From b589c56e0c86cfca2950e855102bfdf0711281db Mon Sep 17 00:00:00 2001 From: syamadanisyah Date: Tue, 28 Jul 2026 09:03:02 +0700 Subject: [PATCH] keluarkan file copy dari repository --- virtualEnvironment/.gitignore | 3 + virtualEnvironment/evaluasi3_copy.py | 210 ---------------------- virtualEnvironment/preproseccing1_copy.py | 92 ---------- virtualEnvironment/training2_copy.py | 140 --------------- 4 files changed, 3 insertions(+), 442 deletions(-) delete mode 100644 virtualEnvironment/evaluasi3_copy.py delete mode 100644 virtualEnvironment/preproseccing1_copy.py delete mode 100644 virtualEnvironment/training2_copy.py diff --git a/virtualEnvironment/.gitignore b/virtualEnvironment/.gitignore index bb78af6..05f6052 100644 --- a/virtualEnvironment/.gitignore +++ b/virtualEnvironment/.gitignore @@ -13,6 +13,9 @@ __pycache__/ *.pyc *.pyo +# File duplikat/cadangan, cukup disimpan lokal +*_copy.py + # Sistem .env .DS_Store diff --git a/virtualEnvironment/evaluasi3_copy.py b/virtualEnvironment/evaluasi3_copy.py deleted file mode 100644 index 06018a1..0000000 --- a/virtualEnvironment/evaluasi3_copy.py +++ /dev/null @@ -1,210 +0,0 @@ -# 3 evaluasi hasil model -import joblib -import matplotlib.pyplot as plt -import seaborn as sns -from sklearn.metrics import accuracy_score, classification_report, confusion_matrix -import os - -print("šŸ“Š [TAHAP 3] Evaluasi Hasil Model...") - -# --- PENYESUAIAN FOLDER --- -FOLDER_OUTPUT = 'virtualEnvironment/output' -FOLDER_MODELS = 'virtualEnvironment/models' -FOLDER_IMAGES = 'virtualEnvironment/images' - -# 0. CEK KEAMANAN -file_xtest = f'{FOLDER_OUTPUT}/X_test.pkl' -file_svm = f'{FOLDER_MODELS}/model_svm.pkl' - -if not os.path.exists(file_xtest): - raise FileNotFoundError(f"āŒ File '{file_xtest}' tidak ditemukan! Pastikan Tahap 1 sudah dijalankan.") -if not os.path.exists(file_svm): - raise FileNotFoundError(f"āŒ File '{file_svm}' tidak ditemukan! Pastikan Tahap 2 sudah selesai 100%.") - -# Bikin folder images otomatis di dalam virtualEnvironment -os.makedirs(FOLDER_IMAGES, exist_ok=True) - -# 1. Ambil Data Uji -print(" - Memuat data uji...") -X_test = joblib.load(file_xtest) -y_test = joblib.load(f'{FOLDER_OUTPUT}/y_test.pkl') - -# 2. Daftar Model -print(" - Memuat model-model AI...") -daftar_model = { - "SVM": joblib.load(file_svm), - "KNN": joblib.load(f'{FOLDER_MODELS}/model_knn.pkl'), - "Ensemble": joblib.load(f'{FOLDER_MODELS}/model_ensemble.pkl') -} - -# 3. Loop Evaluasi -for nama, model in daftar_model.items(): - print(f"\n==========================================") - print(f"--- Evaluasi Model: {nama} ---") - print(f"==========================================") - - # Lakukan Prediksi - y_pred = model.predict(X_test) - - # Hitung Akurasi - acc = accuracy_score(y_test, y_pred) - print(f"šŸŽÆ Akurasi {nama}: {acc*100:.2f}%\n") - - # Laporan Lengkap (Precision, Recall, F1-Score) - print("šŸ“‹ Laporan Klasifikasi:") - print(classification_report(y_test, y_pred)) - - # Bikin Grafik Confusion Matrix - cm = confusion_matrix(y_test, y_pred) - plt.figure(figsize=(7, 5)) - sns.heatmap(cm, annot=True, fmt='d', cmap='Blues', - annot_kws={"size": 14}) # Angka di dalam kotak diperbesar - - # Hiasan Grafik (Lebih rapi untuk masuk ke buku Skripsi) - plt.title(f'Confusion Matrix - {nama}\n(Akurasi: {acc*100:.2f}%)', fontsize=14, fontweight='bold', pad=15) - plt.xlabel('Prediksi Mesin', fontsize=12, fontweight='bold') - plt.ylabel('Label Asli', fontsize=12, fontweight='bold') - - # Tambahan Keterangan Sumbu X dan Y biar dosen mudah baca - plt.xticks(ticks=[0.5, 1.5, 2.5], labels=['0 (Netral)', '1 (rasional negatif)', '2 (cacimaki/intoleransi)']) - plt.yticks(ticks=[0.5, 1.5, 2.5], labels=['0 (Netral)', '1 (rasional negatif)', '2 (cacimaki/intoleransi)'], rotation=0) - - # Simpan Gambar dengan resolusi tinggi (dpi=300) - nama_file = f'{FOLDER_IMAGES}/cm_{nama}.png' - plt.savefig(nama_file, bbox_inches='tight', dpi=300) - print(f"šŸ–¼ļø Grafik Confusion Matrix tersimpan: {nama_file}") - - # Tutup plot supaya tidak numpuk di memori - plt.close() - -print("\nšŸŽ‰ SEMUA TAHAPAN SELESAI!") -print(f"Cek folder '{FOLDER_IMAGES}' untuk melihat gambar Confusion Matrix-nya ya.") - -# 3 evaluasi hasil model -import joblib -import matplotlib.pyplot as plt -import seaborn as sns -from sklearn.metrics import accuracy_score, classification_report, confusion_matrix -import os - -print("šŸ“Š [TAHAP 3] Evaluasi Hasil Model...") - -# --- PENYESUAIAN FOLDER --- -FOLDER_OUTPUT = 'virtualEnvironment/output' -FOLDER_MODELS = 'virtualEnvironment/models' -FOLDER_IMAGES = 'virtualEnvironment/images' - -# 0. CEK KEAMANAN -file_xtest = f'{FOLDER_OUTPUT}/X_test.pkl' -file_svm = f'{FOLDER_MODELS}/model_svm.pkl' - -if not os.path.exists(file_xtest): - raise FileNotFoundError(f"āŒ File '{file_xtest}' tidak ditemukan! Pastikan Tahap 1 sudah dijalankan.") -if not os.path.exists(file_svm): - raise FileNotFoundError(f"āŒ File '{file_svm}' tidak ditemukan! Pastikan Tahap 2 sudah selesai 100%.") - -# Bikin folder images otomatis di dalam virtualEnvironment -os.makedirs(FOLDER_IMAGES, exist_ok=True) - -# 1. Ambil Data Uji -print(" - Memuat data uji...") -X_test = joblib.load(file_xtest) -y_test = joblib.load(f'{FOLDER_OUTPUT}/y_test.pkl') - -# 2. Daftar Model -print(" - Memuat model-model AI...") -daftar_model = { - "SVM": joblib.load(file_svm), - "KNN": joblib.load(f'{FOLDER_MODELS}/model_knn.pkl'), - "Ensemble": joblib.load(f'{FOLDER_MODELS}/model_ensemble.pkl') -} - -# 3. Loop Evaluasi -for nama, model in daftar_model.items(): - print(f"\n==========================================") - print(f"--- Evaluasi Model: {nama} ---") - print(f"==========================================") - - # Lakukan Prediksi - y_pred = model.predict(X_test) - - # Hitung Akurasi - acc = accuracy_score(y_test, y_pred) - print(f"šŸŽÆ Akurasi {nama}: {acc*100:.2f}%\n") - - # Laporan Lengkap (Precision, Recall, F1-Score) - print("šŸ“‹ Laporan Klasifikasi:") - print(classification_report(y_test, y_pred)) - - # Bikin Grafik Confusion Matrix - cm = confusion_matrix(y_test, y_pred) - plt.figure(figsize=(7, 5)) - sns.heatmap(cm, annot=True, fmt='d', cmap='Blues', - annot_kws={"size": 14}) # Angka di dalam kotak diperbesar - - # Hiasan Grafik (Lebih rapi untuk masuk ke buku Skripsi) - plt.title(f'Confusion Matrix - {nama}\n(Akurasi: {acc*100:.2f}%)', fontsize=14, fontweight='bold', pad=15) - plt.xlabel('Prediksi Mesin', fontsize=12, fontweight='bold') - plt.ylabel('Label Asli', fontsize=12, fontweight='bold') - - # Tambahan Keterangan Sumbu X dan Y biar dosen mudah baca - plt.xticks(ticks=[0.5, 1.5, 2.5], labels=['0 (Netral)', '1 (rasional negatif)', '2 (cacimaki/intoleransi)']) - plt.yticks(ticks=[0.5, 1.5, 2.5], labels=['0 (Netral)', '1 (rasional negatif)', '2 (cacimaki/intoleransi)'], rotation=0) - - # Simpan Gambar dengan resolusi tinggi (dpi=300) - nama_file = f'{FOLDER_IMAGES}/cm_{nama}.png' - plt.savefig(nama_file, bbox_inches='tight', dpi=300) - print(f"šŸ–¼ļø Grafik Confusion Matrix tersimpan: {nama_file}") - - # Tutup plot supaya tidak numpuk di memori - plt.close() - -print("\nšŸŽ‰ SEMUA TAHAPAN SELESAI!") -print(f"Cek folder '{FOLDER_IMAGES}' untuk melihat gambar Confusion Matrix-nya ya.") - -# ============================================ -# TAMBAHAN: Ekstraksi Pola Kesalahan SVM -# ============================================ -print("\n" + "="*60) -print("šŸ“‹ EKSTRAKSI POLA KESALAHAN KLASIFIKASI (SVM)") -print("="*60) - -import pandas as pd -import numpy as np -from sklearn.model_selection import train_test_split - -# Load ulang data asli untuk dapat teks tweet -FILE_DATA = r'D:\project skripsi machine learning intoleransi\virtualEnvironment\dataset\dataYangDiPakai\data_label_3_kategori_v2 - Copy.csv' -df_asli = pd.read_csv(FILE_DATA, sep=';') -df_asli = df_asli.dropna(subset=['clean_text', 'label']).reset_index(drop=True) - -# Replikasi split yang sama dengan Tahap 1 (random_state=42) -indeks_semua = np.arange(len(df_asli)) -_, indeks_test = train_test_split(indeks_semua, test_size=0.2, random_state=42) - -# Prediksi pakai SVM -y_pred_svm = daftar_model['SVM'].predict(X_test) -y_test_arr = np.array(y_test) - -# Filter yang salah -salah_mask = y_pred_svm != y_test_arr -indeks_salah = indeks_test[salah_mask] - -# Bikin dataframe kesalahan -label_map = {0: 'Netral', 1: 'Rasional Negatif', 2: 'Cacimaki/Intoleransi'} -df_salah = df_asli.loc[indeks_salah].copy() -df_salah['label_asli'] = [label_map[x] for x in y_test_arr[salah_mask]] -df_salah['label_prediksi'] = [label_map[x] for x in y_pred_svm[salah_mask]] -df_salah['pola_kesalahan'] = df_salah['label_asli'] + ' ā†’ ' + df_salah['label_prediksi'] - -# Simpan ke CSV -nama_file_salah = f'{FOLDER_OUTPUT}/kesalahan_svm.csv' -df_salah[['clean_text', 'label_asli', 'label_prediksi', 'pola_kesalahan']].to_csv( - nama_file_salah, index=False, sep=';' -) - -# Statistik pola kesalahan -print(f"\nšŸ“Š Total kesalahan SVM: {len(df_salah)} dari {len(y_test_arr)} data uji") -print(f"\nšŸ“Š Distribusi Pola Kesalahan:") -print(df_salah['pola_kesalahan'].value_counts().to_string()) -print(f"\nšŸ’¾ Detail tersimpan di: {nama_file_salah}") \ No newline at end of file diff --git a/virtualEnvironment/preproseccing1_copy.py b/virtualEnvironment/preproseccing1_copy.py deleted file mode 100644 index 061e94b..0000000 --- a/virtualEnvironment/preproseccing1_copy.py +++ /dev/null @@ -1,92 +0,0 @@ -# 1 extraction features TF-IDF (VERSI MODIFIKASI - STRATIFIED + BIGRAM) -import pandas as pd -import joblib -import os -from sklearn.feature_extraction.text import TfidfVectorizer -from sklearn.model_selection import train_test_split - -print("šŸ”„ [TAHAP 1] Memulai Preprocessing & TF-IDF...") - -# --- CONFIG --- -FILE_DATA = r'D:\project skripsi machine learning intoleransi\virtualEnvironment\dataset\dataYangDiPakai\data_label_3_kategori_v2 - Copy.csv' - -FOLDER_OUTPUT = 'virtualEnvironment/output' -FOLDER_MODELS = 'virtualEnvironment/models' - -# 0. CEK KEAMANAN FILE -if not os.path.exists(FILE_DATA): - raise FileNotFoundError(f"āŒ File tidak ditemukan di jalur:\n{FILE_DATA}") - -os.makedirs(FOLDER_OUTPUT, exist_ok=True) -os.makedirs(FOLDER_MODELS, exist_ok=True) - -# 1. LOAD DATA -print(" - Membaca dataset...") -df = pd.read_csv(FILE_DATA, sep=';') - -if 'clean_text' not in df.columns or 'label' not in df.columns: - print(f"Daftar kolom: {df.columns.tolist()}") - raise KeyError("āŒ Kolom 'clean_text' atau 'label' tidak ada!") - -df = df.dropna(subset=['clean_text', 'label']) -print(f" - Total data bersih: {len(df)} baris") - -# 2. TF-IDF (MODIFIKASI: Tambah bigram, min_df, max_df) -print(" - Melakukan ekstraksi fitur TF-IDF (Unigram + Bigram)...") -vectorizer = TfidfVectorizer( - max_features=10000, # naik dari 5000 - ngram_range=(1, 2), # tambah bigram - min_df=2, # buang kata yang muncul cuma 1x - max_df=0.95 # buang kata yang muncul di >95% dokumen -) -X = vectorizer.fit_transform(df['clean_text'].astype(str)) -y = df['label'].astype(int) - -print(f" - Jumlah fitur TF-IDF aktual: {X.shape[1]}") - -# 3. SIMPAN VECTORIZER -print(f" - Menyimpan vectorizer ke '{FOLDER_MODELS}'...") -joblib.dump(vectorizer, f'{FOLDER_MODELS}/vectorizer_tfidf.pkl') - -# 4. SPLIT DATA dengan STRATIFIED (80% Latih, 20% Uji) -print(" - Memecah data dengan Stratified Split (menjaga distribusi label)...") -X_train, X_test, y_train, y_test = train_test_split( - X, y, - test_size=0.2, - random_state=42, - stratify=y # ā† PERUBAHAN UTAMA: stratify -) - -# 4.1 TAMPILKAN HASIL DISTRIBUSI LABEL -print("\n" + "="*55) -print("šŸ“Š HASIL STRATIFIED SPLIT") -print("="*55) -print(f"\nšŸ“ˆ Total Data Awal : {len(y)} baris") -print(f"šŸ“ˆ Total Data Latih : {len(y_train)} baris ({len(y_train)/len(y)*100:.1f}%)") -print(f"šŸ“ˆ Total Data Uji : {len(y_test)} baris ({len(y_test)/len(y)*100:.1f}%)") - -print(f"\nšŸ“Š Distribusi Label Dataset Awal:") -for