EDA Phase

Author: raptor419

…eamline/p1_eda_processing/dataprocess.py …reamline/p1_data_process/data_process.pystreamline/p1_eda_processing/dataprocess.py renamed to streamline/p1_data_process/data_process.py streamline/p1_eda_processing/dataprocess.py renamed to streamline/p1_data_process/data_process.py

@@ -17,7 +17,7 @@
 
 from streamline.utils.job import Job
 from streamline.utils.dataset import Dataset
-from streamline.dataprep.kfold_partitioning import KFoldPartitioner
+from streamline.p1_eda_processing.utils.kfold_partitioning import KFoldPartitioner
 from scipy.stats import chi2_contingency, mannwhitneyu, skew, kurtosis, f_oneway, spearmanr
 import seaborn as sns
 import warnings
@@ -37,7 +37,7 @@ def __init__(self, dataset, experiment_path, ignore_features=None,
                  categorical_features=None, quantitative_features=None, exclude_eda_output=None,
                  categorical_cutoff=10, sig_cutoff=0.05, featureeng_missingness=0.5,
                  cleaning_missingness=0.5, correlation_removal_threshold=1.0,
-                 partition_method="Stratified", n_splits=10,
+                 partition_method="Stratified", n_splits=10, one_hot_encoding=True,
                  random_state=None, show_plots=False):
         """
         Initialization function for Exploratory Data Analysis Class. Parameters are defined below.

…amline/p1_eda_processing/p1_jobsubmit.py …reamline/p1_data_process/p1_jobsubmit.pystreamline/p1_eda_processing/p1_jobsubmit.py renamed to streamline/p1_data_process/p1_jobsubmit.py streamline/p1_eda_processing/p1_jobsubmit.py renamed to streamline/p1_data_process/p1_jobsubmit.py

@@ -13,7 +13,7 @@
 from streamline.utils.cluster import get_cluster
 
 
-class DataProcessRunner:
+class P1Runner:
     """
     Description: Phase 1 of STREAMLINE - This 'Main' script manages Phase 1 run parameters, \
     updates the metadata file (with user specified run parameters across pipeline run) \

streamline/p1_eda_processing/p1_runner.py streamline/p1_data_process/p1_runner.pystreamline/p1_eda_processing/p1_runner.py renamed to streamline/p1_data_process/p1_runner.py

@@ -5,12 +5,12 @@
 import dask
 from pathlib import Path
 from joblib import Parallel, delayed
-from streamline.dataprep.scale_and_impute import ScaleAndImpute
+from streamline.p2_imputation_scaling.imputaion import ImputeAndScale
 from streamline.utils.runners import runner_fn, num_cores
 from streamline.utils.cluster import get_cluster
 
 
-class ImputationRunner:
+class P2Runner:
     """
     Runner class for Data Processing Jobs of CV Splits
     """