modified loopity and multclass3 to have skf_cv as a parameters for cv
This commit is contained in:
parent
97620c1bb0
commit
d0c329a1d9
8 changed files with 161 additions and 127 deletions
|
|
@ -61,23 +61,39 @@ from imblearn.combine import SMOTEENN
|
|||
from imblearn.under_sampling import EditedNearestNeighbours
|
||||
|
||||
#%%
|
||||
rs = {'random_state': 42}
|
||||
# Done: add preprocessing step with one hot encoder
|
||||
# Done: get accuracy and other scores through K-fold stratified cv
|
||||
# rs = {'random_state': 42}
|
||||
# njobs = {'n_jobs': 10}
|
||||
|
||||
scoring_fn = ({ 'fscore' : make_scorer(f1_score)
|
||||
, 'mcc' : make_scorer(matthews_corrcoef)
|
||||
, 'precision' : make_scorer(precision_score)
|
||||
, 'recall' : make_scorer(recall_score)
|
||||
, 'accuracy' : make_scorer(accuracy_score)
|
||||
, 'roc_auc' : make_scorer(roc_auc_score)
|
||||
#, 'jaccard' : make_scorer(jaccard_score)
|
||||
scoring_fn = ({ 'fscore' : make_scorer(f1_score)
|
||||
, 'mcc' : make_scorer(matthews_corrcoef)
|
||||
, 'precision' : make_scorer(precision_score)
|
||||
, 'recall' : make_scorer(recall_score)
|
||||
, 'accuracy' : make_scorer(accuracy_score)
|
||||
, 'roc_auc' : make_scorer(roc_auc_score)
|
||||
#, 'jaccard' : make_scorer(jaccard_score)
|
||||
})
|
||||
|
||||
|
||||
# Multiple Classification - Model Pipeline
|
||||
def MultClassPipelineCV(X_train, X_test, y_train, y_test, input_df, var_type = ['numerical', 'categorical','mixed']):
|
||||
def MultClassPipeSKFCV(input_df, target, skf_cv, var_type = ['numerical', 'categorical','mixed']):
|
||||
|
||||
'''
|
||||
@ param input_df: input features
|
||||
@ type: df with input features WITHOUT the target variable
|
||||
|
||||
@param target: target (or output) feature
|
||||
@type: df or np.array or Series
|
||||
|
||||
@param skv_cv: stratifiedK fold int or object to allow shuffle and random state to pass
|
||||
@type: int or StratifiedKfold()
|
||||
|
||||
@var_type: numerical, categorical and mixed to determine what col_transform to apply (MinMaxScalar and/or one-ho t encoder)
|
||||
@type: list
|
||||
|
||||
returns
|
||||
Dict containing multiple classification scores for each model and mean of each Stratified Kfold including training
|
||||
|
||||
'''
|
||||
# determine categorical and numerical features
|
||||
numerical_ix = input_df.select_dtypes(include=['int64', 'float64']).columns
|
||||
numerical_ix
|
||||
|
|
@ -98,66 +114,61 @@ def MultClassPipelineCV(X_train, X_test, y_train, y_test, input_df, var_type = [
|
|||
col_transform = ColumnTransformer(transformers = t
|
||||
, remainder='passthrough')
|
||||
|
||||
#%%
|
||||
#%% Specify multiple Classification models
|
||||
log_reg = LogisticRegression(**rs)
|
||||
nb = BernoulliNB()
|
||||
knn = KNeighborsClassifier()
|
||||
svm = SVC(**rs)
|
||||
mlp = MLPClassifier(max_iter=500, **rs)
|
||||
dt = DecisionTreeClassifier(**rs)
|
||||
