chrom-qsar 0.1.0__tar.gz

chrom_qsar-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Your Name / Your Lab
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

chrom_qsar-0.1.0/PKG-INFO

@@ -0,0 +1,30 @@
+Metadata-Version: 2.4
+Name: chrom-qsar
+Version: 0.1.0
+Summary: A streamlined machine learning pipeline for QSAR and regression tasks with SHAP interpretability.
+Author-email: Your Name <your.email@university.edu>
+License: MIT
+Keywords: machine-learning,qsar,shap,regression,optuna
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pandas>=1.3.0
+Requires-Dist: numpy>=1.21.0
+Requires-Dist: scikit-learn>=1.0.0
+Requires-Dist: xgboost>=1.5.0
+Requires-Dist: lightgbm>=3.3.0
+Requires-Dist: optuna>=3.0.0
+Requires-Dist: shap>=0.41.0
+Requires-Dist: matplotlib>=3.4.0
+Requires-Dist: seaborn>=0.11.0
+Requires-Dist: joblib>=1.1.0
+Requires-Dist: openpyxl>=3.0.0
+Dynamic: license-file

chrom_qsar-0.1.0/chrom_qsar/__init__.py

@@ -0,0 +1,8 @@
+# chrom_qsar/__init__.py
+
+from .pipeline import QSARModelTrainer, QSARModelAnalyzer
+
+__version__ = "0.1.0"
+__author__ = "Liu Xinye"
+
+__all__ = ["QSARModelTrainer", "QSARModelAnalyzer", "__version__"]

chrom_qsar-0.1.0/chrom_qsar/data.py

@@ -0,0 +1,24 @@
+import os
+import pandas as pd
+
+def load_and_clean_data(filepath: str):
+    if not os.path.exists(filepath):
+        parent_path = os.path.join('..', filepath)
+        if os.path.exists(parent_path):
+            filepath = parent_path
+        else:
+            raise FileNotFoundError(f"找不到数据文件: {filepath}")
+            
+    df = pd.read_excel(filepath)
+    y_raw = df.iloc[:, 0]
+    X_raw = df.iloc[:, 1:]
+
+    y = pd.to_numeric(y_raw, errors='coerce')
+    X = X_raw.apply(pd.to_numeric, errors='coerce')
+    clean_df = pd.concat([y.rename('target'), X], axis=1).dropna()
+    
+    X_clean = clean_df.drop(columns=['target'])
+    y_clean = clean_df['target']
+    
+    print(f"数据加载完成: 原始样本 {len(df)} → 有效样本 {len(X_clean)} | 特征维度: {X_clean.shape[1]}")
+    return X_clean, y_clean

