Upload 3 files

app.py

@@ -0,0 +1,38 @@
+import streamlit as st
+import pandas as pd
+import numpy as np
+import joblib
+from sklearn.preprocessing import StandardScaler
+
+# Modeli yükle
+model = joblib.load('best_xgb_model.joblib')
+
+# Önemli özellikler (örnek olarak 106 adet özellik)
+relevant_features = [f'feature_{i}' for i in range(1, 107)]  # feature_1, feature_2, ..., feature_106
+
+# Rastgele veriler oluştur
+def generate_random_input():
+    random_data = {feature: np.random.uniform(0, 1) for feature in relevant_features}
+    return pd.DataFrame(random_data, index=[0])
+
+# Rastgele veriyi al
+input_data = generate_random_input()
+
+# Özellikleri ölçeklendir
+scaler = StandardScaler()
+input_data_scaled = scaler.fit_transform(input_data)
+
+# Tahmin yap
+prediction = model.predict_proba(input_data_scaled)[:, 1]
+
+# Sonucu göster
+st.title('Santander Müşteri Memnuniyeti Tahmini')
+st.subheader('Rastgele Oluşturulan Girdi')
+st.write(input_data)
+
+st.subheader('Tahmin Sonucu')
+st.write(f'Müşteri Memnuniyeti Tahmini: {prediction[0]:.2f}')
+
+# Uygulamayı çalıştırma
+if __name__ == '__main__':
+    st.title('Santander Müşteri Memnuniyeti Tahmini')

best_xgb_model.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8de083f2f2f53757734fd6581ee4c5e38816831a2b3ea2a7be081d73c3b24fbb
+size 561634

requirements.txt

@@ -0,0 +1,12 @@
+streamlit
+tensorflow
+opencv-python
+scikit-learn
+torch
+torchvision
+matplotlib
+transformers
+sentencepiece
+plotly
+xgboost
+joblib