et = ExtraTreesClassifier(**rs)
|
||||
rf = RandomForestClassifier(**rs)
|
||||
rf2 = RandomForestClassifier(
|
||||
min_samples_leaf=50,
|
||||
n_estimators=150,
|
||||
bootstrap=True,
|
||||
oob_score=True,
|
||||
n_jobs=-1,
|
||||
random_state=42,
|
||||
max_features='auto')
|
||||
|
||||
xgb = XGBClassifier(**rs, verbosity=0)
|
||||
nb = BernoulliNB()
|
||||
knn = KNeighborsClassifier()
|
||||
svm = SVC(**rs)
|
||||
mlp = MLPClassifier(max_iter = 500, **rs)
|
||||
dt = DecisionTreeClassifier(**rs)
|
||||
et = ExtraTreesClassifier(**rs)
|
||||
rf = RandomForestClassifier(**rs)
|
||||
rf2 = RandomForestClassifier(
|
||||
min_samples_leaf = 50
|
||||
, n_estimators = 150
|
||||
, bootstrap = True
|
||||
, oob_score = True
|
||||
, **njobs
|
||||
, **rs
|
||||
, max_features = 'auto')
|
||||
xgb = XGBClassifier(**rs
|
||||
, verbosity = 0, use_label_encoder =False)
|
||||
|
||||
models = [
|
||||
('Logistic Regression', log_reg),
|
||||
('Naive Bayes', nb),
|
||||
('K-Nearest Neighbors', knn),
|
||||
('SVM', svm),
|
||||
('MLP', mlp),
|
||||
('Decision Tree', dt),
|
||||
('Extra Trees', et),
|
||||
('Random Forest', rf),
|
||||
('Random Forest2', rf2),
|
||||
#('XGBoost', xgb)
|
||||
]
|
||||
|
||||
skf_cv_scores = {}
|
||||
models = [('Logistic Regression', log_reg)
|
||||
, ('Naive Bayes' , nb)
|
||||
, ('K-Nearest Neighbors', knn)
|
||||
, ('SVM' , svm)
|
||||
, ('MLP' , mlp)
|
||||
, ('Decision Tree' , dt)
|
||||
, ('Extra Trees' , et)
|
||||
, ('Random Forest' , rf)
|
||||
, ('Naive Bayes' , nb)
|
||||
, ('Random Forest2' , rf2)
|
||||
, ('XGBoost' , xgb)]
|
||||
|
||||
mm_skf_scoresD = {}
|
||||
|
||||
for model_name, model_fn in models:
|
||||
print('\nModel_name:', model_name
|
||||
, '\nModel func:' , model_fn
|
||||
, '\nList of models:', models)
|
||||
|
||||
# model_pipeline = Pipeline([
|
||||
# ('pre' , MinMaxScaler())
|
||||
# , ('model' , model_fn)])
|
||||
|
||||
model_pipeline = Pipeline([
|
||||
('prep' , col_transform)
|
||||
, ('model' , model_fn)])
|
||||
, ('model' , model_fn)])
|
||||
|
||||
print('Running model pipeline:', model_pipeline)
|
||||
skf_cv = cross_validate(model_pipeline
|
||||
, X_train
|
||||
, y_train
|
||||
, cv = 10
|
||||
skf_cv_mod = cross_validate(model_pipeline
|
||||
, input_df
|
||||
, target
|
||||
, cv = skf_cv
|
||||
, scoring = scoring_fn
|
||||
, return_train_score = True)
|
||||
skf_cv_scores[model_name] = {}
|
||||
for key, value in skf_cv.items():
|
||||
mm_skf_scoresD[model_name] = {}
|
||||
for key, value in skf_cv_mod.items():
|
||||
print('\nkey:', key, '\nvalue:', value)
|
||||
print('\nmean value:', mean(value))
|
||||
skf_cv_scores[model_name][key] = round(mean(value),2)
|
||||
#pp.pprint(skf_cv_scores)
|
||||
return(skf_cv_scores)
|
||||
mm_skf_scoresD[model_name][key] = round(mean(value),2)
|
||||
#pp.pprint(mm_skf_scoresD)
|
||||
return(mm_skf_scoresD)
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue