fsspark -> fslite

Author: ypriverol

docs/README.data.md

@@ -37,19 +37,21 @@ The following is an example of a TSV file with a binary response variable:
 - `import_table` - Import data from a TSV file into a Spark Data Frame (sdf).
 
 ```python
-from fsspark.utils.io import import_table
-sdf = import_table('data.tsv.bgz', 
-                    sep='\t', 
-                    n_partitions=5)
+from fslite.utils.io import import_table
+
+sdf = import_table('data.tsv.bgz',
+                   sep='\t',
+                   n_partitions=5)
 ```
 
 - `import_table_as_psdf` - Import data from a TSV file into a Spark Data Frame (sdf) and 
 convert it into a Pandas on Spark Data Frame (psdf).
 
 ```python
-from fsspark.utils.io import import_table_as_psdf
-psdf = import_table_as_psdf('data.tsv.bgz', 
-                            sep='\t', 
+from fslite.utils.io import import_table_as_psdf
+
+psdf = import_table_as_psdf('data.tsv.bgz',
+                            sep='\t',
                             n_partitions=5)
 ```
 
@@ -73,9 +75,9 @@ contains the response variable.
 #### How to create a Feature Selection Spark Data Frame (FSDF)
 
 ```python
-from fsspark.config.context import init_spark, stop_spark_session
-from fsspark.fs.core import FSDataFrame
-from fsspark.utils.io import import_table_as_psdf
+from fslite.config.context import init_spark, stop_spark_session
+from fslite.fs.core import FSDataFrame
+from fslite.utils.io import import_table_as_psdf
 
 # Init spark
 init_spark()

docs/README.methods.md

@@ -53,4 +53,4 @@ A typical workflow written using `fsspark` can be divided roughly in four major
 
 ### 5. Feature selection pipeline example
 
-[FS pipeline example](../fsspark/pipeline/fs_pipeline_example.py)
+[FS pipeline example](../fslite/pipeline/fs_pipeline_example.py)

environment.yml

@@ -1,4 +1,4 @@
-name: fsspark-venv
+name: fslite-venv
 channels:
   - defaults
   - conda-forge

fsspark/__init__.py renamed to fslite/__init__.py

@@ -1,12 +1,12 @@
 from abc import ABC, abstractmethod
 from typing import List, Type, Union, Tuple, Optional, Dict, Any
 
-from fsspark.fs.constants import (ML_METHODS, UNIVARIATE_METHODS,
-                                  MULTIVARIATE_METHODS)
-from fsspark.fs.core import FSDataFrame
-from fsspark.fs.ml import MLCVModel
-from fsspark.fs.multivariate import multivariate_filter
-from fsspark.fs.univariate import univariate_filter
+from fslite.fs.constants import (ML_METHODS, UNIVARIATE_METHODS,
+                                 MULTIVARIATE_METHODS)
+from fslite.fs.core import FSDataFrame
+from fslite.fs.ml import MLCVModel
+from fslite.fs.multivariate import multivariate_filter
+from fslite.fs.univariate import univariate_filter
 
 
 class FSMethod(ABC):

fsspark/config/__init__.py renamed to fslite/fs/__init__.py

@@ -20,15 +20,15 @@
 from pyspark.ml.regression import RandomForestRegressionModel, RandomForestRegressor
 from pyspark.ml.tuning import CrossValidator, ParamGridBuilder, CrossValidatorModel, Param
 
-from fsspark.fs.constants import (RF_BINARY,
-                                  LSVC_BINARY,
-                                  FM_BINARY,
-                                  RF_MULTILABEL,
-                                  LR_MULTILABEL,
-                                  RF_REGRESSION,
-                                  FM_REGRESSION,
-                                  ML_METHODS)
-from fsspark.fs.core import FSDataFrame
+from fslite.fs.constants import (RF_BINARY,
+                                 LSVC_BINARY,
+                                 FM_BINARY,
+                                 RF_MULTILABEL,
+                                 LR_MULTILABEL,
+                                 RF_REGRESSION,
+                                 FM_REGRESSION,
+                                 ML_METHODS)
+from fslite.fs.core import FSDataFrame
 
 ESTIMATORS_CLASSES = [RandomForestClassifier, RandomForestRegressionModel, LinearSVC, LogisticRegression]
 EVALUATORS_CLASSES = [BinaryClassificationEvaluator, MulticlassClassificationEvaluator, RegressionEvaluator]

fsspark/fs/constants.py renamed to fslite/fs/constants.py

@@ -6,11 +6,11 @@
 from pyspark.ml.feature import (VarianceThresholdSelector)
 from pyspark.ml.stat import Correlation
 
-from fsspark.fs.constants import MULTIVARIATE_METHODS, MULTIVARIATE_CORRELATION, MULTIVARIATE_VARIANCE
+from fslite.fs.constants import MULTIVARIATE_METHODS, MULTIVARIATE_CORRELATION, MULTIVARIATE_VARIANCE
 
-from fsspark.fs.core import FSDataFrame
-from fsspark.fs.utils import find_maximal_independent_set
-from fsspark.utils.generic import tag
+from fslite.fs.core import FSDataFrame
+from fslite.fs.utils import find_maximal_independent_set
+from fslite.utils.generic import tag
 
 logging.basicConfig(format="%(levelname)s (%(name)s %(lineno)s): %(message)s")
 logger = logging.getLogger("FSSPARK:MULTIVARIATE")