saving and organising work to call form cmd line
This commit is contained in:
parent
d9a1888e8c
commit
f2634f77ef
5 changed files with 232 additions and 106 deletions
|
|
@ -6,6 +6,38 @@ Created on Tue Mar 15 11:09:50 2022
|
|||
@author: tanu
|
||||
"""
|
||||
|
||||
from sklearn.metrics import make_scorer, confusion_matrix, accuracy_score, balanced_accuracy_score, precision_score, average_precision_score, recall_score
|
||||
from sklearn.metrics import roc_auc_score, roc_curve, f1_score, matthews_corrcoef, jaccard_score, classification_report
|
||||
|
||||
from sklearn.model_selection import train_test_split, cross_validate, cross_val_score
|
||||
from sklearn.model_selection import StratifiedKFold,RepeatedStratifiedKFold, RepeatedKFold
|
||||
|
||||
from sklearn.pipeline import Pipeline, make_pipeline
|
||||
#%% GLOBALS
|
||||
rs = {'random_state': 42}
|
||||
njobs = {'n_jobs': 10}
|
||||
|
||||
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)
|
||||
, 'jcc' : make_scorer(jaccard_score)
|
||||
})
|
||||
|
||||
skf_cv = StratifiedKFold(n_splits = 10
|
||||
#, shuffle = False, random_state= None)
|
||||
, shuffle = True,**rs)
|
||||
|
||||
rskf_cv = RepeatedStratifiedKFold(n_splits = 10
|
||||
, n_repeats = 3
|
||||
, **rs)
|
||||
|
||||
mcc_score_fn = {'mcc': make_scorer(matthews_corrcoef)}
|
||||
jacc_score_fn = {'jcc': make_scorer(jaccard_score)}
|
||||
|
||||
###############################################################################
|
||||
#%% MultModelsCl: function call()
|
||||
mm_skf_scoresD = MultModelsCl(input_df = X
|
||||
, target = y
|
||||
|
|
@ -22,35 +54,7 @@ baseline_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
|
|||
|
||||
baseline_BT = baseline_all.filter(like='bts_', axis=1)
|
||||
baseline_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
|
||||
#%% SMOTE OS: Numerical only
|
||||
# mm_skf_scoresD2 = MultModelsCl(input_df = X_sm
|
||||
# , target = y_sm
|
||||
# , var_type = 'numerical'
|
||||
# , skf_cv = skf_cv)
|
||||
# sm_all = pd.DataFrame(mm_skf_scoresD2)
|
||||
# sm_all = sm_all.T
|
||||
|
||||
# sm_CT = sm_all.filter(like='test_', axis=1)
|
||||
#sm_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
|
||||
|
||||
# sm_BT = sm_all.filter(like='bts_', axis=1)
|
||||
#sm_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
|
||||
|
||||
#%% SMOTE ENN: Over + Undersampling combined: Numerical ONLY
|
||||
# mm_skf_scoresD5 = MultModelsCl(input_df = X_enn
|
||||
# , target = y_enn
|
||||
# , var_type = 'numerical'
|
||||
# , skf_cv = skf_cv
|
||||
# , blind_test_input_df = X_bts
|
||||
# , blind_test_target = y_bts)
|
||||
# enn_all = pd.DataFrame(mm_skf_scoresD5)
|
||||
# enn_all = enn_all.T
|
||||
|
||||
# enn_CT = enn_all.filter(like='test_', axis=1)
|
||||
#enn_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
|
||||
|
||||
# enn_BT = enn_all.filter(like='bts_', axis=1)
|
||||
#enn_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
|
||||
#%% SMOTE NC: Oversampling [Numerical + categorical]
|
||||
mm_skf_scoresD7 = MultModelsCl(input_df = X_smnc
|
||||
, target = y_smnc
|
||||
|
|
@ -97,7 +101,7 @@ rus_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
|
|||
rus_BT = rus_all.filter(like='bts_' , axis=1)
|
||||
rus_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
|
||||
#%% ROS + RUS Combined: Numerical + categorical
|
||||
mm_skf_scoresD8= MultModelsCl(input_df = X_rouC
|
||||
mm_skf_scoresD8 = MultModelsCl(input_df = X_rouC
|
||||
, target = y_rouC
|
||||
, var_type = 'mixed'
|
||||
, skf_cv = skf_cv
|
||||
|
|
@ -106,12 +110,43 @@ mm_skf_scoresD8= MultModelsCl(input_df = X_rouC
|
|||
rouC_all = pd.DataFrame(mm_skf_scoresD8)
|
||||
rouC_all = rouC_all.T
|
||||
|
||||
rouC_CT = ros_all.filter(like='test_', axis=1)
|
||||
rouC_CT = rouC_all.filter(like='test_', axis=1)
|
||||
rouC_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
|
||||
|
||||
rouC_BT = ros_all.filter(like='bts_', axis=1)
|
||||
rouC_BT = rouC_all.filter(like='bts_', axis=1)
|
||||
rouC_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
|
||||
#%%
|
||||
|
||||
#%% SMOTE OS: Numerical only
|
||||
# mm_skf_scoresD2 = MultModelsCl(input_df = X_sm
|
||||
# , target = y_sm
|
||||
# , var_type = 'numerical'
|
||||
# , skf_cv = skf_cv)
|
||||
# sm_all = pd.DataFrame(mm_skf_scoresD2)
|
||||
# sm_all = sm_all.T
|
||||
|
||||
# sm_CT = sm_all.filter(like='test_', axis=1)
|
||||
#sm_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
|
||||
|
||||
# sm_BT = sm_all.filter(like='bts_', axis=1)
|
||||
#sm_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
|
||||
|
||||
#%% SMOTE ENN: Over + Undersampling combined: Numerical ONLY
|
||||
# mm_skf_scoresD5 = MultModelsCl(input_df = X_enn
|
||||
# , target = y_enn
|
||||
# , var_type = 'numerical'
|
||||
# , skf_cv = skf_cv
|
||||
# , blind_test_input_df = X_bts
|
||||
# , blind_test_target = y_bts)
|
||||
# enn_all = pd.DataFrame(mm_skf_scoresD5)
|
||||
# enn_all = enn_all.T
|
||||
|
||||
# enn_CT = enn_all.filter(like='test_', axis=1)
|
||||
#enn_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
|
||||
|
||||
# enn_BT = enn_all.filter(like='bts_', axis=1)
|
||||
#enn_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
|
||||
|
||||
#%% Repeated ENN
|
||||
# mm_skf_scoresD6 = MultModelsCl(input_df = X_renn
|
||||
# , target = y_renn
|
||||
# , var_type = 'numerical'
|
||||
|
|
|
|||
|
|
@ -56,7 +56,7 @@ X_ros, y_ros = oversample.fit_resample(X, y)
|
|||
print(X_ros.shape) #228
|
||||
|
||||
#------------------------------
|
||||
# Simple Random oversampling
|
||||
# Simple Random undersampling
|
||||
# [Numerical + catgeorical]
|
||||
#------------------------------
|
||||
undersample = RandomUnderSampler(sampling_strategy='majority')
|
||||
|
|
|
|||
|
|
@ -6,89 +6,93 @@ Created on Fri Mar 4 15:25:33 2022
|
|||
@author: tanu
|
||||
"""
|
||||
#%%
|
||||
|
||||
import os, sys
|
||||
import pandas as pd
|
||||
import numpy as np
|
||||
import pprint as pp
|
||||
#from copy import deepcopy
|
||||
from copy import deepcopy
|
||||
from sklearn import linear_model
|
||||
from sklearn.linear_model import LogisticRegression, LinearRegression
|
||||
from sklearn import datasets
|
||||
from collections import Counter
|
||||
|
||||
from sklearn.linear_model import LogisticRegression, LogisticRegressionCV
|
||||
from sklearn.linear_model import RidgeClassifier, RidgeClassifierCV, SGDClassifier, PassiveAggressiveClassifier
|
||||
|
||||
from sklearn.naive_bayes import BernoulliNB
|
||||
from sklearn.neighbors import KNeighborsClassifier
|
||||
from sklearn.svm import SVC
|
||||
from sklearn.tree import DecisionTreeClassifier
|
||||
from sklearn.ensemble import RandomForestClassifier, ExtraTreesClassifier
|
||||
from sklearn.tree import DecisionTreeClassifier, ExtraTreeClassifier
|
||||
from sklearn.ensemble import RandomForestClassifier, ExtraTreesClassifier, AdaBoostClassifier, GradientBoostingClassifier, BaggingClassifier
|
||||
from sklearn.naive_bayes import GaussianNB
|
||||
from sklearn.gaussian_process import GaussianProcessClassifier, kernels
|
||||
from sklearn.gaussian_process.kernels import RBF, DotProduct, Matern, RationalQuadratic, WhiteKernel
|
||||
|
||||
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis, QuadraticDiscriminantAnalysis
|
||||
from sklearn.neural_network import MLPClassifier
|
||||
|
||||
from sklearn.svm import SVC
|
||||
from xgboost import XGBClassifier
|
||||
from sklearn.naive_bayes import MultinomialNB
|
||||
from sklearn.preprocessing import StandardScaler, MinMaxScaler, OneHotEncoder
|
||||
|
||||
from sklearn.compose import ColumnTransformer
|
||||
from sklearn.compose import make_column_transformer
|
||||
|
||||
from sklearn.metrics import confusion_matrix, accuracy_score, precision_score, recall_score
|
||||
from sklearn.metrics import roc_auc_score, roc_curve, f1_score, matthews_corrcoef, jaccard_score
|
||||
from sklearn.metrics import make_scorer
|
||||
from sklearn.metrics import classification_report
|
||||
from sklearn.metrics import make_scorer, confusion_matrix, accuracy_score, balanced_accuracy_score, precision_score, average_precision_score, recall_score
|
||||
from sklearn.metrics import roc_auc_score, roc_curve, f1_score, matthews_corrcoef, jaccard_score, classification_report
|
||||
|
||||
from sklearn.metrics import average_precision_score
|
||||
from sklearn.model_selection import train_test_split, cross_validate, cross_val_score
|
||||
from sklearn.model_selection import StratifiedKFold,RepeatedStratifiedKFold, RepeatedKFold
|
||||
|
||||
from sklearn.model_selection import cross_validate
|
||||
from sklearn.model_selection import train_test_split
|
||||
from sklearn.model_selection import StratifiedKFold
|
||||
from sklearn.pipeline import Pipeline, make_pipeline
|
||||
|
||||
from sklearn.pipeline import Pipeline
|
||||
from sklearn.pipeline import make_pipeline
|
||||
from sklearn.feature_selection import RFE, RFECV
|
||||
|
||||
from sklearn.feature_selection import RFE
|
||||
from sklearn.feature_selection import RFECV
|
||||
import itertools
|
||||
import seaborn as sns
|
||||
import matplotlib.pyplot as plt
|
||||
import numpy as np
|
||||
print(np.__version__)
|
||||
print(pd.__version__)
|
||||
|
||||
from statistics import mean, stdev, median, mode
|
||||
|
||||
from imblearn.over_sampling import RandomOverSampler
|
||||
from imblearn.under_sampling import RandomUnderSampler
|
||||
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 RepeatedStratifiedKFold
|
||||
from sklearn.ensemble import AdaBoostClassifier
|
||||
from imblearn.combine import SMOTEENN
|
||||
from imblearn.combine import SMOTETomek
|
||||
|
||||
from imblearn.over_sampling import SMOTENC
|
||||
from imblearn.under_sampling import EditedNearestNeighbours
|
||||
from imblearn.under_sampling import RepeatedEditedNearestNeighbours
|
||||
|
||||
from sklearn.discriminant_analysis import QuadraticDiscriminantAnalysis
|
||||
from sklearn.neural_network import MLPClassifier
|
||||
from sklearn.model_selection import GridSearchCV
|
||||
from sklearn.base import BaseEstimator
|
||||
from sklearn.impute import KNNImputer as KNN
|
||||
import json
|
||||
|
||||
from sklearn.linear_model import RidgeClassifier, SGDClassifier, PassiveAggressiveClassifier
|
||||
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
|
||||
from sklearn.svm import SVC
|
||||
from xgboost import XGBClassifier
|
||||
from sklearn.naive_bayes import MultinomialNB
|
||||
from sklearn.naive_bayes import GaussianNB
|
||||
|
||||
from sklearn.linear_model import SGDClassifier
|
||||
from sklearn.preprocessing import StandardScaler, MinMaxScaler, OneHotEncoder
|
||||
from sklearn.utils import all_estimators
|
||||
|
||||
from sklearn.linear_model import LogisticRegression, LogisticRegressionCV
|
||||
|
||||
#%%
|
||||
#%% GLOBALS
|
||||
rs = {'random_state': 42}
|
||||
njobs = {'n_jobs': 10}
|
||||
|
||||
scoring_fn = ({ 'mcc' : make_scorer(matthews_corrcoef)
|
||||
, 'fscore' : make_scorer(f1_score)
|
||||
, 'precision' : make_scorer(precision_score)
|
||||
, 'recall' : make_scorer(recall_score)
|
||||
, 'accuracy' : make_scorer(accuracy_score)
|
||||
, 'roc_auc' : make_scorer(roc_auc_score)
|
||||
, 'jaccard' : make_scorer(jaccard_score)
|
||||
})
|
||||
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)
|
||||
, 'jcc' : make_scorer(jaccard_score)
|
||||
})
|
||||
|
||||
skf_cv = StratifiedKFold(n_splits = 10
|
||||
#, shuffle = False, random_state= None)
|
||||
, shuffle = True,**rs)
|
||||
|
||||
rskf_cv = RepeatedStratifiedKFold(n_splits = 10
|
||||
, n_repeats = 3
|
||||
, **rs)
|
||||
|
||||
mcc_score_fn = {'mcc': make_scorer(matthews_corrcoef)}
|
||||
jacc_score_fn = {'jcc': make_scorer(jaccard_score)}
|
||||
#%%
|
||||
# Multiple Classification - Model Pipeline
|
||||
def MultModelsCl(input_df, target, skf_cv
|
||||
|
|
@ -111,9 +115,9 @@ def MultModelsCl(input_df, target, skf_cv
|
|||
|
||||
returns
|
||||
Dict containing multiple classification scores for each model and mean of each Stratified Kfold including training
|
||||
|
||||
'''
|
||||
# determine categorical and numerical features
|
||||
|
||||
# Determine categorical and numerical features
|
||||
numerical_ix = input_df.select_dtypes(include=['int64', 'float64']).columns
|
||||
numerical_ix
|
||||
categorical_ix = input_df.select_dtypes(include=['object', 'bool']).columns
|
||||
|
|
@ -133,7 +137,7 @@ def MultModelsCl(input_df, target, skf_cv
|
|||
col_transform = ColumnTransformer(transformers = t
|
||||
, remainder='passthrough')
|
||||
|
||||
#%% Specify multiple Classification models
|
||||
# Specify multiple Classification models
|
||||
lr = LogisticRegression(**rs)
|
||||
lrcv = LogisticRegressionCV(**rs)
|
||||
gnb = GaussianNB()
|
||||
|
|
|
|||
127
UQ_pnca_ML.py
127
UQ_pnca_ML.py
|
|
@ -16,11 +16,29 @@ import pprint as pp
|
|||
from copy import deepcopy
|
||||
from collections import Counter
|
||||
from sklearn.impute import KNNImputer as KNN
|
||||
from imblearn.over_sampling import RandomOverSampler
|
||||
from imblearn.under_sampling import RandomUnderSampler
|
||||
from imblearn.over_sampling import SMOTE
|
||||
from sklearn.datasets import make_classification
|
||||
from imblearn.combine import SMOTEENN
|
||||
from imblearn.combine import SMOTETomek
|
||||
|
||||
from imblearn.over_sampling import SMOTENC
|
||||
from imblearn.under_sampling import EditedNearestNeighbours
|
||||
from imblearn.under_sampling import RepeatedEditedNearestNeighbours
|
||||
|
||||
#%% REMOVE once config is set up
|
||||
from UQ_MultModelsCl import MultModelsCl
|
||||
|
||||
rs = {'random_state': 42}
|
||||
njobs = {'n_jobs': 10}
|
||||
|
||||
#%%
|
||||
homedir = os.path.expanduser("~")
|
||||
|
||||
#==============
|
||||
# directories
|
||||
#==============
|
||||
#==============a
|
||||
datadir = homedir + '/git/Data/'
|
||||
indir = datadir + drug + '/input/'
|
||||
outdir = datadir + drug + '/output/'
|
||||
|
|
@ -122,12 +140,12 @@ common_cols_stabiltyN = ['ligand_distance'
|
|||
, 'ddg_dynamut2']
|
||||
|
||||
foldX_cols = ['contacts'
|
||||
#, 'electro_rr', 'electro_mm', 'electro_sm', 'electro_ss'
|
||||
#, 'disulfide_rr', 'disulfide_mm', 'disulfide_sm', 'disulfide_ss'
|
||||
#, 'hbonds_rr', 'hbonds_mm', 'hbonds_sm', 'hbonds_ss'
|
||||
#, 'partcov_rr', 'partcov_mm', 'partcov_sm', 'partcov_ss'
|
||||
#, 'vdwclashes_rr', 'vdwclashes_mm', 'vdwclashes_sm', 'vdwclashes_ss'
|
||||
#, 'volumetric_rr', 'volumetric_mm', 'volumetric_ss'
|
||||
, 'electro_rr', 'electro_mm', 'electro_sm', 'electro_ss'
|
||||
, 'disulfide_rr', 'disulfide_mm', 'disulfide_sm', 'disulfide_ss'
|
||||
, 'hbonds_rr', 'hbonds_mm', 'hbonds_sm', 'hbonds_ss'
|
||||
, 'partcov_rr', 'partcov_mm', 'partcov_sm', 'partcov_ss'
|
||||
, 'vdwclashes_rr', 'vdwclashes_mm', 'vdwclashes_sm', 'vdwclashes_ss'
|
||||
, 'volumetric_rr', 'volumetric_mm', 'volumetric_ss'
|
||||
]
|
||||
|
||||
X_strFN = ['rsa'
|
||||
|
|
@ -196,7 +214,6 @@ all_df_wtgt = training_df[numerical_FN + categorical_FN + ['dst_mode']]
|
|||
all_df_wtgt.shape
|
||||
#%%================================================================
|
||||
#%% Apply ML
|
||||
#TODO: A
|
||||
|
||||
#%% Data
|
||||
#------
|
||||
|
|
@ -222,17 +239,89 @@ X_bts_wt = blind_test_df[numerical_FN + ['dst_mode']]
|
|||
|
||||
# Quick check
|
||||
(X['ligand_affinity_change']==0).sum() == (X['ligand_distance']>10).sum()
|
||||
#%% MultClassPipeSKFCV: function call()
|
||||
# mm_skf_scoresD = MultClassPipeSKFCV(input_df = X
|
||||
# , target = y
|
||||
# , var_type = 'numerical'
|
||||
# , skf_cv = skf_cv)
|
||||
##############################################################################
|
||||
print('Original Data\n', Counter(y)
|
||||
, 'Data dim:', X.shape)
|
||||
|
||||
###############################################################################
|
||||
#%%
|
||||
############################################################################
|
||||
# RESAMPLING
|
||||
###############################################################################
|
||||
#------------------------------
|
||||
# Simple Random oversampling
|
||||
# [Numerical + catgeorical]
|
||||
#------------------------------
|
||||
oversample = RandomOverSampler(sampling_strategy='minority')
|
||||
X_ros, y_ros = oversample.fit_resample(X, y)
|
||||
print('Simple Random OverSampling\n', Counter(y_ros))
|
||||
print(X_ros.shape)
|
||||
|
||||
# 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
|
||||
# print(mm_skf_scores_df_train)
|
||||
# print(mm_skf_scores_df_test)
|
||||
#------------------------------
|
||||
# Simple Random Undersampling
|
||||
# [Numerical + catgeorical]
|
||||
#------------------------------
|
||||
undersample = RandomUnderSampler(sampling_strategy='majority')
|
||||
X_rus, y_rus = undersample.fit_resample(X, y)
|
||||
print('Simple Random UnderSampling\n', Counter(y_rus))
|
||||
print(X_rus.shape)
|
||||
|
||||
#------------------------------
|
||||
# Simple combine ROS and RUS
|
||||
# [Numerical + catgeorical]
|
||||
#------------------------------
|
||||
oversample = RandomOverSampler(sampling_strategy='minority')
|
||||
X_ros, y_ros = oversample.fit_resample(X, y)
|
||||
undersample = RandomUnderSampler(sampling_strategy='majority')
|
||||
X_rouC, y_rouC = undersample.fit_resample(X_ros, y_ros)
|
||||
print('Simple Combined Over and UnderSampling\n', Counter(y_rouC))
|
||||
print(X_rouC.shape)
|
||||
|
||||
#------------------------------
|
||||
# SMOTE_NC: oversampling
|
||||
# [numerical + categorical]
|
||||
#https://stackoverflow.com/questions/47655813/oversampling-smote-for-binary-and-categorical-data-in-python
|
||||
#------------------------------
|
||||
# Determine categorical and numerical features
|
||||
numerical_ix = X.select_dtypes(include=['int64', 'float64']).columns
|
||||
numerical_ix
|
||||
num_featuresL = list(numerical_ix)
|
||||
numerical_colind = X.columns.get_indexer(list(numerical_ix) )
|
||||
numerical_colind
|
||||
|
||||
categorical_ix = X.select_dtypes(include=['object', 'bool']).columns
|
||||
categorical_ix
|
||||
categorical_colind = X.columns.get_indexer(list(categorical_ix))
|
||||
categorical_colind
|
||||
|
||||
k_sm = 5 # 5 is deafult
|
||||
sm_nc = SMOTENC(categorical_features=categorical_colind, k_neighbors = k_sm, **rs, **njobs)
|
||||
X_smnc, y_smnc = sm_nc.fit_resample(X, y)
|
||||
print('SMOTE_NC OverSampling\n', Counter(y_smnc))
|
||||
print(X_smnc.shape)
|
||||
|
||||
###############################################################################
|
||||
#%% SMOTE RESAMPLING for NUMERICAL ONLY*
|
||||
# #------------------------------
|
||||
# # SMOTE: Oversampling
|
||||
# # [Numerical ONLY]
|
||||
# #------------------------------
|
||||
# k_sm = 1
|
||||
# sm = SMOTE(sampling_strategy = 'auto', k_neighbors = k_sm, **rs)
|
||||
# X_sm, y_sm = sm.fit_resample(X, y)
|
||||
# print(X_sm.shape)
|
||||
# print('SMOTE OverSampling\n', Counter(y_sm))
|
||||
# y_sm_df = y_sm.to_frame()
|
||||
# y_sm_df.value_counts().plot(kind = 'bar')
|
||||
|
||||
# #------------------------------
|
||||
# # SMOTE: Over + Undersampling COMBINED
|
||||
# # [Numerical ONLY]
|
||||
# #-----------------------------
|
||||
# sm_enn = SMOTEENN(enn=EditedNearestNeighbours(sampling_strategy='all', **rs, **njobs ))
|
||||
# X_enn, y_enn = sm_enn.fit_resample(X, y)
|
||||
# print(X_enn.shape)
|
||||
# print('SMOTE Over+Under Sampling combined\n', Counter(y_enn))
|
||||
|
||||
###############################################################################
|
||||
# TODO: Find over and undersampling JUST for categorical data
|
||||
|
|
|
|||
|
|
@ -20,11 +20,9 @@ MyGlobalVars()
|
|||
os.chdir(homedir + "/git/ML_AI_training/")
|
||||
|
||||
# my function
|
||||
from UQ_MultClassPipe4 import MultClassPipeSKFCV
|
||||
from UQ_MultModelsCl import MultModelsCl
|
||||
from UQ_pnca_ML.py import *
|
||||
|
||||
#from scriptsfymcn import run_all_ML
|
||||
|
||||
|
||||
# YC_resD2 = run_all_ML(input_pd=X, target_label=y, blind_test_input_df=X_bts, blind_test_target=y_bts, preprocess = True, var_type = 'mixed')
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue