Upload 4 files

app.py

@@ -0,0 +1,201 @@
+import streamlit as st
+import pickle
+import pandas as pd
+import joblib
+
+loaded_model = pickle.load(open('D:/Agri Sparta Indonesia/Credit Score/Multiclass Project Score/deploy/trained_model.sav', 'rb'))
+preprocessor = joblib.load("D:/Agri Sparta Indonesia/Credit Score/Multiclass Project Score/deploy/preprocessor.pkl")
+
+def obj_to_int(data):
+    # Mengganti nilai pada kolom planting_period
+    one_hot_enc = pd.get_dummies(data, columns=['planting_period', 'variety'])
+    
+    return one_hot_enc
+    
+def transform_normalize(data, normalizer):
+    normalize_data = pd.DataFrame(normalizer.transform(data))
+    normalize_data.columns = data.columns
+    normalize_data.index = data.index
+    return normalize_data
+   
+def preprocess(data):
+    # 1. Encoding Categorical Value
+    X_encoded = obj_to_int(data)
+
+    required_features = ['planting_period_MT1',
+                        'planting_period_MT2',
+                        'planting_period_MT3',
+                        'variety_Umum',
+                        'variety_Hibrida'
+                        ]
+
+    existing_features = set(X_encoded.columns)
+
+    # Ambil perbedaan antara fitur yang dibutuhkan dan yang sudah ada
+    missing_features = set(required_features) - existing_features
+
+    list_missing_features = list(missing_features)
+
+    for feature in list_missing_features:
+        X_encoded[feature] = 0
+
+    # urutkan column sesuai data train
+    column_order = ['completion_rate',
+                    'complete_time',
+                    'profit','harvest',
+                    'planting_period_MT1',
+                    'planting_period_MT2',
+                    'planting_period_MT3',
+                    'variety_Hibrida',
+                    'variety_Umum'
+                    ]
+
+    X_encoded = X_encoded[column_order]
+
+    # 2. Normalization
+    X_clean = transform_normalize(data = X_encoded,
+                                    normalizer = preprocessor['normalizer'])
+
+    return X_clean
+
+def calculate_harvest_score(row):
+    variety = row['variety']
+    harvest = row['harvest']
+    variety_umum = ['Umum', 'Sintanur', 'Mentik']
+    variety_hibrida = ['Hibrida', 'Mapan']
+
+    if variety in variety_umum:
+        if harvest < 3000:
+            score_harvest = 46.79
+        elif 3000 <= harvest <= 5000:
+            score_harvest = 64.24
+        elif 5001 <= harvest <= 7000:
+            score_harvest = 93.57
+        else:
+            score_harvest = 102.83
+            
+    elif variety in variety_hibrida:
+        if harvest < 5000:
+            score_harvest = 40.55
+        elif 5001 <= harvest <= 7000:
+            score_harvest = 54.02
+        elif 7001 <= harvest <= 9000:
+            score_harvest = 68.34
+        else:
+            score_harvest = 85.17
+    else:
+        score_harvest = 0
+    
+    return score_harvest
+
+def calculate_profit_score(row):
+    profit = row['profit']
+    
+    if profit <= 0:
+        score_profit = 0
+    elif 1 <= profit <= 2000000:
+        score_profit = 27.84
+    else:
+        score_profit = 39.5
+    
+    return score_profit
+
+def calculate_complete_time_score(row):
+    complete_time = row['complete_time']
+
+    if complete_time <= 3:
+        score_complete_time = 10.21
+        return score_complete_time
+    
+    elif 4 <= complete_time <= 7:
+        score_complete_time = 6.69
+        return score_complete_time
+    
+    else:
+        score_complete_time = 1
+        return score_complete_time
+
+def calculate_completion_rate_score(row):
+    completion_rate = row['completion_rate']
+
+    if completion_rate <= 60:
+        score_completion_rate = 17.31
+        return score_completion_rate
+    
+    elif 61 <= completion_rate <= 70:
+        score_completion_rate = 21.04
+        return score_completion_rate
+    
+    elif 71 <= completion_rate <= 80:
+        score_completion_rate = 25.21
+        return score_completion_rate
+    
+    elif 81 <= completion_rate <= 90:
+        score_completion_rate = 30.1
+        return score_completion_rate
+    
+    else:
+        score_completion_rate = 34.4
+        return score_completion_rate
+
+def total_score(data):
+    harvest_score = data.apply(calculate_harvest_score, axis=1)
+    profit_score = data.apply(calculate_profit_score, axis=1)
+    completion_rate_score = data.apply(calculate_completion_rate_score, axis=1)
+    complete_time_score = data.apply(calculate_complete_time_score, axis=1)
+
+    score = harvest_score + profit_score + complete_time_score + completion_rate_score
+
+    return score
+
+def map_class_to_label(class_score):
+    class_labels = {
+        0: "Sangat Baik",
+        1: "Baik",
+        2: "Cukup",
+        3: "Buruk",
+        4: "Sangat Buruk"
+    }
+    return class_labels.get(class_score, "Unknown")
+
+def calculate_scoring(data):
+    score = total_score(data)
+    clean_data = preprocess(data)
+    hasil = loaded_model.predict(clean_data)
+
+    # Mapping nilai pada hasil ke label yang diinginkan
+    hasil_labels = [map_class_to_label(pred_class) for pred_class in hasil]
+
+    print('Hasil adalah', hasil_labels,
+          '\nTotal Score: ', score)
+    return hasil_labels, score
+
+def main():
+    st.title("Project Scoring")
+
+    # Membuat tombol untuk upload file CSV
+    uploaded_file = st.file_uploader("Upload CSV file", type=["csv"])
+
+    if uploaded_file is not None:
+        # Membaca file CSV menjadi DataFrame
+        data = pd.read_csv(uploaded_file)
+
+        # Menampilkan preview dari data yang diupload
+        st.write("Preview Data:")
+        st.write(data.head())
+
+        # Membuat tombol "Calculate Scoring"
+        if st.button("Calculate Scoring"):
+            # Memanggil fungsi untuk menghitung scoring
+            hasil_scoring = calculate_scoring(data)
+
+            # Menampilkan hasil scoring
+            st.write("Hasil Scoring:")
+            hasil_df = pd.DataFrame({
+                'Kategori': hasil_scoring[0],
+                'Total Score': hasil_scoring[1]
+            })
+            st.table(hasil_df)
+
+if __name__ == "__main__":
+    main()

preprocessor.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23a82f8723bdf2bdc87a564ae0bcf069f5f160bf31a76c6fd54070f1eb5a88e7
+size 11522768

requirements.txt

@@ -0,0 +1,10 @@
+streamlit==1.29.0
+pandas==1.5.3
+transformers==4.36.0
+streamlit==1.29.0
+pandas==1.5.3
+joblib==1.2.0
+scikit-learn==1.2.2
+numpy==1.23.3
+xgboost==2.0.2
+pickle