PranjalDureja0002

#In the 80% train set, split the train set into d1 and d2.(50-50).
d1,d2,y1,y2 = train_test_split(X_train,y_train,stratify=y_train,test_size=0.5,random_state=15)
d1 = d1.reset_index(drop=True)
d2 = d2.reset_index(drop=True)
y1 = y1.reset_index(drop=True)
y2 = y2.reset_index(drop=True)

def generating_samples(d1, y1):
    """From this d1,sampling with replacement is done
    """

PranjalDureja0002

+---------------------+-----------------+----------------+----------------+---------------+
|        Model        | Train AUC Score | Test AUC Score | Train F1 Score | Test F1 Score |
+---------------------+-----------------+----------------+----------------+---------------+
| Stacking_Classifier |     0.99537     |     0.9902     |    0.99429     |    0.98759    |
+---------------------+-----------------+----------------+----------------+---------------+

PranjalDureja0002

x_cfl=XGBClassifier(n_estimators=1000,nthread=-1)
x_1=XGBClassifier(n_estimators=500,nthread=-1)
x_2=XGBClassifier(n_estimators=500,nthread=-1)

x_3 = DecisionTreeClassifier(max_depth=best_depth,min_samples_split=best_samples,class_weight='balanced')
x_4 = LogisticRegression(class_weight='balanced')
s_clf = StackingClassifier(classifiers=[x_1,x_2,x_3,x_4],meta_classifier=x_cfl)
s_clf.fit(X_train,y_train)
#sig_clf = CalibratedClassifierCV(x_cfl, method="sigmoid")
#sig_clf.fit(X_train_f, y_train_f)

PranjalDureja0002

+---------+-----------------+----------------+----------------+---------------+
|  Model  | Train AUC Score | Test AUC Score | Train F1 Score | Test F1 Score |
+---------+-----------------+----------------+----------------+---------------+
| XgBoost |     0.99938     |    0.99855     |     0.9998     |    0.990791   |
+---------+-----------------+----------------+----------------+---------------+

PranjalDureja0002

s1 = data['score']
s_s1 = sum(s1.tolist())
s_s1

plt.style.use('fivethirtyeight')
ax=data.head(20).plot(kind = 'barh' , color = 'red')
for p in ax.patches:
        percentage = '{:.1f}%'.format(100 * p.get_width()/s_s1) 
        x = p.get_x() + p.get_width() - 0.5
        y = p.get_y() + p.get_height()

PranjalDureja0002

provider_count	14960
State	5550
attend_physician_count	4258
County	3218
OPAnnualReimbursementAmt	816
total_diff_amount	800
ClmDiagnosisCode_1_count	713
OPAnnualDeductibleAmt	668
InscClaimAmtReimbursed	634

PranjalDureja0002

feature_important = xg1.get_booster().get_score(importance_type='weight')
keys = list(feature_important.keys())
values = list(feature_important.values())

data = pd.DataFrame(data=values, index=keys, columns=["score"]).sort_values(by = "score", ascending=False)

PranjalDureja0002

training score: 0.9998006310038143
testing score: 0.990791808142236

PranjalDureja0002

# A parameter grid for XGBoost
parameters = {    
    'n_estimators': [100,500,1000],
    'learning_rate': [0.1, 0.01, 0.05]
}

xgb = XGBClassifier(objective='binary:logistic',
                    silent=True, nthread=4)

xg_grid = GridSearchCV(xgb, param_grid=parameters, n_jobs=-1, verbose=1,scoring='f1_macro',cv=3,return_train_score=True)

PranjalDureja0002

+---------------+-----------------+----------------+----------------+---------------+
|     Model     | Train AUC Score | Test AUC Score | Train F1 Score | Test F1 Score |
+---------------+-----------------+----------------+----------------+---------------+
| Decision_Tree |      0.9967     |     0.9909     |    0.99314     |     0.9771    |
+---------------+-----------------+----------------+----------------+---------------+