copy of ML dir to an FS-only version
This commit is contained in:
parent
52cc16f3fa
commit
80e6b3af96
23 changed files with 3115 additions and 243 deletions
130
UQ_LR_FS_p1.py
130
UQ_LR_FS_p1.py
|
|
@ -12,60 +12,20 @@ Created on Tue Mar 15 11:09:50 2022
|
|||
|
||||
@author: tanu
|
||||
"""
|
||||
#%% Import libs
|
||||
import numpy as np
|
||||
import pandas as pd
|
||||
from sklearn.model_selection import GridSearchCV
|
||||
from sklearn import datasets
|
||||
from sklearn.ensemble import ExtraTreesClassifier
|
||||
from sklearn.ensemble import RandomForestClassifier
|
||||
from sklearn.ensemble import AdaBoostClassifier
|
||||
from sklearn.ensemble import GradientBoostingClassifier
|
||||
from sklearn.svm import SVC
|
||||
|
||||
from sklearn.base import BaseEstimator
|
||||
from sklearn.naive_bayes import MultinomialNB
|
||||
from sklearn.linear_model import SGDClassifier
|
||||
from sklearn.pipeline import Pipeline
|
||||
from sklearn.model_selection import GridSearchCV
|
||||
from sklearn.linear_model import LogisticRegression
|
||||
from sklearn.preprocessing import StandardScaler, MinMaxScaler, OneHotEncoder
|
||||
from xgboost import XGBClassifier
|
||||
#####################
|
||||
from sklearn.feature_selection import RFE
|
||||
from sklearn.feature_selection import RFECV
|
||||
from sklearn.linear_model import LogisticRegression
|
||||
from sklearn.feature_selection import SelectFromModel
|
||||
from sklearn.feature_selection import SequentialFeatureSelector
|
||||
# Attempting feature selection for LR WITHOUT ClfSwitcher Class
|
||||
|
||||
#%% Import libraries, data, and scoring func: UQ_pnca_ML.py
|
||||
rs = {'random_state': 42}
|
||||
njobs = {'n_jobs': 10}
|
||||
#%%
|
||||
|
||||
y.to_frame().value_counts().plot(kind = 'bar')
|
||||
blind_test_df['dst_mode'].to_frame().value_counts().plot(kind = 'bar')
|
||||
|
||||
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)
|
||||
, 'jaccard' : make_scorer(jaccard_score)
|
||||
})
|
||||
|
||||
mcc_score_fn = {'mcc': make_scorer(matthews_corrcoef)}
|
||||
jacc_score_fn = {'jcc': make_scorer(jaccard_score)}
|
||||
|
||||
#%% Logistic Regression + hyperparam + FS: BaseEstimator: ClfSwitcher()
|
||||
#%% Logistic Regression + hyperparam + FS: Pipeline takes GridSearchCV (not the other way round!)
|
||||
model_lr = LogisticRegression(**rs)
|
||||
model_rfecv = RFECV(estimator = model_lr
|
||||
, cv = rskf_cv
|
||||
, cv = skf_cv
|
||||
#, cv = 10
|
||||
, scoring = 'matthews_corrcoef'
|
||||
)
|
||||
|
||||
# model_rfecv = SequentialFeatureSelector(estimator = model_lr
|
||||
# model_sfs = SequentialFeatureSelector(estimator = model_lr
|
||||
# , n_features_to_select = 'auto'
|
||||
# , tol = None
|
||||
# # , cv = 10
|
||||
|
|
@ -74,23 +34,9 @@ model_rfecv = RFECV(estimator = model_lr
|
|||
# , direction ='forward'
|
||||
# , **njobs)
|
||||
|
||||
# param_grid = [
|
||||
# { 'C': np.logspace(0, 4, 10),
|
||||
# 'penalty': ['l1', 'l2'],
|
||||
# 'max_iter': [100],
|
||||
# 'solver': ['saga']
|
||||
# }#,
|
||||
# # { 'C': [1],
|
||||
# # 'penalty': ['l1'],
|
||||
# # 'max_iter': [100],
|
||||
# # 'solver': ['saga']
|
||||
# # }
|
||||
# ]
|
||||
|
||||
param_grid2 = [
|
||||
{
|
||||
#'clf__estimator': [LogisticRegression(**rs)],
|
||||
#'C': [0.001, 0.01, 0.1, 1, 10, 100, 1000],
|
||||
'C': np.logspace(0, 4, 10),
|
||||
'penalty': ['none', 'l1', 'l2', 'elasticnet'],
|
||||
'max_iter': list(range(100,800,100)),
|
||||
|
|
@ -98,7 +44,6 @@ param_grid2 = [
|
|||
},
|
||||
{
|
||||
#'clf__estimator': [LogisticRegression(**rs)],
|
||||
#'C': [0.001, 0.01, 0.1, 1, 10, 100, 1000],
|
||||
'C': np.logspace(0, 4, 10),
|
||||
'penalty': ['l2', 'none'],
|
||||
'max_iter': list(range(100,800,100)),
|
||||
|
|
@ -106,13 +51,24 @@ param_grid2 = [
|
|||
},
|
||||
{
|
||||
#'clf__estimator': [LogisticRegression(**rs)],
|
||||
#'C': [0.001, 0.01, 0.1, 1, 10, 100, 1000],
|
||||
'C': np.logspace(0, 4, 10),
|
||||
'penalty': ['l1', 'l2'],
|
||||
'max_iter': list(range(100,800,100)),
|
||||
'solver': ['liblinear']
|
||||
}
|
||||
|
||||
|
||||
# lesser params for testing
|
||||
# { 'C': np.logspace(0, 4, 10),
|
||||
# 'penalty': ['l1', 'l2'],
|
||||
# 'max_iter': [100],
|
||||
# 'solver': ['saga']
|
||||
# },
|
||||
# { 'C': [1],
|
||||
# 'penalty': ['l1'],
|
||||
# 'max_iter': [100],
|
||||
# 'solver': ['saga']
|
||||
# }
|
||||
|
||||
]
|
||||
|
||||
#-------------------------------------------------------------------------------
|
||||
|
|
@ -127,24 +83,21 @@ gscv_lr = GridSearchCV(model_lr
|
|||
|
||||
#------------------------------------------------------------------------------
|
||||
# Create pipeline
|
||||
pipeline = Pipeline([('pre', MinMaxScaler())
|
||||
pipeline2 = Pipeline([('pre', MinMaxScaler())
|
||||
#, ('feature_selection', sfs_selector)
|
||||
, ('feature_selection', model_rfecv )
|
||||
, ('clf', gscv_lr)])
|
||||
|
||||
# Fit
|
||||
lr_fs = pipeline.fit(X,y)
|
||||
pipeline2.fit(X,y)
|
||||
pipeline2.predict(X_bts)
|
||||
|
||||
# Assigning fit an then running predict: sanity check
|
||||
#lr_fs = pipeline.fit(X,y)
|
||||
#lr_fs.predict(X_bts)
|
||||
|
||||
pipeline.predict(X_bts)
|
||||
lr_fs.predict(X_bts)
|
||||
|
||||
test_predict = pipeline.predict(X_bts)
|
||||
print(test_predict)
|
||||
print(np.array(y_bts))
|
||||
#y_btsf = np.array(y_bts)
|
||||
|
||||
print(accuracy_score(y_bts, test_predict))
|
||||
print(matthews_corrcoef(y_bts, test_predict))
|
||||
|
||||
###############################################################################
|
||||
#####################
|
||||
|
|
@ -160,13 +113,12 @@ print(matthews_corrcoef(y_bts, test_predict))
|
|||
#print('\nBlind test score, mcc:', ))
|
||||
|
||||
#test_predict = gscv_lr_fit.predict(X_bts)
|
||||
test_predict = pipeline.predict(X_bts)
|
||||
test_predict_fs = sfs_selector.predict(X_bts)
|
||||
test_predict = pipeline2.predict(X_bts)
|
||||
|
||||
print(test_predict)
|
||||
|
||||
print(accuracy_score(y_bts, test_predict))
|
||||
print(matthews_corrcoef(y_bts, test_predict))
|
||||
print('\nMCC on Blind test:' , round(matthews_corrcoef(y_bts, test_predict),2))
|
||||
print('\nAccuracy on Blind test:', round(accuracy_score(y_bts, test_predict),2))
|
||||
|
||||
# create a dict with all scores
|
||||
lr_bts_dict = {#'best_model': list(gscv_lr_fit_be_mod.items())
|
||||
|
|
@ -237,7 +189,7 @@ from sklearn.feature_selection import SequentialFeatureSelector
|
|||
|
||||
# RFE: ~ model coef or feature_importance
|
||||
rfe_selector = RFECV(estimator = LogisticRegression(**rs
|
||||
, penalty='l1'
|
||||
, penalty='l2'
|
||||
, solver='saga'
|
||||
, max_iter = 100
|
||||
, C= 1.0)
|
||||
|
|
@ -249,6 +201,30 @@ rfe_fs = X.columns[rfe_selector.get_support()]
|
|||
print('\nFeatures selected from Recursive Feature Elimination:', len(rfe_fs)
|
||||
, '\nThese are:', rfe_fs)
|
||||
|
||||
# blind test
|
||||
TEST_PREDICT = rfe_selector.predict(X_bts)
|
||||
TEST_PREDICT
|
||||
|
||||
print('\nMCC on Blind test:' , round(matthews_corrcoef(y_bts, TEST_PREDICT),2))
|
||||
print('\nAccuracy on Blind test:', round(accuracy_score(y_bts, TEST_PREDICT),2))
|
||||
|
||||
# add pipeline with preprocessing: changes numbers
|
||||
pipe = Pipeline([
|
||||
('pre', MinMaxScaler())
|
||||
#, ('fs', model_rfecv)
|
||||
, ('fs', rfe_selector)
|
||||
, ('clf', LogisticRegression(**rs))])
|
||||
|
||||
pipe.fit(X,y)
|
||||
|
||||
tp = pipe.predict(X_bts)
|
||||
|
||||
print('\nMCC on Blind test:' , round(matthews_corrcoef(y_bts, tp),2))
|
||||
print('\nAccuracy on Blind test:', round(accuracy_score(y_bts, tp),2))
|
||||
|
||||
##################################
|
||||
|
||||
|
||||
# SFM: ~ model coef or feature_importance
|
||||
sfm_selector = SelectFromModel(estimator = LogisticRegression(**rs
|
||||
, penalty='l1'
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue