302 lines
No EOL
11 KiB
Python
302 lines
No EOL
11 KiB
Python
#!/usr/bin/env python3
|
|
# -*- coding: utf-8 -*-
|
|
"""
|
|
Created on Mon May 16 05:59:12 2022
|
|
|
|
@author: tanu
|
|
"""
|
|
#!/usr/bin/env python3
|
|
# -*- coding: utf-8 -*-
|
|
"""
|
|
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
|
|
|
|
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()
|
|
model_lr = LogisticRegression(**rs)
|
|
model_rfecv = RFECV(estimator = model_lr
|
|
, cv = rskf_cv
|
|
#, cv = 10
|
|
, scoring = 'matthews_corrcoef'
|
|
)
|
|
|
|
# model_rfecv = SequentialFeatureSelector(estimator = model_lr
|
|
# , n_features_to_select = 'auto'
|
|
# , tol = None
|
|
# # , cv = 10
|
|
# , cv = rskf_cv
|
|
# # , direction ='backward'
|
|
# , 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)),
|
|
'solver': ['saga']
|
|
},
|
|
{
|
|
#'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)),
|
|
'solver': ['newton-cg', 'lbfgs', 'sag']
|
|
},
|
|
{
|
|
#'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']
|
|
}
|
|
|
|
]
|
|
|
|
#-------------------------------------------------------------------------------
|
|
# Grid search CV + FS
|
|
gscv_lr = GridSearchCV(model_lr
|
|
, param_grid2
|
|
, scoring = mcc_score_fn, refit = 'mcc'
|
|
, cv = skf_cv
|
|
, return_train_score = False
|
|
, verbose = 3
|
|
, **njobs)
|
|
|
|
#------------------------------------------------------------------------------
|
|
# Create pipeline
|
|
pipeline = Pipeline([('pre', MinMaxScaler())
|
|
#, ('feature_selection', sfs_selector)
|
|
, ('feature_selection', model_rfecv )
|
|
, ('clf', gscv_lr)])
|
|
|
|
# Fit
|
|
lr_fs = pipeline.fit(X,y)
|
|
|
|
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))
|
|
|
|
###############################################################################
|
|
#####################
|
|
# Feature selection: AFTER model selection
|
|
# https://towardsdatascience.com/5-feature-selection-method-from-scikit-learn-you-should-know-ed4d116e4172
|
|
|
|
###############################################################################
|
|
|
|
######################################
|
|
# Blind test
|
|
######################################
|
|
# See how it does on the BLIND test
|
|
#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)
|
|
|
|
print(test_predict)
|
|
|
|
print(accuracy_score(y_bts, test_predict))
|
|
print(matthews_corrcoef(y_bts, test_predict))
|
|
|
|
# create a dict with all scores
|
|
lr_bts_dict = {#'best_model': list(gscv_lr_fit_be_mod.items())
|
|
'bts_fscore':None
|
|
, 'bts_mcc':None
|
|
, 'bts_precision':None
|
|
, 'bts_recall':None
|
|
, 'bts_accuracy':None
|
|
, 'bts_roc_auc':None
|
|
, 'bts_jaccard':None }
|
|
lr_bts_dict
|
|
lr_bts_dict['bts_fscore'] = round(f1_score(y_bts, test_predict),2)
|
|
lr_bts_dict['bts_mcc'] = round(matthews_corrcoef(y_bts, test_predict),2)
|
|
lr_bts_dict['bts_precision'] = round(precision_score(y_bts, test_predict),2)
|
|
lr_bts_dict['bts_recall'] = round(recall_score(y_bts, test_predict),2)
|
|
lr_bts_dict['bts_accuracy'] = round(accuracy_score(y_bts, test_predict),2)
|
|
lr_bts_dict['bts_roc_auc'] = round(roc_auc_score(y_bts, test_predict),2)
|
|
lr_bts_dict['bts_jaccard'] = round(jaccard_score(y_bts, test_predict),2)
|
|
lr_bts_dict
|
|
|
|
# Create a df from dict with all scores
|
|
lr_bts_df = pd.DataFrame.from_dict(lr_bts_dict,orient = 'index')
|
|
lr_bts_df.columns = ['Logistic_Regression']
|
|
print(lr_bts_df)
|
|
|
|
# d2 = {'best_model_params': lis(gscv_lr_fit_be_mod.items() )}
|
|
# d2
|
|
# def Merge(dict1, dict2):
|
|
# res = {**dict1, **dict2}
|
|
# return res
|
|
# d3 = Merge(d2, lr_bts_dict)
|
|
# d3
|
|
|
|
# Create df with best model params
|
|
model_params = pd.Series(['best_model_params', list(gscv_lr_fit_be_mod.items() )])
|
|
model_params_df = model_params.to_frame()
|
|
model_params_df
|
|
model_params_df.columns = ['Logistic_Regression']
|
|
model_params_df.columns
|
|
|
|
# Combine the df of scores and the best model params
|
|
lr_bts_df.columns
|
|
lr_output = pd.concat([model_params_df, lr_bts_df], axis = 0)
|
|
lr_output
|
|
|
|
# Format the combined df
|
|
# Drop the best_model_params row from lr_output
|
|
lr_df = lr_output.drop([0], axis = 0)
|
|
lr_df
|
|
|
|
#FIXME: tidy the index of the formatted df
|
|
|
|
###############################################################################
|
|
# FIXME: confusion matrix
|
|
|
|
print(confusion_matrix(y_bts, test_predict))
|
|
#%% Feature selection
|
|
|
|
#####################
|
|
# Feature selection: AFTER model selection?
|
|
# ADD that within the loop
|
|
# https://towardsdatascience.com/5-feature-selection-method-from-scikit-learn-you-should-know-ed4d116e4172
|
|
#####################
|
|
from sklearn.feature_selection import RFECV
|
|
from sklearn.linear_model import LogisticRegression
|
|
from sklearn.feature_selection import SelectFromModel
|
|
from sklearn.feature_selection import SequentialFeatureSelector
|
|
|
|
# RFE: ~ model coef or feature_importance
|
|
rfe_selector = RFECV(estimator = LogisticRegression(**rs
|
|
, penalty='l1'
|
|
, solver='saga'
|
|
, max_iter = 100
|
|
, C= 1.0)
|
|
#, n_features_to_select = None # median by default
|
|
, step = 1
|
|
, cv = 10)
|
|
rfe_selector.fit(X, y)
|
|
rfe_fs = X.columns[rfe_selector.get_support()]
|
|
print('\nFeatures selected from Recursive Feature Elimination:', len(rfe_fs)
|
|
, '\nThese are:', rfe_fs)
|
|
|
|
# SFM: ~ model coef or feature_importance
|
|
sfm_selector = SelectFromModel(estimator = LogisticRegression(**rs
|
|
, penalty='l1'
|
|
, solver='saga'
|
|
, max_iter = 100
|
|
, C= 1.0)
|
|
, threshold = "median"
|
|
, max_features = None ) # median by default
|
|
sfm_selector.fit(X, y)
|
|
sfm_fs = X.columns[sfm_selector.get_support()]
|
|
|
|
print('\nFeatures selected from Select From Model:', len(sfm_fs)
|
|
, '\nThese are:', sfm_fs)
|
|
|
|
# SFS:ML CV
|
|
sfs_selector = SequentialFeatureSelector(estimator = LogisticRegression(**rs
|
|
, penalty='l1'
|
|
, solver='saga'
|
|
, max_iter = 100
|
|
, C = 1.0)
|
|
, n_features_to_select = 'auto'
|
|
, tol = None
|
|
, cv = 10
|
|
#, cv = skf_cv
|
|
# , direction ='backward'
|
|
, direction ='forward'
|
|
|
|
, **njobs)
|
|
sfs_selector.fit(X, y)
|
|
sfsb_fs = X.columns[sfs_selector.get_support()]
|
|
|
|
print('\nFeatures selected from Sequential Feature Selector (Greedy):', len(sfsb_fs)
|
|
, '\nThese are:', sfsb_fs)
|
|
|
|
#Features selected from Sequential Feature Selector (Greedy, Backward): 7 [CV = SKF_CV]
|
|
#These are: Index(['ligand_distance', 'duet_stability_change', 'ddg_foldx', 'deepddg',
|
|
# 'contacts', 'rd_values', 'snap2_score']
|
|
|
|
#Features selected from Sequential Feature Selector (Greedy, Backward): 7 [CV=10]
|
|
#These are: Index(['ligand_distance', 'deepddg', 'contacts', 'rsa', 'kd_values',
|
|
# 'rd_values', 'maf']
|
|
|
|
#-----
|
|
# Features selected from Sequential Feature Selector (Greedy, Forward): 6 [CV = SKF_CV]
|
|
# These are: Index(['ligand_distance', 'ddg_dynamut2', 'rsa', 'kd_values', 'rd_values', 'maf']
|
|
|
|
# Features selected from Sequential Feature Selector (Greedy, Forward): 6 [CV = 10]
|
|
#These are: Index(['duet_stability_change', 'deepddg', 'ddg_dynamut2', 'rsa', 'kd_values', 'maf']
|
|
###############################################################################
|
|
# IMP: nice eg of including it as part of pipeline
|
|
# https://www.tomasbeuzen.com/post/scikit-learn-gridsearch-pipelines/ |