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

added different scaling options

Browse source
This commit is contained in:
Tanushree Tunstall 2022-07-05 22:47:13 +01:00
parent ebef0c7967
commit 8d831f3613
3 changed files with 99 additions and 31 deletions
Download patch file Download diff file Expand all files Collapse all files

74
scripts/ml/ml_functions/MultClfs.py
View file

@ -142,7 +142,9 @@ scoreBT_mapD = {'bts_mcc' : 'MCC'
# Run Multiple Classifiers
############################
# Multiple Classification - Model Pipeline
def MultModelsCl(input_df, target, skf_cv
def MultModelsCl(input_df, target
#, skf_cv
, sel_cv
, blind_test_df
, blind_test_target
, tts_split_type
@ -150,7 +152,8 @@ def MultModelsCl(input_df, target, skf_cv
, resampling_type = 'none' # default
, add_cm = True # adds confusion matrix based on cross_val_predict
, add_yn = True # adds target var class numbers
, var_type = ['numerical', 'categorical','mixed']
, var_type = ['numerical', 'categorical','mixed']
, scale_numeric = ['min_max', 'std', 'min_max_neg', 'none']
, run_blind_test = True
, return_formatted_output = True):
@ -182,24 +185,52 @@ def MultModelsCl(input_df, target, skf_cv
#======================================================
# Determine preprocessing steps ~ var_type
#======================================================
if var_type == 'numerical':
t = [('num', MinMaxScaler(), numerical_ix)]
# if var_type == 'numerical':
# t = [('num', MinMaxScaler(), numerical_ix)]
# if var_type == 'categorical':
# t = [('cat', OneHotEncoder(), categorical_ix)]
# # if var_type == 'mixed':
# # t = [('num', MinMaxScaler(), numerical_ix)
# # , ('cat', OneHotEncoder(), categorical_ix) ]
# if var_type == 'mixed':
# t = [('cat', OneHotEncoder(), categorical_ix) ]
if type(var_type) == list:
var_type = str(var_type[0])
else:
var_type = var_type
if var_type in ['numerical','mixed']:
if scale_numeric == ['none']:
t = [('cat', OneHotEncoder(), categorical_ix)]
if scale_numeric != ['none']:
if scale_numeric == ['min_max']:
scaler = MinMaxScaler()
if scale_numeric == ['min_max_neg']:
scaler = MinMaxScaler(feature_range=(-1, 1))
if scale_numeric == ['std']:
scaler = StandardScaler()
t = [('num', scaler, numerical_ix)
, ('cat', OneHotEncoder(), categorical_ix)]
if var_type == 'categorical':
t = [('cat', OneHotEncoder(), categorical_ix)]
if var_type == 'mixed':
t = [('num', MinMaxScaler(), numerical_ix)
, ('cat', OneHotEncoder(), categorical_ix) ]
col_transform = ColumnTransformer(transformers = t
, remainder='passthrough')
#======================================================
# Specify multiple Classification Models
#======================================================
models = [('AdaBoost Classifier' , AdaBoostClassifier(**rs) )
, ('Bagging Classifier' , BaggingClassifier(**rs, **njobs, bootstrap = True, oob_score = True) )
, ('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) )
@ -211,18 +242,18 @@ def MultModelsCl(input_df, target, skf_cv
, ('Logistic Regression' , LogisticRegression(**rs) )
, ('Logistic RegressionCV' , LogisticRegressionCV(cv = 3, **rs))
, ('MLP' , MLPClassifier(max_iter = 500, **rs) )
, ('Multinomial' , MultinomialNB() )
#, ('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') )
# , ('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) )
@ -254,7 +285,7 @@ def MultModelsCl(input_df, target, skf_cv
skf_cv_modD = cross_validate(model_pipeline
, input_df
, target
, cv = skf_cv
, cv = sel_cv
, scoring = scoring_fn
, return_train_score = True)
#==============================
@ -283,7 +314,7 @@ def MultModelsCl(input_df, target, skf_cv
cmD = {}
# Calculate cm
y_pred = cross_val_predict(model_pipeline, input_df, target, cv = skf_cv, **njobs)
y_pred = cross_val_predict(model_pipeline, input_df, target, cv = sel_cv, **njobs)
#_tn, _fp, _fn, _tp = confusion_matrix(y_pred, y).ravel() # internally
tn, fp, fn, tp = confusion_matrix(y_pred, target).ravel()
@ -334,8 +365,9 @@ def MultModelsCl(input_df, target, skf_cv
bts_mcc_score = round(matthews_corrcoef(blind_test_target, bts_predict),2)
print('\nMCC on Blind test:' , bts_mcc_score)
print('\nAccuracy on Blind test:', round(accuracy_score(blind_test_target, bts_predict),2))
#print('\nAccuracy on Blind test:', round(accuracy_score(blind_test_target, bts_predict),2))
print('\nMCC on Training:' , mm_skf_scoresD[model_name]['test_mcc'] )
mm_skf_scoresD[model_name]['bts_mcc'] = bts_mcc_score
mm_skf_scoresD[model_name]['bts_fscore'] = round(f1_score(blind_test_target, bts_predict),2)
mm_skf_scoresD[model_name]['bts_precision'] = round(precision_score(blind_test_target, bts_predict),2)