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

modified loopity and multclass3 to have skf_cv as a parameters for cv

Browse source
This commit is contained in:
Tanushree Tunstall 2022-03-17 18:17:58 +00:00
parent 97620c1bb0
commit d0c329a1d9
8 changed files with 161 additions and 127 deletions
Download patch file Download diff file Expand all files Collapse all files

57
loopity_loop.py
View file

@ -33,23 +33,30 @@ from sklearn.metrics import roc_auc_score, roc_curve, f1_score, matthews_corrcoe
from statistics import mean, stdev, median, mode
#%%
rs = {'random_state': 42}
njobs = {'n_jobs': 10}
# Done: add preprocessing step with one hot encoder
# TODO: supply stratified K-fold cv train and test data
# TODO: supply stratified K-fold cv train and test dataskf
# TODO: get accuracy and other scores through K-fold cv
# Multiple Classification - Model Pipeline
def MultClassPipeSKF(input_df, y_targetF, var_type = ['numerical', 'categorical','mixed'], skf_splits = 10):
def MultClassPipeSKFLoop(input_df, target, skf_cv, var_type = ['numerical','categorical','mixed']):
'''
@ param input_df: input features
@ type: df (gets converted to np.array for stratified Kfold, and helps identify names to apply column transformation)
@ type: df with input features WITHOUT the target variable
@param y_outputF: target (or output) feature
@type: df or np.array
@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-hot encoder)
@type: list
returns
multiple classification model scores
Dict containing multiple classification scores for each model and each Stratified Kfold
'''
# Determine categorical and numerical features
@ -86,17 +93,17 @@ def MultClassPipeSKF(input_df, y_targetF, var_type = ['numerical', 'categorical'
, n_estimators = 150
, bootstrap = True
, oob_score = True
, n_jobs = -1
, **njobs
, **rs
, max_features = 'auto')
xgb = XGBClassifier(**rs, verbosity = 0)
xgb = XGBClassifier(**rs, verbosity = 0, use_label_encoder = False)
classification_metrics = {
'F1_score': []
,'MCC': []
,'Precision': []
,'Recall': []
,'Accuracy': []
, 'Accuracy': []
,'ROC_AUC': []
}
models = [
@ -109,33 +116,29 @@ def MultClassPipeSKF(input_df, y_targetF, var_type = ['numerical', 'categorical'
, ('Extra Trees' , et)
, ('Random Forest' , rf)
, ('Naive Bayes' , nb)
, ('Random Forest2' , rf2)
#, ('XGBoost' , xgb)
, ('Random Forest2' , rf2)
, ('XGBoost' , xgb)
]
skf = StratifiedKFold(n_splits = skf_splits
, shuffle = True
, **rs)
# skf = StratifiedKFold(n_splits = 10
# #, shuffle = False, random_state= None)
# , shuffle = True,**rs)
# skf_dict = {}
fold_no = 1
fold_dict={}
for model_name, model in models:
fold_dict.update({ model_name: {}})
#scores_df = pd.DataFrame()
for train_index, test_index in skf.split(input_df, y_targetF):
for train_index, test_index in skf_cv.split(input_df, target):
x_train_fold, x_test_fold = input_df.iloc[train_index], input_df.iloc[test_index]
y_train_fold, y_test_fold = y_targetF.iloc[train_index], y_targetF.iloc[test_index]
y_train_fold, y_test_fold = target.iloc[train_index], target.iloc[test_index]
#print("Fold: ", fold_no, len(train_index), len(test_index))
for model_name, model in models:
print("\nStart of model", model_name, "\nLoop no.", fold_no)
#skf_dict.update({model_name: classification_metrics })
model_pipeline = Pipeline(steps=[('prep' , col_transform)
model_pipeline = Pipeline(steps=[('prep' , col_transform)
, ('classifier' , model)])
model_pipeline.fit(x_train_fold, y_train_fold)
y_pred_fold = model_pipeline.predict(x_test_fold)
@ -168,14 +171,4 @@ def MultClassPipeSKF(input_df, y_targetF, var_type = ['numerical', 'categorical'
fold_dict[model_name][fold].update({'ROC_AUC' : roc_auc})
fold_no +=1
#pp.pprint(skf_dict)
return(fold_dict)
#%% CAll function
# t3_res = MultClassPipeSKF(input_df = numerical_features_df
# , y_targetF = target1
# , var_type = 'numerical'
# , skf_splits = 10)
# pp.pprint(t3_res)
# #print(t3_res)
return(fold_dict)