tanu/LSHTM_analysis
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

minor var bame update in ml_iterator

Browse source
This commit is contained in:
Tanushree Tunstall 2022-07-09 10:52:50 +01:00
parent 8079dd7b6c
commit 8bde6f0640
3 changed files with 39 additions and 37 deletions
Download patch file Download diff file Expand all files Collapse all files

59
scripts/ml/ml_functions/MultClfs_SIMPLE.py
View file

@ -144,10 +144,9 @@ scoreBT_mapD = {'bts_mcc' : 'MCC'
############################
# Multiple Classification - Model Pipeline
def MultModelsCl(input_df, target
#, skf_cv
, sel_cv
#, blind_test_df
#, blind_test_target
, blind_test_df
, blind_test_target
, tts_split_type
, resampling_type = 'none' # default
@ -230,37 +229,37 @@ def MultModelsCl(input_df, target
#======================================================
# Specify multiple Classification Models
#======================================================
models = [('AdaBoost Classifier' , AdaBoostClassifier(**rs) )
# , ('Bagging Classifier' , BaggingClassifier(**rs, **njobs, bootstrap = True, oob_score = True, verbose = 3, n_estimators = 100) )
# , ('Decision Tree' , DecisionTreeClassifier(**rs) )
# , ('Extra Tree' , ExtraTreeClassifier(**rs) )
# , ('Extra Trees' , ExtraTreesClassifier(**rs) )
# , ('Gradient Boosting' , GradientBoostingClassifier(**rs) )
# , ('Gaussian NB' , GaussianNB() )
# , ('Gaussian Process' , GaussianProcessClassifier(**rs) )
# , ('K-Nearest Neighbors' , KNeighborsClassifier() )
models = [('AdaBoost Classifier' , AdaBoostClassifier(**rs) )
, ('Bagging Classifier' , BaggingClassifier(**rs, **njobs, bootstrap = True, oob_score = True, verbose = 3, n_estimators = 100) )
, ('Decision Tree' , DecisionTreeClassifier(**rs) )
, ('Extra Tree' , ExtraTreeClassifier(**rs) )
, ('Extra Trees' , ExtraTreesClassifier(**rs) )
, ('Gradient Boosting' , GradientBoostingClassifier(**rs) )
, ('Gaussian NB' , GaussianNB() )
, ('Gaussian Process' , GaussianProcessClassifier(**rs) )
, ('K-Nearest Neighbors' , KNeighborsClassifier() )
, ('LDA' , LinearDiscriminantAnalysis() )
, ('Logistic Regression' , LogisticRegression(**rs) )
# , ('Logistic RegressionCV' , LogisticRegressionCV(cv = 3, **rs))
# , ('MLP' , MLPClassifier(max_iter = 500, **rs) )
#, ('Multinomial' , MultinomialNB() )
# , ('Naive Bayes' , BernoulliNB() )
# , ('Passive Aggresive' , PassiveAggressiveClassifier(**rs, **njobs) )
# , ('QDA' , QuadraticDiscriminantAnalysis() )
, ('Logistic RegressionCV' , LogisticRegressionCV(cv = 3, **rs))
, ('MLP' , MLPClassifier(max_iter = 500, **rs) )
, ('Multinomial' , MultinomialNB() )
, ('Naive Bayes' , BernoulliNB() )
, ('Passive Aggresive' , PassiveAggressiveClassifier(**rs, **njobs) )
, ('QDA' , QuadraticDiscriminantAnalysis() )
# , ('Random Forest' , RandomForestClassifier(**rs, n_estimators = 1000, **njobs ) )
# # , ('Random Forest2' , RandomForestClassifier(min_samples_leaf = 5
# , n_estimators = 1000
# , bootstrap = True
# , oob_score = True
# , **njobs
# , **rs
# , max_features = 'auto') )
# , ('Ridge Classifier' , RidgeClassifier(**rs) )
# , ('Ridge ClassifierCV' , RidgeClassifierCV(cv = 3) )
# , ('SVC' , SVC(**rs) )
# , ('Stochastic GDescent' , SGDClassifier(**rs, **njobs) )
, ('Random Forest2' , RandomForestClassifier(min_samples_leaf = 5
, n_estimators = 1000
, bootstrap = True
, oob_score = True
, **njobs
, **rs
, max_features = 'auto') )
, ('Ridge Classifier' , RidgeClassifier(**rs) )
, ('Ridge ClassifierCV' , RidgeClassifierCV(cv = 3) )
, ('SVC' , SVC(**rs) )
, ('Stochastic GDescent' , SGDClassifier(**rs, **njobs) )
, ('XGBoost' , XGBClassifier(**rs, verbosity = 0, use_label_encoder =False, **njobs) )
#
]
mm_skf_scoresD = {}

13
scripts/ml/ml_functions/test_func_singlegene.py
View file

@ -45,10 +45,13 @@ spl_type = '70_30'
#spl_type = '80_20'
#spl_type = 'sl'
#data_type = "actual"
data_type = "complete"
df2 = split_tts(df
, data_type = 'actual'
, data_type = data_type
, split_type = spl_type
, oversampling = False
, oversampling = True
, dst_colname = 'dst'
, target_colname = 'dst_mode'
, include_gene_name = True
@ -67,8 +70,8 @@ Counter(df2['y'])
Counter(df2['y_bts'])
fooD = MultModelsCl(input_df = df2['X']
, target = df2['y']
fooD = MultModelsCl(input_df = df2['X_ros']
, target = df2['y_ros']
, sel_cv = skf_cv
, run_blind_test = True
, blind_test_df = df2['X_bts']
@ -83,7 +86,7 @@ fooD = MultModelsCl(input_df = df2['X']
for k, v in fooD.items():
print('\nModel:', k
, '\nTRAIN MCC:', fooD[k]['test_mcc']
, '\nBTS MCC:' , fooD[k]['bts_mcc']
, '\nBTS MCC:' , fooD[k]['bts_mcc']
, '\nDIFF:',fooD[k]['bts_mcc'] - fooD[k]['test_mcc'] )
#%% CHECK SCALING