207 lines
6.8 KiB
Python
Executable file
207 lines
6.8 KiB
Python
Executable file
#!/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
|
|
rs = {'random_state': 42}
|
|
njobs = {'n_jobs': 10}
|
|
#%% Get train-test split and scoring functions
|
|
|
|
|
|
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: BaseEstimator: ClfSwitcher()
|
|
class ClfSwitcher(BaseEstimator):
|
|
def __init__(
|
|
self,
|
|
estimator = SGDClassifier(),
|
|
):
|
|
"""
|
|
A Custom BaseEstimator that can switch between classifiers.
|
|
:param estimator: sklearn object - The classifier
|
|
"""
|
|
self.estimator = estimator
|
|
|
|
def fit(self, X, y=None, **kwargs):
|
|
self.estimator.fit(X, y)
|
|
return self
|
|
|
|
def predict(self, X, y=None):
|
|
return self.estimator.predict(X)
|
|
|
|
def predict_proba(self, X):
|
|
return self.estimator.predict_proba(X)
|
|
|
|
def score(self, X, y):
|
|
return self.estimator.score(X, y)
|
|
|
|
parameters = [
|
|
{
|
|
'clf__estimator': [LogisticRegression(**rs)],
|
|
#'clf__estimator__C': [0.001, 0.01, 0.1, 1, 10, 100, 1000],
|
|
'clf__estimator__C': np.logspace(0, 4, 10),
|
|
'clf__estimator__penalty': ['none', 'l1', 'l2', 'elasticnet'],
|
|
'clf__estimator__max_iter': list(range(100,800,100)),
|
|
'clf__estimator__solver': ['saga']
|
|
},
|
|
{
|
|
'clf__estimator': [LogisticRegression(**rs)],
|
|
#'clf__estimator__C': [0.001, 0.01, 0.1, 1, 10, 100, 1000],
|
|
'clf__estimator__C': np.logspace(0, 4, 10),
|
|
'clf__estimator__penalty': ['l2', 'none'],
|
|
'clf__estimator__max_iter': list(range(100,800,100)),
|
|
'clf__estimator__solver': ['newton-cg', 'lbfgs', 'sag']
|
|
},
|
|
{
|
|
'clf__estimator': [LogisticRegression(**rs)],
|
|
#'clf__estimator__C': [0.001, 0.01, 0.1, 1, 10, 100, 1000],
|
|
'clf__estimator__C': np.logspace(0, 4, 10),
|
|
'clf__estimator__penalty': ['l1', 'l2'],
|
|
'clf__estimator__max_iter': list(range(100,800,100)),
|
|
'clf__estimator__solver': ['liblinear']
|
|
}
|
|
|
|
]
|
|
|
|
# Create pipeline
|
|
pipeline = Pipeline([
|
|
('pre', MinMaxScaler()),
|
|
('clf', ClfSwitcher()),
|
|
])
|
|
|
|
# Grid search i.e hyperparameter tuning and refitting on mcc
|
|
gscv_lr = GridSearchCV(pipeline
|
|
, parameters
|
|
#, scoring = 'f1', refit = 'f1'
|
|
, scoring = mcc_score_fn, refit = 'mcc'
|
|
#, cv = skf_cv
|
|
, cv = rskf_cv
|
|
, **njobs
|
|
, return_train_score = False
|
|
, verbose = 3)
|
|
|
|
# Fit
|
|
gscv_lr_fit = gscv_lr.fit(X, y)
|
|
gscv_lr_fit_be_mod = gscv_lr_fit.best_params_
|
|
gscv_lr_fit_be_res = gscv_lr_fit.cv_results_
|
|
|
|
print('Best model:\n', gscv_lr_fit_be_mod)
|
|
print('Best models score:\n', gscv_lr_fit.best_score_, ':' , round(gscv_lr_fit.best_score_, 2))
|
|
|
|
#print('\nMean test score from fit results:', round(mean(gscv_lr_fit_be_res['mean_test_mcc']),2))
|
|
print('\nMean test score from fit results:', round(np.nanmean(gscv_lr_fit_be_res['mean_test_mcc']),2))
|
|
|
|
###############################################################################
|
|
|
|
######################################
|
|
# Blind test
|
|
######################################
|
|
# See how it does on the BLIND test
|
|
#print('\nBlind test score, mcc:', ))
|
|
|
|
test_predict = gscv_lr_fit.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))
|
|
|
|
# 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))
|
|
|
|
cm = confusion_matrix(y_bts, test_predict)
|
|
|