tanu/ML_AI_training
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity
ML_AI_training/classification_params_FS.py

803 lines
27 KiB
Python
Executable file
Raw Permalink Blame History

# Date: 25/05/2020
# https://scikit-learn.org/stable/supervised_learning.html
# try features from Autosklearn:
# autosklearn --> pipleine --> components --> classification
# https://github.com/automl/auto-sklearn/tree/master/autosklearn/pipeline/components/classification
# ADDED 27/05/2022: Extra Tree + LRCV and RCCV
######https://scikit-learn.org/stable/supervised_learning.html
########################################################################
#======================
# AdaBoostClassifier()
#https://github.com/automl/auto-sklearn/blob/master/autosklearn/pipeline/components/classification/adaboost.py
#https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.AdaBoostClassifier.html
#======================
estimator = AdaBoostClassifier(**rs)
# Define pipleline with steps
pipe_abc = Pipeline([
('pre', MinMaxScaler())
, ('fs', RFECV(DecisionTreeClassifier(**rs), cv = cv, scoring = 'matthews_corrcoef'))
# , ('fs', RFECV(estimator, cv = cv, scoring = 'matthews_corrcoef'))
# , ('clf', AdaBoostClassifier(**rs))])
, ('clf', estimator)
])
# Define hyperparmeter space to search for
param_grid_abc = [
{
'fs__min_features_to_select' : [1,2]
# , 'fs__cv': [cv]
},
{
# 'clf': [AdaBoostClassifier(**rs)],
# 'clf__n_estimators': [50, 100, 150, 200, 250, 300, 350, 400, 450, 500]
'clf__n_estimators': [50, 100, 200, 300, 400, 500],
'clf__learning_rate': [0.01, 0.1, 1, 1.5, 2],
'clf__max_depth': [1, 5, 10],
# 'clf__base_estimator' : ['SVC']
}
]
#======================
# Extra TreesClassifier()
#https://github.com/automl/auto-sklearn/blob/master/autosklearn/pipeline/components/classification/extra_trees.py
#https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.ExtraTreesClassifier.html
#======================
estimator = ExtraTreesClassifier(**rs)
# Define pipleline with steps
pipe_abc = Pipeline([
('pre', MinMaxScaler())
, ('fs', RFECV(DecisionTreeClassifier(**rs), cv = cv, scoring = 'matthews_corrcoef'))
# , ('fs', RFECV(estimator, cv = cv, scoring = 'matthews_corrcoef'))
# , ('clf', ExtraTreesClassifier(**rs))])
, ('clf', estimator)
])
# Define hyperparmeter space to search for
param_grid_abc = [
{
'fs__min_features_to_select' : [1,2]
# , 'fs__cv': [cv]
},
# 'clf': [ExtraTreesClassifier(**rs)],
'clf__n_estimators': [100, 300, 500], # sklearn has no tuning
'clf__max_depth': [None],
'clf__criterion': ['gini', 'entropy'],
'clf__max_features': [None, 'sqrt', 'log2', 0.5, 1],
'clf__min_samples_leaf': [1, 5, 10, 15, 20],
'clf__min_samples_split': [2, 5, 10, 15, 20]
}
]
#======================
# Extra TreeClassifier()
https://scikit-learn.org/stable/modules/generated/sklearn.tree.ExtraTreeClassifier.html
#======================
estimator = ExtraTreeClassifier(**rs)
# Define pipleline with steps
pipe_abc = Pipeline([
('pre', MinMaxScaler())
, ('fs', RFECV(DecisionTreeClassifier(**rs), cv = cv, scoring = 'matthews_corrcoef'))
# , ('fs', RFECV(estimator, cv = cv, scoring = 'matthews_corrcoef'))
# , ('clf', ExtraTreesClassifier(**rs))])
, ('clf', estimator)
])
# Define hyperparmeter space to search for
param_grid_abc = [
{
'fs__min_features_to_select' : [1,2]
# , 'fs__cv': [cv]
},
# 'clf': [ExtraTreeClassifier(**rs)],
'clf__max_depth': [None],
'clf__criterion': ['gini', 'entropy'],
'clf__max_features': [None, 'sqrt', 'log2', 0.5, 1],
'clf__min_samples_leaf': [1, 5, 10, 15, 20],
'clf__min_samples_split': [2, 5, 10, 15, 20]
}
]
#===========================
# DecisionTreeClassifier()
https://github.com/automl/auto-sklearn/blob/master/autosklearn/pipeline/components/classification/decision_tree.py
https://scikit-learn.org/stable/modules/generated/sklearn.tree.DecisionTreeClassifier.html
#===========================
# Define estimator
estimator = DecisionTreeClassifier(**rs)
# Define pipleline with steps
pipe_dt = Pipeline([
('pre', MinMaxScaler())
, ('fs', RFECV(DecisionTreeClassifier(**rs), cv = cv, scoring = 'matthews_corrcoef'))
# , ('fs', RFECV(estimator, cv = cv, scoring = 'matthews_corrcoef'))
, ('clf', estimator)
])
# Define hyperparmeter space to search for
param_grid_dt = [
{
'fs__min_features_to_select' : [1,2]
# , 'fs__cv': [cv]
},
{
# 'clf': [DecisionTreeClassifier(**rs)],
# 'clf__max_depth': [None, 2, 6, 10, 14, 16, 20],
'clf__max_depth': [None, 0, 0.2, 0.5],
'clf__class_weight':[None, 'balanced'],
'clf__criterion': ['gini', 'entropy'],
'clf__max_features': [None, 'sqrt', 'log2', 1],
'clf__min_samples_leaf': [1, 5, 10, 15, 20],
'clf__min_samples_split': [2, 5, 10, 15, 20]
}
]
########################################################################
#===========================
# RandomForestClassifier()
https://github.com/automl/auto-sklearn/blob/master/autosklearn/pipeline/components/classification/random_forest.py
https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.RandomForestClassifier.html
#===========================
# Define estimator
estimator = [RandomForestClassifier(**rs, **njobs, bootstrap = True, oob_score = True)](**rs)
# Define pipleline with steps
pipe_rf = Pipeline([
('pre', MinMaxScaler())
, ('fs', RFECV(DecisionTreeClassifier(**rs), cv = cv, scoring = 'matthews_corrcoef'))
# , ('fs', RFECV(estimator, cv = cv, scoring = 'matthews_corrcoef'))
, ('clf', estimator)
])
# Define hyperparmeter space to search for
param_grid_rf = [
{
'fs__min_features_to_select' : [1,2]
# , 'fs__cv': [cv]
},
{
# 'clf': [RandomForestClassifier(**rs, **njobs, bootstrap = True, oob_score = True)],
# 'clf__max_depth': [4, 6, 8, 10, 12, 16, 20, None]
'clf__max_depth': [None, 2, 6, 10, 14, 16, 20] #autosk: None
, 'clf__class_weight':[None, 'balanced']
, 'clf__n_estimators': [50, 100, 200, 300] # autodesk: no
, 'clf__criterion': ['gini', 'entropy']
, 'clf__max_features': ['sqrt', 'log2', None, 0, 0.5, 1]
, 'clf__min_samples_leaf': [1, 5, 10, 15, 20]
, 'clf__min_samples_split': [2, 5, 15, 20]
}
]
#=================
# XGBClassifier ()
#=================
# https://www.kaggle.com/code/stuarthallows/using-xgboost-with-scikit-learn/notebook
# Define estimator
#https://www.datatechnotes.com/2019/07/classification-example-with.html
# XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
# colsample_bynode=1, colsample_bytree=1, gamma=0, learning_rate=0.1,
# max_delta_step=0, max_depth=3, min_child_weight=1, missing=None,
# n_estimators=100, n_jobs=1, nthread=None,
# objective='multi:softprob', random_state=0, reg_alpha=0,
# reg_lambda=1, scale_pos_weight=1, seed=None, silent=None,
# subsample=1, verbosity=1)
estimator = XGBClassifier(**rs, **njobs, verbose = 3)
# Define pipleline with steps
pipe_xgb = Pipeline([
('pre', MinMaxScaler())
, ('fs', RFECV(DecisionTreeClassifier(**rs), cv = cv, scoring = 'matthews_corrcoef'))
# , ('fs', RFECV(estimator, cv = cv, scoring = 'matthews_corrcoef'))
, ('clf', estimator)
])
param_grid_xgb = [
{
'fs__min_features_to_select' : [1,2]
# , 'fs__cv': [cv]
},
{
# 'clf': [XGBClassifier(**rs , **njobs, verbose = 3)],
'clf__learning_rate': [0.01, 0.05, 0.1, 0.2]
, 'clf__max_depth' : [3, 8, 10, 12, 16, 20]
, 'clf__n_estimators': [50, 100, 200, 300]
}
]
#######################################################################
########################################################################
#======================
# BaggingClassifier()*
#https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.BaggingClassifier.html
#======================
estimator = BaggingClassifier(**rs
, **njobs
, bootstrap = True
, oob_score = True)
# Define pipleline with steps
pipe_bc = Pipeline([
('pre', MinMaxScaler())
, ('fs', RFECV(DecisionTreeClassifier(**rs), cv = cv, scoring = 'matthews_corrcoef'))
# , ('fs', RFECV(estimator, cv = cv, scoring = 'matthews_corrcoef'))
, ('clf', estimator)
])
# Define hyperparmeter space to search for
param_grid_bc = [
{
'fs__min_features_to_select' : [1,2]
# , 'fs__cv': [cv]
},
{
# 'clf': [BaggingClassifier(**rs, **njobs , bootstrap = True, oob_score = True)],
'clf__n_estimators' : [10, 25, 50, 100, 150, 200, 500, 700, 1000]
# , 'clf__base_estimator' : ['None', 'SVC()', 'KNeighborsClassifier()'] # if none, DT is used
}
]
########################################################################
#======================
# BernoulliNB ()
#https://github.com/automl/auto-sklearn/blob/master/autosklearn/pipeline/components/classification/bernoulli_nb.py
#https://scikit-learn.org/stable/modules/generated/sklearn.naive_bayes.BernoulliNB.html
#======================
# Define estimator
estimator = BernoulliNB()
# Define pipleline with steps
pipe_bnb = Pipeline([
('pre', MinMaxScaler())
, ('fs', RFECV(DecisionTreeClassifier(**rs), cv = cv, scoring = 'matthews_corrcoef'))
# , ('fs', RFECV(estimator, cv = cv, scoring = 'matthews_corrcoef'))
, ('clf', estimator)
])
# Define hyperparmeter space to search for
param_grid_bnb = [
{'fs__min_features_to_select' : [1,2]
# , 'fs__cv': [cv]
},
{
# 'clf': [BernoulliNB()],
'clf__alpha': [0.01, 0, 1, 10, 100]
, 'clf__binarize':[None, 0] # autosk has no, maybe just use None
, 'clf__fit_prior': [True]
, 'clf__class_prior': [None]
}
]
#########################################################################
#==============================
# GradientBoostingClassifier()
#https://github.com/automl/auto-sklearn/blob/master/autosklearn/pipeline/components/classification/gradient_boosting.py
#https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.GradientBoostingClassifier.html
#==============================
# Define estimator
estimator = GradientBoostingClassifier(**rs)
# Define pipleline with steps
pipe_gbc = Pipeline([
('pre', MinMaxScaler())
, ('fs', RFECV(DecisionTreeClassifier(**rs), cv = cv, scoring = 'matthews_corrcoef'))
# , ('fs', RFECV(estimator, cv = cv, scoring = 'matthews_corrcoef'))
, ('clf', estimator)
])
# Define hyperparmeter space to search for
param_grid_gbc = [
{
'fs__min_features_to_select' : [1,2]
# , 'fs__cv': [cv]
},
{
# 'clf': [GradientBoostingClassifier(**rs)],
'clf__loss' : ['log_loss', 'exponential'],
'clf__n_estimators' : [10, 100, 200, 500, 1000], # autosklearn: not there
'clf__learning_rate' : [0.01,0.1, 0, 0.5, 1],
'clf__subsample' : [0.5, 0.7, 1.0],
'clf__max_depth' : [3, 7, 9],
'clf__min_samples_leaf' : [1, 20, 50, 100, 150, 200],
'clf__max_depth' : [None],
'clf__max_leaf_nodes' : [3, 31, 51, 331, 2047] # autosklearn: log = T
'clf__l2_regularization' : [0.0000000001, 0.000001, 0.0001, 0.01, 0.1, 1], #lower=1E-10, upper=1, log = T
'n_iter_no_change' : [None, 1, 5, 10, 15, 20], # autsk: 1, 20
'validation_fraction' : [0.01, 0.03, 0.2, 0.3, 0.4] # autosk: 0.01, 0.4
}
]
#########################################################################
#===========================
# GaussianNB()
#https://github.com/automl/auto-sklearn/blob/master/autosklearn/pipeline/components/classification/gaussian_nb.py
#https://scikit-learn.org/stable/modules/generated/sklearn.naive_bayes.GaussianNB.html
#===========================
# Define estimator
estimator = GaussianNB()
# Define pipleline with steps
pipe_gnb = Pipeline([
('pre', MinMaxScaler())
, ('fs', RFECV(DecisionTreeClassifier(**rs), cv = cv, scoring = 'matthews_corrcoef'))
# , ('fs', RFECV(estimator, cv = cv, scoring = 'matthews_corrcoef'))
, ('clf', estimator)
])
# Define hyperparmeter space to search for
param_grid_gnb = [
{
'fs__min_features_to_select' : [1,2]
# , 'fs__cv': [cv]
},
{
# 'clf': [GaussianNB()],
'clf__priors': [None]
, 'clf__var_smoothing': np.logspace(0,-9, num=100)
}
]
#########################################################################
#===========================
# GaussianProcessClassifier() *
# https://scikit-learn.org/stable/modules/generated/sklearn.gaussian_process.GaussianProcessClassifier.html
#===========================
# Define estimator
estimator = GaussianProcessClassifier(**rs)
# Define pipleline with steps
pipe_gbc = Pipeline([
('pre', MinMaxScaler())
, ('fs', RFECV(DecisionTreeClassifier(**rs), cv = cv, scoring = 'matthews_corrcoef'))
# , ('fs', RFECV(estimator, cv = cv, scoring = 'matthews_corrcoef'))
, ('clf', estimator)
])
# Define hyperparmeter space to search for
param_grid_gbc = [
{
'fs__min_features_to_select' : [1,2]
# , 'fs__cv': [cv]
},
{
# 'clf': [GaussianProcessClassifier(**rs)],
'clf__kernel': [1*RBF(), 1*DotProduct(), 1*Matern(), 1*RationalQuadratic(), 1*WhiteKernel()]
}
]
#########################################################################
#===========================
# KNeighborsClassifier ()
#https://github.com/automl/auto-sklearn/blob/master/autosklearn/pipeline/components/classification/k_nearest_neighbors.py
#https://scikit-learn.org/stable/modules/generated/sklearn.neighbors.KNeighborsClassifier.html
#===========================
# Define estimator
estimator = KNeighborsClassifier(**njobs)
# Define pipleline with steps
pipe_knn = Pipeline([
('pre', MinMaxScaler())
, ('fs', RFECV(DecisionTreeClassifier(**rs), cv = cv, scoring = 'matthews_corrcoef'))
# , ('fs', RFECV(estimator, cv = cv, scoring = 'matthews_corrcoef'))
, ('clf', estimator)
])
# Define hyperparmeter space to search for
param_grid_knn = [
{
'fs__min_features_to_select' : [1,2]
# , 'fs__cv': [cv]
},
{
# 'clf': [KNeighborsClassifier(**njobs)],
#, 'clf__n_neighbors': [5, 7, 11]
#'clf__n_neighbors': list(range(21, 51, 4),)
'clf__n_neighbors' : [1, 11, 21, 51, 71, 101],
'clf__metric' : ['euclidean', 'manhattan', 'minkowski'],
'clf__weights' : ['uniform', 'distance']
}
]
#########################################################################
#===========================
# LogisticRegression () *
# https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html
#===========================
# Define estimator
estimator = LogisticRegression(**rs)
# Define pipleline with steps
pipe_lr = Pipeline([
('pre', MinMaxScaler())
, ('fs', RFECV(LogisticRegression(**rs), cv = rskf_cv, scoring = 'matthews_corrcoef'))
# , ('fs', RFECV(estimator, cv = cv, scoring = 'matthews_corrcoef'))
, ('clf', estimator)])
# Define hyperparmeter space to search for
param_grid_lr = [
{'fs__min_features_to_select' : [1,2]
# , 'fs__cv': [rskf_cv]
},
{
# 'clf': [LogisticRegression(**rs)],
'clf__C': np.logspace(0, 4, 10),
'clf__penalty': ['none', 'l1', 'l2', 'elasticnet'],
'clf__max_iter': list(range(100,800,100)),
'clf__solver': ['saga']
},
{
# 'clf': [LogisticRegression(**rs)],
'clf__C': np.logspace(0, 4, 10),
'clf__penalty': ['l2', 'none'],
'clf__max_iter': list(range(100,800,100)),
'clf__solver': ['newton-cg', 'lbfgs', 'sag']
},
{
# 'clf': [LogisticRegression(**rs)],
'clf__C': np.logspace(0, 4, 10),
'clf__penalty': ['l1', 'l2'],
'clf__max_iter': list(range(100,800,100)),
'clf__solver': ['liblinear']
}
]
#########################################################################
#===========================
# LogisticRegressionCV () *
# https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegressionCV.html
#===========================
# Define estimator
estimator = LogisticRegressionCV(cv = 10, **rs)
# Define pipleline with steps
pipe_lr = Pipeline([
('pre', MinMaxScaler())
, ('fs', RFECV(LogisticRegression(**rs), cv = rskf_cv, scoring = 'matthews_corrcoef'))
# , ('fs', RFECV(estimator, cv = cv, scoring = 'matthews_corrcoef'))
, ('clf', estimator)])
# Define hyperparmeter space to search for
param_grid_lr = [
{'fs__min_features_to_select' : [1,2]
# , 'fs__cv': [rskf_cv]
},
{
# 'clf': [LogisticRegressionCV(cv = 10, **rs)],
'clf__C': np.logspace(0, 4, 10),
'clf__penalty': ['none', 'l1', 'l2', 'elasticnet'],
'clf__max_iter': list(range(100,800,100)),
'clf__solver': ['saga']
},
{
# 'clf': [LogisticRegressionCV(cv = 10, **rs)],
'clf__C': np.logspace(0, 4, 10),
'clf__penalty': ['l2', 'none'],
'clf__max_iter': list(range(100,800,100)),
'clf__solver': ['newton-cg', 'lbfgs', 'sag']
},
{
# 'clf': [LogisticRegressionCV(cv = 10, **rs)],
'clf__C': np.logspace(0, 4, 10),
'clf__penalty': ['l1', 'l2'],
'clf__max_iter': list(range(100,800,100)),
'clf__solver': ['liblinear']
}
]
#########################################################################
#==================
# MLPClassifier()
#https://github.com/automl/auto-sklearn/blob/master/autosklearn/pipeline/components/classification/mlp.py
#https://scikit-learn.org/stable/modules/generated/sklearn.neural_network.MLPClassifier.html
#==================
# Define estimator
estimator = MLPClassifier(**rs)
# Define pipleline with steps
pipe_mlp = Pipeline([
('pre', MinMaxScaler())
, ('fs', RFECV(DecisionTreeClassifier(**rs), cv = cv, scoring = 'matthews_corrcoef'))
# , ('fs', RFECV(estimator, cv = cv, scoring = 'matthews_corrcoef'))
, ('clf', estimator)
])
param_grid_mlp = [ {
'fs__min_features_to_select' : [1,2]
# , 'fs__cv': [cv]
},
{
# 'clf': [MLPClassifier(**rs, max_iter = 1000)],
'clf__max_iter': [200, 500, 1000, 2000], # no autosklearn
'clf__hidden_layer_sizes': [(100), (1), (2), (3), (5), (10) ], #no autosklearn
'clf__solver': ['lbfgs', 'sgd', 'adam'], #no autosklearn
'clf__learning_rate': ['constant', 'invscaling', 'adaptive'] #no autosklearn
}
]
#########################################################################
#==================================
# QuadraticDiscriminantAnalysis()
https://github.com/automl/auto-sklearn/blob/master/autosklearn/pipeline/components/classification/qda.py
https://scikit-learn.org/stable/modules/generated/sklearn.discriminant_analysis.QuadraticDiscriminantAnalysis.html
#==================================
# Define estimator
estimator = QuadraticDiscriminantAnalysis(**rs)
# Define pipleline with steps
pipe_qda = Pipeline([
('pre', MinMaxScaler())
, ('fs', RFECV(DecisionTreeClassifier(**rs), cv = cv, scoring = 'matthews_corrcoef'))
# , ('fs', RFECV(estimator, cv = cv, scoring = 'matthews_corrcoef'))
, ('clf', estimator)
])
# Define hyperparmeter space to search for
param_grid_qda = [
{
'fs__min_features_to_select' : [1,2]
# , 'fs__cv': [cv]
},
{
# 'clf': [QuadraticDiscriminantAnalysis()],
'clf__priors': [None],
'clf__reg_param': [0, 1]
}
]
#########################################################################
#====================
# RidgeClassifier() *
https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.RidgeClassifier.html
#====================
# Define estimator
estimator = RidgeClassifier(**rs)
# Define pipleline with steps
pipe_rc = Pipeline([
('pre', MinMaxScaler())
, ('fs', RFECV(DecisionTreeClassifier(**rs), cv = cv, scoring = 'matthews_corrcoef'))
# , ('fs', RFECV(estimator, cv = cv, scoring = 'matthews_corrcoef'))
, ('clf', estimator)
])
param_grid_rc = [
{
'fs__min_features_to_select' : [1,2]
# , 'fs__cv': [cv]
},
{
#'clf' : [RidgeClassifier(**rs)],
'clf__alpha': [0.1, 0.2, 0.5, 0.8, 1.0]
}
]
#######################################################################
#====================
# RidgeClassifier() *
https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.RidgeClassifierCV.html
#====================
# Define estimator
estimator = RidgeClassifierCV(cv = 10, **rs)
# Define pipleline with steps
pipe_rc = Pipeline([
('pre', MinMaxScaler())
, ('fs', RFECV(DecisionTreeClassifier(**rs), cv = cv, scoring = 'matthews_corrcoef'))
# , ('fs', RFECV(estimator, cv = cv, scoring = 'matthews_corrcoef'))
, ('clf', estimator)
])
param_grid_rc = [
{
'fs__min_features_to_select' : [1,2]
# , 'fs__cv': [cv]
},
{
#'clf' : [RidgeClassifierCV(cv = 10, **rs)],
'clf__alpha': [0.1, 0.2, 0.5, 0.8, 1.0]
}
]
#######################################################################
#========
# SVC()
# https://github.com/automl/auto-sklearn/blob/master/autosklearn/pipeline/components/classification/libsvm_svc.py
# paper that supports libSVM/SVC param searching
# https://www.csie.ntu.edu.tw/~cjlin/papers/guide/guide.pdf
https://scikit-learn.org/stable/modules/generated/sklearn.svm.SVC.html
##########https://github.com/automl/auto-sklearn/blob/master/autosklearn/pipeline/components/classification/liblinear_svc.py (NOT the one used, but they are very similar!)
#========
estimator = SVC(**rs)
# Define pipleline with steps
pipe_svc = Pipeline([
('pre', MinMaxScaler())
, ('fs', RFECV(DecisionTreeClassifier(**rs), cv = cv, scoring = 'matthews_corrcoef'))
# , ('fs', RFECV(estimator, cv = cv, scoring = 'matthews_corrcoef'))
, ('clf', estimator)
])
# Define hyperparmeter space to search for
param_grid_svc = [
{
'fs__min_features_to_select' : [1,2]
# , 'fs__cv': [cv]
},
{
# 'clf': [SVC(**rs)],
# 'clf__kernel': ['poly', 'rbf', 'sigmoid']
, 'clf__kernel': ['rbf']
# , 'clf__C' : [50, 10, 1.0, 0.1, 0.01]
, 'clf__C' : [1, 0.03, 10, 100, 1000, 10000, 32768]
, 'clf__gamma' : ['scale', 'auto']
}
]
#######################################################################
#######################################################################
#========
# LDA
# https://github.com/automl/auto-sklearn/blob/master/autosklearn/pipeline/components/classification/lda.py
# https://scikit-learn.org/stable/modules/generated/sklearn.discriminant_analysis.LinearDiscriminantAnalysis.html
#========
estimator = LinearDiscriminantAnalysis()
# Define pipleline with steps
pipe_lda = Pipeline([
('pre', MinMaxScaler())
, ('fs', RFECV(DecisionTreeClassifier(**rs), cv = cv, scoring = 'matthews_corrcoef'))
# , ('fs', RFECV(estimator, cv = cv, scoring = 'matthews_corrcoef'))
, ('clf', estimator)
])
# Define hyperparmeter space to search for
param_grid_lda = [
{
'fs__min_features_to_select' : [1,2]
# , 'fs__cv': [cv]
},
{
# 'clf': [LinearDiscriminantAnalysis()],
'clf__solver' : ['svd', 'lsqr', 'eigen'],
'clf__shrinkage' : [None, 'auto', 0, 0.5, 1],
}
]
#######################################################################
#========
# Multinomial_nb
# https://github.com/automl/auto-sklearn/blob/master/autosklearn/pipeline/components/classification/multinomial_nb.py
# https://scikit-learn.org/stable/modules/generated/sklearn.naive_bayes.MultinomialNB.html
#========
estimator = MultinomialNB()
# Define pipleline with steps
pipe_mnb = Pipeline([
('pre', MinMaxScaler())
, ('fs', RFECV(DecisionTreeClassifier(), cv = cv, scoring = 'matthews_corrcoef'))
# , ('fs', RFECV(estimator, cv = cv, scoring = 'matthews_corrcoef'))
, ('clf', estimator)
])
# Define hyperparmeter space to search for
param_grid_mnb = [
{
'fs__min_features_to_select' : [1,2]
# , 'fs__cv': [cv]
},
{
# 'clf': [MultinomialNB()],
'clf__alpha': [0.01, 0.1, 1, 20, 25, 50, 55, 100]
}
]
#######################################################################
#========
# passive_aggressive
# https://github.com/automl/auto-sklearn/blob/master/autosklearn/pipeline/components/classification/passive_aggressive.py
# https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.PassiveAggressiveClassifier.html
#========
estimator = PassiveAggressiveClassifier(**rs, **njobs)
# Define pipleline with steps
pipe_pa = Pipeline([
('pre', MinMaxScaler())
, ('fs', RFECV(DecisionTreeClassifier(**rs), cv = cv, scoring = 'matthews_corrcoef'))
# , ('fs', RFECV(estimator, cv = cv, scoring = 'matthews_corrcoef'))
, ('clf', estimator)
])
# Define hyperparmeter space to search for
param_grid_pa = [
{
'fs__min_features_to_select' : [1,2]
# , 'fs__cv': [cv]
},
{
# 'clf': [PassiveAggressiveClassifier(**rs, **njobs)],
'clf__C' : [1, 0.03, 10, 100, 1000, 10000, 32768],
'clf__maxt_iter' : [1000, 500, 200, 100, 50, 10, 1],
'clf__loss' : ['hinge', 'squared_hinge'],
'clf_tol' : [1e-4, 1e-5, 1e-2, 1e-1]
}
]
#######################################################################
#========
# SGD
# https://github.com/automl/auto-sklearn/blob/master/autosklearn/pipeline/components/classification/sgd.py
# https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.SGDClassifier.html
#========
estimator = SGDClassifier(**rs, **njobs)
# Define pipleline with steps
pipe_sgd = Pipeline([
('pre', MinMaxScaler())
, ('fs', RFECV(DecisionTreeClassifier(**rs), cv = cv, scoring = 'matthews_corrcoef'))
# , ('fs', RFECV(estimator, cv = cv, scoring = 'matthews_corrcoef'))
, ('clf', estimator)
])
# Define hyperparmeter space to search for
param_grid_sgd = [
{
'fs__min_features_to_select' : [1,2]
# , 'fs__cv': [cv]
},
{
# 'clf': [SGDClassifier(**rs, **njobs)],
'clf__loss': = ['hinge', 'log', 'modified_huber', 'squared_hinge', 'perceptron'],
'clf__penalty':['l1', 'l2', 'elasticnet'],
'clf__alpha': [0.0000001, 0.00001, 0.0001, 0.01, 0.1, 1, 10, 100], #autosk learn: 1e-7, 1e-1, log=True, default_value=0.0001
'clf__learning_rate': ['constant', 'optimal', 'invscaling', 'adaptive'],
'clf__eta0' : [0.0000001, 0.00001, 0.0001, 0.01] # autosklearn 1e-7, 1e-1, default_value=0.01, log=True
}
]
Reference in a new issue View git blame Copy permalink