chrom_qsar-0.1.0/chrom_qsar/interpreter.py

@@ -0,0 +1,57 @@
+import os
+import shap
+import numpy as np
+import matplotlib.pyplot as plt
+from sklearn.pipeline import Pipeline
+
+def run_comprehensive_shap_analysis(model, X_test, feature_names, model_name, out_dir):
+    print(f"  ├─ 启动 SHAP 分析 ({model_name})...")
+    is_pipeline = isinstance(model, Pipeline)
+
+    try:
+        if is_pipeline:
+            n_feat = X_test.shape[1]
+            min_evals = min(2 * n_feat + 1, 1000)
+            explainer = shap.PermutationExplainer(model.predict, X_test, max_evals=min_evals)
+        else:
+            explainer = shap.Explainer(model, X_test)
+    except Exception:
+        n_feat = X_test.shape[1]
+        min_evals = min(2 * n_feat + 1, 1000)
+        explainer = shap.PermutationExplainer(model.predict, X_test, max_evals=min_evals)
+
+    shap_output = explainer(X_test)
+    shap_arr = shap_output.values if hasattr(shap_output, 'values') else np.array(shap_output)
+    if shap_arr.ndim == 1:
+        shap_arr = shap_arr.reshape(1, -1)
+    
+    mean_abs_shap = np.mean(np.abs(shap_arr), axis=0)
+    top_indices = np.argsort(mean_abs_shap)[::-1][:15]
+    top_feats = [feature_names[i] for i in top_indices]
+    
+    try:
+        plt.figure(figsize=(12, 8))
+        if hasattr(shap.plots, 'beeswarm'):
+            shap.plots.beeswarm(shap_output, max_display=15, show=False)
+        else:
+            shap.summary_plot(shap_output, X_test, feature_names=feature_names, max_display=15, show=False)
+        plt.title(model_name, fontsize=16, fontweight='bold', pad=10)
+        plt.tight_layout()
+        plt.savefig(os.path.join(out_dir, f'shap_summary_{model_name}.png'), dpi=300, bbox_inches='tight')
+        plt.close()
+    except Exception as e:
+        print(f"  └─ Summary Plot 失败: {e}")
+
+    plt.figure(figsize=(10, 8))
+    plt.barh(range(len(top_feats)), mean_abs_shap[top_indices][::-1], color='#4C72B0', edgecolor='k', alpha=0.8)
+    plt.yticks(range(len(top_feats)), top_feats[::-1], fontsize=12)
+    plt.xlabel('Mean |SHAP Value|', fontsize=14, fontweight='bold')
+    plt.title(model_name, fontsize=16, fontweight='bold', pad=10)
+    plt.grid(axis='x', linestyle='--', alpha=0.4)
+    plt.tight_layout()
+    plt.savefig(os.path.join(out_dir, f'shap_importance_{model_name}.png'), dpi=300, bbox_inches='tight')
+    plt.close()
+    
+    import pandas as pd
+    pd.DataFrame(shap_arr, columns=feature_names).to_csv(os.path.join(out_dir, f'shap_values_{model_name}.csv'), index=False)
+    print(f"  └─ SHAP 分析完成，结果已保存至 {out_dir}")

