'].min()) / (ogrenme_seti['kelsay'].max() - ogrenme_seti['kelsay'].min())
    kelsay_normal.append(normal)

#Set'e eklenme
ogrenme_seti['kelsay'] = kelsay_normal

oguzhari

#Veri yükleme
ogrenme_seti = pd.read_csv('set/ogrenme_seti.csv', sep=',')
corpus = pd.read_csv('set/hepsiburada_corpus.csv', sep=';')
#Veriler arasında farklar olduğu için sep değişkenleri dosyadan dosyaya değişmekte.

oguzhari

#Gerekli Kütüphanelerin import edilmesi
import warnings
warnings.filterwarnings("ignore", category=FutureWarning)
warnings.filterwarnings("ignore", category=UserWarning)
from sklearn.metrics import classification_report, f1_score, confusion_matrix, accuracy_score, roc_auc_score,roc_curve, precision_score, recall_score
from sklearn.model_selection import cross_val_score
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClassifier
from sklearn.naive_bayes import MultinomialNB