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
|
|
@ -61,9 +61,8 @@ 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)
|
||||
|
|
@ -76,8 +75,25 @@ scoring_fn = ({ 'fscore' : make_scorer(f1_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
|
||||
|
|
@ -98,7 +114,7 @@ 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()
|
||||
|
|
@ -108,56 +124,51 @@ def MultClassPipelineCV(X_train, X_test, y_train, y_test, input_df, var_type = [
|
|||
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')
|
||||
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)
|
||||
|
||||
xgb = XGBClassifier(**rs, verbosity=0)
|
||||
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)]
|
||||
|
||||
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 = {}
|
||||
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)])
|
||||
|
||||
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)
|
||||
|
||||
|
|
|
|||
|
|
@ -5,29 +5,19 @@ Created on Tue Mar 15 11:09:50 2022
|
|||
|
||||
@author: tanu
|
||||
"""
|
||||
# stratified shuffle split
|
||||
X_train, X_test, y_train, y_test = train_test_split(num_df_wtgt[numerical_FN]
|
||||
, num_df_wtgt['mutation_class']
|
||||
, test_size = 0.33
|
||||
, **rs
|
||||
, shuffle = True
|
||||
, stratify = num_df_wtgt['mutation_class'])
|
||||
#%% Data
|
||||
X = all_df_wtgt[numerical_FN+categorical_FN]
|
||||
y = all_df_wtgt['mutation_class']
|
||||
#%% variables
|
||||
|
||||
y_train.to_frame().value_counts().plot(kind = 'bar')
|
||||
y_test.to_frame().value_counts().plot(kind = 'bar')
|
||||
|
||||
MultClassPipelineCV(X_train, X_test, y_train, y_test
|
||||
, input_df = num_df_wtgt[numerical_FN]
|
||||
, var_type = 'numerical')
|
||||
#%% MultClassPipeSKFCV: function call()
|
||||
mm_skf_scoresD = MultClassPipeSKFCV(input_df = X
|
||||
, target = y
|
||||
, var_type = 'mixed'
|
||||
, skf_cv = skf_cv)
|
||||
|
||||
|
||||
skf_cv_scores = MultClassPipelineCV(X_train, X_test, y_train, y_test
|
||||
, input_df = num_df_wtgt[numerical_FN]
|
||||
, var_type = 'numerical')
|
||||
|
||||
pp.pprint(skf_cv_scores)
|
||||
# construct a df
|
||||
skf_cv_scores_df = pd.DataFrame(skf_cv_scores)
|
||||
skf_cv_scores_df
|
||||
skf_cv_scores_df_test = skf_cv_scores_df.filter(like='test_', axis=0)
|
||||
skf_cv_scores_df_train = skf_cv_scores_df.filter(like='train_', axis=0)
|
||||
mm_skf_scores_df_all = pd.DataFrame(mm_skf_scoresD)
|
||||
mm_skf_scores_df_all
|
||||
mm_skf_scores_df_test = mm_skf_scores_df_all.filter(like='test_', axis=0)
|
||||
mm_skf_scores_df_train = mm_skf_scores_df_all.filter(like='train_', axis=0) # helps to see if you trust the results
|
||||
|
|
|
|||
Binary file not shown.
Binary file not shown.
|
|
@ -138,6 +138,14 @@ parameters = [
|
|||
#'tfidf__stop_words': [None],
|
||||
'clf__estimator__alpha': (1e-2, 1e-3, 1e-1),
|
||||
},
|
||||
|
||||
{
|
||||
'clf__estimator': [LogisticRegression()],
|
||||
'C': [0.001, 0.01, 0.1, 1, 10, 100, 1000],
|
||||
'penalty': ['none', 'l1', 'l2', 'elasticnet'],
|
||||
'max_iter': list(range(100,800,100)),
|
||||
'solver': ['newton-cg', 'lbfgs', 'liblinear', 'sag', 'saga'],
|
||||
},
|
||||
]
|
||||
|
||||
pipeline = Pipeline([
|
||||
|
|
|
|||
41
imports.py
41
imports.py
|
|
@ -17,8 +17,12 @@ from sklearn.neighbors import KNeighborsClassifier
|
|||
from sklearn.svm import SVC
|
||||
from sklearn.tree import DecisionTreeClassifier
|
||||
from sklearn.ensemble import RandomForestClassifier, ExtraTreesClassifier
|
||||
from sklearn.ensemble import AdaBoostClassifier
|
||||
from sklearn.ensemble import GradientBoostingClassifier
|
||||
from sklearn.neural_network import MLPClassifier
|
||||
from xgboost import XGBClassifier
|
||||
from sklearn.naive_bayes import MultinomialNB
|
||||
from sklearn.linear_model import SGDClassifier
|
||||
from sklearn.preprocessing import StandardScaler, MinMaxScaler, OneHotEncoder
|
||||
|
||||
from sklearn.compose import ColumnTransformer
|
||||
|
|
@ -52,11 +56,29 @@ from imblearn.over_sampling import RandomOverSampler
|
|||
from imblearn.over_sampling import SMOTE
|
||||
from imblearn.pipeline import Pipeline
|
||||
#from sklearn.datasets import make_classification
|
||||
from sklearn.model_selection import cross_validate
|
||||
from sklearn.model_selection import cross_validate, cross_val_score
|
||||
from sklearn.model_selection import RepeatedStratifiedKFold
|
||||
from sklearn.ensemble import AdaBoostClassifier
|
||||
from imblearn.combine import SMOTEENN
|
||||
from imblearn.under_sampling import EditedNearestNeighbours
|
||||
|
||||
from sklearn.model_selection import GridSearchCV
|
||||
from sklearn.base import BaseEstimator
|
||||
|
||||
scoring_fn = ({'accuracy' : make_scorer(accuracy_score)
|
||||
, 'fscore' : make_scorer(f1_score)
|
||||
, 'mcc' : make_scorer(matthews_corrcoef)
|
||||
, 'precision' : make_scorer(precision_score)
|
||||
, 'recall' : make_scorer(recall_score)
|
||||
, 'roc_auc' : make_scorer(roc_auc_score)
|
||||
})
|
||||
|
||||
rs = {'random_state': 42}
|
||||
njobs = {'n_jobs': 10}
|
||||
skf_cv = StratifiedKFold(n_splits = 10
|
||||
#, shuffle = False, random_state= None)
|
||||
, shuffle = True,**rs)
|
||||
|
||||
#%%
|
||||
homedir = os.path.expanduser("~")
|
||||
os.chdir(homedir + "/git/ML_AI_training/")
|
||||
|
|
@ -64,8 +86,8 @@ os.chdir(homedir + "/git/ML_AI_training/")
|
|||
# my function
|
||||
from MultClassPipe import MultClassPipeline
|
||||
from MultClassPipe2 import MultClassPipeline2
|
||||
from loopity_loop import MultClassPipeSKF
|
||||
from MultClassPipe3 import MultClassPipelineCV
|
||||
from loopity_loop import MultClassPipeSKFLoop
|
||||
from MultClassPipe3 import MultClassPipeSKFCV
|
||||
|
||||
|
||||
gene = 'pncA'
|
||||
|
|
@ -199,3 +221,16 @@ cat_df_wtgt.shape
|
|||
|
||||
all_df_wtgt = my_df[numerical_FN + categorical_FN + ['mutation_class']]
|
||||
all_df_wtgt.shape
|
||||
|
||||
#%%
|
||||
#%% Get train-test split and scoring functions
|
||||
X = num_df_wtgt[numerical_FN]
|
||||
y = num_df_wtgt['mutation_class']
|
||||
|
||||
X_train, X_test, y_train, y_test = train_test_split(X
|
||||
,y
|
||||
, test_size = 0.33
|
||||
, random_state = 2
|
||||
, shuffle = True
|
||||
, stratify = y)
|
||||
|
||||
|
|
@ -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
|
||||
|
|
@ -86,11 +93,11 @@ 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': []
|
||||
|
|
@ -109,32 +116,28 @@ def MultClassPipeSKF(input_df, y_targetF, var_type = ['numerical', 'categorical'
|
|||
, ('Extra Trees' , et)
|
||||
, ('Random Forest' , rf)
|
||||
, ('Naive Bayes' , nb)
|
||||
|
||||
, ('Random Forest2' , rf2)
|
||||
#, ('XGBoost' , xgb)
|
||||
, ('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)
|
||||
, ('classifier' , model)])
|
||||
model_pipeline.fit(x_train_fold, y_train_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)
|
||||
|
|
|
|||
|
|
@ -5,22 +5,19 @@ Created on Fri Mar 11 11:15:50 2022
|
|||
|
||||
@author: tanu
|
||||
"""
|
||||
#%%
|
||||
del(t3_res)
|
||||
# t3_res = MultClassPipeSKF(input_df = numerical_features_df
|
||||
# , y_targetF = target1
|
||||
# , var_type = 'numerical'
|
||||
# , skf_splits = 10)
|
||||
# pp.pprint(t3_res)
|
||||
# #print(t3_res)
|
||||
#%% variables
|
||||
rs = {'random_state': 42}
|
||||
|
||||
t3_res = MultClassPipeSKF(input_df = num_df_wtgt[numerical_FN]
|
||||
, y_targetF = num_df_wtgt['mutation_class']
|
||||
skf_cv = StratifiedKFold(n_splits = 10
|
||||
#, shuffle = False, random_state= None)
|
||||
, shuffle = True,**rs)
|
||||
#%% MultClassPipeSKFLoop: function call()
|
||||
t3_res = MultClassPipeSKFLoop(input_df = num_df_wtgt[numerical_FN]
|
||||
, target = num_df_wtgt['mutation_class']
|
||||
, var_type = 'numerical'
|
||||
, skf_splits = 10)
|
||||
, skf_cv = skf_cv)
|
||||
pp.pprint(t3_res)
|
||||
#print(t3_res)
|
||||
|
||||
################################################################
|
||||
# extract items from wwithin a nested dict
|
||||
#%% Classification Metrics we need to mean()
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue