saving work
This commit is contained in:
parent
7b378ca6f3
commit
137f19a285
5 changed files with 1289 additions and 1102 deletions
|
|
@ -41,6 +41,9 @@ from sklearn.compose import make_column_transformer
|
|||
from sklearn.metrics import make_scorer, confusion_matrix, accuracy_score, balanced_accuracy_score, precision_score, average_precision_score, recall_score
|
||||
from sklearn.metrics import roc_auc_score, roc_curve, f1_score, matthews_corrcoef, jaccard_score, classification_report
|
||||
|
||||
# added
|
||||
from sklearn.model_selection import train_test_split, cross_validate, cross_val_score, LeaveOneOut, KFold, RepeatedKFold, cross_val_predict
|
||||
|
||||
from sklearn.model_selection import train_test_split, cross_validate, cross_val_score
|
||||
from sklearn.model_selection import StratifiedKFold,RepeatedStratifiedKFold, RepeatedKFold
|
||||
|
||||
|
|
@ -69,18 +72,20 @@ from sklearn.model_selection import GridSearchCV
|
|||
from sklearn.base import BaseEstimator
|
||||
from sklearn.impute import KNNImputer as KNN
|
||||
import json
|
||||
import argparse
|
||||
import re
|
||||
|
||||
#%% GLOBALS
|
||||
rs = {'random_state': 42}
|
||||
njobs = {'n_jobs': 10}
|
||||
|
||||
scoring_fn = ({ 'mcc' : make_scorer(matthews_corrcoef)
|
||||
, 'fscore' : make_scorer(f1_score)
|
||||
, 'precision' : make_scorer(precision_score)
|
||||
, 'recall' : make_scorer(recall_score)
|
||||
, 'accuracy' : make_scorer(accuracy_score)
|
||||
, 'roc_auc' : make_scorer(roc_auc_score)
|
||||
, 'jcc' : make_scorer(jaccard_score)
|
||||
scoring_fn = ({ 'mcc' : make_scorer(matthews_corrcoef)
|
||||
, 'fscore' : make_scorer(f1_score)
|
||||
, 'precision' : make_scorer(precision_score)
|
||||
, 'recall' : make_scorer(recall_score)
|
||||
, 'accuracy' : make_scorer(accuracy_score)
|
||||
, 'roc_auc' : make_scorer(roc_auc_score)
|
||||
, 'jcc' : make_scorer(jaccard_score)
|
||||
})
|
||||
|
||||
skf_cv = StratifiedKFold(n_splits = 10
|
||||
|
|
@ -98,6 +103,8 @@ jacc_score_fn = {'jcc': make_scorer(jaccard_score)}
|
|||
def MultModelsCl(input_df, target, skf_cv
|
||||
, blind_test_input_df
|
||||
, blind_test_target
|
||||
, add_cm = True # adds confusion matrix based on cross_val_predict
|
||||
, add_yn = True # adds target var class numbers
|
||||
, var_type = ['numerical', 'categorical','mixed']):
|
||||
|
||||
'''
|
||||
|
|
@ -116,14 +123,18 @@ def MultModelsCl(input_df, target, skf_cv
|
|||
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
|
||||
categorical_ix = input_df.select_dtypes(include=['object', 'bool']).columns
|
||||
categorical_ix
|
||||
|
||||
#======================================================
|
||||
# Determine preprocessing steps ~ var_type
|
||||
#======================================================
|
||||
if var_type == 'numerical':
|
||||
t = [('num', MinMaxScaler(), numerical_ix)]
|
||||
|
||||
|
|
@ -138,42 +149,42 @@ def MultModelsCl(input_df, target, skf_cv
|
|||
, remainder='passthrough')
|
||||
|
||||
#======================================================
|
||||
# Specify multiple Classification models
|
||||
# Specify multiple Classification Models
|
||||
#======================================================
|
||||
models = [('Logistic Regression' , LogisticRegression(**rs) )
|
||||
, ('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 = {}
|
||||
|
||||
|
||||
print('\n==============================================================\n'
|
||||
, '\nRunning several classification models (n):', len(models)
|
||||
,'\nList of models:')
|
||||
|
|
@ -198,8 +209,74 @@ def MultModelsCl(input_df, target, skf_cv
|
|||
, target
|
||||
, cv = skf_cv
|
||||
, scoring = scoring_fn
|
||||
, return_train_score = True)
|
||||
, return_train_score = True)
|
||||
|
||||
#######################################################################
|
||||
#======================================================
|
||||
# Option: Add confusion matrix from cross_val_predict
|
||||
# Understand and USE with caution
|
||||
# cross_val_score, cross_val_predict, "Passing these predictions into an evaluation metric may not be a valid way to measure generalization performance. Results can differ from cross_validate and cross_val_score unless all tests sets have equal size and the metric decomposes over samples."