label, jumlah in y.value_counts().sort_index().items(): - persen = jumlah / len(y) * 100 - print(f" - Label {label}: {jumlah} data ({persen:.2f}%)") - -print(f"\nšŸ“Š Distribusi Label Data Latih:") -for label, jumlah in y_train.value_counts().sort_index().items(): - persen = jumlah / len(y_train) * 100 - print(f" - Label {label}: {jumlah} data ({persen:.2f}%)") - -print(f"\nšŸ“Š Distribusi Label Data Uji:") -for label, jumlah in y_test.value_counts().sort_index().items(): - persen = jumlah / len(y_test) * 100 - print(f" - Label {label}: {jumlah} data ({persen:.2f}%)") - -print("="*55 + "\n") - -# 5. SIMPAN DATA MATANG -print(f" - Menyimpan data matang ke '{FOLDER_OUTPUT}'...") -joblib.dump(X_train, f'{FOLDER_OUTPUT}/X_train.pkl') -joblib.dump(X_test, f'{FOLDER_OUTPUT}/X_test.pkl') -joblib.dump(y_train, f'{FOLDER_OUTPUT}/y_train.pkl') -joblib.dump(y_test, f'{FOLDER_OUTPUT}/y_test.pkl') - -print("āœ… SELESAI TAHAP 1. Lanjut jalankan 'training2.py'") \ No newline at end of file diff --git a/virtualEnvironment/training2_copy.py b/virtualEnvironment/training2_copy.py deleted file mode 100644 index b6af705..0000000 --- a/virtualEnvironment/training2_copy.py +++ /dev/null @@ -1,140 +0,0 @@ -# 2 pelatihan model SVM, KNN dan ensemble -import joblib -import pandas as pd -import os -from sklearn.svm import SVC -from sklearn.neighbors import KNeighborsClassifier -from sklearn.ensemble import VotingClassifier -from sklearn.model_selection import GridSearchCV, cross_val_score - -print("šŸ‹ļø [TAHAP 2] Training: DATA ASLI (Mode TURBO Aktif šŸš€)...") - -# --- PENYESUAIAN FOLDER --- -FOLDER_OUTPUT = 'virtualEnvironment/output' -FOLDER_MODELS = 'virtualEnvironment/models' - -# 0. CEK KEAMANAN: Pastikan folder dan file Tahap 1 sudah ada -file_xtrain = f'{FOLDER_OUTPUT}/X_train.pkl' -if not os.path.exists(file_xtrain): - raise FileNotFoundError(f"āŒ File '{file_xtrain}' tidak ditemukan! Pastikan kamu sudah menjalankan '1_preprocessing.py' terlebih dahulu.") - -# Jaga-jaga kalau folder models belum ada, otomatis dibikin -os.makedirs(FOLDER_MODELS, exist_ok=True) - -# 1. AMBIL DATA DARI TAHAP 1 -print(" - Memuat data latih...") -X_train = joblib.load(f'{FOLDER_OUTPUT}/X_train.pkl') -y_train = joblib.load(f'{FOLDER_OUTPUT}/y_train.pkl') - -print(f" - Jumlah Data Latih Asli: {len(y_train)} baris") -print(f" - Komposisi Label: {y_train.value_counts().to_dict()}") - -# --------------------------------------------------------- -# 2. LATIH SVM (MODEL UTAMA) -# --------------------------------------------------------- -print("\nšŸš€ Melatih SVM (Mencari Settingan Terbaik)...") -print(" (Menggunakan seluruh inti CPU laptop...)") - -param_svm = { - 'C': [0.01, 0.1, 1, 10, 100], - 'kernel': ['linear'], - 'gamma': ['scale'] -} - -svm_grid = GridSearchCV( - SVC(probability=True, random_state=42), - param_svm, - cv=5, - scoring='f1_macro', - verbose=1, - n_jobs=-1 - ) - -svm_grid.fit(X_train, y_train) - -best_svm = svm_grid.best_estimator_ -joblib.dump(best_svm, f'{FOLDER_MODELS}/model_svm.pkl') - -# ā­ TAMBAHAN: Print akurasi validasi & parameter terbaik SVM -svm_acc_val = svm_grid.best_score_ * 100 -print(f" āœ… SVM Selesai (F1-Macro Validasi: {svm_acc_val:.2f}%)") -print(f" šŸ“Œ Parameter Terbaik SVM: {svm_grid.best_params_}") - -# --------------------------------------------------------- -# 3. LATIH KNN (METRIC COSINE) -# --------------------------------------------------------- -print("\nšŸš€ Melatih KNN (Wajib Cosine)...") - -param_knn = { - 'n_neighbors': [3, 5, 7, 9, 11, 15, 21, 25], - 'metric': ['cosine'], - 'weights': ['uniform', 'distance'] -} - -knn_grid = GridSearchCV( - KNeighborsClassifier(), - param_knn, - cv=5, - scoring='f1_macro', - verbose=1, - n_jobs=-1 - ) -knn_grid.fit(X_train, y_train) - -best_knn = knn_grid.best_estimator_ -joblib.dump(best_knn, f'{FOLDER_MODELS}/model_knn.pkl') - -# ā­ TAMBAHAN: Print akurasi validasi & parameter terbaik KNN -knn_acc_val = knn_grid.best_score_ * 100 -print(f" āœ… KNN Selesai (Best K: {knn_grid.best_params_['n_neighbors']})") -print(f" šŸ“Œ Parameter Terbaik KNN: {knn_grid.best_params_}") -print(f" šŸ“Œ F1-Macro Validasi KNN: {knn_acc_val:.2f}%") - -# --------------------------------------------------------- -# 4. LATIH ENSEMBLE (SVM + KNN) -# --------------------------------------------------------- -print("\nšŸš€ Melatih ENSEMBLE (Voting SVM + KNN)...") - -# Gabungkan dua model terbaik -ensemble_model = VotingClassifier( - estimators=[ - ('svm', best_svm), - ('knn', best_knn) - ], - voting='soft', - weights=[2, 1] # SVM kita beri bobot suara lebih tinggi -) - -ensemble_model.fit(X_train, y_train) -joblib.dump(ensemble_model, f'{FOLDER_MODELS}/model_ensemble.pkl') -print(" āœ… Ensemble Selesai.") - -# ā­ TAMBAHAN: Hitung akurasi validasi Ensemble pakai cross_val_score -print(" šŸ“Œ Menghitung Akurasi Validasi Ensemble (3-fold CV)...") -print(" (Sabar ya, ini agak lama karena ensemble = SVM + KNN x 3 fold)") -ensemble_scores = cross_val_score(ensemble_model, X_train, y_train, cv=3, n_jobs=-1) -ensemble_acc_val = ensemble_scores.mean() * 100 -print(f" šŸ“Œ Akurasi Validasi Ensemble: {ensemble_acc_val:.2f}%") - -# --------------------------------------------------------- -# 5. RINGKASAN AKHIR -# --------------------------------------------------------- -print("\n" + "="*60) -print("šŸ“Š RINGKASAN HASIL TRAINING") -print("="*60) -print(f"\nšŸ”¹ SVM") -print(f" Parameter : {svm_grid.best_params_}") -print(f" Akurasi Validasi : {svm_acc_val:.2f}%") - -print(f"\nšŸ”¹ KNN") -print(f" Parameter : {knn_grid.best_params_}") -print(f" Akurasi Validasi : {knn_acc_val:.2f}%") - -print(f"\nšŸ”¹ Ensemble (SVM + KNN)") -print(f" Voting : soft, weights=[2, 1]") -print(f" Akurasi Validasi : {ensemble_acc_val:.2f}%") - -print("\n" + "="*60) -print("šŸŽ‰ TRAINING DATA MURNI SELESAI!") -print("šŸ‘‰ Silakan jalankan '3_evaluasi.py' untuk melihat hasil akhirnya.") -print("="*60) \ No newline at end of file