chrom_qsar-0.1.0/chrom_qsar/models.py

@@ -0,0 +1,37 @@
+from sklearn.linear_model import LinearRegression, Ridge, Lasso, ElasticNet
+from sklearn.cross_decomposition import PLSRegression
+from sklearn.svm import SVR
+from sklearn.tree import DecisionTreeRegressor
+from sklearn.ensemble import RandomForestRegressor, AdaBoostRegressor, ExtraTreesRegressor, HistGradientBoostingRegressor
+import xgboost as xgb
+import lightgbm as lgb
+
+def get_model_configs():
+    def pls_space(trial): return {'n_components': trial.suggest_int('n_components', 2, 50)}
+    def ridge_space(trial): return {'alpha': trial.suggest_float('alpha', 1e-3, 1e3, log=True)}
+    def lasso_space(trial): return {'alpha': trial.suggest_float('alpha', 1e-3, 1e3, log=True)}
+    def enet_space(trial): return {'alpha': trial.suggest_float('alpha', 1e-3, 1e3, log=True), 'l1_ratio': trial.suggest_float('l1_ratio', 0.0, 1.0)}
+    def svr_space(trial): return {'C': trial.suggest_float('C', 0.1, 100.0, log=True), 'epsilon': trial.suggest_float('epsilon', 0.01, 0.5, log=True), 'kernel': trial.suggest_categorical('kernel', ['rbf', 'linear'])}
+    def dt_space(trial): return {'max_depth': trial.suggest_int('max_depth', 3, 20), 'min_samples_split': trial.suggest_int('min_samples_split', 2, 10), 'min_samples_leaf': trial.suggest_int('min_samples_leaf', 1, 8)}
+    def rf_space(trial): return {'n_estimators': trial.suggest_int('n_estimators', 200, 800, step=50), 'max_depth': trial.suggest_int('max_depth', 5, 30), 'min_samples_split': trial.suggest_int('min_samples_split', 2, 10), 'min_samples_leaf': trial.suggest_int('min_samples_leaf', 1, 8), 'max_features': trial.suggest_categorical('max_features', ['sqrt', 'log2', None])}
+    def xgb_space(trial): return {'n_estimators': trial.suggest_int('n_estimators', 200, 1000, step=50), 'max_depth': trial.suggest_int('max_depth', 3, 12), 'learning_rate': trial.suggest_float('learning_rate', 1e-3, 0.3, log=True), 'subsample': trial.suggest_float('subsample', 0.6, 1.0), 'colsample_bytree': trial.suggest_float('colsample_bytree', 0.6, 1.0), 'reg_alpha': trial.suggest_float('reg_alpha', 1e-8, 10.0, log=True), 'reg_lambda': trial.suggest_float('reg_lambda', 1e-8, 10.0, log=True)}
+    def lgb_space(trial): return {'n_estimators': trial.suggest_int('n_estimators', 200, 1000, step=50), 'max_depth': trial.suggest_int('max_depth', 3, 12), 'learning_rate': trial.suggest_float('learning_rate', 1e-3, 0.3, log=True), 'num_leaves': trial.suggest_int('num_leaves', 20, 100), 'subsample': trial.suggest_float('subsample', 0.6, 1.0), 'colsample_bytree': trial.suggest_float('colsample_bytree', 0.6, 1.0), 'reg_alpha': trial.suggest_float('reg_alpha', 1e-8, 10.0, log=True), 'reg_lambda': trial.suggest_float('reg_lambda', 1e-8, 10.0, log=True)}
+    def ada_space(trial): return {'n_estimators': trial.suggest_int('n_estimators', 50, 500, step=25), 'learning_rate': trial.suggest_float('learning_rate', 0.01, 1.0, log=True), 'loss': trial.suggest_categorical('loss', ['linear', 'square', 'exponential'])}
+    def et_space(trial): return {'n_estimators': trial.suggest_int('n_estimators', 200, 800, step=50), 'max_depth': trial.suggest_int('max_depth', 5, 30), 'min_samples_split': trial.suggest_int('min_samples_split', 2, 10), 'min_samples_leaf': trial.suggest_int('min_samples_leaf', 1, 8), 'max_features': trial.suggest_categorical('max_features', ['sqrt', 'log2', None])}
+    def hgb_space(trial): return {'max_iter': trial.suggest_int('max_iter', 200, 1000, step=50), 'max_depth': trial.suggest_int('max_depth', 3, 12), 'learning_rate': trial.suggest_float('learning_rate', 1e-3, 0.3, log=True), 'min_samples_leaf': trial.suggest_int('min_samples_leaf', 10, 50), 'l2_regularization': trial.suggest_float('l2_regularization', 1e-4, 10.0, log=True)}
+
+    return {
+        'PLSR': {'model': PLSRegression, 'space': pls_space},
+        'LinearRegression': {'model': LinearRegression, 'space': None},
+        'Ridge': {'model': Ridge, 'space': ridge_space},
+        'Lasso': {'model': Lasso, 'space': lasso_space},
+        'ElasticNet': {'model': ElasticNet, 'space': enet_space},
+        'SVR': {'model': SVR, 'space': svr_space},
+        'DecisionTree': {'model': DecisionTreeRegressor, 'space': dt_space},
+        'RandomForest': {'model': RandomForestRegressor, 'space': rf_space},
+        'XGBoost': {'model': xgb.XGBRegressor, 'space': xgb_space},
+        'LightGBM': {'model': lgb.LGBMRegressor, 'space': lgb_space},
+        'AdaBoost': {'model': AdaBoostRegressor, 'space': ada_space},
+        'ExtraTrees': {'model': ExtraTreesRegressor, 'space': et_space},
+        'HistGradientBoosting': {'model': HistGradientBoostingRegressor, 'space': hgb_space}
+    }

chrom_qsar-0.1.0/chrom_qsar/pipeline.py

@@ -0,0 +1,137 @@
+import os
+import glob
+import joblib
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+from sklearn.model_selection import train_test_split
+from sklearn.metrics import r2_score, mean_squared_error, mean_absolute_error
+from .utils import setup_environment, set_seed
+from .data import load_and_clean_data
+from .models import get_model_configs
+from .trainer import optimize_model
+from .interpreter import run_comprehensive_shap_analysis
+
+class QSARModelTrainer:
+    def __init__(self, data_path: str, out_dir: str = 'training_results', n_trials: int = 100):
+        setup_environment()
+        set_seed(42)
+        self.data_path = data_path
+        self.out_dir = out_dir
+        self.n_trials = n_trials
+        os.makedirs(out_dir, exist_ok=True)
+        
+    def run(self):
+        print("="*60 + "\n 开始自动化建模与优化流程\n" + "="*60)
+        X, y = load_and_clean_data(self.data_path)
+        X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+        configs = get_model_configs()
+        results = []
+        
+        for name, cfg in configs.items():
+            print(f"\n[ {name} ] 处理中...")
+            if cfg['space'] is not None:
+                model, best_params = optimize_model(
+                    cfg['model'], cfg['space'], X_train, y_train, 
+                    n_trials=self.n_trials, is_svr=(name == 'SVR')
+                )
+                print(f"  ├─ 最优参数: {best_params}")
+            else:
+                model = cfg['model']()
+                
+            model.fit(X_train, y_train)
+            y_pred = model.predict(X_test)
+            
+            r2 = r2_score(y_test, y_pred)
+            rmse = np.sqrt(mean_squared_error(y_test, y_pred))
+            mae = mean_absolute_error(y_test, y_pred)
+            print(f"  ├─ 测试集: R²={r2:.4f} | RMSE={rmse:.4f} | MAE={mae:.4f}")
+            
+            results.append({'Model': name, 'R2': r2, 'RMSE': rmse, 'MAE': mae})
+            
+            # 保存模型和特征
+            joblib.dump(model, os.path.join(self.out_dir, f'model_{name}.pkl'))
+            joblib.dump(X.columns.tolist(), os.path.join(self.out_dir, f'features_{name}.pkl'))
+            
+            # SHAP 分析
+            run_comprehensive_shap_analysis(model, X_test, X.columns.tolist(), name, self.out_dir)
+            
+        # 汇总结果
+        res_df = pd.DataFrame(results).sort_values('R2', ascending=False)
+        res_df.to_csv(os.path.join(self.out_dir, 'model_comparison.csv'), index=False)
+        print("\n训练流程结束，结果已保存至:", self.out_dir)
+        return res_df
+
+
+class QSARModelAnalyzer:
+    def __init__(self, data_path: str, model_dir: str = '.', out_dir: str = 'batch_analysis_results'):
+        setup_environment()
+        set_seed(42)
+        self.data_path = data_path
+        self.model_dir = model_dir
+        self.out_dir = out_dir
+        os.makedirs(out_dir, exist_ok=True)
+
+    def run(self):
+        print("="*60 + f"\n 开始批量模型分析 (目录: {self.model_dir})\n" + "="*60)
+        X, y = load_and_clean_data(self.data_path)
+        X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+        
+        model_files = sorted(glob.glob(os.path.join(self.model_dir, 'model_*.pkl')))
+        if not model_files:
+            print("未找到任何 model_*.pkl 文件！")
+            return
+            
+        results = []
+        for mfile in model_files:
+            name = os.path.basename(mfile).replace('model_', '').replace('.pkl', '')
+            ffile = os.path.join(self.model_dir, f'features_{name}.pkl')
+            
+            if not os.path.exists(ffile):
+                print(f"跳过 [{name}]: 缺少特征文件")
+                continue
+                
+            print(f"\n[ {name} ] 分析中...")
+            model = joblib.load(mfile)
+            feat_names = joblib.load(ffile)
+            X_test_aligned = X_test[feat_names]
+            
+            # 预测
+            y_pred = model.predict(X_test_aligned)
+            r2 = r2_score(y_test, y_pred)
+            rmse = np.sqrt(mean_squared_error(y_test, y_pred))
+            mae = mean_absolute_error(y_test, y_pred)
+            results.append({'Model': name, 'R2': r2, 'RMSE': rmse, 'MAE': mae})
+            
+            # 1. True vs Predicted 散点图
+            self._plot_true_vs_pred(model, X_train, X_test_aligned, y_train, y_test, feat_names, name)
+            
+            # 2. SHAP 分析
+            run_comprehensive_shap_analysis(model, X_test_aligned, feat_names, name, self.out_dir)
+            
+        # 汇总
+        res_df = pd.DataFrame(results).sort_values('R2', ascending=False)
+        res_df.to_csv(os.path.join(self.out_dir, 'model_summary_metrics.csv'), index=False)
+        print("\n批量分析结束，结果已保存至:", self.out_dir)
+
+    def _plot_true_vs_pred(self, model, X_train, X_test, y_train, y_test, feat_names, name):
+        y_train_pred = model.predict(X_train[feat_names])
+        y_test_pred = model.predict(X_test)
+        r2_train = r2_score(y_train, y_train_pred)
+        r2_test = r2_score(y_test, y_test_pred)
+        
+        plt.figure(figsize=(8, 8))
+        plt.scatter(y_train, y_train_pred, c='#2E86AB', alpha=0.6, edgecolor='white', s=80, label=f'Train (R²={r2_train:.3f})')
+        plt.scatter(y_test, y_test_pred, c='#E94F37', alpha=0.7, edgecolor='black', s=100, label=f'Test (R²={r2_test:.3f})')
+        
+        lims = [min(y_train.min(), y_test.min()) - 0.5, max(y_train.max(), y_test.max()) + 0.5]
+        plt.plot(lims, lims, 'k--', lw=2.0, zorder=0)
+        
+        plt.xlabel('True Adsorption Capacity', fontsize=14, fontweight='bold')
+        plt.ylabel('Predicted Adsorption Capacity', fontsize=14, fontweight='bold')            
+        plt.title(name, fontsize=16, pad=10, fontweight='bold')          
+        plt.legend(fontsize=12, frameon=True, loc='upper left')
+        plt.grid(axis='both', linestyle=':', alpha=0.4)
+        plt.tight_layout()         
+        plt.savefig(os.path.join(self.out_dir, f'true_pred_{name}.png'), dpi=300, bbox_inches='tight')
+        plt.close()

chrom_qsar-0.1.0/chrom_qsar/trainer.py

@@ -0,0 +1,37 @@
+import optuna
+from sklearn.model_selection import cross_val_score
+from sklearn.pipeline import make_pipeline
+from sklearn.preprocessing import StandardScaler
+
+def get_safe_params(model_class, params: dict) -> dict:
+    safe_params = params.copy()
+    try: model_class(random_state=42); safe_params['random_state'] = 42
+    except TypeError: pass
+    try: model_class(n_jobs=-1); safe_params['n_jobs'] = -1
+    except TypeError: pass
+    return safe_params
+
+def optimize_model(model_class, space_func, X_train, y_train, n_trials: int = 100, is_svr: bool = False):
+    def objective(trial):
+        params = space_func(trial) if space_func else {}
+        safe_params = get_safe_params(model_class, params)
+        
+        if is_svr:
+            model = make_pipeline(StandardScaler(), model_class(**safe_params))
+        else:
+            model = model_class(**safe_params)
+            
+        score = cross_val_score(model, X_train, y_train, cv=10, scoring='neg_root_mean_squared_error', n_jobs=-1).mean()
+        return score
+
+    study = optuna.create_study(
+        direction='maximize',
+        sampler=optuna.samplers.TPESampler(seed=42),
+        pruner=optuna.pruners.MedianPruner(n_startup_trials=5, n_warmup_steps=3)
+    )
+    study.optimize(objective, n_trials=n_trials, show_progress_bar=True)
+    
+    best_params = get_safe_params(model_class, study.best_trial.params)
+    if is_svr:
+        return make_pipeline(StandardScaler(), model_class(**best_params)), study.best_trial.params
+    return model_class(**best_params), study.best_trial.params

chrom_qsar-0.1.0/chrom_qsar/utils.py

@@ -0,0 +1,21 @@
+import warnings
+import numpy as np
+import random
+import matplotlib.pyplot as plt
+import seaborn as sns
+
+def setup_environment():
+    warnings.filterwarnings('ignore')
+    plt.rcParams['font.sans-serif'] = ['SimHei', 'Arial']  
+    plt.rcParams['axes.unicode_minus'] = False
+    plt.rcParams['font.size'] = 12
+    plt.rcParams['axes.labelsize'] = 14
+    plt.rcParams['xtick.labelsize'] = 12
+    plt.rcParams['ytick.labelsize'] = 12
+    plt.rcParams['legend.fontsize'] = 12
+    plt.rcParams['axes.titlesize'] = 16
+    sns.set_style('whitegrid')
+
+def set_seed(seed: int = 42):
+    random.seed(seed)
+    np.random.seed(seed)

chrom_qsar-0.1.0/chrom_qsar.egg-info/PKG-INFO

@@ -0,0 +1,30 @@
+Metadata-Version: 2.4
+Name: chrom-qsar
+Version: 0.1.0
+Summary: A streamlined machine learning pipeline for QSAR and regression tasks with SHAP interpretability.
+Author-email: Your Name <your.email@university.edu>
+License: MIT
+Keywords: machine-learning,qsar,shap,regression,optuna
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pandas>=1.3.0
+Requires-Dist: numpy>=1.21.0
+Requires-Dist: scikit-learn>=1.0.0
+Requires-Dist: xgboost>=1.5.0
+Requires-Dist: lightgbm>=3.3.0
+Requires-Dist: optuna>=3.0.0
+Requires-Dist: shap>=0.41.0
+Requires-Dist: matplotlib>=3.4.0
+Requires-Dist: seaborn>=0.11.0
+Requires-Dist: joblib>=1.1.0
+Requires-Dist: openpyxl>=3.0.0
+Dynamic: license-file

chrom_qsar-0.1.0/chrom_qsar.egg-info/SOURCES.txt

@@ -0,0 +1,14 @@
+LICENSE
+pyproject.toml
+chrom_qsar/__init__.py
+chrom_qsar/data.py
+chrom_qsar/interpreter.py
+chrom_qsar/models.py
+chrom_qsar/pipeline.py
+chrom_qsar/trainer.py
+chrom_qsar/utils.py
+chrom_qsar.egg-info/PKG-INFO
+chrom_qsar.egg-info/SOURCES.txt
+chrom_qsar.egg-info/dependency_links.txt
+chrom_qsar.egg-info/requires.txt
+chrom_qsar.egg-info/top_level.txt

chrom_qsar-0.1.0/chrom_qsar.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

chrom_qsar-0.1.0/chrom_qsar.egg-info/requires.txt

@@ -0,0 +1,11 @@
+pandas>=1.3.0
+numpy>=1.21.0
+scikit-learn>=1.0.0
+xgboost>=1.5.0
+lightgbm>=3.3.0
+optuna>=3.0.0
+shap>=0.41.0
+matplotlib>=3.4.0
+seaborn>=0.11.0
+joblib>=1.1.0
+openpyxl>=3.0.0

chrom_qsar-0.1.0/chrom_qsar.egg-info/top_level.txt

@@ -0,0 +1 @@
+chrom_qsar

chrom_qsar-0.1.0/pyproject.toml

@@ -0,0 +1,38 @@
+[build-system]
+requires = ["setuptools>=61.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "chrom-qsar"          
+version = "0.1.0"                    
+description = "A streamlined machine learning pipeline for QSAR and regression tasks with SHAP interpretability."
+readme = "README.md"                 
+requires-python = ">=3.8"
+license = {text = "MIT"}             
+authors = [
+  {name = "Your Name", email = "your.email@university.edu"}
+]
+keywords = ["machine-learning", "qsar", "shap", "regression", "optuna"]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Science/Research",
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.8",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+]
+dependencies = [
+    "pandas>=1.3.0",
+    "numpy>=1.21.0",
+    "scikit-learn>=1.0.0",
+    "xgboost>=1.5.0",
+    "lightgbm>=3.3.0",
+    "optuna>=3.0.0",
+    "shap>=0.41.0",
+    "matplotlib>=3.4.0",
+    "seaborn>=0.11.0",
+    "joblib>=1.1.0",
+    "openpyxl>=3.0.0"
+]

chrom_qsar-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+