Create app.py

app.py

@@ -0,0 +1,81 @@
+import os
+import pandas as pd
+import streamlit as st
+from sklearn.linear_model import LinearRegression
+
+def predict_hotel_price(train_features_path, train_label_path, test_features_path):
+    # Baca data dari file train_features.csv
+    train_features = pd.read_csv(train_features_path)
+
+    # Baca data dari file train_label.csv
+    train_label = pd.read_csv(train_label_path)
+
+    # Gabungkan kedua dataframe berdasarkan indeks
+    df_merged = pd.concat([train_features, train_label], axis=1)
+
+    # Tambahkan kolom 'id' di paling kiri dengan menggunakan range indeks
+    df_merged.insert(0, 'ID', range(len(df_merged)))
+
+    # Simpan dataframe ke dalam file CSV
+    df_merged.to_csv('merged_data.csv', index=False)
+
+    # Baca file merged_data.csv sebagai hasil prapemrosesan
+    hasil_features = pd.read_csv('merged_data.csv')
+
+    # Prapemrosesan data pada kolom rating dengan mengubah format string menjadi float
+    hasil_features['rating'] = hasil_features['rating'].apply(lambda x: float(x.split()[0]) if isinstance(x, str) and len(x.split())>0 and x.split()[0].replace('.','').isdigit() else None)
+    hasil_features['Price'] = hasil_features['Price'].apply(lambda x: float(x.replace(',', '').replace('avg/night', '')) if isinstance(x, str) else x)
+
+    # Menghilangkan missing value pada kolom rating
+    hasil_features.dropna(subset=['rating'], inplace=True)
+    hasil_features = hasil_features.drop(['facilities', 'location'], axis=1)
+
+    # Membuat model Linear Regression
+    model = LinearRegression()
+
+    # Melatih model dengan dataset train
+    model.fit(hasil_features.drop(['ID', 'Price'], axis=1), hasil_features['Price'])
+
+    # Membaca dataset test dan menghapus kolom facilities, location, dan ID
+    test_features = pd.read_csv(test_features_path)
+    test_features = test_features.drop(['facilities', 'location', 'ID'], axis=1)
+
+    # Prapemrosesan data pada kolom rating dengan mengubah format string menjadi float
+    test_features['rating'] = test_features['rating'].apply(lambda x: float(x.split()[0]) if isinstance(x, str) else x)
+
+    # Melakukan prediksi terhadap dataset test
+    predictions = model.predict(test_features)
+
+    # Convert predictions to a pandas dataframe
+    predictions_df = pd.DataFrame(predictions, columns=['Price'])
+
+    # Add the 'ID' column using square bracket notation
+    predictions_df.insert(loc=0, column='ID', value=range(len(predictions_df)))
+
+    # mengubah nilai kolom Price menjadi bilangan bulat
+    predictions_df['Price'] = predictions_df['Price'].astype(int)
+
+    # Membuat file CSV dari dataframe predictions_df
+    predictions_df.to_csv('predictions.csv', index=False)
+    return predictions_df
+
+def main():
+    st.title("Hotel Price Prediction")
+    st.write("Predict the price of hotel rooms based on the given features")
+
+    # Membuat list nama file dari direktori yang berisi file input
+    input_dir = '/content/dataset'
+    input_files = os.listdir(input_dir)
+
+    # Mengubah list nama file menjadi opsi dropdown
+    train_features_path = st.selectbox("Train Features", [os.path.join(input_dir, file) for file in input_files])
+    train_label_path = st.selectbox("Train Label", [os.path.join(input_dir, file) for file in input_files])
+    test_features_path = st.selectbox("Test Features", [os.path.join(input_dir, file) for file in input_files])
+
+    # Menjalankan fungsi predict_hotel_price dan menampilkan hasilnya
+    if st.button("Predict"):
+        predictions_df = predict_hotel_price(train_features_path, train_label_path, test_features_path)
+        st.write(predictions_df)
+
+if __name__ == '__main__':
+    main()