changeset 36:40e31fb88836 draft

"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit 208a8d348e7c7a182cfbe1b6f17868146428a7e2"

--- a/fitted_model_eval.py	Tue Apr 13 19:05:25 2021 +0000
+++ b/fitted_model_eval.py	Tue Apr 13 22:20:07 2021 +0000
@@ -1,13 +1,13 @@
 import argparse
 import json
-import pandas as pd
 import warnings
 
+import pandas as pd
+from galaxy_ml.utils import get_scoring, load_model, read_columns
 from scipy.io import mmread
-from sklearn.pipeline import Pipeline
 from sklearn.metrics.scorer import _check_multimetric_scoring
 from sklearn.model_selection._validation import _score
-from galaxy_ml.utils import get_scoring, load_model, read_columns
+from sklearn.pipeline import Pipeline
 
 
 def _get_X_y(params, infile1, infile2):

--- a/keras_deep_learning.py	Tue Apr 13 19:05:25 2021 +0000
+++ b/keras_deep_learning.py	Tue Apr 13 22:20:07 2021 +0000
@@ -1,14 +1,14 @@
 import argparse
 import json
+import pickle
+import warnings
+from ast import literal_eval
+
 import keras
 import pandas as pd
-import pickle
 import six
-import warnings
-
-from ast import literal_eval
-from keras.models import Sequential, Model
-from galaxy_ml.utils import try_get_attr, get_search_params, SafeEval
+from galaxy_ml.utils import get_search_params, SafeEval, try_get_attr
+from keras.models import Model, Sequential
 
 
 safe_eval = SafeEval()

--- a/keras_train_and_eval.py	Tue Apr 13 19:05:25 2021 +0000
+++ b/keras_train_and_eval.py	Tue Apr 13 22:20:07 2021 +0000
@@ -1,32 +1,32 @@
 import argparse
-import joblib
 import json
-import numpy as np
 import os
-import pandas as pd
 import pickle
 import warnings
 from itertools import chain
-from scipy.io import mmread
-from sklearn.pipeline import Pipeline
-from sklearn.metrics.scorer import _check_multimetric_scoring
-from sklearn.model_selection._validation import _score
-from sklearn.model_selection import _search, _validation
-from sklearn.utils import indexable, safe_indexing
 
+import joblib
+import numpy as np
+import pandas as pd
 from galaxy_ml.externals.selene_sdk.utils import compute_score
-from galaxy_ml.model_validations import train_test_split
 from galaxy_ml.keras_galaxy_models import _predict_generator
+from galaxy_ml.model_validations import train_test_split
 from galaxy_ml.utils import (
-    SafeEval,
+    clean_params,
+    get_main_estimator,
+    get_module,
     get_scoring,
     load_model,
     read_columns,
+    SafeEval,
     try_get_attr,
-    get_module,
-    clean_params,
-    get_main_estimator,
 )
+from scipy.io import mmread
+from sklearn.metrics.scorer import _check_multimetric_scoring
+from sklearn.model_selection import _search, _validation
+from sklearn.model_selection._validation import _score
+from sklearn.pipeline import Pipeline
+from sklearn.utils import indexable, safe_indexing
 
 
 _fit_and_score = try_get_attr("galaxy_ml.model_validations", "_fit_and_score")
@@ -104,7 +104,7 @@
         rval = train_test_split(*new_arrays, **kwargs)
 
     for pos in nones:
-        rval[pos * 2 : 2] = [None, None]
+        rval[pos * 2: 2] = [None, None]
 
     return rval
 

--- a/ml_visualization_ex.py	Tue Apr 13 19:05:25 2021 +0000
+++ b/ml_visualization_ex.py	Tue Apr 13 22:20:07 2021 +0000
@@ -1,21 +1,20 @@
 import argparse
 import json
+import os
+import warnings
+
 import matplotlib
 import matplotlib.pyplot as plt
 import numpy as np
-import os
 import pandas as pd
 import plotly
 import plotly.graph_objs as go
-import warnings
-
+from galaxy_ml.utils import load_model, read_columns, SafeEval
 from keras.models import model_from_json
 from keras.utils import plot_model
 from sklearn.feature_selection.base import SelectorMixin
-from sklearn.metrics import precision_recall_curve, average_precision_score
-from sklearn.metrics import roc_curve, auc, confusion_matrix
+from sklearn.metrics import auc, average_precision_score, confusion_matrix, precision_recall_curve, roc_curve
 from sklearn.pipeline import Pipeline
-from galaxy_ml.utils import load_model, read_columns, SafeEval
 
 
 safe_eval = SafeEval()

--- a/model_prediction.py	Tue Apr 13 19:05:25 2021 +0000
+++ b/model_prediction.py	Tue Apr 13 22:20:07 2021 +0000
@@ -4,13 +4,10 @@
 
 import numpy as np
 import pandas as pd
+from galaxy_ml.utils import get_module, load_model, read_columns, try_get_attr
 from scipy.io import mmread
 from sklearn.pipeline import Pipeline
 
-from galaxy_ml.utils import (get_module, load_model,
-                             read_columns, try_get_attr)
-
-
 N_JOBS = int(__import__("os").environ.get("GALAXY_SLOTS", 1))
 
 

--- a/search_model_validation.py	Tue Apr 13 19:05:25 2021 +0000
+++ b/search_model_validation.py	Tue Apr 13 22:20:07 2021 +0000
@@ -1,15 +1,27 @@
 import argparse
 import collections
+import json
+import os
+import pickle
+import sys
+import warnings
+
 import imblearn
 import joblib
-import json
 import numpy as np
-import os
 import pandas as pd
-import pickle
 import skrebate
-import sys
-import warnings
+from galaxy_ml.utils import (
+    clean_params,
+    get_cv,
+    get_main_estimator,
+    get_module,
+    get_scoring,
+    load_model,
+    read_columns,
+    SafeEval,
+    try_get_attr
+)
 from scipy.io import mmread
 from sklearn import (
     cluster,
@@ -20,21 +32,8 @@
     preprocessing,
 )
 from sklearn.exceptions import FitFailedWarning
+from sklearn.model_selection import _search, _validation
 from sklearn.model_selection._validation import _score, cross_validate
-from sklearn.model_selection import _search, _validation
-from sklearn.pipeline import Pipeline
-
-from galaxy_ml.utils import (
-    SafeEval,
-    get_cv,
-    get_scoring,
-    load_model,
-    read_columns,
-    try_get_attr,
-    get_module,
-    clean_params,
-    get_main_estimator,
-)
 
 
 _fit_and_score = try_get_attr("galaxy_ml.model_validations", "_fit_and_score")

--- a/simple_model_fit.py	Tue Apr 13 19:05:25 2021 +0000
+++ b/simple_model_fit.py	Tue Apr 13 22:20:07 2021 +0000
@@ -1,8 +1,8 @@
 import argparse
 import json
-import pandas as pd
 import pickle
 
+import pandas as pd
 from galaxy_ml.utils import load_model, read_columns
 from scipy.io import mmread
 from sklearn.pipeline import Pipeline

--- a/stacking_ensembles.py	Tue Apr 13 19:05:25 2021 +0000
+++ b/stacking_ensembles.py	Tue Apr 13 22:20:07 2021 +0000
@@ -1,13 +1,14 @@
 import argparse
 import ast
 import json
-import mlxtend.regressor
-import mlxtend.classifier
-import pandas as pd
 import pickle
 import sys
 import warnings
-from galaxy_ml.utils import load_model, get_cv, get_estimator, get_search_params
+
+import mlxtend.classifier
+import mlxtend.regressor
+import pandas as pd
+from galaxy_ml.utils import get_cv, get_estimator, get_search_params, load_model
 
 
 warnings.filterwarnings("ignore")

--- a/train_test_eval.py	Tue Apr 13 19:05:25 2021 +0000
+++ b/train_test_eval.py	Tue Apr 13 22:20:07 2021 +0000
@@ -3,7 +3,6 @@
 import os
 import pickle
 import warnings
-
 from itertools import chain
 
 import joblib
@@ -21,7 +20,6 @@
 from scipy.io import mmread
 from sklearn import pipeline
 from sklearn.metrics.scorer import _check_multimetric_scoring
-from sklearn.model_selection._validation import _score
 from sklearn.model_selection import _search, _validation
 from sklearn.model_selection._validation import _score
 from sklearn.utils import indexable, safe_indexing

--- a/train_test_split.py	Tue Apr 13 19:05:25 2021 +0000
+++ b/train_test_split.py	Tue Apr 13 22:20:07 2021 +0000
@@ -1,8 +1,8 @@
 import argparse
 import json
-import pandas as pd
 import warnings
 
+import pandas as pd
 from galaxy_ml.model_validations import train_test_split
 from galaxy_ml.utils import get_cv, read_columns