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
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
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue