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

changed blind_test_input_df to blind_test_df in MultModelsCl

Browse source
This commit is contained in:
Tanushree Tunstall 2022-06-22 16:42:04 +01:00
parent bc12dbd7c2
commit 0350784d52
114 changed files with 107251 additions and 863011 deletions
Download patch file Download diff file Expand all files Collapse all files

58
scripts/ml/MultModelsCl.py
View file

@ -101,7 +101,7 @@ jacc_score_fn = {'jcc': make_scorer(jaccard_score)}
#%%
# Multiple Classification - Model Pipeline
def MultModelsCl(input_df, target, skf_cv
, blind_test_input_df
, blind_test_df
, blind_test_target
, add_cm = True # adds confusion matrix based on cross_val_predict
, add_yn = True # adds target var class numbers
@ -155,32 +155,32 @@ def MultModelsCl(input_df, target, skf_cv
, ('Logistic RegressionCV' , LogisticRegressionCV(**rs) )
, ('Gaussian NB' , GaussianNB() )
, ('Naive Bayes' , BernoulliNB() )
# , ('K-Nearest Neighbors' , KNeighborsClassifier() )
# , ('SVC' , SVC(**rs) )
# , ('MLP' , MLPClassifier(max_iter = 500, **rs) )
# , ('Decision Tree' , DecisionTreeClassifier(**rs) )
# , ('Extra Trees' , ExtraTreesClassifier(**rs) )
# , ('Extra Tree' , ExtraTreeClassifier(**rs) )
# , ('Random Forest' , RandomForestClassifier(**rs, n_estimators = 1000 ) )
# , ('Random Forest2' , RandomForestClassifier(min_samples_leaf = 5
# , n_estimators = 1000
# , bootstrap = True
# , oob_score = True
# , **njobs
# , **rs
# , max_features = 'auto') )
# , ('XGBoost' , XGBClassifier(**rs, verbosity = 0, use_label_encoder =False) )
# , ('LDA' , LinearDiscriminantAnalysis() )
# , ('Multinomial' , MultinomialNB() )
# , ('Passive Aggresive' , PassiveAggressiveClassifier(**rs, **njobs) )
# , ('Stochastic GDescent' , SGDClassifier(**rs, **njobs) )
# , ('AdaBoost Classifier' , AdaBoostClassifier(**rs) )
# , ('Bagging Classifier' , BaggingClassifier(**rs, **njobs, bootstrap = True, oob_score = True) )
# , ('Gaussian Process' , GaussianProcessClassifier(**rs) )
# , ('Gradient Boosting' , GradientBoostingClassifier(**rs) )
# , ('QDA' , QuadraticDiscriminantAnalysis() )
# , ('Ridge Classifier' , RidgeClassifier(**rs) )
# , ('Ridge ClassifierCV' , RidgeClassifierCV(cv = 10) )
, ('K-Nearest Neighbors' , KNeighborsClassifier() )
, ('SVC' , SVC(**rs) )
, ('MLP' , MLPClassifier(max_iter = 500, **rs) )
, ('Decision Tree' , DecisionTreeClassifier(**rs) )
, ('Extra Trees' , ExtraTreesClassifier(**rs) )
, ('Extra Tree' , ExtraTreeClassifier(**rs) )
, ('Random Forest' , RandomForestClassifier(**rs, n_estimators = 1000 ) )
, ('Random Forest2' , RandomForestClassifier(min_samples_leaf = 5
, n_estimators = 1000
, bootstrap = True
, oob_score = True
, **njobs
, **rs
, max_features = 'auto') )
, ('XGBoost' , XGBClassifier(**rs, verbosity = 0, use_label_encoder =False) )
, ('LDA' , LinearDiscriminantAnalysis() )
, ('Multinomial' , MultinomialNB() )
, ('Passive Aggresive' , PassiveAggressiveClassifier(**rs, **njobs) )
, ('Stochastic GDescent' , SGDClassifier(**rs, **njobs) )
, ('AdaBoost Classifier' , AdaBoostClassifier(**rs) )
, ('Bagging Classifier' , BaggingClassifier(**rs, **njobs, bootstrap = True, oob_score = True) )
, ('Gaussian Process' , GaussianProcessClassifier(**rs) )
, ('Gradient Boosting' , GradientBoostingClassifier(**rs) )
, ('QDA' , QuadraticDiscriminantAnalysis() )
, ('Ridge Classifier' , RidgeClassifier(**rs) )
, ('Ridge ClassifierCV' , RidgeClassifierCV(cv = 10) )
]
mm_skf_scoresD = {}
@ -293,9 +293,9 @@ def MultModelsCl(input_df, target, skf_cv
# Blind test: BTS results
#=========================
# Build the final results with all scores for the model
#bts_predict = gscv_fs.predict(blind_test_input_df)
#bts_predict = gscv_fs.predict(blind_test_df)
model_pipeline.fit(input_df, target)
bts_predict = model_pipeline.predict(blind_test_input_df)
bts_predict = model_pipeline.predict(blind_test_df)
bts_mcc_score = round(matthews_corrcoef(blind_test_target, bts_predict),2)
print('\nMCC on Blind test:' , bts_mcc_score)