4 examples of 'shufflesplit sklearn' in Python
Every line of 'shufflesplit sklearn' code snippets is scanned for vulnerabilities by our powerful machine learning engine that combs millions of open source libraries, ensuring your Python code is secure.
All examples are scanned by Snyk Code
By copying the Snyk Code Snippets you agree to
6 def split(df): 7 ''' 8 9 :param df: Dataframe to be splited 10 :return: Sorted list of dataframe's splited list 11 ''' 12 trainingSet, testSet = train_test_split(df, test_size=0.2) 13 sorted_trainSet = trainingSet.sort_values('user_id') 14 sorted_testSet = testSet.sort_values('user_id') 15 return sorted_testSet, sorted_trainSet
423 def _train_val_split(df, validation): 424 train_df = df 425 val_df = None 426 validation_ratio = 0.0 427 428 if isinstance(validation, float) and validation > 0: 429 train_df, val_df = train_df.randomSplit([1.0 - validation, validation]) 430 validation_ratio = validation 431 elif isinstance(validation, str): 432 dtype = [field.dataType for field in df.schema.fields if field.name == validation][0] 433 bool_dtype = isinstance(dtype, BooleanType) 434 val_df = train_df.filter( 435 f.col(validation) if bool_dtype else f.col(validation) > 0).drop(validation) 436 train_df = train_df.filter( 437 ~f.col(validation) if bool_dtype else f.col(validation) == 0).drop(validation) 438 439 # Approximate ratio of validation data to training data for proportionate scale 440 # of partitions 441 timeout_ms = 1000 442 confidence = 0.90 443 train_rows = train_df.rdd.countApprox(timeout=timeout_ms, confidence=confidence) 444 val_rows = val_df.rdd.countApprox(timeout=timeout_ms, confidence=confidence) 445 validation_ratio = val_rows / (val_rows + train_rows) 446 elif validation: 447 raise ValueError('Unrecognized validation type: {}'.format(type(validation))) 448 449 return train_df, val_df, validation_ratio
220 def randomSplit(self, weights, seed=None): 221 """ 222 223 :param weights: 224 :param seed: 225 :return: 226 """ 227 pass
167 @staticmethod 168 def _get_split(X, y): 169 split = ShuffleSplit(y.shape[0], n_iter=1) 170 train, validate = list(split)[0] 171 X_train, X_validate, y_train, y_validate = X[train], X[validate], y[train], y[validate] 172 return X_train, X_validate, y_train, y_validate