def _eval_swap_params(params_builder):
swap_params = {}
for p in params_builder['param_set']:
swap_value = p['sp_value'].strip()
if swap_value == '':
continue
param_name = p['sp_name']
if param_name.lower().endswith(NON_SEARCHABLE):
warnings.warn("Warning: `%s` is not eligible for search and was "
"omitted!" % param_name)
continue
if not swap_value.startswith(':'):
safe_eval = SafeEval(load_scipy=True, load_numpy=True)
ev = safe_eval(swap_value)
else:
# Have `:` before search list, asks for estimator evaluatio
safe_eval_es = SafeEval(load_estimators=True)
swap_value = swap_value[1:].strip()
# TODO maybe add regular express check
ev = safe_eval_es(swap_value)
swap_params[param_name] = ev
return swap_params
def _handle_image_generator_params(params, image_df):
"""reconstruct generator kwargs from tool inputs
"""
safe_eval = SafeEval()
options = {}
headers = image_df.columns
options['x_col'] = headers[params['x_col'][0] - 1]
y_col = list(map(lambda x: x - 1, params['y_col']))
if len(y_col) == 1:
options['y_col'] = headers[y_col[0]]
else:
options['y_col'] = list(headers[y_col])
weight_col = params['weight_col'][0]
if weight_col is None:
options['weight_col'] = None
else:
options['weight_col'] = headers[weight_col - 1]
other_options = params['options']
for k, v in other_options.items():
if k == 'target_size' or k.endswith('_range'):
v = v.strip()
if not v:
other_options[k] = None
else:
other_options[k] = safe_eval(v)
if k == 'classes':
v = v.strip()
if not v:
other_options[k] = None
else:
other_options[k] = [x.strip() for x in v.split(',')]
options.update(other_options)
return options
import numpy as np
import os
import pandas as pd
import plotly
import plotly.graph_objs as go
import warnings
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.pipeline import Pipeline
from galaxy_ml.utils import load_model, read_columns, SafeEval
safe_eval = SafeEval()
# plotly default colors
default_colors = [
'#1f77b4', # muted blue
'#ff7f0e', # safety orange
'#2ca02c', # cooked asparagus green
'#d62728', # brick red
'#9467bd', # muted purple
'#8c564b', # chestnut brown
'#e377c2', # raspberry yogurt pink
'#7f7f7f', # middle gray
'#bcbd22', # curry yellow-green
'#17becf' # blue-teal
]
def _eval_search_params(params_builder):
search_params = {}
for p in params_builder['param_set']:
search_list = p['sp_list'].strip()
if search_list == '':
continue
param_name = p['sp_name']
if param_name.lower().endswith(NON_SEARCHABLE):
print("Warning: `%s` is not eligible for search and was "
"omitted!" % param_name)
continue
if not search_list.startswith(':'):
safe_eval = SafeEval(load_scipy=True, load_numpy=True)
ev = safe_eval(search_list)
search_params[param_name] = ev
else:
# Have `:` before search list, asks for estimator evaluatio
safe_eval_es = SafeEval(load_estimators=True)
search_list = search_list[1:].strip()
# TODO maybe add regular express check
ev = safe_eval_es(search_list)
preprocessings = (
preprocessing.StandardScaler(), preprocessing.Binarizer(),
preprocessing.MaxAbsScaler(), preprocessing.Normalizer(),
preprocessing.MinMaxScaler(),
preprocessing.PolynomialFeatures(),
preprocessing.RobustScaler(), feature_selection.SelectKBest(),
feature_selection.GenericUnivariateSelect(),
feature_selection.SelectPercentile(),
feature_selection.SelectFpr(), feature_selection.SelectFdr(),
feature_selection.SelectFwe(),
feature_selection.VarianceThreshold(),
decomposition.FactorAnalysis(random_state=0),
decomposition.FastICA(random_state=0),
decomposition.IncrementalPCA(),
decomposition.KernelPCA(random_state=0, n_jobs=N_JOBS),
decomposition.LatentDirichletAllocation(random_state=0,
n_jobs=N_JOBS),
decomposition.MiniBatchDictionaryLearning(random_state=0,
n_jobs=N_JOBS),
decomposition.MiniBatchSparsePCA(random_state=0,
n_jobs=N_JOBS),
decomposition.NMF(random_state=0),
decomposition.PCA(random_state=0),
decomposition.SparsePCA(random_state=0, n_jobs=N_JOBS),
decomposition.TruncatedSVD(random_state=0),
kernel_approximation.Nystroem(random_state=0),
kernel_approximation.RBFSampler(random_state=0),
kernel_approximation.AdditiveChi2Sampler(),
kernel_approximation.SkewedChi2Sampler(random_state=0),
cluster.FeatureAgglomeration(),
skrebate.ReliefF(n_jobs=N_JOBS), skrebate.SURF(n_jobs=N_JOBS),
skrebate.SURFstar(n_jobs=N_JOBS),
skrebate.MultiSURF(n_jobs=N_JOBS),
skrebate.MultiSURFstar(n_jobs=N_JOBS),
imblearn.under_sampling.ClusterCentroids(random_state=0,
n_jobs=N_JOBS),
imblearn.under_sampling.CondensedNearestNeighbour(
random_state=0, n_jobs=N_JOBS),
imblearn.under_sampling.EditedNearestNeighbours(random_state=0,
n_jobs=N_JOBS),
imblearn.under_sampling.RepeatedEditedNearestNeighbours(
random_state=0, n_jobs=N_JOBS),
imblearn.under_sampling.AllKNN(random_state=0, n_jobs=N_JOBS),
imblearn.under_sampling.InstanceHardnessThreshold(
random_state=0, n_jobs=N_JOBS),
imblearn.under_sampling.NearMiss(random_state=0,
n_jobs=N_JOBS),
imblearn.under_sampling.NeighbourhoodCleaningRule(
random_state=0, n_jobs=N_JOBS),
imblearn.under_sampling.OneSidedSelection(random_state=0,
n_jobs=N_JOBS),
imblearn.under_sampling.RandomUnderSampler(random_state=0),
imblearn.under_sampling.TomekLinks(random_state=0,
n_jobs=N_JOBS),
imblearn.over_sampling.ADASYN(random_state=0, n_jobs=N_JOBS),
imblearn.over_sampling.RandomOverSampler(random_state=0),
imblearn.over_sampling.SMOTE(random_state=0, n_jobs=N_JOBS),
imblearn.over_sampling.SVMSMOTE(random_state=0, n_jobs=N_JOBS),
imblearn.over_sampling.BorderlineSMOTE(random_state=0,
n_jobs=N_JOBS),
imblearn.over_sampling.SMOTENC(categorical_features=[],
random_state=0,
n_jobs=N_JOBS),
imblearn.combine.SMOTEENN(random_state=0),
imblearn.combine.SMOTETomek(random_state=0))
newlist = []
for obj in ev:
if obj is None:
newlist.append(None)
elif obj == 'all_0':
newlist.extend(preprocessings[0:35])
elif obj == 'sk_prep_all': # no KernalCenter()
newlist.extend(preprocessings[0:7])
elif obj == 'fs_all':
newlist.extend(preprocessings[7:14])
elif obj == 'decomp_all':
newlist.extend(preprocessings[14:25])
elif obj == 'k_appr_all':
newlist.extend(preprocessings[25:29])
elif obj == 'reb_all':
newlist.extend(preprocessings[30:35])
elif obj == 'imb_all':
newlist.extend(preprocessings[35:54])
elif type(obj) is int and -1 < obj < len(preprocessings):
newlist.append(preprocessings[obj])
elif hasattr(obj, 'get_params'): # user uploaded object
if 'n_jobs' in obj.get_params():
newlist.append(obj.set_params(n_jobs=N_JOBS))
else:
newlist.append(obj)
else:
sys.exit("Unsupported estimator type: %r" % (obj))
search_params[param_name] = newlist
return search_params