py2ls 0.2.4.8__py3-none-any.whl → 0.2.4.9__py3-none-any.whl

py2ls/ml2ls.py

@@ -582,7 +582,8 @@ def get_features(
     strict: bool = False,
     n_shared: int = 2,  # 只要有两个方法有重合,就纳入common genes
     use_selected_features: bool = True,
-) -> dict:
+    plot_: bool = True,
+    dir_save:str="./") -> dict:
     """
     Master function to perform feature selection and validate models.
     """
@@ -598,11 +599,15 @@ def get_features(
     # fill na
     if fill_missing:
         ips.df_fillna(data=X,method='knn',inplace=True,axis=0)
-
-    # rm missing values
-    X.dropna(inplace=True)
-    y.dropna(inplace=True)
+    if isinstance(y, str) and y in X.columns: 
+        y_col_name=y
+        y=X[y]
+        y=ips.df_encoder(pd.DataFrame(y),method='dummy')
+        X = X.drop(y_col_name,axis=1)
+    else:
+        y=ips.df_encoder(pd.DataFrame(y),method='dummy').values.ravel()
     y = y.loc[X.index]  # Align y with X after dropping rows with missing values in X
+    y = y.ravel() if isinstance(y, np.ndarray) else y.values.ravel()
 
     if X.shape[0] != len(y):
         raise ValueError("X and y must have the same number of samples (rows).")
@@ -894,9 +899,13 @@ def get_features(
         results = {
             "selected_features": features_df,
             "cv_train_scores": cv_train_results_df,
-            "cv_test_scores": rank_models(cv_test_results_df),
+            "cv_test_scores": rank_models(cv_test_results_df,plot_=plot_),
             "common_features": list(common_features),
         }
+        if all([plot_,dir_save]):
+            from datetime import datetime
+            now_ = datetime.now().strftime("%y%m%d_%H%M%S")
+            ips.figsave(dir_save+f"features{now_}.pdf")
     else:
         results = {
             "selected_features": pd.DataFrame(),
@@ -1707,36 +1716,55 @@ def predict(
     smote: bool = False,
     n_jobs:int  = -1,
     plot_: bool = True,
+    dir_save:str="./",
     test_size:float=0.2,# specific only when x_true is None
     cv_folds:int=5,# more cv_folds 得更加稳定,auc可能更低
     cv_level:str="l",#"s":'low',"m":'medium',"l":"high"
     class_weight: str = "balanced",
     verbose:bool=False,
-    dir_save:str="./"
 ) -> pd.DataFrame:
-    """
-    1. 对x_train进行split_train_test,并对其进行validate
-    predict(x_train, y_train)
-    2. 利用x_train, y_train的数据,对x_true的数据进行predict
-    predict(x_train, y_train, x_true)
-    3. 利用x_train, y_train的数据,validate x_true和y_true
-    predict(x_train, y_train, x_true, y_true)
- 
-    Advanced master predictor function with grid search for hyperparameter tuning.
-
-    Parameters:
-    - x_train, y_train: Training dataset.
-    - x_true, y_true: Dataset for validation or prediction (y_true=None for prediction).
-    - common_features (set): Common features to use for validation.
-    - purpose (str): Task type - 'classification' or 'regression'.
-    - models (dict): Dictionary of models and parameters.
-    - metrics (list): Metrics to compute.
-    - random_state (int): Seed for reproducibility.
-    - smote (bool): Use SMOTE for class imbalance (classification only).
-    - class_weight (str): Class weights to handle imbalance.
-
-    Returns:
-    - df_results (pd.DataFrame): DataFrame with performance metrics and hyperparameters.
+    """ 
+        第一种情况是内部拆分，第二种是直接预测，第三种是外部验证。
+        Usage:
+            (1). predict(x_train, y_train,...) 对 x_train 进行拆分训练/测试集，并在测试集上进行验证.
+                predict 函数会根据 test_size 参数，将 x_train 和 y_train 拆分出内部测试集。然后模型会在拆分出的训练集上进行训练，并在测试集上验证效果。
+            (2). predict(x_train, y_train, x_true,...)使用 x_train 和 y_train 训练并对 x_true 进行预测
+                由于传入了 x_true，函数会跳过 x_train 的拆分，直接使用全部的 x_train 和 y_train 进行训练。然后对 x_true 进行预测，但由于没有提供 y_true，
+                因此无法与真实值进行对比。
+            (3). predict(x_train, y_train, x_true, y_true,...)使用 x_train 和 y_train 训练，并验证 x_true 与真实标签 y_true.
+                predict 函数会在 x_train 和 y_train 上进行训练，并将 x_true 作为测试集。由于提供了 y_true，函数可以将预测结果与 y_true 进行对比，从而
+                计算验证指标，完成对 x_true 的真正验证。
+        trains and validates a variety of machine learning models for both classification and regression tasks. 
+        It supports hyperparameter tuning with grid search and includes additional features like cross-validation, 
+        feature scaling, and handling of class imbalance through SMOTE.
+
+        Parameters:
+            - x_train (pd.DataFrame):Training feature data, structured with each row as an observation and each column as a feature.
+            - y_train (pd.Series):Target variable for the training dataset.
+            - x_true (pd.DataFrame, optional):Test feature data. If not provided, the function splits x_train based on test_size.
+            - y_true (pd.Series, optional):Test target values. If not provided, y_train is split into training and testing sets.
+            - common_features (set, optional):Specifies a subset of features common across training and test data.
+            - purpose (str, default = "classification"):Defines whether the task is "classification" or "regression". Determines which 
+                metrics and models are applied.
+            - cls (dict, optional):Dictionary to specify custom classifiers/regressors. Defaults to a set of common models if not provided.
+            - metrics (list, optional):List of evaluation metrics (like accuracy, F1 score) used for model evaluation.
+            - random_state (int, default = 1):Random seed to ensure reproducibility.
+            - smote (bool, default = False):Applies Synthetic Minority Oversampling Technique (SMOTE) to address class imbalance if enabled.
+            - n_jobs (int, default = -1):Number of parallel jobs for computation. Set to -1 to use all available cores.
+            - plot_ (bool, default = True):If True, generates plots of the model evaluation metrics.
+            - test_size (float, default = 0.2):Test data proportion if x_true is not provided.
+            - cv_folds (int, default = 5):Number of cross-validation folds.
+            - cv_level (str, default = "l"):Sets the detail level of cross-validation. "s" for low, "m" for medium, and "l" for high.
+            - class_weight (str, default = "balanced"):Balances class weights in classification tasks.
+            - verbose (bool, default = False):If True, prints detailed output during model training.
+            - dir_save (str, default = "./"):Directory path to save plot outputs and results.
+
+        Key Steps in the Function:
+            Model Initialization: Depending on purpose, initializes either classification or regression models.
+            Feature Selection: Ensures training and test sets have matching feature columns.
+            SMOTE Application: Balances classes if smote is enabled and the task is classification.
+            Cross-Validation and Hyperparameter Tuning: Utilizes GridSearchCV for model tuning based on cv_level.
+            Evaluation and Plotting: Outputs evaluation metrics like AUC, confusion matrices, and optional plotting of performance metrics.
     """
     from tqdm import tqdm
     from sklearn.ensemble import RandomForestClassifier, RandomForestRegressor, ExtraTreesClassifier, ExtraTreesRegressor, BaggingClassifier, BaggingRegressor, AdaBoostClassifier, AdaBoostRegressor
@@ -1858,8 +1886,12 @@ def predict(
             y_true=ips.df_encoder(pd.DataFrame(y_true),method='dummy').values.ravel()
 
     # to convert the 2D to 1D: 2D column-vector format (like [[1], [0], [1], ...]) instead of a 1D array ([1, 0, 1, ...]
-    y_train=y_train.values.ravel() if y_train is not None else None
-    y_true=y_true.values.ravel() if y_true is not None else None
+
+    # y_train=y_train.values.ravel() if y_train is not None else None
+    # y_true=y_true.values.ravel() if y_true is not None else None
+    y_train = y_train.ravel() if isinstance(y_train, np.ndarray) else y_train.values.ravel()
+    y_true = y_true.ravel() if isinstance(y_true, np.ndarray) else y_true.values.ravel()
+
     
     # Ensure common features are selected
     if common_features is not None:
@@ -2440,15 +2472,18 @@ def predict(
         df_results=df_results.loc[df_scores.index]
 
         if plot_:
+            from datetime import datetime
+            now_ = datetime.now().strftime("%y%m%d_%H%M%S")
             nexttile=plot.subplot(figsize=[12, 10])
             plot.heatmap(df_scores, kind="direct",ax=nexttile())
             plot.figsets(xangle=30)
             if dir_save:
-                ips.figsave(dir_save+"scores_sorted_heatmap.pdf")
-            plot.heatmap(df_scores, kind="direct",cluster=True)
-            plot.figsets(xangle=30)
-            if dir_save:
-                ips.figsave(dir_save+"scores_clus.pdf")
+                ips.figsave(dir_save+f"scores_sorted_heatmap{now_}.pdf")
+            if df_scores.shape[0]>1:# draw cluster
+                plot.heatmap(df_scores, kind="direct",cluster=True)
+                plot.figsets(xangle=30)
+                if dir_save:
+                    ips.figsave(dir_save+f"scores_clus{now_}.pdf")
     if all([plot_, y_true is not None, purpose=='classification']):
         try:
             if len(models)>3:
@@ -2456,7 +2491,7 @@ def predict(
             else:
                 plot_validate_features_single(df_results,figsize=(12,4*len(models)))
             if dir_save:
-                ips.figsave(dir_save+"validate_features.pdf")
+                ips.figsave(dir_save+f"validate_features{now_}.pdf")
         except Exception as e:
             print(f"Error: 在画图的过程中出现了问题:{e}")
     return df_results

py2ls/plot.py

@@ -3020,7 +3020,7 @@ def plotxy(
         sns_info = pd.DataFrame(fload(current_directory / 'data' / 'sns_info.json'))
  
     valid_kinds = list(default_settings.keys())
-    print(valid_kinds)
+    # print(valid_kinds)
     if kind is not None:
         if isinstance(kind, str):
             kind = [kind]
@@ -3032,13 +3032,7 @@ def plotxy(
         if kind is not None:
             for k in kind:
                 if k in valid_kinds:
-                    print(f"{k}:\n\t{default_settings[k]}")
-                    print(
-                        sns_info[sns_info["Functions"].str.contains(k)]
-                        .iloc[:, -1]
-                        .tolist()[0]
-                    )
-                    print()
+                    print(f"{k}:\n\t{default_settings[k]}") 
         usage_str = """plotxy(data=ranked_genes,
         x="log2(fold_change)",
         y="-log10(p-value)",
@@ -3102,7 +3096,6 @@ def plotxy(
             hue = kwargs.pop("hue", None)
             if isinstance(kws_scatter, dict):  # Check if kws_scatter is a dictionary
                 kws_scatter.pop("hue", None)  # Safely remove 'hue' if it exists
-
             palette = kws_scatter.pop("palette",get_color(data[hue].nunique()) if hue is not None else None)
             s = kws_scatter.pop("s", 10)
             alpha = kws_scatter.pop("alpha", 0.7)

{py2ls-0.2.4.8.dist-info → py2ls-0.2.4.9.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: py2ls
-Version: 0.2.4.8
+Version: 0.2.4.9
 Summary: py(thon)2(too)ls
 Author: Jianfeng
 Author-email: Jianfeng.Liu0413@gmail.com
@@ -56,7 +56,7 @@ Requires-Dist: coverage (>=7.6.0)
 Requires-Dist: coveralls (>=4.0.1)
 Requires-Dist: crashtest (>=0.4.1)
 Requires-Dist: cycler (>=0.12.1)
-Requires-Dist: dask[dataframe] (>=2023.6,<2024.0)
+Requires-Dist: dask (>=2024.7.1)
 Requires-Dist: debugpy (>=1.8.2)
 Requires-Dist: decorator (>=5.1.1)
 Requires-Dist: defusedxml (>=0.7.1)

{py2ls-0.2.4.8.dist-info → py2ls-0.2.4.9.dist-info}/RECORD

@@ -17,7 +17,7 @@ py2ls/.git/hooks/pre-receive.sample,sha256=pMPSuce7P9jRRBwxvU7nGlldZrRPz0ndsxAlI
 py2ls/.git/hooks/prepare-commit-msg.sample,sha256=6d3KpBif3dJe2X_Ix4nsp7bKFjkLI5KuMnbwyOGqRhk,1492
 py2ls/.git/hooks/push-to-checkout.sample,sha256=pT0HQXmLKHxt16-mSu5HPzBeZdP0lGO7nXQI7DsSv18,2783
 py2ls/.git/hooks/update.sample,sha256=jV8vqD4QPPCLV-qmdSHfkZT0XL28s32lKtWGCXoU0QY,3650
-py2ls/.git/index,sha256=w4n_eE4nWnGzWPUMesYlqgV_hldK1TphJVZrRyij5Vo,4232
+py2ls/.git/index,sha256=CwYqVYvTvnn8cGWn-ctzQIfhmbgRfxtYXrAkmCA1AuU,4232
 py2ls/.git/info/exclude,sha256=ZnH-g7egfIky7okWTR8nk7IxgFjri5jcXAbuClo7DsE,240
 py2ls/.git/logs/HEAD,sha256=8ID7WuAe_TlO9g-ARxhIJYdgdL3u3m7-1qrOanaIUlA,3535
 py2ls/.git/logs/refs/heads/main,sha256=8ID7WuAe_TlO9g-ARxhIJYdgdL3u3m7-1qrOanaIUlA,3535
@@ -214,17 +214,17 @@ py2ls/export_requirements.py,sha256=x2WgUF0jYKz9GfA1MVKN-MdsM-oQ8yUeC6Ua8oCymio,
 py2ls/fetch_update.py,sha256=9LXj661GpCEFII2wx_99aINYctDiHni6DOruDs_fdt8,4752
 py2ls/freqanalysis.py,sha256=F4218VSPbgL5tnngh6xNCYuNnfR-F_QjECUUxrPYZss,32594
 py2ls/ich2ls.py,sha256=3E9R8oVpyYZXH5PiIQgT3CN5NxLe4Dwtm2LwaeacE6I,21381
-py2ls/ips.py,sha256=OJgNO3F-S7m5QjrwRjFOxG-sIZruRvK52NfnTm9yhTU,260110
-py2ls/ml2ls.py,sha256=SODP4ebQnbpdhX1VeUXTkHIKSxz37c0Brxis87vPv4U,102625
+py2ls/ips.py,sha256=2Ds3kra7LtxVu5L1vNrpKjGFhg2mdnS5qcqSqHDNkkQ,265181
+py2ls/ml2ls.py,sha256=EN-ufKgFs6NWPJVyh3mu9VmRyRK4vgi6rzufDd7B2pA,106633
 py2ls/mol.py,sha256=AZnHzarIk_MjueKdChqn1V6e4tUle3X1NnHSFA6n3Nw,10645
 py2ls/netfinder.py,sha256=RJFr80tGEJiuwEx99IBOhI5-ZuXnPdWnGUYpF7XCEwI,56426
 py2ls/ocr.py,sha256=5lhUbJufIKRSOL6wAWVLEo8TqMYSjoI_Q-IO-_4u3DE,31419
-py2ls/plot.py,sha256=IBIlcOYmXLrsgq_7338JlowZVPns8Hr3dHnvozwINl4,167825
+py2ls/plot.py,sha256=LeQpTLvRHMDrQtU8yaeXEOgDdVm7KWLcAuRia6wWMYQ,167604
 py2ls/setuptools-70.1.0-py3-none-any.whl,sha256=2bi3cUVal8ip86s0SOvgspteEF8SKLukECi-EWmFomc,882588
 py2ls/sleep_events_detectors.py,sha256=bQA3HJqv5qnYKJJEIhCyhlDtkXQfIzqksnD0YRXso68,52145
 py2ls/stats.py,sha256=DMoJd8Z5YV9T1wB-4P52F5K5scfVK55DT8UP4Twcebo,38627
 py2ls/translator.py,sha256=zBeq4pYZeroqw3DT-5g7uHfVqKd-EQptT6LJ-Adi8JY,34244
 py2ls/wb_detector.py,sha256=7y6TmBUj9exCZeIgBAJ_9hwuhkDh1x_-yg4dvNY1_GQ,6284
-py2ls-0.2.4.8.dist-info/METADATA,sha256=Fr6xazl4OK1paux9REIe5pEKB-xDp4soHe7PLsvIHmA,20055
-py2ls-0.2.4.8.dist-info/WHEEL,sha256=FMvqSimYX_P7y0a7UY-_Mc83r5zkBZsCYPm7Lr0Bsq4,88
-py2ls-0.2.4.8.dist-info/RECORD,,
+py2ls-0.2.4.9.dist-info/METADATA,sha256=4HaavKedVGS05_RLEBRr7E_A9XJotqR0oXRC0u-qR4k,20038
+py2ls-0.2.4.9.dist-info/WHEEL,sha256=FMvqSimYX_P7y0a7UY-_Mc83r5zkBZsCYPm7Lr0Bsq4,88
+py2ls-0.2.4.9.dist-info/RECORD,,