|
||||
# https://stackoverflow.com/questions/65645125/producing-a-confusion-matrix-with-cross-validate
|
||||
#======================================================
|
||||
if add_cm:
|
||||
|
||||
#-----------------------------------------------------------
|
||||
# Initialise dict of Confusion Matrix (cm)
|
||||
#-----------------------------------------------------------
|
||||
cmD = {}
|
||||
|
||||
# Calculate cm
|
||||
y_pred = cross_val_predict(model_pipeline, input_df, target, cv = skf_cv, **njobs)
|
||||
#_tn, _fp, _fn, _tp = confusion_matrix(y_pred, y).ravel() # internally
|
||||
tn, fp, fn, tp = confusion_matrix(y_pred, target).ravel()
|
||||
|
||||
# Build dict
|
||||
|
||||
cmD = {'TN' : tn
|
||||
, 'FP': fp
|
||||
, 'FN': fn
|
||||
, 'TP': tp}
|
||||
#---------------------------------
|
||||
# Update cv dict with cmD and tbtD
|
||||
#----------------------------------
|
||||
skf_cv_modD.update(cmD)
|
||||
else:
|
||||
skf_cv_modD = skf_cv_modD
|
||||
#######################################################################
|
||||
#=============================================
|
||||
# Option: Add targety numbers for data
|
||||
#=============================================
|
||||
if add_yn:
|
||||
|
||||
#-----------------------------------------------------------
|
||||
# Initialise dict of target numbers: training and blind (tbt)
|
||||
#-----------------------------------------------------------
|
||||
tbtD = {}
|
||||
|
||||
# training y
|
||||
tyn = Counter(target)
|
||||
tyn_neg = tyn[0]
|
||||
tyn_pos = tyn[1]
|
||||
|
||||
# blind test y
|
||||
btyn = Counter(blind_test_target)
|
||||
btyn_neg = btyn[0]
|
||||
btyn_pos = btyn[1]
|
||||
|
||||
# Build dict
|
||||
tbtD = {'trainingY_neg' : tyn_neg
|
||||
, 'trainingY_pos' : tyn_pos
|
||||
, 'blindY_neg' : btyn_neg
|
||||
, 'blindY_pos' : btyn_pos}
|
||||
|
||||
#---------------------------------
|
||||
# Update cv dict with cmD and tbtD
|
||||
#----------------------------------
|
||||
skf_cv_modD.update(tbtD)
|
||||
else:
|
||||
skf_cv_modD = skf_cv_modD
|
||||
|
||||
#######################################################################
|
||||
#==============================
|
||||
# Extract mean values for CV
|
||||
#==============================
|
||||
|
|
@ -207,15 +284,15 @@ def MultModelsCl(input_df, target, skf_cv
|
|||
|
||||
for key, value in skf_cv_modD.items():
|
||||
print('\nkey:', key, '\nvalue:', value)
|
||||
print('\nmean value:', mean(value))
|
||||
mm_skf_scoresD[model_name][key] = round(mean(value),2)
|
||||
|
||||
print('\nmean value:', np.mean(value))
|
||||
mm_skf_scoresD[model_name][key] = round(np.mean(value),2)
|
||||
|
||||
#return(mm_skf_scoresD)
|
||||
#%%
|
||||
#=========================
|
||||
# Blind test: BTS results
|
||||
#=========================
|
||||
# Build the final results with all scores for a feature selected model
|
||||
# Build the final results with all scores for the model
|
||||
#bts_predict = gscv_fs.predict(blind_test_input_df)
|
||||
model_pipeline.fit(input_df, target)
|
||||
bts_predict = model_pipeline.predict(blind_test_input_df)
|
||||
|
|
@ -225,28 +302,16 @@ def MultModelsCl(input_df, target, skf_cv
|
|||
print('\nAccuracy on Blind test:', round(accuracy_score(blind_test_target, bts_predict),2))
|
||||
|
||||
# Diff b/w train and bts test scores
|
||||
#train_test_diff_MCC = cvtrain_mcc - bts_mcc_score
|
||||
# train_test_diff_MCC = cvtrain_mcc - bts_mcc_score
|
||||
# print('\nDiff b/w train and blind test score (MCC):', train_test_diff)
|
||||
|
||||
|
||||
# # create a dict with all scores
|
||||
# lr_btsD = { 'model_name': model_name
|
||||
# , 'bts_mcc':None
|
||||
# , 'bts_fscore':None
|
||||
# , 'bts_precision':None
|
||||
# , 'bts_recall':None
|
||||
# , 'bts_accuracy':None
|
||||
# , 'bts_roc_auc':None
|
||||
# , 'bts_jaccard':None}
|
||||
|
||||
|
||||
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)
|
||||
mm_skf_scoresD[model_name]['bts_recall'] = round(recall_score(blind_test_target, bts_predict),2)
|
||||
mm_skf_scoresD[model_name]['bts_accuracy'] = round(accuracy_score(blind_test_target, bts_predict),2)
|
||||
mm_skf_scoresD[model_name]['bts_roc_auc'] = round(roc_auc_score(blind_test_target, bts_predict),2)
|
||||
mm_skf_scoresD[model_name]['bts_jaccard'] = round(jaccard_score(blind_test_target, bts_predict),2)
|
||||
mm_skf_scoresD[model_name]['bts_jcc'] = round(jaccard_score(blind_test_target, bts_predict),2)
|
||||
#mm_skf_scoresD[model_name]['diff_mcc'] = train_test_diff_MCC
|
||||
|
||||
return(mm_skf_scoresD)
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue